This paper investigates the Idle Mode Capability (IMC) in heterogeneous cellular networks through a dual approach that combines Monte Carlo-based MATLAB simulations with supervised machine learning prediction. Unlike prior studies that mainly emphasize energy savings, this work provides a broader performance evaluation across urban, suburban, and rural deployments. Using a two-tier network model of macro and pico base stations, we analyze the effects of IMC and its advanced variants—IMC+CoMP (Coordinated Multi-Point), IMC+DSA (Dynamic Spectrum Access), IMC+ABS (Almost Blank Subframes), and IMC_A_BS (Adaptive Base Station Switching)—on key performance indicators including coverage probability, signal-to-interference-plus-noise ratio (SINR), area spectral efficiency (ASE), and energy efficiency (EE). The results demonstrate that baseline IMC improves EE across all deployment types, with the strongest gains in suburban and rural networks, while dense urban scenarios require interference management. When IMC is combined with DSA or adaptive BS switching, coverage exceeds 95% in dense urban layouts, ASE improves by up to 25%, and EE reaches its maximum values. The predictive models, based on decision tree regressors, achieved low root mean square error values (0.0267 for Coverage Probability, 1.1004 for ASE, and 0.041 for EE), validating their robustness in forecasting performance from system parameters. These findings confirm that IMC alone is insufficient for high-density environments, but IMC combined with interference-aware strategies provides a scalable path to greener 5G/6G networks. Future work should validate these predictive insights with real-world IoT traffic traces and mobility-aware models, enabling adaptive and sustainable cellular network planning.

Reliable, privacy-preserving emotion sensing is essential for next-generation IoT applications; however, vision or audio-only pipelines often break down when faces are masked, environments are noisy, or multiple speakers coexist. We present AuraVox, a contactless system that couples millimetre-wave lip micro-Doppler with speech acoustics and fuses them through AuraNet, a bespoke cross-modal transformer. The radar first localizes each talker via MUSIC-based direction-of-arrival estimation and Bartlett beamforming, then captures high-resolution Doppler signatures of lip motion; in parallel, prosodic and spectral speech cues are extracted from a lapel microphone. AuraNet holistically attends to these heterogeneous streams and produces a unified representation for emotion classification. Evaluated on a 30-subject bilingual (English/Mandarin) corpus that includes mask-wearing, multi-speaker overlap, and 30–90 cm ranges, AuraVox attains 96% macro-F1, outperforming radar-only and audio-only baselines by up to eight percentage points. End-to-end latency is 12.8 ms per frame on a 10 W Jetson Xavier NX, meeting real-time constraints for edge deployment. By unifying beamformed lip kinematics with speech cues through AuraNet, AuraVox delivers the first multi-speaker, cross-language, mask-resilient emotion recognizer that runs on commodity hardware. Representative use cases include stress-aware in-cabin driver assistance, hospital check-in triage, and mood-adaptive smart-home interfaces.

The growing use of Internet of Medical Things (IoMT) systems demands accurate sentiment analysis, nuanced emotion tracking, and seamless integration of multimodal data. Current models often struggle when handling heterogeneous sources and evolving emotional patterns. To address these issues, this study proposes QED-Net—a quantum-inspired deep learning architecture designed specifically for IoMT environments. It introduces four modular components. The quantum-driven sentiment amplification (QSA) enhances contextual sentiment interpretation. The temporal emotion evolution graph (TEEG) captures the shifting nature of emotional states over time. The hyperdimensional quantum tensor fusion (HD-QTF) supports synchronized integration of diverse modalities. Finally, the emotion-to-medical ontology encoder (EMOE) translates emotional cues into actionable clinical signals. These components operate both independently and in synergy, allowing for flexible deployment in real-world scenarios. Simulations conducted on benchmark datasets confirm the model’s effectiveness, with QED-Net achieving 93.2% precision in sentiment detection, 92.3% in emotion tracking, and 91.6% robustness in multimodal fusion.

The rapid advancement of next-generation sequencing (NGS) technology and the expanding availability of NGS datasets have led to a significant surge in biomedical research. To better understand the molecular processes, underlying cancer and to support its development, diagnosis, prediction, and therapy; NGS data analysis is crucial. However, the NGS multi-layer omics high-dimensional dataset is highly complex. In recent times, some computational methods have been developed for cancer omics data interpretation. However, various existing methods face challenges in accounting for diverse types of cancer omics data and struggle to effectively extract informative features for the integrated identification of core units. To address these challenges, we proposed a hybrid feature selection (HFS) technique to detect optimal features from multi-layer omics datasets. Subsequently, this study proposes a novel hybrid deep recurrent neural network-based model DOMSCNet to classify stomach cancer. The proposed model was made generic for all four multi-layer omics datasets. To observe the robustness of the DOMSCNet model, the proposed model was validated with eight external datasets. Experimental results showed that the SelectKBest-maximum relevancy minimum redundancy-Boruta (SMB), HFS technique outperformed all other HFS techniques. Across four multi-layer omics datasets and validated datasets, the proposed DOMSCNet model outdid existing classifiers along with other proposed classifiers.

