Search

Abstract In late 2023, the United Nations conference on climate change (COP28), which was held in Dubai, encouraged a quick move from fossil fuels to renewable energy. Solar energy is one of the most promising forms of energy that is both sustainable and renewable. Generally, photovoltaic systems transform solar irradiance into electricity. Unfortunately, instability and intermittency in solar radiation can lead to interruptions in electricity production. The accurate forecasting of solar irradiance guarantees sustainable power production even when solar irradiance is not present. Batteries can store solar energy to be used during periods of solar absence. Additionally, deterministic models take into account the specification of technical PV systems and may be not accurate for low solar irradiance. This paper presents a comparative study for the most common Deep Learning (DL) and Machine Learning (ML) algorithms employed for short-term solar irradiance forecasting. The dataset was gathered in Islamabad during a five-year period, from 2015 to 2019, at hourly intervals with accurate meteorological sensors. Furthermore, the Grid Search Cross Validation (GSCV) with five folds is introduced to ML and DL models for optimizing the hyperparameters of these models. Several performance metrics are used to assess the algorithms, such as the Adjusted R 2 score, Normalized Root Mean Square Error (NRMSE), Mean Absolute Deviation (MAD), Mean Absolute Error (MAE) and Mean Square Error (MSE). The statistical analysis shows that CNN-LSTM outperforms its counterparts of nine well-known DL models with Adjusted R 2 score value of 0.984. For ML algorithms, gradient boosting regression is an effective forecasting method with Adjusted R 2 score value of 0.962, beating its rivals of six ML models. Furthermore, SHAP and LIME are examples of explainable Artificial Intelligence (XAI) utilized for understanding the reasons behind the obtained results.

Abstract Breast cancer is a prevalent disease and the second leading cause of death in women globally. Various imaging techniques, including mammography, ultrasonography, X-ray, and magnetic resonance, are employed for detection. Thermography shows significant promise for early breast disease detection, offering advantages such as being non-ionizing, non-invasive, cost-effective, and providing real-time results. Medical image segmentation is crucial in image analysis, and this study introduces a thermographic image segmentation algorithm using the improved Black Widow Optimization Algorithm (IBWOA). While the standard BWOA is effective for complex optimization problems, it has issues with stagnation and balancing exploration and exploitation. The proposed method enhances exploration with Levy flights and improves exploitation with quasi-opposition-based learning. Comparing IBWOA with other algorithms like Harris Hawks Optimization (HHO), Linear Success-History based Adaptive Differential Evolution (LSHADE), and the whale optimization algorithm (WOA), sine cosine algorithm (SCA), and black widow optimization (BWO) using otsu and Kapur's entropy method. Results show IBWOA delivers superior performance in both qualitative and quantitative analyses including visual inspection and metrics such as fitness value, threshold values, peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and feature similarity index (FSIM). Experimental results demonstrate the outperformance of the proposed IBWOA, validating its effectiveness and superiority.

Abstract Significant advancements in machine learning algorithms have the potential to aid in the early detection and prevention of cancer, a devastating disease. However, traditional research methods face obstacles, and the amount of cancer-related information is rapidly expanding. The authors have developed a helpful support system using three distinct deep-learning models, ResNet-50, EfficientNet-B3, and ResNet-101, along with transfer learning, to predict lung cancer, thereby contributing to health and reducing the mortality rate associated with this condition. This offer aims to address the issue effectively. Using a dataset of 1,000 DICOM lung cancer images from the LIDC-IDRI repository, each image is classified into four different categories. Although deep learning is still making progress in its ability to analyze and understand cancer data, this research marks a significant step forward in the fight against cancer, promoting better health outcomes and potentially lowering the mortality rate. The Fusion Model, like all other models, achieved 100% precision in classifying Squamous Cells. The Fusion Model and ResNet-50 achieved a precision of 90%, closely followed by EfficientNet-B3 and ResNet-101 with slightly lower precision. To prevent overfitting and improve data collection and planning, the authors implemented a data extension strategy. The relationship between acquiring knowledge and reaching specific scores was also connected to advancing and addressing the issue of imprecise accuracy, ultimately contributing to advancements in health and a reduction in the mortality rate associated with lung cancer.

The rising number of Internet of Things (IoT) devices, powered by inexpensive sensors and rapid wireless connections, places challenge on existing internet infrastructure and concerns sustainability issues. For networks to satisfy Quality-of-Service (QoS) standards in the Software-Defined IoT (SDIoT) network, efficient algorithms for routing are required. In SDIoT framework, this research proposes to develop a traffic-aware QoS routing algorithm dependent on ant behavior. In order to enhance QoS routing metrics, this work proposes an Ant Colony Optimization (ACO) based algorithm that focuses IoT device flows that are jitter, delay, and loss-sensitive. The proposed approach optimizes overall network performance with utilizing the fewest resources possible by optimizing the routing path to meet application-specific QoS standards using Yen’s k shortest path algorithm. The suggested approach outperforms current techniques in terms of fulfilling all three types of flows, resulting in sustained network performance enhancements of 5.25% in average delay, 5.15% in QoS-violated flows with Ant-inspired routing, 7% in average packet loss, and 4.65% in average jitter. This research provides an efficient practical way to deal with the growing challenges that IoT applications are posing for network sustainability.

The aim of this study is to establish an effective modeling technique for simulating the performance of photovoltaic modules by calculating their electrical parameters based on the two-diode model. The suggested methodology involves reducing the scope of the study from seven unknown parameters to only three, and that without resorting to any approximations. The first four parameters are calculated analytically based on the data representing the crucial positions on the current-voltage graph and using a new expression of the fill-factor derived from the two-diode equivalent circuit. The remaining parameters are established numerically based on a simple iterative technique adaptable with two sites of data availability. The photovoltaic modeling begins by utilizing the values of key-points. Subsequently, to ensure the proposed approach's adaptability to various scenarios of available information about PV generators, it is invested and applied for an optimization process. The accuracy is evaluated for diverse types of photovoltaic modules, and the results are weighed against widely reviewed numerical methods and evolutionary optimization algorithms in the literature. As a result, the new method demonstrates superior performance, yielding the smallest values for the utilized statistical indicators and reducing compilation time. These findings underscore its flexibility and high efficiency in simulating photovoltaic devices.

Breast cancer (BC) is the leading cause of female cancer mortality and is a type of cancer that is a major threat to women's health. Deep learning methods have been used extensively in many medical domains recently, especially in detection and classification applications. Studying histological images for the automatic diagnosis of BC is important for patients and their prognosis. Owing to the complication and variety of histology images, manual examination can be difficult and susceptible to errors and thus needs the services of experienced pathologists. Therefore, publicly accessible datasets called BreakHis and invasive ductal carcinoma (IDC) are used in this study to analyze histopathological images of BC. Next, using super-resolution generative adversarial networks (SRGANs), which create high-resolution images from low-quality images, the gathered images from BreakHis and IDC are pre-processed to provide useful results in the prediction stage. The components of conventional generative adversarial network (GAN) loss functions and effective sub-pixel nets were combined to create the concept of SRGAN. Next, the high-quality images are sent to the data augmentation stage, where new data points are created by making small adjustments to the dataset using rotation, random cropping, mirroring, and color-shifting. Next, patch-based feature extraction using Inception V3 and Resnet-50 (PFE-INC-RES) is employed to extract the features from the augmentation. After the features have been extracted, the next step involves processing them and applying transductive long short-term memory (TLSTM) to improve classification accuracy by decreasing the number of false positives. The results of suggested PFE-INC-RES is evaluated using existing methods on the BreakHis dataset, with respect to accuracy (99.84%), specificity (99.71%), sensitivity (99.78%), and F1-score (99.80%), while the suggested PFE-INC-RES performed better in the IDC dataset based on F1-score (99.08%), accuracy (99.79%), specificity (98.97%), and sensitivity (99.17%).

