ABSTRACT Chronic Kidney Disease (CKD) is a growing global health burden whose late detection leads to costly treatments and long‐term strain on healthcare systems. Early prediction supported by Artificial Intelligence (AI) can contribute to more sustainable healthcare by reducing resource‐intensive interventions such as dialysis and transplantation. This study presents an efficiency‐aware and explainable machine learning framework for CKD prediction using the UCI CKD dataset. Thirteen models including Logistic Regression, SVM, KNN, Decision Tree, Random Forest, XGBoost, LightGBM and CatBoost are evaluated using accuracy, precision, recall, F1‐score, ROC‐AUC, calibration, learning curves and confusion matrices. To align with sustainable and green AI principles, we additionally analyse model complexity and execution time as proxies for computational cost. Explainable AI techniques (SHAP and LIME) are integrated to ensure transparency and support trustworthy clinical deployment. Results show that ensemble models, especially LightGBM, XGBoost and CatBoost, achieve superior predictive performance, whereas LR and LightGBM offer strong trade‐offs between accuracy, interpretability and efficiency. The experimental findings on the UCI CKD dataset indicate that ensemble models attain a performance of up to 100% accuracy, with various classifiers having an accuracy of over 98% with their calibration, interpretability and computational efficiency being high. The proposed framework demonstrates how explainable and energy‐efficient AI can enhance early CKD detection and support sustainable, resource‐conscious healthcare systems.

Online marketplaces offer vast product assortments, presenting consumers with the contradiction of choice, where abundant options delay the discovery of ideal items. While recommendation systems dynamically assist users, they struggle to address changing preferences and challenges such as data sparsity and the cold-start problem. This research proposes an innovative hybrid framework merging granular pattern discovery (GPD) with collaborative filtering (CF) to boost recommendation accuracy. The GPD stage applies techniques including decision trees, sequence mining, data transformations, clustering, and text analytics to heterogeneous user activity logs, extracting detailed behavioral patterns. These granular patterns enrich user profiles, enabling CF to more effectively match users by reducing data sparsity and enhancing prediction accuracy for new users or products with limited historical data. A graph-based algorithm matches consumers with associated preferences through similarity computations between profile vectors, seamlessly integrating neighborhood-based collaboration for personalized product rating predictions. Top-N recommendations are generated by ranking items based on predicted user–item affinity. Extensive testing demonstrates significant improvements over existing methods in key accuracy and ranking metrics, achieving a precision of 0.89 (compared with baseline methods of 0.68 and 0.62), a recall of 0.85, and an F1-score of 0.87. These improvements directly enhance user experience by increasing recommendation relevance and item discoverability, crucial for engagement and conversion in practical e-commerce scenarios. The proposed fusion approach significantly improves adaptability and accuracy, setting the stage for next-generation intelligent recommendation engines responsive to evolving user interests.

ABSTRACT Industrial robotic manipulators are prone to surface wear and damage, leading to unexpected failures and costly downtimes. Early detection of such defects is crucial for enabling predictive maintenance. This study proposes a vision‐based pattern recognition framework that combines convolutional neural networks (CNN) and generative adversarial networks (GANs) to enhance defect detection and tool failure prediction in IoRT‐connected environments. The proposed scheme leverages CNN to extract multi‐scale visual features from raw images of industrial machine components. Convolutional layers are stacked with varying filter sizes to capture fine‐grained surface defects and broader contextual patterns. The pooling layers selectively retain discriminative activations, producing feature embeddings that highlight characteristics such as pitting, scratches, and cracks. This structure allows the network to transform raw pixels into meaningful patterns for reliable classification. To address data scarcity and improve generalisation, the GAN component generates synthetic defect images by simulating real‐world variability, including defect shape, background textures and orientation. The adversarial training between the generator and discriminator enhances the realism and diversity of augmented data, which in turn improves the CNN's robustness. Applied to ball screw drive spindle images, the integrated CNN‐GAN model achieves 96.7% classification accuracy, with 94% precision, 92% recall and 93% AUC. These results support the system's suitability for predictive maintenance and real‐time deployment in smart industrial settings.

