Search

This study introduces a reflective polarization converter based on metasurface, designed to offer both Linear-to-Linear polarization (LLP) and Linear-to-Circular polarization (LCP). The design comprises two periodically arranged split ring resonators with a slotted stripe that operate in the X, Ku, and K bands. The three discrete frequency bands demonstrate over 90% Polarization Conversion Rate for LLP for oblique incidence waves up to 45°. Additionally, the proposed converter achieves Left-Hand Circular Polarization (LHCP) in two sub-bands and Right-Hand Circular Polarization (RHCP) in two sub-bands for oblique incidence waves up to 45°. The metasurface design introduced in this study exhibits significant potential for satellite applications in 6G networks, owing to its versatile LLP and LCP conversion properties in the X, Ku, and K bands.

Sentiment analysis (SA) is a popular method for obtaining relevant and subjective information from textual content. Sentiment analysis of multimedia material is helpful for various reasons but it is seen as challenging since the messages are often brief, unstructured, and contain linguistic inconsistencies. Previous research on sentiment analysis usually focused on dual or triple-class analysis while using older language modeling techniques. Furthermore, penta-class classification tasks have not been addressed as much. To deal with the challenge, we present a transformer-based model called BertSent that uses ordered preprocessing steps combined with transformer-based tokenization and optimization to get the best sentiment analysis results focused on dealing with limited data. Moreover, our framework handles the challenge of penta-class classification of tweets, and to that end, we combine many preprocessing techniques to fine-tune our transformer-based model. We employ resampling techniques to address class imbalance issues in the penta-class setup which improves model generalization and performance. For that purpose, we incorporate both over-sampling and under-sampling to tackle the challenge of class imbalance when dealing with the penta-class classification problem. Moreover, this article also compares the performance of the transformer-based model against a variety of deep learning-based models, including bi-directional models. The experimentations and results support our model’s remarkable performance considering the limited data and penta-class classification challenge. The results provide an interesting perspective as both under-sampling and oversampling provide similar results. BertSent model combined with over-sampling provides slightly better performance with 75.3% test accuracy in comparison to under-sampling which resulted in 75.1% accuracy.

With the advancements in space technology and the development of lightweight synthetic aperture radar (SAR) satellites by commercial companies, such as ICEYE, Capella Space and Umbra, SAR images have become available on a wide scale. Ship detection is a classic problem in the interpretation and analysis of satellite images and has its significance both in maritime as well as defense applications. In the case of SAR images, ship detection becomes even more challenging due to the presence of large-scale distortions as well as interclass similarity signature problem. Moreover, the state-of-the-art (SOTA) object detection models have weak generalization capability over SAR datasets. To overcome these challenges, we propose a You Only Look Once (YOLO)-based optimized ship detection model called YOLO-OSD. Our optimized ship detector is based on a hybrid data-model centric approach, which utilizes the statistical characteristics of the datasets under observation and has an efficient model architecture. We also carry out a detailed comparative analysis of our proposed model with other SOTA deep learning models on three well-known publicly available datasets. Our results show that the proposed YOLO-OSD outperforms YOLO5, YOLO7, and RetinaNet on all datasets under observation in terms of F1 score and mean average precision. YOLO-OSD also has approximately 16% fewer network parameters as compared with the original YOLO5. Moreover, our proposed model is at least 37.7% faster than YOLO7 and 41.02% faster than the YOLO8 model in terms of training time and thus suitable for real-time satellite-based SAR ship detection.

Wi-Fi based human activity recognition is emerging and preferable over other approaches due to its numerous advantages, including privacy considerations, ubiquitousness, and easy deployment. While existing literature predominantly focuses on identifying the activities of a single-user, recognizing multi-person interactions (MPIs) is increasingly significant due to their profound social implications. However, research in this area has not progressed due to the limitation of publicly available Wi-Fi datasets and the complexities of MPI recognition. Motivated by this, we develop and publicly release a Wi-Fi channel state information (CSI) based MPI recognition dataset, coined Wi-MIR, that uses three transmit and three receive antennas to capture 270 ( $ {3}\times {3}\times {30}$ ) subcarriers with a sampling rate of 950 Hz. This dataset consists of 3740 trials encompassing seventeen distinct MPIs and is collected by eleven human pairs in an indoor environment. We put forth a lightweight deep learning model with attention mechanisms for MPI recognition from CSI, named CSI-IRNet, that adeptly concentrates on pertinent features, filtering out irrelevant elements, and mitigating the impact of signal complexity within the CSI for recognizing MPIs accurately. In addition, we compare the developed Wi-MIR and the existing public dataset by evaluating the performance of MPI recognition on both datasets to highlight the strengths and advancements provided by Wi-MIR. The evaluation results show that Wi-MIR dataset demonstrates a superior recognition performance by utilizing more subcarriers with a higher sampling rate as well as covering more diverse kinds of MPIs (Bowing, Conversation, Exchanging objects, Helping standup, Helping walk, and Touching another person).