Abstract Recent advances in imaging technologies have led to a significant increase in the adoption of stereoscopic images. However, despite this proliferation, in-depth research into the complex analysis of the visual content of these stereoscopic images is still relatively rare. The advent of stereoscopic imaging has brought a new dimension to visual content. These images offer a higher level of visual detail, making them increasingly common in a variety of fields, including medicine and industrial applications. However, exploiting the full potential of stereoscopic images requires a deeper understanding. By exploiting the capabilities of octonion moments and the power of artificial intelligence, we aim to break new ground by introducing a novel method for classifying stereoscopic images. The proposed method is divided into two key stages: The first stage involves data preprocessing, during which we strive to construct a balanced database divided into three distinct categories. In addition, we extract the stable Octonion Krawtchouk moments (SOKM) for each image, leading to a database of moment images with dimensions of 128 × 128 × 1. In the second step, we train a convolutional neural network (CNN) model using this database, with the aim of discriminating between different categories. Standard measures such as precision, accuracy, recall, F1 score, and ROC curves are used to assess the effectiveness of our method. These measures provide a quantitative assessment of the performance of our object classification approach for stereoscopic images.

Abstract Deep fake technology has emerged as a double-edged sword in the digital world. While it holds potential for legitimate uses, it can also be exploited to manipulate video content, causing severe social and security concerns. The research gap lies in the fact that traditional deep fake detection methods, such as visual quality analysis or inconsistency detection, need help to keep up with the rapidly advancing technology used to create deep fakes. That means there's a need for more sophisticated detection techniques. This paper introduces an enhanced approach for detecting deep fake videos using graph neural network (GNN). The proposed method splits the detection process into two phases: a mini-batch graph convolution network stream four-block CNN stream comprising Convolution, Batch Normalization, and Activation function. The final step is a flattening operation, which is essential for connecting the convolutional layers to the dense layer. The fusion of these two phases is performed using three different fusion networks: FuNet-A (additive fusion), FuNet-M (element-wise multiplicative fusion), and FuNet-C (concatenation fusion). The paper further evaluates the proposed model on different datasets, where it achieved an impressive training and validation accuracy of 99.3% after 30 epochs.

Abstract Chest radiographs are examined in typical clinical settings by competent physicians for tuberculosis diagnosis. However, this procedure is time consuming and subjective. Due to the growing usage of machine learning techniques in applied sciences, researchers have begun applying comparable concepts to medical diagnostics, such as tuberculosis screening. In the period of extremely deep neural nets which comprised of hundreds of convolution layers for feature extraction, we create a shallow-CNN for screening of TB condition from Chest X-rays so that the model is able to offer appropriate interpretation for right diagnosis. The suggested model consists of four convolution-maxpooling layers with various hyperparameters that were optimized for optimal performance using a Bayesian optimization technique. The model was reported with a peak classification accuracy, F1-score, sensitivity and specificity of 0.95. In addition, the receiver operating characteristic (ROC) curve for the proposed shallow-CNN showed a peak area under the curve value of 0.976. Moreover, we have employed class activation maps (CAM) and Local Interpretable Model-agnostic Explanations (LIME), explainer systems for assessing the transparency and explainability of the model in comparison to a state-of-the-art pre-trained neural net such as the DenseNet.

Federated learning uses the concept of decentralized training of n number of local clients for a small number of epochs say 2-5, and then averaging the learned weights of all local clients, and evaluating on test dataset with the average weights loaded to a global model. The train dataset is split into n clusters and each cluster acts as a distributed data for each local model. Each round of weight averaging and then uploading the average weights on each local client for further training is called communication round and it was observed that similar accuracy can be obtained with a lesser amount of training time. In this paper, instead of averaging the weights, a weighted mean concept was developed where the PSO vector helps to find the weight values for the best accuracy of a global model. It was found that PSO can help in two ways by bettering the accuracy and also reducing the training time. The proposed approach can enhance the performance of pre-trained models like AlexNet, VGG16, InceptionV3, and ResNet50 on CIFAR-10 and CIFAR-100 datasets. The maximum increase was found with VGG16 of around 26.01% for CIFAR-10 and 26.84% for CIFAR-100. Similarly, on the Tomato dataset, AlexNet accuracy can be increased by 28.56%. Multi-modal model accuracy on the fake news dataset was also enhanced by 8.21%.

Quantum computers use quantum-mechanical phenomena for knowledge manipulation and depend on quantum bits or qubits. A qubit can be created in several different ways, and out of this, one way of creating a quantum state is by using superconductivity. They must be held very cold to work on these superconductive qubits for long periods. The key to information storage and manipulation is the skill of all computer systems. Current traditional computers handle single bits stored in binary states of 0 and 1 form. Every temperature factor inside the device may be updated; thus, quantum computers are more excellent than the vacuum of space at temperatures similar to absolute null. Consider how the dilution refrigerator of a quantum computer consisting of over 2000 components provides a cold atmosphere for the inside of the qubits. Researchers from all around the world today are using actual quantum processors for validating algorithms for different fields of operation. Yet quantum computation was a strictly speculative topic a couple of decades ago. Quantum cryptography, also known as quantum encoding, uses quantum mechanics principles to encrypt messages in a way nobody else reads. It benefits quantum states, along with its “theory of no transition,” which means that it cannot be disrupted unknowingly. Quantum-improved AI calculations are especially applicable to the area. This work focuses on the implementation patterns of quantum computing in real-time cryptography so that the overall communication will be secured and integrity aware.

The advancement of Internet of Everything (IoE) propels the fast growth of next-generation, such as 6G networks, leading to a new era of coverage, connectivity, and technological innovation, which calls for novel approaches to address rising energy consumption and maximize resource use. The proposed article presents a robust hybrid algorithm that combines leader-based optimization and Adaptive Differential Evolution (DE) in the framework of the Energy Efficient Hybrid Evolutionary Algorithm (EEHEA), which is specifically designed for the complex environment of IoE-enabled 6G networks. The scheme EEHEA combines the efficacy of leader-based optimization (LBO) for an effective decision-making process and adaptive differential evolutionary optimization (ADE)’s dynamic network-parameters adaptation, enhanced convergence, and global searching ability, persistently fine-tuning optimization strategies based on the dynamics of the network. Combining these components into the scheme EEHEA allows it to balance local exploitation and global exploration effectively. This implies better resource allocation and improved energy efficiency in ecosystems with IoE-driven 6G (IoE-6G). The outcomes report that the scheme EEHEA can address the rising energy consumption issues and enhance the efficiency of IoE-6G. Based on simulation experiments, the proposed scheme EEHEA can demonstrate faster convergence times, higher accuracy, and superior flexibility concerning changing network conditions. Its capability to handle energy-related challenges and navigate complex network environments with resilience shows the ability to enhance the performance of IoE-6G. The EEHEA scheme reports its efficacy over state-of-the-art schemes regarding localization, latency, coverage, and energy expenditure performance metrics.

