Prediction of calving to conception interval (days open) in dairy cows using recurrent neural networks Mahdi Ravakhah, Mohammad Alishahi, Mohammad Mahdi Gheysari Gholami Journal of Dairy Research, 2026 This research paper addresses the hypothesis that sequence-based long short-term memory (LSTM) architectures improve the prediction of the next DO (days open) relative to a feed-forward multi-layer perceptron and a Cox model under strictly temporally valid predictors. Modern dairy farming can heavily benefit from optimising ‘days open’ for profitability and animal welfare. Machine learning can forecast this metric, improving farm management, disease prevention and culling decisions. This study used a dataset of 16,472 breeding records. The study compared the performance of feed-forward neural networks and two types of recurrent neural networks (RNNs). The results showed that LSTM most accurately forecasted the next ‘days open’. This demonstrates that RNN models, due to their ability to capture temporal patterns in the data, significantly outperform feed-forward and traditional statistical methods in terms of mean absolute error and concordance.
Design of a single input control signal for fault-tolerant synchronization of fractional order hyperchaotic Lu system Alireza Sabaghian, Saeed Balochian, Mohammad Alishahi Cyber Physical Systems, 2024 The authors of this paper used an adaptive-sliding mode controller (A-SMC) to synchronise two fractional-order hyperchaotic (FOHC) Lu systems in the presence of external disturbance and bounded parametric uncertainty with unknown bounds. They employed the Riemann–Liouville fractional order and defined a new fractional-order sliding surface for the FOHC Lu system to determine a proper active control. Additionally, they utilised adaptive laws to estimate uncertainty bounds and unknown disturbance signals. The authors proved the stability of the closed-loop control system using the Lyapunov theory. Simulation results in MATLAB demonstrated the desirable performance of this method in the presence of disturbance and parametric uncertainty.
Flying-inductor-cell based inverters for single-phase transformerless PV applications Mohammad Reza Aalami, Mahdi Zarif, Mohammad Alishahi, Ali Asghar Shojaei, Hamed Heydari Doostabad Iet Power Electronics, 2023 Abstract The application of the general flying‐inductor (FI) cell in two novel transformerless photo‐voltaic (PV) inverters are proposed and investigated. The simultaneous step up and down ability is possible with both topologies, while a high conversion efficiency and a high‐quality AC current are achieved. The leakage current problem, which is a main concern with the transformerless PV inverters, is also considered. One of the proposed topologies presents a higher efficiency, while the other one provides the high quality of injected current with the lowest number active switches. The current control, especially at transition modes of operation is highly improved by utilizing a fast response dead‐beat control scheme. The working principles of the proposed converters are explained in details and 0.88‐kW experimental prototypes are implemented to confirm the theoretical achievements. Finally, a comparison with other existing topologies has been investigated for better clarification of the advantages and disadvantages of the proposed inverters.
A novel output power determination and power distribution of hybrid energy storage system for wind turbine power smoothing Mohammad Eydi, Mohammad Alishahi, Mahdi Zarif Iet Electric Power Applications, 2022 Abstract This paper deals with the power smoothing of the wind power plants connected to a microgrid using a hybrid energy storage system (HESS). In a HESS, the power should be distributed between the battery and capacitor such that the capacitor supplies the peaks of power and its high‐frequency fluctuations, and the battery compensates for the rest. Besides, due to the relatively low lifetime of the batteries compared to the capacitors, it is preferred to transfer power fluctuations to the capacitor as much as possible. In this paper, methods for calculating the output, battery, and capacitor powers are presented. The output power is determined based on the grid restrictions and the battery SOC. The battery and capacitor powers are decided via an adaptive low‐pass filter. The cut‐off frequency of the low‐pass filter is specified by a fuzzy controller such that not only the power spikes and high‐frequency fluctuations are transferred to the capacitor but also the battery SOC variations are reduced. The simulation results show that for the presented wind speed profile, the output power determination reduces 13.7% of the HESS exchanged energy compared to the ramp limiting method. Besides, the proposed power distribution method reduces 92.6% of the unbeneficial charges and discharges of HESS and 8% of the battery exchanged energy compared to the condition that the constant cut‐off frequency filter is utilised. The experimental results confirm the effectiveness of the proposed output power determination and HESS power distribution methods. Analysing the methods’ cost proves that although the utilisation of the capacitor bank increases the system initial investment cost, it will return after a while relying on the units’ capacity, power fluctuations, control method etc.
