Agricultural and Biological Sciences, Engineering, Industrial and Manufacturing Engineering, Environmental Engineering
4
Scopus Publications
12
Scholar Citations
2
Scholar h-index
Scopus Publications
Enhancing autonomous agriculture control systems in greenhouses for sustainable resource usage using deep learning techniques Iman Hindi, Adham Alsharkawi, Malik Al-Ajlouni, Bassam Qarallah Plos One, 2026 Greenhouse climate control is essential for optimizing crop growth while minimizing resource consumption in controlled environment agriculture. Traditional rule-based and fixed-action strategies often struggle to achieve a balance between these objectives. This paper proposes a reinforcement learning (RL) based framework for greenhouse climate control, integrating deep learning models to predict both crop growth and resource consumption. The framework enables an RL agent to optimize greenhouse control setpoints dynamically, maximizing crop yield while ensuring sustainable resource usage. The proposed system incorporates a Multi-Layer Perceptron (MLP) model to predict internal greenhouse climate conditions, a Long Short-Term Memory (LSTM) model for crop parameter estimation, and a separate LSTM model for forecasting daily resource consumption. These models collectively simulate a greenhouse environment where an RL agent learns to regulate temperature, CO 2 concentration, and irrigation levels by interacting with the virtual environment. A custom reward function is designed to guide the agent, considering key crop parameters; stem elongation, stem thickness, and cumulative trusses; alongside resource consumption metrics, including heating, electricity, CO 2 , and irrigation costs. To enhance the adaptability of the RL agent, a feature-selection mechanism identified the most influential climate and control features, reducing observation complexity and accelerating convergence. Retraining under stochastic weather conditions strengthened robustness to dynamic environments, enabling the agent to consistently outperform fixed-action strategies. Evaluation revealed a stable Pareto frontier between yield and resource consumption, confirming that the framework accurately captured the productivity and sustainability trade-off and remained robust across varying reward-weight settings. Comparative analysis of multiple RL algorithms; Proximal Policy Optimization (PPO), Deep Deterministic Policy Gradient (DDPG), Soft Actor-Critic (SAC), and Twin Delayed Deep Deterministic Policy Gradient (TD3) demonstrated that TD3 outperforms other algorithms, achieving the highest cumulative rewards and reaching optimal policies faster. Experimental evaluations demonstrate that the proposed TD3 RL-based greenhouse control system achieves higher crop yield growth rates while optimizing resource usage, outperforming conventional greenhouse control strategies. This study presents a novel data-driven, adaptive greenhouse management approach, bridging the gap between crop growth modeling and autonomous climate control, contributing to sustainable and intelligent agricultural practices.
Improving Arabic Dialect Text Classification by Finetuning A Pretrained Token-Free Large Language Model Iman I. Hindi, Gheith A. Abandah 2025 1st International Conference on Computational Intelligence Approaches and Applications Icciaa 2025 Proceedings, 2025 Classifying Arabic dialect texts is a critical preprocessing step for natural language processing tasks and helps identify the demographics of text sources. However, the significant variability among dialects and the lack of standardized orthography make this task highly challenging. This study explores the use of a token-free large language model for Arabic dialect classification. We fine-tune the Hugging Face ByT5 pretrained model, which operates without requiring a traditional tokenizer, enabling it to handle the diverse and non-standard vocabulary of Arabic dialects effectively. Comparative experiments with convolutional neural networks (CNNs) and long short-term memory (LSTM) networks show that ByT5 achieves superior performance, offering better accuracy and robustness. Extensive evaluation on the QADI dataset highlights the ByT5 model's state-of-the-art results, achieving an F1 score of 74%. These findings underscore the importance of token-free approaches and transfer learning in overcoming the complexities of Arabic dialect classification.
Optimizing Cherry Tomato Crop Irrigation: A Robust Daily Schedule Incorporating Weather, Soil, and Irrigation Data through Cascaded-Output ANN Iman Hindi, Mohammad Al Mashagbeh, Adham Alsharkawi 2024 15th International Conference on Information and Communication Systems Icics 2024, 2024 Water scarcity and the lack of fertile agricultural land are pressing issues in many countries, including Jordan, one of the world's driest nations. This study aims to develop an AI-driven irrigation system to optimize the daily irrigation schedule and water quantity for cherry tomato plants. Utilizing data from the Autonomous Greenhouse Challenge, this research focuses on creating a reliable multi-output regressor to determine the ideal time, duration, and amount of irrigation needed. The data, collected every five minutes over 166 days, encompasses external weather, greenhouse climate, soil, and root zone conditions. The study introduces a Cascaded Output Artificial Neural Network (Cascaded-Out ANN), which sequentially processes each predicted output as an input for the subsequent layer, outperforming traditional multi-output regression models. Evaluations using metrics such as normalized RMSE, MSE, and R<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> scores demonstrate significant improvements in prediction accuracy. The Cascaded-Out ANN model's superior performance is further validated through RMSE confidence interval comparisons, confirming its efficacy in managing water resources for cherry tomato cultivation. This approach not only addresses water conservation but also enhances crop yield and quality, thereby supporting Jordanian farmers in increasing profitability and reducing costs.
