Haodong Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Haodong Liu has a total of 32 co-authors. Here are the top co-authors by number of shared publications:
- Changhong Wang
School of Biomedical Engineering, Shenzhen Campus of Sun Yat-sen University, Shenzhen, Guangdong, China
3 shared publications - Guanzheng Liu
School of Biomedical Engineering, Shenzhen Campus of Sun Yat-sen University, Shenzhen, China
1 shared publication - Hanjie Ying
College of Biotechnology and Pharmaceutical Engineering, Nanjing Tech University, Nanjing 210009, China
1 shared publication - Hongyuan Zhu
Institute for Infocomm Research, A*STAR, Singapore, Singapore
1 shared publication - Hua Liu
School of Mathematics and Computer Science, Northwest Minzu University, Lanzhou, Gansu 730000, P. R. China
1 shared publication - Huayu Li
School of Physics and Electronics, Nanning Normal University, Nanning 530100, China
1 shared publication
Latest Publications
- 16 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Social Systems
- Vol. PP, 1-15
Heterogeneous Multimodal Multilabel Behavioral Context Recognition Using Wearable Sensors and Mobile Devices
Accurate behavioral context recognition (BCR) is essential for advancing social intelligence in smart home settings and social companion pairing. With advancements in mobile computing technologies, wearable sensors, and mobile devices have become crucial for multimodal data collection to interpret behavioral context. However, existing methods may overlook the multilabel attribute of behavioral context, limiting their ability to model modality-to-label and label-to-label dependencies. Moreover, the unique label heterogeneity in BCR, arising from category-specific differences among labels, is often underestimated. To overcome these challenges, we propose a heterogeneous multimodal multilabel recognition method to capture the relationships between modalities and labels, while taking the label heterogeneity into account. Using specialized heterogeneous decoders with self-adaptive attention and a heterogeneous graph attention network based on the dual-level attention mechanism, our method captures complex dependencies among labels and modalities. Experiments on two benchmark datasets demonstrate the superior performance of our approach, with ablation studies validating the contributions of each component.
- 16 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Social Systems
- Vol. PP, 1-15
Heterogeneous Multimodal Multilabel Behavioral Context Recognition Using Wearable Sensors and Mobile Devices
Accurate behavioral context recognition (BCR) is essential for advancing social intelligence in smart home settings and social companion pairing. With advancements in mobile computing technologies, wearable sensors, and mobile devices have become crucial for multimodal data collection to interpret behavioral context. However, existing methods may overlook the multilabel attribute of behavioral context, limiting their ability to model modality-to-label and label-to-label dependencies. Moreover, the unique label heterogeneity in BCR, arising from category-specific differences among labels, is often underestimated. To overcome these challenges, we propose a heterogeneous multimodal multilabel recognition method to capture the relationships between modalities and labels, while taking the label heterogeneity into account. Using specialized heterogeneous decoders with self-adaptive attention and a heterogeneous graph attention network based on the dual-level attention mechanism, our method captures complex dependencies among labels and modalities. Experiments on two benchmark datasets demonstrate the superior performance of our approach, with ablation studies validating the contributions of each component.
- 19 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Robotics and Bionics
- Vol. 6 (4) , 1478-1489
Automatic Centroid Angle Measurement From CT Image for Preoperative Rod Design of Robotic-Assisted Screw-Rod System Implantation
Robotic-assisted implantation of screw-rod systems serves as an advanced therapy for spinal diseases. A precise curvature fit between rods and spines is critical to postoperative spinal stability. Currently, rod curvature is determined intraoperatively to accommodate screw positions, which is hardly conducive to optimal rod bending and is vulnerable to surgeons’ expertise. To address this challenge, we propose an automated and efficient method for measuring the centroid angle to guide preoperative rod design from CT images. The centroid angle is defined by lines connecting centroids of the upper and lower vertebrae pairs, providing a reliable measurement for spinal deformities. The proposed pipeline includes (1) 3D spine segmentation with multiscale multitask deep learning; (2) vertebrae recognition using graphical morphology; (3) automatic and reproducible centroid angle measurement. Our method is evaluated on both healthy and pathological spines. Compared to manual measurements by professional surgeons, our method achieves an accuracy of 94.50% and 91.93% on adjacent and non-adjacent vertebrae, respectively. A Slicer-based plugin for robotic-assisted screw-rod systems implantation is built, providing a new clinical tool to personalize screw-rod systems consistent with the natural spinal curvature, thereby enhancing biomechanical properties.