Recent advancements in image processing and computer vision have brought significant transformations in healthcare technology, leading to significant improvements in diagnosis accuracy, cost-effectiveness, and time efficiency. Magnetic Resonance Imaging (MRI) is employed by the radiologist for its remarkable ability to detect even the most subtle brain abnormalities. This study considers a comprehensive analysis of the two prominent object identification frameworks, YOLOv5 and YOLOv7, leveraging state-of-the-art deep learning architectures to classify and detect brain cancers within MRI. The brain tumor dataset encompasses three distinct classes, including meningiomas, gliomas and pituitary tumors. To ensure precise segmentation of the tumor regions, the preprocessing phase incorporates advanced mask alignment techniques. This preprocessed dataset has been used to evaluate the performance of the deep learning models for brain tumor detection and classification. From the numerical results of YOLOv5, it was noticed that a recall score of 0.905 for box detection and 0.906 for mask segmentation, with a precision score of 0.94 and 0.936, respectively. At an IoU threshold of 0.5, both box detection and mask segmentation achieve a mAP of 0.947, whereas, at an IoU threshold of 0.5 to 0.95, they achieve mAPs of 0.666 and 0.657, respectively. In comparison, YOLOv7 exhibits strong performance with box detection accuracy of 0.936 and a mask segmentation accuracy of 0.935. The recall score are 0.904 for box detection and mask segmentation is 0.903. Notably, the mAP result at the IoU threshold of 0.5 are 0.94 for box detection and mask segmentation is 0.941. Over the broader IoU spectrum of 0.5 to 0.95, the mAP was 0.677 for box detection and 0.659 for mask segmentation. To underscore the novelty of the approach, the performance of the proposed framework is systematically compared with established methods such as RCNN, Faster RCNN, and Mask RCNN.

Industry 4.0 is fundamentally based on networked systems. Real-time communication between machines, sensors, devices, and people makes it easier to transmit the data needed to make decisions. Informed decision-making is empowered by the comprehensive insights and analytics made possible by this connectedness in conjunction with information transparency. Industry 4.0-based wireless sensor networks (WSNs) are an integral part of modern industrial operations however, these networks face escalating cybersecurity threats. These networks are always vulnerable to cyber-attacks as they continuously collect data and optimize processes. Increased connections make people more susceptible to cyberattacks, necessitating the use of strong cybersecurity measures to protect sensitive data. This study proposes a predictive framework intended to intelligently prioritize and prevent cybersecurity intrusions on WSNs in Industry 4.0. The proposed framework enhances the cybersecurity of WSNs in Industry 4.0 using a multi-criteria approach. It implements machine-learning and deep-learning algorithms for cybersecurity intrusion detection in WSNs of Industry 4.0 and provides prevention by assigning priorities to the threats based on the situation and nature of the attacks. We implemented three models, i.e., Decision Tree, MLP, and Autoencoder, as proposed algorithms in the framework. For multidimensional classification and detection of cybersecurity intrusions, we implemented Decision Tree and MLP models. For binary classification and detection of cybersecurity intrusions in WSNs of Industry 4.0, we implemented Autoencoder model. Simulation results show that the Decision Tree model provides an accuracy of 99.48%, precision of 99.49%, recall of 99.48%, and F1 score of 99.49% in the detection and classification of cybersecurity intrusions. The MLP model provides an accuracy of 99.52%, precision of 99.5%, recall of 99.5%, and F1 score of 99.5% in the detection and classification of cybersecurity intrusions. The implementation of Autoencoder with binary classification yields an accuracy of 91%, a precision of 92%, a recall of 91%, and an F1 score of 91%. The benchmark models, i.e., Random Forest (RF) for multidimensional classification and Logistic Regression (LR) for binary classification, have also been implemented. We compared the performance of the benchmark models with the models implemented in the proposed framework, revealing that the models in the proposed framework

Smart farming, popularly called precision agriculture, refers to technologies like the Internet of Things (IoT), Artificial Intelligence (AI), and drones that are rapidly transforming age-old farming traditions. This paper investigates how smart farming technologies are revolutionizing the practice of agriculture, specifically focusing on monitoring and control solutions of IoT devices and LoRaWAN networked. Therefore, the implementation of IoT devices would give the farmer access to current readings when needed for making decisions and optimizing their resources on the most important parameters for agricultural activity. And this is where IoT devices come in, making possible precision agriculture techniques with lowered costs by customizing farming practice for each crop or section of land. It means that even the most remote farms will benefit from monitoring and control solutions within LoRaWAN networks. Moreover, low power with long-range wireless connectivity technology devised by LoRaWAN ensures communication and data analysis to be a reliable one within the system. It introduces an intelligent LoRaWAN-based IoT device for the monitoring and controlling solutions with the parameters of performance evaluation, experimental setup, and the dataset used for its analysis. This paper elaborates on anomaly detection through Isolation Forest and proves it for the identification of anomalies in data related to temperature and humidity. Predominantly, the study also indicates precision in the temperature variation prediction model through the use of the predictive model based on the linear regression and random forest algorithms. This improves smart farming practices developed for precision agriculture in terms of efficiency, productivity, and sustainability.

Emergency situations, such as accidents, explosions, or earthquakes, pose significant challenges for healthcare providers as patients arrive at hospitals with little to no prior information about their medical history or treatment. Doctors frequently lack crucial information regarding past hospitalisations, surgeries, any allergies, previous treatments, and medical issues particularly when patients are alone and unable to communicate. Addressing these challenges requires a medical and technical solution that can rapidly access and incorporate a patient’s past medical history while ensuring data privacy and security. By integrating these technologies, our framework not only ensures swift access to critical information but also maintains the highest standards of data privacy and security. To address this issue, we propose a framework that combines federated learning and blockchain technology to facilitate real-time emergency response while incorporating patient historical data. The proposed framework empowers doctors to make informed decisions and deliver personalized care based on a patient’s comprehensive medical history, leading to improved treatment outcomes.