Abstract The rapid evolution of electronic media in recent decades has exponentially amplified the propagation of fake news, resulting in widespread confusion and misunderstanding among the masses, especially concerning critical topics like the COVID‐19 pandemic. Consequently, detecting fake news on social media has emerged as a prominent area of research, attracting significant attention. This article introduces a novel cascaded group multi‐head attention (CGMHA) model for COVID‐19 fake news detection. Our research collected Twitter datasets with accurate and fake tweets in Urdu. The novel CGMHA model and depth‐wise convolution capture local and global contextual information by employing multiple attention heads in a cascaded fashion, enabling a comprehensive understanding of fake news. While achieving state‐of‐the‐art performance, we also highlight challenges such as language variations and misinformation nuances in the detection process, contributing to a more comprehensive understanding of the complexities involved in combatting fake news. Our proposed model surpasses the performance of state‐of‐the‐art models in classifying fake news and achieves accuracy, F1 score, precision, and recall of 0.98, 0.96, 0.95, and 0.95, respectively.

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 Cardiovascular disease (CVD) believes to be a major cause of transience and indisposition worldwide. Early diagnosis and timely intervention are critical in preventing the progression of CVD and improving patient outcomes. Machine learning (ML) algorithms have emerged as powerful tools in CVD recognition, with the potential to assist physicians in making accurate and efficient diagnoses. This research paper explores the combination of multiple ML algorithms for CVD recognition, utilizing diverse datasets such as the Cleveland, Hungarian, Switzerland, statlog, and VA Long Beach datasets. Additionally, a CVD dataset comprising 12 attributes and 70,000 records is employed, demonstrating improved results through the proposed and trained model compared to previous prediction techniques for CVD. The performance of various ML techniques, including support vector machines (SVM), naive Bayes (NB), K‐nearest neighbour (KNN), random forest (RF), and logistic regression (LR), is evaluated and compared. The impact of feature selection and feature scaling on the models' performance is also examined. An ensemble bagging technique is applied which is being embedded with other classifiers. LR classifier embedded with bagging techniques proved to be our proposed model. The findings reveal that the proposed Hybrid Linear Regression Bagging Model (HLRBM) outperforms other models. Furthermore, the study highlights the significance of data preprocessing techniques, such as data normalization and class balancing, which significantly enhance the performance of all models. To this end, standard scalar and synthetic minority over‐sampling technique (SMOTE) are employed. The study emphasizes the importance of selecting an appropriate ensemble technique in conjunction with various ML algorithms and preprocessing methods for CVD prediction. Overall, the research provides valuable insights into the potential of ML in improving CVD risk assessment.

Abstract The growing ubiquity of Internet of Things (IoT) devices within smart homes demands the use of advanced strategies in IoT implementation, with an emphasis on energy efficiency and security. The incorporation of Artificial Intelligence (AI) within the IoT framework improves the overall efficiency of the network. An inefficient mechanism of parent selection at the network layer of IoT causes energy drain in the nodes, particularly near the sink node. As a result, nodes die earlier, causing network holes that further increase the control message overhead as well as the energy consumption of the network, compromising network security. This research introduces an AI‐based approach to parent selection of the Routing Protocol for Low Power and Lossy networks (RPL) at the network layer of IoT to enhance security and energy efficiency. A novel objective function, named Energy and Parent Load Objective Function (EA‐EPL), is also proposed that considers the composite metrics, including energy and parent load. Extensive experiments are conducted to assess EA‐EPL against OF0 and MRHOF algorithms. Experimental results show that EA‐EPL outperformed these algorithms in improving energy efficiency, network stability, and packet delivery ratio. The results also demonstrate a significant enhancement in the overall efficiency of IoT networks and increased security in smart home environments.

