behrooz shahrokhzadeh

This paper provides a comprehensive review of the potential of game theory as a solution for sensor-based human activity recognition (HAR) challenges. Game theory is a mathematical framework that models interactions between multiple entities in various fields, including economics, political science, and computer science. In recent years, game theory has been increasingly applied to machine learning challenges, including HAR, as a potential solution to improve recognition performance and efficiency of recognition algorithms. The review covers the shared challenges between HAR and machine learning, compares previous work on traditional approaches to HAR, and discusses the potential advantages of using game theory. It discusses different game theory approaches, including non-cooperative and cooperative games, and provides insights into how they can improve the HAR systems. The authors propose new game theory-based approaches and evaluate their effectiveness compared to traditional approaches. Overall, this review paper contributes to expanding the scope of research in HAR by introducing game-theoretic concepts and solutions to the field and provides valuable insights for researchers interested in applying game-theoretic approaches to HAR.

The goal of recommender system is to provide desired items for users. One of the main challenges affecting the performance of recommendation systems is the cold-start problem that is occurred as a result of lack of information about a user/item. In this article, first we will present an approach, uses social streams such as Twitter to create a behavioral profile, then user profiles are clustering with machine learning techniques. Based on this clustering, predictions are made using machine learning techniques such as the Random Forest algorithm (RF) and the Gradient Boosting algorithm (GB). Therefore, the user is not required to provide any kind of data explicitly anymore. As a result of this method, cold start problem will decrease among users' social networks. Because the system uses this data to create user profiles, this will be an input for recommender systems. Numerous experiments have been performed in this field and compared to some new cold start algorithms; very satisfactory results have been obtained. In this paper, we have concluded that the clustering process greatly increases the performance accuracy of the models and reduces the average absolute error, and also the Gradient Boosting algorithm has a better performance than the Random Forest algorithm.

Target coverage is one of the important problems in visual sensor networks. The coverage should be accompanied with an efficient use of energy in order to increase the network lifetime. In this paper, we address the maximum lifetime for visual sensor networks (MLV) problem by maximizing the network lifetime while covering all the targets. For this purpose, we develop a simulated annealing (SA) algorithm that divides the sensors’ Field-of-View (FoV) to a number of cover sets and then applies a sleep-wake schedule for cover sets. We also identify the best possible FoV of sensors according to the targets’ location using rotating cameras, to reduce the solution space and approaching to a near-optimal solution. Our proposed energy and neighbor generating functions of the SA result in a balanced distribution of energy consumption as well as escaping from local optima. We conduct some simulation experiments to evaluate the performance of our proposed method by comparing with some well-known solutions in the literature.