ABSTRACT Modelling the evolution of Alzheimer's disease (AD) requires a thorough spatiotemporal study of longitudinal neuroimaging data. We propose in this paper a novel deep learning framework that uses a parallel combination of Recurrent Neural Networks (RNNs) and Vision Transformers (ViT) to extract temporal disease dynamics and spatial structural changes from serial MRI data. While the RNN evaluates sequential dependencies across timepoints, the ViT branch uses self‐attention to derive hierarchical brain‐region characteristics. A stacked auto‐encoder (SAE) fuses these features into a compact representation, enhancing discriminative power while reducing redundancy. Fully connected layers are given the fused features in order to predict progression and classify AD (CN/MCI/AD). We used the ADNI dataset to test our proposed methodology. In terms of disease stage differentiation, our approach reaches state‐of‐the‐art accuracy of 92.3%. Compared to CNN or RNN‐only models, it considerably improves the prediction of the early conversion of MCI to AD (AUC = 0.94). When processing heterogeneous neuroimaging data, the SAE‐based fusion outperforms attention methods. With potential uses in customised treatment planning, this hybrid approach provides a clinically interpretable tool for longitudinal AD.

ABSTRACT Smart healthcare systems are expected to grow exponentially in the 6G era, relying on their capacity to provide superior network services in terms of data rates and deployment scale. This generates vast amounts of health data that must be processed in real‐time. Therefore, computational offloading for smart healthcare systems is an inevitable trend and is widely applied in numerous medical applications, ranging from image diagnosis and clinical treatment to responding to viral pandemics. In this study, we provide a comprehensive overview of computational offloading for Health Internet of Things (HIoT) applications, examining various aspects. Then, we propose a deep reinforcement learning (DRL)‐based intelligent task offloading framework that performs decision‐making on local devices, accounts for real‐time resource constraints and provides detailed analyses. The results demonstrate that the DRL‐based offloading strategy outperformed Greedy and Threshold‐based methods by 20%, 10% and 45% in latency, energy consumption and failure rate, respectively. Finally, we identified challenges and open issues related to pervasive smart healthcare systems.

ABSTRACT The sixth‐generation communications networks (6G) are expected to be deployed in the 2030s with integrated space‐aerial‐ground and undersea architecture to provide seamless global connectivity. In this architecture, unmanned aerial vehicles (UAVs) are one of the most unique characteristics and are becoming increasingly important. The flexibility, high speed, and infrastructure independence of UAV systems make them ideal for many applications. However, these advantages also create great challenges in effective communication between UAVs. To address these challenges, reinforcement learning (RL) algorithms such as Q‐Learning have been investigated. However, the traditional Q‐learning algorithm mainly relies on delay parameters in the reward function for decision‐making route selection. Aiming to optimise the selection of sustainable and efficient communication for UAVs, we propose an improved routing algorithm based on Q‐Learning for UAV communication. Our method integrates latency, energy consumption, and link quality parameters into the reward function to make smarter routing decisions. The simulation results show that Q‐Proposed achieves significant gains in terms of packet delivery ratio and end‐to‐end delay compared to other methods, paving the way for sustainable 6G UAV communications.

The development of real-time applications integrated with Intent-Based Networking (IBN) integrates an Internet of Things (IoT), providing interconnection between heterogeneous devices and physical objects for the formulation of smart cities. These systems provide seamless communication and maintain the adaptive network policies and infrastructure. Many existing schemes have proposed solutions for efficient routing with support from intelligent architectures; however, although most of them overlook the bounded and limited resources of IoT networks, they impose additional overhead while addressing unpredictable communications in IBN-IoT. Furthermore, security and trustworthiness are significant research challenges that must be addressed to prevent data breaches and allow only the use of authentic devices. This research presents a scalable model for an IBN-IoT environment that utilizes edge computing to enable trustworthy and fault-tolerant communication with energy efficiency. Firstly, Software-Defined Networking (SDN) is explored for load balancing and effective resource allocation in 6G Internet of Things (IoT) systems. Secondly, the proposed model explores artificial intelligence techniques to analyze the network environment and predict anomalies in the fault tolerance approach. Lastly, data is kept private and maintained in integrity using a private blockchain, providing a more reliable, distributed, autonomous system with minimal overhead. Using synthetic data, the proposed model is validated against QGA-ACO and MER-ODLADT solutions for energy consumption, anomaly detection, and time-to-failure metrics across dynamic scenarios.

Human Activity Recognition (HAR) has emerged as a critical component in intent-aware, AI-driven Internet of Things (IoT) Communication systems, enabling context-aware responses in smart environments. Recently, WiFi-based HAR has gained significant attention due to its non-intrusive nature, low deployment cost, and ability to preserve privacy. However, they face a major challenge across domains. To address this limitation, we propose a novel cross-domain HAR framework (called TransHAR) by introducing a lightweight and efficient transformer model. On one hand, we design a feature representation block that processes the Wi-Fi channel frequency response (CFR) phase data to estimate Doppler shifts, capturing motion-related dynamics while remaining invariant to static, environment-specific structures, enhancing generalization across domains. On the other hand, we propose a lightweight Transformer architecture, termed ResDyTFormer, which minimizes reliance on normalization layers by incorporating a novel Residual Dynamic Tanh function. This function dynamically learns to balance between traditional normalization and the Dynamic Tanh operation, thereby maintaining training stability and avoiding gradient vanishing issues often encountered when using Dynamic Tanh alone. Extensive experiments on two benchmark datasets demonstrate that the proposed TransHAR framework achieves state-of-the-art performance in both in-domain and cross-domain HAR tasks with only 0.17M parameters. On the SHARP dataset, it attains an impressive 99.04% F1 score and 98.94% accuracy. On the 3DO dataset, it achieves 86.10% accuracy and 84.95% F1 score. These results highlight the potential of TransHAR as an efficient and scalable framework for real-world WiFi-based human activity sensing.

Human Activity Recognition (HAR) has become a cornerstone in the dynamic development of the Industrial Internet of Things (IIoT). This study introduces an extensive framework aimed at embedding HAR functionality into industrial settings to promote workplace safety, streamline operations, and facilitate predictive maintenance. Through AI techniques, HAR problems can be achieved with high accuracy. However, traditional AI models require centrally trained data on remotely powerful cloud servers. This leads to issues with privacy and security of health records and increases latency. To address this problem, the Federated Learning (FL) technique was proposed. FL allows distributed training on the patient’s IoT devices and serves as the communication mechanism between local devices and the FL aggregator. Thanks to this architecture, the health data needs only to be stored locally on its devices without being uploaded to data centers, thus ensuring security and reducing service response times and computational costs. In this study, we implement FedANN and FedConvNN independently in a federated learning setting to address human activity recognition problems toward real-time applications. Finally, we evaluate the effectiveness of the based on the variation initiation of the number of different training clients. The results show that the FedConvNN solution improves accuracy and reduces model and communication complexity compared to FedANN and centralized training models, with the potential for real-time deployment in HAR tasks. Our code is available on our GitHub repository: https://github.com/itsminhcs/Fedavg-HAR.git.

Responsible and Trustworthy AI is essential for accurate precipitation prediction, which impacts agriculture, transportation, and disaster prevention, where errors can lead to severe economic losses and casualties. In the 6G era, AI models must be reliable in addressing small sample biases and extreme weather data scarcity, while remaining lightweight for efficient real-time deployment and ultra-fast communication. Most deep learning-based methods struggle to capture the temporal evolution of spatial features effectively. The limitations include insufficient awareness of temporal trends and a lack of precise control over the spatial representation of temporal features. To address these issues, we propose a Lightweight Trend Perception Network (LTPNet) for precipitation prediction. It consists of an encoder, a decoder, and two stacked layers of Trend Perception (TP) units. Specifically, in the TP unit, the spatial matching module is proposed to extract the spatio-temporal dependency information of the history in the current situation. At the same time, a time channel fusion module is proposed to capture the spatial variation trend of precipitation. Experimental evaluation on the WeatherBench dataset demonstrates that LTPNet outperforms other state-of-the-art methods objectively and subjectively.

As next-generation communication networks increasingly rely on AI-driven automation, ensuring robust and secure intrusion detection becomes critical, especially under limited labeled data. In this context, we introduceMulti-Space Prototypical Learning(MSPL), a few-shot intrusion detection framework that improves prototype-based classification by fusing complementary metric-induced spaces (Euclidean, Cosine, Chebyshev, and Wasserstein) via a constrained weighting mechanism. MSPL further enhances stability through Polyak-averaged prototype generation and balanced episodic training to mitigate class imbalance across diverse attack categories. In a few-shot setting with as few as 200 training samples, MSPL consistently outperforms single-metric baselines across three benchmarks: on CICEVSE Network2024, AUPRC improves from 0.3719 to 0.7324 and F1 increases from 0.4194 to 0.8502; on CICIDS2017, AUPRC improves from 0.4319 to 0.4799; and on CICIoV2024, AUPRC improves from 0.5881 to 0.6144. These results demonstrate that multi-space metric fusion yields more discriminative and robust representations for detecting rare and emerging attacks in intelligent network environments.

ABSTRACT Consumer Internet of Things (CIoT) has revolutionised agriculture by integrating intelligent computing, artificial intelligence and big data technologies in crop monitoring. This paper explores the application of intelligent computing and deep learning methodologies in crop monitoring within the CIoT framework. In CIoT‐based crop monitoring, a vision sensor collects real‐time data from crop leaf images. The image dataset is processed using state‐of‐the‐art deep learning models and intelligent computing algorithms. This integration enables the early detection of crop diseases by leveraging computer vision and deep learning. Intelligent computing systems provide accurate disease classification, real‐time alerts, and actionable recommendations for optimised crop management practises. This advanced system empowers farmers to make data‐driven decisions, such as irrigation optimization, targeted pesticide application and nutrient supplementation, to maximise crop productivity and minimise losses. A benchmark dataset of leaf images is used, and a deep learning based model is presented for classifying healthy and diseased leaves. Experimental results demonstrate an accuracy rate of 0.98, with detailed validation, including dataset size and model parameters. Key benefits of intelligent computing in CIoT‐based crop monitoring include enhanced resource efficiency, reduced environmental impact, and improved sustainability. The paper also addresses the challenges of implementing AI and big data technologies, such as data privacy, security, interoperability and resource management in agricultural settings.

Abstract The rapid advancement of the Internet and digital payments has transformed the landscape of financial transactions, leading to both technological progress and an alarming rise in cybercrime. This study addresses the critical issue of financial fraud detection in the era of digital payments, focusing on enhancing operational risk frameworks to mitigate the increasing threats. The objective is to improve the predictive performance of fraud detection systems using machine learning techniques. The methodology involves a comprehensive data preprocessing and model creation process, including one‐hot encoding, feature selection, sampling, standardization, and tokenization. Six machine learning models are employed for fraud detection, and their hyperparameters are optimized. Evaluation metrics such as accuracy, precision, recall, and F 1‐score are used to assess model performance. Results reveal that XGBoost and Random Forest outperform other models, achieving a balance between false positives and false negatives. The study meets the requirements for fraud detection systems, ensuring accuracy, scalability, adaptability, and explainability. This paper provides valuable insights into the efficacy of machine learning models for financial fraud detection and emphasizes the importance of striking a balance between false positives and false negatives.

ABSTRACT Chatbots have become widely adopted tools for improving user interactions across multiple platforms. They are advanced software applications designed to emulate human conversation across various platforms. Moreover, developing chatbots using existing platforms and frameworks presents challenges, such as the lock‐in of NLP services, and incurs substantial costs. Recently, research has introduced solutions to ease chatbot development. Many of these approaches utilise Model‐Driven Engineering (MDE) and Domain‐Specific Languages (DSLs) to automate processes and simplify implementation. Through the use of MDE and DSLs, these solutions enhance efficiency and make chatbot creation more accessible. This study aims to provide a comprehensive survey on MDE and DSLs in chatbot development, highlighting key research topics, opportunities, and challenges. The first contribution explores the primary application domains of DSLs in chatbot development and the associated challenges in their adoption. Second, this work examines the various ways in which DSLs are employed to model and develop chatbots, assessing their impact on automation and efficiency. Additionally, this study identifies the challenges and limitations of using DSLs in chatbot development. Atlast, it investigates the influence of DSL utilisation on user experience, both from the perspective of chatbot developers and end‐users, to determine how DSLs enhance the chatbot development process and interaction quality. To achieve this, a comprehensive search will be conducted across Scopus, Web of Science, and ScienceDirect for studies published between 2014 and 2024. A total of 306 publications were reviewed, of which 15 were identified as primary studies.

Abstract Conversational assistants (CAs) and Task‐oriented ones, in particular, are designed to interact with users in a natural language manner, assisting them in completing specific tasks or providing relevant information. These systems employ advanced natural language understanding (NLU) and dialogue management techniques to comprehend user inputs, infer their intentions, and generate appropriate responses or actions. Over time, the CAs have gradually diversified to today touch various fields such as e‐commerce, healthcare, tourism, fashion, travel, and many other sectors. NLU is fundamental in the natural language processing (NLP) field. Identifying user intents from natural language utterances is a sub‐task of NLU that is crucial for conversational systems. The diversity in user utterances makes intent detection (ID) even a challenging problem. Recently, with the emergence of Deep Neural Networks. New State of the Art (SOA) results have been achieved for different NLP tasks. Recurrent neural networks (RNNs) and Transformer architectures are two major players in those improvements. RNNs have significantly contributed to sequence modelling across various application areas. Conversely, Transformer models represent a newer architecture leveraging attention mechanisms, extensive training data sets, and computational power. This review paper begins with a detailed exploration of RNN and Transformer models. Subsequently, it conducts a comparative analysis of their performance in intent recognition for Task‐oriented (CAs). Finally, it concludes by addressing the main challenges and outlining future research directions.

Abstract Alzheimer's disease (AD) is a major global health concern that affects millions of people globally. This study investigates the technical challenges in AD analysis and provides a thorough analysis of AD, emphasizing the disease's worldwide effects as well as the predicted increase. It explores the technological difficulties associated with AD analysis, concentrating on the shift in automated clinical diagnosis using MRI data from conventional machine learning to deep learning techniques. This study advances our knowledge of the effects of AD and provides new developments in deep learning for precise diagnosis, providing insightful information for both clinical and future research. The research introduces an innovative deep learning model, leveraging YOLOv5 and variants of YOLOv8, to classify AD images into four (NC, EMCI, LMCI, AD) categories. This study evaluates the performance of YOLOv5 which achieved high accuracy (97%) in multi‐class classification (classes 0 to 3) with precision, recall, and F1‐score reported for each class. YOLOv8 (Small) and YOLOv8 (Medium) models are also assessed for Alzheimer's disease diagnosis, demonstrating accuracy of 97% and 98%, respectively. Precision, recall, and F1‐score metrics provide detailed insights into the models' effectiveness across different classes. Comparative analysis against a transfer learning model reveals YOLOv5, YOLOv8 (Small), and YOLOv8 (Medium) consistently outperforming across six binary classifications related to cognitive impairment. These models show improved sensitivity and accuracy compared to baseline architectures from [32]. In AD/NC classification, YOLOv8 (Medium) achieves 98.43% accuracy and 97.45% sensitivity, for EMCI/LMCI classification, YOLOv8 (Medium) also excels with 92.12% accuracy and 90.12% sensitivity. The results highlight the effectiveness of YOLOv5 and YOLOv8 variants in neuroimaging tasks, showcasing their potential in clinical applications for cognitive impairment classification. The proposed models showcase superior performance, achieving high accuracy, sensitivity, and F1‐scores, surpassing baseline architectures and previous methods. Comparative analyses highlight the robustness and effectiveness of the proposed models in AD classification tasks, providing valuable insights for future research and clinical applications.

ABSTRACT No‐reference image quality assessment (NR‐IQA) has garnered significant attention due to its critical role in various image processing applications. This survey provides a comprehensive and systematic review of NR‐IQA methods, datasets, and challenges, offering new perspectives and insights for the field. Specifically, we propose a novel taxonomy for NR‐IQA methods based on distortion scenarios and design principles, which distinguishes this work from previous surveys. Representative methods within each category are thoroughly examined, with a focus on their strengths, limitations, and performance characteristics. Additionally, we review 20 widely used NR‐IQA datasets that serve as benchmarks for evaluating these methods, providing detailed information on the number of images, distortion types, and distortion levels for each dataset. Furthermore, we identify and discuss key challenges currently faced by NR‐IQA methods, such as handling diverse and complex distortions, ensuring generalisation across datasets and devices, and achieving real‐time performance. We also suggest potential future research directions to address these issues. In summary, this survey offers a comprehensive and systematic examination of NR‐IQA methods, datasets, and challenges, offering valuable insights and guidance for researchers and practitioners working in the NR‐IQA domain.

ABSTRACT Many mobile devices—including digital cameras, smartphones, and personal digital assistants (PDAs)—rely on single image sensors to capture scenes for real‐time processing. Convolutional neural networks (CNNs) have shown outstanding performance in various image processing tasks. In this paper, we propose a novel demosaicking method based on a transformer and long‐range attention network (TLAN). The approach begins by initializing the mosaicked image using a bicubic interpolation algorithm, which provides a coarse reconstruction. TLAN is then applied to refine the output and accurately reconstruct the three colour channels. Our TLAN architecture combines the Swin Transformer (ST) with a dedicated long‐range attention (LA) mechanism. The overall framework consists of both shallow and deep feature extraction modules. The deep extraction module is built from multiple residual swin transformer blocks (RSTBs), each composed of several Swin Transformer layers and augmented with a long‐range attention block (LAB) to capture extended spatial dependencies. Experimental results demonstrate that the proposed method achieves superior performance in both PSNR and visual quality compared to existing demosaicking techniques.

