The Mobile Internet of Things (MIoT) represents a significant evolution of traditional IoT by enabling seamless connectivity for mobile devices and sensors in dynamic environments. Given the resource constraints and mobility challenges in MIoT networks, developing adaptive and energy-efficient routing strategies is important. This paper proposes a novel routing protocol that integrates Grey Wolf Optimization (GWO) and Recurrent Neural Networks (RNNs) to enhance energy efficiency, reliability, and responsiveness in MIoT systems. The protocol features dynamic clustering, predictive traffic load balancing, and multi-objective optimization for Cluster Head (CH) selection, where RNNs forecast traffic trends and GWO optimizes routing paths. Simulation results demonstrate that the proposed method reduces energy consumption, lowers end-to-end delays, and improves packet delivery ratio (PDR) and network reliability under both static and mobile conditions. Compared to existing methods such as the Krill Herd (KH) algorithm, Dynamic Multi-Sink Routing Protocol (DMS-RP), and Evolutionary Fuzzy Rule-based (EFR) models, the proposed solution exhibits superior performance, validating its scalability and effectiveness for real-world MIoT applications.

Abstract Efficient and intelligent task scheduling in heterogeneous multi-cloud environments remains a complex challenge due to conflicting objectives such as energy consumption, delay minimization, service-level agreement (SLA) compliance, and host utilization. This paper proposes a hybrid framework that integrates Long Short-Term Memory (LSTM) networks for temporal workload forecasting with Elephant Herding Optimization with Memory (EHOM) for multi-objective task-to-host allocation. The framework is implemented as containerized microservices on an OpenStack Yoga private cloud with Prometheus telemetry, Kafka streaming, TensorFlow Serving for LSTM-based forecasting, and a Python-based EHOM optimizer orchestrated through OpenStack. Performance is benchmarked against Trust-Aware Spring Swarm Optimization (TSSO), Auto Clipped Double Deep Q-Learning (Auto-CDDQL), Self-Adaptive Flower Pollination-based RSA (SA-FPRSA), Elephant Herding Lion Optimizer (EHLO), and a Markov-based scheduler. Experimental results across workloads of 200–1000 tasks show that the proposed method reduces total energy consumption by 12–22%, decreases normalized delay by 8–15%, and improves deadline satisfaction ratio (DSR) by 2.5–5.3 percentage oints, while consistently maintaining availability and reliability above 97%. These improvements confirm the robustness, scalability, and real-time applicability of the proposed framework for SLA-sensitive multi-cloud environments. The system links LSTM forecasts with an EHOM-based allocator in a closed loop.

Abstract Efficient load balancing stands out as a crucial challenge in multi-cloud environments, particularly for applications that demand ultra-reliable, low-latency communications (URLLC). This paper proposes a novel approach integrating Decision Functions with Normal Distributions (DFND) for precise probabilistic modeling of task-to-cloud compatibility. Multivariate normal distributions capture interdependencies between resource features such as CPU, memory, bandwidth, and latency, ensuring accurate resource compatibility evaluation. Additionally, the Tasmanian Devil Optimization (TDO) algorithm employs dynamic exploration and exploitation strategies inspired by natural behaviors, providing rigorous optimization to improve task assignment in dynamic, multi-cloud environments. It uses flexible methods to ensure the optimization process is both efficient and scalable. Simulation results using CloudSim demonstrate significant improvements over state-of-the-art methods in terms of makespan reduction, response time minimization, resource utilization, and cost efficiency. The proposed framework effectively supports latency-sensitive, large-scale applications in dynamic, heterogeneous multi-cloud environments.

Abstract One of the time-consuming and expensive phases in software development is software testing, which is used to improve the quality of software systems. Therefore, Software test automation is a helpful technique that can alleviate testing time. Several techniques based on evolutionary and heuristic algorithms have been put forth to produce maximum coverage test sets. The primary shortcomings of earlier methods are inconsistent outcomes, insufficient branch coverage, and low fault-detection rates. Increasing branch coverage rate, defect detection rate, success rate, and stability are the primary goals of this research. A time- and cost-effective method has been suggested in this research to produce test data automatically by utilizing machine learning and horse herd optimization algorithms. In the first stage of the proposed method, the suggested machine learning classification model identifies the non-error-propagating instructions of the input program using machine learning algorithms. In the second stage, a test generator was suggested to cover only the program's fault-propagating instructions. The main characteristics of produced test data are avoiding the coverage of non-error-propagating instructions, maximizing the coverage of error-propagating instructions, maximizing success rate, and the fault discovery capability. Several experiments have been performed using nine standard benchmark programs. In the first stage, the suggested instruction classifier provides 90% accuracy and 82% precision. In the second stage, according to the results, the produced test data by the suggested method cover 99.93% of the error-prone instructions. The average success percentage with this method was 98.93%. The suggested method identifies roughly 89.40% of the injected faults by mutation testing tools.