Determining indicators or retinal wounds is essential for accurate diagnosis and retinal disorders grading. To view the retinal microarchitecture and easily screen for anomalies, optical coherence tomography (OCT) images are utilized. Numerous studies have already tried to use OCT to overcome that issue. Throughout this study, we describe an OCT image-based transfer learning (TL) approach for the identification of four retinal diseases. This study compares four distinct models with one another. A MobileNetV2 model’s detection accuracy on the test set is 100%; an InceptionNetV3 model’s is 99.9%; an EfficientNet model’s is 99.38%; and a DenseNet model’s is 99.79%. The InceptionNetV3 model approaches the highest accuracy, while MobileNetV2 model achieves the maximum accuracy. The suggested method may influence the development of a tool for automatically identifying retinal disorders. The promising suggested architecture’s qualitative assessments and quantitative outcomes through creating a confusion matrix demonstrate how the suggested methodology can be utilized in healthcare settings as a diagnostic tool to assist medical professionals in making more accurate diagnoses.

Community detection is a very important research topic in the field of Social Network Analysis. Lots of researchers are working in this field due to its applications in various fields like medicine, social, Business, Marketing, and research. Researchers are proposing new algorithms to detect the communities having better performance as compared to the existing techniques. Initially, Newman and Girvan proposed traditional algorithms for community detection from social networks in 2004, but with the growth of social networks, Convolutional Neural Network (CNN) based algorithms are proposed by different researchers in recent years due to the inefficiency of traditional methods. After reviewing the state-of-the-art algorithms based on CNN learned that MRFasGCN is having the best performance compared to any other state-of-the-art algorithms for large data sets. In this algorithm, researchers have integrated the technique of Graph Convolutional Neural Network (GCN) with the statistical model Markov Random Field (MRF) to get better results and after implementing it on large datasets comparison is done on its results with other state-of-the-art algorithms and got to know its performance is far better than any other algorithm. While MRFasGCN is performing well on social networks and provides ground truth communities, there is a possibility available for improvement due to the sparsity problem. This paper proposes a new algorithm called Modified MRFasGCN. Two modifications are done to the existing algorithm, 1. In pre-processing, rather than passing the adjacency matrix with the normalized adjacency matrix, it will pass the reconstructed adjacency matrix and normalized reconstructed adjacency matrix, which resolves the sparsity problem, 2. GCN layer output will be fed to the MRF layer and refined results will be passed to the Adam optimizer without subtraction. Our experimental analysis shows that the modified algorithm provides better ground truth communities than the MRFasGCN and solves the problem of sparsity as passes a reconstructed adjacency matrix. In this paper, the proposed algorithm is executed on different datasets having different sizes like CORA (2708 Nodes), Flicker (80513 Nodes) and DBLP (317080 Nodes) and compared on different Community Detection metrics like accuracy, NMI, F1 Score, and execution time with other algorithms. After Experiments NMI value for MRFasGCN on DBLP data set is 0.662 while for Modified MRFasGCN it is 0.672, Modified MRFasGCN algorithm provides significant improvement of 2.9% in performance as compared to MRFasGCN. F1-Score of proposed algorithm is 0.511 on DBLP dataset which is better than MRFasGCN.

Alzheimer’s Disease (AD) is characterized by the gradual degeneration and decline of brain cells, leading to irreversible neurological changes. This study investigates advanced image enhancement techniques for improving AD diagnosis using brain MRI. The methods used include CLAHE (Contrast Limited Adaptive Histogram Equalization) to enhance local image contrast and ESRGAN (Enhanced Super-Resolution Generative Adversarial Networks) to improve image resolution. These preprocessing methods improve MRI images and classification accuracy. An ensemble model of MobileNetV2 and DenseNet121, two efficient deep-learning models with feature extraction capabilities, were used as classifiers. This approach addresses challenges in AD diagnosis by leveraging deep learning for more accurate classification of brain tissue images. The model achieved an accuracy of 80.31% for MobileNetV2 and 89.22% for DenseNet121 when no enhancements were utilized. The model achieved accuracies of 92.34% and 89.38% for MobileNetV2 and DenseNet121, respectively, when enhancement methods were utilized, indicating strong dependability with the Kaggle dataset of MRI images. These findings underscore the efficacy of advanced image processing and deep learning in the early and accurate detection of Alzheimer’s disease.

The Internet of Things (IoT) has revolutionized various domains, enabling interconnected devices to communicate and exchange data. The integration of Artificial Intelligence (AI) in IoT systems further enhances their capabilities and potential benefits. Unfortunately, in the era of AI, ensuring the privacy and security of the IoT faces novel and specific challenges. IoT security is imperative, necessitating comprehensive strategies, including comprehension of IoT security challenges, implementation of AI methodologies, adoption of resilient security frameworks, and handling of privacy and ethical concerns to construct dependable and secure IoT systems. It is vital to note that the term ‘security’ encompasses a more comprehensive view than cyberattacks alone. Therefore, with an emphasis on securing against cyberattacks, this comprehensive survey also includes physical security threats on the IoT. It investigates the complexities and solutions for IoT systems, placing particular emphasis on AI-based security techniques. The paper undertakes a categorization of the challenges associated with ensuring IoT security, investigates the utilization of AI in IoT security, presents security frameworks and strategies, underscores privacy and ethical considerations, and provides insights derived from practical case studies. Furthermore, the survey sheds light on emerging trends concerning IoT security in the AI era. This survey provides significant contributions to the understanding of establishing dependable and secure IoT systems through an exhaustive examination of the present condition of IoT security and the ramifications of AI on it.

