Jincui Yang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jincui Yang has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Yuyu Yuan
Beijing University of Posts and Telecommunications
10 shared publications - Ahmed Zahir
Key Laboratory of Trustworthy Distributed Computing and Service, Ministry of Education, School of Software, Beijing University of Posts and Telecommunications, Beijing 100876, China
2 shared publications - Chenlong Li
School of Computer Science (National Pilot Software Engineering School), Beijing University of Posts and Telecommunications, Beijing 100876, China
2 shared publications - Lei Chen
School of Computer Science (National Pilot Software Engineering School), Beijing University of Posts and Telecommunications, Beijing 100876, China
2 shared publications - Shasha Zhang
School of Computer Science (National Pilot Software Engineering School), Beijing University of Posts and Telecommunications, Beijing 100876, China
2 shared publications - Wen Wen
School of Computer Science (National Pilot Software Engineering School), Beijing University of Posts and Telecommunications, Beijing 100876, China
2 shared publications
Latest Publications
- 30 August 2025
- Published by Springer Nature
- p. 476-490
Rule-Based Learning for Explainable XGBoost Internal Threat Detection
- 30 August 2025
- Published by Springer Nature
- p. 476-490
Rule-Based Learning for Explainable XGBoost Internal Threat Detection
- Open Access
- 8 March 2023
- Published by MDPI AG in Applied Sciences
- Vol. 13 (6) , 3459
An Improved Confounding Effect Model for Software Defect Prediction
Software defect prediction technology can effectively improve software quality. Depending on the code metrics, machine learning models are built to predict potential defects. Some researchers have indicated that the size metric could cause confounding effects and bias the prediction results. However, evidence shows that the real confounder should be the development cycle and number of developers, which could bring confounding effects when using code metrics for prediction. This paper proposes an improved confounding effect model, introducing a new confounding variable into the traditional model. On multiple projects, we experimentally analyzed the effect extent of the confounding variable. Furthermore, we verified that controlling confounding variables helps improve the predictive model’s performance.
- 8 March 2023
- Published by MDPI AG in Applied Sciences
- Vol. 13 (6) , 3459
Open AccessAn Improved Confounding Effect Model for Software Defect Prediction
Software defect prediction technology can effectively improve software quality. Depending on the code metrics, machine learning models are built to predict potential defects. Some researchers have indicated that the size metric could cause confounding effects and bias the prediction results. However, evidence shows that the real confounder should be the development cycle and number of developers, which could bring confounding effects when using code metrics for prediction. This paper proposes an improved confounding effect model, introducing a new confounding variable into the traditional model. On multiple projects, we experimentally analyzed the effect extent of the confounding variable. Furthermore, we verified that controlling confounding variables helps improve the predictive model’s performance.
- Open Access
- 12 January 2023
- Published by MDPI AG in Electronics
- Vol. 12 (2) , 402
A Multidimensional Model for Recommendation Systems Based on Classification and Entropy
The proliferation of false and redundant information on e-commerce platforms as well as the prevalence of ineffective recommendations and other untrustworthy behaviors has seriously impeded the healthy development of these platforms. To address these issues and enhance prediction accuracy and user trust, contemporary recommendation systems often utilize additional information (i.e., side information). In this work, we propose a model to improve the recommendation quality by employing the information entropy of user-item ratings. The entropy was used as side information to reflect the global rating behavior of the user and item. We also utilized the classification of the user and item as heuristic information to improve the prediction quality. In our best result, we achieved a significant improvement of 8.2% in prediction accuracy. The model classified the items by the users’ actual preference, which is more trustworthy for users. We evaluated our model with three real-world datasets. The performance of our proposed model was significantly better than the other baseline methods. The similarity calculation method employed in the present model has the potential to mitigate the data sparsity problem associated with correlation-based similarity. The proposed weight matrix has zero sparsity. Furthermore, the proposed model has a more favorable computational complexity for prediction compared to the conventional k-nearest neighbor method.
