AJAli Akbar Jalali

Ali Akbar Jalali

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Ali Akbar Jalali has a total of 41 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Statistical Database of Human Motion Recognition Using Wearable IoT—A Review

    by Eghbal Foroughi Asl, Saeed Ebadollahi, Reza Vahidnia, Aliakbar Jalali

    Wearable sensors and the Internet of Things (IoT) will be two buzzwords that will be heard commonly in the coming decades. The combination of these two technologies soon will create a great revolution in applications that require motion recognition such as health care, sports, entertainment, etc. The development of technology has made wearable sensors one of the most basic tools for human motion analysis. We believe that IoT is the most powerful complement to the use of wearable sensors in the analysis of human body motion. Using wearable IoT, all necessary human data will be collected and delivered via the Internet to the experts who can make accurate decisions about the type of activity, falling situations, freezing of gait (fog), etc. In this paper, the human motion analysis is presented in a chart and is divided into two parts: movement measurement and movement classification. However, this paper focuses on movement classification which includes three sub-sections: Gait Analysis (GA), Gesture Recognition (GR), and Human Activity Recognition (HAR), and is closely related to human motion recognition. In this paper, our goal is to first acquaint the reader with the important steps required to classify the movement of the human body by wearable sensors and then by using tables to determine the most used algorithms and methods for each step. After briefly reviewing IoT concepts, directions for further research will be provided.


  • Consensus of Uncertain Multiagent Systems Under Granular Differentiability Concept

    by Razieh Abdollahipour, Khosro Khandani, Aliakbar Jalali

    In this paper, the problem of consensus of linear multi-agent systems with both uncertain dynamics and uncertain switching topology is investigated. Uncertainties are considered as granular fuzzy numbers whicharerepresentedvia horizontalmembership functions (HMFs) and Relative Distance Measurement (RDM) arithmetic. It is first proved that there exists a crisp solution to a fuzzyLinear Matrix Inequality(LMI) problem. This proof creates a bridge such that multidimensional RDM arithmetic that has been devoted to linear functions so far could be entered into some problems with nonlinear functions. Then an algorithm is proposed for the consensus of the multi-agent systems with uncertainty. Here, by proving the existence of a crisp solution for fuzzy LMI, we are able to prove that the proposed algorithm can ensure achieving consensus. Furthermore, the gain coefficients obtained for this fuzzy system are crisp numbers and can be applied to real systems in practical applications. Finally, the final value of consensus is calculated as a fuzzy number to present a better understanding of the effect of uncertaintyon the final value of consensus. In addition, the efficiency of the proposed algorithm is shown in a simulation example.


  • Open Access

    Decentralized energy management system for smart microgrids using reinforcement learning

    by Razieh Darshi, Saeed Shamaghdari, Aliakbar Jalali, Hamidreza Arasteh

    This paper presents a novel fully decentralized and intelligent energy management system (EMS) for a smart microgrid based on reinforcement learning (RL) strategy. The purpose of the proposed EMS is to maximize the benefit of all microgrid entities comprising customers and distributed energy resources (DERs). Due to unpredictable features of renewable energy sources and variability of consumers’ demands, designing the microgrid EMS is a complicated task. To overcome this issue, the multi‐agent hour‐ahead energy management problem is modelled as a finite Markov decision process. The microgrid entities are considered as intelligent agents. The optimal policy of agents is obtained through a newly developed framework of the model‐free Q‐learning algorithm to maximize the benefit of all renewable and non‐renewable energy resources and battery energy storage system. The degradation model of the battery is considered to reduce the number of battery replacements. To ensure customers’ comfort, customers’ expenses are decreased without demand curtailment via introducing two types of load shifting techniques. The microgrid operation is analysed under four scenarios comprising no‐learning, generator‐learning, customer‐learning, and whole‐learning. the performance of the proposed algorithm is compared to the Monte Carlo method and simulation results on the real power‐grid dataset show the superiority of the algorithm.


