Search

Constructed wetlands (CWs) are considered one of the most efficient solutions for treating wastewater and reusing water resources. The present study aimed to monitor the performance of an integrated constructed wetland (ICW) located at NUST, H-12 campus, Islamabad. It has a sedimentation tank for pre-treatment, eight ponds planted with different vegetation (Typha latifolia, Pistia stratiotes, and Centella asiatica), and a FILTER (filtration and irrigated cropping for land treatment and effluent reuse) technology. The objectives of the present study were divided into the analysis of the physicochemical parameters, microbial analysis, and comparison with the past studies on the same ICW. The samples for physicochemical and microbial analysis were collected from four points, i.e., the inlet, sedimentation tank, pond 8, and collection tank. The results indicated that average temperature, pH, and DO range between 23.95-24.20, 6.95-7.20, and 2.25-3.10, respectively. Whereas other parameters showed the removal efficiency as follows: EC 10%, turbidity 73.99%, TSS 79.16%, TDS 32.60%, TS 47.22%, COD 69.01%, NO3-N 52.76%, NO2-N 50.53%, TKN 63.50%, and PO₄³⁻ 41.24%. Gram-negative bacteria with dominating microbial species such as Salmonella, Shigella, and E. coli were found to have a removal rate of up to 95%. The findings indicate that ICW is effective at removing pathogenic microorganisms, organic contaminants, nutrients, and maintaining temperature and pH changes in the water. Moreover, the comparison with past studies showed that the performance of ICW has been maintained over the years.

For organizing and analyzing massive amounts of data and revealing hidden patterns and structures, clustering is a crucial approach. This paper examines unique strategies for rapid clustering, highlighting the problems and possibilities in this area. The paper includes a brief introduction to clustering, discussing various clustering algorithms, improvements in handling various data types, and appropriate evaluation metrics. It then highlights the unsupervised nature of clustering and emphasizes its importance in many different fields, including customer segmentation, market research, and anomaly detection. This review emphasizes ongoing efforts to address these issues through research and suggests exciting directions for future investigations. By examining the advancements, challenges, and future opportunities in clustering, this research aims to increase awareness of cutting-edge approaches and encourage additional innovations in this essential field of data analysis and pattern identification. It highlights the need for resilience to noise and outliers, domain knowledge integration, scalable and efficient algorithms, and interpretable clustering technologies. In addition to managing high-dimensional data, creating incremental and online clustering techniques, and investigating deep learning-based algorithms, the study suggests future research areas. Additionally featured are real-world applications from several sectors. Although clustering approaches have made a substantial contribution, more research is necessary to solve their limitations and fully realize their promise for data analysis.

Emotional health significantly impacts physical and psychological well-being, with emotional imbalances and cognitive disorders leading to various health issues. Timely diagnosis of mental illnesses is crucial for preventing severe disorders and enhancing medical care quality. Physiological signals, such as Electrocardiograms (ECG) and Electroencephalograms (EEG), which reflect cardiac and neuronal activities, are reliable for emotion recognition as they are less susceptible to manipulation than physical signals. Galvanic Skin Response (GSR) is also closely linked to emotional states. Researchers have developed various methods for classifying signals to detect emotions. However, these signals are susceptible to noise and are inherently non-stationary, meaning they change constantly over time. Consequently, emotions can vary rapidly. Traditional techniques for analyzing physiological signals may not be adequate to study the dynamic changes in emotional states. This research introduces a deep learning approach using a combination of advanced signal processing and machine learning to analyze physiological signals for emotion recognition. We propose a CNN-Vision Transformer (CVT) based method with ensemble classification. The process involves decomposing signals into segments, removing noise, and extracting features using 1D CNN and Vision Transformers. These features are integrated into a single vector for classification by an ensemble of LSTM, ELM, and SVM classifiers. The outputs are then synthesized using Model Agnostic Meta Learning (MAML) to improve prediction accuracy. Validated on AMIGOS and DEAP datasets with 10-fold cross-validation, our method achieved accuracies up to 98.2%, sensitivity of 99.15%, and specificity of 99.53%, outperforming existing emotion charting techniques. This novel method provides significant improvements 3 to 4% in the accuracy, sensitivity, and specificity of emotion detection, leveraging physiological signals for comprehensive emotional assessments.

In the field of real-time systems, component-based models for mixed criticality systems (MCS) on multicore platform are gaining significant attention of the researchers from the recent past. The concept of mixed-criticality is firstly applied on single core systems but after gaining attention, it evolved to multicore platform. Initially, the tasks of MCS executes in low mode however if a task having high criticality does not its scheduling requirements complete its low mode, then the system switch to high mode. In high mode, only high critical tasks executes its high mode scheduling requirements, while all low tasks are discarded from further execution. In the realm of MCS, the component-based model have high importance and has been used in large and complex real-time systems. In component-based model, the component of a system is splatted into multiple components. In this study, a new component-based scheduling approach is proposed for multicore MCS. In the multicore mixed-criticality compositional framework, special emphasis is given on deriving the supply bound function, which represents available core supply, and the demand bound function, which indicates the requirements of resources for scheduling. A mixed-criticality multicore compositional framework (MMCF) is introduced for component-based MCS having tightened deadline. For the proposed strategy, a schedulability analysis is conducted, ensuring that the system can be scheduled only if the supply bound function is equal to or less than the demand bound function. On a 4-core platform, the scheduleability for the three scheduling strategies i.e. MMCF, MC-Partition, and Global are shown at different utilization levels of resource. 100% schedulability is shown by the proposed MMCF, MC-Partition, and global techniques for target utilizations of 0.7, 0.5, and 0.4, respectively. For a given utilization U=0.6, the proposed MMCF approach shows 100 % schedulability, while the MC-partition and global approaches show 90% and 20% schedulabilities respectively. It shows that the proposed MMCF approach schedules 10% and 80% more task sets than the MC-partition and global approaches respectively. The experimental results reveal that the proposed MMCF approach offers better schedulability than the other two approaches.

Conventional centralized optimization and management approaches may not work well in an emerging and distributed energy system with a high penetration of electric vehicles and green energy sources. The usage of blockchain technology is growing as a strong competitor as it can provide this kind of market with a transparent, secure, and efficient transactional platform. Nevertheless, most energy systems usually depend on complex mathematical optimization, which is poorly incorporated into blockchain applications. Moreover, time-sensitive message dissemination requirements, resource-intensiveness, high computational load, and communication overhead of the traditional blockchain consensus mechanisms make it difficult to connect with real-time vehicular networks. Here, we employ Proof of Intelligence (PoI), a novel prosumer-centric blockchain consensus mechanism to develop a comprehensive model of trust based on commitments of supply and demand through the application of peer-to-peer energy exchange with effective and dynamic integration of renewable sources and electric vehicles both in the day ahead and real-time energy trading platforms. Additionally, the PoI smart contract is developed to seamlessly incorporate mathematical optimization with an increased level of security, scalability, throughput, and low confirmation latency of transactions achieved through the reduced effort involved in finding and confirming the optimal solution in comparison with conventional blockchain consensus mechanisms.

The current age is witnessing an unprecedented dependence on data originating from humans through the devices that comprise the Internet of Things. The data collected by these devices are used for many purposes, including predictive maintenance, smart analytics, preventive healthcare, disaster protection, and increased operational efficiency and performance. However, most applications and systems that rely on user data to achieve their business objectives fail to comply with privacy regulations and expose users to numerous privacy threats. Such privacy breaches raise concerns about the legitimacy of the data being processed. Hence, this paper reviews some notable techniques for transparently, securely, and privately separating and sharing personally identifiable and non-personally identifiable information in various domains. One of the key findings of this study is that, despite various advantages, none of the existing techniques or data sharing applications preserve data/user privacy throughout the data life cycle. Another significant issue is the lack of transparency for data subjects during the collection, storage, and processing of private data. In addition, as privacy is unique to every user, there cannot be a single autonomous solution to identify and secure personally identifiable information for users of a particular application, system, or people living in different states/countries. Therefore, this research suggests a way forward to prevent the leakage of personally identifiable information at various stages of the data life cycle in compliance with some of the common privacy regulations around the world. The proposed approach aims to empower data owners to select, share, monitor, and control access to their data. In addition, the data owner is a stakeholder and a party to all data sharing contracts related to his personal data. The proposed solution has broad security and privacy controls that can be tailored to the privacy needs of specific applications.

