Yangyang Huang
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
Yangyang Huang has a total of 36 co-authors. Here are the top co-authors by number of shared publications:
- Linhua Ye
South China University of Technology
3 shared publications Ronghua Luo
3 shared publications- Ronghua Luo
South China University of Technology
2 shared publications - Bo Chi
State Key Laboratory of Materials-Oriented Chemical Engineering, Nanjing Tech University, Nanjing 211816, PR China
1 shared publication Bo Zhao
National and Local Joint Engineering Research Center of Biomedical Functional Materials School of Chemistry and Materials Science Nanjing Normal University Nanjing 210023 China
1 shared publication- Chao-Jun Chen
Yunnan Key Laboratory of Plateau Geographical Processes & Environmental Changes, Faculty of Geography, Yunnan Normal University, Kunming 650500, China
1 shared publication
Latest Publications
- 12 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ASME Transactions on Mechatronics
- Vol. 31 (2) , 1369-1376
Deep Learning Enabled in Predicting Flight Parameters Using Piezoelectric Sensor
In this article, a novel flight parameter identification system (FPIS) integrated with a piezoelectric cantilevers array, and a Transformer network for precisely predicting the flight attitude, which include the airspeed (v), angle of attack (α), and angle of sideslip (β), is proposed. A circular array configuration formed by four kinds of pizeoelectric bimorph cantilevers is designed for adapt to the aerodynamic requirements Simultaneously, several comprehensive experiments are performed to obtain the sensing characteristics of flight parameters identification and to verified the above transformer network for two commonly used conical angles in aircraft head design, including FPIS-40°and FPIS-60° prototype. The experimental results indicate that U increases with v continuously increased for both of the FPIS-40° and FPIS-60°. Moreover, comparisons of predictive and experimental results show that the absolute errors of the v, α, and β of FPIS-40° (FPIS-60°) are less than 0.02 m/s (0.01 m/s), 0.05° (0.02°), 0.04° (0.02°), respectively. Therefore, the superiority of the FPIS’s performance on predicting the flight attitude is demonstrated, and the dynamic identification accuracy of v, α, and β exceeds the previous state-of-the-art method, and the advantages are 0.01 m/s versus 0.064 m/s, 0.02° versus 0.16°, 0.02° versus 0.27°, respectively.
- 12 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ASME Transactions on Mechatronics
- Vol. 31 (2) , 1369-1376
Deep Learning Enabled in Predicting Flight Parameters Using Piezoelectric Sensor
In this article, a novel flight parameter identification system (FPIS) integrated with a piezoelectric cantilevers array, and a Transformer network for precisely predicting the flight attitude, which include the airspeed (v), angle of attack (α), and angle of sideslip (β), is proposed. A circular array configuration formed by four kinds of pizeoelectric bimorph cantilevers is designed for adapt to the aerodynamic requirements Simultaneously, several comprehensive experiments are performed to obtain the sensing characteristics of flight parameters identification and to verified the above transformer network for two commonly used conical angles in aircraft head design, including FPIS-40°and FPIS-60° prototype. The experimental results indicate that U increases with v continuously increased for both of the FPIS-40° and FPIS-60°. Moreover, comparisons of predictive and experimental results show that the absolute errors of the v, α, and β of FPIS-40° (FPIS-60°) are less than 0.02 m/s (0.01 m/s), 0.05° (0.02°), 0.04° (0.02°), respectively. Therefore, the superiority of the FPIS’s performance on predicting the flight attitude is demonstrated, and the dynamic identification accuracy of v, α, and β exceeds the previous state-of-the-art method, and the advantages are 0.01 m/s versus 0.064 m/s, 0.02° versus 0.16°, 0.02° versus 0.27°, respectively.