A parallel CNN-BiGRU network for short-term load forecasting in demand-side management Arghavan Irankhah, Sahar Rezazadeh Saatlou, Mohammad Hossein Yaghmaee, Sara Ershadi-Nasab, Mohammad Alishahi 2022 12th International Conference on Computer and Knowledge Engineering Iccke 2022, 2022 Nowadays, power companies are trying to monitor energy consumption to provide demand response. Energy management and scheduling are possible through short-term load forecasting. Energy supply stability and efficiency depend on accurate forecasting, which balances demand and supply. In this paper, a novel hourly energy prediction method is introduced. A new parallel deep learning network is presented based on CNN and GRU networks. Firstly, some features are extracted from the dataset during pre-processing. Then, the CNN models extract more information from these features in two parallel paths. Afterward, Bi-GRU networks are used to observe the extracted features from previous layers in both two directions to learn long dependency patterns. The real-world data collected by Mashhad energy distribution company is used to evaluate the proposed method. The results demonstrate that the proposed method reached the lowest values containing 49.04, 34.37, and 3.81 for RMSE, MAE, and MAPE metrics in comparison with existing methods.
Turn off/on Base Stations with CSO approach using Simulated Annealing Algorithm in 5G Networks Leili Mortazavi, Mohammad Alishahi, Ameneh Rajabi Darbandiolya, Amir Mohammad Nazemi 2020 10h International Conference on Computer and Knowledge Engineering Iccke 2020, 2020 The demand of users and the increase of devices connected to cellular networks has increased accordingly, since the advent of different generations of mobile phones and the communication between people through mobile phones. Over the years, researchers and mobile operators have come to the conclusion that current technologies do not meet the needs of users. Therefore, to meet the needs of users, the number of micro-cells is increasing sharply, but with this volume of increase, mobile operators are facing the challenge of energy consumption. Using the cell shutdown approach, key and very useful solutions can be provided to optimize energy consumption in mobile cellular networks. In the cell shutdown method, shutting down a number of cells, moving them to an adjacent cell, without compromising the quality of service and reducing the covered areas, is a requirement of this approach. This paper simulates a solution to reduce energy consumption in base stations by clustering and selecting a base station based on the annealing algorithm. The simulation results show that the proposed model, compared to the model that is performed only with respect to the node Euclidean distance to the base station, has improved an operational power of more than 5%, a power consumption of more than 2% and a network lifetime of more than 3%. While the average of inactive base stations in the proposed model has been up to 8% higher.
An Efficient Authentication and Key Agreement Scheme Based on ECDH for Wireless Sensor Network Mostafa Farhadi Moghadam, Mahdi Nikooghadam, Maytham Azhar Baqer Al Jabban, Mohammad Alishahi, Leili Mortazavi, Amirhossein Mohajerzadeh IEEE Access, 2020 Wireless sensor networks (WSN) consist of a large number of resource-constrained sensor nodes, different types of controls, and gateway nodes. these kinds of networks are used as control systems and remote monitoring in industries such as health care, defense, agriculture, and disaster management. Due to the widespread use of wireless sensor networks, valuable information is exchanged between network entities such as sensors, gates, users, etc. in an unsafe channel, and the presence of important and sensitive information in the network increases the importance of security issues. In this article, we analyzed Majid Alotaibi schema and identify some security breaches in this article. We have also described a security attack against the proposed protocol based on security problems. In addition, to address the security issues of M. Alotaibi proposed protocol, we have introduced a mutual authentication and key agreement protocol based on ECDH (elliptic-curve Diffie–Hellman). We have implemented our own method using the Scyther tool, manually reviewed its security features and also compared it with other methods.