ABSTRACT The widespread use of Internet has accelerated the explosive growth of data, which in turn leads to information overload and information confusion. This makes it difficult for us to communicate effectively in social groups, thereby intensifying the demands for emotional companionship. Therefore, we propose a novel social group chatting framework based on Large Language Model (LLM) powered multiple autonomous agents collaboration in this article. Specifically, BERTopic is used to extract topics from history chatting content for each social group everyday, and then multiple topics tracking is realised through multi‐level association by adaptive time sliding‐window mechanism and optimal matching. Furthermore, we use topic tracking architecture and prompts to design and implement an AI Chatbot system with different characters that can conduct natural language conversations with users in online social group. LLM, as the controller and coordinator of the whole AI Chatbot for sub‐tasks, allows different AI Agents to autonomously decide whether to participate in current topic, how to generate response, and whether to propose a new topic. Each AI Agent has their own multi‐store memory system based on the Atkinson‐Shiffrin model. Finally, we construct a verification environment based on online game that is consistent with real society. Subjective and objective evaluation methods were deployed to perform qualitative and quantitative analyses to demonstrate the performance of our AI Chatbot system.

Abstract In the global monitoring of smart cities, the demands of global object detection systems based on cloud and fog computing in intelligent systems can be satisfied by photographs with globally recognized properties. Nevertheless, conventional techniques are constrained by the imaging depth of field and can produce artefacts or indistinct borders, which can be disastrous for accurately detecting the object. In light of this, this paper proposes an artificial intelligence‐based gradient learning network that gathers and enhances domain information at different sizes in order to produce globally focused fusion results. Gradient features, which provide a lot of boundary information, can eliminate the problem of border artefacts and blur in multi‐focus fusion. The multiple‐receptive module (MRM) facilitates effective information sharing and enables the capture of object properties at different scales. In addition, with the assistance of the global enhancement module (GEM), the network can effectively combine the scale features and gradient data from various receptive fields and reinforce the features to provide precise decision maps. Numerous experiments have demonstrated that our approach outperforms the seven most sophisticated algorithms currently in use.

Autonomous driving has been significantly advanced in today’s society, which revolutionized daily routines and facilitated the development of the Internet of Vehicles (IoV). A crucial aspect of this system is understanding traffic density to enable intelligent traffic management. With the rapid improvement in deep neural networks (DNNs), the accuracy of density estimation has markedly improved. However, there are two main issues that remain unsolved. First, current DNN-based models are excessively heavy, characterized by an overwhelming number of training parameters (millions or even billions) and substantial computational complexity, indicated by a high number of FLOPs. These requirements for storage and computation severely limit the practical application of these models, especially on edge devices with limited capacity and computational power. Second, despite the superior performance of DNN models, their effectiveness largely depends on the availability of large-scale data for training. Growing privacy concerns have made individuals increasingly hesitant to allow their data to be publicly used for model training, particularly in vehicle-related applications that might reveal personal movements, which leads to data isolation issues. In this article, we address these two problems at once with a systematic framework. Specifically, we introduce the proxy model distributed learning (PMDL) model for traffic density estimation. PMDL model is composed of two main components. First, we introduce a proxy model learning strategy that transfers fine-grained knowledge from a larger master model to a lightweight proxy model, i.e., a proxy model. Second, we design a distributed learning strategy that trains multiple proxy models with privacy-aware local data and seamlessly aggregates these models via a global parameter server. This ensures privacy protection while significantly improving estimation performance compared to training models with limited, isolated data. We tested the proposed model on four major vehicle density analysis benchmarks and demonstrated its efficiency by outperforming other state-of-the-art competitors. The code is available athttps://github.com/jinyongch/DPML.

The objective of cross-camera persson association is to identify individuals captured across disjoint cameras. It is achieved by Re-Identification (ReID) models, which extract unique identity representations from the visual input, dominated by video sequence. Most ReID methods primarily focus on modifying the backbone network architecture to learn more representative features of people. However, these methods often overlook the impact of low-quality frames on the training process. Several studies have confirmed that low-quality data not only hinders the model from learning meaningful content but also diminishes its performance. One possible solution is to manually label the quality of each frames, but this is time-consuming and inefficient. In this paper, we propose a Unsupervised Frame Clustering and Selection framework called UFCS to address this problem by applying the unsupervised clustering to automatically select high-quality frames. Specifically, we applied three unsupervised clustering solutions for high-quality frame selection, namely K-means, Deep K-means, and DBSCAN. These clustering techniques integrate both appearance and, indirectly, temporal consistency by operating within tracklets. These schemes perform clustering in the image or deep feature space to select highquality frames for network training. This straightforward yet effective approach enables the ReID network to generate a more discriminative representations, thereby improving recognition performance. Experimental results obtained on the challenging video-based person ReID datasets MARS indicate that our proposed scheme can outperform related state-of-the-art methods by a large margin.

In the Industrial Internet of Things (IIoT) environment, the integration of the Internet of Things (IoT) and Artificial Intelligence (AI) facilitates various applications. Sensors deployed in critical areas continuously collect diverse data, including real-time air quality monitoring, to provide accurate environmental insights. However, these systems are susceptible to adversarial examples (AEs), including physical AEs. These attacks can compromise the accuracy of predictions and lead to misinterpretation of carbon emission levels. For instance, malicious factory owners could exploit AEs to evade carbon emission inspections. To address this challenge, this study introduces a method that utilizes Poisson distribution-based statistical modeling to detect AEs by analyzing distinct neuron activation patterns. Furthermore, to address the complexity and variability of air quality data, we introduce a vector projection technique to enhance the alignment of probability vectors with the model’s actual output feature space. Experimental results demonstrate the effectiveness of this method in detecting attacks generated by FGSM, PGD, DeepFool, and C&W, achieving F1-scores of 0.993, 0.992, 0.972, and 0.961, respectively. This enhances the reliability and energy efficiency of IoT-based air quality monitoring systems within carbon-intelligent IIoT framework.

An informative 3-D avatar, closely mirroring real-world traits, plays a pivotal role in accessing the metaverse. Traditional methods for creating 3-D avatars usually employ one-to-one training, which restricts avatar diversity. To enhance style diversity in generated 3-D avatars, we utilize synthesized images derived with prompts from ChatGPT in a conversational manner, ultimately resulting in a broader range of 3-D variations. Rather than creating models from scratch, we devise a training-free framework that utilizes established large-scale foundation models. Specifically, we employ a real-world image synthesis technique guided by text prompts that are generated by ChatGPT in a conversational manner, to describe the desired characteristics of the synthesized image. As a result, these informative latent representations can accurately reflect the distinct style of the synthesized image, and further lead to the creation of photorealistic and diverse 3D avatars. Our training-free design allows this proposed method to achieve competitive performance compared to existing generation models, while requiring minimal computational resources.

The rapid advancement of deepfake technology has threatened the community’s sense of security, particularly in the context of face-based payment systems. Thus, deepfake detection has emerged as a critical issue demanding immediate attention. However, the generalization performance of existing detection models is limited as they are overly reliant on specific forged features while ignoring the common forged features. To address this problem, we introduce the context-aware decoupling network (CADNet) for deepfake detection. Specifically, a context self-calibration (CSC) module is constructed to guide the network to focus on local forged regions. It enlarges possible regions to increase the likelihood of forgery cues. Meanwhile, a frequency domain decoupling (FDD) module is introduced to extract and fuse different frequency components. It realizes the collaborative representation optimization of global semantics and local details. The experimental results prove that the proposed model exhibits strong generalization capability across multiple standard datasets. It achieves average area under the curve (AUC) values of 98.64% for in-domain evaluation and 75.52% for cross-dataset generalization.

The widespread misinformation generated by deepfake systems has emerged as a significant challenge in the dynamic realm of digital media. It poses threats to credibility, privacy, and security of information in daily life. Moreover, the increasing accessibility to facial editing tools further enables users to alter facial characteristics subtly through a series of intricate steps. To address the issue, we introduce a space–frequency and global–local attentive network (SFGLA-Net) for sequential deepfake detection. This method is designed to identify and analyze the sophisticated manipulated attributes of deepfake images. Specifically, we introduce a space–frequency fusion module to leverage the deep feature extracted in spatial and frequency domains, so as to exploit subtle inconsistencies and artifacts that are not perceptible in the spatial domain alone. Additionally, we design a global–local attention module to pinpoint the manipulated areas more accurately. Extensive experiments demonstrate the superior performance of the proposed method by significantly outperforming existing techniques in sequential deepfake detection. The code is available athttps://github.com/guishengzhanga/SFGLA.

Social fintech envelopes social networks within financial concepts and tokenization, and its complexity requires innovative technological solutions and theories to meet user demands and achieve sustainability. The first thing is the mapping principle between physical real society and virtual digital world. Therefore, this article uses online gameNova Empireas a case study, aiming at using multiplex networks to understand the physical–digital structural consistency for social fintech sustainable development. Specifically, we first proposed an eight-layer multiplex network to model the complex gaming behaviors for players. Furthermore, we analyze the structural properties and social balance of the social networks. Particularly, the layers in multiplex networks composed of positive behaviors has higher reciprocity than the layers composed of negative behaviors, the out-degree distributions of nodes in the layers composed of negative behaviors basically conform to the power-law distribution, and the small-world phenomenon is also common in virtual game. The experimental results prove the structural consistency between physical and digital. Finally, new solutions for social fintech and mobile Internet industry are proposed based on the mapping principle, which will provide technical supports for the realization of sustainable development and social responsibility of social fintech.

Vehicle association is a vital yet complex task to retrieve specific vehicles across various camera angles, time frames, and geographical locations. In environments supported by autonomous driving and 6G networks, this task plays a vital role in urban surveillance and traffic management by enabling the real-time sharing of vehicle location and status information through ultra-high-speed, low-latency 6G communication. The success of a retrieval model largely depends on the quality of the extracted representations, which can be influenced by factors such as background diversity and occlusions. This study proposes a method to extract representations that remain consistent across different domains while retaining the discriminative power necessary to determine a vehicle’s spatial location, regardless of background or environmental variations. To achieve this, we introduce a framework called Generic Representation Learning (GRL). Within GRL, we leverage large-scale pre-trained foundational models to provide spatial priors of vehicles, specifically the Grounding DINO model for object detection and the SAM model for object segmentation. These modules collaborate to help the network understand the spatial context of the object, enabling the feature extractor to focus on discriminative areas while minimizing interference. Additionally, we introduce a complementary feature alignment mechanism based on a memory bank to explore globally applicable knowledge within the learned representation of the object. These constituent elements collectively form SRP, to enhance its capability for outstanding performance in vehicle retrieval. Extensive experimentation demonstrates that SRP significantly outperforms existing models on widely recognized benchmarks.

In the absence of sufficient labels, deep neural networks (DNNs) are prone to overfitting, resulting in poor performance and difficulty in training. Thus, many semisupervised methods aim to use unlabeled sample information to compensate for the lack of label quantity. However, as the available pseudolabels increase, the fixed structure of traditional models has difficulty in matching them, limiting their effectiveness. Therefore, a deep-growing neural network with manifold constraints (DGNN-MC) is proposed. It can deepen the corresponding network structure with the expansion of a high-quality pseudolabel pool and preserve the local structure between the original and high-dimensional data in semisupervised learning. First, the framework filters the output of the shallow network to obtain pseudolabeled samples with high confidence and adds them to the original training set to form a new pseudolabeled training set. Second, according to the size of the new training set, it increases the depth of the layers to obtain a deeper network and conducts the training. Finally, it obtains new pseudolabeled samples and deepens the layers again until the network growth is completed. The growing model proposed in this article can be applied to other multilayer networks, as their depth can be transformed. Taking HSI classification as an example, a natural semisupervised problem, the experimental results demonstrate the superiority and effectiveness of our method, which can mine more reliable information for better utilization and fully balance the growing amount of labeled data and network learning ability.

In recent years, the exponential increase in mobile and Internet of Things (IoT) data traffic has placed substantial demands on infrastructure for Internet Service Providers (ISPs). To meet these demands sustainably, it is critical to enhance energy efficiency, resource utilization, and cost-effectiveness while reducing the carbon footprint. Simply adding hardware is not a viable solution. This study introduces an innovative approach to 3D cellular deployment in sustainable B5G/6G networks, designed to optimize Quality of Service (QoS) for users and IoT devices. Although 5G/B5G utilizes millimeter waves for high data rate transmission, their limited coverage and susceptibility to interference from buildings pose unique deployment challenges. To address these, we formulate the 3D cellular deployment problem as a Multi-Objective Optimization (MOO) problem and propose an advanced deployment strategy using VA-NSGA-II, a metaheuristic-based algorithm. By factoring in building interference, Received Signal Strength Indicator (RSSI), coverage, deployment cost, and a balance between performance and sustainability, VA-NSGA-II provides an optimal deployment solution. Simulation results demonstrate that VA-NSGA-II achieves effective deployment performance across various building materials, highlighting its adaptability and effectiveness in different environmental scenarios.

This study explores the effectiveness of Convolutional Neural Networks (CNNs) in automatically classifying skin cancer for e-health applications. The trained model showcases impressive performance by leveraging the HAM10000 dataset, which includes a wide range of skin lesion images from seven different classes. The parameters and architecture of the CNN model are presented in a systematic manner, providing valuable insights into the reasoning behind its design. The model is optimized using the Adam optimizer and annealing techniques to ensure efficient convergence. The model’s performance is assessed on validation and test datasets, showcasing an accuracy of 78.55% and 76.49%, respectively, for skin cancer classification. This study highlights the significant potential of CNN as a powerful tool for automating the diagnosis of skin cancer, which is in line with the growing trend of using deep learning for medical image analysis.

The rapid advancement of deepfake technology has enabled the creation of highly realistic forged face images or videos. While deepfake technology adds entertainment to people’s lives, it also poses a potential threat to social security. Deepfake detection is a crucial technology for identifying forged images. However, existing deep learning-based models for deepfake detection often overlook subtle forged traces. To solve this problem, we propose a Progressive Attention Network (PANet). The PANet incorporates two attention modules, namely the Efficient Multi-Scale Attention Module (EMAM) and the Spatial and Channel Attention Module (SCAM), in a progressive manner. The EMAM focuses on crucial facial regions, such as the eyes, nose, and mouth, rather than the entire face. The SCAM facilitates fine-grained feature extraction. Experimental results demonstrate that the proposed method achieves state-of-the-art results on deepfake detection datasets.

Imagined speech production with electrocorticography (ECoG) plays a crucial role in brain-computer interface system. A challenging issue is the great variation underlying the frequency bands of the ECoG signals’ encode information, which makes current methods difficult to generate imagined speech with stable quality among different persons. To this end, we propose a robust model to generate high-quality imagined speech from ECoG. A frequency enhancement branch is first designed to adaptively modulate the frequency information, whose product is fed into the following multi-scale channel attention module for robust feature extraction and fusion. By incorporating both the mel-spectrum and audio as training constraints, a multi-constraint decoder branch is finally constructed for imagined speech production. The performance of our model is evaluated on a high-quality dateset, i.e, Single Word Production Dutch-iBIDS. It yields Pearson correlation scores that are all above 0.8, and the standard deviationsare are all below 0.2 in different volunteers. Experimental results demonstrate that our model is effective and robust for ECoG based imagined speech production, and has advantages over peer methods.

Skin cancer diagnosis, a critical task in the medical domain, can be revolutionized through the application of advanced deep-learning techniques. This work investigates the efficacy of Convolutional Neural Networks (CNNs) in the automated classification of skin cancer. The process begins with a comprehensive explanation of key CNN layers: Conv2D, MaxPool2D, Dropout, and Dense. The Conv2D layers employ learnable filters that transform localized image segments, while MaxPool2D contributes to downsampling, effectively reducing computational cost and overfitting risk. Integrating these layers enables the network to capture local and global characteristics, which is crucial for accurate classification. Adding Dropout layers enhances generalization and mitigates overfitting by introducing randomness during training. ReLU activation functions infuse non-linearity, and the Flatten layer facilitates the transition to fully connected layers. The proposed CNN architecture is meticulously designed considering filter counts, kernel sizes, and pooling dimensions. The trained model demonstrates promising performance by utilizing the HAM10000 dataset, encompassing diverse skin lesion images across seven classes. The CNN model’s parameters and architecture are systematically presented, offering insights into its design rationale. The model undergoes optimization with the Adam optimizer and annealing techniques to facilitate convergence. The model’s effectiveness is evaluated on validation and test datasets, demonstrating an accuracy of 78.55% and 76.49%, respectively, for skin cancer classification. Data augmentation strategies are introduced to enhance model generalization further. The results underscore CNN’s potential as a robust tool for automating skin cancer diagnosis, aligning with the broader trend of leveraging deep learning for medical image analysis

The utilization of Artificial intelligence (AI) and other cutting-edge techniques in the field of medical image analysis has exhibited significant potential. Nevertheless, a significant obstacle that impedes the extensive implementation of these models in the healthcare sector is their restricted interpretability. The concept of explainability is a subject of extensive discussion and debate within the context of utilizing Artificial intelligence in the healthcare domain. Notwithstanding the empirical evidence demonstrating the superior performance of AI-driven systems compared to humans in certain analytical tasks, particularly in the field of medical image computing, these systems still encounter challenges due to their limited explainability. The present study provides a comprehensive assessment of the significance of explainability in the field of medical Artificial intelligence and performs an ethical analysis of the influence of explainability on the incorporation of AI-driven tools in data engineering in medicine and health care. The paper examines various subjects including data security, confidentiality, privacy, fairness, and discrimination, among others.

