Yang Weng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yang Weng has a total of 47 co-authors. Here are the top co-authors by number of shared publications:
- Wenxing Hong
Xiamen University, Xiamen, China
6 shared publications - Haiying Yan
Department of Pulmonary and Critical Care Medicine, Cheng Du Qing Cheng Mt. Hospital, Chongzhou City, Chengdu, China
2 shared publications - Haotian Lei2 shared publications
Jianwei Qi
School of Aerospace Engineering, Xiamen University, Xiamen, China
2 shared publicationsLei Wu
Sichuan Univ, Dept Math, Chengdu 610064, Sichuan, Peoples R China
2 shared publications- Lihua Xie
Nanyang Technological University
2 shared publications
Latest Publications
- 3 June 2026
- Published by Springer Nature
- p. 140-152
Leveraging Query Selection for Efficient Relationship Detection
- 3 June 2026
- Published by Springer Nature
- p. 140-152
Leveraging Query Selection for Efficient Relationship Detection
- 3 June 2026
- Published by Springer Nature
- p. 113-126
CNN-Transformer for Tool Wear Condition Recognition Based on Data Augmentation
- 3 June 2026
- Published by Springer Nature
- p. 113-126
CNN-Transformer for Tool Wear Condition Recognition Based on Data Augmentation
- 26 February 2024
- Published by Springer Nature
- p. 400-414
Exploring the Causal Relationship Between Forgiveness and Sentencing Outcomes in Dangerous Driving Cases
- 26 February 2024
- Published by Springer Nature
- p. 400-414
Exploring the Causal Relationship Between Forgiveness and Sentencing Outcomes in Dangerous Driving Cases
- Open Access
A Novel Piecewise Cubic Hermite Interpolating Polynomial-Enhanced Convolutional Gated Recurrent Method under Multiple Sensor Feature Fusion for Tool Wear Prediction
The monitoring of the lifetime of cutting tools often faces problems such as life data loss, drift, and distortion. The prediction of the lifetime in this situation is greatly compromised with respect to the accuracy. The recent rise of deep learning, such as Gated Recurrent Unit Units (GRUs), Hidden Markov Models (HMMs), Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Attention networks, and Transformers, has dramatically improved the data problems in tool lifetime prediction, substantially enhancing the accuracy of tool wear prediction. In this paper, we introduce a novel approach known as PCHIP-Enhanced ConvGRU (PECG), which leverages multiple—feature fusion for tool wear prediction. When compared to traditional models such as CNNs, the CNN Block, and GRUs, our method consistently outperformed them across all key performance metrics, with a primary focus on the accuracy. PECG addresses the challenge of missing tool wear measurement data in relation to sensor data. By employing PCHIP interpolation to fill in the gaps in the wear values, we have developed a model that combines the strengths of both CNNs and GRUs with data augmentation. The experimental results demonstrate that our proposed method achieved an exceptional relative accuracy of 0.8522, while also exhibiting a Pearson’s Correlation Coefficient (PCC) exceeding 0.95. This innovative approach not only predicts tool wear with remarkable precision, but also offers enhanced stability.
Open AccessA Novel Piecewise Cubic Hermite Interpolating Polynomial-Enhanced Convolutional Gated Recurrent Method under Multiple Sensor Feature Fusion for Tool Wear Prediction
The monitoring of the lifetime of cutting tools often faces problems such as life data loss, drift, and distortion. The prediction of the lifetime in this situation is greatly compromised with respect to the accuracy. The recent rise of deep learning, such as Gated Recurrent Unit Units (GRUs), Hidden Markov Models (HMMs), Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Attention networks, and Transformers, has dramatically improved the data problems in tool lifetime prediction, substantially enhancing the accuracy of tool wear prediction. In this paper, we introduce a novel approach known as PCHIP-Enhanced ConvGRU (PECG), which leverages multiple—feature fusion for tool wear prediction. When compared to traditional models such as CNNs, the CNN Block, and GRUs, our method consistently outperformed them across all key performance metrics, with a primary focus on the accuracy. PECG addresses the challenge of missing tool wear measurement data in relation to sensor data. By employing PCHIP interpolation to fill in the gaps in the wear values, we have developed a model that combines the strengths of both CNNs and GRUs with data augmentation. The experimental results demonstrate that our proposed method achieved an exceptional relative accuracy of 0.8522, while also exhibiting a Pearson’s Correlation Coefficient (PCC) exceeding 0.95. This innovative approach not only predicts tool wear with remarkable precision, but also offers enhanced stability.
