A novel augmented reality and reinforcement learning empowered communication framework for underwater unmanned autonomous vehicle Abdullah Lakhan, Mazin Abed Mohammed, Mohd Khanapi Abd Ghani, Sajida Memon, Suleman Khan, Haydar Abdulameer Marhoon, Ahmed Dheyaa Radhi, Radek Martinek Scientific Reports, 2026 These days, autonomous uncrewed underwater vehicles (UUVs) play a crucial role in marine exploration, surveillance, and environmental monitoring. However, their communication and object identification are key challenges due to high latency, limited bandwidth, and security vulnerabilities. Traditional UUV frameworks have distinct limitations and pose challenges for dynamic communication in critical environments. To address the above issue, this paper presents a novel augmented reality and reinforcement learning-enabled communication framework for UUAV applications to improve communication quality, enhance object detection, and identify system vulnerabilities. In this framework, we propose adaptive augmented reality and reinforcement learning scheduling strategies (AARLSS) to optimize communication at long and short ranges during navigation and to identify objects and vulnerabilities at runtime while executing applications. AARLSS optimises the performance of UUAV, minimises energy consumption and delay, reduces security risks, and improves the accuracy of objective detection. AARLSS offers various methods and functionalities, including using other sensors as inputs, preprocessing, and training the entire workload as a mini-benchmark using deep Q-learning (DQN). A scheduler allocates them to available resources before execution, subject to time and deadline constraints, and verifies them using an adaptive intrusion detection system (IDS). We created an augmented and virtual reality testbed for the experimental setup and evaluated the performance of different methods. The results show that the proposed methods minimised UUAs' energy consumption by 20 to 21%, reduced delay by 18 to 20%, and improved accuracy by 97 to 98% during experiments on the testbed setup.
Secure IoMT smartwatch-based blood glucose monitoring using multimodal activity and nutrition data with transfer learning Mazin Abed Mohammed, Mohd Khanapi Abd Ghani, Sajida Memon, Abdullah Lakhan, Haydar Abdulameer Marhoon, Ahmed Dheyaa Radhi, Lukas Danys, Radek Martinek Scientific Reports, 2026 In the modern era, healthcare faces critical challenges as individuals often consume unbalanced diets and neglect physical activity. A primary concern is elevated blood glucose levels, which commonly result from high carbohydrate intake and a sedentary lifestyle. To address this, the paper proposes a novel system: Enhanced Body Sugar Monitoring-Secure Smartwatches Leveraging IoMT for Activity and Nutrition Execution Based on Transfer Learning. The system collects multimodal data, including subject, nutrition, and activity records, to predict and display blood sugar levels under varying dietary and activity conditions using open-world multimodal datasets. The presented smartwatch-enabled framework is equipped with various Internet of Medical Things (IoMT) sensors, including heart rate, blood pressure, oxygen saturation, and more. These sensors are the inputs to different tasks that have collected data from them and offloaded execution to remote services. At the same time, the TL-DCNNOS algorithm processes the entire workflow through separate pipelines, such as data collection and encryption, and offloads task data to nearby edge nodes for secure execution. For real-time learning and training on sensor data while executing tasks across different nodes, we employ transfer learning and DCNNs to learn patterns of behavior such as eating, sitting, walking, and more to identify normal and abnormal behavior. We used the open-world IoMT dataset to train the initial model, and then trained and classified at runtime during real-time experiments on the testbed with different subjects. Simulation results show that we minimized time consumption and security risk and improved sugar prediction accuracy to 99% with various runtime activities, compared with existing studies.