Abstract Image fusion plays a significant role in computer vision since numerous applications benefit from the fusion results. The existing image fusion methods are incapable of perceiving the most discriminative regions under varying illumination circumstances and thus fail to emphasize the salient targets and ignore the abundant texture details of the infrared and visible images. To address this problem, a multiscale aggregation and illumination‐aware attention network (MAIANet) is proposed for infrared and visible image fusion. Specifically, the MAIANet consists of four modules, namely multiscale feature extraction module, lightweight channel attention module, image reconstruction module, and illumination‐aware module. The multiscale feature extraction module attempts to extract multiscale features in the images. The role of the lightweight channel attention module is to assign different weights to each channel so as to focus on the essential regions in the infrared and visible images. An illumination‐aware module is employed to assess the probability distribution regarding the illumination factor. Meanwhile, an illumination perception loss is formulated by the illumination probabilities to enable the proposed MAIANet to better adjust to the changes in illumination. Experimental results on three datasets, that is, MSRS, TNO, and RoadSence, verify the effectiveness of the MAIANet in both qualitative and quantitative evaluations.

Abstract The Internet of Health Things (IoHT) has grown in importance for developing medical applications with the support of wireless communication systems. IoHT is integrated with many sensors to capture the patients' records and transmits them to hospital centres for analysis and reporting. Controlling and managing health records has been addressed in several ways, however, it is noted that two key research problems for vital communication systems are reliability and reducing data loss. To enhance the sustainability of health applications and effectively use the network infrastructure when transferring sensitive data, this research provides a machine learning approach. Moreover, data collected from the IoHTs are protected and can be securely received for physical process in hospitals using authentication trees. Firstly, the undirected graphs are explored based on the multi‐parametric machine learning approach to minimize the computation overheads and traffic congestion. Secondly, it evaluates the nodes' level behaviour over the heterogeneous traffic load with efficient identification of redundant links. Finally, in‐depth analysis and simulation results have shown that the proposed protocol is more effective than existing approaches for data accuracy and security analysis.

Abstract Heart sound signal analysis is very important for the early identification and treatment of cardiovascular illness. With rapid advancements in science and technology, artificial intelligence technologies are providing tremendous opportunities to enhance diagnosis and clinical decision‐making. Instruments can now perform clinical diagnoses that previously could only be handled by human experts more conveniently and efficiently. Despite multiple works on automatic heart sound analysis, there are few summarization and review works. This article attempts to give a thorough overview of various heart sound analysis subtasks and examine the improvements made in each subtask by both machine learning techniques and deep learning algorithms. It goals to highlight the potential of AI to revolutionize cardiovascular healthcare by enabling accurate and automated analysis of heart sounds. The findings of this review are beneficial for researchers, clinicians, and engineers in the development and application of AI‐based solutions for improved heart sound classification and diagnosis.

A pipeline of constant data streams is being built by the Internet of Things (IoT) to monitor information about the physical environment. In parallel, Artificial Intelligence (AI) is constantly developing and enhancing industrial, economic, and academic endeavors as well as quality of life thanks to these IoT data. In streaming contexts, Kafka-ML is our open-source framework that enables the management of Machine Learning (ML) and AI pipelines over data streams. Accordingly, it simplifies the deployment of Deep Neural Networks (DNNs) in practical applications. Nonetheless, this framework did not support the possibility of carrying out an Online Learning (OL) process, which is needed when new data are continuously arriving, and the models need to adapt to them on the fly. In this work, we have extended our previous work, the Kafka-ML framework, to enhance the management of ML/AI pipelines with OL features to enable both ML/AI distributed and centralized models to learn indefinitely over time. These models are continuously upgraded thanks to a process where automatic and flexible inference is carried out when improvements in the model performance are achieved. This opens up a large number of new possibilities within different fields of application, development, and work under the premise of incremental learning with ML models such as Electrical Vehicles and Industry 5.0. We have validated these new features by adapting and deploying state-of-the-art DNN models in different online scenarios, for both single and distributed configurations. The results show the capability of Kafka-ML to execute effective online training processes for ML models, improving their performance over time as new data becomes available.

Integrating Internet of Things (IoT) and artificial intelligence (AI) techniques have found widespread application in various fields, including smart cities, agriculture, and environmental monitoring. With the increasing availability of satellite imagery and other remote sensing data, deep learning algorithms can be used and trained to detect, classify, and segment flood regions in real time. In addition, deep learning techniques, such as convolutional neural networks (CNNs), have been successful in this field, enabling the automated analysis of vast amounts of satellite imagery. By combining AI-based flood detection with other data sources, such as meteorological forecasts and ground-based sensors, comprehensive flood monitoring systems that provide early warning of flood events and facilitate effective emergency response can be developed. In this article, we developed an image-based flood segmentation system called DeepLab that uses a deep learning algorithm to detect and segment the presence and extent of floods with high accuracy and speed. The neural network was trained on an extensive collection of satellite images, which were complemented by ground truth labels that indicated the presence of flooded areas. The trained DeepLabv3 model is applied to new satellite images during inference to forecast the likelihood of each pixel belonging to a flooded area. To do this, a binary flood map was generated from the pixel-level forecasts by incorporating a threshold into the output probabilities. The proposed system’s accuracy was high compared to the state-of-the-art methods, as evidenced by segmentation and experimental results. The segmentation accuracy achieved an overall score of 87%.

Benefiting from the progresses of sensing and sustainable computing technologies, recent years have witnessed the dramatic progresses of artificial intelligence of things (AIoT). As a typical AIoT application, WiFi-based human activity recognition has increasing popularities in smart homes. However, WiFibased action recognition often has unstable performance due to environmental interference. To this end, a robust deep learning framework called MSF-Net is proposed for coarse and fine activity recognition using channel state information (CSI) information. First, a dual-stream structure incorporating short-time Fourier transform and discrete wavelet transform is developed to highlight abnormal information in the CSI data. Then, a Transformer is employed as the backbone to effectively extract high-level features. In addition, an attention-based fusion branch is designed to enhance cross-model fusion. Experimental results show that MSF-Net achieves Cohens Kappa scores of 91.82%, 69.76%, 85.91%, and 75.66% on the SignFi, Widar3.0, UT-HAR, and NTU-HAR datasets, respectively. These performance records demonstrate the advantages of MSF-Net over existing methods for coarse and fine activity recognition based on WiFi data.

Abstract The integration of remote sensing object counting in the Mobile Edge Computing (MEC) environment is of crucial significance and practical value. However, the presence of significant background interference in remote sensing images poses a challenge to accurate object counting, as the results are easily affected by background noise. Additionally, scale variation within remote sensing images presents a further difficulty, as traditional counting methods face challenges in adapting to objects of different scales. To address these challenges, we propose a selective spatial‐frequency pyramid network (SSFPNet). Specifically, the SSFPNet consists of two core modules, namely the pyramid attention (PA) module and the hybrid feature pyramid (HFP) module. The PA module accurately extracts target regions and eliminates background interference by operating on four parallel branches. This enables more precise object counting. The HFP module is introduced to fuse spatial and frequency domain information, leveraging scale information from different domains for object counting, so as to improve the accuracy and robustness of counting. Experimental results on RSOC, CARPK, and PUCPR+ benchmark datasets demonstrate that the SSFPNet achieves state‐of‐the‐art performance in terms of accuracy and robustness.

Millions of individuals around the world have been impacted by the ongoing coronavirus outbreak, known as the COVID-19 pandemic. Blockchain, Artificial Intelligence (AI), and other cutting-edge digital and innovative technologies have all offered promising solutions in such situations. AI provides advanced and innovative techniques for classifying and detecting symptoms caused by the coronavirus. Additionally, Blockchain may be utilized in healthcare in a variety of ways thanks to its highly open, secure standards, which permit a significant drop in healthcare costs and opens up new ways for patients to access medical services. Likewise, these techniques and solutions facilitate medical experts in the early diagnosis of diseases and later in treatments and sustaining pharmaceutical manufacturing. Therefore, in this work, a smart blockchain and AI-enabled system is presented for the healthcare sector that helps to combat the coronavirus pandemic. To further incorporate Blockchain technology, a new deep learning-based architecture is designed to identify the virus in radiological images. As a result, the developed system may offer reliable data-gathering platforms and promising security solutions, guaranteeing the high quality of COVID-19 data analytics. We created a multi-layer sequential deep learning architecture using a benchmark data set. In order to make the suggested deep learning architecture for the analysis of radiological images more understandable and interpretable, we also implemented the Gradient-weighted Class Activation Mapping (Grad-CAM) based colour visualization approach to all of the tests. As a result, the architecture achieves a classification accuracy rate of 0.96, thus producing excellent results.

Current human being's lifestyle has caused / exacerbated many diseases. One of these diseases is cancer, and among all kinds of cancers like, brain pulmonary; lung cancer is fatal. The cancers could be detected early to save lives using Computer Aided Diagnosis (CAD) systems. CT scans medical images are one the best images in detecting these tumors in lungs that are especially accepted among doctors. However, the location, random shape of tumors, and poor quality of CT scan images are among the main challenges for physicians in identifying these tumors. Therefore, deep learning algorithms have been highly regarded by researchers. This paper proposed a new model for tumors and nodules segmentation in CT scans images based on convolution neural network (CNN) algorithm. The proposed model comprises preprocessing and postprocessing for fine segmentation of nodules. Filtering is used for image enhancement in preprocessing, and morphological operators are used for fine segmentation in post-processing. Finally, the active counter algorithm implementation exhibited tumors and nodules detection precisely. The sensitivity assessment and dice similarity criteria qualitatively measure the proposed model efficiency on the benchmark dataset. The obtained results with 98.33% accuracy 99.25% validity,98.18% dice similarity criterion show superiority of the proposed model.

In the recent era, the communication network with the support of many wireless technologies is giving benefits for remote access. Such a communication model increases the flexibility for data storage with the management of network resources efficiently with the integration of the Internet of Things (IoT). Although, the industrial Internet of Things (IIoT) has enabled the development of numerous machine learning-based solutions to provide real-time applications. However, most of the solutions are not prepared to cope with heterogeneous services and the huge amount of device data in the digital world. Furthermore, conducting financial transactions over the Internet raises several security issues. Such restrictions compromise the sensitive data of financial institutions and also degrade the trust of network users in the system. Thus, this article presents a secured blockchain model for high-performance computing in a big data environment, which aims to protect the business activities for financial interaction with intelligent services of software-defined network (SDN) architecture. First, to keep the security credentials, the SDN controller creates an association between the IoT devices and maintains local and global records. Second, the machine learning approach is explored using reliable and fault-tolerant methods to support the network scalability and extract the updated routing information for transmitting financial data. The proposed protocol also provides data integrity with a high level of network availability and copes with the financial security of big data by investigating cryptographic approaches. Our proposed protocol is tested using simulation, and various experiments are performed to show its efficacy in terms of network throughput, computing overhead, data delay, response time, and dropped packets as compared to tunicate swarm algorithm-based optimized routing mechanism (TORM) and RouteChain.

As a common phenomenon that often appears on social platforms, news sites, and community forums, topics have played an irreplaceable role in public opinion and social governance. Meanwhile, people's daily lives are increasingly dependent on the breeding, transformation, and attenuation of hot topics. This article aims to discuss the problem about topic duration, that is, what are the principle factors that affect topic duration? Why do some topics survive longer and even generate subtopics, while other topics disappear rapidly? To answer these questions, we innovatively use 104 121 alliance chat content inNova Empire IIfrom July 2023 to December 2023 as a case study. Dynamic topics trajectories are first obtained from a novel multilevel association model. Then, a potential factors system based on the dimensions of topic properties, topic users, and social network is established to quantitatively evaluate the influence for different factors. Experimental results from a robust statistical analysis framework demonstrate that higher topic discussion intensity, more content from opinion leader, faster information diffusion, and closer intertopic correlations will significantly improve the topic duration. Finally, a series of strategies are proposed to promote the design of social system applications from the perspectives of online social group.

Object counting, defined as the task of accurately predicting the number of objects in static images or videos, has recently attracted considerable interest. However, the unavoidable presence of background noise prevents counting performance from advancing further. To address this issue, we created a group and graph attention network (GGANet) for dense object counting. GGANet is an encoder-decoder architecture incorporating a group channel attention (GCA) module and a learnable graph attention (LGA) module. The GCA module groups the feature map into several subfeatures, each of which is assigned an attention factor through the identical channel attention. The LGA module views the feature map as a graph structure in which the different channels represent diverse feature vertices, and the responses between channels represent edges. The GCA and LGA modules jointly avoid the interference of irrelevant pixels and suppress the background noise. Experiments are conducted on four crowd-counting datasets, two vehicle-counting datasets, one remote-sensing counting dataset, and one few-shot object-counting dataset. Comparative results prove that the proposed GGANet achieves superior counting performance.

Convolutional Neural Networks (CNNs) have been highly successful in computer vision tasks, including leaf disease detection. However, their lack of interpretability limits our understanding of their decision-making process and undermines trust in their predictions. In this study, we aim to unravel the black box of CNNs for leaf disease detection through a comprehensive model analysis and feature importance study. We review various techniques in explainable artificial intelligence and propose a methodology that combines model analysis and feature importance methods. We analyze the model’s internal representations and activations in order to understand how different layers process information. Additionally, we employ feature importance methods, like SHapley Additive exPlanations (SHAP), to quantify the influence of individual features on predictions. By assigning importance scores to each pixel or feature, we identify the most discriminative regions or characteristics used by the CNN for disease detection. These insights provide a deeper understanding of learned representations, the decision-making process, and the key visual cues used by CNNs. Our findings enhance interpretability, foster trust in automated leaf disease detection systems, and facilitate the development of more explainable and reliable models in precision agriculture.

Recent years have witnessed dramatic progress in computer vision technologies and their broad applications, where manufacturing and industrial fields are important branches that highly require computer vision to bring them intelligent updating. As the name suggests, our workshop focus on advanced multimedia computing for smart manufacturing and engineering. We want to collect advances in using computer vision in various applications of smart manufacturing and engineering, theoretical research and practical applications are both welcome. The accepted papers cover the practical applications of advanced multimedia computing in tunnel water leakage recognition and segmentation, multi-class lane detection, gaze estimation, and also the theoretical achievements on spectrum sensing, semantic segmentation, image classification, information security, etc. This workshop goals to boost the concern of the public on exploiting multimedia computing for intelligent manufacturing and engineering.

Summary Text classification is one of the most important tasks to extract information from the Internet and identifying the best text representation settings. With the increase of data volume on the world wide web, the significance of text classification increases. This situation requires huge human efforts to understand and classify the digital data available on the Internet. Text classification is classifying the number of text files into different classes. The data or text available on the Internet is in an unstructured form which increases the difficulty to understand and classify it for useful purposes. This paper proposes a context‐aware text classification system to improve text quality. We use a content‐aware recommendation system to extract the data from well‐known news databases. Text preprocessing techniques like tokenization, stemming, and stop words removal are studied in detail. Furthermore, unigram, bigram, and trigram attributes are also being tested. Attribute selection methods are also examined and their impact on the text classification results. To carry out a detailed investigation, 11 versions are created of each dataset to save the time in experimentation process and applied the different preprocessing techniques to understand the impact of each technique on classification results. The proposed system is compared with the existing approach to check the accuracy where the proposed system achieved better performance.

The Internet of Things (IoT) has demonstrated promising growth, as it is crucial to numerous application domains in smart ecosystems, such as the smart city. Decentralization can help achieve growth, with previous research proposing the use of the decentralized blockchain technology in IoT ecosystems as, among others, it can offer cryptographically trustworthy interactions, nonrepudiable smart contracts, and interoperability between stakeholders. However, proposals are often theoretical or very specific to IoT ecosystem subareas, for instance, healthcare. In both cases, implementation may not be feasible in a larger ecosystem. This article investigates the performance, particularly throughput, aspect of feasibility. It proposes and demonstrates a platform that uses the blockchain technology as a building block in an IoT ecosystem. A permissioned blockchain network is built, performance is measured, and the measurements are interpreted in a smart city context, thus, providing valuable insights about real-world implementations and their degree of feasibility.

The task of crowd counting and localization is to predict the count and position of people in a crowd, which is a practical and essential sub-task in crowd analysis and smart city systems. However, the inherent problems of scale variation and background disturbance restrain their performance. While recent researches focus on studying counting and localization independently, a few works are capable of executing both tasks simultaneously. To this end, we propose a Scale-Context Perceptive Network (SCPNet) to jointly tackle the crowd counting and localization tasks in a unified framework. Specifically, a scale perceptive (SP) module with a local-global branch schema is designed to capture multiscale information. Meanwhile, a context perceptive (CP) module, by the channel-spatial self-attention mechanism, is derived to suppress the background disturbance. Furthermore, a novel hierarchical scale loss function that combines the Euclidean loss function and structural similarity loss function is designed to prompt the proposed model to fulfill the counting and localization simultaneously. Extensive experiments on challenging crowd datasets prove the superiority of the proposed SCPNet compared with the state-of-the-art competitors in both objective and subjective evaluations.

With the transformation of human life into virtual worlds based on the reality, current researches of smart cities and sustainability should integrate the factors of virtual social behaviors. Virtual games are an ideal domain and tools for exploring social science. Therefore, our work innovatively using Nova Empire as a case study to reveal the social group long-term survival via complexity analysis of behavior graph structural properties for building smart cities. Specifically, behavioral data of 101424 players and 5324 alliances from September 2021 to February 2022 are used. Our observations show that the phenomenon of “gap of wealth” in real society also exists in the virtual game. Meanwhile, the player online time is significantly positive related to alliance survival time, which is the foundation of our work. Then, correlation and regression analysis are performed to understand the significance of different structural properties on alliance survival time. Our original findings demonstrate that larger alliance, more subgroups, balanced player distribution, and frequent behavioral interactions will promote long-term survival of the alliance. Small subgroup and a relaxed social environment can improve player online time. Furthermore, we transfer the conclusions from virtual game to real society based on the mapping principle. Finally, new virtual tools and solutions for policymakers to improve smart cities and sustainable society ecosystem, and operation strategies for game designers to improve players retention rate are proposed.