- Open Access
- 16 June 2023
- Published by Wolters Kluwer Health in Medicine
- Vol. 102 (24) , e33845
Pulmonary aspergillus infection with abnormal imaging successfully treated with omalizumab: A case report
Background: Pulmonary aspergillosis is a pulmonary infectious disease that is clinically difficult to diagnose and treat. When the lower respiratory tract is invaded by Aspergillus, the clinical manifestations and imaging features vary among patients with different immune states. The use of antifungal drugs and glucocorticoids are important, but some patients do not respond satisfactorily to treatment. Case presentation: A 59-year-old female had a long history of asthma and poor symptom control, with long-term use of long-acting inhaled glucocorticoids combined with a long-acting β2 receptor agonists (ICS + LABA) (salmeterol fluticasone inhalation powder). The ground glass shadow, tree-in-bud sign, and bronchiectasis in the middle lobe of the right lung and the lower lobe of both lungs were first detected by chest CT over 5 years ago. Atelectasis in the middle lobe of the right lung was detected over 3 years ago. Over 2 years ago, the patient was hospitalized and a repeat chest CT showed persistent atelectasis in the middle lobe of the right lung, and more lesions in bilateral lower lungs than before. Aspergillus fumigatus was detected in alveolar lavage fluid and sputum pathogenic culture, which confirmed the diagnosis of pulmonary aspergillosis. After treatment with voriconazole and amphotericin B, the middle lobe of the right lung partially reopened, but the lesions in bilateral lower lungs persisted. After 21 weeks of treatment, the antifungal drugs were stopped because the patient refused to use oral/intravenous glucocorticoids, and omalizumab was finally chosen for treatment. After 1 month of treatment, the patient’s clinical symptoms began to ease. After 1 year of treatment, imaging reexamination of lung showed that the lesions were completely cleared, accompanied by significant improvement in nutritional status and airway function. Conclusions: We reported the case of a patient with pulmonary Aspergillus infection who was treated with omalizumab and showed significant improvement in clinical symptoms and imaging abnormalities, which provides a new option for patients with pulmonary Aspergillus infection who show unsatisfactory response with first-line drugs.
- 16 June 2023
- Published by Wolters Kluwer Health in Medicine
- Vol. 102 (24) , e33845
Open AccessPulmonary aspergillus infection with abnormal imaging successfully treated with omalizumab: A case report
Background: Pulmonary aspergillosis is a pulmonary infectious disease that is clinically difficult to diagnose and treat. When the lower respiratory tract is invaded by Aspergillus, the clinical manifestations and imaging features vary among patients with different immune states. The use of antifungal drugs and glucocorticoids are important, but some patients do not respond satisfactorily to treatment. Case presentation: A 59-year-old female had a long history of asthma and poor symptom control, with long-term use of long-acting inhaled glucocorticoids combined with a long-acting β2 receptor agonists (ICS + LABA) (salmeterol fluticasone inhalation powder). The ground glass shadow, tree-in-bud sign, and bronchiectasis in the middle lobe of the right lung and the lower lobe of both lungs were first detected by chest CT over 5 years ago. Atelectasis in the middle lobe of the right lung was detected over 3 years ago. Over 2 years ago, the patient was hospitalized and a repeat chest CT showed persistent atelectasis in the middle lobe of the right lung, and more lesions in bilateral lower lungs than before. Aspergillus fumigatus was detected in alveolar lavage fluid and sputum pathogenic culture, which confirmed the diagnosis of pulmonary aspergillosis. After treatment with voriconazole and amphotericin B, the middle lobe of the right lung partially reopened, but the lesions in bilateral lower lungs persisted. After 21 weeks of treatment, the antifungal drugs were stopped because the patient refused to use oral/intravenous glucocorticoids, and omalizumab was finally chosen for treatment. After 1 month of treatment, the patient’s clinical symptoms began to ease. After 1 year of treatment, imaging reexamination of lung showed that the lesions were completely cleared, accompanied by significant improvement in nutritional status and airway function. Conclusions: We reported the case of a patient with pulmonary Aspergillus infection who was treated with omalizumab and showed significant improvement in clinical symptoms and imaging abnormalities, which provides a new option for patients with pulmonary Aspergillus infection who show unsatisfactory response with first-line drugs.