Regression testing is carried out to ensure that changes or enhancements are not impacting previous working software. Deciding how much retesting is required after modifications, bug fixes or before product deployments are difficult. Therefore, Test Case Selection (TCS) select the satisfactory subset of modified test cases from already executed test suites. The testing primary concerns in TCS for regression testing are efficiency (i.e., coverage, fault detection ability, redundancy) and time. The first challenge in TCS concerns the efficiency of multi-objective test case selection. The second challenge is to improve the execution time to detect the changes in a test suite, which makes it impractical to use these efficiency measures as a single goal for TCS. To overcome these challenges, there is a need to introduce an efficient detection-based multi-objective framework to improve the Time and efficiency of TCS. A multi-objective advanced and efficient regression test case selection (ARTeCS) framework is devised to improve the time performance and efficiency of a given TCS objective relative to the other TCS approaches. An algorithm to detect the changes in test cases using multiple TCS objectives. This comparison found that the enhanced ARTeCS algorithm improves redundancy efficiency by 44.02%. The selection technique showed ARTeCS improved the modified change detection by 43.00%, whereas the Hybrid Whale Optimization Algorithm (HWOA) stated 23% and ACO showed 33% only for selected test cases. Regarding average for fault detection, ACO scores 21%, HWOA scores 11%, and ARTeCS scores 31.08% with total execution times of 12, 21 and 09 seconds, respectively. In conclusion, the multiple-objective ARTeCS framework with four test suite selection parameters is more efficient than the existing multi-objective selection framework.

Wafer mappings (WM) help diagnose low-yield issues in semiconductor production by offering vital information about process anomalies. As integrated circuits continue to grow in complexity, doing efficient yield analyses is becoming more essential but also more difficult. Semiconductor manufacturers require constant attention to reliability and efficiency. Using the capabilities of convolutional neural network (CNN) models improved by hierarchical attention module (HAM), wafer hotspot detection is achieved throughout the fabrication process. In an effort to achieve accurate hotspot detection, this study examines a variety of model combinations, including CNN, CNN+long short-term memory (LSTM) LSTM, CNN+Autoencoder, CNN+artificial neural network (ANN), LSTM+HAM, Autoencoder+HAM, ANN+HAM, and CNN+HAM. Data augmentation strategies are utilized to enhance the model’s resilience by optimizing its performance on a variety of datasets. Experimental results indicate a superior performance of 94.58% accuracy using the CNN+HAM model. K-fold cross-validation results using 3, 5, 7, and 10 folds indicate mean accuracy of 94.66%, 94.67%, 94.66%, and 94.66%, for the proposed approach, respectively. The proposed model performs better than recent existing works on wafer hotspot detection. Performance comparison with existing models further validates its robustness and performance.

New approaches to software testing are required due to the rising complexity of today’s software applications and the rapid growth of software engineering practices. Among these methods, one that has shown promise is the introduction of Natural Language Processing (NLP) tools to software testing practices. NLP has witnessed a rise in popularity within all IT fields, especially in software engineering, where its use has improved the way we extract information from textual data. The goal of this systematic literature review (SLR) is to provide an in-depth analysis of the present body of the literature on the expanding subject of NLP-based software testing. Through a repeatable process, that takes into account the quality of the research, we examined 24 papers extracted from Web of Science and Scopus databases to extract insights about the usage of NLP techniques in the field of software testing. Requirements analysis and test case generation popped up as the most hot topics in the field. We also explored NLP techniques, software testing types, machine/deep learning algorithms, and NLP tools and frameworks used in the studied body of literature. This study also stressed some recurrent open challenges that need further work in future research such as the generalization of the NLP algorithm across domains and languages and the ambiguity in the natural language requirements. Software testing professionals and researchers can get important insights from the findings of this SLR, which will help them comprehend the advantages and challenges of using NLP in software testing.

Advanced Persistent Threats commonly use Domain Generation Algorithms to evade advanced detection methods to establish communication with their command and control servers. To overcome the DNS protocol legitimacy breach, several Domain Generation Algorithms detection methods have been proposed. To solve the problem of DGA malware detection amicably, Deep Learning based detection schemes attracted researchers’ interest recently. However, Deep Learning has already achieved optimal results and the gap is identified as fine-tuning of Deep Learning model hyper-parameters. The proposed solution is focusing on a model specific hyper-parameter known as the gradient optimizer. Gradient Optimisers are broadly categorised into Stochastic Gradient and Adaptive Moment based Gradient. Moment-based Gradient optimizer approaches are identified with suffering from weight decay and leading to poor generalization. Adaptive Moment (Adam) has improved with weight Decay as AdamW. To optimise moment-based gradient optimizers, Adam and AdamW are analyzed deeply. To optimize the functioning of AdamW, we present AdamW+, a novel solution for detecting DGA algorithms through re-implementing and nullifying the weight decay in AdamW. AdamW+ has been successfully implemented and shown promising results compared to Adam and AdamW optimizers in practice. AdamW+ preserved the properties of Adaptive Optimizer Adam while simplifying the weight decay implementation of AdamW. Empirical analysis has proved that AdamW+ has outperformed Adam and AdamW. The experimental result have substantiated that the proposed algorithm achieves the best accuracy result.

Humans can carry various diseases, some of which are poorly understood and lack comprehensive solutions. Such a disease can exists in human eye that can affect one or both eyes is diabetic retinopathy (DR) which can impair function, vision, and eventually result in permanent blindness. It is one of those complex complexities. Therefore, early detection of DR can significantly reduce the risk of vision impairment by appropriate treatment and necessary precautions. The primary aim of this study is to leverage cutting-edge models trained on diverse image datasets and propose a CNN model that demonstrates comparable performance. Specifically, we employ transfer learning models such as DenseNet121, Xception, Resnet50, VGG16, VGG19, and InceptionV3, and machine learning models such as SVM, and neural network models like (RNN) for binary and multi-class classification. It has been shown that the proposed approach of multi-label classification with softmax functions and categorical cross-entropy works more effectively, yielding perfect accuracy, precision, and recall values. In particular, Xception achieved an impressive 82% accuracy among all the transfer learning models, setting a new benchmark for the dataset used. However, our proposed CNN model shows superior performance, achieving an accuracy of 95.27% on this dataset, surpassing the state-of-the-art Xception model. Moreover, for single-label (binary classifications), our proposed model achieved perfect accuracy as well. Through exploration of these advances, our objective is to provide a comprehensive overview of the leading methods for the early detection of DR. The aim is to discuss the challenges associated with these methods and highlight potential enhancements. In essence, this paper provides a high-level perspective on the integration of deep learning techniques and machine learning models, coupled with explainable artificial intelligence (XAI) and gradient-weighted class activation mapping (Grad-CAM). We present insights into their respective accuracy and the challenges they face. We anticipate that these insights will prove valuable to researchers and practitioners in the field. Our ambition is that this in-depth study and comparison of models will inform and inspire future research endeavors, ultimately leading to enhanced disease detection in medical imaging and thereby assisting healthcare professionals.