Fake news, colloquially referred to as false news, exerts a profound influence on fundamental facets of our societal framework. Manual fact verification is a frequently utilized strategy for mitigating the harmful impacts of false news transmission. However, when assessing the massive volume of freshly produced material, manual fact verification is insufficient. Furthermore, the quantity of labeled datasets is limited, people are unreliable annotators, resources are largely in the English language, and they mostly concentrate on articles related to news. Cutting-edge deep learning algorithms are employed to deal with this challenge automatically and address these difficulties. Nevertheless, the large number of models and variability of characteristics utilized in the literature frequently constitute a barrier for researchers attempting to enhance the effectiveness of models. This paper introduces a model designed to address the issue of false news, with a focus on analyzing news headlines. The approach is rooted in a hybrid classification model where our model integrates a BERT architecture, and the outputs are seamlessly linked to bi-directional deep learning layers, including a bi-LSTM layer and a bi-GRU layer. The model’s training and evaluation were conducted using the WELFake dataset, comprising four prevalent news databases. A comparative analysis was carried out using the proposed model and standard classification models. Additionally, standard machine learning and deep learning models along with vanilla BERT were trained on the same dataset with comparable constraints to assess the impact of integrating a bi-directional deep learning layer with BERT. The results revealed an improvement in accuracy, as our proposed model achieved an accuracy of 98.1% and an F1 score of 0.982.

The smart grid relies on Advanced Metering Infrastructure (AMI) to function. Because of the significant packet loss and slow transmission rate of the wireless connection between smart meters in AMI, these infrastructures are considered Low-power and Lossy Networks (LLNs). The routing protocol in an AMI network is crucial for ensuring the availability and timeliness of data transfer. IPv6 Routing Protocol for Low-power and lossy networks (RPL) is an excellent routing option for the AMI communication configuration. However, it is highly at risk against many external and internal attacks, and its effectiveness may be severely diminished by Sybil assault. Different trust-based techniques have been suggested to mitigate internal attacks. However, existing trust systems have high energy consumption issues, which cause a reduction in the performance of LLNs due to complex calculations at the node level. Therefore, this paper presents a novel fog-enabled GINI index-based trust mechanism (GITM) to mitigate Sybil attacks using the forwarding behavior of legitimate member nodes. Regarding identifying and isolating Sybil assaults, our approach outperforms the state-of-the-art methods. GITM detects and isolates a more significant number of malicious network nodes compared to other techniques within a similar time frame. By using the proposed GITM framework, the Sybil attack detection rate increases by 4.48%, energy consumption reduces by 21%, and isolation latency reduces by 26.30% (concerning time). Furthermore, the end-to-end delay is merely 0.30% more in our case, and the number of control messages decreases by 28%.

Presents corrections to the paper, (Corrections to ‘‘Securing the Internet of Things in Artificial Intelligence Era: A Comprehensive Survey’’).

Predicting heart disease is regarded as one of the most difficult challenges in the health-care profession. To predict cardiac disease, researchers employed a variety of algorithms including LDA, RF, GBC, DT, SVM, and KNN, as well as the feature selection algorithm sequential feature selection. For verification, the system employs the K-fold cross-validation approach. These six strategies were used to conduct the comparative study. The Dataset for Cleveland, Hungray, Switzerland, and Long Beach V, as well as the Dataset Heart Statlog Cleveland Hungary, were used to assess the models performance. For both Hungary, Switzerland & Long Beach V and Heart Statlog Cleveland Hungary Dataset, Random Forest Classifier sfs and Decision Tree Classifier sfs produced the highest and almost identical accuracy values (100%, 99.40% and 100%, 99.76% respectively). The findings were compared to previous research that focused on cardiac prediction. In the future, we hope to extend the model even further so that it may be used with various feature selection techniques; another possibility is to use a random forest classifier. The major goal of this study is to improve on previous work by developing a new and unique technique for creating the model, as well as to make the model relevant and easy to use in real-world situations.

Hand gesture is a visual input of human-computer interaction for providing different applications in smart homes, healthcare, and eldercare. Most deep learning-based techniques adopt standard convolution neural networks (CNNs) which require a large number of model parameters with high computational complexity; thus, it is not suitable for application in devices with limited computational resources. However, fewer model parameters can reduce the system accuracy. To address this challenge, we propose a lightweight heterogeneous deep learning-based gesture recognition system, coined CSI-DeepNet. The CSI-DeepNet comprises four steps: i) data collection, ii) data processing, iii) feature extraction, and iv) classification. We utilize a low-power system-on-chip (SoC), ESP-32, for the first time to collect alphanumeric hand gesture datasets using channel state information (CSI) with 1,800 trials of 20 gestures, including the steady-state data of ten people. A Butterworth low-pass filter with Gaussian smoothing is applied to remove noise; subsequently, the data is split into windows with sufficient dimensions in the data processing step before feeding to the model. The feature extraction section utilizes a depthwise separable convolutional neural network (DS-Conv) with a feature attention (FA) block and residual block (RB) to extract fine-grained features while reducing the complexity using fewer model parameters. Finally, the extracted refined features are classified in the classification section. The proposed system achieves an average accuracy of 96.31% with much less computational complexity, which is better than the results obtained using state-of-the-art pre-trained CNNs and two deep learning models using CSI data.