ABSTRACT Due to the recent advancements in high‐speed networks, underlying hardware computing resources and resource scheduling algorithms, Cloud computing has emerged as a popular computing paradigm globally providing end‐user services such as infrastructure, hardware platforms and application tools. Subsequently, the researchers across various domains have integrated different services to facilitate the end users. However, the real issue faced by the cloud infrastructure is the network latency due to the physical dispersion between clients and cloud data centers. According to an estimate, billions of internet of things (IoT) devices are sharing approximately two exabytes of data daily. Such a huge amount of data can affect network performance if the underlying physical system does not expand up to the required levels, leading to performance degradation. To overcome these issues, a new computing paradigm called Fog Computing has emerged in recent years. In this paper, we discuss the recent developments in fog computing with the integration of real‐time Healthcare 5.0 technology. Furthermore, we describe the proposed layered architecture and taxonomy of resource management (RM) techniques in fog computing, which consists of energy awareness, scheduling, reliability and scalability. Besides that, our survey covers the three‐tier layered architecture, evaluation metrics, real‐time application aspects of fog computing and tools providing the implementation of RM techniques in fog computing. Furthermore, the proposed layered architecture of the standard fog framework and different state‐of‐the‐art techniques for utilising the computing resources of fog networks have been covered in this study. Moreover, we include various sensors to demonstrate the fog data offloading example in healthcare 5.0 applications. We also present a thorough discussion on various current and future real‐time applications of fog computing. Finally, open challenges and promising future research directions have been identified and discussed in the area of fog‐based real‐time applications.

ABSTRACT In the context of Cloud and Fog computing settings, recent developments in deep learning techniques show great potential for changing several fields, including healthcare. In this study, we make a contribution to this changing field by proposing an enhanced deep learning‐based strategy for classifying chest X‐ray images, using pre‐trained models such as RetinaNet, EfficientNet and Faster‐R‐CNN, which we use through transfer learning. Our strategy outperforms single models and traditional techniques by leveraging critical data gleaned from multiple models, demonstrating the ability of deep learning to improve diagnostic precision. Our approach presents a novel dual‐check system in the context of worries about security, privacy and trust in Cloud and Fog‐based Smart Systems. In this case, a decision support system uses chest X‐ray images to make an initial diagnosis that is then confirmed by a medical practitioner. This cooperative strategy not only reduces diagnostic errors that come from machine and human sources but also emphasises how crucial it is to incorporate AI‐driven solutions into safe and reliable healthcare ecosystems. Our approach raises the bar for the quality of patient care and healthcare outcomes by overcoming the drawbacks of traditional diagnostic methods that depend on the subjective opinions of physicians. Our work brings out how deep learning might transform clinical diagnostics by distinguishing inflammatory regions in chest X‐ray images. Research is needed to fully grasp the transformative potential of deep learning in medical image processing, especially as the healthcare industry continues to embrace AI‐driven solutions. Further research endeavours have to dig into tactics like broadening the scope of datasets, executing data augmentation methodologies and incorporating bespoken features to augment the elasticity and effectiveness of AI‐driven diagnostic systems.

ABSTRACT Chronic kidney disease (CKD) is a major global health concern caused mostly by high blood pressure and glucose levels. Detecting CKD early is critical for reducing its negative consequences since it can lead to increased mortality rates. With CKD's rising incidence expected to make it the fifth biggest cause of death by 2040, rapid advances in diagnostic approaches are required. This study presents the Reciprocal Domain Adaptation Network (RDAN) as a potential approach to the various issues of CKD diagnosis. RDAN is a neural network model that will help to traverse the complexity of CKD diagnosis by smoothly combining diverse data sets. RDAN consists of two critical units at its foundation: Mutual Model Adaptation (MMA) and Domain Model Learning. The MMA unit uses a powerful Global and Local Pyramid Pooling technique to extract rich features from a variety of data domains. Meanwhile, the DML unit uses semi‐supervised domain‐independent features combined with MMA features to improve representation learning. RDAN includes a reciprocal regularizer to promote cross‐domain knowledge transfer, maximising feature representation for accurate CKD identification. An analysis of RDAN's performance on a variety of real‐world datasets showed remarkable results in terms of accuracy (96.94%), precision (98.81%), recall (98.73%), F1‐Score (98.88%), and area under the curve (AUC—99.35%). These results highlight the unmatched expertise of RDAN in managing data bias, domain changes, and privacy issues related to CKD diagnosis. Beyond statistical measures, RDAN's implications promise revolutionary breakthroughs in early CKD identification and subsequent therapeutic therapies. RDAN stands out as a groundbreaking method for diagnosing CKD. It delivers exceptional accuracy and can be seamlessly applied in various clinical environments.