- 12 January 2023
- Published by MDPI AG in Electronics
- Vol. 12 (2) , 402
Open AccessA Multidimensional Model for Recommendation Systems Based on Classification and Entropy
The proliferation of false and redundant information on e-commerce platforms as well as the prevalence of ineffective recommendations and other untrustworthy behaviors has seriously impeded the healthy development of these platforms. To address these issues and enhance prediction accuracy and user trust, contemporary recommendation systems often utilize additional information (i.e., side information). In this work, we propose a model to improve the recommendation quality by employing the information entropy of user-item ratings. The entropy was used as side information to reflect the global rating behavior of the user and item. We also utilized the classification of the user and item as heuristic information to improve the prediction quality. In our best result, we achieved a significant improvement of 8.2% in prediction accuracy. The model classified the items by the users’ actual preference, which is more trustworthy for users. We evaluated our model with three real-world datasets. The performance of our proposed model was significantly better than the other baseline methods. The similarity calculation method employed in the present model has the potential to mitigate the data sparsity problem associated with correlation-based similarity. The proposed weight matrix has zero sparsity. Furthermore, the proposed model has a more favorable computational complexity for prediction compared to the conventional k-nearest neighbor method.
- Open Access
Predicting Blood Glucose Concentration after Short-Acting Insulin Injection Using Discontinuous Injection Records
Diabetes is an increasingly common disease that poses an immense challenge to public health. Hyperglycemia is also a common complication in clinical patients in the intensive care unit, increasing the rate of infection and mortality. The accurate and real-time prediction of blood glucose concentrations after each short-acting insulin injection has great clinical significance and is the basis of all intelligent blood glucose control systems. Most previous prediction methods require long-term continuous blood glucose records from specific patients to train the prediction models, resulting in these methods not being used in clinical practice. In this study, we construct 13 deep neural networks with different architectures to atomically predict blood glucose concentrations after arbitrary independent insulin injections without requiring continuous historical records of any patient. Using our proposed models, the best root mean square error of the prediction results reaches 15.82 mg/dL, and 99.5% of the predictions are clinically acceptable, which is more accurate than previously proposed blood glucose prediction methods. Through the re-validation of the models, we demonstrate the clinical practicability and universal accuracy of our proposed prediction method.
Open AccessPredicting Blood Glucose Concentration after Short-Acting Insulin Injection Using Discontinuous Injection Records
Diabetes is an increasingly common disease that poses an immense challenge to public health. Hyperglycemia is also a common complication in clinical patients in the intensive care unit, increasing the rate of infection and mortality. The accurate and real-time prediction of blood glucose concentrations after each short-acting insulin injection has great clinical significance and is the basis of all intelligent blood glucose control systems. Most previous prediction methods require long-term continuous blood glucose records from specific patients to train the prediction models, resulting in these methods not being used in clinical practice. In this study, we construct 13 deep neural networks with different architectures to atomically predict blood glucose concentrations after arbitrary independent insulin injections without requiring continuous historical records of any patient. Using our proposed models, the best root mean square error of the prediction results reaches 15.82 mg/dL, and 99.5% of the predictions are clinically acceptable, which is more accurate than previously proposed blood glucose prediction methods. Through the re-validation of the models, we demonstrate the clinical practicability and universal accuracy of our proposed prediction method.
- Open Access
- 6 May 2022
- Published by MDPI AG in Electronics
- Vol. 11 (9) , 1495
Coronary Artery Disease Detection Model Based on Class Balancing Methods and LightGBM Algorithm
Coronary artery disease (CAD) is a disease with high mortality and disability. By 2019, there were 197 million CAD patients in the world. Additionally, the number of disability-adjusted life years (DALYs) owing to CAD reached 182 million. It is widely known that the early and accurate diagnosis of CAD is the most efficient method to reduce the damage of CAD. In medical practice, coronary angiography is considered to be the most reliable basis for CAD diagnosis. However, unfortunately, due to the limitation of inspection equipment and expert resources, many low- and middle-income countries do not have the ability to perform coronary angiography. This has led to a large loss of life and medical burden. Therefore, many researchers expect to realize the accurate diagnosis of CAD based on conventional medical examination data with the help of machine learning and data mining technology. The goal of this study is to propose a model for early, accurate and rapid detection of CAD based on common medical test data. This model took the classical logistic regression algorithm, which is the most commonly used in medical model research as the classifier. The advantages of feature selection and feature combination of tree models were used to solve the problem of manual feature engineering in logical regression. At the same time, in order to solve the class imbalance problem in Z-Alizadeh Sani dataset, five different class balancing methods were applied to balance the dataset. In addition, according to the characteristics of the dataset, we also adopted appropriate preprocessing methods. These methods significantly improved the classification performance of logistic regression classifier in terms of accuracy, recall, precision, F1 score, specificity and AUC when used for CAD detection. The best accuracy, recall, F1 score, precision, specificity and AUC were 94.7%, 94.8%, 94.8%, 95.3%, 94.5% and 0.98, respectively. Experiments and results have confirmed that, according to common medical examination data, our proposed model can accurately identify CAD patients in the early stage of CAD. Our proposed model can be used to help clinicians make diagnostic decisions in clinical practice.
