Zokir Mamadiyarov
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Zokir Mamadiyarov has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Abdieva Nargiza Shukhratovna1 shared publication
Deepender Kumar
1 shared publication- Dr.M. Rajeswari1 shared publication
- E. Laxmi Lydia
VR Siddhartha Engineering College(A), Siddhartha Academy of Higher Education (Deemed to be University)
1 shared publication - Elvir Akhmetshin
Mamun University
1 shared publication - Emil Hajiyev
Department of Business Management, Azerbaijan State University of Economics (UNEC), Baku, Azerbaijan
1 shared publication
Latest Publications
- 12 December 2025
- Published by Natural and Engineering Sciences
- Vol. 10 (3) , 819-832
AI-Enabled Neural Computing and Genetic Algorithm Optimization for Resource-Efficient Smart Environments in IoT Applications
The recent accelerated growth of Internet of Things (IoT) implementations in smart environments has amplified the situation regarding the energy efficiency and computational scalability coupled with dynamic resource management in heterogeneous and timevarying conditions. Old-fashioned centralised and non-adaptive based optimization mechanisms are growing to be ineffective mainly because they are very rigid, and they consume a lot of overhead. In order to overcome these limitations, the given paper will introduce an AI-assisted hybrid optimization strategy which incorporates the principles of neural computing with those of genetic algorithm (GA)-run evolutionary optimization to facilitate resource-optimal and intelligent performance of IoT-driven smart surroundings. Under the suggested methodology, lightweight neural computing frameworks implemented at the edge tier offer real-time local awareness and forecast estimation of the workload, energy requirements and network states of affair. A multi-objective GA then uses these predictions to produce dynamic optimization of the critical system parameters such as task scheduling, duty cycling, transmission power and edge-cloud offloading decisions. Closed-loop feedback allows the hybrid neural to act proactively and to implement global optimization and dynamically adapt itself through a hybrid neural structure. Comprehensive simulations of the framework on the basis of different node densities and traffic conditions prove that the proposed framework outperforms the traditional heuristic, neural-only, and GA-only strategies through optimization significantly. Experiments have shown significant energy savings and latency at the end, and significant increases in network lifetime and Quality of service (QoS) sustainability. The solution proposed is scalable, computationally efficient and is well adapted to the deployment in next-generation smart cities, smart buildings and industrial IoT systems that need smart, autonomous and resource-aware operation.
- 12 December 2025
- Published by Natural and Engineering Sciences
- Vol. 10 (3) , 819-832
AI-Enabled Neural Computing and Genetic Algorithm Optimization for Resource-Efficient Smart Environments in IoT Applications
The recent accelerated growth of Internet of Things (IoT) implementations in smart environments has amplified the situation regarding the energy efficiency and computational scalability coupled with dynamic resource management in heterogeneous and timevarying conditions. Old-fashioned centralised and non-adaptive based optimization mechanisms are growing to be ineffective mainly because they are very rigid, and they consume a lot of overhead. In order to overcome these limitations, the given paper will introduce an AI-assisted hybrid optimization strategy which incorporates the principles of neural computing with those of genetic algorithm (GA)-run evolutionary optimization to facilitate resource-optimal and intelligent performance of IoT-driven smart surroundings. Under the suggested methodology, lightweight neural computing frameworks implemented at the edge tier offer real-time local awareness and forecast estimation of the workload, energy requirements and network states of affair. A multi-objective GA then uses these predictions to produce dynamic optimization of the critical system parameters such as task scheduling, duty cycling, transmission power and edge-cloud offloading decisions. Closed-loop feedback allows the hybrid neural to act proactively and to implement global optimization and dynamically adapt itself through a hybrid neural structure. Comprehensive simulations of the framework on the basis of different node densities and traffic conditions prove that the proposed framework outperforms the traditional heuristic, neural-only, and GA-only strategies through optimization significantly. Experiments have shown significant energy savings and latency at the end, and significant increases in network lifetime and Quality of service (QoS) sustainability. The solution proposed is scalable, computationally efficient and is well adapted to the deployment in next-generation smart cities, smart buildings and industrial IoT systems that need smart, autonomous and resource-aware operation.
- Open Access
- 8 December 2025
- Published by Engineering, Technology & Applied Science Research in Engineering, Technology & Applied Science Research
- Vol. 15 (6) , 29035-29040
A Financial Time Series Forecasting Model Using Quasi-Recurrent Neural Networks and the Crown Porcupine Optimizer for Stock Market Risk Prediction
Stock is a financial product described by flexible trading, high risk, and high return, which is favored by many investors. Investors may obtain sufficient returns by precisely approximating stock price developments. However, a stock price is affected by several factors, such as market conditions, macroeconomic situation, major economic and social events, and managerial decisions of companies. As a result, Stock Price Prediction (SPP) has consistently attracted attention and is an important field of investigation. Currently, Machine Learning (ML) is extensively utilized in SPP, but considerably more appropriate techniques are suggested for the prediction of stock prices, as numerous investigations have proved that Deep Learning (DL) has better efficacy than other methods. The paper proposes a Financial Time Series Forecasting Using Quasi Recurrent Neural Network and Crown Porcupine Optimizer (FTSF-QRNNCPO) method, offering an intelligent framework for financial stock market price prediction to accurately assess market volatility and forecast associated investment risks. The FTSF-QRNNCPO method begins with data preprocessing, comprising missing value handling, data cleaning, and normalization to prepare the input data effectively. The Secretary Bird Optimization Algorithm (SBOA) is employed for optimal Feature Selection (FS). Then, the Quasi-Recurrent Neural Network (QRNN) approach is employed for prediction. The Crown Porcupine Optimizer (CPO) approach is employed in the parameter tuning process. The FTSF-QRNNCPO technique was experimentally evaluated on a Tesla stock price dataset, demonstrating superior accuracy, achieving a significantly lower MAPE of 0.415% and outperforming previous models.
- 8 December 2025
- Published by Engineering, Technology & Applied Science Research in Engineering, Technology & Applied Science Research
- Vol. 15 (6) , 29035-29040
Open AccessA Financial Time Series Forecasting Model Using Quasi-Recurrent Neural Networks and the Crown Porcupine Optimizer for Stock Market Risk Prediction
Stock is a financial product described by flexible trading, high risk, and high return, which is favored by many investors. Investors may obtain sufficient returns by precisely approximating stock price developments. However, a stock price is affected by several factors, such as market conditions, macroeconomic situation, major economic and social events, and managerial decisions of companies. As a result, Stock Price Prediction (SPP) has consistently attracted attention and is an important field of investigation. Currently, Machine Learning (ML) is extensively utilized in SPP, but considerably more appropriate techniques are suggested for the prediction of stock prices, as numerous investigations have proved that Deep Learning (DL) has better efficacy than other methods. The paper proposes a Financial Time Series Forecasting Using Quasi Recurrent Neural Network and Crown Porcupine Optimizer (FTSF-QRNNCPO) method, offering an intelligent framework for financial stock market price prediction to accurately assess market volatility and forecast associated investment risks. The FTSF-QRNNCPO method begins with data preprocessing, comprising missing value handling, data cleaning, and normalization to prepare the input data effectively. The Secretary Bird Optimization Algorithm (SBOA) is employed for optimal Feature Selection (FS). Then, the Quasi-Recurrent Neural Network (QRNN) approach is employed for prediction. The Crown Porcupine Optimizer (CPO) approach is employed in the parameter tuning process. The FTSF-QRNNCPO technique was experimentally evaluated on a Tesla stock price dataset, demonstrating superior accuracy, achieving a significantly lower MAPE of 0.415% and outperforming previous models.