Abstract Sarcasm detection is challenging in natural language processing (NLP) due to its implicit nature, particularly in low‐resource languages. Despite limited linguistic resources, researchers have focused on detecting sarcasm on social media platforms, leading to the development of specialized algorithms and models tailored for Urdu text. Researchers have significantly improved sarcasm detection accuracy by analysing patterns and linguistic cues unique to the language, thereby advancing NLP capabilities in low‐resource languages and facilitating better communication within diverse online communities. This work introduces UrduSarcasmNet, a novel architecture using cascaded group multi‐head attention, which is an innovative deep‐learning approach that employs cascaded group multi‐head attention techniques to enhance effectiveness. By employing a series of attention heads in a cascading manner, our model captures both local and global contexts, facilitating a more comprehensive understanding of the text. Adding a group attention mechanism enables simultaneous consideration of various sub‐topics within the content, thereby enriching the model's effectiveness. The proposed UrduSarcasmNet approach is validated with the Urdu‐sarcastic‐tweets‐dataset (UST) dataset, which has been curated for this purpose. Our experimental results on the UST dataset show that the proposed UrduSarcasmNet framework outperforms the simple‐attention mechanism and other state‐of‐the‐art models. This research significantly enhances natural language processing (NLP) and provides valuable insights for improving sarcasm recognition tools in low‐resource languages like Urdu.

ABSTRACT Heart disease continues to be a primary cause of mortality globally, highlighting the critical necessity for efficient early prediction and classification techniques. This study presents a new hybrid model attention‐based CNN‐Bi‐LSTM that integrates the SMOTE with an attention‐driven improved convolutional neural network‐recurrent neural network architecture to improve the classification of heart sounds, especially from imbalanced datasets. Heart sounds are difficult to classify because of their complex acoustic properties and the variability of their characteristics across frequency and temporal domains. The proposed model utilises an advanced CNN to effectively extract global and local features, in conjunction with a bidirectional long short‐term memory network to improve the architecture by capturing contextual information from both preceding and subsequent time sequences. The incorporation of spatial attention within the CNN and temporal attention in the RNN enables the model to concentrate on the most pertinent audio segments. To address the challenges presented by imbalanced and noisy datasets that may impede the efficacy of deep learning algorithms, our model employs SMOTE to improve data representation. The hybrid model outperformed popular models such as CNN, LSTM and CNN‐LSTM, achieving a classification accuracy of more than 97% on the PCG and PASCAL heart sound datasets. The findings demonstrate the model's reliability as an initial evaluation tool in clinical settings, thereby improving support for cardiovascular disease diagnosis.

Electrocardiogram (ECG) arrhythmia identification is critical for early cardiovascular disease diagnosis and monitoring in Internet of Things (IoT) industry. Still, it is difficult due to complicated waveforms, individual variability, and the requirement for real-time analysis on resource-limited equipment. Traditional approaches sometimes fail to detect complicated spatial-temporal correlations in ECG data, limiting their efficiency in identifying arrhythmias. Furthermore, deploying these models in tinyML contexts, such as edge and IoT devices limited by large computational and memory needs, emphasizes the importance of lightweight, accurate models for real-time applications. Our suggested solution consists of three main components: SigNet, DualGCNN, and FusionGCNN. SigNet uses Separable Convolution layers to effectively extract local spatial features, making it ideal for IoT-based healthcare deployment. DualGCNN combines dual Graph Convolutional layers with spatial attention, allowing the model to capture local and global dependencies for better classification of arrhythmia. FusionGCNN combines the capabilities of GCN and SigNet with an effective feature fusion technique to improve feature representation while remaining computationally economical. Ablation tests show that FusionGCNN improves performance considerably, with greater accuracy (0.9641), lower training error (0.0004), and a higher F1 Score (0.9645) across a variety of ECG patterns. FusionGCNN, with its low training error, high stability, and computational economy, is well-suited to tinyML requirements, allowing implementation on edge and IoT devices for scalable, real-time ECG monitoring in healthcare.