Polar codes have garnered substantial research attention due to their impressive performance characteristics and have found applications in recent technologies, including 5G New Radio (NR) systems, Internet of Things (IoT) communications, and cyber-physical systems that utilize sensor and actuator networks. However, the existing SC decoders suffer from lengthy processing latencies due to their sequential processing steps, thereby restricting the practical applicability of polar codes. To address this latency issue, this paper introduces a Compound Pipeline Processing Unit (CPPU) and its simplified counterpart, a crucial step in realizing tree-level compound pipelining. In contrast to sequential circuitry, the previously described combinational architecture lacks internal storage elements, with the clock period defined by the longest path delay. This strategy conserves hardware resources by avoiding memory usage, but it inevitably decelerates the decoder’s performance. Notably, implementation results underline the efficiency of the proposed CPPU-based SC polar decoder using a fully unrolled encoder and decoder on the targeted platform of a Virtex UltraScale - XCVU190 Field Programmable Gate Array (FPGA), using a parametric approach in the Very High-Speed Integrated Circuit Hardware Description Language (VHDL). The assessment of error-correction performance involves examining various combinations of integral and fractional bits in LLR quantized representations. This approach achieves a throughput of about 2672 Mbps, accompanied by a substantial reduction of 17% in Lookup Table (LUT) usage. Furthermore, the decoder’s speed is enhanced by approximately 17.34% for a code length of 128 bits and LLR quantization of 5 bits.

In this current era, cyber-physical systems (CPSs) have gained concentrated consideration in various fields because of their emergent applications. Though the robust dependence on communication networks creates cyber-physical systems susceptible to deliberated cyber related attacks and detecting these cyber-attacks are the most challenging task. There is the interaction among the components of the cyber and physical worlds, so CPS security needs a distinct approach from past security concerns. Deep learning (DL) distributes better performance than machine learning (ML) due to its layered architecture and the efficient algorithm for extracting prominent information from training data. So, the deep learning models are taken into consideration quickly for detecting cyber-attacks in cyber physical systems. As numerous attack detection methods have been proposed by various authors for enforcing CPS security, this paper reviews and analyzes multiple ways of attack detection presented for CPS using deep learning. We will be putting the excellent potential for detecting cyber-attacks for CPS concerning deep learning modules. The admirable performance is attained partly as highly quality datasets are eagerly obtainable for the use of the public. Moreover, various challenges and research inclinations are also discussed in impending research.

Effective research has been aimed at increasing the distributed compute dependent Software Define Network (SDN) with high-level Intelligent - Internet of Things (I-IoT). Wireless sensor networks come with a set of resource restrictions. Still, only a few functions are often configured such as energy restraint and the concerted demands that are vital for IoT application routing performance. A major technique for solving the expansion of network scalability by applying Mobile Sink (MS). The construction of data transmission optimal path, the detection of an optimal set data-gathering points $O_{DG} $ and MS scheduled with dynamic networks for energy-efficient techniques, that the network’s lifetime in enormous complications, principally in large-scale IoT networks. The research work proposes an Research Objective: i) Develop an energy-efficient routing technique for large-scale I-IoT networks within a cloud-based SDN system. ii) Optimize network scalability, lower-level routing, and load balancing using Genetic Algorithm (GA), Particle Swarm Optimization (PSO), and Artificial Bee Colony (ABC). The prime aim of cloud-based SDN with AI is to determine: a lower level routing in the perception layer, a load-balanced Cluster Table (CT), an optimal $O_{DG} $ points, and MS optimal paths $O_{MSpath} $ . The main contribution of proposed routing is i) Energy Minimization (EM): The proposed routing minimizes energy dissemination by the Cluster Head (CH) in critical conditions (EM-CH). ii) Enhanced Energy Balance (EEB): The EC-based SDN, considering both Optimal Data-Gathering ( $O_{DG}$ ) and Mobile Sink (MS) advancements, achieves enhanced energy balance during network routing (EEB-SDN). Research results validate the proposed model stability that improves the network lifetime up to 63%, the energy usage in the network is reduced up to 78%, the high volume data loaded to the MS up to 95%, and the delay of the $O_{MSpath} $ by 69% when compared with various model.

Abstract A drop in physical activity and a deterioration in the capacity to undertake daily life activities are both connected with ageing and have negative effects on physical and mental health. An Elderly and Visually Impaired Human Activity Monitoring (EV-HAM) system that keeps tabs on a person’s routine and steps in if a change in behaviour or a crisis might greatly help an elderly person or a visually impaired. These individuals may find greater freedom with the help of an EVHAM system. As the backbone of human-centric applications like actively supported living and in-home monitoring for the elderly and visually impaired, an EVHAM system is essential. Big data-driven product design is flourishing in this age of 5G and the IoT. Recent advancements in processing power and software architectures have also contributed to the emergence and development of artificial intelligence (AI). In this context, the digital twin has emerged as a state-of-the-art technology that bridges the gap between the real and virtual worlds by evaluating data from several sensors using artificial intelligence algorithms. Although promising findings have been reported by Wi-Fi-based human activity identification techniques so far, their effectiveness is vulnerable to environmental variations. Using the environment-independent fingerprints generated from the Wi-Fi channel state information (CSI), we introduce Wi-Sense. This human activity identification system employs a Deep Hybrid convolutional neural network (DHCNN). The proposed system begins by collecting the CSI with a regular Wi-Fi Network Interface Controller. Wi-Sense uses the CSI ratio technique to lessen the effect of noise and the phase offset. The t- Distributed Stochastic Neighbor Embedding (t-SNE) is used to eliminate unnecessary data further. The data dimension is decreased, and the negative effects on the environment are eliminated in this process. The resulting spectrogram of the processed data exposes the activity’s micro-Doppler fingerprints as a function of both time and location. These spectrograms are put to use in the training of a DHCNN. Based on our findings, EVHAM can accurately identify these actions 99% of the time.

The current work proposes a novel method for photovoltaic (PV) modules’ performance estimation at various weather conditions based on the extraction of the single-diode model’s five parameters. The new modeling technique is not built on any approximations or iterative processes, and this makes the approach combining two substantial benefits in the PV simulation field which are the accuracy of prediction and the rapidity of convergence. Moreover, the method is founded on the resolution of matrix equations based on reduced forms, and that assures its simplicity by avoiding tedious calculations. Indeed, only the mean points of the current–voltage characteristic are employed to get the values of the five parameters by calculating two of them using a numerical resolution of a two non-linear equations’ system. Then, the expressions giving the three last parameters are determined as functions of the two first parameters and regrouped in a matrix equation, which is solved analytically to get the values of these remaining parameters. The productiveness of the proposed method is tested using PV modules of various technologies and proved using eight well-known simulating methods for the one-diode model. Furthermore, the root mean squared errors matching the new method have not exceeded 0.093 A and the obtained convergence time is less than 0.27 s. The results attest to the relevance of the new method for dynamic applications and for PV designers requiring simple modeling techniques.

