Jing Jin

Jing Jin

Auto-generated profile, based on publicly available information

Jing Jin

Department of Gynecology Maternal and Child Health Hospital of Hubei Province Wuhan PR China

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
9 March 2022 in Monthly Notices of the Royal Astronomical Society
Verified
Journal Article
Closed access
PDF file
HZHongyang Zhao
Hongyang Zhao
JJJing Jin
Jing Jin
YLYi Liu
Yi Liu
YSYi Shen
Yi Shen
YJYu Jiang
Yu Jiang
Pulsar observation and research are of great significance. With the gradual increase in the performance and quantity of observing equipment, the received pulsar observation data also increase geometrically. Machine learning can mine large-scale pulsar data sets to realize automatic pulsar candidate identification. However, the pulsar candidate and non-pulsar candidate data sets are highly imbalanced. The traditional classifier trained on the data set with imbalanced class distribution usually shows poor generalization performance, which will cause the classifier to be biased towards negative instances. To address the problem of poor identification algorithm performance caused by sample imbalance, we describe a new framework, namely AdaBoost-multi-input-CNN (AdaBoost-MICNN). In AdaBoost, multiple baseline models are trained sequentially, and the weight of each training sample changes as the training progresses. Especially the minority samples, which are more easily ignored, will get more attention in subsequent baseline models. This will solve the problem of imbalanced classification. Meanwhile, there are usually four pulsar diagnostic plots. To automatically extract and integrate these four diagnostic plots features, we use multi-input-CNN (MICNN) as the baseline model of AdaBoost. The attention mechanism is introduced to enhance the performance of MICNN’s extraction of features, and design an objective function that adds the maximum mean discrepancy to enhance the anti-interference ability of the model. Finally, the proposed method is tested in the High Time Resolution Universe Medlat Data, and the experimental results verify the effectiveness and efficiency of the method.


1 October 2019
Verified
Conference Paper
Closed access
TXTeng Xue
Teng Xue
XZXiaodan Zhang
Xiaodan Zhang
JJJing Jin
Jing Jin
JZJinzhuan Zhang
Jinzhuan Zhang
CLChengyao Li
Chengyao Li
QFQiang Fu
Qiang Fu
The flowers, leaves and stems of artificial green plants have been chosen as the study objects and the pyrolysis characteristics of these three parts have been analyzed in order to identify the fire characteristics of the typical thermoplastic artificial green plants. The pyrolysis activation energy distribution of the three parts of the sample has been studied through Starink method and Firedman method respectively and the accuracy of the two methods have been compared. The most probable mechanism functions of the primary pyrolysis stages of the three parts have been discussed through Malek method. The Coats-Redfern method has been used to verify the obtained most probable mechanism functions. The results of thermogravimetric experiments show that the pyrolysis of the flowers and leaves of the artificial green plants can be divided into two stages. The temperature at which these two parts reach the maximum heating rate is basically the same. The residual amount of the flower sample keeps decreasing with the increase of the heating rate while the residual amount of the leaves increases with the increasing heating rate. The pyrolysis of stems involves three stages, in which the second stage owns the highest mass loss rate, and the residual amount of stems decreases with the rising heating rate. The analysis results of the pyrolysis kinetics of artificial green plants show that the activation energy of stems is relatively low, most likely to be pyrolyzed in case of fire. The partial activation energy of the leaves is relatively high, contributing to high thermal stability in case of fire. As the reaction proceeds, the pyrolysis mechanisms of the artificial green plant flowers, leaves and stems transform from random nucleation to two-dimensional diffusion, from random nucleation to phase boundary reaction and from chemical reaction to three-dimensional diffusion respectively.

24 February 2022 in arXiv
Verified
Preprint
Open access
PDF file
JJJing Jin
Jing Jin
HWHoufeng Wang
Houfeng Wang
Machine Reading Comprehension(MRC) has achieved a remarkable result since some powerful models, such as BERT, are proposed. However, these models are not robust enough and vulnerable to adversarial input perturbation and generalization examples. Some works tried to improve the performance on specific types of data by adding some related examples into training data while it leads to degradation on the original dataset, because the shift of data distribution makes the answer ranking based on the softmax probability of model unreliable. In this paper, we propose a method to improve the robustness by using a calibrator as the post-hoc reranker, which is implemented based on XGBoost model. The calibrator combines both manual features and representation learning features to rerank candidate results. Experimental results on adversarial datasets show that our model can achieve performance improvement by more than 10\% and also make improvement on the original and generalization datasets.

27 August 2022 in arXiv
Verified
Preprint
Open access
PDF file
QWQing Wang
Qing Wang
JJJing Jin
Jing Jin
Xiaofeng LiuXiaofeng Liu
Xiaofeng Liu
HZHuixuan Zong
Huixuan Zong
YSYunfeng Shao
Yunfeng Shao
YLYinchuan Li
Yinchuan Li
Federated learning (FL) is a new distributed machine learning framework that can achieve reliably collaborative training without collecting users' private data. However, due to FL's frequent communication and average aggregation strategy, they experience challenges scaling to statistical diversity data and large-scale models. In this paper, we propose a personalized FL framework, named Tensor Decomposition based Personalized Federated learning (TDPFed), in which we design a novel tensorized local model with tensorized linear layers and convolutional layers to reduce the communication cost. TDPFed uses a bi-level loss function to decouple personalized model optimization from the global model learning by controlling the gap between the personalized model and the tensorized local model. Moreover, an effective distributed learning strategy and two different model aggregation strategies are well designed for the proposed TDPFed framework. Theoretical convergence analysis and thorough experiments demonstrate that our proposed TDPFed framework achieves state-of-the-art performance while reducing the communication cost.