- 16 May 2023
- Published by Springer Nature
- p. 123-135
Research on Hierarchical Teaching Using Propensity Score Weighting-Based Causal Inference Model
- 16 May 2023
- Published by Springer Nature
- p. 123-135
Research on Hierarchical Teaching Using Propensity Score Weighting-Based Causal Inference Model
- 14 May 2023
- Published by Springer Nature
- p. 92-104
Topic Term Clustering Based on Semi-supervised Co-occurrence Graph and Its Application in Chinese Judgement Documents
- 14 May 2023
- Published by Springer Nature
- p. 92-104
Topic Term Clustering Based on Semi-supervised Co-occurrence Graph and Its Application in Chinese Judgement Documents
- 14 May 2023
- Published by Springer Nature
- p. 595-605
Deep Neural Networks with Cross-Charge Features
- 13 October 2020
- Published by Springer Nature
- p. 298-309
Deep Dependency Network for Multi-label Text Classification
- 13 October 2020
- Published by Springer Nature
- p. 298-309
Deep Dependency Network for Multi-label Text Classification
- Open Access
- 17 April 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 75022-75034
Few-Shot Learning for Chinese Legal Controversial Issues Classification
Chinese courts organize debates surrounding controversial issues along with the gradual formation of the new procedural system. With the progress of China’s judicial reform, more than 80 million judgement documents have been made public online. Similar controversial issues identified in and among the massive public judgment documents are of significant value for judges in their trial work. Hence, homogeneous controversial issues classification becomes the basis for similar cases retrieval. However, controversial issues follow the power-law distribution, not all of them are within the labels provided by manual annotation and their categories cannot be exhausted. In order to generalize those unfamiliar categories without necessitating extensive retraining, we propose a controversial issues classification algorithm based on few-shot learning. Two few-shot learning algorithms are proposed for our controversial issues problem, Relation Network and Induction Network, respectively. With only a handful of given instances, both of them have shown excellent results on the two datasets, which proves their effectiveness in adapting to accommodating new categories not seen in training. The proposed method provides trial assistance for judges, promotes the dissemination of experience and improves fairness of adjudication.
- 17 April 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 75022-75034
Open AccessFew-Shot Learning for Chinese Legal Controversial Issues Classification
Chinese courts organize debates surrounding controversial issues along with the gradual formation of the new procedural system. With the progress of China’s judicial reform, more than 80 million judgement documents have been made public online. Similar controversial issues identified in and among the massive public judgment documents are of significant value for judges in their trial work. Hence, homogeneous controversial issues classification becomes the basis for similar cases retrieval. However, controversial issues follow the power-law distribution, not all of them are within the labels provided by manual annotation and their categories cannot be exhausted. In order to generalize those unfamiliar categories without necessitating extensive retraining, we propose a controversial issues classification algorithm based on few-shot learning. Two few-shot learning algorithms are proposed for our controversial issues problem, Relation Network and Induction Network, respectively. With only a handful of given instances, both of them have shown excellent results on the two datasets, which proves their effectiveness in adapting to accommodating new categories not seen in training. The proposed method provides trial assistance for judges, promotes the dissemination of experience and improves fairness of adjudication.