TLDR: EvoFed integrates Evolutionary Strategies with Federated Learning (FL) to reduce communication costs in distributed training. Instead of sharing model parameters, nodes transmit similarity measures between local and perturbed models, generated synchronously using random seeds. This reduces the communication load while preserving model performance. EvoFed achieves comparable results to FedAvg with reduced communication but requires more local processing.

@article{rahimi2024evofed,
                title={EvoFed: leveraging evolutionary strategies for communication-efficient federated learning},
                author={Rahimi, Mohammad Mahdi and Bhatti, Hasnain Irshad and Park, Younghyun and Kousar, Humaira and Kim, Do-Yeon and Moon, Jaekyun},
                journal={Advances in Neural Information Processing Systems},
                volume={36},
                year={2024}
              }           
           

TLDR: The sun and wind as renewable energy sources are attracting more regard as alternative energy sources. In addition to the decreasing fuel sources, pollution and global warming are important problems. Fuel cells are a beneficial energy technology that generates electric energy through the reaction between the fuel sources rich in hydrogen and oxygen. In comparsion with combustion engines, fuel cells have many advantages, such as high efficiency and low emissions. Furthermore the by-products of fuel cells are heat and water. Proton exchange membrane fuel cells (PEMFCs) have attracted much interests recently. PEM fuel cells are Pollution-Free high-efficiency power sources for urban vehicles that recently corporate by legislative initiatives.

@article{haghighi2018opem,
                title={OPEM: Open source PEM cell simulation tool},
                author={Haghighi, Sepand and Askari, Kasra and Hamidi, Sarmin and Rahimi, Mohammad Mahdi},
                journal={Journal of Open Source Software},
                volume={3},
                number={27},
                pages={676},
                year={2018}}
             

TLDR: This paper illustrates detailed mechanical, electronics, control, and software improvements made by Parsian Small Size Soccer team since last year. The notable mechanical change is improving the dribbler system to receive and control the ball more proficiently. Likewise, some improvements have been made in electronic to cooperate more efficiently with the software system. We used computational geometry algorithm to improve the path planning. Moreover, providing the inverse-model of the robots’ kinematics was profitable to correct the robot motion. New developments in the log analyzer have also been provided. Lastly, an attempt to learn the opponent defense strategies have been explained.

@article{behzad2019parsian,
                  title={PARSIAN 2019 Extended Team Description Paper},
                  author={Behzad, Kian and Daneshmand, Elham and Moradi, Nadia and
                    Hajmohammadi,Mahdi and Onidin, Mohammad Reza Kolani and
                    Gharib, Yasamin Alizadeh and Pirmoradi, Atiyeh and
                    Rahimi, Mohammad Mahdi and Shirazi, Mohammad Mahdi and Khosravi, Mohammad Azam}
                }
             

TLDR: This paper presents Parsian’s hardware elaboration, the soft-ware architecture and all improvements that have been made since lastyear, including useful innovations in hardware, e.g. new ball detectionsensor, debugger module and robot’s fault recovery. Noteworthy enhance-ments in software such as micro-service architecture by ROS, open loopmotion correction, motion profiler and new obstacle avoidance strategyare described.

@inproceedings{Rahimi2018PARSIAN2E,
                  title={PARSIAN 2018 Extended Team Description Paper},
                  author={M. Rahimi and M. M. Shirazi and Maziar Arfaee and Mohammad Amin Najaf Gholian
                    and A. H. Zamani and H. Hosseini and Fateme Hashemi Chaleshtori and N. Moradi and
                    Atousa Ahsani and M. Jafari and A. Zahedi and Parsa Abdollahi and A. Zolanvari
                    and M. Azam and Khosravi},
                  year={2018}
                }
             

TLDR: In this paper detailed description of Parsian robots’ hardware improvement, as well as the software architecture with focus on new improvements that have been made since last year, is represented. Improvements and developments that seemed innovative and useful in hardware like fault detection, two way communication and dribbler system and also improvements in software such as pass and interception skills’ behavior, adaptive attack strategy for regular game and reactive offense and defense for free kicks will be discussed in detail.

@inproceedings{Rahimi2017PARSIAN2E,
                  title={PARSIAN 2017 Extended Team Description Paper},
                  author={M. Rahimi and M. M. Shirazi and Maziar Arfaee and Mohammad Amin Najaf Gholian and
                    A. H. Zamani and H. Hosseini and Fateme Hashemi Chaleshtori and
                    N. Moradi and Atousa Ahsani and M. Jafari and A. Zahedi and
                    Parsa Abdollahi and A. Zolanvari and M. Azam and Khosravi}
                  year={2017}
                }
             

TLDR: The Parsianteam placed top eight teams in the Small Size League of RoboCup 2015. In this paper, we present our robots’ current design in mechanical, electrical and the team’s recent work on the offensive and defensive tactics, low level skills. Among the offensive tactics, we introduce new features in our visual planner and that in both play on and play off then We present a change in defense mark system that increase reliability and robot ball-manipulation skill that keep ball till asuitable situation occurs. Finally, we describe improvements to the ball and robots state estimation algorithms by profiling robots and field.

@article{zolanvarimohammad,
                    title={PARSIAN 2016 Extended Team Description Paper},
                    author={Mohammad Mahdi Rahimi, Mohammad Mahdi Shirazi, Seyede Parisa Dajkhosh,
                      Alireza Zolanvari, Maziar Arfaee, Hamidreza Kazemi Khoshkijari,
                      Amirhossein Abbasi Fashami, Alireza Saeidi Shahrivar and
                      Mohammad Azam Khosravi.}
                  }
             

TLDR: This is the team description paper of the Small Size Soccer Robot team “PARSIAN” for entering the RoboCup 2015 competitions in China. In this paper we will represent our robots’ current design in mechanical, electrical, control and software parts. Improvements and developments like new mechanical design, control system, visual plannerand enhancements in predefined plays.

@article{naderialireza,
                  title={PARSIAN 2015 Extended Team Description Paper},
                  author={Alireza Zolanvari, Mohammad Mahdi Shirazi, Seyede Parisa Dajkhosh,
                  Amir Mohammad Naderi, Maziar Arfaee, Mohammad Behbooei, Hamidreza Kazemi Khoshkijari,
                  Erfan Tazimi, Mohammad Mahdi Rahimi and Alireza Saeidi Shahrivar.}
                }