Developing a predictive model for detecting cardiovascular diseases (CVDs) is crucial due to its high global fatality rate. With the advancements in artificial intelligence, the availability of large-scale data, and i...Developing a predictive model for detecting cardiovascular diseases (CVDs) is crucial due to its high global fatality rate. With the advancements in artificial intelligence, the availability of large-scale data, and increased access to computational capability, it is feasible to create robust models that can detect CVDs with high precision. This study aims to provide a promising method for early diagnosis by employing various machine learning and deep learning techniques, including logistic regression, decision trees, random forest classifier, extreme gradient boosting (XGBoost), and a sequential model from Keras. Our evaluation identifies the random forest classifier as the most effective model, achieving an accuracy of 0.91, surpassing other machine learning and deep learning approaches. Close behind are XGBoost (accuracy: 0.90), decision tree (accuracy: 0.86), and logistic regression (accuracy: 0.70). Additionally, our deep learning sequential model demonstrates promising classification performance, with an accuracy of 0.80 and a loss of 0.425 on the validation set. These findings underscore the potential of machine learning and deep learning methodologies in advancing cardiovascular disease prediction and management strategies.展开更多
The prediction of academic performance is one of the most important tasks in educational data mining, and has been widely studied in massive open online courses （MOOCs） and intelligent tutoring systems. Academic per...The prediction of academic performance is one of the most important tasks in educational data mining, and has been widely studied in massive open online courses （MOOCs） and intelligent tutoring systems. Academic performance can be affected by factors like personality, skills, social environment, and the use of library books. However, it is still less investigated about how the use of library books can affect the academic performance of college students and even leverage book-loan history for predicting academic performance. To this end, we propose a supervised content-aware matrix factorization for mutual reinforcement of academic performance prediction and library book recommendation. This model not only addresses the sparsity challenge by explainable dimension reduction techniques, but also quantifies the importance of library books in predicting academic performance. Finally, we evaluate the proposed model on three consecutive years of book-loan history and cumulative grade point average of 13 047 undergraduate students in one university. The results show that the proposed model outperforms the competing baselines on both tasks, and that academic performance not only is predictable from the book-loan history but also improves the recommendation of library books for students.展开更多
The use of a Traffic Matrix（TM） to describe the characteristics of a global network has attracted significant interest in network performance research. Due to the high dimensionality and sparsity of network traffic,...The use of a Traffic Matrix（TM） to describe the characteristics of a global network has attracted significant interest in network performance research. Due to the high dimensionality and sparsity of network traffic, Principal Component Analysis（PCA） has been successfully applied to TM analysis. PCA is one of the most common methods used in analysis of high-dimensional objects. This paper shows how to apply PCA to TM analysis and anomaly detection. The experiment results demonstrate that the PCA-based method can detect anomalies for both single and multiple nodes with high accuracy and efficiency.展开更多
文摘Developing a predictive model for detecting cardiovascular diseases (CVDs) is crucial due to its high global fatality rate. With the advancements in artificial intelligence, the availability of large-scale data, and increased access to computational capability, it is feasible to create robust models that can detect CVDs with high precision. This study aims to provide a promising method for early diagnosis by employing various machine learning and deep learning techniques, including logistic regression, decision trees, random forest classifier, extreme gradient boosting (XGBoost), and a sequential model from Keras. Our evaluation identifies the random forest classifier as the most effective model, achieving an accuracy of 0.91, surpassing other machine learning and deep learning approaches. Close behind are XGBoost (accuracy: 0.90), decision tree (accuracy: 0.86), and logistic regression (accuracy: 0.70). Additionally, our deep learning sequential model demonstrates promising classification performance, with an accuracy of 0.80 and a loss of 0.425 on the validation set. These findings underscore the potential of machine learning and deep learning methodologies in advancing cardiovascular disease prediction and management strategies.
基金This work was supported by the National Natural Science Foundation of China under Grant Nos. 61502077 and 61672483, and the Fundamental Research Funds for the Central Universities of China under Grant No. ZYGX2016J087.
文摘The prediction of academic performance is one of the most important tasks in educational data mining, and has been widely studied in massive open online courses （MOOCs） and intelligent tutoring systems. Academic performance can be affected by factors like personality, skills, social environment, and the use of library books. However, it is still less investigated about how the use of library books can affect the academic performance of college students and even leverage book-loan history for predicting academic performance. To this end, we propose a supervised content-aware matrix factorization for mutual reinforcement of academic performance prediction and library book recommendation. This model not only addresses the sparsity challenge by explainable dimension reduction techniques, but also quantifies the importance of library books in predicting academic performance. Finally, we evaluate the proposed model on three consecutive years of book-loan history and cumulative grade point average of 13 047 undergraduate students in one university. The results show that the proposed model outperforms the competing baselines on both tasks, and that academic performance not only is predictable from the book-loan history but also improves the recommendation of library books for students.
基金supported by the National Natural Science Foundation of China (No. 61100218)
文摘The use of a Traffic Matrix（TM） to describe the characteristics of a global network has attracted significant interest in network performance research. Due to the high dimensionality and sparsity of network traffic, Principal Component Analysis（PCA） has been successfully applied to TM analysis. PCA is one of the most common methods used in analysis of high-dimensional objects. This paper shows how to apply PCA to TM analysis and anomaly detection. The experiment results demonstrate that the PCA-based method can detect anomalies for both single and multiple nodes with high accuracy and efficiency.