Reference-based super-resolution (RefSR), which aims to introduce an additional high-resolution (HR) reference (Ref) image to improve the reconstruction performance of low-resolution (LR) image, has achieved great success. Existing RefSR methods rely on the texture information of the reference image to compensate for the missing information. However, the differences of scale and orientation are unavoidable when obtaining useful information from the Ref image. In addition, it is difficult to achieve a good match due to the ill-posed between the LR image and Ref image. To address these challenges, we propose a new matching module, named progressive spatial adaptation module (PSAM). PSAM is a progressive alignment model to effectively overcome the ill-pose between the LR image and the Ref image. Further, we propose a spatial correction module (SCM) to correct for scale and orientation. Meanwhile, we introduce a gradient map to further correct the matched features. In addition, we propose a new loss function MC-Loss to ensure the success of correction. Experiments show that the matching method using PSAM to directly replace the existing RefSR is significantly better than the original matching method in terms of both quantitative and qualitative results.

Text sentiment style transfer aims to extract the sentiment words from a sentence and transfer them into another expected sentiment style while retaining the original sentence's content. However, previous works have not achieved satisfactory performance on the text sentiment style transfer task, especially for non-parallel text. In this article, a novel framework with the attention mechanism and embedding perturbed encoder is proposed to improve the performance of non-parallel text sentiment style transfer. Firstly, the reverse attention mechanism is adopted to disentangle the sentiment style information from the latent representation. And then an embedding perturbed encoder is designed to append an adjustable noise to the embedding space to make the latent representation more semantic. Finally, the attention mechanism is introduced to give different weights for generated words during the decoding process, so that the model can focus on those high-weight words to enhance the quality of sentiment style transfer. Experiments on the corpora of Yelp and IMDB demonstrate that the suggested framework outperforms previous works on the aspects of sentiment style transfer accuracy, content preservation and language fluency.

Recent advancement in biomedical imaging technologies has contributed to tremendous opportunities for the health care sector and the biomedical community. However, collecting, measuring, and analyzing large volumes of health-related data like images is a laborious and time-consuming job for medical experts. Thus, in this regard, artificial intelligence applications (including machine and deep learning systems) help in the early diagnosis of various contagious/ cancerous diseases such as lung cancer. As lung or pulmonary cancer may have no apparent or clear initial symptoms, it is essential to develop and promote a Computer Aided Detection (CAD) system that can support medical experts in classifying and detecting lung nodules at early stages. Therefore, in this article, we analyze the problem of lung cancer diagnosis by classification and detecting pulmonary nodules, i.e., benign and malignant, in CT images. To achieve this objective, an automated deep learning based system is introduced for classifying and detecting lung nodules. In addition, we use novel state-of-the-art detection architectures, including, Faster-RCNN, YOLOv3, and SSD, for detection purposes. All deep learning models are evaluated using a publicly available benchmark LIDC-IDRI data set. The experimental outcomes reveal that the False Positive Rate (FPR) is reduced, and the accuracy is enhanced.

In the pharmaceutical industry, problems like counterfeit drugs, including vaccines, and their supply chain management problems like transparency, immutability, and traceability exist. In the case of vaccines, it becomes more difficult to standardize and detect fake vaccines because the public has less awareness and knowledge about vaccines. Moreover, the increase in online pharmacies gives more opportunities for counterfeiting vaccines to enter the authentic supply chain management system. We present transparent, immutable and secure vaccine supply chain (TISVSchain), a framework based on blockchain to handle the issues of counterfeited vaccines and vaccine supply chain problems like transparency, immutability, and traceability. Our proposed framework can run both on the private and public blockchain. We have implemented the framework on public blockchain by using remix ide and the smart contracts designed by solidity language run on very low gas cost. We also carried out several experiments by changing the number of nodes and their block time to evaluate the performance of our framework in terms of transaction per second (TPS), gas cost, and propagation delay. Our proposed framework improves the security by using offline unique account addresses in blockchain-based frameworks and improves the overall efficiency of the framework by keeping the gas cost low, finding a way to decrease the number of lost blocks to keep low propagation delay, and keeping high TPS value. TISVSchain shows us promising results to improve vaccine supply chain management’s overall performance, security, and efficiency.

With the constant fusion of virtual and reality, a new vision of human beings has emerged—Metaverse. At present, the development of metaverse is still in its infancy, and although the industry has put feverish investment into it, there are still many problems that need to be discussed in academia. The first thing is user engagement. Metaverse relies heavily on massive online users to realize its social value. In other words, user engagement is the foundation of the metaverse ecosystem. Therefore, our research uses Nova Empire as a case study, aiming at understanding metaverse engagement via complexity analysis of social patterns and reward mechanisms. Specifically, the behavioral data of 46 954 players in September 2021 are used for analysis. Our observations show that social behavior is not the main factor for user engagement. Then, we perform a correlation analysis of trigger times for different gaming behaviors to verify the above observations. The results prove that the main factors affecting user engagement are game tasks and reward mechanisms in the early stage and social gaming behaviors environment with alliances in the middle and late stages. Finally, we discuss the implications of our findings for the design of future games and propose operation strategies on user engagement to improve the metaverse ecosystem and other online social space.

5G is becoming the foundation for the Industrial Internet of Things (IIoT) enabling more effective low-latency integration of artificial intelligence and cloud computing in a framework of a smart and intelligent IIoT ecosystems enhancing the entire industrial procedure. However, it also increases the functional complexities of the underlying control system and introduces new powerful attack vectors leading to severe security and data privacy risks. Malware attacks are starting targeting weak but highly connected IoT devices showing the importance of security and privacy in this scenario. This article designs a 5G-enabled system, consisted in a deep learning based architecture aimed to classify malware attacks on the IIoT. Our methodology is based on an image representation of the malware and a convolutional neural networks that is designed to differentiate various malware attacks. The proposed architecture extracts complementary discriminative features by combining multiple layers achieving 97% of accuracy.

The characteristics of sea clutter in real marine environments in different sea areas play a vital role in military industry, such as radar detection, remote sensing, SAR imaging, and situational awareness. In this article, a deep neural network (DNN) sea clutter model is proposed based on the sea clutter big data under the real marine environment to study the characteristics of sea clutter and parameter inversion. Based on the ERA-Interim reanalysis (2015–2017), a database of marine environmental elements in China's offshore waters was established, and a spatiotemporal prediction model for marine environmental elements was proposed to improve missing values. Considering the scattering mechanism of sea surface at different scales comprehensively, a large database of sea clutter time series of multiscale real surface is established and comparison with the experimental data. Aiming at the coastal waters of China, the long short-term memory model and DNN are used to establish the correlation model between marine environmental elements and sea clutter characteristics, and the prediction and parameter inversion of sea clutter characteristics based on sea clutter big data are studied. The results show that the coefficients of determination of the predicted fitted curves for the HH and VV polarization amplitudes reach 0.9249 and 0.8872, respectively. The inversion of wave heights in different sea areas is the lowest in the South China Sea (accuracy rate of 78%) and the highest in the East China Sea (accuracy rate is 90%). The results of this article can help improve the ability of sea surface remote sensing and sea clutter suppression.

Currently, COVID-19 is circulating in crowded places as an infectious disease. COVID-19 can be prevented from spreading rapidly in crowded areas by implementing multiple strategies. The use of unmanned aerial vehicles (UAVs) as sensing devices can be useful in detecting overcrowding events. Accordingly, in this article, we introduce a real-time system for identifying overcrowding due to events such as congestion and abnormal behavior. For the first time, a monitoring approach is proposed to detect overcrowding through the UAV and social monitoring system (SMS). We have significantly improved identification by selecting the best features from the water cycle algorithm (WCA) and making decisions based on deep transfer learning. According to the analysis of the UAV videos, the average accuracy is estimated at 96.55%. Experimental results demonstrate that the proposed approach is capable of detecting overcrowding based on UAV videos' frames and SMS's communication even in challenging conditions.

Increasingly serious health problems have made the usage of computed tomography surge. Therefore, algorithms for processing CT images are becoming more and more abundant. These algorithms can lessen the harm of cumulative radiation in CT technology for the patient while eliminating the noise of image caused by dose reduction. However, the mainstream CNN-based algorithms are inefficient when dealing with features in broad regions. Inspired by the large receptive field of transformer framework, this paper designs an end-to-end low-dose CT (LDCT) denoising network based on the transformer. The overall network contains a main branch and dual side branches. Specifically, the overlapping-free window-based self-attention transformer block is adopted on the main branch to realize image denoising. On the dual side branches, we propose double enhancement module to enrich edge, texture, and context information of LDCT images. Meanwhile, the receptive field of network is further enlarged after processing, which is helpful for building model's long-range dependencies. The outputs of the side branches are concatenated for enhancing information and generating high-quality CT images. In addition, to better train the network, we introduce a compound loss function including mean squared error (MSE), multi-scale perceptual (MSP), and Sobel-L1 (SL) to make the denoised image closer to the targeted norm-dose CT (NDCT) image. Lastly, we conducted experiments on two clinical datasets including abdomen, head, and chest LDCT images with 25%, 25%, and 10% of the full dose, respectively. The experimental results demonstrated that the proposed DEformer achieved better denoising performance than the existing algorithms.

Integration of advanced signal processing, image processing, deep learning, edge computing, and the Internet of Things (IoT) into vehicles allows intelligent automated vehicles to navigate autonomously in different environments. It is crucial for reliable and safe driving that an autonomous vehicle can accurately, effectively, and efficiently recognize, perceive, and observe the surrounding environments. Autonomous vehicles comprise advanced sensor technologies such as RGB cameras and LiDaR that produce an extensive data set in the form of RGB images and 3D measurement points, also recognized as a point cloud. It is necessary to understand and interpret collected data information efficiently and to identify other road users, such as pedestrians and vehicles. Thus, we introduced a smart IoT-enabled deep learning based end-to-end 3D object detection system that works in real-time, emphasizing autonomous driving situations. The detection model is based on YOLOv3; firstly, the model is utilized for 2D object detection and then modified for 3D object detection purposes. The presented model uses point cloud, and RGB image data as input and outputs detected bounding boxes with confidence scores and class labels. Experiments are carried out on the Lyft data set; results reveal that the YOLOv3 model achieves high accuracy and outperforms from other state-of-the-art detection models in terms of effectiveness and accuracy. The overall accuracy of the model is 96% and 97% for 2D and 3D object detection, respectively.

Self-driving technology and safety monitoring devices in intelligent transportation systems require superb capacity for context awareness. Accurately inferring the counts of crowds and vehicles are the two practical and fundamental tasks in the transportation system. However, the scale variation and background interference in the traffic image hinder the counting performance. To solve the aforementioned problems, a scale region recognition network (SRRNet) is proposed in this paper. It has two key components, termed scale level awareness (SLA) module and object region recognition (ORR) module. The SLA module aims to encode the representations at multiple scales, which are beneficial to address the scale variation. The ORR module is designed to suppress background interference through the visual attention mechanism. Extensive experimental results on four crowd counting datasets and five vehicle counting datasets have demonstrated the superiority of the proposed SRRNet in both counting accuracy and robustness compared with the mainstream competitors. Meanwhile, substantial ablation studies have proved the effectiveness of the proposed SLA and ORS modules.

Intelligent Transportation Systems (ITS) have gained popularity due to smart services and applications to facilitate the users on the roads. The increasing growth of users in these networks created new and complex data processing, storage, security, and privacy concerns. These networks are using centralized edge, fog, or cloud architecture for data management. User privacy is compromised in these networks due to the increasing demands and service provider’s services. To ensure the data privacy, the centralized architectures are used without privacy regulations. In this paper, we present a Blockchain-based Privacy-Preserving Authentication (BPPAU) model for ITS networks to ensures users privacy and security. The proposed model provides data storage, data accessing, and processing management by using a blockchain smartcontract system, access control policy and on demand based functions. The proposed model is tested in a simulation environment to check its performance in terms of transaction cost with data size, transaction per second analysis with block time, and computational time analysis with several transactions.

Today big data pipelines are increasingly adopted by service applications representing a key enabler for enterprises to compete in the global market. However, the management of non-functional aspects of the big data pipeline (e.g., security, privacy) is still in its infancy. As a consequence, while functionally appealing, the big data pipeline does not provide a transparent environment, impairing the users’ ability to evaluate its behavior. In this paper, we propose a security assurance methodology for big data pipelines grounded on the DevSecOps development paradigm to increase trustworthiness allowing reliable security and privacy by design. Our methodology models and annotates big data pipelines with non-functional requirements verified by assurance checks ensuring requirements to hold along with the pipeline lifecycle. The performance and quality of our methodology are evaluated in a real walkthrough analytics scenario.

The Internet of Things or IoT describes the network of physical terminals, the “objects” that integrate sensors, software, and other technologies to connect to different terminals and systems on the Internet and exchange data with them. These terminals can be simple household appliances and industrial tools of great complexity. Augmented Reality (AR) provides operators with information directly in their field of vision, using a helmet or adapted glasses. The obstacles to the adoption of Augmented Reality are related to several factors. First, the devices do not yet offer efficient and discreet ergonomics and are still expensive. While IoT and sensors are focused on the productivity of machines, Augmented Reality makes it possible to increase the performance of a human. Industrial Augmented Reality aims to improve the factory’s economic performance. This article proposes a hybrid solution between mixed Reality and IIoT for industrial applications.

Summary Structure Query Language Injection Attack is among the top 10‐security threats that can be used on the web application to cause severe damage or gain unauthorized data access to the application server. Many reports have indicated an average of 64% of global websites are at risk of being attack by SQL injection, and many of the top companies have experienced thousands of attacks attempts through SQL injection. The current trend shows the increasing number of attacks factor as a result of the daily deployment of these applications without security detection and prevention mechanism is placed. To overcome this challenge, researches in academia and industry presented a proposal that automates SQL injection vulnerabilities assessment on the tested application. Current studies show the need to enhance techniques of these proposals to reduce the false alarms. In this study, we propose a component‐based technique to minimize the incidence of inaccurate results, as well as enable the ease of improving the proposed solution. The study uses three costumed applications as tested to evaluate the accuracy of the proposed solution. Each of these testbed consists of several vulnerabilities where the experimental evaluation performs to test the proposed tool. An empirical evaluation is carried out on three vulnerable custom websites to evaluate the effectiveness of the proposed study. The experiment results indicated significant results in terms of high accuracy. On the other hand, the proposed solution also has better capabilities to analyze page response based on four different techniques. Moreover, the proposed solution is the only solution that performs stored procedure attacks SQL and bypass login authentication even if the returned records are limited restriction is applied.

Summar Software Defined Networks (SDN) is now the leading framework for the existing network infrastructure. Increasing Internet traffic leads to attract SDN infrastructure in large networks like enterprise or data centers by using logical centralize control concept. This abstraction, flexibility, and agility enable the network managers to view the global picture of the network and flow the traffic in an efficient way to avoid congestion and traffic delay issues. However, besides the benefits, the internal mechanism of SDN has some serious challenges, which leads flow table overflow, congestions, controller and switch overloading, link failure and latency issues. This research focus on the delays produced during communication between control plane and data plane due to the parameters like rule formation, mismatches, buffer/queue constraints, flow entries, controller resource utilization or duplicate flow packets, and unordered packets. These delays become more critical in large networks especially in‐case of reactive modes. Furthermore, the frequent rule composition and installation causes extra burden at the controller, this control communication needs prompt reply to forward the traffic in a stipulated time. This article presents the Efficient Resource Management Scheme (ERMS), which efficiently handle the inter‐communication delay and minimize the network overheads. The experiment results depict the better performance of ERMS during the communication between controller and switch by efficient packet handling and flow rules management while minimizes the overheads on controller. The proposed solution enhances the performance of SDN networks by improving the quality of services parameters.

Abstract Software‐defined networks have been developed to allow the entire network to be managed as a programmable entity. As a well‐known protocol in this field, OpenFlow installs new packet forwarding rules of the distinct packets of Big Data flows (known as flow entries) in the flow tables of network switches in order to implement the desired management policies. Despite the high speed, flow tables have limited capacity to store the information of Big Data flows. As a result of inefficient policy for replacing the entries of the flow table, lack of flow entries corresponding to the incoming packets in the flow table of the switch will increase the references to the controller for forwarding this packet as well as the amount of delay in packet forwarding. The underlying idea of the proposed method is to make use of the popularity of traffic flows in the table to select the intended flow for the replacement. For replacement of flow table entries, a novel and intelligent method is proposed in this research which uses a reference history of flows to assign an importance degree to each table entry. Comparison of the simulation results confirms the superiority of the method for reducing the controller's overflow.

Artificial intelligence (AI), combined with the Internet of Things (IoT), plays a beneficial role in various fields, including intelligent surveillance applications. With IoT and 5G advancement, intelligent sensors, and devices in the surveillance environment collect large amounts of data in the form of videos and images. These collected data require intelligent information processing solutions, help analyze the recorded videos and images to detect and identify various objects in the scene, particularly humans. In this study, an automated human detection system is presented for a complex industrial environment, in which people are monitored/detected from a top view perspective. A top view is usually preferred because it can provide sufficient coverage and enough visibility of a scene. This study demonstrates the applications, efficiency, and effectiveness of deep learning architectures, that is, Faster Region Convolutional Neural Network (Faster R-CNN), Single Shot MultiBox Detector (SSD), and You Only Look Once (YOLOv3), with transfer learning. Experimental results reveal that with additional training and transfer learning, the performance of all detection architectures is significantly improved. The detection results are also compared using the same data set. The deep learning architectures achieve promising results with maximum true-positive rate of 93%, 94%, and 94% for Faster-RCNN, SSD, and YOLOv3, respectively. Furthermore, a detailed study is performed on output results that highlight challenges and probable future trends.