Introduction: Eye movement is one of the cues used in human–machine interface technologies for predicting the intention of users. The developing application in eye movement event detection is the creation of assistive technologies for paralyzed patients. However, developing an effective classifier is one of the main issues in eye movement event detection.Methods: In this paper, bidirectional long short-term memory (BILSTM) is proposed along with hyperparameter tuning for achieving effective eye movement event classification. The Lévy flight and interactive crossover-based reptile search algorithm (LICRSA) is used for optimizing the hyperparameters of BILSTM. The issues related to overfitting are avoided by using fuzzy data augmentation (FDA), and a deep neural network, namely, VGG-19, is used for extracting features from eye movements. Therefore, the optimization of hyperparameters using LICRSA enhances the classification of eye movement events using BILSTM.Results and Discussion: The proposed BILSTM–LICRSA is evaluated by using accuracy, precision, sensitivity, F1-score, area under the receiver operating characteristic (AUROC) curve measure, and area under the precision–recall curve (AUPRC) measure for four datasets, namely, Lund2013, collected dataset, GazeBaseR, and UTMultiView. The gazeNet, human manual classification (HMC), and multi-source information-embedded approach (MSIEA) are used for comparison with the BILSTM–LICRSA. The F1-score of BILSTM–LICRSA for the GazeBaseR dataset is 98.99%, which is higher than that of the MSIEA.

Handwritten character recognition is one of the classical problems in the field of image classification. Supervised learning techniques using deep learning models are highly effective in their application to handwritten character recognition. However, they require a large dataset of labeled samples to achieve good accuracies. Recent supervised learning techniques for Kannada handwritten character recognition have state of the art accuracy and perform well over a large range of input variations. In this work, a framework is proposed for the Kannada language that incorporates techniques from semi-supervised learning. The framework uses features extracted from a convolutional neural network backbone and uses regularization to improve the trained features and label propagation to classify previously unseen characters. The episodic learning framework is used to validate the framework. Twenty-four classes are used for pre-training, 12 classes are used for testing and 11 classes are used for validation. Fine-tuning is tested using one example per unseen class and five examples per unseen class. Through experimentation the components of the network are implemented in Python using the Pytorch library. It is shown that the accuracy obtained 99.13% make this framework competitive with the currently available supervised learning counterparts, despite the large reduction in the number of labeled samples available for the novel classes.

As is well-known, multicriteria decision-making (MCDM) approaches can aid decision-makers in identifying the optimal alternative based on predetermined criteria. However, it is a big challenge to apply this approach in complex applications such as 5th generation (5G) industry assessment because criteria are challenging and trade-offs between them are hard. Also, assessment of the 5G industry involve strong uncertainty. So, this study is the first to evaluate the 5G industry using a new neutrosophic simple multi-attribute rating technique (N-SMART). Since neutrosophic set considers truth-degree, indeterminacy-degree, and falsity-degree, it is a more accurate instrument for evaluating uncertainty. The 5G assessment issue exemplifies the validity and great performance of our proposed method as: (1) its ability to deal with uncertainty phenomena; (2) its simplicity; and (3) its enhanced capacity to discern alternatives. Also, by considering the 5G service provided in the Egyptian New Administrative capital as a case study, the results showed that Ericsson 5G is the best choice and Nokia 5G is the worst choice.

The 2017 World Health Organization Fact Sheet highlights that coronary artery disease is the leading cause of death globally, responsible for approximately 30% of all deaths. In this context, machine learning (ML) technology is crucial in identifying coronary artery disease, thereby saving lives. ML algorithms can potentially analyze complex patterns and correlations within medical data, enabling early detection and accurate diagnosis of CAD. By leveraging ML technology, healthcare professionals can make informed decisions and implement timely interventions, ultimately leading to improved outcomes and potentially reducing the mortality rate associated with coronary artery disease. Machine learning algorithms create non-invasive, quick, accurate, and economical diagnoses. As a result, machine learning algorithms can be employed to supplement existing approaches or as a forerunner to them. This study shows how to use the CNN classifier and RNN based on the LSTM classifier in deep learning to attain targeted “risk” CAD categorization utilizing an evolving set of 450 cytokine biomarkers that could be used as suggestive solid predictive variables for treatment. The two used classifiers are based on these “45” different cytokine prediction characteristics. The best Area Under the Receiver Operating Characteristic curve (AUROC) score achieved is (0.98) for a confidence interval (CI) of 95; the classifier RNN-LSTM used “450” cytokine biomarkers had a great (AUROC) score of 0.99 with a confidence interval of 0.95 the percentage 95, the CNN model containing cytokines received the second best AUROC score (0.92). The RNN-LSTM classifier considerably beats the CNN classifier regarding AUROC scores, as evidenced by a p-value smaller than 7.48 obtained via an independent t-test. As large-scale initiatives to achieve early, rapid, reliable, inexpensive, and accessible individual identification of CAD risk gain traction, robust machine learning algorithms can now augment older methods such as angiography. Incorporating 65 new sensitive cytokine biomarkers can increase early detection even more. Investigating the novel involvement of cytokines in CAD could lead to better risk detection, disease mechanism discovery, and new therapy options.

Several deep-learning assisted disease assessment schemes (DAS) have been proposed to enhance accurate detection of COVID-19, a critical medical emergency, through the analysis of clinical data. Lung imaging, particularly from CT scans, plays a pivotal role in identifying and assessing the severity of COVID-19 infections. Existing automated methods leveraging deep learning contribute significantly to reducing the diagnostic burden associated with this process. This research aims in developing a simple DAS for COVID-19 detection using the pre-trained lightweight deep learning methods (LDMs) applied to lung CT slices. The use of LDMs contributes to a less complex yet highly accurate detection system. The key stages of the developed DAS include image collection and initial processing using Shannon's thresholding, deep-feature mining supported by LDMs, feature optimization utilizing the Brownian Butterfly Algorithm (BBA), and binary classification through three-fold cross-validation. The performance evaluation of the proposed scheme involves assessing individual, fused, and ensemble features. The investigation reveals that the developed DAS achieves a detection accuracy of 93.80% with individual features, 96% accuracy with fused features, and an impressive 99.10% accuracy with ensemble features. These outcomes affirm the effectiveness of the proposed scheme in significantly enhancing COVID-19 detection accuracy in the chosen lung CT database.

Abstract Spectrum sensing describes, whether the spectrum is occupied or empty. Main objective of cognitive radio network (CRN) is to increase probability of detection (Pd) and reduce probability of error (Pe) for energy consumption. To reduce energy consumption, probability of detection should be increased. In cooperative spectrum sensing (CSS), all secondary users (SU) transmit their data to fusion center (FC) for final measurement according to the status of primary user (PU). Cluster should be used to overcome this problem and improve performance. In the clustering technique, all SUs are grouped into clusters on the basis of their similarity. In cluster technique, SU transfers their data to cluster head (CH) and CH transfers their combined data to FC. This paper proposes the detection performance optimization of CRN with a machine learning-based metaheuristic algorithm using clustering CSS technique. This article presents a hybrid support vector machine (SVM) and Red Deer Algorithm (RDA) algorithm named Hybrid SVM–RDA to identify spectrum gaps. Algorithm proposed in this work outperforms the computational complexity, an issue reported with various conventional cluster techniques. The proposed algorithm increases the probability of detection (up to 99%) and decreases the probability of error (up to 1%) at different parameters.