Smart Alarm IoT System: Monitoring Elevator Traffic and Meteorological Data on Job Sites Using MQTT and InfluxDB integrated with Grafana Iman Hindi, Musa Alyaman, Amani AboZenah, Albaraa Zaid, Mohammad Shrara 2024 15th International Conference on Information and Communication Systems Icics 2024, 2024 In this paper, we design and implement an IoT system as part of a comprehensive solution to collect and analyze meteorologiacal and elevator traffic data at job sites, with the ultimate goal of developing a sophisticated smart alarm system. This system is designed to wake workers at an optimal time, considering various job site conditions to minimize delays and ensure timely arrival. The system utilizes MQTT to publish data from various stations across the site, with a central station subscribing to this data for further processing. InfluxDB is employed as the cloud storage solution for structured data, which is then integrated with Grafana for advanced analysis. This allows us to determine peak elevator traffic hours and average daily outside temperatures in addition to fuel tank level estimation of heating system. This done by using a Raspberry-Pi with a camera captures periodic images, which are published to an MQTT broker. The main PC subscribes to this topic, processes the images to detect the number of faces; which represent the elevator traffic load at this moment of capturing the photo; then sends the results with timestamps to InfluxDB, alongside meteorological data. In addition to job site monitoring we implement the rout to work system to log the time needed by attached a GSM module in the body of the car. These analyses are crucial for developing the next phase of the Smart wakeup Alarm IoT system. The system underscores the potential of IoT technologies in reducing worker delays and improving punctuality
RECENT SCHOLAR PUBLICATIONS
Enhancing autonomous agriculture control systems in greenhouses for sustainable resource usage using deep learning techniques I Hindi, A Alsharkawi, M Al-Ajlouni, B Qarallah Plos one 21 (3), e0344946 , 2026 2026.0 Citations: 1
Improving Arabic Dialect Text Classification by Finetuning A Pretrained Token-Free Large Language Model II Hindi, GA Abandah 2025 1st International Conference on Computational Intelligence Approaches … , 2025 2025.0 Citations: 1
Optimizing Cherry Tomato Crop Irrigation: A Robust Daily Schedule Incorporating Weather, Soil, and Irrigation Data through Cascaded-Output ANN I Hindi, M Al Mashagbeh, A Alsharkawi 2024 15th International Conference on Information and Communication Systems … , 2024 2024.0 Citations: 2
Smart Alarm IoT System: Monitoring Elevator Traffic and Meteorological Data on Job Sites Using MQTT and InfluxDB integrated with Grafana I Hindi, M Alyaman, A AboZenah, A Zaid, M Shrara 2024 15th International Conference on Information and Communication Systems … , 2024 2024.0 Citations: 8
Amoura, Motasem 62 Attia, Ayman 13 M Azzeh, M Bani Yassein, M Bani Younes, R Bani-Hani, O Banimelhem, ...
MOST CITED SCHOLAR PUBLICATIONS
Smart Alarm IoT System: Monitoring Elevator Traffic and Meteorological Data on Job Sites Using MQTT and InfluxDB integrated with Grafana I Hindi, M Alyaman, A AboZenah, A Zaid, M Shrara 2024 15th International Conference on Information and Communication Systems … , 2024 2024.0 Citations: 8
Optimizing Cherry Tomato Crop Irrigation: A Robust Daily Schedule Incorporating Weather, Soil, and Irrigation Data through Cascaded-Output ANN I Hindi, M Al Mashagbeh, A Alsharkawi 2024 15th International Conference on Information and Communication Systems … , 2024 2024.0 Citations: 2
Enhancing autonomous agriculture control systems in greenhouses for sustainable resource usage using deep learning techniques I Hindi, A Alsharkawi, M Al-Ajlouni, B Qarallah Plos one 21 (3), e0344946 , 2026 2026.0 Citations: 1
Improving Arabic Dialect Text Classification by Finetuning A Pretrained Token-Free Large Language Model II Hindi, GA Abandah 2025 1st International Conference on Computational Intelligence Approaches … , 2025 2025.0 Citations: 1
Amoura, Motasem 62 Attia, Ayman 13 M Azzeh, M Bani Yassein, M Bani Younes, R Bani-Hani, O Banimelhem, ...
Publications
Enhancing autonomous agriculture control systems in greenhouses for sustainable resource usage using deep learning techniques
Iman Hindi,Adham Alsharkawi ,Malik Al-Ajlouni,Bassam Qarallah
Published: March 26, 2026
