Search

The human brain can effortlessly perform vision processes using the visual system, which helps solve multi-object tracking (MOT) problems. However, few algorithms simulate human strategies for solving MOT. Therefore, devising a method that simulates human activity in vision has become a good choice for improving MOT results, especially occlusion. Eight brain strategies have been studied from a cognitive perspective and imitated to build a novel algorithm. Two of these strategies gave our algorithm novel and outstanding results, rescuing saccades and stimulus attributes. First, rescue saccades were imitated by detecting the occlusion state in each frame, representing the critical situation that the human brain saccades toward. Then, stimulus attributes were mimicked by using semantic attributes to reidentify the person in these occlusion states. Our algorithm favourably performs on the MOT17 dataset compared to state-of-the-art trackers. In addition, we created a new dataset of 40,000 images, 190,000 annotations and 4 classes to train the detection model to detect occlusion and semantic attributes. The experimental results demonstrate that our new dataset achieves an outstanding performance on the scaled YOLOv4 detection model by achieving a 0.89 mAP 0.5.

There is a crucial need to process patient's data immediately to make a sound decision rapidly; this data has a very large size and excessive features. Recently, many cloud-based IoT healthcare systems are proposed in the literature. However, there are still several challenges associated with the processing time and overall system efficiency concerning big healthcare data. This paper introduces a novel approach for processing healthcare data and predicts useful information with the support of the use of minimum computational cost. The main objective is to accept several types of data and improve accuracy and reduce the processing time. The proposed approach uses a hybrid algorithm which will consist of two phases. The first phase aims to minimize the number of features for big data by using the Whale Optimization Algorithm as a feature selection technique. After that, the second phase performs real-time data classification by using Naïve Bayes Classifier. The proposed approach is based on fog Computing for better business agility, better security, deeper insights with privacy, and reduced operation cost. The experimental results demonstrate that the proposed approach can reduce the number of datasets features, improve the accuracy and reduce the processing time. Accuracy enhanced by average rate: 3.6% (3.34 for Diabetes, 2.94 for Heart disease, 3.77 for Heart attack prediction, and 4.15 for Sonar). Besides, it enhances the processing speed by reducing the processing time by an average rate: 8.7% (28.96 for Diabetes, 1.07 for Heart disease, 3.31 for Heart attack prediction, and 1.4 for Sonar).

Particle swarm optimization (PSO) suffers from delayed convergence and stagnation in the local optimal solution, as do most meta-heuristic algorithms. This study proposes a time-based leadership particle swarm-based Salp (TPSOSA) to address the PSO's limitations. The TPSOSA is a novel search technique that addresses population diversity, an imbalance between exploitation and exploration, and the premature convergence of the PSO algorithm. Hybridization in TPSOSA is divided into two stages: The PSO hierarchy of leaders and followers is first represented as a time-varying dynamic structure. Because we need much exploration at the beginning and many exploitative steps at the end, this method raises the number of leaders while decreasing the number of follower particles linearly. In the time-varying form of the PSO (TPSOSA), unlike the PSO, the number of leaders and followers changes over time. PSO's robust search strategy is used to update the leaders' positions. Second, the SSA's powerful exploitation is utilized to update the followers' swarm population position. The purpose of tweaking the particle swarm optimizer algorithm is to aid the fundamental method in avoiding premature convergence and quickly directing the search to the most promising likely search space. The proposed TPSOSA method is tested using the CEC 2017 benchmark, seven CEC2008lsgo test functions with 200, 500, and 1000 decision variables, and 19 datasets (including three high-dimensional datasets and the NSL-KDD Dataset for Intrusion Detection System). In each experiment, TPSOSA is compared to various state-of-the-art metaheuristics methods. Friedman and Wilcoxon rank-sum statistical tests are also used to analyze the data. Experimental data and statistical tests show that the TPSOSA algorithm is very competitive and often superior to the algorithms used in the studies. According to the results, TPSOSA can also find an optimal feature subset that enhances classification accuracy while reducing the number of features employed. [ABSTRACT FROM AUTHOR]