- 6 May 2022
- Published by MDPI AG in Electronics
- Vol. 11 (9) , 1495
Open AccessCoronary Artery Disease Detection Model Based on Class Balancing Methods and LightGBM Algorithm
Coronary artery disease (CAD) is a disease with high mortality and disability. By 2019, there were 197 million CAD patients in the world. Additionally, the number of disability-adjusted life years (DALYs) owing to CAD reached 182 million. It is widely known that the early and accurate diagnosis of CAD is the most efficient method to reduce the damage of CAD. In medical practice, coronary angiography is considered to be the most reliable basis for CAD diagnosis. However, unfortunately, due to the limitation of inspection equipment and expert resources, many low- and middle-income countries do not have the ability to perform coronary angiography. This has led to a large loss of life and medical burden. Therefore, many researchers expect to realize the accurate diagnosis of CAD based on conventional medical examination data with the help of machine learning and data mining technology. The goal of this study is to propose a model for early, accurate and rapid detection of CAD based on common medical test data. This model took the classical logistic regression algorithm, which is the most commonly used in medical model research as the classifier. The advantages of feature selection and feature combination of tree models were used to solve the problem of manual feature engineering in logical regression. At the same time, in order to solve the class imbalance problem in Z-Alizadeh Sani dataset, five different class balancing methods were applied to balance the dataset. In addition, according to the characteristics of the dataset, we also adopted appropriate preprocessing methods. These methods significantly improved the classification performance of logistic regression classifier in terms of accuracy, recall, precision, F1 score, specificity and AUC when used for CAD detection. The best accuracy, recall, F1 score, precision, specificity and AUC were 94.7%, 94.8%, 94.8%, 95.3%, 94.5% and 0.98, respectively. Experiments and results have confirmed that, according to common medical examination data, our proposed model can accurately identify CAD patients in the early stage of CAD. Our proposed model can be used to help clinicians make diagnostic decisions in clinical practice.
- Open Access
- 27 January 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (3) , 1387
Causally Remove Negative Confound Effects of Size Metric for Software Defect Prediction
Software defect prediction technology can effectively detect potential defects in the software system. The most common method is to establish machine learning models based on software metrics for prediction. However, most of the prediction models are proposed without considering the confounding effects of size metric. The size metric has unexpected correlations with other software metrics and introduces biases into prediction results. Suitably removing these confounding effects to improve the prediction model’s performance is an issue that is still largely unexplored. This paper proposes a method that can causally remove the negative confounding effects of size metric. First, we quantify the confounding effects based on a causal graph. Then, we analyze each confounding effect to determine whether they are positive or negative, and only the negative confounding effects are removed. Extensive experimental results on eight data sets demonstrate the effectiveness of our proposed method. The prediction model’s performance can, in general, be improved after removing the negative confounding effects of size metric.
- 27 January 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (3) , 1387
Open AccessCausally Remove Negative Confound Effects of Size Metric for Software Defect Prediction
Software defect prediction technology can effectively detect potential defects in the software system. The most common method is to establish machine learning models based on software metrics for prediction. However, most of the prediction models are proposed without considering the confounding effects of size metric. The size metric has unexpected correlations with other software metrics and introduces biases into prediction results. Suitably removing these confounding effects to improve the prediction model’s performance is an issue that is still largely unexplored. This paper proposes a method that can causally remove the negative confounding effects of size metric. First, we quantify the confounding effects based on a causal graph. Then, we analyze each confounding effect to determine whether they are positive or negative, and only the negative confounding effects are removed. Extensive experimental results on eight data sets demonstrate the effectiveness of our proposed method. The prediction model’s performance can, in general, be improved after removing the negative confounding effects of size metric.
