Hongjie Ma
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Hongjie Ma has a total of 34 co-authors. Here are the top co-authors by number of shared publications:
- Edward Smart
School of Electrical and Mechanical Engineering, University of Portsmouth, Portsmouth PO1 3DJ, UK
4 shared publications - Branislav Vuksanovic
School of Energy and Electronic Engineering, Faculty of Technology, University of Portsmouth, Portsmouth, UK
2 shared publications - David Brown
Medical Affairs, AstraZeneca Australia, Macquarie Park, NSW, Australia
2 shared publications - Hui Yu
University of Glasgow
2 shared publications - Yongqiang Lu
School of Electrical and Mechanical Engineering, University of Portsmouth, Portsmouth, U.K.
2 shared publications Adeel Ahmed
Department of Institute of Industrial Research, University of Portsmouth, Portsmouth, U.K.
1 shared publication
Latest Publications
- Open Access
- 24 August 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (17) , 9302
Energy Management Strategy for Hybrid Electric Vehicles Based on Experience-Pool-Optimized Deep Reinforcement Learning
The energy management strategy of Hybrid Electric Vehicles (HEVs) plays a key role in improving fuel economy and reducing battery energy consumption. This paper proposes a Deep Reinforcement Learning-based energy management strategy optimized by the experience pool (P-HER-DDPG), aimed at improving the fuel efficiency of HEVs while accelerating the training speed. The method integrates the mechanisms of Prioritized Experience Replay (PER) and Hindsight Experience Replay (HER) to address the reward sparsity and slow convergence issues faced by the traditional Deep Deterministic Policy Gradient (DDPG) algorithm when handling continuous action spaces. Under various standard driving cycles, the P-HER-DDPG strategy outperforms the traditional DDPG strategy, achieving an average fuel economy improvement of 5.85%, with a maximum increase of 8.69%. Compared to the DQN strategy, it achieves an average improvement of 12.84%. In terms of training convergence, the P-HER-DDPG strategy converges in 140 episodes, 17.65% faster than DDPG and 24.32% faster than DQN. Additionally, the strategy demonstrates more stable State of Charge (SOC) control, effectively mitigating the risks of battery overcharging and deep discharging. Simulation results show that P-HER-DDPG can enhance fuel economy and training efficiency, offering an extended solution in the field of energy management strategies.
- 24 August 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (17) , 9302
Open AccessEnergy Management Strategy for Hybrid Electric Vehicles Based on Experience-Pool-Optimized Deep Reinforcement Learning
The energy management strategy of Hybrid Electric Vehicles (HEVs) plays a key role in improving fuel economy and reducing battery energy consumption. This paper proposes a Deep Reinforcement Learning-based energy management strategy optimized by the experience pool (P-HER-DDPG), aimed at improving the fuel efficiency of HEVs while accelerating the training speed. The method integrates the mechanisms of Prioritized Experience Replay (PER) and Hindsight Experience Replay (HER) to address the reward sparsity and slow convergence issues faced by the traditional Deep Deterministic Policy Gradient (DDPG) algorithm when handling continuous action spaces. Under various standard driving cycles, the P-HER-DDPG strategy outperforms the traditional DDPG strategy, achieving an average fuel economy improvement of 5.85%, with a maximum increase of 8.69%. Compared to the DQN strategy, it achieves an average improvement of 12.84%. In terms of training convergence, the P-HER-DDPG strategy converges in 140 episodes, 17.65% faster than DDPG and 24.32% faster than DQN. Additionally, the strategy demonstrates more stable State of Charge (SOC) control, effectively mitigating the risks of battery overcharging and deep discharging. Simulation results show that P-HER-DDPG can enhance fuel economy and training efficiency, offering an extended solution in the field of energy management strategies.