The resource allocation solution offered based on non-orthogonal multiple access (NOMA) and orthogonal multiple access (OMA) schemes are sub-optimal to address the challenging quality of service (QoS) and higher data rate viz-a-viz energy efficiency (EE) requirements in 5th generation (5G) cellular networks. In this work, we maximize the EE using user equipment (UE) clustering (UE-C) with downlink hybrid NOMA (H-NOMA) assisted beyond 5G (B5G) HetNets. We formulate an optimization problem incorporating UE admission in a cluster, UE association with a base station (BS), and power allocation assisted by H-NOMA, i.e., OMA and NOMA schemes in the macro base station (MBS) only and heterogeneous networks (HetNets) environments. The problem formulated is a type of non-linear concave fractional programming (CFP) problem. The Charnes-Cooper transformation (CCT) is applied to the formulated non-linear CFP problem to convert it into a concave optimization, i.e., mixed-integer non-linear programming (MINLP) problem. A two-phase $\epsilon $ -optimal outer approximation algorithm (OAA) is used to solve the MINLP problem. The simulation results show that H-NOMA with HetNets outperforms H-NOMA with MBS only in terms of UE admission, UE association, throughput, and EE.

To restore vision to the low vision, epiretinal implants have been developed to electrically stimulate the healthy retinal ganglion cells (RGCs) in the degenerate retina. Given the diversity of retinal ganglion cells as well as the difference in their visual function, selective activation of RGCs subtypes can significantly improve the quality of the restored vision. Our recent results demonstrated that with the proper modulation of the current amplitude, small D1-bistratified cells with the contribution to blue/yellow color opponent pathway can be selectively activated at high frequency (200 Hz). The computational results correlated with the clinical findings revealing the blue sensation of 5/7 subjects with epiretinal implants at high frequency. Here we further explored the impacts of alterations in pulse duration and interphase gap on the response of RGCs at high frequency. We used the developed RGCs, A2-monostratified and D1-bistratified, and examined their response to a range of pulse durations (0.1-1.2 ms) and interphase gaps (0-1 ms). We found that the use of short pulse durations with no interphase gap at high frequency increases the differential response of RGCs, offering better opportunities for selective activation of D1 cells. The presence of the interphase gap has shown to reduce the overall differential response of RGCs. We also explored how the low density of calcium channels enhances the responsiveness of RGCs at high frequency.

In recent years, Wi-Fi infrastructures have become ubiquitous, providing device-free passive-sensing features. Wi-Fi signals can be affected by their reflection, refraction, and absorption by moving objects in their path. The channel state information (CSI), a signal property indicator, of the Wi-Fi signal can be analyzed for human activity recognition (HAR). Deep learning-based HAR models can enhance performance and accuracy without sacrificing computational efficiency. However, to save computational power, an inception network, which uses a variety of techniques to boost speed and accuracy, can be adopted. In contrast, the concept of spatial attention can be applied to obtain refined features. In this paper, we propose a human–human interaction (HHI) classifier, CSI-IANet, which uses a modified inception CNN with a spatial-attention mechanism. The CSI-IANet consists of three steps: i) data processing, ii) feature extraction, and iii) recognition. The data processing layer first uses the second-order Butterworth low-pass filter to denoise the CSI signal and then segment it before feeding it to the model. The feature extraction layer uses a multilayer modified inception CNN with an attention mechanism that uses spatial attention in an intense structure to extract features from captured CSI signals. Finally, the refined features are exploited by the recognition section to determine HHIs correctly. To validate the performance of the proposed CSI-IANet, a publicly available HHIs CSI dataset with a total of 4800 trials of 12 interactions was used. The performance of the proposed model was compared to those of existing state-of-the-art methods. The experimental results show that CSI-IANet achieved an average accuracy of 91.30%, which is better than that of the existing best method by 5%.

Internet of medical things (IoMT) is getting researchers' attention due to its wide applicability in healthcare. Smart healthcare sensors and IoT enabled medical devices exchange data and collaborate with other smart devices without human interaction to securely transmit collected sensitive healthcare data towards the server nodes. Alongside data communications, security and privacy is also quite challenging to securely aggregate and transmit healthcare data towards Fog and cloud servers. We explored the existing surveys to identify a gap in literature that a survey of fog-assisted secure healthcare data collection schemes is yet contributed in literature. This paper presents a survey of different data collection and secure transmission schemes where Fog computing based architectures are considered. A taxonomy is presented to categorize the schemes. Fog assisted smart city, smart vehicle and smart grids are also considered that achieve secure, efficient and reliable data collection with low computational cost and compression ratio. We present a summary of these scheme along with analytical discussion. Finally, a number of open research challenges are identified. Moreover, the schemes are explored to identify the challenges that are addressed in each scheme.