Deepfake text known as synthetic text, involves using artificial intelligence (AI)-generated text to create fabricated information or imitate actual individuals. Twitter tweets related to deepfake can be used for many malicious intents, including impersonation, creating fake news, and spreading misinformation. The main goal of this investigation is to detect people’s sentiments related to deepfake technology with an advanced technique. A novel sentiment majority voting classifier (SMVC) is proposed for the sentiment labeling of collected tweets. The proposed SMVC selects the final sentiment from three lexicon-based models TextBlob, valence-aware dictionary and sentiment reasoner (VADER), and AFINN using a majority voting mechanism. For sentiment classification, we propose a novel transfer feature where embedding features are fed to a long short-term memory (LSTM), and decision tree (DT) models and outputs are combined into a single feature set. Extensive experiments show that transfer learning-based feature engineering results in the highest performance. The logistic regression outperforms with the highest accuracy of 98.9% with minimum computational complexity. The sentiment classification performance of each applied model is validated using the k-fold cross-validations. Moreover, performance assessment with existing state-of-the-art models is also carried out to show the robustness of the proposed technique.

Efficient traffic management has become a major concern within the framework of smart city projects. However, the increasing complexity of data exchanges and the growing importance of big data makes this task more challenging. Vehicular ad hoc networks (VANETs) face various challenges, including the management of massive data generated by different entities in their environment. In this context, a proposal is put forth for a real-time anomaly detection system with parallel data processing, thereby speeding up data processing. This approach accurately computes vehicle density for each section at any given time, enabling precise traffic management and the provision of information to vehicles regarding traffic density and the safest route to their destination. Furthermore, a machine learning-based prediction system has been developed to mitigate congestion problems and reduce accident risks. Simulations demonstrate that the proposed solution effectively addresses transportation issues while maintaining low latency and high precision.

The amalgamation of ubiquity, mobility, computing prowess, storage, and communication of the portable electronic devices including smartphones, wearable devices, tablets have significantly altered the fabric of human existence. The software applications for these mobile devices possess the capability to disseminate and receive information, thereby enable the development of applications that may execute in collaborative manner. However, in situations with ad-hoc connectivity unavailability of infrastructure and communication breakdown are common, which inhibit information sharing across the devices, and hence affect the applications running in the collaborative spaces. Further the applications developers face challenges while developing reliable collaborative applications that can seamlessly execute in ad-hoc communication settings with recurring issues with device connectivity. Therefore, it is necessary to provide a reliable framework to the application developers which provides such an abstraction that they may create robust applications without any concern about random communication disruptions. To address the aforementioned issues, this article proposes a framework that facilitates the development of reliable and efficient collaborative applications that communicate across devices while working in ad-hoc device connectivity settings. The proposed framework provides an abstraction of some major components including service exposition, service registration, storage, and synchronization while ensuring robustness to the challenges posed by the intermittent connectivity failures. The efficacy of the framework has been demonstrated through a detailed experimental evaluation using a custom developed collaborative application run in a variety of operational settings over different portable devices in ad-hoc settings. The results reveal that the framework not only successfully mitigates the challenges posed by the ad-hoc device connectivity, but also the abstractions provided by the framework not only enables the application developers create customized robust collaborative applications with significantly fewer lines of code, but also without worrying about the intermittent communication failures among the involved devices.

In the emerging and well-rooted field of Vehicular Adhoc-Networks (VANETs), the imperative of secure content exchange via Vehicle-to-Vehicle (V2V) communication for better safety emphasizes the importance of strong communication protocols. Implementing Information-Centric Networking (ICN) in VANETs allows for more efficient resource utilization via name-based content requests and delivery techniques. However, the dynamic and open nature of VANETs creates major security risks, necessitating rigorous defence against malicious attacks. To address these challenges, we introduce a novel trust-aware VANET framework that integrates ICN and Blockchain for content security. Our method uses authenticated vehicle data to ensure content integrity across the network, resulting in effective and efficient security measures. Through precise simulation, our technique exhibits resilience against malicious assaults by improving bandwidth utilization, throughput transactions, network content utilization, and content delivery in the face of hostile scenarios. The experimental results confirm the efficacy and feasibility of our proposed technique, highlighting its potential to improve VANET content security in real-world applications.

Online platforms are fostering social interaction, but unfortunately, this has given rise to antisocial behaviors such as cyberbullying, trolling, and hate speech on a global scale. The detection of hate and aggression has become a vital aspect of combating cyberbullying and cyberharassment. Cyberbullying involves using aggressive and offensive language including rude, insulting, hateful, and teasing comments to harm individuals on social media platforms. Human moderation is both slow and expensive, making it impractical in the face of rapidly growing data. Automatic detection systems are essential to curb trolling effectively. This research deals with the challenge of automatically identifying cyberbullying in tweets from a publicly available cyberbullying dataset. This research work employs robustly optimized bidirectional encoder representations from the transformers approach (RoBERTa), utilizing global vectors for word representation (GloVe) word embedding features. The proposed approach is further compared with the state-of-the-art machine, deep, and transformer-based learning approaches with the FastText word embedding approach. Statistical results demonstrate that the proposed model outperforms others, achieving a 95% accuracy for detecting cyberbullying tweets. In addition, the model obtains 95%, 97%, and 96% for precision, recall, and F1 score, respectively. Results from k-fold cross-validation further affirm the supremacy of the proposed model with a mean accuracy of 95.07%.

Real-time audio/video transmission through Internet media is an important part of communication. Due to bandwidth limitations and a noisy environment, delivery of multimedia content to a remote location is not 100% guaranteed. These limitations are the basic cause of missing packets which affect the Quality of Service (QoS). A protocol for the recovery of lost packets is described in [Maxemchuk, Nicholas F., K. Padmanabhan, and S. Lo. “A cooperative packet recovery protocol for multicast video.” Network Protocols, 1997. Proc. of 1997 International Conference on. IEEE]. This protocol claims significant improvement in QoS. We formally specify the protocol in a network of timed automata. By model-checking (A mathematical technique), we find that packet recovery is not always there. In this article, We report such scenarios of malfunctioning in the protocol when the size of multimedia contents is known (e.g., live video/audio broadcasting) and middle-level servers have different rates of data sending and receiving. We formulate the effect of inter-packet delay and transmission speed difference on a buffer.

Software defect identification (SDI) is a key part of improving the quality of software projects and lowering the risks that along with maintenance. It does identify the software defect causes that have not been reached yet to get sufficient results. On the other hand, many researchers have recently developed several models, including NN, ML, DL, advanced CNN, and LSTM, to enhance the effectiveness of defect prediction. Due to an insufficient dataset size, repeated investigations, and no longer appropriate baseline selection, the research on the CNN model was unable to produce reliable results. In addition, XAI a well-known explainability approach creates deep models in computer vision, as well as successfully handles the software defect prediction that is easy for humans to understand. To address these issues, firstly we have used SMOTE for preprocessing which was collected from the NASA repository; categorical and numerical data. Secondly, we have experimented with software defect prediction using 1D-CNN and 2D-CNN named lightweight CNN (LCNN). Subsequently, evaluation we have employed a 100-repetition holdout validation. For the cross-validation setup, we utilized the 1D-CNN model was $20\times 1$ , and for the 2D-CNN model, it was $4\times 5 \times 1$ . After that, the results of the experiment were compared and assessed in terms of accuracy, MSE, and AUC. The result shows that 2D-CNN shows 1.36% better contrast with 1D-CNN. Thirdly, we have conducted research on the identification of software defect features via LIME and SHAP in XAI stand as state-of-the-art techniques. However, we cannot use 2D-CNN because it involves more complex relationships, making it challenging to create transparent explanations. That is why we have realized that 1D-CNN will superior result to explain the root cause of software feature identifications. Finally, LIME provides accurate visualization of software defect features in contrast with SHAP, as well as it helps the stakeholders of the software industry easily find actual root causes of software defect identification.