Summary End‐user feedback in social media platforms, particularly in the app stores, is increasing exponentially with each passing day. Software researchers and vendors started to mine end‐user feedback by proposing text analytics methods and tools to extract useful information for software evolution and maintenance. In addition, research shows that positive feedback and high‐star app ratings attract more users and increase downloads. However, it emerged in the fake review market, where software vendors started incorporating fake reviews against their corresponding applications to improve overall software ratings. For this purpose, we conducted an exploratory study to understand how end‐users register and write fake reviews in the Google Play Store. We curated a research data set containing 68,000 end‐user comments from the Google Play Store and a fake review generator, that is, the Testimonial generator (TG). Its purpose is to understand fake reviews on these platforms and identify the common patterns potential end‐users and professionals use to report fake reviews by critically analyzing the end‐user feedback. We conducted a detailed survey at the University of Science and Technology Bannu, Pakistan, to identify the intelligence and accuracy of crowd‐users in manually identifying fake reviews. In addition, we developed a ground truth to be compared with the results obtained from the automated machine and deep learning (M&DL) classifier experiment. In the survey, 512 end‐users participated and recorded their responses in identifying fake reviews. Finally, various M&DL classifiers are employed to classify and identify end‐user reviews into real and fake to automate the process. Unlike humans, the M&DL classifiers performed well in automatically classifying reviews into real and fake by obtaining much higher accuracy, precision, recall, and f‐measures. The accuracy of manually identifying fake reviews by the crowd‐users is 44.4%. In contrast, the M&DL classifiers obtained an average accuracy of 96%. The experimental results obtained with various M&DL classifiers are encouraging. It is the first step towards identifying fake reviews in the app store by studying its implications in software and requirements engineering.

In the n-tier framework, data generated by the sensors requires immediate execution. The processing elements need powerful resources to entertain incoming requests. Fog computing, unlike cloud computing, provides low latency for real-time applications. However, data generated by the real-time Internet of Things (IoT) devices significantly impacts the fog devices. The data generated must be processed by the fog devices with quick response time, minimum delay, and energy consumption and send it back to the end-users with high reliability and success rate. However, devices fail due to damage or internal state of a fog device which measures incorrectly or causes destruction which badly affects the overall system performance. The end-to-end transmission requests from the IoT devices require immediate response with minimal delay, execution cost, and energy consumption in spite the occurrence of fog devices failure. In this article, we propose a novel energy efficient task scheduling algorithm based on reactive fault tolerance in an n-tier fog computing framework for IoT applications to enhance the overall fog computing performance. In case of fog device failure, the assigned task is rescheduled to other executable fog nodes without further delay. The proposed framework is based on the modified particle swarm optimization and is designed and evaluated in iFogSim. The main objective of the proposed technique is to reduce energy consumption, latency, network bandwidth utilization, and increase system reliability and success rate. Several experiments have been carried out by taking a maximum of ten iterations based on which it is concluded that the proposed technique reduces energy consumption by 3%, latency by 5%, network bandwidth utilization by 3%, and increases the system reliability by 2% and success rate by 8%.

The Hybrid Parallel Fuzzy CNN (HP-FCNN) is a ground-breaking method for medical image analysis that combines the interpretive capacity of fuzzy logic with the capabilities of a convolutional neural network (CNN). This novel combination tackles problems related to brain image processing, reducing problems such as noise and hazy borders that are common in Magnetic Resonance Imaging (MRI). Unlike other CNN models, HP-FCNN combines fine-grained fuzzy representations with crisp CNN features, improving interpretability by displaying hidden layers. This insight into activation patterns facilitates comprehension of the decision-making processes necessary for the diagnosis of brain diseases. HP-FCNN outperforms other pretrained models (ResNet, DenseNet, VGG, and EfficientNet) on measures such as the confusion matrix and AUC-ROC, according to comparative assessments. Furthermore, the addition of Adaptive Class Activation Mapping (AD-CAM) enhances HPFCNN by identifying salient features during backpropagation and bolstering the network's capacity to enhance brain illness diagnosis and treatment planning. Our methodology, incorporating AD-CAM, yielded compelling results with a 96.86 F1-Score, 96.41 AUC, and 96.81 Accuracy, showcasing the effectiveness of our approach in achieving high-performance metrics in brain MRI analysis. With a 15% increase in accuracy, a 10% increase in sensitivity, and a 12% decrease in false positives, HP-FCNN outperforms its predecessors. These impressive advancements represent a quantifiable breakthrough in the capabilities of medical image processing technology; they are more than just anecdotal evidence.