The use of metaheuristics in estimating the exact parameters of solar cell systems contributes greatly to performance improvement. The nonlinear electrical model of the solar cell has some parameters whose values are necessary to design photovoltaic (PV) systems accurately. The metaheuristic algorithms used to determine solar cell parameters have achieved remarkable success; however, most of these algorithms still produce local optimum solutions. In any case, changing to more suitable candidates through elephant herd optimization (EHO) equations is not guaranteed; in addition, instead of making parameter α adaptive throughout the evolution of the EHO, making them adaptive during the evolution of the EHO might be a preferable choice. The EHO technique is used in this work to estimate the optimum values of unknown parameters in single-, double-, and three-diode solar cell models. Models for five, seven, and ten unknown PV cell parameters are presented in these PV cell models. Applications are employed on two types of PV solar cells: the 57 mm diameter RTC Company of France commercial silicon for single- and double-diode models and multi-crystalline PV solar module CS6P-240P for the three-diode model. The total deviations between the actual and estimated result are used in this study as the objective function. The performance measures used in comparisons are the RMSE and relative error. The performance of EHO and the proposed three improved EHO algorithms are evaluated against the well-known optimization algorithms presented in the literature. The experimental results of EHO and the three improved EHO algorithms go as planned and proved to be comparable to recent metaheuristic algorithms. The three EHO-based variants outperform all competitors for the single-diode model, and in particular, the culture-based EHO (CEHO) outperforms others in the double/three-diode model. According the studied cases, the EHO variants have low levels of relative errors and therefore high accuracy compared with other optimization algorithms in the literature. [ABSTRACT FROM AUTHOR]

Cuckoo search algorithm is one of the most prominent meta-heuristic optimization algorithms which is applied to various applications. The discovery probability is the one and the only tuning parameter of the cuckoo search algorithm. The physical meaning of this parameter contradicts its implementation in the standard algorithm. Therefore, this study concerns the correction to the definition and implementation of the cuckoo search algorithm to resolve this conflict. Moreover, a novel algorithm called double exponential cuckoo search is proposed, in which the discovery probability became adaptive based on the concept of the double Mersenne numbers. The proposed algorithm is compared to nine other variants to find the best variant that makes the discovery probability adaptive. All the variants are compared and tested on 30 and 50 dimensions of CEC2017 benchmark functions. The results have been statistically proved using the sign test, Wilcoxon signed-rank test, and Friedman test. Moreover, multiple graphical methods are also used to visualize the median performance such as Violin plots and mean convergence graphs. Simulation results prove the superior performance of the proposed algorithm over all other variants. [ABSTRACT FROM AUTHOR]

Unlike classical wired networks and wireless sensor networks, WMSN differs from their predecessor’s scalar network basically in the following points; nature and size of data being transmitted, important memory resources, as well as, power consumed per each node for processing and transmission. The most effective solution to overcome those problems is image compression. As the image contains massive amount of redundancies resulting from high correlation between pixels, many compression algorithms have been developed. The main objective of this survey was to study and analyze relevant research directions and the most recent algorithms of image compression over WMSN. This survey characterizes the benefits and shortcomings of recent efforts of such algorithms. Moreover, it provides an open research issue for each compression method; and its potentials to WMSN. Reducing consumed power thus granting long life time is considered the main performance metric and will be the main target in the investigated solution. [ABSTRACT FROM AUTHOR]

Abstract: The main weak points in using AI optimization techniques are the possibility of being trapped at local minima, being confined to the population space, difficulty to solve heavily nonlinear problems and to make full use of the historical information beside the lack of prediction about the search space. This paper is concerned with a hybrid optimization technique; namely cultural-based genetic algorithm MCBGA for solving multidimensional and nonlinear applications. The feature of proposed MCBGA technique is enhanced using biased initialization and dynamic parameters setting. Also elitism is carried out. The proposed approach has been carried out on pressure vessel design, fed-batch fermentor and continuous Stirred Tank Reactor CSTR test systems as well as Rastrigin, a well known standard workbench. The proposed MCBGA in terms of the diversity of the optimal solutions are obtained and compared to real coded genetic algorithm as well as other optimization techniques reported in the literature such as binary Genetic Algorithm (GA), Particle Swarm Optimization (PSO) and its variants. The results obtained using the proposed algorithm are more accurate and the fast convergence is obvious. [Copyright &y& Elsevier]