In today’s fast-paced world, the Internet has become a prevalent source of information for people worldwide. With the increasing use of various applications, people can get updates in real time, making access to information more convenient than ever. However, this easy access to the Internet has also led to the rise of fake news, making it difficult for individuals to differentiate between true and false information. This is where deep learning (DL) comes into play, offering a solution to identify and combat fake news. In this era of technology, DL can be a game-changer in detecting fake news and preventing potential damage to individuals and organizations. A hybrid N-gram and long short-term memory (LSTM) model improves accuracy, recall rate, and computation time, making the fake news detection process more elegant. This proposed model utilizes a classifier to classify fake news. It is based on the parallel and distributed platform, enabling it to build the DL model using big data analytics. This platform improves the training and testing time and enhances the accuracy of the proposed model. The proposed system classifies news into two categories“, fake news” and “real news”, while quantifying the results to develop a system that can detect fake news with high accuracy and a meager mistake rate. Integrating the deep neural network (DNN) and Spark architecture of big data makes the proposed model highly efficient, as demonstrated by the results.

Social media platforms are heavily used by people to express their views in their native languages. Besides positive views, people often use abusive or offensive language to express their anger or frustration. Resource-rich languages have offensive language detection systems which automatically monitor and block offensive content, however, they are very rare for low-resourced languages. This is because of the nonavailability of datasets for local languages. This article proposes a model which automatically detects offensive language for a very low-resource language, i.e., Pashto. The Roman Pashto dataset is created by picking 60 thousand comments from different social media and labeling them manually. The proposed model is trained and tested using three different feature extraction approaches, i.e., bag-of-words (BoW), term frequency-inverse document frequency (TF-IDF), and sequence integer encoding. Four traditional classifiers and a deep sequence model are used to train on this task. Experimental result shows that the random forest classifier works best and give 94.07 % testing accuracy on a combination of unigrams, bigrams, and trigrams. The same classifier gives maximum accuracy of 93.90 % with TF-IDF. However, the overall highest testing accuracy of 97.21% is achieved by using bidirectional long short-term memory (BLSTM). The corpus created in this work is made available for the researcher working in this domain.

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.

In An era where technology advances at an unprecedented pace, the healthcare sector stands at the cusp of a transformative revolution. The confluence of distributed Big Data intelligence with instantaneous e-healthcare services heralds a new paradigm, where the boundaries between medicine, artificial intelligence, and data science are blurred, giving rise to innovative solutions that redefine patient care. The emergence of personalized medicine, bolstered by the power of machine learning, graph-based techniques, and real-time analysis, is not merely a technological triumph but a testament to human ingenuity. It's a response to a world grappling with complex diseases, burgeoning healthcare costs, and an ever-increasing demand for precision and efficiency.

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.

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.

Summary Social networking websites such as Twitter provide a platform where users share their opinions about different news, events, and products. A recent research has identified that 81% of users search online first before purchasing products. Reviews are written in natural language and needs sentiment analysis for opinion extraction. Various approaches have been proposed to perform sentiment classification based on polarity bearing words in reviews such as noun, verb, adverb, and an adjective. Prior researchers have also identified the role of an adverb as a feature. However, impact analysis of adverb forms, are not yet studied and remains an open research area. This study focused on the following tasks: (1) impact of different forms of adverbs that are not studied for sentiment classification; (2) analysis of possible combinations of eight forms that are 255. The different forms are Adverb (RA), Degree Adverbs (RG), Degree Comparative Adverbs (RGR), General Adverbs (RR), General Comparative Adverbs (RRR), Locative Adverbs (RL), Prep. Adverb (RP), and Adverbs of time (RT); (3) comparison with benchmark dataset. Dataset of 5513 tweets is used to evaluate the idea. The findings of this work show that RRR and RR are important polarities bearing words for neutral opinions, RL for positive, and RP for negative opinions.