Towards intelligent air quality forecasting using integrated machine learning framework with variational mode decomposition and catboost feature selection Iman Ahmadianfar, Zaher Mundher Yaseen, Haydar Abdulameer Marhoon, Bijay Halder, Mou Leong Tan, Huseyin Cagan Kilinc, Sani I. Abba, Salim Heddam, Leonardo Goliatt, Vahdettin Demir, Ahmed M. Al-Areeq Scientific Reports, 2026 Predicting air pollution is crucial in improving air quality (AQ), which consequently provides benefits to the ecosystems and human health. AQ predictions often make use of Machine Learning (ML) approaches; nevertheless, these methods are not without their limitations. The main contribution of this research is to develop an efficient framework using machine learning (ML) for forecasting daily air quality metrics for Sulfur dioxide (SO 2 ) and Nitrogen dioxide (NO 2 ) in Changping, China. The suggested ML method is based on a set of local weights and a kernel extreme learning machine (LWKELM) model integrated with an efficient feature selection, the Catboost method, to extract influential input variables. Additionally, the input variables, collected from 2013 to 2017, are decomposed using multivariate variational mode decomposition (MVMD), which enhanced the predicting accuracy. Furthermore, the interior search algorithm (ISA), a robust optimization strategy, is a possible way of optimizing the models’ hyperparameters. The results of the developed model was compared with the four other reliable ML approaches, including the locally weighted linear regression (LWLR), gaussian process regression (GPR), KELM, and multivariate adaptive regression spline (MARS) models. Based on the results, the proposed model demonstrates superior performance across statistical metrics for both parameters (NO₂: R = 0.978, RMSE = 0.537 and SO₂: R = 0.974, RMSE = 1.965) compared to alternative models. The MVMD-LWKELM-ISA model delivers highly accurate one-day-ahead forecasts for SO 2 and NO 2 and stands out as the most effective and intelligent approach for forecasting these daily parameters.
Modeling and Analysis of WSN-Enabled Solar Tracking System with On-Nodes Energy Harvesting Dr. Raaid Alubady, Dr. Atheer Y. Oudah, Dr. Haydar Abdulameer Marhoon Journal of Wireless Mobile Networks Ubiquitous Computing and Dependable Applications, 2026 This paper proposes and discusses a WSNs-based solar tracking system which is targeted at maximizing the collection of PV energy at low operation costs. The modules are all autonomous sensors of the solar elevation, calculating the associated maximum tilt and changing its direction every hour with a low-complexity controller, given Gaussian sensing noise. The by tracking the sun in a dynamical way over a 24-hours period in the MATLAB implementation, the system has an average tracking error of less than 2o, which translates to a greater than 99.9 % optical effectiveness. The simulation has indicated that this system increases the most daily energy production by nearly a twofold, which is 1.8 kWh of energy produced by the fixed-tilt arrays and about 3.4kwh/module of energy generated by 90 tilt a 90 % enhancement. This is greatest during the periods of 9 AM to 3 PM, when the losses of cosine of fixed systems are highest. The operating value of the system is less than 0.01kWh/day per node. Communication is done with short-range and single hop radio connections to a sink at the center. The system is well designed in space organization and orientation to have homogeneous wireless coverage; This is ensured by a 3D deployment visualization that confirms the robust design of the system. These results confirm the fact that WSN-based tracking is an energy-saving, cost-efficient option in the next-generation of PV systems, in particular, the distributed or off-grid solar systems. The efficiency and the low cost of running the energy harvesting applications with WSNs is guaranteed by the integration of WSNs.
A secure mist-fog-assisted cooperative offloading framework for sustainable smart city development Subhranshu Sekhar Tripathy, Sujit Bebortta, Mazin Abed Mohammed, Muhammet Deveci, Haydar Abdulameer Marhoon, Radek Martinek Digital Communications and Networks, 2026 Practical applications of smart cities and the Internet of Things (IoT) have multiplied, posing many difficulties in network performance, dependability, and security. Concerns of accessibility, reliability, sustainability, and security too have arisen correspondingly because of the decentralized character of the smart city and IoT systems. Fog computing offers a foundation for various applications, including cognitive support, health and social services, intelligent transportation systems, and pervasive computing and communications. Fog computing can help enhance these apps' productivity and lower the end-to-end delay experienced by such time-sensitive applications. In this research, we propose a reliable and secure service delivery strategy at the network edge for smart cities. To improve the availability and dependability, along with the security of smart city applications, the approach employs a combined method uniting distributed fog servers in addition to mist servers with the help of an intrusion detection system. Simulation findings suggest a reduction of 40.3% in the delay incurred by each service request for highly dense areas and 60.6% for moderately dense environments. Furthermore, the system has low false-negative rates and high detection and accuracy rates, decreasing service requests 2%.
