ABSTRACT Autonomous vehicles (AVs) are one of the building blocks of modern intelligent transportation systems and have the potential to change some aspects related to mobility, safety, and operational efficiency. In this paper, we analyze recent progress in AV algorithms and simulation frameworks, emphasizing their roles in decision‐making processes, trajectory planning, object detection, and traffic optimization strategies. This paper provides technical discussions on the three core research questions: (RQ1) Major methodologies used for decision‐making, trajectory planning, and traffic optimization in AV communications (RQ2) Effectiveness of simulation platforms at closing the gap between algorithm testing and real‐world performance (RQ3) Challenges for the scalability and deployment of AV technologies. This paper collates the results from important individual research articles from scientific databases that present different methodologies including deep learning, reinforcement learning, and rule‐based approaches. The major conclusions pointed out in this regard include increased reliance on deep learning for complex task handling, its good effectiveness in hybrid learning paradigms, and, most importantly, the central role that simulations can play in assessing scalability and safety over a large range of conditions. Still, several challenges do remain, including high computational demands for real‐ time decision‐making, integration of V2X communication, and the gap between simulated and real‐world performance. This paper identifies the emerging trends, highlights the technical limitations, and provides a roadmap for AV development using robust algorithms with realistic simulations.

ABSTRACT Autonomous vehicles (AVs), including drones, rely on sensors, machine learning algorithms, and large datasets for perception, decision‐making, and control. However, the high dimensionality of these datasets increases computational load and hampers real‐time performance. In Unmanned Aerial Vehicle (UAV) systems, feature selection is critical for reducing complexity and enhancing processing efficiency, thereby enabling faster and more accurate decision‐making. In this study, we enhance the Harris Hawks Optimization (HHO) algorithm by introducing a novel ambush‐based operator to regulate selection pressure, resulting in an improved variant named AMHHO. The effectiveness of AMHHO is validated using IEEE CEC2019 benchmark functions and compared against several well‐known optimization algorithms. To further evaluate its robustness, ablation studies and sensitivity analyses are conducted to identify the most efficient AMHHO variants. Furthermore, a binary version of AMHHO (BAMHHO) is applied to ten high‐dimensional datasets and the UAV‐IDS‐2020 dataset for feature selection and classification tasks. BAMHHO is assessed based on classification accuracy, fitness value, feature selection ratio, and computation time, demonstrating superior performance across multiple datasets and outperforming state‐of‐the‐art methods. To rigorously evaluate the statistical significance of its results, Wilcoxon Signed‐Rank test is applied to compare BAMHHO with other well‐known algorithms, confirming the statistical superiority of BAMHHO. In conclusion, BAMHHO not only achieves effective performance on high‐dimensional datasets but also achieves 100% classification accuracy on the UAV‐IDS‐2020 dataset, all while maintaining an optimal balance between feature reduction and computational efficiency. These findings confirm BAMHHO's effectiveness in handling high‐dimensional data and highlight its potential for application in UAV‐based intrusion detection systems.

Neuro Degenerative Disorders (NDDs) involve progressive nerve cell loss, impacting functions like sensation, movement, memory, and cognition, posing life-threatening risks. Despite extensive research, viable therapies remain elusive due to complex pathophysiology. Artificial Intelligence (AI), particularly Machine Learning (ML) and Deep Learning (DL), shows promise in NDD diagnosis and treatment by leveraging vast datasets for accurate predictions. However, because AI models are “black boxes,” explainable AI (XAI) had to be created to make sure that physicians and patients would trust and accept it. Early detection is critical to stop degeneration and make things better for patients. Many in-depth studies on XAI are designed explicitly for NDDs. Existing research does not constantly look at how to interpret NDDs, how to evaluate them, or how to keep them safe. This paper fills in these gaps by looking at and grouping XAI methods for different NDDs, to make them easier to understand and use in medical settings. In this paper, we look at the interpretability methods used in various NDD studies. The methods are split into five groups based on the conditions they are used to treat: Frontotemporal Dementia (FTD), Multiple Sclerosis (MS), Amyotrophic Lateral Sclerosis (ALS), and Alzheimer's Disease (AD). It organizes XAI methods into groups and talks about their pros, cons, and clinical importance. The study also finds some important research gaps. For example, it says that there are no good security frameworks and that XAI is hard to use in real-life healthcare settings. By giving helpful information and a plan for future research, this paper shows how XAI could change how NDDs are found, treated, and predicted. AI technologies will be used more in healthcare, and this will help us learn more about these challenging conditions.