- Top Cited PapersOpen Access
A Review of Recent Advances in Unidirectional Ultrasonic Guided Wave Techniques for Nondestructive Testing and Evaluation
Unidirectional ultrasonic guided waves (UGWs) play a crucial role in the nondestructive testing and evaluation (NDT&E) domains, offering unique advantages in detecting material defects, evaluating structural integrity, and improving the accuracy of thickness measurements. This review paper thoroughly studies the state of the art of unidirectional UGWs before presenting a comprehensive review of the foundational mathematical principles of unidirectional UGWs, focusing on the recent advancements in their methodologies and applications. This review introduces ultrasonic guided waves and their modes before looking at mode excitability and selectivity, signal excitation, and mechanisms used to generate and receive guided waves unidirectionally. This paper outlines the applications of unidirectional UGWs to reflect their effectiveness, for instance, in measuring thickness and in identifying defects such as cracks and corrosion in pipelines, etc. The paper also studies the challenges associated with unidirectional UGW generation and utilisation, such as multi-mode and side lobes. It includes a review of the literature to mitigate these challenges. Finally, this paper highlights promising future perspectives and develops directions for the technique. This review aims to create a useful resource for researchers and practitioners to comprehend unidirectional ultrasonic guided waves’ capabilities, challenges, and prospects in NDT&E applications.
Top Cited PapersOpen AccessA Review of Recent Advances in Unidirectional Ultrasonic Guided Wave Techniques for Nondestructive Testing and Evaluation
Unidirectional ultrasonic guided waves (UGWs) play a crucial role in the nondestructive testing and evaluation (NDT&E) domains, offering unique advantages in detecting material defects, evaluating structural integrity, and improving the accuracy of thickness measurements. This review paper thoroughly studies the state of the art of unidirectional UGWs before presenting a comprehensive review of the foundational mathematical principles of unidirectional UGWs, focusing on the recent advancements in their methodologies and applications. This review introduces ultrasonic guided waves and their modes before looking at mode excitability and selectivity, signal excitation, and mechanisms used to generate and receive guided waves unidirectionally. This paper outlines the applications of unidirectional UGWs to reflect their effectiveness, for instance, in measuring thickness and in identifying defects such as cracks and corrosion in pipelines, etc. The paper also studies the challenges associated with unidirectional UGW generation and utilisation, such as multi-mode and side lobes. It includes a review of the literature to mitigate these challenges. Finally, this paper highlights promising future perspectives and develops directions for the technique. This review aims to create a useful resource for researchers and practitioners to comprehend unidirectional ultrasonic guided waves’ capabilities, challenges, and prospects in NDT&E applications.
- 1 February 2025
- Published by Bentham Science Publishers Ltd. in Recent Patents on Anti-Cancer Drug Discovery
- Vol. 20 (2) , 145-157
Curcumin Inhibits the Growth of Hepatocellular Carcinoma via the MARCH1-mediated Modulation of JAK2/STAT3 Signaling
Background: Curcumin has been reported to have anti-hepatocellular carcinoma (HCC) effects, but the underlying mechanism is not well known. Objectives: To investigate whether membrane-associated RING-CH 1 (MARCH1) is involved in the curcumin-induced growth suppression in HCC and its underlying molecular mechanism. A few recent patents for curcumin for cancer are also reviewed in this article. Methods: The effect of curcumin on growth inhibition of HCC cells was analyzed through in vitro and in vivo experiments, and the expression levels of MARCH1, Bcl-2, VEGF, cyclin B1, cyclin D1, and JAK2/STAT3 signaling molecules were measured in HCC cells and the xenograft tumors in nude mice. Cell transfection with MARCH1 siRNAs or expression plasmid was used to explore the role of MARCH1 in the curcumin-induced growth inhibition of HCC cells. Results: Curcumin inhibited cell proliferation, promoted apoptosis, and arrested the cell cycle at the G2/M phase in HCC cells with the decrease of Bcl-2, VEGF, cyclin B1, and cyclin D1 expression as well as JAK2 and STAT3 phosphorylation, resulting in the growth suppression of HCC cells. MARCH1 is highly expressed in HCC cells, and its expression was downregulated after curcumin treatment in a dose-dependent manner. The knockdown of MARCH1 by siRNA decreased the phosphorylation levels of JAK2 and STAT3 and inhibited the growth of HCC cells. In contrast, opposite results were observed when HCC cells overexpressed MARCH1. A xenograft tumor model in nude mice also showed that curcumin downregulated MARCH1 expression and decelerated the growth of transplanted HCC with the downregulation of JAK2/STAT3 signaling and functional molecules. The ADC value of MRI analysis showed that curcumin slowed down the progression of HCC. Conclusion: Our results demonstrated that curcumin may inhibit the activation of JAK2/STAT3 signaling pathway by downregulating MARCH1 expression, resulting in the growth suppression of HCC. MARCH1 may be a novel target of curcumin in HCC treatment.