Abstract Feature selection and hyper-parameters optimization (tuning) are two of the most important and challenging tasks in machine learning. To achieve satisfying performance, every machine learning model has to be adjusted for a specific problem, as the efficient universal approach does not exist. In addition, most of the data sets contain irrelevant and redundant features that can even have a negative influence on the model’s performance. Machine learning can be applied almost everywhere; however, due to the high risks involved with the growing number of malicious, phishing websites on the world wide web, feature selection and tuning are in this research addressed for this particular problem. Notwithstanding that many metaheuristics have been devised for both feature selection and machine learning tuning challenges, there is still much space for improvements. Therefore, the research exhibited in this manuscript tries to improve phishing website detection by tuning extreme learning model that utilizes the most relevant subset of phishing websites data sets features. To accomplish this goal, a novel diversity-oriented social network search algorithm has been developed and incorporated into a two-level cooperative framework. The proposed algorithm has been compared to six other cutting-edge metaheuristics algorithms, that were also implemented in the framework and tested under the same experimental conditions. All metaheuristics have been employed in level 1 of the devised framework to perform the feature selection task. The best-obtained subset of features has then been used as the input to the framework level 2, where all algorithms perform tuning of extreme learning machine. Tuning is referring to the number of neurons in the hidden layers and weights and biases initialization. For evaluation purposes, three phishing websites data sets of different sizes and the number of classes, retrieved from UCI and Kaggle repositories, were employed and all methods are compared in terms of classification error, separately for layers 1 and 2 over several independent runs, and detailed metrics of the final outcomes (output of layer 2), including precision, recall, f1 score, receiver operating characteristics and precision–recall area under the curves. Furthermore, an additional experiment is also conducted, where only layer 2 of the proposed framework is used, to establish metaheuristics performance for extreme machine learning tuning with all features, which represents a large-scale NP-hard global optimization challenge. Finally, according to the results of statistical tests, final research findings suggest that the proposed diversity-oriented social network search metaheuristics on average obtains better achievements than competitors for both challenges and all data sets. Finally, the SHapley Additive exPlanations analysis of the best-performing model was applied to determine the most influential features.

Abstract Pancreatic cancer is associated with higher mortality rates due to insufficient diagnosis techniques, often diagnosed at an advanced stage when effective treatment is no longer possible. Therefore, automated systems that can detect cancer early are crucial to improve diagnosis and treatment outcomes. In the medical field, several algorithms have been put into use. Valid and interpretable data are essential for effective diagnosis and therapy. There is much room for cutting-edge computer systems to develop. The main objective of this research is to predict pancreatic cancer early using deep learning and metaheuristic techniques. This research aims to create a deep learning and metaheuristic techniques-based system to predict pancreatic cancer early by analyzing medical imaging data, mainly CT scans, and identifying vital features and cancerous growths in the pancreas using Convolutional Neural Network (CNN) and YOLO model-based CNN (YCNN) models. Once diagnosed, the disease cannot be effectively treated, and its progression is unpredictable. That's why there's been a push in recent years to implement fully automated systems that can sense cancer at a prior stage and improve diagnosis and treatment. The paper aims to evaluate the effectiveness of the novel YCNN approach compared to other modern methods in predicting pancreatic cancer. To predict the vital features from the CT scan and the proportion of cancer feasts in the pancreas using the threshold parameters booked as markers. This paper employs a deep learning approach called a Convolutional Neural network (CNN) model to predict pancreatic cancer images. In addition, we use the YOLO model-based CNN (YCNN) to aid in the categorization process. Both biomarkers and CT image dataset is used for testing. The YCNN method was shown to perform well by a cent percent of accuracy compared to other modern techniques in a thorough review of comparative findings.

Abstract Breast cancer is a hazardous disease that should be seriously tackled to reduce its danger in all aspects of the world. Therefore, several imaging ways to detect this disease were considered, but the produced images need to be accurately processed to effectively detect it. Image segmentation is an indispensable step in image processing to segment the homogenous regions that have similar features such as brightness, color, texture, contrast, form, and size. Several techniques like region-based, threshold-based, edge-based, and feature-based clustering have been developed for image segmentation; however, thresholding, which is divided into two classes: bilevel and multilevel, won the highest attention by the researchers due to its simplicity, ease of use and accuracy. The multilevel thresholding-based image segmentation is difficult to be tackled using traditional techniques, especially with increasing the threshold level; therefore, the researchers pay attention to the metaheuristic algorithms which could overcome several hard problems in a reasonable time. In this paper, a new hybrid metaheuristic algorithm based on integrating the jellyfish search algorithm with an effective improvement method is proposed for segmenting the color images of breast cancer, namely the hybrid jellyfish search algorithm HJSO. Experiments are extensively performed to appear the superiority of the proposed algorithm, including validating its performance using various breast cancer images and conducting an extensive comparison with several rival algorithms to explore its effectiveness. The experimental findings, including various performance metrics like fitness values, CPU time, Peak signal-to-noise ratio (PSNR), standard deviation, Features similarity index (FSIM), and Structural similarity index (SSIM), totally show the efficiency of HJSO.

Currently, visual data security plays a significant role in various fields, especially in medical imaging. Addressing the challenges associated with limited key space and vulnerability to different types of attacks within current encryption schemes, this work proposes an optimal compression-encryption scheme for large medical images that incorporates elements of Archimedes' optimization algorithm, discrete orthogonal Hahn moments, chaotic systems, and DNA coding. The primary aim of this study is to develop an optimal and exceptionally resilient compression-encryption scheme capable of countering various attack types effectively. This approach is structured into three principal phases: a compression phase harnessing the efficiencies of Hahn's discrete orthogonal moments (HMs) in signal and image representation, coupled with the Archimedes optimization algorithm (AO) to ensure optimal tuning of polynomial parameters (a, b) for superior image reconstruction quality. The encryption phase is performed on the compressed image, using hyperchaotic memristive 4-D (HCM-4D), adapted logistics map (ALM) and DNA coding. Initially, the adapted logistics map is responsible for generating random sequences linked to the compressed image. Subsequently, chaotic sequences originating from the hyperchaotic 4-D memristive system govern both random sequences and DNA processes. The optimization phase, facilitated by the AO algorithm, focuses on minimizing the value of the objective function (correlation) on the compressed and encrypted images. Ultimately, the image with the lowest correlation value is designated as the optimal compressed-encrypted representation.The simulation results clearly illustrate the resilience of the AO algorithm when juxtaposed with other optimization algorithms, especially with respect to convergence speed and computational efficiency. On the other hand, the proposed compression approach demonstrated exceptional efficiency in compressing medical images, offering us the possibility to achieve impressive compression ratio (CR) as well as exceptional quality in decompressed images, evident thanks to high PSNR values. In addition, security analyze demonstrate that the proposed compression-encryption benefits from a larger key space and superior resistance against different types of attacks. Furthermore, our approach was subjected to a comparative analysis alongside various encryption method. These comparisons demonstrate that our encryption algorithm surpasses others in terms of both security and effectiveness.