The agricultural sector is more vulnerable to the adverse effects of climate change and excessive pesticide application, posing a significant risk to global food security. Accurately predicting crop yields is essential for mitigating these risks and providing information on sustainable agricultural practices. This research presents a novel crop yield prediction system that utilizes a year’s worth of meteorological data, pesticide records, crop yield data, and machine learning techniques. We employed rigorous methods to gather, clean, and enhance data and then trained and evaluated three machine learning models: Gradient Boosting, K-Nearest Neighbors, and Multivariate Logistic Regression. We utilized the GridSearchCV method for hyper-parameter tweaking to identify the most suitable hyper-parameter throughout K-Fold cross-validation, aiming to improve the model’s performance by avoiding overfitting. The remarkable performance of the Gradient Boosting model, with an almost flawless coefficient of determination ( $R^{2}$ ) of 99.99%, demonstrates its promise for precise yield prediction. This research also examined the correlation between projected and actual crop yields and identified the ideal meteorological conditions. It paves the way for data-driven methods in sustainable agriculture and resource distribution, ultimately leading to a more secure future with respect to food availability and resilience to climate change.

This study proposes a novel light detection and ranging (LiDAR) sensor. The sensor integrates a variable field-of-view (FoV) function by utilizing optical orthogonal frequency-division multiple access (OOFDMA) to generate laser pulse streams and a Risley prism for steering. Using this approach, the LiDAR sensor can adjust the scanning pattern and density of the point cloud to match different sizes, distances, and distributions of objects. To ensure security against external threats, the LiDAR sensor incorporates advanced encryption standards (AES) and wavelength selection techniques. Additionally, the sensor employs various methods to achieve accurate and reliable measurements while minimizing mutual interference between laser signals. This innovative sensor has the potential to enhance the reliability and accuracy of LiDAR technology in aerial applications, thus facilitating the development of more advanced urban air mobility (UAM) sensors for diverse applications. The study evaluated a prototype LiDAR sensor that utilizes a coded laser pulse stream and OOFDMA technology for distance measurement. The LiDAR sensor incorporates three laser diodes with different wavelengths and a Risley prism for steering. The experimental results demonstrate that the proposed LiDAR sensor outperforms existing sensors in terms of accuracy and precision.

Smart contracts are becoming increasingly popular for managing transactions or activities in fog computing environments. However, the use of smart contracts for registration and resource access granting is vulnerable to various types of attacks that can compromise their security. Detecting these attacks can be challenging, as attackers can use sophisticated techniques to evade detection. This research uses a machine learning-based approach for detecting different attacks on smart contracts used for registration and resource access granting in fog computing. Data is collected from online Ethereum’s official site “etherscan.io”. Different feature extraction methods and machine learning models are tested. Using accuracy, precision, recall, F1 score, cross-validation, and computational time, the performance of models is evaluated. Results indicate that extreme gradient boosting (XGB) and random forest (RF) provide the highest accuracy of 80% using the term frequency-inverse document frequency (TF-IDF) approach. The light gradient boost classifier provides the highest accuracy of 81% with the Bag of Word (BoW) approach. Similarly, the extra tree provides the highest accuracy of 83% using the N-gram technique. Furthermore, performance using TF-IDF is slightly poorer than BoW and N-gram, however, it has less computational complexity.

Medicinal plants are essential to healthcare since ancient times and are integral to developing drugs and other medical treatments. More than 25% of medicines in developed countries are produced from medicinal plants, while in developing countries, approximately 80% of individuals receive primary healthcare from these plants. Traditionally, these plants are identified manually by experts, which is tedious, time-consuming, subjective and dependent on the availability of experts. Furthermore, a wrong detection can result in serious health issues or death. This signifies the need for a more reliable approach to identifying medicinal plants, which is accurate and practical. Several automated methods were proposed previously, utilizing deep learning and traditional machine learning (TML) techniques, but they require singular leaf images and failed to achieve sufficient accuracy when demonstrated in a different setting. Capturing singular leaf images for each plant is also time-consuming and laborious. This paper presents a robust, accurate and practical system to identify medicinal plants from smartphone-captured plant images in the site of plants. The proposed system utilized a cascaded architecture to extract features using a pre-trained ResNet50 model, which were optimized using Particle Swarm Optimization (PSO) to classify the plants using a Support Vector Machine (SVM). The proposed ResNet50-PSO-SVM network classified seven medicinal plants with 99.60% accuracy, outperforming the state-of-the-art (99%). The system was demonstrated for three different smartphones, classifying an image in 0.15 seconds with 97.79% accuracy on average. The system’s high accuracy, rapid identification time and robustness ensured its practical use.

Diabetic retinopathy (DR) can be defined as visual impairment caused by prolonged diabetes affecting the blood vessels in the retina. Globally, it stands as the primary contributor to blindness, impacting approximately 191 million individuals. While prior research has addressed DR classification using retinal fundus images, existing methods often focus on isolated lesion detection, lacking a comprehensive framework for the simultaneous identification of all lesions. Previous studies concentrated on early-stage features like exudates, aneurysms, hemorrhages, and blood vessels, sidelining severe-stage lesions such as cotton wool spots, venous beading, very severe intraretinal microvascular abnormalities (IRMA), diffuse intraretinal hemorrhages, capillary degeneration, highly activated microglia, and retinal pigment epithelium (RPE) damage. In this study, a deep learning approach is proposed to classify DR fundus images by severity levels, utilizing GoogleNet and ResNet models based on adaptive particle swarm optimizer (APSO), for enhanced feature extraction. The extracted features from the hybrid model are further used with different machine learning models like random forest, support vector machine, decision tree, and linear regression models. Experimental results showcased the proposed hybrid framework outperforming advanced approaches with a remarkable 94% accuracy on the benchmark dataset. This method demonstrates potential enhancements in precision, recall, accuracy, and F1 score for different DR severity levels.

Due to exponential population growth, climate change, and an increasing demand for food, there is an unprecedented need for a timely, precise, and dependable assessment of crop yield on a large scale. Wheat, a staple crop worldwide, requires accurate and prompt prediction of its output for global food security. Traditionally, the development of empirical models for crop yield forecasting has relied on climate data, satellite data, or a combination of both. Despite the enhanced performance achieved by integrating satellite and climate data, the contributions from various sources (Climate, Soil, Socioeconomic, and Remote sensing) remain unclear. The lack of well-defined comparisons between the performance of regression-based approaches and different Machine Learning (ML) methods in yield prediction necessitates further investigation. This study addresses the gaps by combining data from multiple sources to forecast wheat yield in the Multan region in the Punjab province of Pakistan. The findings are compared to the benchmark provided by Crop Report Services (CRS) Punjab, with three widely used ML techniques (support vector machine (SVM), Random Forest (RF), and Least Absolute Shrinkage and Selection Operator (LASSO)) by integrating publicly available data within the GEE (Google Earth Engine) platform, including climate, satellite, soil properties, and spatial information data to develop alternative empirical models for yield prediction using data from 2017 to 2022, selecting the best attribute subset related to crop output. The district-level simulated yield data set was analyzed with three ML models (SVM, RF, and LASSO) as a function of seasonal weather, satellite, and soil. The results indicate that combining all datasets using three ML algorithms achieves better yield prediction performance ( $R^{2}$ : 0.74-0.88). Incorporating spatial information and other properties into benchmark models can improve the prediction from 0.08 to 0.12. Random forest outperformed the competitor models with a Root Mean Square Error (RMSE) of 0.05 q/ha and $R^{2}$ of 0.88. Comparative analysis shows that random forest with 97% and SVM with 93% yielded better results in the study area.