- 19 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Robotics and Bionics
- Vol. 6 (4) , 1478-1489
Automatic Centroid Angle Measurement From CT Image for Preoperative Rod Design of Robotic-Assisted Screw-Rod System Implantation
Robotic-assisted implantation of screw-rod systems serves as an advanced therapy for spinal diseases. A precise curvature fit between rods and spines is critical to postoperative spinal stability. Currently, rod curvature is determined intraoperatively to accommodate screw positions, which is hardly conducive to optimal rod bending and is vulnerable to surgeons’ expertise. To address this challenge, we propose an automated and efficient method for measuring the centroid angle to guide preoperative rod design from CT images. The centroid angle is defined by lines connecting centroids of the upper and lower vertebrae pairs, providing a reliable measurement for spinal deformities. The proposed pipeline includes (1) 3D spine segmentation with multiscale multitask deep learning; (2) vertebrae recognition using graphical morphology; (3) automatic and reproducible centroid angle measurement. Our method is evaluated on both healthy and pathological spines. Compared to manual measurements by professional surgeons, our method achieves an accuracy of 94.50% and 91.93% on adjacent and non-adjacent vertebrae, respectively. A Slicer-based plugin for robotic-assisted screw-rod systems implantation is built, providing a new clinical tool to personalize screw-rod systems consistent with the natural spinal curvature, thereby enhancing biomechanical properties.
- 10 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 11 (16) , 27139-27152
A Multiscale Cross-Modal Interactive Fusion Network for Human Activity Recognition Using Wearable Sensors and Smartphones
Human activity recognition (HAR) enables real-time monitoring of human movement, posture, and activity level, and can provide valuable information for the health management. With the continuous advancement of Internet of Things (IoT) technology, wearable sensors and smartphones equipped with various types of sensors have become widely utilized to collect multimodal data for HAR. However, in multimodal HAR, current fusion methods fall short in capturing intermodality correlations, hampering the full exploitation of complementary information between the modalities and leading to lower recognition accuracy. We thus propose a novel multiscale cross-modal interactive fusion network (MCIFN), which can fully capture correlations between various modalities and obtain an effective fused representation for HAR. Specifically, we employ a multiscale parallel convolution module to extract features from each modality at multiple scales. Then, an interactive fusion strategy based on the cross-modal attention mechanism is introduced to adjust and enhance each modality based on its correlations with other modalities. Additionally, to resolve the information redundancy caused by the interactive fusion strategy, we utilize a hybrid attention module to focus on important information in the fusion representation. Extensive experiments conducted on three publicly available data sets and one private data set demonstrate that our proposed network outperforms the previous baseline networks for HAR. Additionally, our proposed fusion strategy yielded a notable improvement in accuracy ranging from 1.87% to 9.96% compared to existing strategies. These findings imply that our newly proposed network can realize comprehensive multimodal fusion and effectively enhance HAR accuracy, potentially contributing to advancements in individual health management and personalized healthcare interventions.
- 10 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 11 (16) , 27139-27152
A Multiscale Cross-Modal Interactive Fusion Network for Human Activity Recognition Using Wearable Sensors and Smartphones
Human activity recognition (HAR) enables real-time monitoring of human movement, posture, and activity level, and can provide valuable information for the health management. With the continuous advancement of Internet of Things (IoT) technology, wearable sensors and smartphones equipped with various types of sensors have become widely utilized to collect multimodal data for HAR. However, in multimodal HAR, current fusion methods fall short in capturing intermodality correlations, hampering the full exploitation of complementary information between the modalities and leading to lower recognition accuracy. We thus propose a novel multiscale cross-modal interactive fusion network (MCIFN), which can fully capture correlations between various modalities and obtain an effective fused representation for HAR. Specifically, we employ a multiscale parallel convolution module to extract features from each modality at multiple scales. Then, an interactive fusion strategy based on the cross-modal attention mechanism is introduced to adjust and enhance each modality based on its correlations with other modalities. Additionally, to resolve the information redundancy caused by the interactive fusion strategy, we utilize a hybrid attention module to focus on important information in the fusion representation. Extensive experiments conducted on three publicly available data sets and one private data set demonstrate that our proposed network outperforms the previous baseline networks for HAR. Additionally, our proposed fusion strategy yielded a notable improvement in accuracy ranging from 1.87% to 9.96% compared to existing strategies. These findings imply that our newly proposed network can realize comprehensive multimodal fusion and effectively enhance HAR accuracy, potentially contributing to advancements in individual health management and personalized healthcare interventions.