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 Web scraping is the process of extracting data from web pages and it is an essential part for the generation of datasets. Currently the field is dominated by capable commercial applications, however, there is always a need for web crawling and web scraping applications for custom projects. Developing fit for purpose tools for retrieving and structuring data from web services, cloud systems, and big data is a challenging task. Based on empirical studies, some of the challenges include structural issues, formatting/ presentation, availability, denial of service, size, and information fetching problems with browsers. Additionally, the data become inaccessible after the structure/template of the website changes for example, after the website update. Thus the dataset cannot be updated in the future without manually modifying the parameters of the Web Scraper. In this paper we propose an algorithm capable of autocorrecting the template (web scraping parameters) used for locating the target data and dealing with some common empirical problems. This is very useful in case there is a need for updating the dataset later, as usually, websites tend to change their pages. Moreover, we introduce an implementation of the algorithm via a tool developed for extracting data from the unity asset store. The tool can capture and store data in XML format. The tool extracted a total of 46 785 (40 611 3D and 6174 2D) items, with 35 successful first retries, 11 second retries and 5 fails.

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.

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.

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.

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.

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.

in recent time rapid and extraordinary technological advancement is dominated by the social internet of things (SIoT). SIoT connects people together socially and opens doors to people, to share ideas by using this information. Typically, SIoT deals with the massive amount of data and information. This data is used by various online social networks (ONS), i.e. Twitter, LinkedIn and Facebook etc. analyzing and mining of useful extracted information from these social networks is not an easy task. SIoT has a special interest in numerous research fields, i.e. computer sciences and social sciences. The detection and mining of a community reveal how the structure affects the people and their relationships. In order to facilitate the community discovery, a wide range of tools has been developed over years. Each of them differs from other, in respect of features and benefits. Choosing the right tool is somehow a difficult task. In order to overcome this difficulty, our work offers an analysis by dividing them into various categories such as network platform, algorithm complexity, community detection and their execution time. Finally, we discussed various visualization layouts of social networks which are helpful in order to precise the network data.

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.

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.

Aphasia is a common adult language disorder acquired after a stroke, head injury, tumor, etc. Accurate diagnosis influences the prognosis of any speech and language disorder including aphasia. Therefore, in this paper we have proposed a semi-automated Aphasia diagnosis and classification framework employing feature extraction and pattern matching techniques of the digital signal processing (DSP). The proposed scheme evaluates the acoustic properties, time consumed, and speech characteristics for each language component i.e. naming, repetition, and comprehension. The naming and repetition tasks utilize DSP techniques. The proposed solution is highly scalable since it determines the diagnosis based on acoustic properties instead of the language characteristics. Thus, it eases extending into multiple languages. The mathematical relationships calculate the corresponding score for each component. The framework then determines the diagnosis according to the obtained scores. Since it occupies computational analysis of the speech signals, it reduces the subjectivity of the manual diagnosis process, meanwhile increasing the efficiency and accuracy by consistent diagnosis decisions. Finally, it distinguishes two sub types of Aphasia i.e. Anomic Aphasia and Wernicke's Aphasia. The results clearly revealed the efficiency improvement achieved by replacing the live auditory model with pre-recorded auditory model.

Geosocial Network data can be served as an asset for the authorities to make real-time decisions and future planning by analyzing geosocial media posts. However, there are millions of Geosocial Network users who are producing overwhelming of data, called “Big Data” that is challenging to be analyzed and make real-time decisions. Therefore, in this paper, we proposed an efficient system for exploring Geosocial Networks while harvesting data as well as user's location information. A system architecture is proposed that processes an abundant amount of various social networks' data to monitor Earth events, incidents, medical diseases, user trends, and views to make future real-time decisions and facilitate future planning. The proposed system consists of five layers, i.e., data collection, data processing, application, communication, and data storage. The system deploys Spark at the top of the Hadoop ecosystem in order to run real-time analyses. Twitter and Flickr are analyzed using the proposed architecture in order to identify current events or disasters, such as earthquakes, fires, Ebola virus, and snow. The system is evaluated with respect to efficiency while considering system throughput. We proved that the system has higher throughput and is capable of analyzing massive Geosocial Network data at real-time.

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.

