Lifen Jiang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Lifen Jiang has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Jiaxu Yang
College of Computer and Information Engineering, Tianjin Normal University, China
2 shared publications - Shibo Fu
Tianjin Normal University, China
2 shared publications - Dongbin Zhang
Horgos Business School, Yili Normal University, Yining, Xinjiang, China
1 shared publication - Fan Sun
School of Computer Science and Engineering, University of Electronic Science and Technology of China, China
1 shared publication - Haoyu Guo
College of Computer and Information Engineering, Tianjin Normal University, China
1 shared publication - Jialin Chen
College of Computer and Information Engineering, Tianjin Normal University, China
1 shared publication
Latest Publications
- Open Access
- 22 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 69-74
Research on the Application of Deep Learning-Based Intelligent Universal Language Listening and Speaking Training Systems in Minority Language Education
- 22 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 69-74
Open AccessResearch on the Application of Deep Learning-Based Intelligent Universal Language Listening and Speaking Training Systems in Minority Language Education
- Open Access
- 1 March 2024
- Published by Association for Computing Machinery (ACM)
- p. 383-387
Chinese Long Text Classification Based On Gate-Temporal Convolutional Neural Network
Convolutional neural networks can effectively extract text features but cannot adequately capture the contextual semantic information between texts, and are weak in processing long texts. In this paper, we propose a text classification model based on Temporal Convolutional Network (TCN) to address this shortcoming, and we propose Gated Temporal Convolutional Neural Network (Gate-TCN) to address the problem that the performance of the model degrades due to the introduction of noise when the number of layers of the network is deep. The model introduces the gating mechanism in the TCN module, which can effectively filter the noise and retain the effective information to improve the overall performance of the model. The Gate-TCN is used for comparison experiments on a publicly available long text classification dataset. The experiments demonstrate that compared with the traditional baseline model, the algorithm proposed in this paper has a substantial improvement in both the accuracy and F1-score. Compared with the temporal convolutional neural network (TCN), the accuracy of the Gate-TCN model is improved by 2.66% and the F1- score improved by 1.32%. The experiments show that the Gate-TCN model proposed in this paper can effectively improve the long text classification and outperforms the commonly used models.
- 1 March 2024
- Published by Association for Computing Machinery (ACM)
- p. 383-387
Open AccessChinese Long Text Classification Based On Gate-Temporal Convolutional Neural Network
Convolutional neural networks can effectively extract text features but cannot adequately capture the contextual semantic information between texts, and are weak in processing long texts. In this paper, we propose a text classification model based on Temporal Convolutional Network (TCN) to address this shortcoming, and we propose Gated Temporal Convolutional Neural Network (Gate-TCN) to address the problem that the performance of the model degrades due to the introduction of noise when the number of layers of the network is deep. The model introduces the gating mechanism in the TCN module, which can effectively filter the noise and retain the effective information to improve the overall performance of the model. The Gate-TCN is used for comparison experiments on a publicly available long text classification dataset. The experiments demonstrate that compared with the traditional baseline model, the algorithm proposed in this paper has a substantial improvement in both the accuracy and F1-score. Compared with the temporal convolutional neural network (TCN), the accuracy of the Gate-TCN model is improved by 2.66% and the F1- score improved by 1.32%. The experiments show that the Gate-TCN model proposed in this paper can effectively improve the long text classification and outperforms the commonly used models.
- Open Access
- 15 September 2023
- Published by Association for Computing Machinery (ACM)
- p. 202-206
Clinical Risk Predication for Hepatocellular Carcinoma Based on Swin Transformer
Hepatocellular Carcinoma (HCC), a common malignancy, remains a major health challenge worldwide. In order to accurately assess the severity of HCC patients and guide treatment choices, the BCLC (Barcelona Clinic Liver Cancer) staging system has become an important classification tool. However, traditional BCLC staging mainly relies on physicians’ subjective judgement and imaging characterisation, which may be subjective and inconsistent. This study categorizes the very early, early, and intermediate stages in the traditional BCLC staging system as low-risk categories, while classifying the advanced and end-stage stages as high-risk categories. On this basis, we propose a classification model based on the combination of Swin Transformer model and gradient penalty, where Swin Transformer can effectively extract the features of CT images, and gradient penalty can effectively prevent overfitting and improve the generalisation ability of the model. To evaluate our model, we conducted rigorous experiments on a public dataset. The experimental results show that our proposed model achieves superior performance in the HCC staging task compared to other classification models. In summary, the Swin Transformer-based classification model proposed in this paper provides a new and reliable way to assess the condition and treatment selection of HCC patients, which can provide decision support for physicians.
- 15 September 2023
- Published by Association for Computing Machinery (ACM)
- p. 202-206
Open AccessClinical Risk Predication for Hepatocellular Carcinoma Based on Swin Transformer
Hepatocellular Carcinoma (HCC), a common malignancy, remains a major health challenge worldwide. In order to accurately assess the severity of HCC patients and guide treatment choices, the BCLC (Barcelona Clinic Liver Cancer) staging system has become an important classification tool. However, traditional BCLC staging mainly relies on physicians’ subjective judgement and imaging characterisation, which may be subjective and inconsistent. This study categorizes the very early, early, and intermediate stages in the traditional BCLC staging system as low-risk categories, while classifying the advanced and end-stage stages as high-risk categories. On this basis, we propose a classification model based on the combination of Swin Transformer model and gradient penalty, where Swin Transformer can effectively extract the features of CT images, and gradient penalty can effectively prevent overfitting and improve the generalisation ability of the model. To evaluate our model, we conducted rigorous experiments on a public dataset. The experimental results show that our proposed model achieves superior performance in the HCC staging task compared to other classification models. In summary, the Swin Transformer-based classification model proposed in this paper provides a new and reliable way to assess the condition and treatment selection of HCC patients, which can provide decision support for physicians.