- 27 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. 7 (3) , 1596-1609
Robust Unknown Object Detection in Dynamic Environments Through Dual-Granularity Reconstruction Error Modeling
Open World Object Detection (OWOD) aims to detect both known and unknown objects in dynamic environments, where unknown instances lack ground-truth supervision during training. Existing methods typically rely on supervision from known categories, leading models to overconfidently classify visually similar unknowns as known classes, and dissimilar ones as background. This known-class prior bias severely hinders the detection of truly novel objects. To address this challenge, we propose a robust unknown object detection method based on dual-granularity reconstruction error modeling. At the fine-grained level, we propose Fine-grained Masked Reconstruction (FMR), which randomly masks feature regions to guide reconstruction toward semantic structures, thereby improving foreground–background discrimination. At the coarse-grained level, we propose Adaptive Region-based Error Aggregation (AREA), which aggregates reconstruction errors over object proposals to enhance the model’s sensitivity to ambiguous semantic boundaries while suppressing local outliers. Furthermore, we perform decoupled probabilistic modeling of foreground and background reconstruction errors, enabling soft estimation of unknown object likelihoods without supervision. Extensive experiments on standard OWOD benchmarks demonstrate that our method consistently outperforms state-of-the-art approaches, achieving a +20.6 improvement in unknown object recall (U-Recall) while maintaining strong performance on known classes.
- 27 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. 7 (3) , 1596-1609
Robust Unknown Object Detection in Dynamic Environments Through Dual-Granularity Reconstruction Error Modeling
Open World Object Detection (OWOD) aims to detect both known and unknown objects in dynamic environments, where unknown instances lack ground-truth supervision during training. Existing methods typically rely on supervision from known categories, leading models to overconfidently classify visually similar unknowns as known classes, and dissimilar ones as background. This known-class prior bias severely hinders the detection of truly novel objects. To address this challenge, we propose a robust unknown object detection method based on dual-granularity reconstruction error modeling. At the fine-grained level, we propose Fine-grained Masked Reconstruction (FMR), which randomly masks feature regions to guide reconstruction toward semantic structures, thereby improving foreground–background discrimination. At the coarse-grained level, we propose Adaptive Region-based Error Aggregation (AREA), which aggregates reconstruction errors over object proposals to enhance the model’s sensitivity to ambiguous semantic boundaries while suppressing local outliers. Furthermore, we perform decoupled probabilistic modeling of foreground and background reconstruction errors, enabling soft estimation of unknown object likelihoods without supervision. Extensive experiments on standard OWOD benchmarks demonstrate that our method consistently outperforms state-of-the-art approaches, achieving a +20.6 improvement in unknown object recall (U-Recall) while maintaining strong performance on known classes.
- 13 August 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 297
SALLM: Open world object detection empowered by self adaptive learning and large model
- 13 August 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 297
SALLM: Open world object detection empowered by self adaptive learning and large model
- 24 July 2025
- Published by Springer Nature
- p. 63-73
Decoupled Modeling of Foreground and Background for Open-World Object Detection
- 24 July 2025
- Published by Springer Nature
- p. 63-73
Decoupled Modeling of Foreground and Background for Open-World Object Detection
- 19 March 2025
- Published by Elsevier in Image and Vision Computing
- Vol. 157
DDMCB: Open-world object detection empowered by Denoising Diffusion Models and Calibration Balance
- 19 March 2025
- Published by Elsevier in Image and Vision Computing
- Vol. 157
DDMCB: Open-world object detection empowered by Denoising Diffusion Models and Calibration Balance
- 3 March 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 275
FMDL: Enhancing Open-World Object Detection with foundation models and dynamic learning
- 3 March 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 275
FMDL: Enhancing Open-World Object Detection with foundation models and dynamic learning
- Open Access
- 10 May 2022
- Published by Springer Nature in World Journal of Surgical Oncology
- Vol. 20 (1) , 1-8
Multiple endocrine neoplasia type 1 involving both the liver and lung: a case report
Background: Multiple endocrine neoplasia type 1 (MEN1) is a rare autosomal dominant tumor syndrome with a high degree of heterogeneity in clinical phenotypes, generally involving the parathyroid, anterior pituitary, and enteropancreas. In recent years, several new insights into the clinical features of MEN1 have been reported in the literature. However, it is not clear whether MEN1-associated primary tumors can occur in the liver. Case presentation: We report the case of a 52-year-old man with multiple endocrine neoplasia type 1 diagnosed by genetic sequencing. After uniportal thoracoscopic right middle lobectomy, laparoscopic radical resection of the liver tumors, and radiofrequency ablation of the parathyroid space, the parathyroid hormone level decreased from 177 pg/ml to a normal level (20 pg/ml). No local tumor recurrence was observed during a follow-up of 5 months. Conclusion: We report the first case of MEN1 with simultaneous liver and lung involvement in which the patient underwent radical resection of the tumors, and we propose the possibility that the liver and other nonendocrine organs may also develop diseases associated with MEN1; although, this view needs further verification. Gene detection has crucial clinical significance for guiding diagnosis and treatment.