Internet of Medical Things (IoMT) is becoming an essential part of remote health monitoring due to the evolution of medical wireless sensors and intelligent communication technologies. IoT-based healthcare applications are employed in the medical centers to provide continuous health monitoring of a patient. However, recent smart medical devices have limited resources to handle the huge amount of healthcare data. IoMT faces several challenging issues, like security, privacy, anonymity, and interoperability. In data aggregation and communication, the privacy and security of medical information is a demanding task. Therefore, we proposed a suitable scheme to overcome the limitations of existing research studies. This paper presents an Efficient and Secure Data Transmission and Aggregation (ESDTA) scheme to enhance aggregation efficiency and data security. Our proposed work provides secure data aggregation and data forwarding of healthcare parameter values by employing the Secure Message Aggregation (SMA) algorithm and Secure Message Decryption (SMD) algorithm at the Mobile Node (MN) and Fog Node (FN), respectively. From a security perspective, the proposed scheme preserves the data integrity and also protect against several security threats like data fabrication and replay attack. The proposed scenario is simulated through simulation tool NS 2.35. The simulation results prove that aggregation at the MN effectively reduces transmission and communication costs. Furthermore, the effective computation at the FN minimizes the storage and computational cost at the cloud server. Thus, the analysis of the proposed scheme shows the supremacy of our proposed work. We compare our scheme with other related secure data aggregation-based schemes in terms of communication cost, energy consumption, resilience, storage and computational cost.

In this article, we propose a novel feature selection method based on hybrid neural networks for emotional classification avoiding expensive computation. With the development of neural networks for machine learning tools, the Electroencephalogram (EEG)-based classification of human emotions is increasingly important in providing health-care for Edge Computing in support of multiple Internet of Things (IoT) applications. However, classifying emotions through EEG signals is very challenging due to the low temporal boundaries and non-linear nature of EEG signals. Regarding non-linearity, we propose a hierarchical Semi-skipping Layered Gated Unit (SLGU) besides Efficient Network (ENet) for feature extraction. For faster processing, we have introduced a semi-skipping layer for Gated Recurrent Units (GRU) in Recurrent Neural Networks (RNN). The entered layer automatically skips the divergent factor during network training. Preprocessed EEG signals are sent to the hybrid SLGU-ENet model for deep feature extraction. To overcome the computational cost, an optimal function reduction method called the Bag of Visualized Characteristics (BoVC) is used. The entire facility is verified against two publicly available datasets. The results show that the classification performance of the proposed model achieves superior classification precision in a short processing time compared to the state-of-the-art models. The proposed algorithm required around 1.2-5 seconds, suitable for real-time IoT applications.

Beyond fifth-generation (5G) heterogeneous networks (HetNets) are facing the challenge of accommodating enormous mobile users and data traffic with scarce spectrum resources in the microWave ( $\mu $ Wave) band. In this work, we consider both challenges in HetNets comprising large size, high power base station (LHB) and relay operating in $\mu $ Wave band and small size, low power base station (SLB) and device-to-device (D2D) operating in millimeter wave (mmWave) band. We formulate user association optimization problems to pitch user association schemes based on downlink uplink decoupled (DU-DPL) access against traditional downlink uplink coupled (DU-CPL) access in HetNets to gauge the performance of these access schemes in terms of accommodating users and spectrum efficiency in $\mu $ Wave and mmWave bands. Formulated problems are non-deterministic polynomial-time hard (NP-hard) and solved using $\epsilon $ -optimal algorithm. Simulation results show the edge of DU-DPL access over DU-CPL access in terms of users association and spectrum efficiency.

With the new age of data innovation, the Internet of Things (IoT) proliferation has drawn enormous thought and has applied to help applications in different fields i.e., natural assurance, military observing, and industrial applications. WSNs are the essential segment of IoT for monitoring as well as tracking. The most preeminent applications provide confinement and identification of continuous objects i.e. wildfire, toxic gas, bio synthetics concoctions, and so forth. In the case of continuous objects such as fire and toxic gases are detected to identify the boundary of damage and alert teams for rescue efforts. It is also helpful in identifying safe paths for rescue. We have investigated various existing surveys that carried out different concepts associated with continuous object tracking and find out the deficit of boundary detection of object. In order to replete the present cleft of analysis, we have inspected various current state-of-the-art works on boundary detection of a continuous object that has yet not been added to the current writing. This paper presents an extensive overview of different continuous object tracking schemes which involve energy efficiency, boundary detection, communication, data aggregation, and network structural design in literature with the aid of featuring taxonomy. We summarized, compared, and classified these schemes along with their analysis and performance. Moreover, for further evaluation mechanism, strengths and weaknesses of these schemes are presented. Finally, various state-of-the-art open research challenges are identified. Moreover, there is a need to overcome these challenges through novel and reliable arrangements by the researchers.

A common challenge forward-looking utilities are facing when deploying advanced applications that facilitate voltage optimization and service restoration is to provide adequate sensor data for a Distribution System State Estimator (DSSE) so that it provides sufficiently accurate estimates of the system states to enable these applications in an operational environment. We developed a stochastic method that informs telemetry and operational forecasting requirements by quantifying the DSSE performance in supporting advanced applications. The performance metric used is the α risk, which is the likelihood of a DSSE giving a false positive when determining if voltage and loading constraints are met. We applied this method to six real-world industrial/commercial/residential distribution circuits and evaluated α risk improvements provided by circuit-level sensors and operational forecasting. The results show that a combination of sensor deployment schemes was needed to reduce the α risk for undervoltage to effectively zero. Also, sensors deployed at large loads significantly reduce c risks on industrial/commercial circuits while operational forecasting consistently reduces α risks on all circuits. The practical method does not require advanced mathematics and can be readily used by utilities to inform grid modernization investments in sensor technologies so that advanced applications can be executed optimally and violation-free.

