Manh-Hung Ha

Manh-Hung Ha

Auto-generated profile, based on publicly available information

Manh-Hung Ha

Vietnam National University, Hanoi

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 May 2023 in Electronics
Verified
Journal Article
Open access
PDF file
SDSon Tung Dang
Son Tung Dang
XDXuan Minh Dinh
Xuan Minh Dinh
TKThai Dinh Kim
Thai Dinh Kim
HLHai Xuan Le
Hai Xuan Le
MHManh-Hung Ha
Manh-Hung Ha
This paper proposes a new adaptive controller for three-wheeled mobile robots (3WMRs) called the ABHSMC controller. This ABHSMC controller is developed through a cooperative approach, combining a backstepping controller and a Radial Basis Function (RBF) neural network-based Hierarchical Sliding Mode Controller (HSMC). Notably, the RBF neural network exhibits the remarkable capability to estimate both the uncertainty components of the model and systematically adapt its parameters, leading to enhanced output trajectory responses. A novel navigational model, constructed by the connection to the adaptive BHSMC controller, Timed Elastic Band (TEB) Local Planner, and A-star (A*) Global Planner, is called ABHSMC navigation stack, and it is applied to effectively solve the tracking issue and obstacle avoidance for the 3-Wheeled Mobile Robot (3WMR). The simulation results implemented in the Matlab/Simulink platform demonstrate that the 3WMRs can precisely follow the desired trajectory, even in the presence of disturbances and changes in model parameters. Furthermore, the controller’s reliability is endorsed on our constructed self-driving car model. The achieved experimental results indicate that the proposed navigational structure can effectively control the actual vehicle model to track the desired trajectory with a small enough error and avoid a sudden obstacle simultaneously.

1 January 2021 in IEEE Access
Verified
Journal Article
Open access
MHManh-Hung Ha
Manh-Hung Ha
OCOscal Tzyh-Chiang Chen
Oscal Tzyh-Chiang Chen
This work develops Deep Neural Networks (DNNs) by adopting Capsule Networks (CapsNets) and spatiotemporal skeleton-based attention to effectively recognize subject actions from abundant spatial and temporal contexts of videos. The proposed generic DNN includes four 3D Convolutional Neural Networks (3D_CNNs), Attention-Jointed Appearance (AJA) and Attention-Jointed Motion (AJM) generation layers, two Reduction Layers (RLs), two Attention-based Recurrent Neural Networks (A_RNNs), and an inference classifier, where RGB, transformed skeleton, and optical-flow channel streams are inputs. The AJA and AJM generation layers emphasize skeletons to the appearances and motions of a subject, respectively. A_RNNs generate attention weights over time steps to highlight rich temporal contexts. To integrate CapsNets in this generic DNN, three types of CapsNet-based DNNs are devised, where the CapsNets take over a classifier, A_RNN+classifier, and RL+A_RNN+classifier. The experimental results reveal that the proposed DNN using CapsNet as an inference classifier outperforms the other two CapsNet-based DNNs and the generic DNN adopting the feedforward neural network as an inference classifier. Additionally, our best CapsNet-based DNN achieves average accuracies of 98.5% for the state-of-the-art performance in UCF101, 82.1% for near-state-of-the-art performance in HMDB51, and 95.3% for panoramic videos, to the best of our knowledge. Particularly, it is determined that the generic CapsNet behaves as an outstanding inference classifier but is slightly worse than the A_RNN in interpreting temporal evidence for recognition. Therefore, the proposed DNN, which employs CapsNet to fulfill an inference classifier, can be superiorly applied to various context-aware visual applications.