Diabetic Retinopathy (DR) is a major type of eye defect that is caused by abnormalities in the blood vessels within the retinal tissue. Early detection by automatic approach using modern methodologies helps prevent consequences like vision loss. So, this research has developed an effective segmentation approach known as Level-set Based Adaptive-active Contour Segmentation (LBACS) to segment the images by improving the boundary conditions and detecting the edges using Level Set Method with Improved Boundary Indicator Function (LSMIBIF) and Adaptive-Active Counter Model (AACM). For evaluating the DR system, the information is collected from the publically available datasets named as Indian Diabetic Retinopathy Image Dataset (IDRiD) and Diabetic Retinopathy Database 1 (DIARETDB 1). Then the collected images are pre-processed using a Gaussian filter, edge detection sharpening, Contrast enhancement, and Luminosity enhancement to eliminate the noises/interferences, and data imbalance that exists in the available dataset. After that, the noise-free data are processed for segmentation by using the Level set-based active contour segmentation technique. Then, the segmented images are given to the feature extraction stage where Gray Level Co-occurrence Matrix (GLCM), Local ternary, and binary patterns are employed to extract the features from the segmented image. Finally, extracted features are given as input to the classification stage where Long Short-Term Memory (LSTM) is utilized to categorize various classes of DR. The result analysis evidently shows that the proposed LBACS-LSTM achieved better results in overall metrics. The accuracy of the proposed LBACS-LSTM for IDRiD and DIARETDB 1 datasets is 99.43% and 97.39%, respectively which is comparably higher than the existing approaches such as Three-dimensional semantic model, Delimiting Segmentation Approach Using Knowledge Learning (DSA-KL), K-Nearest Neighbor (KNN), Computer aided method and Chronological Tunicate Swarm Algorithm with Stacked Auto Encoder (CTSA-SAE).

This paper presents a binary variant of a novel physics-based meta-heuristic optimization algorithm, namely Light spectrum optimizer (LSO), for tackling both the 0–1 knapsack (KP01) and multidimensional knapsack problems (MKP). Because of the continuous nature of the standard LSO that contradicts the knapsack problem's discrete nature, two various transfer functions: S-shaped and X-shaped, are used to convert the continuous values produced by LSO into discrete ones. Some binary solutions produced by the binary LSO (BLSO) may be infeasible, so an improvement-repair strategy is used to convert those solutions into feasible ones by making some improvements on them. Moreover, the classical LSO was modified in this study to propose a new binary variant, namely BMLSO, with better exploration and exploitation operators for overcoming the knapsack problems. Additionally, a novel method, which simulates the swarm intelligence behaviors and the simulated binary crossover (SBX) to accelerate the convergence speed with avoiding stuck into local minima, has been proposed for producing a new binary variant of MLSO known as BHLSO. To verify the performance of the proposed binary variants of LSO, 45 benchmark instances of KP01 and 30 benchmark instances of MKP used commonly in the literature have been used in our experiments. The experimental findings show the superiority of BHLSO for both KP01 and MKP compared with several well-known algorithms in terms of CPU time, convergence speed, and accuracy.

In this paper, a new analytical approach based on an explicit model with one shape parameter has been proposed to forecast the peak power of the photovoltaic modules (PV) under varying operating conditions. A new analytical model of shape parameter has been developed according the relationship between the parameters of the explicit model and those of the single diode model (SDM). Furthermore, a novel open circuit voltage model as a function of solar irradiation and PV module temperature has been proposed. Temporal variations of PV module temperature and solar irradiation during one reference day have been used to extract the explicit model parameters and then to forecast the peak power for all other days. The proposed method is validated using measured data of different PV module technologies operating outdoor recorded by National Renewable Energy Laboratory (NREL). The results have shown a good agreement between the experimental and the optimized data of the I-V characteristics and the maximum power point for a reference day and the normalized error has not exceed 2.9%. Moreover, the predicted values of maximum power point in two other arbitrary days have a good agreement with experimental ones, and the normalized error has not exceeded 3.6%.

The past decades witness a tremendous exchange in data and information in almost all domains. This leads to the need for applying data security to ensure information safety during communication. One of the main used technique is the steganography. Steganography is a technique that involves hiding information within objects, such as images, audio, video, or 3D objects, without leaving any noticeable alterations. We propose a 3D steganographic technique that increases security using Gray-code sequence and a Least Significant Bit technique. We construct the 64-binary representation for the 3D cover-object. A Gray-code sequence defined the 3D object vertices that will be utilized for concealing the information. The binary representation of the information is to be concealed in the least significant bits of either the x- or the y-components of the defined vertices. The least significant bits, are the last two bits in the binary representation of the vertex components. Exploitation the binary representation, gives us the capability of increasing the data security, and the data capacity. The proposed steganographic technique has been evaluated through multiple evaluation metrics to assess its performance; including Mean Square Error Ratio, Peak Signal-to-Noise Ratio, Histogram, and Normalized Correlation Experimental results, indicate that the security level of the proposed technique is superior comparing to several existed techniques. Moreover, when testing against some common attacks such as the noise, the median, the Gaussian and the Laplacian filters; the results show the efficiency and the robustness of the proposed technique.

Hot topic trends have become increasingly important in the era of social media, as these trends can spread rapidly through online platforms and significantly impact public discourse and behavior. As a result, the scope of distributed representations has expanded in machine learning and natural language processing. As these approaches can be used to effectively identify and analyze hot topic trends in large datasets. However, previous research has shown that analyzing sequential periods in data streams to detect hot topic trends can be challenging, particularly when dealing with large datasets. Moreover, existing methods often fail to accurately capture the semantic relationships between words over different time periods, limiting their effectiveness in trend prediction and relationship analysis. This paper aims to utilize a distributed representations approach to detect hot topic trends in streaming text data. For this purpose, we build a sequential evolution model for a streaming news website to identify hot topic trends in streaming text data. Additionally, we create a visual display model and knowledge graph to further enhance our proposed approach. To achieve this, we begin by collecting streaming news data from the web and dividing it chronologically into several datasets. In addition, word2vec models are built in different periods for each dataset. Finally, we compare the relationship of any target word in sequential word2vec models and analyze its evolutionary process. Experimental results show that the proposed method can detect hot topic trends and provide a graphical representation of any raw data that cannot be easily designed using traditional methods.

The accomplishment of blockchain has increased the focus on the various applications for simplifying the confidentiality and transaction sanctuary using the decentralized architecture via consensus mechanisms between different internet of things (IoT) nodes in daily increasing societal areas. The growth of blockchain lasted to grow and used to do compare technologies. The major shortcomings of blockchain is the lack of scalability in modern application settings. Holochain technology vends itself as a “thinking” exterior to blocks, and it is a peer-to-peer disseminated ledger technology. It works contrarily compared to the blockchain, and it offers an exclusive value in the existing market. IoT devices are continuously used in distributed environments, in various smart applications. The peer-to-peer IoT networks, connected to smart agricultural systems are exposed to the security issues. Specifically, the personal data of agricultural land records need protection against unauthorized access and eradicate corruption in land transactions. The Blockchain offers a possible solution based on distributed ledger, but it has scalability issues due to high storage and processing requirements with growing network size. Also data is not locally stored in a Blockchain. This paper studies the conventions of holochain technology, its architecture and challenges, and critical mechanisms of holochain applications. We also analyze the numerous models utilized for the implementation of protected transactions. We discuss an agent centric framework with distributed hash table for secured applications.