- 1 February 2025
- Published by Bentham Science Publishers Ltd. in Recent Patents on Anti-Cancer Drug Discovery
- Vol. 20 (2) , 145-157
Curcumin Inhibits the Growth of Hepatocellular Carcinoma via the MARCH1-mediated Modulation of JAK2/STAT3 Signaling
Background: Curcumin has been reported to have anti-hepatocellular carcinoma (HCC) effects, but the underlying mechanism is not well known. Objectives: To investigate whether membrane-associated RING-CH 1 (MARCH1) is involved in the curcumin-induced growth suppression in HCC and its underlying molecular mechanism. A few recent patents for curcumin for cancer are also reviewed in this article. Methods: The effect of curcumin on growth inhibition of HCC cells was analyzed through in vitro and in vivo experiments, and the expression levels of MARCH1, Bcl-2, VEGF, cyclin B1, cyclin D1, and JAK2/STAT3 signaling molecules were measured in HCC cells and the xenograft tumors in nude mice. Cell transfection with MARCH1 siRNAs or expression plasmid was used to explore the role of MARCH1 in the curcumin-induced growth inhibition of HCC cells. Results: Curcumin inhibited cell proliferation, promoted apoptosis, and arrested the cell cycle at the G2/M phase in HCC cells with the decrease of Bcl-2, VEGF, cyclin B1, and cyclin D1 expression as well as JAK2 and STAT3 phosphorylation, resulting in the growth suppression of HCC cells. MARCH1 is highly expressed in HCC cells, and its expression was downregulated after curcumin treatment in a dose-dependent manner. The knockdown of MARCH1 by siRNA decreased the phosphorylation levels of JAK2 and STAT3 and inhibited the growth of HCC cells. In contrast, opposite results were observed when HCC cells overexpressed MARCH1. A xenograft tumor model in nude mice also showed that curcumin downregulated MARCH1 expression and decelerated the growth of transplanted HCC with the downregulation of JAK2/STAT3 signaling and functional molecules. The ADC value of MRI analysis showed that curcumin slowed down the progression of HCC. Conclusion: Our results demonstrated that curcumin may inhibit the activation of JAK2/STAT3 signaling pathway by downregulating MARCH1 expression, resulting in the growth suppression of HCC. MARCH1 may be a novel target of curcumin in HCC treatment.
- 27 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 26 (3) , 3198-3209
Enhancing Autonomous Driving Decision: A Hybrid Deep Reinforcement Learning-Kinematic-Based Autopilot Framework for Complex Motorway Scenes
Autonomous vehicles (AVs) still pose challenges in improving intelligence, safety, and reliability in complex motorway scenarios. Recently, deep reinforcement learning (DRL) has demonstrated superior decision-making capabilities in dynamic environments compared to rule-based methods. However, it requires considerable training resources due to a lack of innovative DRL component design (e.g., state space and reward) to link observation and action accurately. Its opaque nature may also result in hazardous driving conditions. In this paper, we introduce a hybrid autopilot framework that amalgamates three modules: (i) DRL is employed to build a smart, learnable, and scalable driving policy across various motorway scenarios; (ii) a kinematic-based co-pilot strategy is devised to bolster training efficiency and provide flexible decision-making guidance; and (iii) a rule-based system assesses and determines the final action outputs in real-time between itself and the DRL policy to further enhance safety. Extensive simulations are conducted under different complex motorway scenarios. The results indicate that the proposed framework surpasses the baseline DRL policy in terms of training efficiency, intelligence, safety, and reliability.