- Open Access
- 25 November 2021
- Published by MDPI AG in Applied Sciences
- Vol. 11 (23) , 11208
Reinforcement Learning for Options Trading
Reinforcement learning has been applied to various types of financial assets trading, such as stocks, futures, and cryptocurrencies. Options, as a novel kind of derivative, have their characteristics. Because there are too many option contracts for one underlying asset and their price behavior is different. Besides, the validity period of an option contract is relatively short. To apply reinforcement learning to options trading, we propose the options trading reinforcement learning (OTRL) framework. We use options’ underlying asset data to train the reinforcement learning model. Candle data in different time intervals are utilized, respectively. The protective closing strategy is added to the model to prevent unbearable losses. Our experiments demonstrate that the most stable algorithm for obtaining high returns is proximal policy optimization (PPO) with the protective closing strategy. The deep Q network (DQN) can exceed the buy and hold strategy in options trading, as can soft actor critic (SAC). The OTRL framework is verified effectively.
- 25 November 2021
- Published by MDPI AG in Applied Sciences
- Vol. 11 (23) , 11208
Open AccessReinforcement Learning for Options Trading
Reinforcement learning has been applied to various types of financial assets trading, such as stocks, futures, and cryptocurrencies. Options, as a novel kind of derivative, have their characteristics. Because there are too many option contracts for one underlying asset and their price behavior is different. Besides, the validity period of an option contract is relatively short. To apply reinforcement learning to options trading, we propose the options trading reinforcement learning (OTRL) framework. We use options’ underlying asset data to train the reinforcement learning model. Candle data in different time intervals are utilized, respectively. The protective closing strategy is added to the model to prevent unbearable losses. Our experiments demonstrate that the most stable algorithm for obtaining high returns is proximal policy optimization (PPO) with the protective closing strategy. The deep Q network (DQN) can exceed the buy and hold strategy in options trading, as can soft actor critic (SAC). The OTRL framework is verified effectively.
- Open Access
- 18 January 2021
- Published by MDPI AG in Electronics
- Vol. 10 (2) , 214
Improving the Prediction Quality in Memory-Based Collaborative Filtering Using Categorical Features
Despite years of evolution of recommender systems, improving prediction accuracy remains one of the core problems among researchers and industry. It is common to use side information to bolster the accuracy of recommender systems. In this work, we focus on using item categories, specifically movie genres, to improve the prediction accuracy as well as coverage, precision, and recall. We derive the user’s taste for an item using the ratings expressed. Similarly, using the collective ratings given to an item, we identify how much each item belongs to a certain genre. These two vectors are then combined to get a user-item-weight matrix. In contrast to the similarity-based weight matrix in memory-based collaborative filtering, we use user-item-weight to make predictions. The user-item-weights can be used to explain to users why certain items have been recommended. We evaluate our proposed method using three real-world datasets. The proposed model performs significantly better than the baseline methods. In addition, we use the user-item-weight matrix to alleviate the sparsity problem associated with correlation-based similarity. In addition to that, the proposed model has a better computational complexity for making predictions than the k-nearest neighbor (kNN) method.
- 18 January 2021
- Published by MDPI AG in Electronics
- Vol. 10 (2) , 214
Open AccessImproving the Prediction Quality in Memory-Based Collaborative Filtering Using Categorical Features
Despite years of evolution of recommender systems, improving prediction accuracy remains one of the core problems among researchers and industry. It is common to use side information to bolster the accuracy of recommender systems. In this work, we focus on using item categories, specifically movie genres, to improve the prediction accuracy as well as coverage, precision, and recall. We derive the user’s taste for an item using the ratings expressed. Similarly, using the collective ratings given to an item, we identify how much each item belongs to a certain genre. These two vectors are then combined to get a user-item-weight matrix. In contrast to the similarity-based weight matrix in memory-based collaborative filtering, we use user-item-weight to make predictions. The user-item-weights can be used to explain to users why certain items have been recommended. We evaluate our proposed method using three real-world datasets. The proposed model performs significantly better than the baseline methods. In addition, we use the user-item-weight matrix to alleviate the sparsity problem associated with correlation-based similarity. In addition to that, the proposed model has a better computational complexity for making predictions than the k-nearest neighbor (kNN) method.