- 10 May 2022
- Published by Springer Nature in World Journal of Surgical Oncology
- Vol. 20 (1) , 1-8
Open AccessMultiple endocrine neoplasia type 1 involving both the liver and lung: a case report
Background: Multiple endocrine neoplasia type 1 (MEN1) is a rare autosomal dominant tumor syndrome with a high degree of heterogeneity in clinical phenotypes, generally involving the parathyroid, anterior pituitary, and enteropancreas. In recent years, several new insights into the clinical features of MEN1 have been reported in the literature. However, it is not clear whether MEN1-associated primary tumors can occur in the liver. Case presentation: We report the case of a 52-year-old man with multiple endocrine neoplasia type 1 diagnosed by genetic sequencing. After uniportal thoracoscopic right middle lobectomy, laparoscopic radical resection of the liver tumors, and radiofrequency ablation of the parathyroid space, the parathyroid hormone level decreased from 177 pg/ml to a normal level (20 pg/ml). No local tumor recurrence was observed during a follow-up of 5 months. Conclusion: We report the first case of MEN1 with simultaneous liver and lung involvement in which the patient underwent radical resection of the tumors, and we propose the possibility that the liver and other nonendocrine organs may also develop diseases associated with MEN1; although, this view needs further verification. Gene detection has crucial clinical significance for guiding diagnosis and treatment.
- 1 March 2021
- Published by Elsevier in Applied Geochemistry
- Vol. 126, 104873
Significance of active speleothem δ18O at annual-decadal timescale——A case study from monitoring in Furong Cave
- 1 March 2021
- Published by Elsevier in Applied Geochemistry
- Vol. 126, 104873
Significance of active speleothem δ18O at annual-decadal timescale——A case study from monitoring in Furong Cave
- 21 May 2019
- Published by Wiley in Angewandte Chemie
- Vol. 131 (31) , 10692-10696
A Safe and Efficient Strategy for the Rapid Elimination of Blood Lead In Vivo Based on a Capture–Fix–Separate Mechanism
Lead poisoning is an important problem because of its serious effects on human health. Yet a solution is not available due to an incomplete understanding of the state of lead ions in blood. Since most blood lead binds to hemoglobin (Hb) in red blood cells, identifying and capturing lead‐contaminated Hb in RBCs is important. Herein, a magnetic blood lead remover with hyperbranched poly(amidoamine)s (HPAM) as template/co‐adsorbent and core–shell mesoporous structure was synthesized. Lead‐containing Hb was selectively captured and then fixed by mesoporous channels. The magnetic separation technology was used to separate the magnetic remover from blood. A related blood lead clean‐up apparatus was used to remove lead from the blood of a pig in vivo. Results of physical/chemical characterizations, biocompatibility experiments, animal tests, and theoretical simulation verify the safety and efficiency of this removal strategy and the high efficiency of the blood lead clean‐up apparatus.
- 21 May 2019
- Published by Wiley in Angewandte Chemie
- Vol. 131 (31) , 10692-10696
A Safe and Efficient Strategy for the Rapid Elimination of Blood Lead In Vivo Based on a Capture–Fix–Separate Mechanism
Lead poisoning is an important problem because of its serious effects on human health. Yet a solution is not available due to an incomplete understanding of the state of lead ions in blood. Since most blood lead binds to hemoglobin (Hb) in red blood cells, identifying and capturing lead‐contaminated Hb in RBCs is important. Herein, a magnetic blood lead remover with hyperbranched poly(amidoamine)s (HPAM) as template/co‐adsorbent and core–shell mesoporous structure was synthesized. Lead‐containing Hb was selectively captured and then fixed by mesoporous channels. The magnetic separation technology was used to separate the magnetic remover from blood. A related blood lead clean‐up apparatus was used to remove lead from the blood of a pig in vivo. Results of physical/chemical characterizations, biocompatibility experiments, animal tests, and theoretical simulation verify the safety and efficiency of this removal strategy and the high efficiency of the blood lead clean‐up apparatus.