An Efficient Target Tracking in Directional Sensor Networks Using Adapted Unscented Kalman Filter Zahra Izadi-Ghodousi, Mahsa Hosseinpour, Fatemeh Safaei, Amir Hossein Mohajerzadeh, Mohammad Alishahi Wireless Personal Communications, 2019 In this paper we have considered an efficient adapted Unscented Kalman Filter based target tracking in directional wireless sensor networks while observations are noise-corrupted. In directional sensor networks, sensors are able to observe the target only in specified (and certainly changeable) directions. Also, sensor nodes are capable of measuring the bearings (relative angle to the target). To make target tracking efficient, first, we use scheduling algorithm which determines the sensor nodes activity. Also coverage is a challenge that we will discuss in this paper as well. Sensor nodes activation algorithm directly affects the target areas coverage. Second, we use time series to predict the motion of the target. Using ARIMA, in each step of target position estimation, an area will be predicted where the target would be there with high probability. Third, we use a version of UKF, which is adjusted to the requirements of the target tracking application, to determine the position of the target with desired precision. Fourth, a routing algorithm called as C-RPL is used to perform the communications between sensor nodes in each step. Simulation results approve that the proposed efficient target tracking algorithm achieves its goals.
Multi-class routing protocol using virtualization and SDN-enabled architecture for smart grid Mohammad Alishahi, Mohammad Hossein Yaghmaee Moghaddam, Hamid Reza Pourreza Peer to Peer Networking and Applications, 2018 Routing Protocol for Low Power and Lossy Network (RPL) is standardized and known as the primary solution for the last mile communication network in the smart grid. Various applications with different requirements are rapidly developed in the smart grid. The need to provide Quality of Service (QoS) for such a communication network is inevitable. In this paper, we use the benefits of virtualization and software-defined networking to present a virtual version of the RPL protocol which we name OMC-RPL (Optimized Multi-Class RPL). We present an SDN-enabled architecture consisting of a central controller and some SDN nodes. This implementation reduces the complexity and controls interactions to distribute the network states and other related information in the network. The proposed SDN-enabled architecture consists of different components including Network Link Discovery, Topology Manager, and Virtual Routing. OMC-RPL utilizes a holistic objective function including distinctive metrics related to QoS, and supports the data classification which is an essential requirement in this context. The proposed objective function considers different numbers of traffic classes by using weighting parameters. An optimization algorithm determines the best values of these coefficients. OMC-RPL is evaluated in different aspects. Simulation results show that the new idea significantly decreases both the end-to-end delay and packet loss which are the important factors of QoS. The virtualization idea is also investigated, which results in less message exchange.
Data quality improvement using fuzzy association rules Fatemeh Ghorbanpour Alizamini, Mir Mohsen Pedram, Mohammad Alishahi, Kambiz Badie Iceie 2010 2010 International Conference on Electronics and Information Engineering Proceedings, 2010
Prediction of calving to conception interval (days open) in dairy cows using recurrent neural networks M Ravakhah, M Alishahi, MMG Gholami Journal of Dairy Research 93 (1), 42-50 , 2026 2026
Design of a optimal robust adaptive neural network-based fractional-order PID controller for H-bridge single-phase inverter R Kashfi, S Balochian, M Alishahi Applied Soft Computing 166, 112142 , 2024 2024 Citations: 11