A recent technology trend known as the Internet of Things (IoT) involves using devices like smartphones, smart TVs, medical and healthcare equipment, and home appliances to generate data. This paper introduces a novel framework, Reinforcement Learning with Black Widow Optimization (RL-BWO), to enhance IoT service recommendations through responsiveness to evolving service requests and optimized resource usage. Unlike prior hybrid approaches that rely on static recommendation strategies or single-pass learning, RL-BWO uniquely integrates incremental Reinforcement Learning (RL) with evolutionary optimization, enabling continuous policy refinement in dynamic environments. The framework features a multi-batch data partitioning mechanism, and a service-request interactive simulator based on Markov Decision Processes (MDP) to support real-time adaptation. The Black Widow Optimization (BWO) algorithm is used to fine-tune service selection through fitness-based ranking, ensuring high-quality recommendations under resource constraints. Experimental results in a smart city simulation show that RL-BWO improves the solved request rate by up to 12.8%, reduces latency by 17%, and enhances reliability by 9.6% compared to leading methods such as Genetic Algorithm–Simulated Annealing–Particle Swarm Optimization (GASAPSO), Time Correlation Coefficient with Cuckoo Search–K-means (TCCF), and Artificial Bee Colony with Genetic Algorithm (ABCGA). These results demonstrate RL-BWO’s superior scalability, accuracy, and responsiveness, making it a robust solution for large-scale, real-time IoT service recommendation.

Abstract The lack of symptoms in the early stages of liver disease may cause wrong diagnosis of the disease by many doctors and endanger the health of patients. Therefore, earlier and more accurate diagnosis of liver problems is necessary for proper treatment and prevention of serious damage to this vital organ. We attempted to develop an intelligent system to detect liver failure using data mining and artificial neural networks (ANN), this approach considers all factors impacting patient identification and enhances the probability of success in diagnosing liver failure. We employ multilayer perceptron neural networks for diagnosing liver failure via a liver patient dataset (ILDP). The proposed approach using the backpropagation algorithm, improves the diagnosis rate, and predicts liver failure intelligently. The simulation and data analysis outputs revealed that the proposed method has 99.5% accuracy, 99.65% sensitivity, and 99.57% specificity, making it more accurate than Previous related methods.

Abstract SQL injection is one of the important security issues in web applications because it allows an attacker to interact with the application's database. SQL injection attacks can be detected using machine learning algorithms. The effective features should be employed in the training stage to develop an optimal classifier with optimal accuracy. Identifying the most effective features is an NP-complete combinatorial optimization problem. Feature selection is the process of selecting the training dataset's smallest and most effective features. The main objective of this study is to enhance the accuracy, precision, and sensitivity of the SQLi detection method. In this study, an effective method to detect SQL injection attacks has been proposed. In the first stage, a specific training dataset consisting of 13 features was prepared. In the second stage, two different binary versions of the Gray-Wolf algorithm were developed to select the most effective features of the dataset. The created optimal datasets were used by different machine learning algorithms. Creating a new SQLi training dataset with 13 numeric features, developing two different binary versions of the gray wolf optimizer to optimally select the features of the dataset, and creating an effective and efficient classifier to detect SQLi attacks are the main contributions of this study. The results of the conducted tests indicate that the proposed SQL injection detector obtain 99.68% accuracy, 99.40% precision, and 98.72% sensitivity. The proposed method increases the efficiency of attack detection methods by selecting 20% of the most effective features.

Abstract One of the most important and costly stages in software development is maintenance. Understanding the structure of software will make it easier to maintain it more efficiently. Clustering software modules is thought to be an effective reverse engineering technique for deriving structural models of software from source code. In software module clustering, the most essential objectives are to minimize connections between produced clusters, maximize internal connections within created clusters, and maximize clustering quality. Finding the appropriate software system clustering model is considered an NP‐complete task. The previously proposed approaches' key limitations are their low success rate, low stability, and poor modularization quality. In this paper, for optimal clustering of software modules, Chaotic based heuristic method using a forest optimization algorithm is proposed. The impact of chaos theory on the performance of the other SFLA‐GA and PSO‐GA has also been investigated. The results show that using the logistic chaos approach improves the performance of these methods in the software‐module clustering problem. The performance of chaotic based FOA, SFLA‐GA and PSO‐GA is superior to the other heuristic methods in terms of modularization quality and stability of the results.