Abstract Natural disasters are becoming more frequent and more severe as a result of global warming. It is critical to take precautions before disasters, to gather and analyze information simultaneously while they are happening, and to make accurate assessments after them given that the deaths and injuries brought on by such disasters both leave lasting traumas in the life of society and damage the economy. Internet of Things (IoT) technology, is a young field that can assist intelligent safety-critical systems with data collection, processing in cloud edge data centers, and application of prediction methodologies for discovering key points and unexpected patterns using 5G technology. With the use of a cloud-based prediction algorithm for disaster management in the IoT environment, this study seeks to quickly process the data that is gathered during disasters and to speed up the analysis that will be done both during and after the disasters. An Optimized Ensemble Bagged Tree (OEBT) algorithm with ANOVA-based feature selection is developed for this aim. The experimental results show that accuracy, F1-Score, precision, and recall of the proposed OEBT algorithm utilizing the US Natural Disasters Dataset are 97.9%, 78.3%, 98.7%, and 78.9%, respectively. Comparisons with decision tree, logistic regression, and the traditional ensemble techniques are made. The suggested algorithm outperforms them all in terms of success rates.

The Social Internet of Things (S-IoT) paradigm is focused on topic of the Internet of Things (IoT), which accelerates the object issues by working with the concept of social networks. Searching and finding a new object in the community are considered to manage the number of friends and complex relationships between them and affect the ability to navigate at the cloud-edge layer, and resources, such as battery lifetime of S-IoT devices and energy resources, are important challenges in this field. In the processing of social messages of remote devices, increasing the battery life of devices that require such requirements plays the most important role. In this research, a collaboration scenario is presented to consider object attributes, friend’s functions and intelligent friend selection among objects for group messaging. First, a general reference model is designed and presented to select a friend to access group message remote processing services and minimize cloud-edge resources. The simulation results show that, for the correct communication of friends at the edge of the network and in each service discovery, according to the length of the path in the network, it is possible to establish stable communication and make better service with the least possible. The results show that if we want to develop a method for friendship between objects in communication in cloud computing, the proposed method can greatly improve the effectiveness of providing reliable message processing types.

In recent years, the Internet of Things (IoT) developments have made it one of the most important technologies. The exponential growth of data and increasing the number of latency-sensitive applications has necessitated a new approach to support these applications. The emerging fog computing architecture has partially addressed the issue of latency and other limitations of the IoT-based cloud computing paradigm. In order to achieve high-quality services and high system performance, an appropriate and efficient task scheduling method is needed, in addition, the energy consumption of computing devices should be considered. In this article, a constraint bi-objective optimization problem is designed to minimize the servers’ energy consumption and overall response time simultaneously. Then, to solve this problem, by introducing a recombination operator and modifying NSGA-II, a directed non-dominated sorting genetic algorithm, called D-NSGA-II is proposed. This algorithm can control the selection pressure of agents, and balance the exploration and exploitation abilities of the algorithm using this new operator. To evaluate the performance of this algorithm, it is compared with well-known meta-heuristic algorithms. The experimental results demonstrate the D-NSGA-II has better performance than other algorithms. It can also respond to all requests before their deadline.