- 27 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 26 (3) , 3198-3209
Enhancing Autonomous Driving Decision: A Hybrid Deep Reinforcement Learning-Kinematic-Based Autopilot Framework for Complex Motorway Scenes
Autonomous vehicles (AVs) still pose challenges in improving intelligence, safety, and reliability in complex motorway scenarios. Recently, deep reinforcement learning (DRL) has demonstrated superior decision-making capabilities in dynamic environments compared to rule-based methods. However, it requires considerable training resources due to a lack of innovative DRL component design (e.g., state space and reward) to link observation and action accurately. Its opaque nature may also result in hazardous driving conditions. In this paper, we introduce a hybrid autopilot framework that amalgamates three modules: (i) DRL is employed to build a smart, learnable, and scalable driving policy across various motorway scenarios; (ii) a kinematic-based co-pilot strategy is devised to bolster training efficiency and provide flexible decision-making guidance; and (iii) a rule-based system assesses and determines the final action outputs in real-time between itself and the DRL policy to further enhance safety. Extensive simulations are conducted under different complex motorway scenarios. The results indicate that the proposed framework surpasses the baseline DRL policy in terms of training efficiency, intelligence, safety, and reliability.
- 22 April 2024
- Published by Springer Nature in Acoustics Australia
- Vol. 52 (2) , 209-224
Assessing the Acoustic Noise in Intensive Care Units via Deep Learning Technique
- 22 April 2024
- Published by Springer Nature in Acoustics Australia
- Vol. 52 (2) , 209-224
Assessing the Acoustic Noise in Intensive Care Units via Deep Learning Technique
- Open Access
- 1 June 2023
- Published by EJournal Publishing in Journal of Image and Graphics
The Performance Analysis of Facial Expression Recognition System Using Local Regions and Features
Different parts of our face contribute to overall facial expressions, such as anger, happiness and sadness in distinct ways. This paper investigates the degree of importance of different human face parts to the accuracy of Facial Expression Recognition (FER). In the context of machine learning, FER refers to a problem where a computer vision system is trained to automatically detect the facial expression from a presented facial image. This is a difficult image classification problem that is not yet fully solved and has received significant attention in recent years, mainly due to the increased number of possible applications in daily life. To establish the extent to which different human face parts contribute to overall facial expression, various sections have been extracted from a set of facial images and then used as inputs into three different FER systems. In terms of the recognition rates for each facial section, this result confirms that various regions of the face have different levels of importance regarding the accuracy rate achieved by an associated FER system.
- 1 June 2023
- Published by EJournal Publishing in Journal of Image and Graphics
Open AccessThe Performance Analysis of Facial Expression Recognition System Using Local Regions and Features
Different parts of our face contribute to overall facial expressions, such as anger, happiness and sadness in distinct ways. This paper investigates the degree of importance of different human face parts to the accuracy of Facial Expression Recognition (FER). In the context of machine learning, FER refers to a problem where a computer vision system is trained to automatically detect the facial expression from a presented facial image. This is a difficult image classification problem that is not yet fully solved and has received significant attention in recent years, mainly due to the increased number of possible applications in daily life. To establish the extent to which different human face parts contribute to overall facial expression, various sections have been extracted from a set of facial images and then used as inputs into three different FER systems. In terms of the recognition rates for each facial section, this result confirms that various regions of the face have different levels of importance regarding the accuracy rate achieved by an associated FER system.