Advancements in digital technologies, such as the Internet of Things (IoT), fog/edge/cloud computing, and cyber-physical systems have revolutionized a broad spectrum of smart city applications. The significant contributions and rapid developments of advanced artificial intelligence-based technologies and approaches, like, machine learning and deep learning, which are applied for extracting accurate information from extensive data, perform a potential role in IoT applications. Moreover, blockchain technology's fast adoption also contributes a significant role in the development of the new digital smart city ecosystem. Thus, artificial intelligence and blockchain technology convergence revolutionize smart city infrastructures to establish sustainable ecosystems for IoT applications. Nevertheless, these advancements and technological improvements also provide both opportunities and challenges for developing sustainable IoT applications. This paper aims to examine the convergence of blockchain technology and artificial intelligence, a unique driver towards technological transformation in intelligent and sustainable IoT applications. We mainly discussed the advantages of blockchain technology that might promote the advancement and development of sustainable IoT applications. On the basis of the discussion, we introduced a smart and sustainable conceptual framework that leverages cloud computing, IoT devices, and artificial intelligence to process and obtain necessary information. The system provides digital analytics and saves results in decentralized cloud repositories through blockchain technology to promote various applications. Moreover, the layer-based architecture allows a sustainable incentive structure, which can possibly assist secure and protected smart city applications. We reviewed the enhanced solutions, summing up the key points that can be applied for generating various artificial intelligence and blockchain-based systems. Also, we discussed the issues that still remain open and our future research goals; that can introduce new ideas and future guidelines for sustainable IoT applications.

Smart health-care is the innovation that leads to enhanced diagnostic tools, improved patient treatment, and gadgets that ease the quality of life for majority of people. Textual clinical documents about an individual contain sensitive and semantically corelated terms. Most privacy-preserving approaches are not designed to prevent confidentiality threats. Although, recent approaches improved the utility of published output with generalized terms retrieved from several medical and general-purpose knowledge bases like SNOMED-CT and MASH. However, these models work on predefined sensitive terms using Wikipedia articles instead of authentic benchmarks. These Information Content-based methods are not capable to achieve the best balance between privacy and utility. The existing approaches guarantee syntactic privacy by sanitization but lack semantic privacy for textual clinical data. Therefore, it is imperative to design a confidentiality-aware framework to overcome these problems. Our proposed Confidentiality aware Textual Clinical Data Framework use preprocessed combinations of the terms instead of all combinations and perform automatic detection and sanitization of the sensitive and semantically correlated terms. The probabilistic sampling-based method guarantees the semantic privacy. We use high-level Petri nets to perform formal modeling of our proposed approach. Furthermore, we have also performed a detailed complexity analysis of the proposed framework.

Abstract According to the World Health Organization, cardiovascular diseases contribute to 17.7 million deaths per year and are rising with a growing ageing population. In order to handle these challenges, the evolved countries are now evolving workable solutions based on new communication technologies such as ambient assisted living. In these solutions, the most well-known solutions are wearable devices for patient monitoring, telemedicine and mHealth systems. This systematic literature review presents the detailed literature on ambient assisted living solutions and helps to understand how ambient assisted living helps and motivates patients with cardiovascular diseases for self-management to reduce associated morbidity and mortalities. Preferred reporting items for systematic reviews and meta-analyses technique are used to answer the research questions. The paper is divided into four main themes, including self-monitoring wearable systems, ambient assisted living in aged populations, clinician management systems and deep learning-based systems for cardiovascular diagnosis. For each theme, a detailed investigation shows (1) how these new technologies are nowadays integrated into diagnostic systems and (2) how new technologies like IoT sensors, cloud models, machine and deep learning strategies can be used to improve the medical services. This study helps to identify the strengths and weaknesses of novel ambient assisted living environments for medical applications. Besides, this review assists in reducing the dependence on caregivers and the healthcare systems.

Visual relationship detection (VRD) is one newly developed computer vision task, aiming to recognize relations or interactions between objects in an image. It is a further learning task after object recognition, and is important for fully understanding images even the visual world. It has numerous applications, such as image retrieval, machine vision in robotics, visual question answer (VQA), and visual reasoning. However, this problem is difficult since relationships are not definite, and the number of possible relations is much larger than objects. So the complete annotation for visual relationships is much more difficult, making this task hard to learn. Many approaches have been proposed to tackle this problem especially with the development of deep neural networks in recent years. In this survey, we first introduce the background of visual relations. Then, we present categorization and frameworks of deep learning models for visual relationship detection. The high-level applications, benchmark datasets, as well as empirical analysis are also introduced for comprehensive understanding of this task.

Although the performance of pansharpening has been significantly improved by advanced deep-learning (DL) technologies in recent years, most DL-based methods fail to process multispectral (MS) images with arbitrary numbers of bands by a single model. Consequently, it is inevitable to train separate models for MS images with different numbers of bands, which is time- and storage-consuming as well as inefficient in practice. To tackle the above problem, we propose a bidirectional recurrent pansharpening network (named ArbRPN) for MS images with arbitrary numbers of bands. Our ArbRPN can dynamically reconstruct high-resolution (HR) MS images with different numbers of bands by adaptively changing the number of recurrence to the number of bands of the low-resolution (LR) MS images. Leveraging on the ability of the ArbRPN to process MS images with any number of bands, one can even customize the bands to be pansharpened. Moreover, to achieve superior performance, spectral discrepancy and dependence are considered in the ArbRPN. Details from the panchromatic (PAN) image are adaptively injected into the fused product according to the captured spectral dependence. Furthermore, training strategies of existing DL-based pansharpening methods can only group MS images with a constant number of bands into mini-batches. Therefore, we present a mask-based training method (called mask-training) to solve this problem. Benefiting from the mask-training, our ArbRPN can achieve superior performance and robustness during pansharpening. Extensive experiments show the superior performance of our ArbRPN with respect to the state-of-the-art (SOTA) methods applied to MS images with different numbers of bands. The code of our ArbRPN is available onhttps://github.com/Lihui-Chen/ArbRPN.git.

Nowadays, due to the difficult acquisition of true labels, a semisupervised neural network has shown great potential for change detection (CD) in remote sensing images. However, most of the traditional semisupervised neural network detection frameworks are complex to train and require additional structural analysis, along with a fixed structure, lacking universality. In this article, a semisupervised adaptive ladder network (SSALN) for remote sensing image CD is proposed, which enables dual-input label-incremental architecture searching with a concise and variable structure. First, SSALN is suitable for CD from two remote sensing images of any type with the characteristic of minimal label dependency and automatic network structure adjustment. The network can generate more reliable pseudolabels through continuous iterations to help limited real labels exploit implicit information, identify the most effective network, and form the ascending network structure optimization. Second, the acquisition of pseudolabels is the fusion of semisupervised and unsupervised CD approaches, which ensures the multiperspective information supplement. Multiple CD maps are fused to generate labels for the next iteration, making the predicting more reliable. Finally, both homogenous images and heterogenous images are tested with experiments. Even if the detection object is switched, it can be well adaptive and compatible without manual modification of the network. Experimental results demonstrate that the proposed method can promote the flow of label information through structure searching and self-circulation in the ascending network optimization; thus, it has outstanding performance on tasks of remote sensing image CD.

Nowadays, Industry 4.0 can be considered a reality, a paradigm integrating modern technologies and innovations. Artificial intelligence (AI) can be considered the leading component of the industrial transformation enabling intelligent machines to execute tasks autonomously such as self-monitoring, interpretation, diagnosis, and analysis. AI-based methodologies (especially machine learning and deep learning support manufacturers and industries in predicting their maintenance needs and reducing downtime. Explainable artificial intelligence (XAI) studies and designs approaches, algorithms and tools producing human-understandable explanations of AI-based systems information and decisions. This article presents a comprehensive survey of AI and XAI-based methods adopted in the Industry 4.0 scenario. First, we briefly discuss different technologies enabling Industry 4.0. Then, we present an in-depth investigation of the main methods used in the literature: we also provide the details of what, how, why, and where these methods have been applied for Industry 4.0. Furthermore, we illustrate the opportunities and challenges that elicit future research directions toward responsible or human-centric AI and XAI systems, essential for adopting high-stakes industry applications.

Digital twins (DT) have been proposed to support and enhance manufacturing processes of the industries. The outcome of adopting DT is so encouraging that it is hoped that more than 50% of the large industries will benefit from DT by the end of 2021. Unfortunately, DT lacks a single publicly accepted narrative. In order to help researchers for building a common narrative about DT, we present an elaborated structure of DT, namely, spiral DT-framework. Furthermore, for a secure and reliable management of the DT data, we propose using the blockchain technology rather than cloud or fog. As the classical blockchain suffers from transaction confirmation delays and is vulnerable to the quantum attacks, therefore, we propose a new variant of blockchain, namely twinchain, which is quantum-resilient and offers immediate transaction confirmation. This article also presents a framework for deployment of twinchain for manufacturing of a robot surgical machine.

Due to the Internet of Things evolution, the clinical data is exponentially growing and using smart technologies. The generated big biomedical data is confidential, as it contains a patient’s personal information and findings. Usually, big biomedical data is stored over the cloud, making it convenient to be accessed and shared. In this view, the data shared for research purposes helps to reveal useful and unexposed aspects. Unfortunately, sharing of such sensitive data also leads to certain privacy threats. Generally, the clinical data is available in textual format (e.g., perception reports). Under the domain of natural language processing, many research studies have been published to mitigate the privacy breaches in textual clinical data. However, there are still limitations and shortcomings in the current studies that are inevitable to be addressed. In this article, a novel framework for textual medical data privacy has been proposed as Deep-Confidentiality . The proposed framework improves Medical Entity Recognition (MER) using deep neural networks and sanitization compared to the current state-of-the-art techniques. Moreover, the new and generic utility metric is also proposed, which overcomes the shortcomings of the existing utility metric. It provides the true representation of sanitized documents as compared to the original documents. To check our proposed framework’s effectiveness, it is evaluated on the i2b2-2010 NLP challenge dataset, which is considered one of the complex medical data for MER. The proposed framework improves the MER with 7.8% recall, 7% precision, and 3.8% F1-score compared to the existing deep learning models. It also improved the data utility of sanitized documents up to 13.79%, where the value of the k is 3.

Digital twins is a virtual representation of a device and process that captures the physical properties of the environment and operational algorithms/techniques in the context of medical devices and technology. It may allow and facilitate healthcare organizations to determine ways to improve medical processes, enhance the patient experience, lower operating expenses, and extend the value of care. Considering the current pandemic situation of COVID-19, various medical devices, e.g., X-rays and CT scan machines and processes, are constantly being used to collect and analyze medical images. In this situation, while collecting and processing an extensive volume of data in the form of images, machines and processes sometimes suffer from system failures that can create critical issues for hospitals and patients. Thus, in this regard, we introduced a digital twin based smart healthcare system integrated with medical devices so that it can be utilized to collect information about the current health condition, configuration, and maintenance history of the device/machine/system. Furthermore, the medical images, i.e., X-rays, are further analyzed by a deep learning model to detect the infection of COVID-19. The designed system is based on Cascade RCNN architecture. In this architecture, detector stages are deeper and are more sequentially selective against close and small false positives. It is a multi stage extension of the Recurrent Convolution Neural Network (RCNN) model and sequentially trained using the output of one stage for the training of the other one. At each stage, the bounding boxes are adjusted in order to locate a suitable value of nearest false positives during training of the different stages. In this way, an arrangement of detectors is adjusted to increase Intersection over Union (IoU) that overcome the problem of overfitting. We trained the model for X-ray images as the model was previously trained on another data set. The developed system achieves good accuracy during the detection phase of the COVID-19. Experimental outcomes reveal the efficiency of the detection architecture, which gains a mean Average Precision (mAP) rate of 0.94.

Summary With the rapid growth in wireless data networks and increasing demand for multimedia applications, the next generation of wireless networks should be able to provide services for heterogeneous traffic with diverse quality of service (QoS) requirements. Multiuser diversity refers to a type of diversity present across different users in a fading environment. This diversity can be exploited by scheduling transmissions so that users transmit when their channel conditions are favorable. Hence, scheduling algorithms that support QoS and maintain a required throughput to ensure users' satisfaction are crucial to the development of these wireless networks. In this paper, different scheduling techniques have been evaluated using OFDM with different scenarios. The goal is to analyze the properties of networks such as throughput, fairness, and delay. Experimental results indicate that the PFS approach outperforms the other techniques in terms of fairness, throughput, and delay.

Summary Optimizing cell locations of cellular networks is one of the most fundamental problems of network design. However, in order to meet a growing appetite for mobile data services, a large number of base stations are being deployed, which leads to tremendous energy consumption in cellular networks. This augmentation increases not only the system's capital and operational expenditure (CAPEX/OPEX) for mobile operators but also CO2 emissions. Besides the issue of meeting overwhelming traffic demands, network operators around the world now realize the importance of managing their cellular networks in an energy‐efficient manner. In this paper, we develop a self‐organizing framework for energy saving in orthogonal frequency‐division multiple‐access–based cellular access networks. We consider three different objectives, namely, coverage maximization, overlap minimization, and power consumption minimization, which is different from all existing works on energy saving in cellular networks.

Computational intelligence techniques are traditionally adopted in several different application domains such as industry, healthcare, decision making, and gaming, to name but a few. Despite this growing diffusion, there are still many possible areas where computational intelligence application is partial or could be extended and improved due to the actual limitations in terms of computational power or strict requirements in terms of assurance of the results. \n \nThis special issue aims to investigate the impact of the adoption of advanced and innovative computational intelligence techniques in emerging application fields like IoT and big data. This edition of the special issue is focused primarily on industrial and health applications with special emphasis on real-time systems grounded on big data ecosystems. \n \nThe special issue will bring together researchers on different disciplines from academia and industry with a common objective: go beyond the frontiers of today's applications of computational intelligence techniques.

Real-time social multimedia level threat monitoring is becoming harder, due to higher and rapidly increasing data induction. Data induction through electric smart devices is greater compared to information processing capacity. Nowadays, data becomes humongous even coming from the single source. Therefore, when data emanates from all heterogeneous sources distributed over the globe makes data magnitude harder to process up to a needed scale. Big data and Deep learning have become standard in providing well-known solutions built-up using algorithms and techniques in resolving data matching issues. Now, with the involvement of sensors and automation in generating data obscures everything, predicting results to overcome a current era of ever enhancing demands and getting real-time visualization brings the need of feature like human behavior mode extraction to overcome any future threats. Big data analytics can bring the opportunity of predicting any misfortune even before they happen. Map reduce feature of big data supports massive data oriented process execution using distributed processing. Real-time human feature identification and detection can occur through sensors and internet sources. A behavioral prediction can further classify the information collected for introducing enhanced security extents. Real-time sensor devices are producing 24/7-hour data for further processing recording each event. IoT-based sensors can support in behavioral analysis model of a human. Real-time human behavioral monitoring based on image processing and IoT using big data analytics.

Summary This paper proposes a new color interpolation method which can be used in embedded devices for IoT system. In this work, we use regression approach for generating and designing filters to restore color image. The filters are designed with four sizes, 5x5 training filter, 7x7 training filter, 9x9 training filter, and 11x11 training filter. The obtained filters are tested in 25 LC dataset to assess the performance. Experimental results inform that the proposed filters provide outstanding performance when they are compared with conventional methods. As compared with the other methods, the proposed filters produce the best average interpolation performance both objectively and visually.

Summary Human behavior would lead to a significant impact on the environment. By monitoring the environment, we can indirectly monitor human behavior. Remote sensing (RS) technology provides a large number of multispectral (MS) images. When combining the Internet of things (IoT) technology, those images can be used for human behavioral monitoring. However, due to the limitation of the optical sensors embedded in satellites, the spatial resolution of MS image is relatively low, which poses a huge problem for further understanding these images. Pansharpening, also known as multisensor image fusion, aims to sharp an MS image to a high‐resolution multisensor image (HMS) by integrating a corresponding high‐resolution panchromatic (PAN) image. By doing so, the redundancy among big data can be effectively reduced. Traditional Intensity‐Hue‐Saturation (IHS)–based methods often suffer from spectral distortion. To address this problem, a novel pansharpening method is proposed in this paper. Different from those traditional IHS methods, the proposed method first decomposes MS and PAN into high‐frequency‐component (HFC) and low‐frequency‐component (LFC), respectively. Then, the guided filter (GF) is utilized to enhance the spectral information on the detail map. Furthermore, the detail map is refined according to the adaptive coefficients for each band of MS. By performing experiments, we demonstrate the proposed method can obtain satisfying results in both visual quality and object assessment among existing methods.

