Wireless rechargeable sensor networks (WRSNs) consist of sensors equipped with fast-rechargeable batteries and wireless power receivers, where energy storage plays a crucial role in bridging the intermittent nature of wireless power transfer (WPT) with the continuous energy demands of the sensors. The mobile charger (MC) enables network functionality through wireless power transmission, effectively addressing the charging requirements of these networks. This survey seeks to illuminate various aspects of wireless charging schemes regarding management strategies and technical methodologies, particularly in the context of WPT and energy consumption management from a methodological standpoint. By presenting a comprehensive, methodology-driven analysis of wireless charging schemes for WRSNs, this survey makes a significant contribution to the field. Furthermore, this survey aims to provide artificial intelligence (AI)-driven methodological insights into various facets of wireless charging schemes within the framework of sustainable energy management. It examines innovative management strategies and technical methodologies that utilize artificial intelligence to enhance the efficiency of WPT and energy consumption. Each wireless charging scheme is scrutinized through three distinct lenses: technical methodology, charge methodology, and evaluation methodology, considering the specific design parameters relevant to each approach. The technical methodology explores the capabilities and limitations of each scheme, detail the analytical parameters involved, and define the operational objectives. The charge methodology focuses on charging characteristics, including management patterns, operational modes, and categorization of charging processes. The evaluation methodology provides a holistic overview of how these schemes are assessed, encompassing evaluation metrics, simulation configurations, and the simulation environment. To better understand the landscape of these methodologies, this survey categorizes the reviewed schemes into five distinct classes: heuristic-based, metaheuristic-based, fuzzy-based, hybrid approaches that integrate both metaheuristic and fuzzy logic techniques, and reinforcement learning-based techniques. This categorization is grounded in the aforementioned three innovative aspects of technical, charge, and evaluation methodologies. Importantly, this survey aims to offer an exhaustive overview of the capabilities, limitations, and emerging research directions concerning these schemes from a methodology-driven perspective, particularly in the realm of WRSNs. Additionally, it seeks to pave the way for future research by identifying new avenues for exploration, filling the gap left by the lack of comprehensive surveys in this crucial field.

Because of the overgrowth of data, especially in text format, the value and importance of multi-label text classification have increased. Aside from this, preprocessing and particularly intelligent feature selection (FS) are the most important step in classification. Each FS finds the best features based on its approach, but we try to use a multi-strategy approach to find more useful features. Evaluating and comparing features’ importance and relevance makes using multiple strategy and methods more suitable than conventional approaches because each feature is measured based on several perspectives. Nevertheless, the ensemble FS merges the final performance results of various methods to take advantage of different methods’ strengths and better classify. In this article, we have proposed an ensemble FS method for multi-label text data (MLTD) for the first time using the order statistics (EMFS) approach. We have utilized four multi-label FS (MLFS) algorithms with various particular performances to achieve a good result. In this method, as one of the most important statistics methods, Order Statistics was used to aggregate the ranks of different algorithms, which is robust against noise, redundant and inessential features. In the end, the performance of EMFS, executing six MLTDs, was evaluated according to six performance criteria (ranking-based and classification-based). Surprisingly, the proposed method was more accurate than others among all used MLTDs. The proposed method has improved by 1.5% compared to other methods. This value is based on the results obtained based on six evaluation criteria and all tested data sets.

With regard to large dimensions of contemporary data sets and restricted computational time of intelligent systems, reducing the dimensions of data sets is necessary. Feature selection is a practical way to remove a set of redundant, irrelevant, and noisy features. In this way, the speed of decision-making procedure will be increased while the accuracy of decisions will be retained. To this end, numerous attentions have been attracted to the topic and consequently, extensive range of methods has been proposed. Regarding the goals of the feature selection concept, the proposed algorithms in this field must be fast and accurate. Therefore, this paper proposes a light meanwhile accurate algorithm to fulfill the mentioned goals. The presented algorithm takes the speed advantage of Whale Optimization Algorithm (WOA) to propose a novel feature selection method for intelligent systems. Moreover, to reach the goal of accuracy, the proposed strategy considers three important fitness objectives, namely, the number of selected features, the accuracy of classification, and information gain. The proposed scheme considers an accurate multiobjective fitness function instead of manipulating the basic algorithm. The reason is that improving the basic algorithms, WOA in our case, may lead to loading more computational complexity. Also, to make the proposed algorithm as light as possible, this paper considers K-nearest neighbor algorithm as the main classifier. The proposed light feature selection algorithm is run on different data sets. Experimental results prove that this algorithm is able to reduce the number of features meanwhile it retains, and in some cases even increases, the accuracy of classification.

Abstract The clustering of big data streams has become a challenging task due to time and space constraints of the hardware and decreasing accuracy when the dimensionality of input data grows in time. In this paper, fuzzy growing neural gas is introduced, an online fuzzy approach for clustering data streams based on the growing neural gas algorithm, by adopting more restrictive criteria for selecting the winner nodes in the topological graph constructed at each iteration of the algorithm. The algorithm is tested on public datasets, and the results show improvements over existing clustering methods.

Vehicular Ad hoc Networks (VANETs) that are considered as a subset of Mobile Ad hoc Networks (MANETs) can be applied in the field of transportation especially in Intelligent Transportation Systems (ITS). The routing process in these networks is a challenging task due to rapid topology changes, high vehicle mobility and frequent disconnection of links. Therefore, developing an efficient routing protocol that satisfies restriction of delay and minimum overhead is faced with many difficulties and limitations. Also, the detection of malicious vehicles is a significant task in VANETs. To address these issues, using Unmanned Aerial Vehicles (UAVs) can be helpful to cope with these limitations. In this paper, operation of UAVs in ad hoc mode and their cooperation with vehicles in VANETs are studied to help in the process of routing and detection of malicious vehicles. A routing protocol named VRU is proposed that includes two distinct ways of routing of data: (1) delivering packets of data between vehicles with the help of UAVs using a protocol named VRU_vu, and (2) routing packet of data between UAVs using a protocol named VRU_u. The NS-2.35 simulator under Linux Ubuntu 12.04 is utilized in order to appraise the performance of VRU routing components in an urban scenario. Also, VanetMobiSim generator of mobility and MobiSim are used to produce the motions of vehicles and to produce the motions of UAVs, respectively. The performance analysis displays that VRU protocol can improve the packet delivery ratio by 16% and detection ratio by 7% compared to other reviewed routing protocol. Also, VRU protocol decreases end-to-end delay by an average of 13% and overhead by 40%.