Despite significant advancements in Internet of Things (IoT)-based smart cities, service discovery and composition continue to pose challenges. Current methodologies face limitations in optimizing Quality of Service (QoS) in diverse network conditions, thus creating a critical research gap. This study presents an original and innovative solution to this issue by introducing a novel three-layered Recurrent Neural Network (RNN) algorithm. Aimed at optimizing QoS in the context of IoT service discovery, our method incorporates user requirements into its evaluation matrix. It also integrates Long Short-Term Memory (LSTM) networks and a unique Black Widow Optimization (BWO) algorithm, collectively facilitating the selection and composition of optimal services for specific tasks. This approach allows the RNN algorithm to identify the top-K services based on QoS under varying network conditions. Our methodology’s novelty lies in implementing LSTM in the hidden layer and employing backpropagation through time (BPTT) for parameter updates, which enables the RNN to capture temporal patterns and intricate relationships between devices and services. Further, we use the BWO algorithm, which simulates the behavior of black widow spiders, to find the optimal combination of services to meet system requirements. This algorithm factors in both the attractive and repulsive forces between services to isolate the best candidate solutions. In comparison with existing methods, our approach shows superior performance in terms of latency, availability, and reliability. Thus, it provides an efficient and effective solution for service discovery and composition in IoT-based smart cities, bridging a significant gap in current research.

Abstract Reverse engineering is used for extracting and understanding software architecture models from source code when the source code is the only available software product. Software module clustering is a reverse engineering method which decomposes software modules into several clusters (subsystems) by using module dependency graph. Finding the best clusters for the modules of software is a multi‐objective and NP‐hard problem; maximizing the cohesion among the modules, minimizing the coupling among different clusters, and maximizing the software modularization quality are considered as the main objectives of software module clustering. Some of these objectives, such as cohesion and coupling, are in contradiction with each other. Simultaneous improvement of all clustering objectives (cohesion, coupling, modularization quality, size, and number of clusters) is the main goal of this study. In this paper, by capitalizing on multi objective genetic algorithm and a new combination of objective functions, we proposed a homogeneous method, namely, Savalan, for clustering software modules. The proposed method generates high‐quality clusters with strong cohesion within clusters and weak connections between clusters for the input source code. The results of conducted experiments on the 14 benchmark programs indicate that simultaneous improvement of all clustering objectives is the main merit of this method. According to the experimental results, the proposed algorithm was able to outperform the previous multi objective methods.

Abstract Software testing is one of the significant stages in software development life cycle which is a costly and time‐consuming task. Automatic tests data generation is one of the traditional techniques to reduce the cost and time spent in software testing. Different evolutionary algorithms have been proposed to generate test data which cover target paths in a software program. In this paper, shuffled frog leaping algorithm (SFLA) is proposed to generate structural test data. The proposed SFLA algorithm is characterized by high convergence speed and simple implementation. In the proposed SFLA, branch coverage is used as the fitness function to generate effective test data. For comparing the performance of the proposed SFLA with genetic algorithm (GA), particle swarm optimization (PSO), ant colony optimization (ACO), and artificial bee colony (ABC), seven benchmark programs were used. The results indicated that the proposed SFLA has an average of 99.99% for branch coverage, average 99.97% for success rate, and 2.03 for the average number of generation for covering all branches.

Software testing is a process for determining the quality of software system. Many small and medium-sized software projects can be manually tested. Nevertheless, due to the widespread extension of software in large-scale projects, testing them will be highly time consuming and costly. Hence, automated software testing (AST) is considered to be as a solution which can ease and simplify heavy and cumbersome tasks involved in software testing. For AST, certain data are needed through which the quality of systems can be evaluated. In this paper, an artificial bee colony (ABC) algorithm was used for solving the issue of test data generation and branch coverage criterion was used as a fitness function for optimizing the proposed solutions. For doing comparisons, seven well-known and traditional programs in the literature were used as benchmarks. The experimental results indicate that our method, on average, outperforms simulated annealing, genetic algorithm, particle swarm optimization and ant colony optimization based on the following four criteria: 99.99% average branch coverage, 99.94% success rate, 3.59 average convergence generation and 0.18[Formula: see text]ms average execution time.

Soft-errors are increasingly considered as a major cause for computer system failures. Software techniques are used as cost-effective and flexible techniques to tolerate soft-errors but the introduced overhead is not acceptable in some safety-critical real-time systems. The identification of the program blocks and protecting only vulnerable blocks against soft-errors reduces the performance overhead. In this paper, we present a genetic algorithm to identify the vulnerable program blocks as well as the derating program blocks against soft-errors. Then, only vulnerable blocks are protected by some software-based soft-error tolerance techniques to achieve a lower performance and space overhead. This genetic algorithm is implemented by the C++ programming languages as an automatic tool. To evaluate the algorithm, errors are injected using the Simple scalar toolset. The experimental results indicate that the effectiveness of this method is higher than the previous methods.