Privacy-preserving communication in smart city transportation using elliptic curve cryptography Zainab Khalid Mohammed, Mazin Abed Mohammed, Mohd Khanapi Abd Ghani, Salah A. Aliesawi, Abdullah Lakhan, Karrar Hameed Abdulkareem, Haydar Abdulameer Marhoon, Mohammed Nasser Al-Andoli Scientific Reports, 2025 The integration of cyber-physical systems (CPS) with the Internet of Things (IoT) in smart city transportation systems presents promising opportunities, however poses challenges in data privacy and security. This paper proposes a novel approach to address these challenges by incorporating Elliptic Curve Cryptography (ECC) for heightened data security in CPS-IoT integrated transportation. ECC serves as a robust cryptographic solution, safeguarding data confidentiality and integrity during exchanges between IoT devices and infrastructure. Through an in-depth examination of privacy threats and vulnerabilities inherent in such systems, the paper highlights ECC's potential to mitigate risks. Furthermore, it explores the implementation of ECC-based encryption and decryption mechanisms to ensure secure communication and data exchange. Additionally, the paper discusses the adoption of Transport Layer Security (TLS) as a secure data communication protocol and enhancing the overall security and efficiency of CPS-IoT transportation systems. To validate the effectiveness of our framework, we compare it with an assumed framework that utilizes Differential Privacy method and SSL, highlighting the advantages of our approach in terms of security, efficiency, and practicality. By fostering a secure data environment, ECC and TLS contribute to informed decision-making, resource optimization, and the advancement of sustainable transportation infrastructure, thus fostering a circular economy.
Chain-based routing protocols in wireless sensor networks: A survey Arpn Journal of Engineering and Applied Sciences, 2015
RECENT SCHOLAR PUBLICATIONS
Hybrid Ensemble Learning Framework Integrating a Time-Varying Decomposition Method and Optimization Technique for Accurate Disease Outbreak Prediction GS Hassan, HA Marhoon Applied Soft Computing, 115486 , 2026 2026
Secure IoMT smartwatch-based blood glucose monitoring using multimodal activity and nutrition data with transfer learning MA Mohammed, MKA Ghani, S Memon, A Lakhan, HA Marhoon, ... Scientific Reports , 2026 2026
A novel augmented reality and reinforcement learning empowered communication framework for underwater unmanned autonomous vehicle A Lakhan, MA Mohammed, MKA Ghani, S Memon, S Khan, HA Marhoon, ... Scientific Reports , 2026 2026
Towards intelligent air quality forecasting using integrated machine learning framework with variational mode decomposition and catboost feature selection I Ahmadianfar, ZM Yaseen, HA Marhoon, B Halder, ML Tan, HC Kilinc, ... Scientific Reports , 2026 2026 Citations: 1
ECT-DLM: Deep Learning-Based Empirical Curvelet Transform Approach SKD Alkhafaji, S Abdulla, HA Marhoon, M Diykh, MA Majed, J Sadiq, ... ICT for Intelligent Systems: Proceedings of ICTIS 2025, Volume 2 2, 37 , 2026 2026
Traffic congestion estimation and control: A comprehensive review of the applied computational intelligence models YH Taher, JS Mandeep, HA Marhoon, HA Al-Jamimi, H Luqman, ... Archives of Computational Methods in Engineering 33 (1), 339-400 , 2026 2026 Citations: 6
Privacy-preserving communication in smart city transportation using elliptic curve cryptography ZK Mohammed, MA Mohammed, MKA Ghani, SA Aliesawi, A Lakhan, ... Scientific Reports 15 (1), 34342 , 2025 2025 Citations: 3
Adaptive Federated Learning Empowered Wireless Localization Framework Using Vehicle Sensors MA Mohammed, MK Abd Ghani, S Memon, A Lakhan, HA Marhoon, ... Journal of Applied Science and Technology Trends 6 (2) , 2025 2025