The Internet of Things (IoT) phenomenon has undergone several transformations in its characterizing principles and technologies. With the number of connected devises set to top 11 billion in 2018, it will clearly continue to be a hot research topic. It is evident that there is a general misunderstanding on its use; such term is often abused and associated with several different meanings. Such misunderstanding has been amplified by the fact that there is a significant overlapping between the IoT and other important research areas such as smart objects, cyber physical systems, and ambient intelligence. The IoT can be considered as a conceptual framework including technological, service design, and finalizations point of view. These three aspects have to be considered together at the same time when creating IoT solutions; otherwise, the risk is to design a solution belonging to the old domains of pervasive computing, wireless sensor network, M2M, and so on. In this research area, finding a solution to the question “what IoT is and what it is not” avoids confusions that could lead to the rejection of this paradigm, which instead has the potentials to impact significantly on our current social challenges. Especially, this issue is open to all on the theme “Toward the Internet of Things of year 2020” and topics from the fifth edition of the International Workshop on Data Mining on IoT Systems (VICTA 2018) held at Las Palmas de Gran Canaria, Spain (26-29 November 2018). After review, seven papers have been accepted for publication in this issue. For online marketing, it is important to place their websites on the top rank in a result of search engines. However, on-page techniques of traditional search engine optimizations (SEO) do not have logical foundation to select metadata. The contribution by An and Jung1 “A heuristic approach on metadata recommendation for search engine optimization” aims to recommend metadata for building a high ranking search engine result page by considering SEO. Metadata is an important element to prioritize websites when search engine indexing for user queries. Thereby, for online marketing, this study proposes a method for recommending metadata, which consists of two steps: (i) combining keywords and metadata from high-ranked websites and (ii) evaluating the importance of terms based on semantic relevance. First, terms are selected with influential keywords and metadata by using their frequency and weight. Second, prioritize the terms according to semantic relevance based on a competitive learning model. The authors evaluated the validity of the proposed method by using three queries in Google. Through three experiments, authors could find out that the keywords and metadata belong to the top ranking will be used, and terms have to relate semantic relevance with the query. In addition, when metadata and keywords are combined, it has received the increasing amount of its traffic. Experimental results demonstrate that it increases traffic of a website, by using terms, which are high-ranked websites and semantic relevance. The agricultural control starts with analyzing the current situation using chronological data to produce an early warning of possible damages. If any deficiency occurs, such as water shortage, insufficient nutrition, or disease, the growth of the plant slows down and its volume does not increase as much as in the case of normal development. Traditionally, farmers observe plants and detect problems based on their experience and symptoms of certain diseases. However, in most of such cases, the detection point is usually late to allow the plant to recover. The contribution by Lee and Park2 “A spatiotemporal data acquisition toolkit for volume estimation tools in precision agriculture” presents a data acquisition system for precision agriculture. The proposed system can collect various time-series data on target plants and their environmental facts. The designed system consists of server and multiple intranetworked stations and includes a software toolkit that has two independent but synchronized data acquisition processes. An analysis on sampling rate and data acquisition experiments for testing purposes were performed. A data filtering method based on the fast Fourier transform is applied to analyze the noise immunity of the collected data. For the volume estimation, three different methods, (i) with 2-D projection on slices, (ii) with polyhedrons on voxels, and (iii) with enclosed surfaces, were devised to handle various plant types, and were examined for three different types of target plants. The volume estimation errors were measured in range of 6% to 30% in the experiments. The embedded system consumes low power, which is designed to perform unique tasks such as sensors, simple calculator, and remote controls. In general, embedded apparatus is a function of a bigger device, where it executes particular mission of the device. The embedded system is also used in various forms of IoT solutions, particularly for industrial purposes. The IoT is one of well-studied research topics due to the rapid development in information and communication techniques. The electronics with IoT are able to transfer data and act reciprocally with others over the network, and they can be distantly supervised. Possible embedded devices for IoT can include wireless sensor networks, control systems, automation, and video surveillance. The contribution by Jeon et al3 “Image enhancement in embedded devices for internet of things” proposes a new color interpolation method that can be used in embedded devices for IoT system. In this work, the authors use regression approach for generating and designing filters to restore color image. The filters are designed with four sizes: 5-by-5 training filter, 7-by-7 training filter, 9-by-9 training filter, and 11-by-11 training filter. The obtained filters are tested in 25 LC dataset to assess the performance. Experimental results inform that the proposed filters provide outstanding performance when they are compared with conventional methods. Compared with the other methods, the proposed filters produce the best average interpolation performance both objectively and visually. Big data analysis becomes an important issue, and it is getting closely related to sports area. Transfer markets in football have attracted the interest of researchers in economy and management. In the contribution by Kim et al4 “Data-driven exploratory approach on player valuation in football transfer market,” authors propose a high-level analysis approach for classifying player valuation based on their performance during recent seasons. In particular, several data analysis techniques such as regression analysis, feature selection, and cluster analysis are presented for classifying players in term of performances and transfer fee. Specifically, by collecting and analyzing data from Wholescored, the largest detailed football statistics website, the authors have defined players into four groups, which include (i) low performance and low transfer fee, (ii) low performance and high transfer fee, (iii) high performance and high transfer fee, and (4) high performance and low transfer fee. The results in the implementation section show that, with the differences positions, there are different required skills that affect to the performance of players. The authors expect that this study can contribute to the management of Football Teams in terms of integrating these analyses into their management strategy. New technologies, tools, and methodologies have been used in the cultural heritage (CH) scenarios to assist the visitor to enrich and enjoy his experiences during the visit. The CH contexts intelligent systems are typically designed to allow the visitor to enjoy his experience and are usually composed by software tools, digital technologies, and UI/UX strategies that are combined together. Recently, many new models, methods, strategies, and prototypes, usually based on artificial intelligence systems, have been developed for CH in order to give a charming experience to visitors. Several dedicated works show very interesting technological solutions. The intelligent information systems based on machine learning approaches have been specifically designed for CH to enhance the quality of services in art exhibitions and events. In the contribution by Cuomo et al5 “A virtual personal assistant in cultural heritage contexts,” the authors show an innovative framework that can be specifically designed to help visitors during his/her visit by answering to their questions. The authors investigated how a system based on a machine learning approach may be used to develop intelligent tools that help visitors in a CH scenario. The authors also showed their specific implementation of a powerful virtual assistant based on machine learning, speech recognition, and question-answering subsystem that may improve the experience in a real CH site helping visitors enjoying their visit. The authors also describe a system architecture and a case study in a well-defined CH context. The IoT has attracted much attention from both industrial and research communities, and it represents a network consisting of physical objects such as sensors, mobiles, buildings, and vehicles in which software and electronics are embedded to connect with Internet and to enable collecting and exchanging data between them. On the other hand, cloud computing has extensively been leveraged for various services such as analyzing big data generated from and implementing applications worked in the IoT environment. The advent of IoT paradigm is having a great ripple effect in the field of disaster management as well as many other areas. Victim detection has been studied as rescuer- or victim-oriented approach, which utilizes the IoT advanced technologies, but they have weaknesses according to disaster types. In the contribution by Hong and Akerkar6 “Victim detection platform in IoT paradigm,” authors propose a victim detection platform (VDP) architecture combining both approaches using various advanced technologies such as IoT, drone, and edge/cloud computing to offer higher quality services, which ultimately result in swifter, better responses, and more lives saved. First, the authors have reviewed related literature regarding three crucial issues (ie, multimodal evaluation for reliable data, edge-based real-time response, and privacy-preserved Big Data analysis) to satisfy the service. In order to achieve these important aspects, the VDP architecture is described along with roles/relations of technologies and concepts leveraged to and data sources considered in the platform. To explore the realization possibility of the proposed approach in real disasters, a validation scenario considering the critical issues and details in a victim detection task is illustrated, and then appropriate techniques, which will be utilized in the proposed VDP, and its justifications are discussed. Finally, the authors debate how the techniques are harmonized in the VDP and what the challenges are. Currently, public vehicles such as taxies are commonly equipped with single-frequency global positioning system (GPS) data loggers that record the vehicle trajectories. The GPS trajectory data can be used as low-cost sensors to reflect the dynamics of urban traffic status and used to improve the urban design. In the contribution by Liu et al7 “Data analysis and mining of traffic features based on taxi GPS trajectories: a case study in Beijing,” authors analyze the traffic features in Beijing by mining taxi GPS trajectories. The authors analyze the traffic features specifically for Beijing based on the taxi GPS trajectories. For each taxi trajectory, first, the authors define the congestion coefficient as the metric for reflecting the state of traffic congestion. Then, based on the calculated congestion coefficients of all taxi trajectories on working days and on the weekend, the authors analyze the relationship between the distribution of congestion coefficients and traffic congestion. Furthermore, the authors evaluate the influence of the congestion coefficients on the number of served taxies. The findings can be used to improve urban traffic performance. By analyzing the distribution of congestion coefficients of all taxi trajectories, the authors could make following conclusions. On working days, (i) the congestion coefficient is between 0 and 2 (average speed is greater than 0.5 m/s) and is acceptable to taxi drivers, (ii) the morning rush hours are 7:00 to 10:00, (iii) the evening rush hours are 17:00 to 20:00, and (iv) the traffic congestion in the morning rush hours is worse than that in the evening rush hours. On the weekend, (i) the congestion coefficient is less than 0.2 (average speed is greater than 5 m/s) and is acceptable to taxi drivers, (ii) compared with the traffic congestion on working days, there are no significant morning rush hours on the weekend, and (iii) the period of the time between 13:00 and 15:00 could be considered the traffic rush hours on the weekend. These research findings can be used to improve urban traffic management. The articles presented in this special issue provide insights in fields related to IoT: Applications and Future Works, including models, performance evaluation and improvements, and application developments. We wish the readers can benefit from insights of these articles and contribute to these rapidly growing areas. We also hope that this special issue would shed light on major developments in the area of Concurrency and Computation: Practice and Experience and attract attention by the scientific community to pursue further investigations leading to the rapid implementation of these technologies. The authors would like to express our appreciation to all the authors for their informative contributions and the reviewers for their support and constructive critiques in making this special issue possible. Finally, they would like to express our sincere gratitude to Professor Geoffrey Fox, the Editor in Chief, for providing us with this unique opportunity to present our works in the international journal of Concurrency and Computation: Practice and Experience.

Summary In the last decade, artificial intelligent systems based on neural networks have gradually become primary source for clinical decision support systems (CDSS) and are being used in diverse areas of medical diagnosis, classification, and prediction. An artificial neural network (ANN) consists of a large number of processing units which performs the computation in a parallel and distributed environment. They learn the pattern from the examples provided to it and then generalize based on the concepts they have learned while training. This paper presents a review of the current status of ANN and its variants as CDSS in various medical disciplines. The work focuses and describes the methods making use of simple ANN and use of real‐time approaches based on big data using ANN in cloud computing environment for various medical applications. Critical analysis of various methods based on smart approaches indicates that feed‐forward back propagation ANN performs sufficiently better in the domain of medicines with a high degree of accuracy.

Summary Deep learning based neural networks and their variants have gained popularity due to their inherent flexibility to handle unforeseen especially when a chaotic time series big data are required to be dealt with. There are innumerable applications that are beneficiary of vast interest in computational intelligent approaches that include but not limited to robotics, healthcare, transport, industrial, decision making, and gaming. This paper attempts to investigate the effectiveness of using a neural nonlinear autoregressive with exogenous inputs (NARX) controller in an emerging application field of balancing systems like inverted pendulum (IP) using big data. This paper's aim has been to control an IP cart system by designing a neural NARX controller, and the focus is primarily on real‐time processing in industrial applications grounded on big data ecosystems. In the proposed work, an IP system is mathematically modeled and first controlled utilizing a combination of classical proportional‐integral‐derivative (PID) controllers for cart and pendulum. Second, a chaotic time series input–output data are obtained and are used to train two NARX controllers for cart and pendulum, respectively. Both the controllers are designed as single‐input single‐output systems with one layer each at input and output with suitable number of hidden layers and neurons. Performance comparison of NARX system behavior with PID controller indicates that the NARX controllers successfully adapt to two different kinds of unknown inputs and effectively stabilize the plant. Simulation results confirm that NARX controllers follow the training parameters and exhibit superior performance and overall system stability than PID control. Experimental results demonstrate the effectiveness of the approach.

Summary The International Telecommunications Union defines in its IMT‐2020 recommendations three types of use of 5G services: mMTC (massive Machine‐type Communications), eMBB (enhanced Mobile Broadband), and uRLLC (ultra‐Reliable Low Latency Communications). The mMTC service allows a considerable number of machines and devices to communicate while guaranteeing a good quality of service. The eMBB service allows very high data throughput, even at the cell border. The uRLLC service is used for ultra‐reliable communication for critical needs requiring very low latency. These services are provided separately in a given cell. However, the number of connected objects is starting to increase rapidly as well as the bit rates and energy consumption. The 5G network must make it possible to provide access to a vast number of users of its different service categories. Call admission control (CAC) techniques focus more on availability in terms of bit rate and coverage. In this article, we suggest an algorithm for modeling CAC in an area served by the three categories of services in a 5G access network, mainly based on minimum energy consumption. This technique will allow connected objects that consume low energy to connect to the network with an adequate quality of service and enable the development of the Internet of Things.

Summary The northwest region in China located at arid and semiarid areas, atmospheric precipitation converted by the cloud is an important part of water resources, and if we fully utilize cloud for cloud‐water conversion to alleviate the scarcity of water, thereby it is particularly important to analyze the macroscopic characteristics and the changing trends of clouds in the northwest region. In this paper, the 2016 Level 1 data of Fengyun Satellite has been calibrated, corrected, and processed, using the improved multi‐spectral thresholding method to calculate cloud coverage and cloud classification data. The optical thickness inversion uses the SBDART (Santa Barbara DISORT Atmospheric Radiative Transfer) radiation transmission mode to establish a radiation look‐up table with optical thickness as a function variable under different conditions of observation geometry, underlying surface type, and atmospheric environment. The results show that the coverage of clouds in the northwest region accounts for about 45%, and the cloud coverage changes with the seasons. The classification of clouds mainly consists of high clouds, low clouds, and cumulonimbus. The optical thickness of clouds is largely distributed between 10 and 25.

Advancement in the Internet of Medical Things (IoMT), along with machine learning, deep learning, and artificial intelligence techniques, initiated a world of possibilities in healthcare. It has an extensive range of applications: when connected to the Internet, ordinary medical devices and sensors can collect valuable data, deep learning, and artificial intelligence techniques utilize this data and give an insight of symptoms, trends and enable remote care. Recently, Covid-19 pandemic outbreak caused the death of a large number of people. This virus has infected millions of people, and still, the rate of infected people is increasing day by day. Researchers are endeavoring to utilize medical images and deep learning-based models for the detection of Covid-19. Various techniques have been presented that utilize X-Ray images of the chest for the detection of Covid-19. However, the importance of regional-based convolutional neural networks (CNNs) is currently confined. Thus, this research aimed to introduce an IoT-based deep learning framework for early assessment of Covid-19. This framework can reduce the working pressure of medical experts/radiologists and contribute to the pandemic control. A deep learning-based model, i.e., faster regions with CNNs (Faster-RCNN) with ResNet-101, is applied on X-Ray images of the chest for Covid-19 detection. It uses region proposal network (RPN) to perform detection. By employing the model, we achieve a detection accuracy of 98%. Therefore, we believe that the system might be capable in order to assist medical expert/radiologist, to verify early assessment toward Covid-19.

The Internet of Things (IoT) widely supports the smart healthcare field; combined with computer vision, machine, and deep learning techniques; it provides fast and accurate services for automated patient discomfort monitoring/detection systems. Traditional patient monitoring systems are commonly composed of wearable sensors and vision-based methods. In this article, an IoT-based noninvasive automated patient's discomfort monitoring/detection system is presented and implemented, using a deep-learning-based algorithm. The system is based on an IP camera device; the patient's body's movement and posture are detected without using any wearable devices. The Mask-RCNN method is employed for the extraction of different key points on the patient body. These detected key points are then transformed into six major body organs using association rules of data mining. Furthermore, for analyzing the patient's discomfort, detected key point coordinates information is measured. Finally, the distance and the temporal threshold are applied to classify movements as either associated with normal or discomfort conditions. These key points information is also used to determine the postures of the patient lying on the bed. The patient's body position and posture are continuously monitored, based on which comfort and discomfort level are discriminated. For experimental evaluation, different video sequences are recorded covering two patient's beds. The experimental results show the proposed system's worth by achieving a true-positive rate of 94% and a false-positive rate of 7%.

The industrial Internet of Things (IIoT) has the potential to transform several industries. However, reliable data collection, processing, and analytics cannot be performed if the underlying cloud storage is not trustworthy. The current IIoT architectures tend to adopt cloud computing as a backbone for their implementation and further deployment. Therefore, the trustworthiness of the cloud storage is of paramount importance for the design of efficient and reliable IIoT. This becomes very challenging if the data storage is outsourced to a third party, which may raise many problems such as noncompliance to service-level agreement, data theft, and privacy issues. Mobile agents have a number of characteristics including mobility, lightweight, autonomous, reactive, and intelligent making them ideal for deployment in many distributed applications. Therefore, in this article, we propose a multiagent-based approach to address the geolocation assurance problem of the outsourced data in the context of IIoT. As a result, we achieve efficient geolocation assurance with manageable costs without the need of a trusted third party.

Internet of connected vehicles (IoCV) is one of the popular subclasses of vehicle ad hoc networks and an up-rising form based on new Internet, 5G, cloud, and edge computing features. The vehicle nodes in such networks can exchange the information with other nodes with the help of infrastructure or without prior infrastructure. For efficient data communication among the vehicle nodes, the routing protocols play a significant role and able to handle the different network characteristics including high mobility, dynamic topologies, and disconnected links. To address the existing routing protocol issues including data delay, disconnection, interference, scalability, and overhead, this paper presents the Intersection Gateway and Connectivity based Routing (IGCR) protocol for IoCV networks. The proposed protocol uses important traffic-aware routing metrics, including traffic density and direction of nodes towards the destination for route and next forwarder node selection. The experimental results indicated that the proposed protocol well-behaved and showing better performance compared to the state of the art routing protocols in terms of data delivery, data delay, and data throughput.

New integrated technologies have changed various existing fields and converted into new and advanced data communication systems including, smart agriculture, smart homes, smart health, and smart transportation systems. Internet of Things (IoT) has evolved a new theme to vehicular networks field known as the Internet of Vehicles (IoV). This paper presents a comprehensive review and detailed background and motivation to evolve the heterogeneous vehicular networks. Paper also proposed new integrated models and key technologies related to network maintenance, a six-layered architecture model based on protocol stack and network elements, network model based on cloud services, big data analytical model based on data acquisition and analytics, security model based on detection and prevention systems. Paper also envisioned existing challenges and future directions to design the new integrated models.

Introduction to the Special Section on Data Science for Cyber-Physical Systems

The dramatically development of wireless technologies in the last few decades, leads to the growth of channel resources demand in a limited spectrum with inextensible character. Cognitive radio network (CR) is a promising technology that provides solutions for the spectrum management and optimization problems via dynamic spectrum management. The spectrum resources management and optimization are an important part of the future network performances. In this paper, we propose an efficient algorithm to examine the design specification issues regarding the choice of optimal power, optimal speed, and optimal amount of information in a wireless network along with studying the effect of different parameters on the obtained results. Our objectives are to guarantee the protection on licensed users (Primary users ‘PU’) from harmful interference caused by the unlicensed users (Secondary users ‘SU’), more especially, to optimize the quality of communication link, Transmission levels, and battery life of the wireless devices. Results show that our proposed work leads to an efficient utilization of radio spectrum and strongly contributes to alleviating the spectrum scarcity problem.