Most devices in the Internet of Things (IoT) work on unsafe networks and are constrained by limited computing, power, and storage resources. Since the existing centralized signature schemes cannot address the challenges to security and efficiency in IoT identification, this article proposes IdenMultiSig, a decentralized multi-signature protocol that combines identity-based signature (IBS) with Schnorr scheme under discrete logarithms on elliptic curves. First, to solve the problem of offline or faulty devices under unstable networks, we introduce a novel improvement of the existing Schnorr scheme by introducing a threshold Merkle tree for the verification with only$m$valid signatures among$n$participants ($m$–$n$tree), while hiding the real identity to protect the data security and privacy of IoT nodes. Furthermore, to prevent dishonest or malicious behavior of the private key generator (PKG), a consortium blockchain is innovatively applied to replace the traditional PKG as a decentralized and trusted private key issuer. Finally, the proposed scheme is proven to be unforgeable against forgery signature attacks in the random oracle model (ROM) under the elliptic curve discrete logarithm (ECDL) assumption. Theoretical analysis and experimental results show that our scheme matches or outperforms existing research studies in privacy protection, offline device support, decentralized PKG, and provable security.

With the prevalence of Intelligent Transportation Systems (ITS), massive sensors are deployed on roadside, vehicles, and infrastructures. One key challenge is imputing several different types of missing entries in spatial-temporal traffic data to meet the high-quality demand of data science applied in Cooperative-ITS (C-ITS) since accurate data recovery is critical to many downstream tasks in ITSs, such as traffic monitoring and decision making. For such, it is proposed in this article solutions to three kinds of data recovery tasks in a unified model via spatial-temporal aware Graph Neural Networks (GNNs), named Spatial-Temporal Aware Data Recovery Network (STAR), enabling a real-time and inductive inference. A residual gated temporal convolution network is designed to permit the proposed model to learn the temporal pattern from long sequences with masks and an adaptive memory-based attention model for utilizing implicit spatial correlation. To further exploit the generalization power of GNNs, a sampling-based method is adopted to train the proposed model to be robust and inductive for online servicing. Extensive numerical experiments on two real-world spatial-temporal traffic datasets are performed, and results show that the proposed STAR model consistently outperforms other baselines at 1.5-2.5 times on all kinds of imputation tasks. Moreover, STAR can support recovery data for 2 to 5 hours, with its performance barely unchanged, and has comparable performance in transfer learning and time-series forecast. Experimental results demonstrate that STAR provides adequate performance and rich features for multiple data recovery tasks under the C-ITS scenario.

introduction Share on Introduction to the Special Section on Internet of Behavior for Emerging Technologies Authors: Mu-Yen Chen National Cheng Kung University, Taiwan National Cheng Kung University, Taiwan 0000-0002-3945-4363View Profile , Vincenzo Piuri University of Milan, Italy University of Milan, Italy 0000-0003-3178-8198View Profile , Alireza Souri Haliç University, Turkey Haliç University, Turkey 0000-0001-8314-9051View Profile , Mohammad Shojafar University of Surrey, UK University of Surrey, UK 0000-0003-3284-5086View Profile Authors Info & Claims ACM Transactions on Sensor NetworksVolume 19Issue 2Article No.: 23pp 1–3https://doi.org/10.1145/3589021Published:16 May 2023Publication History 0citation21DownloadsMetricsTotal Citations0Total Downloads21Last 12 Months21Last 6 weeks21 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteGet Access

This paper is aimed at improving the performance of the word recognition system (WRS) of handwritten Arabic text by extracting features in the frequency domain using the Stationary Wavelet Transform (SWT) method using machine learning, which is a wavelet transform approach created to compensate for the absence of translation invariance in the Discrete Wavelets Transform (DWT) method. The proposed SWT-WRS of Arabic handwritten text consists of three main processes: word normalization, feature extraction based on SWT, and recognition. The proposed SWT-WRS based on the SWT method is evaluated on the IFN/ENIT database applying the Gaussian, linear, and polynomial support vector machine, the k-nearest neighbors, and ANN classifiers. ANN performance was assessed by applying the Bayesian Regularization (BR) and Levenberg-Marquardt (LM) training methods. Numerous wavelet transform (WT) families are applied, and the results prove that level 19 of the Daubechies family is the best WT family for the proposed SWT-WRS. The results also confirm the effectiveness of the proposed SWT-WRS in improving the performance of handwritten Arabic word recognition using machine learning. Therefore, the suggested SWT-WRS overcomes the lack of translation invariance in the DWT method by eliminating the up-and-down samplers from the proposed machine learning method.