25 May 2024 in Journal of Computing Theories and Applications
Verified
Journal Article
Open access
PDF file
MHManh-Hung Ha
Manh-Hung Ha
To effectively comprehend human actions, we have developed a Deep Neural Network (DNN) that utilizes inner spatiotemporal non-locality to capture meaningful semantic context for efficient action identification. This work introduces the Top-Heavy CapsNet as a novel approach for video analysis, incorporating a 3D Convolutional Neural Network (3DCNN) to apply the thematic actions of local classifiers for effective classification based on motion from the spatiotemporal context in videos. This DNN comprises multiple layers, including 3D Convolutional Neural Network (3DCNN), Spatial Depth-Based Non-Local (SBN) layer, and Deep Capsule (DCapsNet). Firstly, the 3DCNN extracts structured and semantic information from RGB and optical flow streams. Secondly, the SBN layer processes feature blocks with spatial depth to emphasize visually advantageous cues, potentially aiding in action differentiation. Finally, DCapsNet is more effective in exploiting vectorized prominent features to represent objects and various action features for the ultimate label determination. Experimental results demonstrate that the proposed DNN achieves an average accuracy of 97.6%, surpassing conventional DNNs on the traffic police dataset. Furthermore, the proposed DNN attains average accuracies of 98.3% and 80.7% on the UCF101 and HMDB51 datasets, respectively. This underscores the applicability of the proposed DNN for effectively recognizing diverse actions performed by subjects in videos.

26 March 2025 in IEEE Access
Verified
Journal Article
Open access
OCOscal Tzyh-Chiang Chen
Oscal Tzyh-Chiang Chen
YCYu-Xuan Chang
Yu-Xuan Chang
CCChih-Yu Chung
Chih-Yu Chung
YCYa-Yun Cheng
Ya-Yun Cheng
MHManh-Hung Ha
Manh-Hung Ha
The growing demand for edge applications calls for efficient and optimized deep neural network models. Neural Architecture Search (NAS) is instrumental in designing such models, but achieving optimal architectures quickly remains a key challenge. To address this, we propose Hardware-aware Iterative One-shot NAS (HIO-NAS), a highly efficient approach that iteratively explores architectures across predefined search spaces for depth, filter, and width, all while respecting hardware constraints. HIO-NAS operates in four main steps: full training, random search, hardware verification, and retraining with adaptable knowledge distillation, repeated for each search space. The hardware-aware mechanism incorporates a lookup table to evaluate and filter subnetworks sampled during random search, ensuring only the most promising candidates proceed to hardware verification. The top-performing subnetwork(s) are then deployed on the target hardware for further validation. The adaptable knowledge distillation technique dynamically adjusts the teacher model’s influence based on deviations in the cost function during training. By progressively refining search spaces, HIO-NAS reduces computational overhead and avoids convergence issues. Its hypernetwork design emphasizes chain-like structures, where layers maintain connectivity. Applied to MobileNet v2 on CIFAR-100 and YOLOv7 on BDD100K, HIO-NAS delivered significant improvements: a 2.1% accuracy gain and 20.8% reduction in latency for MobileNet v2, and better performance over YOLOv7 and its variants. Interestingly, the findings highlight that unit-sharing topologies excel in depth searches, whereas unit-non-sharing topologies perform better in filter and width searches. Overall, HIO-NAS showcases a robust capability for efficiently discovering high-performance, hardware-optimized architectures, making it ideal for edge applications.

27 August 2025
Verified
Book Chapter
Closed access
PDF file
QNQuang-Anh Duc Nguyen
Quang-Anh Duc Nguyen
MHManh-Hung Ha
Manh-Hung Ha
TDThai Kim Dinh
Thai Kim Dinh
MPMinh-Duc Pham
Minh-Duc Pham
NNNinh Nguyen-Van
Ninh Nguyen-Van

1 May 2025 in Egyptian Informatics Journal
Verified
Journal Article
Open access
DNDuc-Chinh Nguyen
Duc-Chinh Nguyen
MHManh-Hung Ha
Manh-Hung Ha
MDManh-Tuan Do
Manh-Tuan Do
OCOscal Tzyh-Chiang Chen
Oscal Tzyh-Chiang Chen