New generations of mobile telephony succeed every decade, each bringing an evolution or even a revolution. Nowadays, the Internet of Things and the tactile Internet are starting to grow, and 5G technology is there to enable these services. 5G technology has introduced three types of services, namely eMBB (for services requiring very high bit rates), mMTC (for massive connection of user equipment), and uRLLC (for critical services requiring very high reliability and extremely reduced latency). In this paper, we have dealt with some issues encountered by uRLLC services for tactile Internet services. In this article, we have studied the transmission of very small packets as required by the 5G uRLLC services. We also examined the probability of transmission error and its variation concerning the transmission delay and the length of the packet transmitted. This study was conducted considering its application in the Tactile Internet.

Summary Industry and medical imaging are technologies and processes of managing subjective representations of the industry product, interior of a body for analyzing. The deinterlacing is the procedure of transforming interlaced signal into progressive one. In this paper, I propose a new single field deinterlacing method which has three sub‐methods: bilinear method, small filter‐based method, and large filter‐based method. Pixels in a given image are grouped into three regions by calculated local mean and variance values: stable region, neutral region, and complex region. To implement deinterlacing process, I use weight average filter by considering two factors (the likeness factor and the distance factor) and determine region characteristics. Simulation results inform that the presented method yields satisfactory results in objective metrics (PSNR, SSIM, implementation time) and subjective quality.

Computational Intelligence techniques are adopted in many industrial applications, like visual-based quality control, image enhancement in consumer electronics, image quality enhancement, video-based recognition of identity or behaviors, audio-based speech recognition for enhanced human like interaction with machines, and so on.It also has a strong impact in medical applications, like medical image enhancement, semiautomatic detection of pathologies, prefiltering and reconstruction of volumes from medical scans, and so on.Despite this growing diffusion, there are still many possible areas where computational intelligence application is partial or could be extended and improved due to the actual limitations in terms of computational power or strict requirements in terms of assurance of the results. THEMES OF THIS SPECIAL ISSUEStarting from the above considerations, this special issue aims to investigate the impact of the adoption of advanced and innovative Computational Intelligence techniques in industrial and medical applications including the ones that takes advantage of recent Big Data Architectures.This edition of the special issue is focused primarily on signal processing for industrial and medical applications with special emphasis to stream processing and Big Data platforms.This issue is intended to provide a highly recognized international forum to present recent advances in Concurrency and Computation: Practice and Experience.We welcomed both theoretical contributions as well as articles describing interesting applications.Articles were invited for this special issue considering aspects of this problem, including:• Imaging for industrial applications.

Summary Medical image fusion is a technology of combining multi‐modal images to generate a composite image, which is favorable to improve the capability of doctors in diagnosis and treatment of the disease. In order to achieve good performance, a fusion method by combining Laplacian pyramid (LP) and convolutional sparse representation (CSR) is proposed. In the proposed fusion method, LP transform is performed on each pair of pre‐registered computed tomography image and magnetic resonance image to obtain their detail layers and base layer. Then, the base layer is fused with a CSR‐based approach, whereas the detail layers are merged using the popular “max‐absolute” rule. Finally, the fused image is reconstructed by performing the inverse LP transform over the fused base layer and detail layers. The advantages of our method are that the texture detail information contained in source images can be fully extracted and the overall contrast of the final fused image will not be decreased. Experimental results demonstrate the superiority of the proposed method.

Summary Doctors always desire high‐resolution medical images to have accurate diagnosis. Super‐resolution (SR) is a technology that can improve the resolution of medical images. Convolutional neural network (CNN)–based SR methods have achieved desired performance in natural images. In this paper, we apply a deep dense SR (DDSR) convolutional neural networks model to two types of medical images, including Computerized Tomography (CT) images and Magnetic Resonance imaging (MRI) images. This network densely connects every hidden layer to learn high‐level features, which was first proposed for object recognition. A set of medical images is used for experiments. We compare the performance of DDSR with three state‐of‐the‐art SR network models, including SR Convolutional Neural Network (SRCNN), Fast SR Convolutional Neural Network (FSRCNN), and Very Deep SR Convolutional Neural Network (VDSR). Both the objective indices and subjective evaluations are used for comparison. The results show that the proposed network has better performances both on CT and MRI images.

In recent years, data security becomes a critical issue restricting the wider acceptance of Internet of Things (IoT) devices and Cyber-physical systems since they have limited hardware resources and power supply while high data security protection requires relatively large hardware resources and power supply utilization. This contradiction is particularly prominent in the field of Wireless Body Area Networks (WBANs) which is a segment of the IoT field. WBANs are dedicated to transmit and process biomedical data collected from human beings, any kind of tampering or hacking may cause severe consequences to users. However, the limited computing ability and battery supply of biomedical sensors attached or implanted in the users restrict the security protection strength of the data in WBANs. In this paper, a quantized Logistic mapping-based stream encryption scheme for WBANs is proposed. Meanwhile, Power spectral entropy (PSD) and Peak-to-average Power Ratio (PAPR) analysis of the quantized chaotic sequences have been performed to evaluate the chaotic characteristic among different quantization precision to resolve the ineffectiveness of Lyapunov factor in quantized systems. This encryption scheme utilizes chaotic systems with different quantization precision based on the security requirement of every individual communication, which leads to higher hardware and power efficiency. Finally, the proposed encryption scheme is implemented with VHDL and synthesized using SMIC 60 CMOS technology. The evaluation results illustrate that the proposed encryption scheme has the advantages of high-security performance and high-efficiency hardware resources utilization.

The Internet of Things (IoT), with smart sensors, collects and generates big data streams for a wide range of applications. One of the important applications in this regard is video analytics which includes object detection. It has been considered as an important research area particularly after the development of deep neural networks. We demonstrate the applications, effectiveness, and efficiency of the convolutional neural network algorithms, i.e., Faster-RCNN and Mask-RCNN, to facilitate video analytics in the IoT domain, for overhead view multiple object detection and segmentation. We used the Faster-RCNN and Mask-RCNN models trained on the frontal view data set. To evaluate the performance of both algorithms, we used a newly recorded overhead view data set containing images of different objects having variation in field of view, background, illumination condition, poses, scales, sizes, angles, height, aspect ratio, and camera resolutions. Although the overhead view appearance of an object is significantly different as compared to a frontal view, even then the experimental results show the potential of the deep learning models by achieving the promising results. For Faster-RCNN, we achieved a true-positive rate (TPR) of 94% with a false-positive rate (FPR) of 0.4% for the overhead view images of persons, while for other objects the maximum obtained TPR is 92%. The Mask-RCNN model produced TPR of 93% with FPR of 0.5% for person images and maximum TPR of 92% for other objects. Furthermore, the detailed discussion is made on output results which highlights the challenges and possible future directions.

This article proposes a novel methodology to detect malicious uniform resource locators (URLs) using simulated expert (SE) and knowledge-base system (KBS). The proposed study not only efficiently detects known malicious URLs but also adapts countermeasure against the newly generated malicious URLs. Moreover, this article also explored which lexical features are contributing more in final decision using a factor analysis method, and thus help in avoiding the involvement of human experts. Furthermore, we apply the following state-of-the-art machine learning (ML) algorithms, i.e., naïve Bayes (NB), decision tree (DT), gradient boosted trees (GBT), generalized linear model (GLM), logistic regression (LR), deep learning (DL), and random rest (RF), and evaluate the performance of these algorithms on a large-scale real data set of data-driven Web applications. The experimental results clearly demonstrate the efficiency of NB in the proposed model as NB outperforms when compared to the rest of the aforementioned algorithms in terms of average minimum execution time (i.e., 3 s) and is able to accurately classify the 107 586 URLs with 0.2% error rate and 99.8% accuracy rate.

The advent of cloud computing has radically changed the concept of distributed environments, where services can now be composed and reused at high rates. Today, service composition in the cloud is driven by the need of providing stable QoS, where non-functional properties of composite services are proven over time and composite services continuously adapt to both functional and non-functional changes of the component services. This scenario introduces substantial costs on the cloud providers that go beyond the cost of deploying component services, and require to consider the costs of continuously verifying non-functional properties of composite and component services. In this paper, we propose a cost-effective approach to certification-based cloud service composition. This approach is based, on one side, on a portable certification process for the cloud evaluating non-functional properties of composite services and, on the other side, on a cost-evaluation methodology aimed to produce the service composition that minimizes the total cost paid by the cloud providers, taking into account both deployment and certification/verification costs. Our service composition approach is driven by certificates awarded to single services and by a fuzzy-based cost evaluation methodology, and assumes certified properties as must-have requirements for service selection and composition.

With the development of remote sensing technology, spatial and spectral resolutions of hyperspectral images have become increasingly dense. In order to overcome difficulties in the storage, transmission, and manipulation of hyperspectral images, an effective compression algorithm is requisite. The clustered differential pulse code modulation (C-DPCM), which is a prediction-based hyperspectral image lossless compression algorithm, can achieve a relatively high compression ratio, but its efficiency still requires improvement. This paper presents a parallel implementation of the C-DPCM algorithm on graphics processing units (GPUs) with the compute unified device architecture, which is a parallel computing platform and programming model developed by NVIDIA. Three optimization strategies are utilized to implement the C-DPCM algorithm in parallel, including a version that uses shared memory and registers, a version that employs multistream, and a version that uses multi-GPU. In addition, we studied how to assign all classes to each GPU to minimize the processing time. Finally, we reduced the compression time from approximately half an hour to an hour to several seconds, with almost no loss in accuracy.

An efficient facet-based composite scattering model (FBCSM) is developed for calculating the timeevolving electromagnetic (EM) scattering field (TESF) to study the normalized radar cross section and Doppler spectrum characteristics from dynamic sea surfaces. The dynamic sea surface comprises two-scale profiles: smallscale capillary ripples modulated by large-scale gravity waves, which are modeled by millions of small facets. In microwave bands, two scattering mechanisms, quasi-specular scattering with respect to gravity waves and Bragg scattering with respect to ripples, are taken into account in the FBCSM for computation of the time-evolving EM scattering field under diverse polarizations. However, it may be very time-consuming and difficult to calculate the TESF due to the high resolution and dynamic complexity of the large dynamic sea surface. In this paper, the NVIDIA Tesla K80 graphics processing unit (GPU) with the compute unified device architecture is utilized to improve the computational performance of the TESF. The whole GPU-based TESF computation includes the optimal use of temporary variables, shared memory, constant memory and register, fastmath compiler options, asynchronous data transfer, and the most suitable block size and number of registers. By utilizing the proposed five improvement strategies, a significant speedup of 1200× can be achieved for computation of TESF from large dynamic sea surfaces for microwave bands compared with the single-threaded C program executed on the Intel(R) Core(TM) i5-3450 CPU.

The study of sea clutter reflectivity plays an important role in radar performance evaluations in the military industry. The industrial bodies are trying to apply the sea clutter intelligent processing technology to the radar system with the form of Internet of Things and Industry 4.0. Many sea clutter reflectivity models that have been proposed are difficult to fully adapt to the surrounding seas and different radar systems in China. This article proposes a model named multi-source input neural network (MSINN) sea clutter model using sea clutter collected by ultra high frequency (UHF) radar. In order to prepare sea clutter reflectivity data for training MSINN, the radar continuously collects sea clutter containing various disturbances. In the face of the challenges of preprocessing and storage of measured sea clutter big data, this article proposes a sea clutter preprocessing scheme based on yolov3-tiny model. Experimental results show that the average detection precision of test sea clutter Range-Pulse (RP) images is 75.3% and the effective region extraction time of sea clutter RP image is 0.003642 s, which can meet the requirement of real-time detection and data requirement of predicting sea clutter reflectivity based on MSINN. Compared with the traditional empirical model, the average prediction error of sea clutter reflectivity based on MSINN is 1.82 dB, which improves the prediction accuracy and is more suitable for the Yellow Sea in China.

Long distance high bandwidth networks are spanning several continents and many remote Healthcare centers are centralizing their data centers for economic reasons. For the best performance of their data centers, TCP (Transmission Control Protocol) performance and data security are the main critical issues in these network scenarios. TCP performance is directly related to its congestion control mechanism which is responsible for detecting and reacting to the overload traffic on the network. Data security is related to the security mechanism being used by sender and receiver nodes during communication. Linux users, which have rapidly increased in the last five years and most of the Healthcare data centers are being deployed on the Linux operating system, focus the researchers to work on Linux to enhance its performance and security accordingly. The Linux operating system uses TCP CUBIC as a congestion control mechanism with TCP during communication. TCP CUBIC became the default congestion control mechanism of Linux in 2006 after kernel 2.6.18. TCP CUBIC is fundamentally a loss based TCP congestion control mechanism and at each packet loss detection, it reduces its Congestion Window (cwnd) size 20 percent instead of 50 percent as in trademark congestion control mechanism Standard TCP. The aim of this paper is to design a new security mechanism that will work with TCP CUBIC to achieve the maximum possible performance and security over the network link. In this paper, Network Simulator 2 (NS-2) is used to compare the performance of TCP CUBIC with state-of-the-art mechanisms in long and short Round Trip Time (RTT), high bandwidth network scenarios. Results show that when new security mechanism is used with TCP CUBIC, overall better performance in the form of protocol fairness, TCP friendliness, goodput, and convergence time is achieved over the network link.

Recent advances in image super-resolution (SR) explored the power of deep learning to achieve a better reconstruction performance. However, the feedback mechanism, which commonly exists in human visual system, has not been fully exploited in existing deep learning based image SR methods. In this paper, we propose an image super-resolution feedback network (SRFBN) to refine low-level representations with high-level information. Specifically, we use hidden states in a recurrent neural network (RNN) with constraints to achieve such feedback manner. A feedback block is designed to handle the feedback connections and to generate powerful high-level representations. The proposed SRFBN comes with a strong early reconstruction ability and can create the final high-resolution image step by step. In addition, we introduce a curriculum learning strategy to make the network well suitable for more complicated tasks, where the low-resolution images are corrupted by multiple types of degradation. Extensive experimental results demonstrate the superiority of the proposed SRFBN in comparison with the state-of-the-art methods. Code is avaliable at https://github.com/Paper99/SRFBN_CVPR19.

A rapid development has been seen in the Vehicular ad hoc networks (VANETs) because of their applicability and significance in the fields of traffic management, road monitoring and safety, infotainment, and on-demand services. Route planning in vehicular networks based on efficient collection of real-time data can effectively mitigate traffic congestion problems in urban areas. Furthermore, real-time data is shared by using an effective sharing mechanism to avoid redundancy of the collected information. However, dynamic route replanning and effective sharing mechanisms based on real-time data are still challenging problems. Therefore, based on the aforementioned constraints, this paper describes a route discovery technique that uses real time data collected from various vehicles using the Internet of Things. The proposed scheme is based on the novel data dissemination technique for information sharing among the roadside units. RTRD is comprised of VANETs, vehicular traffic servers, and a 5G-based cellular system of public transportation. By considering the traffic congestion in urban areas, the optimal path is calculated to re-plan routes based on the k shortest path algorithm, and a load balancing technique is adopted to avoid further congestion.

Summary Geo‐related data, also known as spatial data, is represented using a vector used for representing longitude, elevation, and latitude. Specially built systems, well known as Geographical Information Systems (GIS), made use of such data for querying, manipulating, navigation, and analyzing. In the current era of data, science needs to involve smart interactive investigation involving Internet of Data (IoD) on predicting upcoming changes and spatial updates on the map is growing rapidly. To resolve issues concerning real‐time spatial data, transformation using semantic annotation can provide a better way to translate spatial relationships. These spatial relationships will support spatial analysis by linking different cause and effect with the help of reasoning mechanism. This research's major focus is on a data transformation methodology for geo‐related semantic annotation. Spatial dataset gets stored in a database and then transformed into Extensible Markup Language (XML) and Resource Description Framework (RDF). Even for bi‐directional transformation to work properly, we need to map different schema level transformations. A deep research is conducted to consider available mappings, implementations, and updates to further improving data fusion for having better compatibility. Then, transformed data as results get analyzed and discussed based on the data mapping rules formulated. It is aimed to show the importance of reducing the response time of investigation and offer compatibility between the web and semantically enriched spatial data.

A top view camera having wide range lens installed overhead of the objects contributes greatly toward resolving the tracking problem and also maintains comprehensive visual access of the environment. Video analytics becoming more important to Internet of Things applications including automatic people monitoring and surveillance systems. We followed an approach based on machine learning features-based person tracking algorithm in industrial environment. The algorithm implements simple motion detection framework through motion blobs. The algorithm, rHOG uses the history of already imaged/blobed population with the anticipated blob position of the person observed. We have compared our results, acquired through five varying test sequences, with established algorithms used for object tracking. The results highlight that our algorithm beats others tracking algorithms by greater margins. The accuracy depicted in our results shows 99% of accuracy compared to the last known best algorithm, the mean shift algorithm, yielding 48% accuracy in result. Furthermore, unlike other blob-based tracking algorithms, our algorithm has additional property to discriminate any blob as a person or no person. Our proposed tracking algorithm has the additional advantage of detecting stationary person for a long time, handling occlusion, abrupt change in the environment, and keeps performing the tracking by compensating for the gaps in data pertaining to all the frames.