Abstract Industrial Internet of Things (IIoT)-based systems have become an important part of industry consortium systems because of their rapid growth and wide-ranging application. Various physical objects that are interconnected in the IIoT network communicate with each other and simplify the process of decision-making by observing and analyzing the surrounding environment. While making such intelligent decisions, devices need to transfer and communicate data with each other. However, as devices involved in IIoT networks grow and the methods of connections diversify, the traditional security frameworks face many shortcomings, including vulnerabilities to attack, lags in data, sharing data, and lack of proper authentication. Blockchain technology has the potential to empower safe data distribution of big data generated by the IIoT. Prevailing data-sharing methods in blockchain only concentrate on the data interchanging among parties, not on the efficiency in sharing, and storing. Hence an element-based K-harmonic means clustering algorithm (CA) is proposed for the effective sharing of data among the entities along with an algorithm named underweight data block (UDB) for overcoming the obstacle of storage space. The performance metrics considered for the evaluation of the proposed framework are the sum of squared error (SSE), time complexity with respect to different m values, and storage complexity with CPU utilization. The results have experimented with MATLAB 2018a simulation environment. The proposed model has better sharing, and storing based on blockchain technology, which is appropriate IIoT.

The parameter assessment of solar cells and photovoltaic (PV) modules is a challenging task due to the non-linearity behavior of the current–voltage (I–V) characteristic curve. This paper presents two hybrid nature-inspired algorithms for estimating the unknown parameters of the Single-Diode Model (SDM), and Double-Diode Model (DDM). These algorithms are based on borrowed exploration and exploitation schemes from three well-known optimization algorithms: Whale optimization algorithm (WOA), Marine Predators Algorithm (MPA), and Generalized Normal Distribution Optimization (GNDO) algorithm. The first proposed algorithm is called Marine-Whale-Generalized (MWG) algorithm. In addition, MWG is effectively integrated with novel exploration and exploitation schemes to further its exploration and exploitation operators in a new variant known as (MWGG). A solar cell from RTC France and five commercial PV module models, including Photowatt-PWP201 (PWP), Ultra 85-P (Ultra), and STM6-40/36 (STM), are being used to test the efficacy and efficiency of the proposed algorithms. The experimental findings proved that MWGG is more accurate and faster at convergent results compared to other comparators.

Internet of Medical Things (IoMT) systems generate medical data transmissions between patients, medical experts, and medical centers over public networks, which require high levels of security to protect the content of medical images and the personal information they contain. In this paper, we propose a new stego image encryption scheme based on a new secret image compression method, wavelet transformation, QR decomposition of the cover image, and a new chaotic map. The secret image is compressed by the Hahn-Krawtchouk hybrid quaternion square moments (HK-HQSM), which are optimized by a new hybrid metaheuristic algorithm based on the Salp Swarm Algorithm (SSA) and the Arithmetic Optimization Algorithm (AOA). To increase the security level when transmitting the proposed stego images over public networks, we introduce a new chaotic map based on the 2D fractional Henon map to encrypt the stego image. To demonstrate the effectiveness of the proposed steganography scheme for IoMT, we implemented this scheme on a low-cost Raspberry Pi 4 hardware board. The results of the performed numerical experiments show that our method is secure and provides exceptional robustness against common standard image processing attacks (steganalysis attacks). The results also demonstrate that our strategy is able to work efficiently and quickly when implemented on a Raspberry Pi board.

This editorial aims to summarize the special issue entitled "Sustainable Solutions for Internet of Things Using Artificial Intelligence and Blockchain in Future Networks", which deals with the impacts of recent infrastructure development using the Internet of things. This special issue consists of four scientific articles.

Developing an appropriate model for accurate prediction of energy consumption is very essential for developing an effective energy management system for residential buildings. In view of this, the Short-term Load Forecasting (STLF) of household appliances has been performing an important role in supervising and managing energy in the residential community. In the domain of big data analytics, data-driven load forecasting approaches have realized an amazing performance in the recognition of patterns of residential electric loads and forecasting energy consumption. Nevertheless, current research emphasizes the use of powerful feature-engineering methods, which are ineffective and result in low generalization performance. Further, considering the differences in the consumption behavior of various home appliances, it is unfeasible to discover energy consumption characteristics physically in the power system. Thus, this study addresses the problems of STLF using a novel two-stream deep learning (DL) model called STLF-Net. The first stream is designed with Gated Recurrent Units (GRUs) to learn and capture the long-term temporal representations of the energy utilization data. Simultaneously, in the second stream, the short-term information and positional representations are modeled using a stack of temporal convolutional (TC) modules. The TC module is designated using dilated causal convolutions and residual connection to enable efficient feature extraction while alleviating the gradient vanishing issues. The learned representations from the two streams are fused and subsequently passed to several dense layers to generate the final hour-ahead load forecasts. Experimental assessments on two public energy consumption predictions datasets (IHEPC and AEP) demonstrated the superior performance of the STLF-Net over the recent cutting-edge data-driven approaches.

Abstract One of the major challenges in photovoltaic (PV) systems is extracting the maximum power from the PV array, especially when they operate under partial shading conditions (PSCs). To address this challenge, this paper introduces a novel hybrid maximum power point tracking (MPPT) method based on grey wolf optimization and particle swarm optimization (GWO–PSO) techniques. The developed MPPT technique not only avoids the common disadvantages of conventional MPPT techniques (such as perturb and observe (P&O) and incremental conductance) but also provides a simple and robust MPPT scheme to effectively handle partial shading in PV systems, since it requires only two control parameters, and its convergence to the global maximum power point (GMPP) is independent of the search process's initial conditions. The feasibility and effectiveness of the hybrid GWO–PSO-based MPPT method are verified via a co-simulation technique that combines MATLAB/SIMULINK and PSIM software environments, while comparing its performance against GWO, PSO and P&O based MPPT methods. The simulation results carried out under dynamic environmental conditions have shown the satisfactory effectiveness of the hybrid MPPT method in terms of tracking accuracy, convergence speed to GMPP and efficiency, compared to other methods.

Abstract There are several multicriteria decision-making (MCDM) approaches presented in the literature with their characteristics. Although traditional MCDM approaches are considered a proper implementation to select the best alternative from available types, they failed to consider uncertainty which is quite high and desires to be thoughtfully measured in the selection process. This research focuses on extending MCDM in the neutrosophic environment using axiomatic design (AD) as a novel contribution to selecting appropriate Computed Tomography (CT) devices. We present a new linguistic scale for evaluating criteria and alternatives based on single-valued triangular neutrosophic numbers (SVTrN). The proposed approach is superior to other existing approaches due to its simplicity and ability to simulate natural human thinking via considering truth, indeterminacy, and falsity degrees. Then, applying it will increase the value of imaging for medical decision-making and decrease needless costs. So, this study can be valuable to researchers by helping them consider the appropriate medical imaging system selection problem theoretically under uncertainty, and for governments and organizations to design better satisfying medical imaging evaluation systems.

With the whirlwind evolution of technology, the quantity of stored data within datasets is rapidly expanding. As a result, extracting crucial and relevant information from said datasets is a gruelling task. Feature selection is a critical preprocessing task for machine learning to reduce the excess data in a set. This research presents a novel quasi-reflection learning arithmetic optimization algorithm - firefly search, an enhanced version of the original arithmetic optimization algorithm. Quasi-reflection learning mechanism was implemented for enhancement of population diversity, while firefly algorithm metaheuristics were used to improve the exploitation abilities of the original arithmetic optimization algorithm. The aim of this wrapper-based method is to tackle a specific classification problem by selecting an optimal feature subset. The proposed algorithm is tested and compared with various well-known methods on ten unconstrained benchmark functions, then on twenty-one standard datasets gathered from the University of California, Irvine Repository and Arizona State University. Additionally, the proposed approach is applied to the Corona disease dataset. The experimental results verify the improvements of the presented method and their statistical significance.