Cyber attacks are growing with the rapid development and wide use of internet technology. Botnet attack emerged as one of the most harmful attacks. Botnet identification is becoming challenging due to the numerous attack vectors and the ongoing evolution of viruses. As the Internet of Things (IoT) technology is developing rapidly, many network devices have been subject to botnet attacks leading to substantial losses in different sectors. Botnets pose serious risks to network security and deep learning models have shown potential for efficiently identifying botnet activity from network traffic data. In this research, a botnet identification system is proposed based on the stacking of artificial neural network (ANN), convolutional neural network (CNN), long short-term memory (LSTM), and recurrent neural network (RNN) (ACLR). The experiments are conducted by employing both the individual models, as well as, the proposed ACLR model for performance comparison. The UNSW-NB15 dataset is used for botnet attacks and contains nine different attack types including ‘Normal’, ‘Generic’, ‘Exploits’, ‘Fuzzers’, ‘DoS’, ‘Reconnaissance’, ‘Analysis’, ‘Backdoor’, ‘Shell code’ and ‘Worms’. Experimental results indicate the proposed ACLR model gains 0.9698 testing accuracy showing that it is successful in capturing the intricate patterns and characteristics of botnet attacks. The proposed ACLR model’s k values (3, 5, 7, and 10) for a K-fold cross-validation accuracy score is 0.9749 indicating that the model’s robustness and generalizability are demonstrated by k = 5. In addition, the proposed model detects botnets with a high receiver operating characteristic area under the curve (ROC-AUC) of 0.9934 and a precision-recall area under the curve (PR-AUC) of 0.9950. Performance comparison with existing state-of-the-art models further corroborates the superior performance of the proposed approach. The results of this research can be helpful against evolving threats and enhance cyber security procedures.

Pneumonia is a potentially life-threatening infectious disease that is typically diagnosed through physical examinations and diagnostic imaging techniques such as chest X-rays, ultrasounds or lung biopsies. Accurate diagnosis is crucial as wrong diagnosis, inadequate treatment or lack of treatment can cause serious consequences for patients and may become fatal. The advancements in deep learning have significantly contributed to aiding medical experts in diagnosing pneumonia by assisting in their decision-making process. By leveraging deep learning models, healthcare professionals can enhance diagnostic accuracy and make informed treatment decisions for patients suspected of having pneumonia. In this study, six deep learning models including CNN, InceptionResNetV2, Xception, VGG16, ResNet50 and EfficientNetV2L are implemented and evaluated. The study also incorporates the Adam optimizer, which effectively adjusts the epoch for all the models. The models are trained on a dataset of 5856 chest X-ray images and show 87.78%, 88.94%, 90.7%, 91.66%, 87.98% and 94.02% accuracy for CNN, InceptionResNetV2, Xception, VGG16, ResNet50 and EfficientNetV2L, respectively. Notably, EfficientNetV2L demonstrates the highest accuracy and proves its robustness for pneumonia detection. These findings highlight the potential of deep learning models in accurately detecting and predicting pneumonia based on chest X-ray images, providing valuable support in clinical decision-making and improving patient treatment.

Quora is an expanding online platform, that contains a growing collection of questions and answers generated by users. The content on this platform is managed by its users which involves creating, editing, and organization. Due to the vast number of users, it is not uncommon to find multiple questions with similar intents, leading to the problem of duplicate and identical questions. Detection of these duplicates could effectively lead to a more efficient search for high-quality answers, ultimately improving the user experience for both readers and writers on Quora. This study utilizes the dataset of Question Pairs for Quora obtained from Kaggle for identifying questions that are duplicates or identical. To vectorize the questions and for model training, six types of word embeddings are implemented including GoogleNewsVector, FastText crawl, FastText crawl sub-words, bidirectional encoder representations from transformers (BERT), robustly optimized BERT pretraining approach (RoBERTa), and embeddings from language models (ELMO) containing 100 dimensions. The Siamese Manhattan long short-term memory (MaLSTM) neural network model, where Ma is Manhattan distance, is applied with ELMO word embedding to predict duplicate questions in the dataset. Experimental results demonstrate that the proposed model attained an accuracy of 95.68% which surpasses the state-of-the-art models.

Unmanned aerial vehicles (UAVs) substantially rely on the utilization of global positioning systems (GPS) to navigate. A simulator for commercial GPS applications with false GPS signals can lead to the deviation of a GPS-guided drone from its planned path. As a result, an anti-spoofing technology is required to assure UAV operating safety. Several approaches have been developed to detect GPS spoofing, however, predominantly such methods rely on additional hardware. Using additional hardware might not be an ideal solution for small and low-capacity UAVs. Detecting signal spoofing attacks in small UAVS has significant importance. This study presents a stacked ensemble approach to detect GPS signal spoofing within the context of small UAVs. The initial phase involves outlining the sequential procedures for obtaining and preparing the GPS signal dataset, including details about the UAV hardware, blocker, data collection timing, environmental factors, and the utilization of z-score normalization for preprocessing. Then controlled simulation tests with varying experimental conditions are conducted and the model is built using a support vector machine and convolutional neural network. Additionally, a comprehensive comparative assessment is conducted to analyze the efficacy of the proposed model against traditional machine learning models. Experimental results demonstrate notably good performance by the proposed model with a 99.74% accuracy, showing its superior performance in the context of GPS signal spoofing in small UAVs.

Retinitis pigmentosa (RP) is a group of genetic retinal disorders characterized by progressive vision loss, culminating in blindness. Identifying pigment signs (PS) linked with RP is crucial for monitoring and possibly slowing the disease’s degenerative course. However, the segmentation and detection of PS are challenging due to the difficulty of distinguishing between PS and blood vessels and the variability in size, shape, and color of PS. Recently, advances in deep learning techniques have shown impressive results in medical image analysis, especially in ophthalmology. This study presents an approach for classifying pigment marks in color fundus images of RP using a modified squeeze-and-excitation ResNet (SE-ResNet) architecture. This variant synergizes the efficiency of residual skip connections with the robust attention mechanism of the SE block to amplify feature representation. The SE-ResNet model was fine-tuned to determine the optimal layer configuration that balances performance metrics and computational costs. We trained the proposed model on the RIPS dataset, which comprises images from patients diagnosed at various RP stages. Experimental results confirm the efficacy of the proposed model in classifying different types of pigment signs associated with RP. The model yielded performance metrics, such as accuracy, sensitivity, specificity, and f-measure of 99.16%, 97.70%, 96.93%, 90.47%, 99.37%, 97.80%, 97.44%, and 90.60% on the testing set, based on GT1 & GT2 respectively. Given its performance, this model is an excellent candidate for integration into computer-aided diagnostic systems for RP, aiming to enhance patient care and vision-related healthcare services.

The MQTTset dataset has been extensively investigated for enhancing anomaly detection in IoT-based systems, with a focus on identifying Denial of Service (DoS) attacks. The research addresses a critical gap in MQTT traffic anomaly detection by proposing the incorporation of the ‘source’ attribute from PCAP files and utilizing hand-crafted feature engineering techniques. Various filtering methods, including data conversion, attribute filtering, handling missing values, and scaling, are employed. Anomalies are categorized and prioritized based on frequency of occurrence, with a specific emphasis on DoS attacks. The study compares the performance of the decision tree and its eight variant models (ID3, C4.5, Random Forest, CatBoost, LightGBM, XGBoost, CART, and Gradient Boosting) for anomaly detection in IoT-based systems. Evaluation metrics such as prediction accuracy, F1 score, and computational times (training and testing) are utilized. Hyperparameter fine-tuning techniques like grid search and random search are applied to enhance model performance, accuracy, and reduce computational costs. Results indicate that the benchmark Decision Tree model achieved 92.57% accuracy and a 92.38% F1 score with training and testing times of 2.95 seconds and 0.86 seconds, respectively. The Feature Engineering (Modified) dataset demonstrated a substantial improvement, reaching 98.56% accuracy and a 98.50% F1 score, with comparable training and testing times of 0.70 seconds and 0.02 seconds. Furthermore, the Modified Decision Tree Algorithm significantly improved accuracy to 99.27%, F1 score to 99.26%, and reduced training time to 0.73 seconds and testing time to 0.14 seconds. The research contributes valuable insights into feature engineering and guides the selection of effective approaches for anomaly detection in IoT-based systems, providing early threat warnings and enhancing overall system security and reliability.