In the realm of machine vision, the convolutional neural network (CNN) is a frequently used and significant deep learning method. It is challenging to comprehend how predictions are formed since the inner workings of CNNs are sometimes seen as a black box. As a result, there has been an increase in interest among AI experts in creating AI systems that are easier to understand. Many strategies have shown promise in improving the interpretability of CNNs, including Class Activation Map (CAM), Grad-CAM, LIME, and other CAM-based approaches. These methods do, however, have certain drawbacks, such as architectural constraints or the requirement for gradient computations. We provide a simple framework termed Adaptive Learning based CAM (Adaptive-CAM) to take advantage of the connection between activation maps and network predictions. This framework includes temporarily masking particular feature maps. According to the Average Drop-Coherence-Complexity (ADCC) metrics, our method outperformed Score-CAM and another CAM-based activation map strategy in Residual Network-based models. With the exception of the VGG16 model, which witnessed a 1.94% decline in performance, the performance improvement spans from 3.78% to 7.72%. Additionally, Adaptive-CAM generates saliency maps that are on par with CAM-based methods and around 153 times superior to other CAM-based methods.

Wireless vision sensor nodes consist of limited resources such as energy, memory, wireless bandwidth and processing. Thus it becomes necessary to investigate lightweight vision tasks. To highlight the foreground objects, many machine vision applications depend on the background subtraction technique. Traditional background subtraction approaches employ recursive and non-recursive techniques and store the whole image in memory. This raises issues like complexity on hardware platform, energy requirements and latency. This work presents a low complexity background subtraction technique for a hardware implemented wireless Vision Sensor Node (VSN). The proposed technique utilizes existing image scaling techniques for scaling down the image. The downscaled image is being stored in internal memory of hardware platform. For subtraction operation, the background pixels are generated in real time with up a scaling technique. The performance, and memory requirements of the system is compared for four image scaling techniques including nearest neighbor, averaging, bilinear, and bicubic. The results show that a system with lightweight scaling techniques, i.e., nearest neighbor and averaging, up to a scaling factor of 8, missed on average less than one object as compared to a system which uses a full original background image. The proposed approach will reduce the memory requirement by a factor of up to 64 besides reduction in design/implementation complexity and cost as compared to background model which involve whole frame.

Wireless Visual Sensor Network (WVSN) is formed by deploying many Visual Sensor Nodes (VSNs) in the field. The VSNs acquire images of the area of interest in the field, perform some local processing on these images and transmit the results using an embedded wireless transceiver. The energy consumption on transmitting the results wirelessly is correlated with the information amount that is being transmitted. The images acquired by the VSNs contain huge amount of data due to many kinds of redundancies in the images. Suitable bi-level image compression standards can efficiently reduce the information amount in images and will thus be effective in reducing the communication energy consumption in the WVSN. But compression capability of the bi-level image compression standards is limited to the underline compression algorithm. Further data reduction can be achieved by detecting Region of Interest (ROI) in the bi-level images and then coding these ROIs using bi-level image compression method. We explored the compression performance of the lossless ROI detection and coding method for various kinds of changes such as different shapes, locations and number of objects in the continuous set of frames. The CCITT Group 4, JBIG2 and Gzip are used for coding the detected ROIs. We concluded that CCITT Group 4 is a better choice for coding the ROIs in the Bi-level images because of its comparatively good compression performance and less computational complexity. This paper is intended to be a resource for the researchers interested in reducing the amount of data in the bi-level images for energy constrained WVSNs.

Wireless vision sensor networks (WVSNs) have a number of wireless vision sensor nodes (VSNs), often spread over a large geographical area. Each node has an image capturing unit, a battery or alternative energy source, a memory unit, a light source, a wireless link, and a processing unit. The challenges associated with WVSNs include low energy consumption, low bandwidth, limited memory, and processing capabilities. In order to meet these challenges, our paper is focused on the exploration of energy-efficient reconfigurable architectures for VSN. In this paper, the design and research challenges associated with the implementation of VSN on different computational platforms, such as microcontroller, field-programmable gate arrays, and server, are explored. In relation to this, the effect on the energy consumption and the design complexity at the node, when the functionality is moved from one platform to another, are analyzed. Based on the implementation of the VSN on embedded platforms, the lifetime of the VSN is predicted using the measured energy values of the platforms for different implementation strategies. The implementation results show that an architecture, where the compressed images after pixel-based operation are transmitted, realize a WVSN system with low energy consumption. Moreover, the complex postprocessing tasks are moved to a server which has less constraints.