Mobile Cloud Computing (MCC) is a developing technology that assists in improving the quality of the mobile services. Since the increase in mobile resources, the researchers have taken the initiative to take into contemplation resource sharing among heterogeneous mobile devices. Therefore, to design a system architecture for mobility models and resource sharing are key issues that require utmost efforts to be solved to achieve anticipated objectives. Therefore, keeping in view the desired goals, in this paper, we present a system architecture based on the hierarchical resource sharing mechanism for MCC. The proposed system architecture is divided into three domains, such as Global Cloud Server (GCS), Local ISP Server (LIS), and Gateway Server (GWS). Also, the novel paradigm for minimizing the delay in the network based on deploying Foglets at each proposed algorithm of clustering mechanism is also present. Moreover, the fuzzy rule-based scheme is proposed to eliminate the inappropriate foglets before deciding an optimal foglet for handover. A foglet selection scheme is developed based on the Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) decision mechanism. Various parameters such as delay, jitter, Bit Error Rate (BER), packet loss, communication cost, response time, and network load are considered for selecting an optimal network. To check the feasibility and performance of the proposed system architecture, the mobility scenario is considered with a different speed of a mobile node ranging from very high to very low. The simulation results and an analytical model are compared with existing scheme for foglet selection by a mobile node. From the analysis and discussion, it is shown that the proposed system architecture helps in minimizing handover delay, packet loss, average queuing delay, and device lifetime. in a network.

As we delve into the Internet of Things (IoT), we are witnessing the intensive interaction and heterogeneous communication among different devices over the Internet. Consequently, these devices generate a massive volume of Big Data. The potential of these data has been analyzed by the complex network theory, describing a specialized branch, known as 'Human Dynamics.' The potential of these data has been analyzed by the complex network theory, describing a specialized branch, known as 'Human Dynamics.' In this extension, the goal is to describe human behavior in the social area at real-time. These objectives are starting to be practicable through the quantity of data provided by smartphones, social network, and smart cities. These make the environment more intelligent and offer an intelligent space to sense our activities or actions, and the evolution of the ecosystem. To address the aforementioned needs, this paper presents the concept of 'defining human behavior' using Big Data in SIoT by proposing system architecture that processes and analyzes big data in real-time. The proposed architecture consists of three operational domains, i.e., object, SIoT server, application domain. Data from object domain is aggregated at SIoT server domain, where the data is efficiently store and process and intelligently respond to the outer stimuli. The proposed system architecture focuses on the analysis the ecosystem provided by Smart Cities, wearable devices (e.g., body area network) and Big Data to determine the human behaviors as well as human dynamics. Furthermore, the feasibility and efficiency of the proposed system are implemented on Hadoop single node setup on UBUNTU 14.04 LTS coreTMi5 machine with 3.2 GHz processor and 4 GB memory.

The rate of data generation is enormously growing due to the number of internet users and its speed. This increases the possibility of intrusions causing serious financial damage. Detecting the intruders in such high-speed data networks is a challenging task. Therefore, in this paper, we present a high-speed Intrusion Detection System (IDS), capable of working in Big Data environment. The system design contains four layers, consisting of capturing layer, filtration and load balancing layer, processing layer, and the decision-making layer. Nine best parameters are selected for intruder flows classification using FSR and BER, as well as by analyzing the DARPA datasets. Among various machine learning approaches, the proposed system performs well on REPTree and J48 using the proposed features. The system evaluation and comparison results show that the system has better efficiency and accuracy as compare to existing systems with the overall 99.9 % true positive and less than 0.001 % false positive using REPTree.

Internet service providers (ISPs) and telecommunication authorities are interested in detecting VoIP calls either to block illegal commercial VoIP or prioritize the paid users VoIP calls. Signature-based, port-based, and pattern-based VoIP detection techniques are not more accurate and not efficient due to complex security and tunneling mechanisms used by VoIP. Therefore, in this paper, we propose a rule-based generic, robust, and efficient statistical analysis-based solution to identify encrypted, non-encrypted, or tunneled VoIP media (voice) flows using threshold approach. In addition, a system is proposed to efficiently process high-speed real-time network traffic. The accuracy and efficiency evaluation results and the comparative study show that the proposed system outperforms the existing systems with the ability to work in real-time and high-speed Big Data environment.