Quantum computing, a transformative field that emerged from quantum mechanics and computer science, has gained immense attention for its potential to revolutionize computation. This paper aims to address the fundamentals of quantum computing and provide a comprehensive guide for both novices and experts in the field of quantum computing. Beginning with the foundational principles of quantum computing, we introduce readers to the fundamental concepts of qubits, superposition, entanglement, interference, and noise. We explore quantum hardware, quantum gates, and basic quantum circuits. This study offers insight into the current phase of quantum computing, including the noisy intermediate-scale quantum (NISQ) era and its potential for solving real-world problems. Furthermore, we discuss the development of quantum algorithms and their applications, with a focus on famous algorithms like Shor’s algorithm and Grover’s algorithm. We also touch upon quantum computing’s impact on various industries, such as cryptography, optimization, machine learning, and material science. By the end of this paper, readers will have a solid understanding of quantum computing’s principles, applications, and the steps involved in developing quantum circuits. Our goal is to provide a valuable resource for those eager to embark on their quantum computing journey and for researchers looking to stay updated on this rapidly evolving field.

Introduction: Compound Muscle Action Potential Scan (CMAP) Scan is an electrophysiological method for diagnosing neuromuscular diseases with axonal loss. Significant differences between CMAPs are termed as Steps. The percentage ratio of all detected steps to the maximum CMAP, a parameter being evidence of motor unit loss and enlargement due to reinnervation is defined as Step Percentage. Materials and Methods: Motor neuron groups were created and stimulated gradually through a simulator software for CMAP Scan. CMAPs were utilized to compute the step sizes. Their cumulative sum greater than two standard deviations were taken for computing Step Percentage. The simulator data were exported for processing in a MATLABⓇ Code for these calculations and for computing regression coefficients of the model for step percentage and the number of axons by the Least Square Method. Results: The greatest step percentage value corresponded to the lowest motor unit number. A steep reduction was observed from 5 axons to 120 axons with increasing axon numbers. The step percentages converged to a steady-state value for the axon numbers between 120 and 300. Discussion and Conclusion: Step percentage values were found greater for lower axon numbers as in the case of Motor Unit loss in neurogenic diseases. They tended to decrease with increasing axon numbers approaching a steady-state value as the presence of intact Motor Units. A new algorithm was proposed to determine the lowest step size quantitatively rather than detecting by inspection as in routine clinical applications for estimating the step percentage. A mathematical model was built to demonstrate the relationship between the step percentage and the number of axons.

Requirements specifications written in natural language enable us to understand a program’s intended functionality, which we can then translate into operational software. At varying stages of requirement specification, multiple ambiguities emerge. Ambiguities may appear at several levels including the syntactic, semantic, domain, lexical, and pragmatic levels. The primary objective of this study is to identify requirements’ pragmatic ambiguity. Pragmatic ambiguity occurs when the same set of circumstances can be interpreted in multiple ways. It requires consideration of the context statement of the requirements. Prior research has developed methods for obtaining concepts based on individual nodes, so there is room for improvement in the requirements interpretation procedure. This research aims to develop a more effective model for identifying pragmatic ambiguity in requirement definition. To better interpret requirements, we introduced the Concept Maximum Matching (CMM) technique, which extracts concepts based on edges. The CMM technique significantly improves precision because it permits a more accurate interpretation of requirements based on the relative weight of their edges. Obtaining an F-measure score of 0.754 as opposed to 0.563 in existing models, the evaluation results demonstrate that CMM is a substantial improvement over the previous method.

In this research, we present two Numerical algorithms for studying the dynamics of spatially extended coupled nonlinear reaction-diffusion model. The difference in this work is to model a system of reacting and diffusing chemicals, and how to predict the dynamics of ecologically relevant behavior, including chaos. The goal can be achieved by applying a proposed staggered grid finite volume method for solving the Reaction model, rigorously validating the numerical method and grid generation techniques against established results. Additionally, we integrate an Alternating Direction Implicit formulation to compare the efficiency and accuracy of the model’s results. Dynamical system analysis, including linear stability analysis, is applied to comprehend the fundamental qualitative features of the inhibitor-activator system inherent in the coupled reaction-diffusion equations. Results, presented in tables and graphical representations, show that the schemes’ high accuracy at fourth-order precision in space and second-order in time, with conditional stability. Numerical results showed that the proposed finite volume approach was exceptionally proficient and accurate for tackling the two-dimensional nonlinear coupled reaction-diffusion model. Overall, the dialog highlights the significance of the proposed staggered grid finite approach and calculations for fathoming coupled reaction-diffusion equations are widely studied in biological and chemical systems of nonlinear differential equations.

Renewable energy is considered to be an alternate option for limiting the consumption of fossil fuel along with reducing environmental pollution. Among the possible renewable energy resources, solar energy is considered to be the key candidate as it is the most economical and energy efficient. Keeping in view its importance, there has been an exponential increase in energy harvesting using photovoltaic (PV) systems across the globe in recent years. However, to ensure optimal performance, system health monitoring is essential for such a system. Current traditional monitoring methods are laborious, expensive, time-consuming, and prone to error. To address the limitations of these approaches, the proposed work follows two main approaches. First, an effective deep-learning method is proposed for the identification of the types of cracks in the PV cell such as microcracks and deep cracks. In microcracks, the crack’s orientation is crucial and therefore classified accordingly. Next, the power analysis is performed based on the severity of the cracks. In case of deep cracks, it is observed that the output power efficiency is proportional to crack size. For crack identification, four deep learning models, namely U-net, LinkNet, FPN, and attention U-net, are trained, evaluated, and compared using an online public dataset of electroluminescence images. The efficiency of the models is evaluated using different metrics, including intersection over union (IoU) and F1-Score. These models are then subjected to an ensemble learning technique, which results in an accurate and robust segmentation, IoU, and F1-Score.

The rapid depletion of fossil fuels, increased electricity consumption, and global environmental concerns have led to shift electricity generation from non-renewable to renewable energy sources. Solar photovoltaic (PV) technology is increasing with significant land requirement. To conserve this valuable land and water evaporation, PV panels are being installed on water bodies such as irrigation canals, lakes and dams. Researchers have found that hybrid power generation systems are more efficient than single power generating system, thus by covering canals with solar panels and harnessing the kinetic energy of flowing water using hydrokinetic turbines (HKT), a massive amount of electricity can be generated. The Hybrid Optimization of Multiple Energy Resources (HOMER) software is used in this study to stimulate and acquire the best results and configuration for a hybrid PV/hydrokinetic system in district Sanghar of Sindh province in Pakistan. Model is designed by covering the 1 km canal surface with PV and the hydrokinetic turbines along with it. The overall potential for 1 km length of canal for both PV/hydrokinetic turbine system is found around 2.8 MW with payback period in 5.7 years and by saving 324.58 million cubic meters of water in terms of evaporation with annual saving in GHG emissions of 416,451.74 kg/yr.

Reconfigurable intelligent surface (RIS) is an emerging tool for 5G and wireless communication technologies that have attracted researchers' interest. However, the passive nature and the high number of reflecting elements in RIS result in a large pilot overhead, which makes channel estimation challenging in multi-user multiple-input multiple-output (MU-MIMO) wireless communication systems. Previous works have shown an improvement in reducing the pilot overhead by exploiting the structured sparsity in rows and columns, which was further improved by compensating offset among users in angular cascaded channels of RIS aided system. To further reduce the pilot overhead, we analyze and adopt coherence-optimized pilots for channel estimation and propose an algorithm to analyze the combined effect of low-coherence pilots with an optimum size of RIS elements for a given number of users, transmit antennas, and normalized error threshold performance. The simulation results illustrate better NMSE performance as compared to contemporary techniques.