- Top Cited Papers
- 18 May 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 23 (7) , 6082-6100
Real-Time Performance-Focused Localization Techniques for Autonomous Vehicle: A Review
Real-time, accurate, and robust localisation is critical for autonomous vehicles (AVs) to achieve safe, efficient driving, whilst real-time performance is essential for AVs to achieve their current position in time for decision making. To date, no review paper has quantitatively compared the real-time performance between different localisation techniques based on various hardware platforms and programming languages and analysed the relations among localisation methodologies, real-time performance and accuracy. Therefore, this paper discusses the state-of-the-art localisation techniques and analyses their overall performance in AV application. For further analysis, this paper firstly proposes a localisation algorithm operations capability (LAOC)-based equivalent comparison method to compare the relative computational complexity of different localisation techniques; then, it comprehensively discusses the relations among methodologies, computational complexity, and accuracy. Analysis results show that the computational complexity of localisation approaches differs by a maximum of about 10⁷ times, whilst accuracy varies by about 100 times. Vision- and data fusion-based localisation techniques have about 2-5 times potential for improving accuracy compared with lidar-based localisation. Lidar- and vision-based localisation can reduce computational complexity by improving image registration method efficiency. Data fusion-based localisation can achieve better real-time performance compared with lidar- and vision-based localisation because each standalone sensor does not need to develop a complex algorithm to achieve its best localisation potential. Vehicle-to-everything (V2X) technology can improve positioning robustness. Finally, the potential solutions and future orientations of AVs' localisation based on the quantitative comparison results are discussed.
- 18 May 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 23 (7) , 6082-6100
Top Cited PapersReal-Time Performance-Focused Localization Techniques for Autonomous Vehicle: A Review
Real-time, accurate, and robust localisation is critical for autonomous vehicles (AVs) to achieve safe, efficient driving, whilst real-time performance is essential for AVs to achieve their current position in time for decision making. To date, no review paper has quantitatively compared the real-time performance between different localisation techniques based on various hardware platforms and programming languages and analysed the relations among localisation methodologies, real-time performance and accuracy. Therefore, this paper discusses the state-of-the-art localisation techniques and analyses their overall performance in AV application. For further analysis, this paper firstly proposes a localisation algorithm operations capability (LAOC)-based equivalent comparison method to compare the relative computational complexity of different localisation techniques; then, it comprehensively discusses the relations among methodologies, computational complexity, and accuracy. Analysis results show that the computational complexity of localisation approaches differs by a maximum of about 10⁷ times, whilst accuracy varies by about 100 times. Vision- and data fusion-based localisation techniques have about 2-5 times potential for improving accuracy compared with lidar-based localisation. Lidar- and vision-based localisation can reduce computational complexity by improving image registration method efficiency. Data fusion-based localisation can achieve better real-time performance compared with lidar- and vision-based localisation because each standalone sensor does not need to develop a complex algorithm to achieve its best localisation potential. Vehicle-to-everything (V2X) technology can improve positioning robustness. Finally, the potential solutions and future orientations of AVs' localisation based on the quantitative comparison results are discussed.
- Open Access
- 26 March 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 50846-50856
STI-GAN: Multimodal Pedestrian Trajectory Prediction Using Spatiotemporal Interactions and a Generative Adversarial Network
Predicting the future trajectories of multiple pedestrians in certain scenes has become a key task for ensuring that autonomous vehicles, socially interactive robots and other autonomous mobile platforms can navigate safely. The social interactions between people and the multimodal nature of pedestrian movement make pedestrian trajectory prediction a challenging task. In this paper, the problem is solved using a generative adversarial network (GAN) and a graph attention network (GAT) based on the spatiotemporal interaction information about pedestrians. Our method, STI-GAN, is based on an end-to-end GAN model that simulates the pedestrian distribution to capture the uncertainty of the predicted paths and generate more reasonable future trajectories. The complex interactions between people are modeled by a GAT, and spatiotemporal interaction information is used to improve the performance of trajectory prediction. We verify the robustness and improvement of our framework by evaluating its results on various datasets and comparing them with the results of several existing baselines. Compared with the existing pedestrian trajectory prediction methods, our method reduces the average displacement error (ADE) and final displacement error (FDE) by 21.9% and 23.8% respectively.