Design of a single input control signal for fault-tolerant synchronization of fractional order hyperchaotic Lu system A Sabaghian, S Balochian, M Alishahi Cyber-Physical Systems 10 (2), 176-196 , 2024 2024 Citations: 2
Predicting Insemination Outcome in Holstein Dairy Cattle using Deep Learning M Alishahi, M Ravakhah یملع هیرشن ناریا یماد مولع یاهشهوژپ, 529 , 2023 2023
Flying‐inductor‐cell based inverters for single‐phase transformerless PV applications MR Aalami, M Zarif, M Alishahi, AA Shojaei, HH Doostabad IET Power Electronics 16 (1), 75-91 , 2023 2023 Citations: 3
A novel output power determination and power distribution of hybrid energy storage system for wind turbine power smoothing M Eydi, M Alishahi, M Zarif IET Electric Power Applications 16 (12), 1559-1575 , 2022 2022 Citations: 15
A parallel CNN-BiGRU network for short-term load forecasting in demand-side management A Irankhah, SR Saatlou, MH Yaghmaee, S Ershadi-Nasab, M Alishahi 2022 12th International Conference on Computer and Knowledge Engineering … , 2022 2022 Citations: 13
Investigation of the effects of residential battery storage deployment on peak-shaving performance M Zarif, M Alishahi, A Ghasemi IRANIAN ELECTRIC INDUSTRY JOURNAL OF QUALITY AND PRODUCTIVITY (IEIJQP) 10 … , 2021 2021
Turn off/on base stations with CSO approach using simulated annealing algorithm in 5G networks L Mortazavi, M Alishahi, AR Darbandiolya, AM Nazemi 2020 10th International Conference on Computer and Knowledge Engineering … , 2020 2020 Citations: 3
An efficient authentication and key agreement scheme based on ECDH for wireless sensor network MF Moghadam, M Nikooghadam, MAB Al Jabban, M Alishahi, L Mortazavi, ... IEEe Access 8, 73182-73192 , 2020 2020 Citations: 98
An Efficient Target Tracking in Directional Sensor Networks Using Adapted Unscented Kalman Filter Z Izadi-Ghodousi, M Hosseinpour, F Safaei, AH Mohajerzadeh, ... Wireless Personal Communications 109 (3), 1925-1954 , 2019 2019 Citations: 4
Power Quality Assessment of a Single Customer Micro Grid-Case Study M Zabihi, N Nakhodchi, H Ghorbanpanah, S Alishahi 25th International Conference on Electricity Distribution (CIRED 2019), 3-6 … , 2019 2019
Multi-class routing protocol using virtualization and SDN-enabled architecture for smart grid M Alishahi, MH Yaghmaee Moghaddam, HR Pourreza Peer-to-Peer Networking and Applications 11 (3), 380-396 , 2018 2018 Citations: 36
Designing optimized scheduling QoS-aware RPL for sensor-based smart grid communication network M Alishahi, MH Yaghmaee Moghadam, H Pourreza Computer and Knowledge Engineering 1 (1), 21-32 , 2018 2018 Citations: 3
An efficient and light asymmetric cryptography to secure communication in smart grid M Alishahi, M Farhadi, S Jafari, M Taghavi, H Moosavi, A Mohajerzadeh 2017 IEEE International Conference on Smart Energy Grid Engineering (SEGE … , 2017 2017 Citations: 6
Development of a resilient hybrid microgrid with integrated renewable power generations supplying DC and AC loads G Wu, Y Ono, M Alishahi 2015 IEEE International Telecommunications Energy Conference (INTELEC), 1-5 , 2015 2015 Citations: 21
Improving the QoS in Intelligent Connected EVSE by Using RPL MHYGW M. Alishahi Amirkabir International Journal of Science& Research (Electrical … , 2015 2015 Citations: 1
Proposing a RPL based protocol for intelligent connected vehicles M Alishahi, M Majidpour 2014 Citations: 4
QoS assurance in Smart Grid for IP-based applications of Mashhad Electric Energy Distribution company M Alishahi, MH Yaghmaee, M Zabihi, SS Khorasani 22nd International Conference and Exhibition on Electricity Distribution … , 2013 2013 Citations: 2
Tag name structure-based clustering of XML documents M Alishahi, M Naghibzadeh, BS Aski International Journal of Computer and Electrical Engineering 2 (1), 119 , 2010 2010 Citations: 20
MOST CITED SCHOLAR PUBLICATIONS
An efficient authentication and key agreement scheme based on ECDH for wireless sensor network MF Moghadam, M Nikooghadam, MAB Al Jabban, M Alishahi, L Mortazavi, ... IEEe Access 8, 73182-73192 , 2020 2020 Citations: 98