Artificial intelligence (AI)-based models have emerged as powerful tools in financial markets, capable of reducing investment risks and aiding in selecting highly profitable stocks by achieving precise predictions. This holds immense value for investors, as it empowers them to make data-driven decisions. Identifying current and future trends in multi-class forecasting techniques employed within financial markets, particularly profitability analysis as an evaluation metric is important. The review focuses on examining stud-ies conducted between 2018 and 2023, sourced from three prominent academic databases. A meticulous three-stage approach was employed, encompassing the systematic planning, conduct, and analysis of the se-lected studies. Specifically, the analysis emphasizes technical assessment, profitability analysis, hybrid mod-eling, and the type of results generated by models. Articles were shortlisted based on inclusion and exclusion criteria, while a rigorous quality assessment through ten quality criteria questions, utilizing a Likert-type scale was employed to ensure methodological robustness. We observed that ensemble and hybrid models with long short-term memory (LSTM) and support vector machines (SVM) are being more adopted for financial trends and price prediction. Moreover, hybrid models employing AI algorithms for feature engineering have great potential at par with ensemble techniques. Most studies only employ performance metrics and lack utilization of profitability metrics or investment or trading strategy (simulated or real-time). Similarly, research on multi-class or output is severely lacking in financial forecasting and can be a good avenue for future research.

Software cost and effort estimation is one of the most significant tasks in the area of software engineering. Research conducted in this field has been evolving with new techniques that necessitate periodic comparative analyses. Software project success largely depends on accurate software cost estimation as it gives an idea of the challenges and risks involved in the development. The great diversity of ML and Non-ML techniques has generated a comparison and progressed into the integration of these techniques. Based on varying advantages it has become imperative to work out preferred estimation techniques to improve the project development process. This study aims to present a systematic literature review (SLR) to investigate the trends of the articles published in the recent one and a half decades and to propose a way forward. This systematic literature review has proposed a three-stage approach to plan (Tollgate approach), conduct (Likert type scale), and report the results from five renowned digital libraries. For the selected 52 articles, artificial neural network model (ANN) and constructive cost model (COCOMO) based approaches have been the favored techniques. The mean magnitude of relative error (MMRE) has been the preferred accuracy metric, software engineering, and project management are the most relevant fields, and the promise repository has been identified as the widely accessed database. This review is likely to be of value for the development, cost, and effort estimations.

The recent advancements in cyber technology have facilitated the global electronic sharing of healthcare data among various healthcare professionals, including clinicians, researchers, business administrators, and others. Fog computing is gaining popularity as a means of disseminating information across industries, especially in medicine and healthcare, due to its capability to manage vast amounts of information and data. The evolution of fog computing now allows it to be adaptable to various budget constraints within healthcare organizations, thanks to technological progress. This adaptation includes features like real-time data breach alerts and automated surveillance. As new communication and computing models emerge, fresh security and privacy concerns arise within medical and health-related data. Existing data privacy and security protocols have proven inadequate in preventing data leaks and theft attacks, especially those orchestrated by malicious parties. While medical data is stored in the cloud, legitimate entities’ authorized access to medical documents remains a significant concern. Therefore, this article designs an authentication and authorization scheme that safeguards the privacy of users’ medical information documents. In response to this challenge, we propose an innovative approach that leverages Decoy information technology and User Behavior profiling. This methodology aims to enhance the security of authorized data access within the Fog environment, ensuring the confidentiality of medical data. The results show that the proposed protocol is more secure against unauthorized access and security attacks and more computationally efficient than its counterparts.

In future mobility, robust obstacle detection is imperative for autonomous vehicles, fostering a reliance on vision-based data and the emergence of light detection and ranging (LiDAR) as a pivotal sensor. Despite challenges of cost and novelty, LiDAR’s unique capabilities find favor among automakers, except Tesla. Offering 3D imaging with superior resolution than radar, LiDAR holds potential significance as a perception sensor for safe and efficient transportation. Its 3D distance measurement using laser pulses and waveform analysis is vital for obstacle detection in autonomous vehicles. Techniques like scanning and flash LiDAR optimize point cloud acquisition, albeit with challenges in balancing resolution and frame rates. Because LiDAR measures the distance to an object using the time-of-flight, the idle listening time required to detect reflected waves increases in proportion to the maximum distance. Both, lateral angular resolution and frame rates are dependent on this idle listening time. Lateral angular resolution impacts LiDAR’s ability to detect objects. This study proposes an optical orthogonal frequency-division multiple access (OFDMA) LiDAR with a coded pulse technique to enhance the detection accuracy of objects. Simulation results demonstrate that the proposed OFDMA LiDAR overcoming false positives and mutual interference through pulse stream LiDARs and strategic approaches is crucial in LiDAR’s integration into future mobility systems.

Blockchain has shifted the paradigm of computer-based commercial applications during the last decade. Initially developed as a public ledger for Bitcoin transactions, it has already shown that it has the potential to revolutionize the world, where trust, security, privacy, and anonymity are the assurances. The data stored within the blockchain remains unchangeable, resistant to tampering, and distributed across multiple locations within a decentralized network. The existence and reliability of blockchain rely heavily on robust cryptographic primitives, as these are fundamental to its operation. While blockchain faces significant challenges in the ever-evolving landscape of hardware and software technologies, it has retained its reputation for being secure due to its underlying cryptographic primitives. The architecture of blockchain, various consensus protocols, and the impacts of quantum computing are also discussed here. This study reviews the existing academic literature on cryptographic primitives used in blockchain and endeavours to bridge the gaps and provide a detailed understanding of their role in blockchain security. An exploratory qualitative research methodology is used in this study and is based on the latest literature on the topics. The findings of this study provide a valuable reference to the knowledge body and enhance the comprehension of blockchain, cryptography, and cryptographic primitives in blockchain for both new and experienced researchers, enabling them to identify new opportunities and challenges in the domain.

Behavioral economics and artificial intelligence (AI) have been two rapidly growing fields of research over the past few years. While behavioral economics aims to combine concepts from psychology, sociology, and neuroscience with classical economic thoughts to understand human decision-making processes in the complex economic environment, AI on the other hand, focuses on creating intelligent machines that can mimic human cognitive abilities such as learning, problem-solving, decision-making, and language understanding. The intersection of these two fields has led to thrilling research theories and practical applications. This study provides a bibliometric analysis of the literature on AI and behavioral economics to gain insight into research trends in this field. We conducted this bibliometric analysis using the Web of Science database on articles published between 2012 and 2022 that were related to AI and behavioral economics. VOSviewer and Bibliometrix R package were utilized to identify influential authors, journals, institutions, and countries in the field. Network analysis was also performed to identify the main research themes and their interrelationships. The analysis revealed that the number of publications on AI and behavioral economics has been increasing steadily over the past decade. We found that most studies focused on customer and consumer behavior, including topics such as decision-making under uncertainty, neuroeconomics, and behavioral game theory, combined mainly with machine learning and deep learning techniques. We also identified several emerging themes, including the use of AI in nudging and prospect theory in behavioral finance, as well as undeveloped themes such as AI-driven behavioral macroeconomics. The findings suggests that there is a need for more interdisciplinary collaboration between researchers in behavioral economics and AI. We also suggest that future research on AI and behavioral economics further consider the ethical implications of using AI and behavioral insights in decision-making. This study can serve as a valuable resource for researchers interested in AI and behavioral economics.

Many stakeholders including students, teachers, and educational institutions, benefit from accurately predicting student performance and facilitating data-driven policies. In this field, providing users with accurate and understandable predictions is challenging, but equally important. The goals of this study are multifaceted: to identify students at-risk; to identify differences in assessment across different environments; methods for assessing students; and to determine the relationship between teacher employment status and student achievement. This study performs an empirical comparison of the performance and efficiency of ensemble classification methods based on bagging, boosting, stacking, and voting for successful predictions. An ensemble model is developed and validated using double, triple, and quadruple combinations of classification algorithms using Naive Bayes, J48 decision trees, Adaboost, logistics, and multilayer perceptron. This study uses primary quantitative data from the learning management system of a university in Pakistan to analyze the performance of these models. The boosted tree detection method outperforms bagged trees when the standard deviation is higher and the data size is large, while stacking is best for smaller datasets. Based on behavioral analysis results of students, academic advice can be given for selected case studies. These will help educational administrators and policymakers working in education to introduce new policies and curricula accordingly.