The 5G is expected to revolutionize every sector of life by providing interconnectivity of everything everywhere at high speed. However, massively interconnected devices and fast data transmission will bring the challenge of privacy as well as energy deficiency. In today's fast-paced economy, almost every sector of the economy is dependent on energy resources. On the other hand, the energy sector is mainly dependent on fossil fuels and is constituting about 80% of energy globally. This massive extraction and combustion of fossil fuels lead to a lot of adverse impacts on health, environment, and economy. The newly emerging 5G technology has changed the existing phenomenon of life by connecting everything everywhere using IoT devices. 5G enabled IIoT devices has transformed everything from traditional to smart, e.g. smart city, smart healthcare, smart industry, smart manufacturing etc. However, massive I/O technologies for providing D2D connection has also created the issue of privacy that need to be addressed. Privacy is the fundamental right of every individual. 5G industries and organizations need to preserve it for their stability and competency. Therefore, privacy at all three levels (data, identity and location) need to be maintained. Further, energy optimization is a big challenge that needs to be addressed for leveraging the potential benefits of 5G and 5G aided IIoT. Billions of IIoT devices that are expected to communicate using the 5G network will consume a considerable amount of energy while energy resources are limited. Therefore, energy optimization is a future challenge faced by 5G industries that need to be addressed. To fill these gaps, we have provided a comprehensive framework that will help energy researchers and practitioners in better understanding of 5G aided industry 4.0 infrastructure and energy resource optimization by improving privacy. The proposed framework is evaluated using case studies and mathematical modelling.

To survive in the competitive environment, most organizations have adopted component-based software development strategies in the rapid technology advancement era and the proper utilization of cloud-based services. To facilitate the continuous configuration, reduce complexity, and faster system delivery for higher user satisfaction in dynamic scenarios. In cloud services, customers select services from web applications dynamically. Healthcare body sensors are commonly used for diagnosis and monitoring patients continuously for their emergency treatment. The healthcare devices are connected with mobile or laptop etc. on cloud environment with network and frequently change applications. Thus, organizations rely on regression testing during changes and implementation to validate the quality and reliability of the system after the alteration. However, for a large application with limited resources and frequently change component management activities in the cloud computing environment, component-based system verification is difficult and challenging due to irrelevant and redundant test cases and faults. In this study, proposed a test case selection and prioritization framework using a design pattern to increase the faults detection rate. First, we select test cases on frequently accessed components using observer patterns and, secondly, prioritize test cases on adopting some strategies. The proposed framework was validated by an experiment and compared with other techniques (previous faults based and random priority). Hence, experimental results show that the proposed framework successfully verified changes. Subsequently, the proposed framework increases the fault detection rate (i.e., more than 90%) than previous faults based and random priority (i.e., more than 80% respectively).

In recent years, the growth rate of Cloud computing technology is increasing exponentially, mainly for its extraordinary services with expanding computation power, the possibility of massive storage, and all other services with the maintained quality of services (QoSs). The task allocation is one of the best solutions to improve different performance parameters in the cloud, but when multiple heterogeneous clouds come into the picture, the allocation problem becomes more challenging. This research work proposed a resource-based task allocation algorithm. The same is implemented and analyzed to understand the improved performance of the heterogeneous multi-cloud network. The proposed task allocation algorithm (Energy-aware Task Allocation in Multi-Cloud Networks (ETAMCN)) minimizes the overall energy consumption and also reduces the makespan. The results show that the makespan is approximately overlapped for different tasks and does not show a significant difference. However, the average energy consumption improved through ETAMCN is approximately 14%, 6.3%, and 2.8% in opposed to the random allocation algorithm, Cloud Z-Score Normalization (CZSN) algorithm, and multi-objective scheduling algorithm with Fuzzy resource utilization (FR-MOS), respectively. An observation of the average SLA-violation of ETAMCN for different scenarios is performed.

Software-defined networking (SDN) separates the network control plane from the packet forwarding plane, which provides comprehensive network-state visibility for better network management and resilience. Traffic classification, particularly for elephant flow detection, can lead to improved flow control and resource provisioning in SDN networks. Existing elephant flow detection techniques use pre-set thresholds that cannot scale with the changes in the traffic concept and distribution. This paper proposes a flow-aware elephant flow detection applied to SDN. The proposed technique employs two classifiers, each respectively on SDN switches and controller, to achieve accurate elephant flow detection efficiently. Moreover, this technique allows sharing the elephant flow classification tasks between the controller and switches. Hence, most mice flows can be filtered in the switches, thus avoiding the need to send large numbers of classification requests and signaling messages to the controller. Experimental findings reveal that the proposed technique outperforms contemporary methods in terms of the running time, accuracy, F-measure, and recall.

A novel Radio Frequency Identification (RFID) based sensor supporting touch detection and localization features is proposed in this work. The formulated sensor leverages chipless variant of RFID technology for the design of a passive fully-printable frequency domain-based sensor-incorporated tag. The sensor is composed of square resonators arranged in a peculiar fashion laid down across a $3\times2$ grid. The proposed sensor incorporated-tag readily keeps track of human-digit position, allowing for tracking of finger-swipes which, in turn, can potentially be used for recognition of unlock patterns and security codes. Performance of the sensor is analyzed using its Radar Cross Section (RCS) response observable in the spectral domain. Each constituent resonant-element making up the sensor resonates at a single frequency represented by a distinct dip in the RCS response. The spectral dip drifts well outside of its allocated band upon occurrence of a touch event. A functional prototype of the sensor tag is fabricated on a 0.508 mm thick Rogers RT/Duroid® 5880 laminate is scrutinized of its electromagnetic performance. The sensor possesses a compact physical footprint equal to 45 mm $\times55$ mm. The obtained results solidify the suitability of the proposed sensor for deployment in secure access control settings prevalent in smart cities and connected home applications.