  • Open Access

    Decentralized Reinforcement Learning Approach for Microgrid Energy Management in Stochastic Environment

    by Razieh Darshi, Saeed Shamaghdari, Aliakbar Jalali, Hamidreza Arasteh

    Microgrids are considered to be smart power grids that can integrate Distributed Energy Resources (DERs) in the main grid cleanly and reliably. Due to the random and unpredictable nature of Renewable Energy Sources (RESs) and electricity demand, designing a control system for microgrid energy management is a complex task. In addition, the policies of microgrid agents are changing over time to improve their expected profits. Therefore, the problem is stochastic and the policies of the agents are not stationary and deterministic. This paper proposes a fully decentralized multiagent Energy Management System (EMS) for microgrids using the reinforcement learning and stochastic game. The microgrid agents, comprising customers, and DERs are considered as intelligent and autonomous decision makers. The proposed method solves a distributed optimization problem for each self-interested decision maker. Interactions between the decision makers and the environment during the learning phase lead the system to converge to the optimal equilibrium point in which the benefits of all the agents are maximized. Simulation studies using a real dataset demonstrate the effectiveness of the proposed method for the hourly energy management of microgrids.


  • Event‐triggered dynamic surface control of uncertain nonlinear networked systems subject to transmission delays

    by Zahra Karimi, Ali Akbar Jalali, Yazdan Batmani

    In this paper, an event‐triggered dynamic surface control technique is proposed for strict‐feedback uncertain nonlinear networked systems in the presence of network‐induced time delays. First, an event‐based dynamic surface control law is designed. Then, by rewriting the control law as a communication‐delay‐distribution‐dependent model, the closed‐loop error dynamics is derived and modeled as a linear time‐delay system with perturbation terms. Next, a periodic event‐triggering condition is designed by imposing some inequality constraints on the perturbations. A theorem related to the ultimate boundedness and quadratic tracking of the closed‐loop system is presented. The proposed technique is utilized to design a decentralized dynamic surface control structure with event‐triggered inter‐vehicle communications for a vehicle platoon.


  • Fuzzy consensus of multi‐agent systems with granular fuzzy uncertainty in communication topology

    by Razieh Abdollahipour, Khosro Khandani, Ali Akbar Jalali

    In this paper, the consensus problem in linear multi‐agent systems with uncertain topology is investigated. The uncertainty in the communication topology is represented by granular fuzzy numbers obtained from expert knowledge, and the required calculations are performed with multidimensional relative–distance–measurement interval arithmetic. The concept of granular fuzzy graph and fuzzy Gershgorin disc theorem is introduced. Then a fuzzy consensus protocol is proposed for the multi‐agent system with fuzzy granular uncertain topology. A two‐step algorithm is also proposed to build the consensus protocol. We also propose a theorem for calculating the final value of fuzzy consensus, which shows the final value of consensus as a fuzzy number. Simulation results show the efficiency of the suggested algorithm.


  • Event-triggered dynamic surface control of uncertain nonlinear systems

    by Zahra Karimi, Ali Akbar Jalali, Yazdan Batmani

    In this paper, an event-triggered dynamic surface controller is proposed for strict-feedback nonlinear networked systems with mismatched uncertainties. Towards this aim and first of all, an event-based dynamic surface control law is designed. Then, the closed-loop error dynamics is derived and rewritten as a linear dynamics with nonlinear perturbation terms. Next, these terms are classified into vanishing and nonvanishing perturbations. Finally, by imposing some constraints on the nonvanishing terms, an event-triggering mechanism is constructed. By formulating the imposed constraints in the form of linear matrix inequalities (LMIs) and using the ultimate boundedness theory, the ultimate error boundedness and quadratic tracking objectives are addressed in the framework of convex optimization. The absence of the Zeno behaviour, which is an important feature of any event-triggered methodology, is also proven. The validity of the theoretical results is illustrated by applying the proposed method to a remotely operated underwater vehicle in a simulation study as well as an experimental implementation on a magnetic levitation system.


  • A Hybrid Recommendation System Based on the Supply Chain in Social Networks

    by Abolfazl Zare, Mohammad Reza Motadel, Aliakbar Jalali

    With the expansion of virtual social networks, finding and recommending appropriate and favorite information and items to users is one of the severe issues in their development. To this end, recommender systems predict and recommend interests based on past behavior reviews and user preferences. However, less research has been done on people to people in social networks, and it is still based on exploring communication and friendship circles, which is generally not desirable for specialized users. Social networks include a variety of entities such as individuals, businesses, companies, and technical communications that also contain a variety of information related to the supply chain interaction, such as industries, functions, and communications between them and users. This paper provides a recommendation system framework for recommending people to people in social networks based on supply chain interactions. For this purpose, it has presented five hybrid methods based on artificial neural networks and fuzzy strategies to provide better and more accurate recommendations than basic methods. Eventually, a case study was conducted on the LinkedIn social network to show the improvements in applying this new approach to primary methods. In this regard, seven specific evaluation criteria of recommender systems have been used.