With the growth in the consumer electronics industry, it is vital to develop an algorithm for ultrahigh definition products that is more effective and has lower time complexity. Image interpolation, which is based on an autoregressive model, has achieved significant improvements compared with the traditional algorithm with respect to image reconstruction, including a better peak signal-to-noise ratio (PSNR) and improved subjective visual quality of the reconstructed image. However, the time-consuming computation involved has become a bottleneck in those autoregressive algorithms. Because of the high time cost, image autoregressive-based interpolation algorithms are rarely used in industry for actual production. In this study, in order to meet the requirements of real-time reconstruction, we use diverse compute unified device architecture (CUDA) optimization strategies to make full use of the graphics processing unit (GPU) (NVIDIA Tesla K80), including a shared memory and register and multi-GPU optimization. To be more suitable for the GPU-parallel optimization, we modify the training window to obtain a more concise matrix operation. Experimental results show that, while maintaining a high PSNR and subjective visual quality and taking into account the I/O transfer time, our algorithm achieves a high speedup of 147.3 times for a Lena image and 174.8 times for a 720p video, compared to the original single-threaded C CPU code with -O2 compiling optimization.

Load balancing and energy conservation techniques are one of the important constraints in the design of in wireless sensor network (WSN). Usually, clustering technique helps the network in the minimum utilization of energy that results in enhancing network lifetime. Moreover, various nodes in the multihop network that are near to the base station drain their battery very quickly thus result in creating hot spot problem in a network. To overcome such constraints, this paper proposes a multi-layer clustering architecture for selection of forwarding node, rotation of cluster head, and inter and intra-cluster routing communication. The proposed scheme efficiently tackle the rotation of forwarder node by incorporating routing table (table list) at each node. Moreover, the rotation is performed by the consideration of two threshold levels of the residual energy of a node. Also, the exploitation of decision maker node, forwarder node, backup forwarder node, and non-forwarder node enhancing the routing strategy in a network. The performance of the proposed scheme is tested and evaluated by C programming language. The results show that the proposed scheme successful achieve better results than TLPER and EADUC in energy consumption per node, end-to-end communication, hop count in cluster formation.

Recently, a rapid growth in the population in urban regions demands the provision of services and infrastructure. These needs can be come up wit the use of Internet of Things (IoT) devices, such as sensors, actuators, smartphones and smart systems. This leans to building Smart City towards the next generation Super City planning. However, as thousands of IoT devices are interconnecting and communicating with each other over the Internet to establish smart systems, a huge amount of data, termed as Big Data, is being generated. It is a challenging task to integrate IoT services and to process Big Data in an efficient way when aimed at decision making for future Super City. Therefore, to meet such requirements, this paper presents an IoT-based system for next generation Super City planning using Big Data Analytics. Authors have proposed a complete system that includes various types of IoT-based smart systems like smart home, vehicular networking, weather and water system, smart parking, and surveillance objects, etc., for dada generation. An architecture is proposed that includes four tiers/layers i.e., 1) Bottom Tier-1, 2) Intermediate Tier-1, 3) Intermediate Tier 2, and 4) Top Tier that handle data generation and collections, communication, data administration and processing, and data interpretation, respectively. The system implementation model is presented from the generation and collection of data to the decision making. The proposed system is implemented using Hadoop ecosystem with MapReduce programming. The throughput and processing time results show that the proposed Super City planning system is more efficient and scalable.

The Internet of Things (IoT) is increasingly becoming a worldwide network of interconnected things that are uniquely addressable, via standard communication protocols. The use of IoT for continuous monitoring of public health is being rapidly adopted by various countries while generating a massive volume of heterogeneous, multisource, dynamic, and sparse high-velocity data. Handling such an enormous amount of high-speed medical data while integrating, collecting, processing, analyzing, and extracting knowledge constitutes a challenging task. On the other hand, most of the existing IoT devices do not cooperate with one another by using the same medium of communication. For this reason, it is a challenging task to develop healthcare applications for IoT that fulfill all user needs through real-time monitoring of health parameters. Therefore, to address such issues, this article proposed a Hadoop-based intelligent care system (HICS) that demonstrates IoT-based collaborative contextual Big Data sharing among all of the devices in a healthcare system. In particular, the proposed system involves a network architecture with enhanced processing features for data collection generated by millions of connected devices. In the proposed system, various sensors, such as wearable devices, are attached to the human body and measure health parameters and transmit them to a primary mobile device (PMD). The collected data are then forwarded to intelligent building (IB) using the Internet where the data are thoroughly analyzed to identify abnormal and serious health conditions. Intelligent building consists of (1) a Big Data collection unit (used for data collection, filtration, and load balancing); (2) a Hadoop processing unit (HPU) (composed of Hadoop distributed file system (HDFS) and MapReduce); and (3) an analysis and decision unit. The HPU, analysis, and decision unit are equipped with a medical expert system, which reads the sensor data and performs actions in the case of an emergency situation. To demonstrate the feasibility and efficiency of the proposed system, we use publicly available medical sensory datasets and real-time sensor traffic while identifying the serious health conditions of patients by using thresholds, statistical methods, and machine-learning techniques. The results show that the proposed system is very efficient and able to process high-speed WBAN sensory data in real time.

Demosaicking is a digital image process to reconstruct full color digital images from incomplete color samples from an image sensor. It is an unavoidable process for many devices incorporating camera sensor (e.g., mobile phones, tablet, and so on). In this paper, we introduce a new demosaicking algorithm based on polynomial interpolation-based demosaicking. Our method makes three contributions: calculation of error predictors, edge classification based on color differences, and a refinement stage using a weighted sum strategy. Our new predictors are generated on the basis of on the polynomial interpolation, and can be used as a sound alternative to other predictors obtained by bilinear or Laplacian interpolation. In this paper, we show how our predictors can be combined according to the proposed edge classifier. After populating three color channels, a refinement stage is applied to enhance the image quality and reduce demosaicking artifacts. Our experimental results show that the proposed method substantially improves over the existing demosaicking methods in terms of objective performance (CPSNR, S-CIELAB ΔE*, and FSIM), and visual performance.

In this letter, we proposed a new framework for color image demosaicking by using different strategies on green (G) and red/blue (R/B) components. Firstly, for G component, the missing samples are estimated by eight-direction weighted interpolation via exploiting spatial and spectral correlations of neighboring pixels. The G plane can be well reconstructed by considering the joint contribution of pre-estimations along eight interpolation directions with different weighting factors. Secondly, we estimate R/B components using guided filter with the reconstructed G plane as guidance image. Simulation results verify that, the proposed framework performs better than state-of-the-art demosaicking methods in term of color peak signal-to-noise ratio (CPSNR) and feature similarity index measure (FSIM), as well as higher visual quality.

This paper presents a novel multidirectional weighted interpolation algorithm for color filter array interpolation. Our proposed method has two contributions to demosaicking. First, different from conventional interpolation methods based on two directions or four directions, the proposed method exploits to greater degree correlations among neighboring pixels along eight directions to improve the interpolation performance. Second, we propose an efficient postprocessing method to reduce interpolation artifacts based on the color difference planes. Compared with conventional state-of-the-art demosaicking algorithms, our experimental results show the proposed algorithm provides superior performance in both objective and subjective image quality. Furthermore, this implementation has moderate computational complexity.

In this paper, we present a novel color image demosaicking algorithm using a voting-based edge direction detection method and a directional weighted interpolation method. By introducing the voting strategy, the interpolation direction of the center missing color component can be determined accurately. Along the determined interpolation direction, the center missing color component is interpolated using the gradient weighted interpolation method by exploring the intra-channel gradient correlation of the neighboring pixels. As compared with the latest demosaicking algorithms, experiments show that the proposed algorithm provides superior performance in terms of both objective and subjective image qualities.

This paper presents a weighted least squares-based intrafield de-interlacing algorithm. First, we formulate the estimation of the missing pixels as a maximum a posteriori (MAP) framework. We deduce the weighted least squares structure from MAP based on the analysis of the statistic model of the original high-resolution images and the associated statistical model of the given low-resolution images and original high-resolution images. The weights affect the estimation of the statistical model. We also design adaptive weights to match regions with different properties. The method is compared with other de-interlacing algorithms in terms of PSNR and SSIM objective quality measures and de-interlacing speed. It was found to provide excellent performance and the best quality-speed tradeoff among the methods studied.

This paper introduces an efficient intra-field deinterlacing algorithm that is based on Taylor series expansion and polynomial regression. In order to estimate the value of an interpolated point using the given data, we rely on a generic local approximation function around this point for estimating the missing data. The well knownN-term Taylor series expansion is regarded as a local representation of the approximation function, and we use polynomial regression to find the optimal local approximation of the function. Instead of estimating the edge orientations as in previous intra-field deinterlacing methods, such as an edge-based line average, we propose an efficient deinterlacing method, which does not consider directional difference measurements that use limited candidate directions. When compared with existing deinterlacing algorithms, the proposed algorithm improves the peak signal-to-noise-ratio while maintaining a high efficiency.

In this paper, we introduce an efficient intra-field deinterlacing algorithm based on moving least squares (MLS). The MLS algorithm has proven successful for approximating scattered data by minimizing a weighted mean-square error norm. In order to estimate the value of the missing point using the given data, we utilize MLS to generate a generic local approximation function about this point. In the MLS method, we adopt trigonometric functions to approximate the local function. This method is compared to other benchmark algorithms in terms of peak signal-to-noise ratio and structural similarity objective quality measures and deinterlacing speed. It was found to provide excellent performance and the best quality-speed tradeoff among the methods studied.

This paper adapts the least-squares luma-chroma demultiplexing (LSLCD) demosaicking method to noisy Bayer color filter array (CFA) images. A model is presented for the noise in white-balanced gamma-corrected CFA images. A method to estimate the noise level in each of the red, green, and blue color channels is then developed. Based on the estimated noise parameters, one of a finite set of configurations adapted to a particular level of noise is selected to demosaic the noisy data. The noise-adaptive demosaicking scheme is called LSLCD with noise estimation (LSLCD-NE). Experimental results demonstrate state-of-the-art performance over a wide range of noise levels, with low computational complexity. Many results with several algorithms, noise levels, and images are presented on our companion web site along with software to allow reproduction of our results.

Recently automatic video surveillance in the digital video recording CCTV system is rapidly becoming one of the most accepted security system. The dangerous situations such as forest fire, flood, and terrorism are increasing, and cause serious casualty and property loss. In this paper, we particularly focus on the fire detection system in video. The proposed block-based fire detection algorithm consists of three basic steps. In the first step, we find motion vector utilizing optical flow and distinguish the suspect as fire region. In the second step, we conduct chromatic detection based on Lab color space. In the final step, we employ motion information for detecting the correct fire block by using the characteristics that fire goes almost upward. Experimental results show that the proposed method yields good performance for fire detection.

This paper proposes an efficient intra-field deinterlacing algorithms using local adaptive rational interpolation filter (LARF). Experimental results show that the proposed algorithm provides satisfied performances in terms of both objective and subjective image qualities. What is more, it just exploits the local spatial gradient information among the neighboring pixels without complex preset-conditions which has lower complexity than most of the existing algorithms.

This paper addresses the problem of interpolating missing color components at the output of a Bayer color filter array (CFA), a process known as demosaicking. A luma-chroma demultiplexing algorithm is presented in detail, using a least-squares design methodology for the required bandpass filters. A systematic study of objective demosaicking performance and system complexity is carried out, and several system configurations are recommended. The method is compared with other benchmark algorithms in terms of CPSNR and S-CIELAB ∆E∗ objective quality measures and demosaicking speed. It was found to provide excellent performance and the best quality-speed tradeoff among the methods studied.

This paper investigates a new interpolation technique based on content adaptive interpolation with fuzzy reasoning. The proposed technique reduces image artifacts in regions where moving object cannot be well traced by motion estimation. Our proposed method consists of two parts: content classification and fuzzy weight assignment process. The spatial deinterlacing methods have been studied excessively in literature. The edge based line average method yields relatively good performance with low complexity. On the basis of the above method, six useful measurements are obtained within the 5-by-3 spatial window to prevent false edge direction decisions in computing the direction where the interpolation is to be operated. The simulation results indicate that the developed method can generate high quality intra-interpolation picture for interlaced images.

This paper considers the LDPC-based Slepian-Wolf coding with decoder side information. The paper analyzes the statistical properties of LDPC syndromes and shows that there are residual redundancies in LDPC syndromes, especially at low rates. Furthermore, this paper proposes a rate-adaptive way to compress LDPC syndromes.

This paper proposes an improved algorithm of the error-resilient entropy coding (EREC). The idea is to record and transmit the states of variable-length data blocks (VLBs) and fixed-length data slots (FLSs) during EREC encoding process. The state information (SI) of VLBs and FLSs is used at the receiver to resynchronize VLBs during EREC decoding process. It is proved that the cost of SI is fewer than 3 bits per VLB. To combat errors in SI bits, we propose to code SI bits into EREC structure. Experimental results show that our proposed method improves recovery quality of VLC bitstream significantly.

Video deinterlacing can be realized using time-space interpolation filters. To improve video deinterlacing quality with respect to missing pixels on moving diagonal lines, we developed a fuzzy concept that utilizes deinterlacing methods. The proposed algorithm consists of three parts. The first part is fuzzy rule-assisted edge-preserving-based deinterlacing (FED), which has an edge-preserving unit that utilizes fuzzy theory to find the most accurate edge direction and interpolates the missing pixels. Using the introduced gradients in the interpolation, the vertical resolution in the deinterlaced image is subjectively concealed. The second part is weighted fuzzy-reasoning-assisted deinterlacing (WFD), which works in the spatio-temporal domain. In this part, the computed weights are considered and multiplied by the candidate deinterlaced pixels, which successively build approximations of the deinterlaced sequence. The third part of the proposed algorithm is weighted fuzzy switching filtering, which analyzes the suitability of each method on system performance and uses a switching algorithm between FED and WFD. The outcome of image interpolation can be adjusted continuously by varying the setting of the membership function for fuzzy inference. Compared with conventional image interpolation methods, the algorithm presented in this paper provides improved edge quality in the deinterlaced image without the introduction of evident artifacts.

This paper addresses the problem of edge restoration in digital images. Taking advantage of an ensemble approach, multiple type-1 fuzzy filters are combined to reach a decision. The fuzzy logic concept for linguistic variables and possibility theory is discussed with regard to knowledge representation and inference procedures. To improve conventional deinterlacing issues, we adopt type-1 fuzzy set concepts to design a weight-measuring approach. We demonstrate that the fuzzy ensemble approach model is well suited to image processing and provide case studies in the video-deinterlacing field. In our proposed method, five fuzzy membership functions (MFs) of linguistic variable-based fuzzy logic filters are derived from the type-1 (a.k.a. ordinary or primary) fuzzy MF. The weight-measuring process of our proposed model is used to assign weights to six candidate deinterlaced pixels (CDPs) that are interpolated according to edge direction. The use of a different MF for each direction allows the filter to characterize each pixel variation influence independently, according to its direction. The weights from all MFs are multiplied with the CDPs. The results of the empirical trials clearly show that the proposed system can successfully deal with several image types containing motion or detail elements.

In this paper, we propose a new weighted fuzzy filter, which selectively uses spatial and temporal information. The accuracy of the edge direction detection, motion detection, and interpolation is crucial key factors to obtain excellent visual quality in deinterlaced images. The adopted fuzzy concepts are utilized to design a weight-evaluating technique. The weights were considered to be multiplied by the candidate deinterlaced pixels. Experimental results demonstrate that the proposed deinterlacing method performs better than previous techniques.

In this paper, we describe a new spatial domain deinterlacing algorithm which based on the fuzzy weight function. This technique is applied to the issue of missing pixel calculation in video deinterlacing. Traditional edge-based deinterlacing methods became poor at detecting precise edge direction which influences deinterlacing performance. Also, they do not use all edge direction information together but just use only one edge direction. In the proposed algorithm, weights are extracted from luminance difference values and multiplied by the candidate deinterlaced pixels. The extracted weights are worth to be used for proposed method to calculate the edge direction precisely. Compared to the conventional edge-based deinterlacing method, the proposed algorithm provides good visual results in various kinds of edges.

H.264/scalable video coding (SVC) is a new compression technique that can adapt to various network environments and applications. However, despite its outstanding performance, H.264/SVC has considerable complexity burden on decoding, especially in inverse transform and interpolation for motion compensation. We first analyze the Joint Scalable Video Model (JSVM) decoder to identify time-consuming modules of H.264/SVC. Based on the analysis, we present the single instruction multiple data (SIMD) Optimization methods for 4×4 inverse transform and interpolation for motion compensation with an efficient data structure. On a 2.4 GHz Intel Pentium IV processor, the proposed methods reduce considerably the computation time for inverse transform and interpolation for motion compensation, compared to JSVM software.

We considered the problem of resampling video frames to adjust from 176x72 to 352times288 display formats. Images were divided into six regions according to six different edge directions and different reconstruction techniques were employed in each region. The algorithms developed and implemented on this system include edge pattern-based region classifier and resampling strategies for digital display. The performance of the proposed algorithm is compared to conventional methods such as nearest-neighbor interpolation, bilinear interpolation, and simple cubic curve fitting interpolation.

A deinterlacing algorithm that is based on rough set theory is researched and applied. In this paper, rough sets serve as a tool for data analysis and knowledge discovery from test sequences. The proposed deinterlacing approach employs a size reduction of the database system, keeping only the essential information for the process. This approach automatically selects the best deinterlacing approach. Decision making and interpolation results are presented.

This paper proposes a novel fuzzy reasoning interpolation method for video deinterlacing. We propose SMDW and TMDW parameters to measure the amount of entropy in the spatial and temporal domains. The shape of the membership function is designed adaptively according to the parameters, and can be utilized to determine edge direction. Our proposed fuzzy edge direction detector follows three processing steps: fuzzification, rule inference, and defuzzification. This filter operates by identifying small pixel variations in nine orientations (0°, ±30°, ±45°, ±55°, and ±60°) in each domain, and works by using rules to infer the edge direction. Detection and interpolation results are presented. The results of computer simulations show that the proposed method is able to outperform a number of methods in the literature.