A PEGASIS RP based-wireless sensor network-enabled smart contact lens for real time ocular monitoring HA Marhoon, A Alamiery, LM Shaker Results in Engineering 26, 105285 , 2025 2025 Citations: 5
ECT-DLM: Deep Learning-Based Empirical Curvelet Transform Approach for Thoracic Disease Diagnosis from X-RAY Images SKD Alkhafaji, S Abdulla, HA Marhoon, M Diykh, MA Majed, J Sadiq, ... International Conference on Information and Communication Technology for … , 2025 2025
An evolutionary optimized automated machine learning approach to soil unconfined compressive strength prediction for sustainable transportation infrastructure L Goliatt, HA Marhoon, ZM Yaseen, S Heddam, AW Al Zand, B Halder, ... Transportation Geotechnics 52, 101550 , 2025 2025 Citations: 5
Optimizing engineering design problems using adaptive differential learning teaching-learning-based optimization: Novel approach H Tao, MS Aldlemy, I Ahmadianfar, L Goliatt, HA Marhoon, RZ Homod, ... Expert Systems with Applications 270, 126425 , 2025 2025 Citations: 5
DCSSGA-UNet: Biomedical image segmentation with DenseNet channel spatial and semantic guidance attention T Hussain, H Shouno, MA Mohammed, HA Marhoon, T Alam Knowledge-Based Systems 314, 113233 , 2025 2025 Citations: 81
Blockchain-Integrated Edge-Cloud-Enabled Healthcare Data Analytics Based on Distributed Federated Learning and Deep Neural Networks MA Mohammed, MKA Ghani, IB Al-Mashhadani, S Memon, HA Marhoon, ... Mesopotamian Journal of CyberSecurity 5 (3), 1122-1140 , 2025 2025 Citations: 2
Designing Wireless Sensor Network Data Based Machine Learning Approach for Accurate Human Activity Recognition. HA Marhoon, AY Oudah, NA Hussien, A Raaid J. Internet Serv. Inf. Secur. 15 (1), 385-400 , 2025 2025 Citations: 14
LEACH-based approach using first-order model for energy efficient routing in WSNs for mobile diabetes patient monitoring HA Marhoon, S LM J Wireless Mobile Netw Ubiquitous Comput , 2025 2025 Citations: 2
ECT-DLM: Deep Learning Based Empirical Curvelet Transform Approach for Thoracic Disease Diagnosis from X-RAY Images S Abdulla, SK Alkhafaji, H Marhoon, M Diykh, MA Majed, J Sadiq, ... ICTIS 2025 , 2025 2025
A barrier-based machine learning approach for intrusion detection in wireless sensor networks H Marhoon, R Sagban, A Oudah, S Ahmed Computers, Materials, & Continua 82 (3), 4181 , 2025 2025 Citations: 2
A secure mist-fog-assisted cooperative offloading framework for sustainable smart city development SS Tripathy, S Bebortta, MA Mohammed, M Deveci, HA Marhoon, ... Digital Communications and Networks , 2024 2024 Citations: 7
PSO-CHS Routing Protocol for Energy Consumption Enhancement in Wireless Sensor Networks IS Fakhri, HA Marhoon, MH Hussein 2024 4th International Conference on Mobile Networks and Wireless … , 2024 2024
MOST CITED SCHOLAR PUBLICATIONS
Groundwater level prediction using machine learning models: A comprehensive review H Tao, MM Hameed, HA Marhoon, M Zounemat-Kermani, S Heddam, ... Neurocomputing 489, 271-308 , 2022 2022 Citations: 457
A comprehensive review on pulsed laser deposition technique to effective nanostructure production: Trends and challenges AJ Haider, T Alawsi, MJ Haider, BA Taha, HA Marhoon Optical and Quantum Electronics 54 (8), 488 , 2022 2022 Citations: 156
Securing healthcare data in industrial cyber-physical systems using combining deep learning and blockchain technology MA Mohammed, A Lakhan, DA Zebari, MK Abd Ghani, HA Marhoon, ... Engineering Applications of Artificial Intelligence 129, 107612 , 2024 2024 Citations: 94
Optimized video internet of things using elliptic curve cryptography based encryption and decryption BSA Alhayani, N Hamid, FH Almukhtar, OA Alkawak, HB Mahajan, ... Computers and Electrical Engineering 101, 108022 , 2022 2022 Citations: 82
DCSSGA-UNet: Biomedical image segmentation with DenseNet channel spatial and semantic guidance attention T Hussain, H Shouno, MA Mohammed, HA Marhoon, T Alam Knowledge-Based Systems 314, 113233 , 2025 2025 Citations: 81