Machine learning has significantly improved disease diagnosis, enhancing the efficiency and accuracy of the healthcare system. One critical area where it proves beneficial is diagnosing brain tumors, a life-threatening disease, where early and accurate predictions can save lives. This study focuses on deploying a machine learning-based approach for brain tumor detection, utilizing Magnetic Resonance Imaging (MRI) features. We train the proposed model using 3D-UNet and 2D-UNet segmentation features extracted from MRI, encompassing shape, statistics, gray level size zone matrix, gray level dependence matrix, gray level co-occurrence matrix, and gray level run length matrix values. To improve performance, we propose a hybrid model that combines the strengths of two machine learning models, K-nearest neighbor (KNN) and gradient boosting classifier (GBC), using soft voting criteria. We combine them because, in cases where KNN exhibits poor performance for certain data points, GBC demonstrates significant performance, and vice versa, where GBC shows poor results, KNN performs significantly better. With 2D-UNet segmentation features, the model achieves a 64% accuracy. By training it on 3D-UNet segmentation features, we achieve a significant accuracy of 71% which surpasses existing state-of-the-art models that utilize 3D-UNet segmentation features.

The cryptocurrency, often known as virtual or digital currency, is one of the most significant breakthroughs brought about by digitalization. It has been mentioned recently, an innovative system for stockholders in particular. Cryptocurrencies of all kinds, including Bitcoin, Shib, Dogecoin, and Tether are decentralized. Categorization complicates decision-making (DM) as well as the transfer of uncertainty and digital currency validation. The multi-attribute group decision-making (MAGDM) method is defined in this article using the Frank weighted averaging and Frank weighted geometric aggregation operators (AOs). This research examines the uniqueness of the qRung orthopair fuzzy hypersoft set (qROFHSS) that is responsive to volatilities, vagueness, doubt, and inaccurate data. Additionally, some specific essential qROFHSS operational laws are defined in this study. The framework presented here is the best alternative for understanding electronic money. This research supports the difficulty of situations involving making choices that must take into account a variety of qualities and sub-attributes to select the best choice. We see that Bitcoin has a variety of applications and that cryptocurrencies have an excellent chance to emerge as a prominent benefit lesson in financial choice-making. In this paper, to demonstrate the viability of the suggested methodology we look at a case study on choosing the best currency out of these that are accessible to manage cryptocurrency. Comparative analysis shows that the suggested strategy is stable and good. We conclude that the proposed methodology provides a thorough and systematic approach to analyzing cryptocurrency. Finally, a numerical example is provided to show the method’s efficiency.

The rising deployment of software in automation and the cognitive skills of machines indicate a machine revolution in modern human civilization. Thus, diagnosing and predicting software faults is crucial to software reliability. In this paper, we first preprocessed four real datasets offered by National Aeronautics and Space Administration with twenty-one features using the Synthetic Minority Oversampling Technique and Label Encoding techniques. Subsequently, we experimented with thirteen software fault diagnosis Machine Learning (ML) models, i.e., Random Forest Regression, Linear Regression, Naïve Bayes, Decision Tree Classifier, Logistic Regression, KNeighbors Classifier, AdaBoost, Gradient Boosting Classifier, Gradient Boosting Regression, XGBR Regressor, XGBoost Classifier, Extra Trees Classifier and Support Vectors Machine after that, we compared each ML Model to select the best diagnostic model. Among them, XGBR outperformed, considering the accuracy, mean square error, and R2 score. We also used Explainable Artificial Intelligence (XAI), Local Interpretable Model (LIME), and SHapley Additive exPlanations (SHAP) to determine software fault features. We observed that Number of static invocations (nosi), Depth Inheritance Tree (dit), and Coupling Between Objects (cbo) features are the most affected software faults feature from datasets. For LIME, the average True positive of nosi is 40%, dit is 15%, and cbo is 20%; on the other hand, the SHAP average true positive value of nosi is 36%, cbo is 15%, and the norm true negative value of dit is 5%. Thus, LIME can afford the greatest impact on the model outcomes to identify features that are the most significant reasons for software defects.

Agricultural production is a cornerstone of national economies, and the prevalence of plant diseases poses a significant threat to crop yields. Timely disease detection is essential to mitigate these risks. However, manual plant observation methods are labor-intensive and time-consuming, necessitating a shift toward automated solutions. This study addresses the pressing problem of plant disease identification by leveraging advanced image processing techniques. This research begins with a comprehensive analysis of the pepper bell leaf disease dataset. Through a series of meticulously designed image processing steps, the dataset is normalized, enhancing its quality and consistency. Building upon this preprocessing, the UNET segmentation technique in conjunction with the InceptionV3 transfer learning model is employed. This novel approach yields exceptional results, with 99.48% accuracy, 99.97% precision, 99.99% recall, and 99.98% F1 scores. To objectively assess the significance of the proposed model, the performance is benchmarked against existing state-of-the-art models. The findings demonstrate the superiority of the proposed approach in the domain of plant disease identification. By automating the detection process, this research not only enhances efficiency but also enables early disease detection, thereby potentially contributing to the agricultural sector to identify crop disease and manage it efficiently.

A Smart City is characterized mainly as an efficient, technologically advanced, green, and socially informed city. An intelligent transportation system (ITS) is a subset area of smart cities that enhances the safety and mobility of road vehicles. It essentially makes travel more convenient, time-efficient and improves the citizens’ quality of life. Accurate and real-time traffic prediction enables law enforcement agencies with well-informed about traffic congestion. However, accurate traffic prediction has been considered a challenging issue. Traffic prediction has restrictions on road network topology and the patterns of dynamic change in time-series data. We propose a novel deep learning framework GCST-GRU, called graph convolutional Spatio-temporal gated recurrent unit, to determine the next traffic state from traffic data. The proposed model learns complex topological structures by capturing a) spatial dependencies from data by using the graph convolution operator, and b) temporal dependencies by using the GRU neural network. Experimental results demonstrate that our framework can obtain complex Spatio-temporal correlations efficiently from the traffic network and perform better than state-of-the-art baseline models on a real-world traffic dataset. The graphical visualization by using convolution operation over the neural network shows that the model outperforms the reachability of the 3-hops neighbor effect in the traffic data graph. Additionally, the training time of the proposed framework is better than the existing state-of-the-art deep learning studies.

Precision Agriculture (PA) techniques employing Internet of Things (IoT) can significantly improve crop yields and enhance productivity. Radio frequency identification (RFID) based IoT systems can enhance precision livestock farming by enabling livestock traceability and identification in large farms, but congestion is a major challenge. In such conditions, livestock estimation using RFID is a complex task because of high chances of tag collision due to significant increase in interference at the gates. Several anti-collision algorithms have been explored in recent past to address this issue with the aid of a single antenna. However, the throughput gains from a single antenna are limited particularly for dense scenarios like gates at a small ruminant farm. Therefore, we propose a multi-antenna RFID reader system with a dynamic frame slotted ALOHA (DFSA) anti-collision algorithm to address the tag collision problem by exploiting the spatial diversity of the multiple inputs and multiple outputs (MIMO) backscattering channel. The proposed technique is simulated in MATLAB for several tag population figures both with and without interference actions of various intensities. Results have shown that significant throughput gains can be achieved, in comparison with gains attained by anti-collision algorithms based on a single antenna. The simulation testbed enables us to evaluate the proposed technique for multiple receive antenna configurations.