In smart cities, the fast increase in automobiles has caused congestion, pollution, and disruptions in the transportation of commodities. Each year, there are more fatalities and cases of permanent impairment due to everyday road accidents. To control traffic congestion, provide secure data transmission also detecting accidents the IoT-based Traffic Management System is used. To identify, gather, and send data, autonomous cars, and intelligent gadgets are equipped with an IoT-based ITM system with a group of sensors. The transport system is being improved via machine learning. In this work, an Adaptive Traffic Management system (ATM) with an accident alert sound system (AALS) is used for managing traffic congestion and detecting the accident. For secure traffic data transmission Secure Early Traffic-Related EveNt Detection (SEE-TREND) is used. The design makes use of several scenarios to address every potential problem with the transportation system. The suggested ATM model continuously modifies the timing of traffic signals based on the volume of traffic and anticipated movements from neighboring junctions. By progressively allowing cars to pass green lights, it considerably reduces traveling time. It also relieves traffic congestion by creating a seamless transition. The results of the trial show that the suggested ATM system fared noticeably better than the traditional traffic-management method and will be a leader in transportation planning for smart-city-based transportation systems. The suggested ATM-ALTREND solution provides secure traffic data transmission that decreases traffic jams and vehicle wait times, lowers accident rates, and enhances the entire travel experience.

Abstract Impacts of blending fusel oil with gasoline on fuel combustion have been investigated experimentally in the current research to evaluate engine performance improvement and exhaust emission. Tested fuel include F10, F20 (10% and 20% of fusel oil by volume) and pure gasoline as baseline fuel have been used to operate 4-cylinder SI engine at increasing engine speed and constant throttle valve of 45%. The present results reveal a shorter combustion duration and better engine performance with F10 over engine speeds with maximum value of 33.9% for the engine brake thermal efficiency. The lowest BSFC of 251 g/kW h was recorded at 3500 rpm engine speed also with F10. All blended fuel have almost similar COVIMEP. Less NOx emission was measured with F10 at 4500 engine speed compared to gasoline. However, CO emissions reduced while higher CO2 was observed with introducing fusel oil in the blend. Moreover, HC emission increased an average by 11% over speed range and the highest value was achieved with 10% fusel oil addition compared to 20% and pure gasoline. Accordingly, higher oxygen content of fusel oil and octane number contribute to improve combustion of fuel mixture.

Abstract In recent years, the improvement of photovoltaic water pumping system (PVWPS) efficiency takes the considerable interest of researchers due to its operating based on cleaner electrical energy production. In this paper, a new approach based on fuzzy logic controller incorporating loss minimization technique applied to the induction machine (IM) is developed for PVWPS applications. The proposed control selects the optimal flux magnitude by minimization of the IM losses. Moreover, Variable step size perturb and observe method is introduced. The suitability of the proposed control is approved by reducing the absorbed current; therefore, the motor losses are minimized and the efficiency is improved. The proposed control strategy is compared with the method without losses minimization. The comparison results illustrate the effectiveness of the proposed method based on losses minimization regarding the electrical speed, absorbed current, flow water and developed flux. A processor-in-the-loop (PIL) test is effectuated as an experimental test of the proposed method. It consists in implementing the generated C code on the STM32F4 discovery board. The obtained results from the embedded board are similar to numerical simulation results.

The world is undergoing a thoughtful revolution with the arrival of the intelligent information era. The central realms accompanying smart living such as transportation, entertainment, healthcare and smart cities are projected to improve service quality assuring a high-end user experience. Future mobile networks are projected to foster the future of ubiquitously connected data-intensive intelligent society powered with complete automation by seamless integrating of all sorts of wireless networks spread over the ground, underwater, air and space. This special issue aims to bring together foremost researchers in academia and engineering from various backgrounds to disseminate to the technical community an outline of emerging technologies, advanced architectures, challenges, open issues and future directions of modern networks in artificial intelligence, internet of things, and blockchain-based applications.

Several massive real-time services could be offered to the residents of smart cities by the incorporation of collaborative applications. All such applications require latency-aware network services for accomplishing various needs of the smart city environment. It requires technological enhancements to the existing mechanisms to serve better in smart environments. Such enhancements to the prevailing approaches also opened a wide range of chances to the intruders. Among such infringes, the identity-based attack is the most powerful attack, which may directly affect the credibility of legitimate network components. Such attackers aim to steal the identity of other legitimate entities. Thus, the prevailing trust-based approaches cannot withstand such attacks. The proposed Edge-based approach, EBAD has been designed for smart city environments, as a robust prevention mechanism for identity theft and misuse. EBAD is efficient enough to identify the Sybil attacker nodes and the early identification of such attacker nodes will nullify the probability of performing the Sybil attack over a Cooperative blackmailing attack (SA-CBA). EBAD uses an Edge-based accusation analysis approach to assess the malicious behavior of the network entities. The major part of the required computations has been placed at the edge node for reducing the computational overload of the end devices. Finally, the efficiency of EBAD has been examined under a malicious environment.

The localization of Wireless sensor networks (WSNs) has been recognized as one of the most challenging problems to overcome. Thus, much work has been given to solving this difficult problem. In emergency services, navigational systems, civil/military surveillance etc., locating the signal source in a WSN is essential. A novel approach for sensor node localization using range-based localization methodology has been proposed to overcome this issue. The problem is expressed in the form of a maximum probability distribution function. The use of an RSSI-based Time Difference of Arrival (TDOA) measurement model, along with the Chan algorithm, is used to find the coordinates of unknown nodes has been proposed. With the help of ultra-wideband, this research aims to develop new and precise localization algorithms for wireless sensor networks (WSNs). This work offers localization using two-hybrid localization algorithms, i.e., ELPSO (Ensemble learning particle swarm optimization) and PSO- BPNN (Back-propagation neural network optimized by particle swarm optimization). Further, the error optimization accuracy has been compared between those algorithms using simulations. The proposed techniques consistently offer a better localization accuracy than the conventional algorithms available in the literature. The new localization methods with optimal techniques reduce the error value to a minimal distance. The distance value of localization error is nearly2.7cms compared to other designs from the literature. It is noted as significantly less.

[This corrects the article DOI: 10.1371/journal.pone.0250959.].

Dental images are utilized to gather significant signs that are useful in disease diagnosis, treatment, and forensic examination. Many dental age and gender detection procedures have limitations, such as minimal accuracy and dependability. Gender identification techniques aren’t well studied, despite the fact that classification effectiveness and accuracy are low. The suggested approach takes into account the shortcomings of the current system. Deep learning techniques can successfully resolve issues that occurred in other classifiers. Human gender and age identification is a crucial process in the fields of forensics, anthropology, and bio archeology. The image preparation and feature extraction process are accomplished by deep learning algorithms. The performance of classification is improved by minimizing the occurrence of loss with the assistance of a spike neuron-based convolutional neural network (SN-CNN). The performance of SN-CNN is examined by comparing the performance metrics with the existing state-of-art techniques. SN-CNN-based classifier achieved 99.6% accuracy over existing techniques.