Multiobjective optimization of a hybrid electricity generation system based on waste energy of internal combustion engine and solar system for sustainable environment SIS Al-Hawary, JRN Alvarez, A Ali, AK Tripathi, U Rahardja, ... Chemosphere 336, 139269 , 2023 2023 Citations: 81
Daily scale river flow forecasting using hybrid gradient boosting model with genetic algorithm optimization HC Kilinc, I Ahmadianfar, V Demir, S Heddam, AM Al-Areeq, SI Abba, ... Water resources management 37 (9), 3699-3714 , 2023 2023 Citations: 58
A deep learning fusion model for accurate classification of brain tumours in Magnetic Resonance images NA Zebari, CN Mohammed, DA Zebari, MA Mohammed, DQ Zeebaree, ... CAAI Transactions on Intelligence Technology 9 (4), 790-804 , 2024 2024 Citations: 55
Implementation of AdaBoost and genetic algorithm machine learning models in prediction of adsorption capacity of nanocomposite materials LI Weidong, MK Suhayb, L Thangavelu, HA Marhoon, I Pustokhina, ... Journal of Molecular Liquids 350, 118527 , 2022 2022 Citations: 55
Machine learning algorithms for high-resolution prediction of spatiotemporal distribution of air pollution from meteorological and soil parameters H Tao, AH Jawad, AH Shather, Z Al-Khafaji, TA Rashid, M Ali, N Al-Ansari, ... Environment international 175, 107931 , 2023 2023 Citations: 52
A metaverse framework for IoT-based remote patient monitoring and virtual consultations using AES-256 encryption ZK Mohammed, MA Mohammed, KH Abdulkareem, DA Zebari, A Lakhan, ... Applied Soft Computing 158, 111588 , 2024 2024 Citations: 50
Multiple machine learning models for prediction of CO2 solubility in potassium and sodium based amino acid salt solutions G Yin, FJI Alazzawi, D Bokov, HA Marhoon, AS El-Shafay, ML Rahman, ... Arabian Journal of Chemistry 15 (3), 103608 , 2022 2022 Citations: 45
Chain-based routing protocols in wireless sensor networks: A survey HA Marhoon, M Mahmuddin, S Awang Nor ARPN Journal of Engineering and Applied Sciences 10 (3), 1389-1398 , 2015 2015 Citations: 45
Edge-cloud remote sensing data-based plant disease detection using deep neural networks with transfer learning MA Mohammed, A Lakhan, KH Abdulkareem, NA Almujally, BBSMT Al, ... IEEE Journal of Selected Topics in Applied Earth Observations and Remote … , 2024 2024 Citations: 42
A multi-objectives framework for secure blockchain in fog–cloud network of vehicle-to-infrastructure applications A Lakhan, MA Mohammed, KH Abdulkareem, M Deveci, HA Marhoon, ... Knowledge-Based Systems 290, 111576 , 2024 2024 Citations: 39
Multi-objectives reinforcement federated learning blockchain enabled Internet of things and Fog-Cloud infrastructure for transport data MA Mohammed, A Lakhan, KH Abdulkareem, MK Abd Ghani, ... Heliyon 9 (11) , 2023 2023 Citations: 37
Coupled extreme gradient boosting algorithm with artificial intelligence models for predicting compressive strength of fiber reinforced polymer-confined concrete H Tao, ZH Ali, F Mukhtar, AW Al Zand, HA Marhoon, L Goliatt, ZM Yaseen Engineering Applications of Artificial Intelligence 134, 108674 , 2024 2024 Citations: 36
Towards resilient machine learning models: Addressing adversarial attacks in wireless sensor network MA Shihab, HA Marhoon, SR Ahmed, AD Radhi, R Sekhar Journal of Robotics and Control (JRC) 5 (5), 1599-1617 , 2024 2024 Citations: 32
Secure blockchain assisted Internet of Medical Things architecture for data fusion enabled cancer workflow A Lakhan, MA Mohammed, KH Abdulkareem, M khanapi Abd Ghani, ... Internet of Things 24, 100928 , 2023 2023 Citations: 30
Industrial Internet of Water Things architecture for data standarization based on blockchain and digital twin technology☆ MA Mohammed, A Lakhan, KH Abdulkareem, MK Abd Ghani, ... Journal of advanced research 66, 1-14 , 2024 2024 Citations: 28