Machine-to-Machine communication (M2M) is nowadays increasingly becoming a world-wide network of interconnected devices uniquely addressable, via standard communication protocols. The prevalence of M2M is bound to generate a massive volume of heterogeneous, multisource, dynamic, and sparse data, which leads a system towards major computational challenges, such as, analysis, aggregation, and storage. Moreover, a critical problem arises to extract the useful information in an efficient manner from the massive volume of data. Hence, to govern an adequate quality of the analysis, diverse and capacious data needs to be aggregated and fused. Therefore, it is imperative to enhance the computational efficiency for fusing and analyzing the massive volume of data. Therefore, to address these issues, this article proposes an efficient, multidimensional, big data analytical architecture based on the fusion model. The basic concept implicates the division of magnitudes (attributes), i.e., big datasets with complex magnitudes can be altered into smaller data subsets using five levels of the fusion model that can be easily processed by the Hadoop Processing Server, resulting in formalizing the problem of feature extraction applications using earth observatory system, social networking, or networking applications. Moreover, a four-layered network architecture is also proposed that fulfills the basic requirements of the analytical architecture. The feasibility and efficiency of the proposed algorithms used in the fusion model are implemented on Hadoop single-node setup on UBUNTU 14.04 LTS core i5 machine with 3.2GHz processor and 4GB memory. The results show that the proposed system architecture efficiently extracts various features (such as land and sea) from the massive volume of satellite data.

The Machine-to-Machine (M2M) communication has the potential to connect millions of devices in the near future. Since they agree on this potential, several standard organizations need to focus on improved general architecture for M2M communications. Currently, there is a lack of consensus to improve the general feasibility of M2M communication. Heterogeneous Mobile Ad hoc Networks (HetMANETs) can normally be considered appropriate for M2M challenges. When a mobile node (MN) moves inside a HetMANET, various challenges including a selection of the target network and energy efficient scanning take place, which need to be addressed for efficient handover. To cope with these issues, we propose a handover management scheme that efficiently initiates a handover process and selects an optimal network. Our proposed scheme is composed of two phases, i.e., i) the MN performs handover triggering based on the optimization of the Receive Signal Strength (RSS) from an access point/base station (AP/BS), and, ii) the network selection process is carried out by considering different parameters such as delay, jitter, velocity, network load, and energy consumption by the network interface. Moreover, if there are more networks available, then the MN selects the one that can provide the highest quality-of- service (QoS) using the Elimination and Choice Expressing Reality (ELECTRE) decision model. The performance of the proposed scheme is compared in the context of the number of handovers, average stay-time of an MN in the network, and energy consumption against periodic and adaptive scanning. Similarly, a two- state Markov model is defined that efficiently distribute the number nodes on the available access points and base stations. The proposed scheme efficiently optimizes the handoff related parameters and outperforms existing schemes.

A reasonable growth has been noticed in the Web of Things (WoT), in which different embedded devices are inter-connected with each other. These devices are capable of sharing and communicating over the web based application. On the other hand, integration of such devices (capillaries) need a comprehensive architecture, which is still missing. Therefore, this paper proposes the concept of Smart Society; propelling the notion of smart home. In the proposed smart society, we present an architecture for smart society. The proposed smart society consists of three domains, i.e., smart home and smart community, with supportive techniques and related challenges, and visualize of value added smart community. We then describe how to realize a robust networking among individual society. The feasibility and efficiency of the proposed system are implemented on Hadoop single node setup by testing the sample medical, sensory data sets and fire detection datasets. Finally, the results show that the proposed system architecture efficiently process, analyze, and integrates different datasets efficiently and triggers actions to provide safety measurements for elderly age people in smart home, vehicles in smart transportation system, and others.