Multi-class routing protocol using virtualization and SDN-enabled architecture for smart grid M Alishahi, MH Yaghmaee Moghaddam, HR Pourreza Peer-to-Peer Networking and Applications 11 (3), 380-396 , 2018 2018 Citations: 36
Development of a resilient hybrid microgrid with integrated renewable power generations supplying DC and AC loads G Wu, Y Ono, M Alishahi 2015 IEEE International Telecommunications Energy Conference (INTELEC), 1-5 , 2015 2015 Citations: 21
Tag name structure-based clustering of XML documents M Alishahi, M Naghibzadeh, BS Aski International Journal of Computer and Electrical Engineering 2 (1), 119 , 2010 2010 Citations: 20
A novel output power determination and power distribution of hybrid energy storage system for wind turbine power smoothing M Eydi, M Alishahi, M Zarif IET Electric Power Applications 16 (12), 1559-1575 , 2022 2022 Citations: 15
A parallel CNN-BiGRU network for short-term load forecasting in demand-side management A Irankhah, SR Saatlou, MH Yaghmaee, S Ershadi-Nasab, M Alishahi 2022 12th International Conference on Computer and Knowledge Engineering … , 2022 2022 Citations: 13
Design of a optimal robust adaptive neural network-based fractional-order PID controller for H-bridge single-phase inverter R Kashfi, S Balochian, M Alishahi Applied Soft Computing 166, 112142 , 2024 2024 Citations: 11
An efficient and light asymmetric cryptography to secure communication in smart grid M Alishahi, M Farhadi, S Jafari, M Taghavi, H Moosavi, A Mohajerzadeh 2017 IEEE International Conference on Smart Energy Grid Engineering (SEGE … , 2017 2017 Citations: 6
Distinguishing fall activities using human shape characteristics H Foroughi, M Alishah, H Pourreza, M Shahinfar Technological Developments in Education and Automation, 523-528 , 2009 2009 Citations: 6
An Efficient Target Tracking in Directional Sensor Networks Using Adapted Unscented Kalman Filter Z Izadi-Ghodousi, M Hosseinpour, F Safaei, AH Mohajerzadeh, ... Wireless Personal Communications 109 (3), 1925-1954 , 2019 2019 Citations: 4
Proposing a RPL based protocol for intelligent connected vehicles M Alishahi, M Majidpour 2014 Citations: 4
XML document clustering based on common tag names anywhere in the structure M Alishahi, M Ravakhah, B Shakeriaski, M Naghibzade 2009 14th International CSI Computer Conference, 588-595 , 2009 2009 Citations: 4
Flying‐inductor‐cell based inverters for single‐phase transformerless PV applications MR Aalami, M Zarif, M Alishahi, AA Shojaei, HH Doostabad IET Power Electronics 16 (1), 75-91 , 2023 2023 Citations: 3
Turn off/on base stations with CSO approach using simulated annealing algorithm in 5G networks L Mortazavi, M Alishahi, AR Darbandiolya, AM Nazemi 2020 10th International Conference on Computer and Knowledge Engineering … , 2020 2020 Citations: 3
Designing optimized scheduling QoS-aware RPL for sensor-based smart grid communication network M Alishahi, MH Yaghmaee Moghadam, H Pourreza Computer and Knowledge Engineering 1 (1), 21-32 , 2018 2018 Citations: 3
Preserving integrity and privacy of data in smart grid communications S Alishahi, SM Seyyedi, MH Yaghmaee, M Alishahi Proc. CIRED Workshop-Rome, 11-12 , 2004 2004 Citations: 3
Design of a single input control signal for fault-tolerant synchronization of fractional order hyperchaotic Lu system A Sabaghian, S Balochian, M Alishahi Cyber-Physical Systems 10 (2), 176-196 , 2024 2024 Citations: 2
QoS assurance in Smart Grid for IP-based applications of Mashhad Electric Energy Distribution company M Alishahi, MH Yaghmaee, M Zabihi, SS Khorasani 22nd International Conference and Exhibition on Electricity Distribution … , 2013 2013 Citations: 2
Improving the QoS in Intelligent Connected EVSE by Using RPL MHYGW M. Alishahi Amirkabir International Journal of Science& Research (Electrical … , 2015 2015 Citations: 1
Prediction of calving to conception interval (days open) in dairy cows using recurrent neural networks M Ravakhah, M Alishahi, MMG Gholami Journal of Dairy Research 93 (1), 42-50 , 2026 2026