- 26 March 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 50846-50856
Open AccessSTI-GAN: Multimodal Pedestrian Trajectory Prediction Using Spatiotemporal Interactions and a Generative Adversarial Network
Predicting the future trajectories of multiple pedestrians in certain scenes has become a key task for ensuring that autonomous vehicles, socially interactive robots and other autonomous mobile platforms can navigate safely. The social interactions between people and the multimodal nature of pedestrian movement make pedestrian trajectory prediction a challenging task. In this paper, the problem is solved using a generative adversarial network (GAN) and a graph attention network (GAT) based on the spatiotemporal interaction information about pedestrians. Our method, STI-GAN, is based on an end-to-end GAN model that simulates the pedestrian distribution to capture the uncertainty of the predicted paths and generate more reasonable future trajectories. The complex interactions between people are modeled by a GAT, and spatiotemporal interaction information is used to improve the performance of trajectory prediction. We verify the robustness and improvement of our framework by evaluating its results on various datasets and comparing them with the results of several existing baselines. Compared with the existing pedestrian trajectory prediction methods, our method reduces the average displacement error (ADE) and final displacement error (FDE) by 21.9% and 23.8% respectively.
- Open Access
- 14 December 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 19 (2) , 572-581
Eco-Driving Assistance System for a Manual Transmission Bus Based on Machine Learning
Driving assistance systems (DAS) is a key technology to improve fuel economy for in-use vehicles. This also reduces the operational cost of running a fleet of these vehicles, such as city buses. In this paper, we develop a novel white-box evaluation model using machine learning for a manual transmission bus based on previous research about fuel consumption sensitivity to driving style. Using the proposed evaluation model, an algorithm for learning path planning (LPP) for a driving style is also proposed. The LPP method plans a step-by-step shortest learning path for different driving styles to achieve eco-driving, while increasing the driver's acceptance and adaptation of DAS. Simulation results based on vehicle and engine physical models show that the proposed evaluation model, a pure data model, can be used as an alternative to physical model for the eco-driving prompt strategy. The results of the verification show that the proposed strategy can progressively guide the driver to improve the fuel consumption by 6.25% with minimal changes to driver's driving task and driving style.
- 14 December 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 19 (2) , 572-581
Open AccessEco-Driving Assistance System for a Manual Transmission Bus Based on Machine Learning
Driving assistance systems (DAS) is a key technology to improve fuel economy for in-use vehicles. This also reduces the operational cost of running a fleet of these vehicles, such as city buses. In this paper, we develop a novel white-box evaluation model using machine learning for a manual transmission bus based on previous research about fuel consumption sensitivity to driving style. Using the proposed evaluation model, an algorithm for learning path planning (LPP) for a driving style is also proposed. The LPP method plans a step-by-step shortest learning path for different driving styles to achieve eco-driving, while increasing the driver's acceptance and adaptation of DAS. Simulation results based on vehicle and engine physical models show that the proposed evaluation model, a pure data model, can be used as an alternative to physical model for the eco-driving prompt strategy. The results of the verification show that the proposed strategy can progressively guide the driver to improve the fuel consumption by 6.25% with minimal changes to driver's driving task and driving style.
- Open Access
- 1 November 2017
- Published by Elsevier in Applied Energy
- Vol. 205, 720-731
Typical solar radiation year construction using k-means clustering and discrete-time Markov chain
- 1 November 2017
- Published by Elsevier in Applied Energy
- Vol. 205, 720-731
Open AccessTypical solar radiation year construction using k-means clustering and discrete-time Markov chain