Internet of Things (IoT) devices are widely considered in smart cities, intelligent medicine, and intelligent transportation, among other fields that facilitate people's lives, producing a large amount of private data. However, due to the mobility, limited performance, and distributed deployment of IoT, traditional access control methods cannot support the security of private data's access control process in current IoT environments. To address such problems, this article proposes an auditable access control model, based on an attribute-based access control model, and manages the access control policy for private data through the request record, the response record, and the access record stored in the blockchain network. Additionally, a Blockchain-based auditable access control system is also proposed based on the auditable access control model, ensuring private data security in IoT environments and realizing effective management and auditable access to these data. Experimental results show that the proposed system can maintain high throughput while ensuring private data security for real application scenarios in IoT environments.

Parity‐check is a simple yet effective error detection method. Several other more sophisticated error detection techniques are founded upon single parity‐check (SPC). Exclusive‐OR (XOR) is known as the parity generator in binary logic. This study suggests some multi‐valued parity generators (MPGs), studies their behaviour, and provides a full discussion about their necessary and optional properties. The concept of Sudoku with some customised rules is used to create MPGs, which are the extended versions of binary parity generator in higher radixes. They are capable of revealing all single‐digit errors. Additionally, they can detect incorrect data delivery with high probability when more than one error occurs (with even higher probability than XOR). The probability of error detection is analytically calculated for the occurrence of two to five errors in different bases. The calculations are then experimentally verified by a formal verification method. The authors’ investigations show that error detection probability increases in higher radixes, and it is independent of dataword size.

Nowadays, detecting anomaly events in communication networks is highly under consideration by many researchers. In a large communication network, traffic is massive, which leads to a larger amount of data travelling and also the growth of noise. Therefore, to extract meaningful data for anomaly detection would be very challenging. Each attack has its own behaviour that determines the type of attack. However, some attacks may have similar behaviours and only differ in some features. Extracting such meaningful features is of special importance. In this study, an association rule mining algorithm, in particular, the Apriori algorithm is employed to extract appropriate features from the raw data including rules and repetitive patterns. The extracted features would be used then for classifying the data and detecting anomalies in communication networks. A hybrid of artificial neural network and AdaBoost classification algorithms are employed for classifying the detected events with normal behaviour and attack events. The proposed method is compared with previous methods reported in this field such as CART, CHAID, multiple linear regression and logistic regression on KDDCUP99 data set. The results showed that the proposed method outperformed other classifiers examined. The strategy of reinforcement learning is used to combine the classifier's results which is based on Max vote strategy.

Summary In recent years, users are becoming increasingly accustomed to using the Internet to gain software resources in the form of web services provided by information technology organizations. Cloud computing is a service delivery paradigm that shares services and resources to access the web services to the end users over the Internet. In the cloud environment, based on the user's needs, various types of services with similar functionalities but different quality‐of‐service (QoS) criteria can be delivered, which often must be combined to meet the users' requests. The optimal selection and composition of these services are realized as an interesting issue. In this paper, we propose a moth‐flame optimization (MFO) algorithm, which is a novel nature‐inspired metaheuristic paradigm for the web service composition (WSC) problem called “MFO‐WSC,” to improve the QoS criteria in the distributed cloud environment. Also, formal modeling is presented for the QoS‐aware MFO‐WSC algorithm with the model checking approach that receives the particular benefits to collaborate the correctness of the proposed algorithm. The correctness of the proposed behavior model is examined using some logical problems such as deadlock‐free, fairness, and reachability conditions in the new symbolic model verifier model checker. The experimental results indicate the effectiveness of the proposed algorithm in comparison with similar related works.