jun ma

Dr. jun ma

lanzhou university

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
14 November 2022 in Applied Intelligence
Verified
Journal Article
Closed access
PDF file
JJJing Jiang
Jing Jiang
RZRuisheng Zhang
Ruisheng Zhang
JMjun ma
jun ma
YLYunwu Liu
Yunwu Liu
EYEnjie Yang
Enjie Yang
YYYongna Yuan
Yongna Yuan

1 November 2020 in Journal of Physics: Conference Series
Verified
Conference Paper
Open access
PDF file
JMjun ma
jun ma
LLLanglang Li
Langlang Li
Text classification is a basic task in natural language processing. When the amount of data is insufficient, the classification accuracy will be greatly affected. We propose to use the back-translation method to expand three Chinese data sets used for text classification, and then train and predict the data sets through deep learning classification model. The results prove that using back-translation to expand the data is particularly helpful on a smaller dataset, it also can reduce the unbalanced distribution of samples and improve the classification performance.

8 March 2024 in Interdisciplinary Sciences: Computational Life Sciences
Verified
Journal Article
Closed access
PDF file
JMjun ma
jun ma
ZZZhili Zhao
Zhili Zhao
TLTongfeng Li
Tongfeng Li
YLYunwu Liu
Yunwu Liu
RZRuisheng Zhang
Ruisheng Zhang

12 April 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
WDWenbin Dai
Wenbin Dai
YMYuxin Ma
Yuxin Ma
YFYan Fan
Yan Fan
JMjun ma
jun ma
Due to the low quality of existing Chinese herbal medicine datasets and the lack of recognition algorithms for herbal images, automatic classification of Chinese herbal medicine is ineffective. In this paper, we constructed a comprehensive dataset comprising 4485 images across 20 categories of Chinese herbal medicine. This dataset captures the morphological diversity of Chinese herbal medicine while reducing inter-class variations and closely mimics real-world complexity. Considering the subtle differences among the data, we proposed a multi-scale feature extraction architecture called MSPyraNet. This architecture is composed of multiple FACNBlock units, which are designed explicitly for herbal medicine characteristics. FACNBlock utilizes a multi-scale representation module, using convolutions and atrous convolutions of varying sizes to generate and fuse multi-scale feature maps. Experimental results show that MSPyraNet improves accuracy by more than 4.72% and 4.54% compared to existing SOTA models on two datasets. Ablation studies validate the effectiveness of the multi-scale representation module. Furthermore, we discovered that MSPyraNet achieves a notable improvement in classifying Chinese herbal medicines that are morphologically similar but belong to different categories. Briefly, this study provides a dataset and methodological reference for future research on Chinese herbal medicine classification.

28 August 2025
Verified
Book Chapter
Closed access
PDF file
WDWenbin Dai
Wenbin Dai
YZYihao Zhao
Yihao Zhao
YCYuduo Chen
Yuduo Chen
JMjun ma
jun ma