Where traditional genetic algorithms tend to prematurely converge on local optima, adaptive strategies aim to maintain a healthy level of population diversity by introducing randomness to the population. Often times this is done through adjusting control parameters according to diversity measurements. While these approaches introduce diversity, they do not aid in focusing or directing the search effort. Meanwhile, other works in the literature propose creating individuals designed to improve the population's health and quality but their effectiveness is limited outside of general problems. This article proposes novel sequence-wise approach to designing and editing genotypes for ordered problems. A Markov model based similarity guide matrix (MSGM) is used to determine the relationships between gene nodes in order to produce new genotypes that focus on improving fitness and increasing population diversity. The proposed MSGM based approach is implemented in a balanced-evolution genetic algorithm framework in order to investigate its characteristics with encouraging results demonstrating its effectiveness when solving combinatorial ordered optimisation problems.

Content-adaptive steganography intends to hide data in the complex texture content of the image. Recently, some secure steganography methods have been proposed to identify the textural complexity of an image. However, most of the techniques do not take into account the information of pixel variation around the central pixel in all possible directions and therefore they are unable to accurately analyse the texture complexity. This work offers a quality-enhanced and secure method of content-adaptive image steganography. The proposed method is divided into three sequential steps: image segmentation, pixel complexity identification, and data embedding. An input cover image is initially divided into small local regions and the pixel-complexity is identified based on the proposed Complex Block Prior (CBP) criterion. In a local block, a high pass filter (HPF) bank is applied and eight residual responses are obtained. Following the CBP criterion, a complexity level out of nine levels is assigned to an individualized pixel block. The pixels are then arranged in the priority of complexity from highest to lowest. Data embedding for the corresponding complexity level then takes place using the proposed adaptive embedding algorithm. Experimental results verify the preservation of visual quality of stego images produced by the proposed method. Three image datasets: Standard test images, BOWS2 and BOSS-base are used for the experimentation and comparison with prior state-of-art methods. Highest values of the IQ (image quality) parameters e.g., SSIM and WPSNR show the effectiveness of the proposed method.

In this paper, a compact and fully passive bit encoding circuit, capable of operating as a chipless radio frequency identification (RFID) tag is presented. The structure consists of novel concentric trefoil-shaped slot resonators realized using Rogers RT/duroid® 5880 laminate, occupying a physical footprint of 13.55 $\times $ 13.55 mm2. Each resonating element is associated with a particular data bit, having a 1:1 resonator-to-bit correspondence. Bit sequences are configured through introducing modifications in the geometric structure either by addition or exclusion of each nested slot resonator. Such changes manifest directly in the electromagnetic signature of the tag as presence or absence of corresponding resonant peaks. The proposed 10-bit tag offers minimized inter-resonator mutual coupling and insensitivity to changes in polarization and incident angles thereby demonstrating orientation independent functionality. Moreover, error-free encoding is achieved through stabilizing the shift in resonant frequencies for a variety of different geometric configurations and orientation of the structure. The tag operates within the license-free ultra-wideband ranging from 5.4 to 10.4 GHz, providing spectral bit capacity and bit density of 2 bits/GHz and 5.44 bits/cm2 respectively.

A robustness-driven hybrid descriptor (RDHD) for noise-deterrent texture classification is presented in this paper. This paper offers the ability to categorize a variety of textures under challenging image acquisition conditions. An image is initially resolved into its low-frequency components by applying wavelet decomposition. The resulting low-frequency components are further processed for feature extraction using completed joint-scale local binary patterns (CJLBP). Moreover, a second feature set is obtained by computing the low order derivatives of the original sample. The evaluated feature sets are integrated to get a final feature vector representation. The texture-discriminating performance of the hybrid descriptor is analyzed using renowned datasets: Outex original, Outex extended, and KTH-TIPS. The experimental results demonstrate a stable and robust performance of the descriptor under a variety of noisy conditions. An accuracy of 95.86%, 32.52%, and 88.74% at noise variance of 0.025 is achieved for the given datasets, respectively. A comparison between performance parameters of the proposed paper with its parent descriptors and recently published paper is also presented.

This paper ideates a novel texture descriptor that retains its classification accuracy under varying conditions of image orientation, scale, and illumination. The proposed Overlapped Multi-oriented Tri-scale Local Binary Pattern (OMTLBP) texture descriptor also remains insensitive to additive white Gaussian noise. The wavelet decomposition stage of the OMTLBP provides robustness to photometric variations, while the two subsequent stages - overlapped multi-oriented fusion and multi-scale fusion - provide resilience against geometric transformations within an image. Isolated encoding of constituent pixels along each scale in the joint histogram enables the proposed descriptor to capture both micro and macro structures within the texture. Performance of the OMTLBP is evaluated by classifying a variety of textured images belonging to Outex, KTH-TIPS, Brodatz, CUReT, and UIUC datasets. The experimental results validate the superiority of the proposed method in terms of classification accuracy when compared with the state-of-the-art texture descriptors for noisy images.