- Open Access
- 1 December 2020
- Published by Elsevier in Global Ecology and Conservation
- Vol. 24, e01370
Effects of biotic/abiotic factors on the seedling regeneration of Dacrydium pectinatum formations in tropical montane forests on Hainan Island, China
- 1 December 2020
- Published by Elsevier in Global Ecology and Conservation
- Vol. 24, e01370
Open AccessEffects of biotic/abiotic factors on the seedling regeneration of Dacrydium pectinatum formations in tropical montane forests on Hainan Island, China
- 1 July 2020
- Published by International Union of Crystallography (IUCr) in Acta crystallographica Section B, Structural science, crystal engineering and materials
- Vol. 76 (4) , 524-533
Crystal forms and phase transformation of 1,5-pentanediamine-terephthalate: a bio-based nylon 5T monomer
Nylon 5T is one of the bio-based nylons, its raw material 1,5-pentanediamine is derived from biomass resources and produced by biological methods. 1,5-pentanediamine-terephthalate (PDA-TPA) is the monomeric salt for nylon 5T polymerization, and its own product quality has a significant impact on the performance of nylon 5T. PDA-TPA was prepared by anti-solvent crystallization in this study. It exists in two solid forms, a monohydrate [form (I)] and an anhydrous phase [form (II)]. The transition temperature of the two phases was around 65°C in the given ethanol–water binary (7:1) mixture. The characterization of monohydrate and anhydrate phases regarding structures and stabilities was carefully carried out using powder X-ray diffraction, single crystal X-ray diffraction, differential scanning calorimetry, thermogravimetric analysis, hot-stage microscopy and Fourier transform infrared spectroscopy. The relationship between the molecular interactions of monohydrate and anhydrate phases under different packing architectures and their thermal behaviours was analysed and established. In addition, the relationships between the structures and thermal behaviours for the two solid forms were analysed and established. In addition, the effect of solvent on phase conversion, the relationships between the temperature and water activity, as well as the relative stability of monohydrate and anhydrate phases under different thermodynamic conditions, were investigated by solid–solid transformation and solvent-mediated transformation experiments. It was obvious that the transition temperature of monohydrate and anhydrate phases of PDA-TPA was significantly influenced by water activity, and the larger the value of water activity is, the higher is the transition temperature. These studies give insight into the transformation of nylon 5T monomer salt and contribute to the control of target crystal preparation.
- 1 July 2020
- Published by International Union of Crystallography (IUCr) in Acta crystallographica Section B, Structural science, crystal engineering and materials
- Vol. 76 (4) , 524-533
Crystal forms and phase transformation of 1,5-pentanediamine-terephthalate: a bio-based nylon 5T monomer
Nylon 5T is one of the bio-based nylons, its raw material 1,5-pentanediamine is derived from biomass resources and produced by biological methods. 1,5-pentanediamine-terephthalate (PDA-TPA) is the monomeric salt for nylon 5T polymerization, and its own product quality has a significant impact on the performance of nylon 5T. PDA-TPA was prepared by anti-solvent crystallization in this study. It exists in two solid forms, a monohydrate [form (I)] and an anhydrous phase [form (II)]. The transition temperature of the two phases was around 65°C in the given ethanol–water binary (7:1) mixture. The characterization of monohydrate and anhydrate phases regarding structures and stabilities was carefully carried out using powder X-ray diffraction, single crystal X-ray diffraction, differential scanning calorimetry, thermogravimetric analysis, hot-stage microscopy and Fourier transform infrared spectroscopy. The relationship between the molecular interactions of monohydrate and anhydrate phases under different packing architectures and their thermal behaviours was analysed and established. In addition, the relationships between the structures and thermal behaviours for the two solid forms were analysed and established. In addition, the effect of solvent on phase conversion, the relationships between the temperature and water activity, as well as the relative stability of monohydrate and anhydrate phases under different thermodynamic conditions, were investigated by solid–solid transformation and solvent-mediated transformation experiments. It was obvious that the transition temperature of monohydrate and anhydrate phases of PDA-TPA was significantly influenced by water activity, and the larger the value of water activity is, the higher is the transition temperature. These studies give insight into the transformation of nylon 5T monomer salt and contribute to the control of target crystal preparation.