- Open Access
- 27 August 2020
- Published by MDPI AG in Electronics
- Vol. 9 (9) , 1384
Using Data Augmentation Based Reinforcement Learning for Daily Stock Trading
In algorithmic trading, adequate training data set is key to making profits. However, stock trading data in units of a day can not meet the great demand for reinforcement learning. To address this problem, we proposed a framework named data augmentation based reinforcement learning (DARL) which uses minute-candle data (open, high, low, close) to train the agent. The agent is then used to guide daily stock trading. In this way, we can increase the instances of data available for training in hundreds of folds, which can substantially improve the reinforcement learning effect. But not all stocks are suitable for this kind of trading. Therefore, we propose an access mechanism based on skewness and kurtosis to select stocks that can be traded properly using this algorithm. In our experiment, we find proximal policy optimization (PPO) is the most stable algorithm to achieve high risk-adjusted returns. Deep Q-learning (DQN) and soft actor critic (SAC) can beat the market in Sharp Ratio.
- 27 August 2020
- Published by MDPI AG in Electronics
- Vol. 9 (9) , 1384
Open AccessUsing Data Augmentation Based Reinforcement Learning for Daily Stock Trading
In algorithmic trading, adequate training data set is key to making profits. However, stock trading data in units of a day can not meet the great demand for reinforcement learning. To address this problem, we proposed a framework named data augmentation based reinforcement learning (DARL) which uses minute-candle data (open, high, low, close) to train the agent. The agent is then used to guide daily stock trading. In this way, we can increase the instances of data available for training in hundreds of folds, which can substantially improve the reinforcement learning effect. But not all stocks are suitable for this kind of trading. Therefore, we propose an access mechanism based on skewness and kurtosis to select stocks that can be traded properly using this algorithm. In our experiment, we find proximal policy optimization (PPO) is the most stable algorithm to achieve high risk-adjusted returns. Deep Q-learning (DQN) and soft actor critic (SAC) can beat the market in Sharp Ratio.
- Open Access
- 16 October 2019
- Published by MDPI AG in Applied Sciences
- Vol. 9 (20) , 4378
Modeling Implicit Trust in Matrix Factorization-Based Collaborative Filtering
Recommendation systems often use side information to both alleviate problems, such as the cold start problem and data sparsity, and increase prediction accuracy. One such piece of side information, which has been widely investigated in addressing such challenges, is trust. However, the difficulty in obtaining explicit relationship data has led researchers to infer trust values from other means such as the user-to-item relationship. This paper proposes a model to improve prediction accuracy by applying the trust relationship between the user and item ratings. Two approaches to implement trust into prediction are proposed: One involves the use of estimated trust, and the other involves the initial trust. The efficiency of the proposed method is verified by comparing the obtained results with four well-known methods, including the state-of-the-art deep learning-based method of neural graph collaborative filtering (NGCF). The experimental results demonstrate that the proposed method performs significantly better than the NGCF, and the three other matrix factorization methods, namely, the singular value decomposition (SVD), SVD++, and the social matrix factorization (SocialMF).
- 16 October 2019
- Published by MDPI AG in Applied Sciences
- Vol. 9 (20) , 4378
Open AccessModeling Implicit Trust in Matrix Factorization-Based Collaborative Filtering
Recommendation systems often use side information to both alleviate problems, such as the cold start problem and data sparsity, and increase prediction accuracy. One such piece of side information, which has been widely investigated in addressing such challenges, is trust. However, the difficulty in obtaining explicit relationship data has led researchers to infer trust values from other means such as the user-to-item relationship. This paper proposes a model to improve prediction accuracy by applying the trust relationship between the user and item ratings. Two approaches to implement trust into prediction are proposed: One involves the use of estimated trust, and the other involves the initial trust. The efficiency of the proposed method is verified by comparing the obtained results with four well-known methods, including the state-of-the-art deep learning-based method of neural graph collaborative filtering (NGCF). The experimental results demonstrate that the proposed method performs significantly better than the NGCF, and the three other matrix factorization methods, namely, the singular value decomposition (SVD), SVD++, and the social matrix factorization (SocialMF).