Shenggen Ju

Shenggen Ju

Auto-generated profile, based on publicly available information

Shenggen Ju

College of Computer Science, Sichuan University, Chengdu, China

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

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

Representative Publications

View All Publications
14 March 2024 in BMC Medical Informatics and Decision Making
Verified
Journal Article
Open access
PDF file
YLYong Liu
Yong Liu
SJShenggen Ju
Shenggen Ju
JWJunfeng Wang
Junfeng Wang
Background: Telemedicine has experienced rapid growth in recent years, aiming to enhance medical efficiency and reduce the workload of healthcare professionals. During the COVID-19 pandemic in 2019, it became especially crucial, enabling remote screenings and access to healthcare services while maintaining social distancing. Online consultation platforms have emerged, but the demand has strained the availability of medical professionals, directly leading to research and development in automated medical consultation. Specifically, there is a need for efficient and accurate medical dialogue summarization algorithms to condense lengthy conversations into shorter versions focused on relevant medical facts. The success of large language models like generative pre-trained transformer (GPT)-3 has recently prompted a paradigm shift in natural language processing (NLP) research. In this paper, we will explore its impact on medical dialogue summarization. Methods: We present the performance and evaluation results of two approaches on a medical dialogue dataset. The first approach is based on fine-tuned pre-trained language models, such as bert-based summarization (BERTSUM) and bidirectional auto-regressive Transformers (BART). The second approach utilizes a large language models (LLMs) GPT-3.5 with inter-context learning (ICL). Evaluation is conducted using automated metrics such as ROUGE and BERTScore. Results: In comparison to the BART and ChatGPT models, the summaries generated by the BERTSUM model not only exhibit significantly lower ROUGE and BERTScore values but also fail to pass the testing for any of the metrics in manual evaluation. On the other hand, the BART model achieved the highest ROUGE and BERTScore values among all evaluated models, surpassing ChatGPT. Its ROUGE-1, ROUGE-2, ROUGE-L, and BERTScore values were 14.94%, 53.48%, 32.84%, and 6.73% higher respectively than ChatGPT’s best results. However, in the manual evaluation by medical experts, the summaries generated by the BART model exhibit satisfactory performance only in the “Readability” metric, with less than 30% passing the manual evaluation in other metrics. When compared to the BERTSUM and BART models, the ChatGPT model was evidently more favored by human medical experts. Conclusion: On one hand, the GPT-3.5 model can manipulate the style and outcomes of medical dialogue summaries through various prompts. The generated content is not only better received than results from certain human experts but also more comprehensible, making it a promising avenue for automated medical dialogue summarization. On the other hand, automated evaluation mechanisms like ROUGE and BERTScore fall short in fully assessing the outputs of large language models like GPT-3.5. Therefore, it is necessary to research more appropriate evaluation criteria.

12 May 2020 in Mathematical Problems in Engineering
Verified
Journal Article
Open access
PDF file
YLYong Liu
Yong Liu
SJShenggen Ju
Shenggen Ju
JWJunfeng Wang
Junfeng Wang
CSChong Su
Chong Su
Feature selection method is designed to select the representative feature subsets from the original feature set by different evaluation of feature relevance, which focuses on reducing the dimension of the features while maintaining the predictive accuracy of a classifier. In this study, we propose a feature selection method for text classification based on independent feature space search. Firstly, a relative document-term frequency difference (RDTFD) method is proposed to divide the features in all text documents into two independent feature sets according to the features’ ability to discriminate the positive and negative samples, which has two important functions: one is to improve the high class correlation of the features and reduce the correlation between the features and the other is to reduce the search range of feature space and maintain appropriate feature redundancy. Secondly, the feature search strategy is used to search the optimal feature subset in independent feature space, which can improve the performance of text classification. Finally, we evaluate several experiments conduced on six benchmark corpora, the experimental results show the RDTFD method based on independent feature space search is more robust than the other feature selection methods.

2 December 2019 in IEEE Access
Verified
Journal Article
Open access
XXXi Xiong
Xi Xiong
CXChuan Xie
Chuan Xie
RZRongmei Zhao
Rongmei Zhao
YLYuanyuan Li
Yuanyuan Li
SJShenggen Ju
Shenggen Ju
MJMing Jin
Ming Jin
Besides the ID class features, the advertisement click log file contains many significant features, which make the study of the advertisement clickthrough rate prediction more difficult. In this study, we convert original features into numerical meaningful ones, which reduce the sparsity and redundancy. In order to solve the problem of class imbalance, we propose a downsampling algorithm based on K-means model to classify large samples, then divide them into some sensible and rational features by the heuristic methods. To further improve the feature representation, we finally select and combine features by the Gradient Boosting Decision Tree model and process high-dimensional features by the logistic regression method. We conducted experiments on the dataset of Tencent SOSO and demonstrated that our approach outperforms the state-of-the-art baseline methods by 0.05% on average in terms of R2 and by 50.5% on average in terms of RMSE.

26 August 2019 in Computer Assisted Surgery
Verified
Journal Article
Open access
WCWuxuan Chen
Wuxuan Chen
PWPeng Wang
Peng Wang
ZZZhihong Zhang
Zhihong Zhang
XDXudong Deng
Xudong Deng
CZCongyao Zhang
Congyao Zhang
SJShenggen Ju
Shenggen Ju
Acoustic nonlinear parameter β, was of great interest in tissue characterization in recent years. Nonlinear imaging methods have been reported to provide improved spatial and contrast resolution. We introduce a nonlinear imaging method derived from nonlinear wave equation based on Gaussian-form solution assumption, which can be applied in pulse-echo mode on diagnostic ultrasound. Through making the use of two pulse transmission, only nonlinear effects are reserved and other effects like scattering, diffraction and linear attenuation can be eliminated. For validation of this method a set of simulation results are generated with a nonlinear simulator. Simulated images also indicate that our method clearly describes the spatial distribution of B/A in the medium.

1 January 2025 in World Wide Web
Verified
Journal Article
Closed access
PDF file
RZRongmei Zhao
Rongmei Zhao
YZYuxin Zhang
Yuxin Zhang
SJShenggen Ju
Shenggen Ju
JPJian Peng
Jian Peng
YYYueting Yang
Yueting Yang

10 March 2026 in Knowledge-Based Systems
Verified
Journal Article
Closed access
TZTao Zhou
Tao Zhou
GLGuilin Li
Guilin Li
YLYanting Li
Yanting Li
RZRenyue Zhang
Renyue Zhang
SJShenggen Ju
Shenggen Ju