Recently,online learning platforms have proven to help people gain knowledge more conveniently.Since the outbreak of COVID-19 in 2020,online learning has become a mainstream mode,as many schools have adopted its forma...Recently,online learning platforms have proven to help people gain knowledge more conveniently.Since the outbreak of COVID-19 in 2020,online learning has become a mainstream mode,as many schools have adopted its format.The platforms are able to capture substantial data relating to the students’learning activities,which could be analyzed to determine relationships between learning behaviors and study habits.As such,an intelligent analysis method is needed to process efficiently this high volume of information.Clustering is an effect data mining method which discover data distribution and hidden characteristic from uncharacterized online learning data.This study proposes a clustering algorithm based on brain storm optimization(CBSO)to categorize students according to their learning behaviors and determine their characteristics.This enables teaching to be tailored to taken into account those results,thereby,improving the education quality over time.Specifically,we use the individual of CBSO to represent the distribution of students and find the optimal one by the operations of convergence and divergence.The experiments are performed on the 104 students’online learning data,and the results show that CBSO is feasible and efficient.展开更多
AIM： To use the cumulative sum analysis score（CUSUM） to construct objectively the learning curve of phacoemulsification competency.METHODS： Three second-year residents and an experienced consultant were monitored ...AIM： To use the cumulative sum analysis score（CUSUM） to construct objectively the learning curve of phacoemulsification competency.METHODS： Three second-year residents and an experienced consultant were monitored for a series of 70 phacoemulsification cases each and had their series analysed by CUSUM regarding posterior capsule rupture（PCR） and best-corrected visual acuity. The acceptable rate for PCR was 〈5%（lower limit h） and the unacceptable rate was 〉10%（upper limit h）. The acceptable rate for bestcorrected visual acuity worse than 20/40 was 〈10%（lower limit h） and the unacceptable rate was 〉20%（upper limit h）. The area between lower limit h and upper limit h is called the decision interval. RESULTS： There was no statistically significant difference in the mean age, sex or cataract grades between groups. The first trainee achieved PCR CUSUM competency at his 22 nd case. His best-corrected visual acuity CUSUM was in the decision interval from his third case and stayed there until the end, never reaching competency. The second trainee achieved PCR CUSUM competency at his 39^ th case. He could reach best-corrected visual acuity CUSUM competency at his 22 ^nd case. The third trainee achieved PCR CUSUM competency at his 41 st case. He reached bestcorrected visual acuity CUSUM competency at his 14 ^th case.CONCLUSION： The learning curve of competency in phacoemulsification is constructed by CUSUM and in average took 38 cases for each trainee to achieve it.展开更多
The global growth of the Internet and the rapid expansion of social networks such as Facebook make multilingual sentiment analysis of social media content very necessary. This paper performs the first sentiment analys...The global growth of the Internet and the rapid expansion of social networks such as Facebook make multilingual sentiment analysis of social media content very necessary. This paper performs the first sentiment analysis on code-mixed Bambara-French Facebook comments. We develop four Long Short-term Memory（LSTM）-based models and two Convolutional Neural Network（CNN）-based models, and use these six models, Na？ve Bayes, and Support Vector Machines（SVM） to conduct experiments on a constituted dataset. Social media text written in Bambara is scarce. To mitigate this weakness, this paper uses dictionaries of character and word indexes to produce character and word embedding in place of pre-trained word vectors. We investigate the effect of comment length on the models and perform a comparison among them. The best performing model is a one-layer CNN deep learning model with an accuracy of 83.23 %.展开更多
Dear Sir,Iam Dr.Kavitha S,from the Department of Electronics and Communication Engineering,Nandha Engineering College,Erode,Tamil Nadu,India.I write to present the detection of glaucoma using extreme learning machine(...Dear Sir,Iam Dr.Kavitha S,from the Department of Electronics and Communication Engineering,Nandha Engineering College,Erode,Tamil Nadu,India.I write to present the detection of glaucoma using extreme learning machine(ELM)and fractal feature analysis.Glaucoma is the second most frequent cause of permanent blindness in industrial展开更多
This study investigated the Chinese learning motivation,learning goals and learning strategies of 26 international students majoring in MBA and MPA at a university with The belt and road college,mainly by questionnair...This study investigated the Chinese learning motivation,learning goals and learning strategies of 26 international students majoring in MBA and MPA at a university with The belt and road college,mainly by questionnaire and interview method,supplemented by classroom observation method.The survey found that 20 of the 24 international students were zero-start Chinese learners,and their learning motivation was mainly"instrumental"and"intrinsic",and they had high enthusiasm for Chinese language and Chinese culture.They have a high enthusiasm for Chinese language and culture,and will actively solve the difficulties they encounter in learning Chinese.At the same time,this study conducted a questionnaire survey on the needs of international students in terms of curriculum and content,teaching materials,teaching assessment and extracurricular activities,combined with the results of individual and group interviews and classroom observations,to summarize the real needs of international students in various aspects of Chinese language learning,so as to provide teaching reference for teachers teaching international students,and to provide a reference for colleges and universities to develop Chinese teaching programs.The survey will provide a basis for the colleges and universities to formulate Chinese teaching programs and coordinate teaching activities,so as to help international students learn Chinese better.展开更多
This study innovatively built an intelligent analysis platform for learning behavior,which deeply integrated the cutting-edge technology of big data and Artificial Intelligence(AI),\mined and analyzed students’learni...This study innovatively built an intelligent analysis platform for learning behavior,which deeply integrated the cutting-edge technology of big data and Artificial Intelligence(AI),\mined and analyzed students’learning data,and realized the personalized customization of learning resources and the accurate matching of intelligent learning partners.With the help of advanced algorithms and multi-dimensional data fusion strategies,the platform not only promotes positive interaction and collaboration in the learning environment but also provides teachers with comprehensive and in-depth students’learning portraits,which provides solid support for the implementation of precision education and the personalized adjustment of teaching strategies.In this study,a recommender system based on user similarity evaluation and a collaborative filtering mechanism is carefully designed,and its technical architecture and implementation process are described in detail.展开更多
This study presents a data-driven approach to predict tailplane aerodynamics in icing conditions,supporting the ice-tolerant design of aircraft horizontal stabilizers.The core of this work is a low-cost predictive mod...This study presents a data-driven approach to predict tailplane aerodynamics in icing conditions,supporting the ice-tolerant design of aircraft horizontal stabilizers.The core of this work is a low-cost predictive model for analyzing icing effects on swept tailplanes.The method relies on a multi-fidelity data gathering campaign,enabling seamless integration into multidisciplinary aircraft design workflows.A dataset of iced airfoil shapes was generated using 2D inviscid methods across various flight conditions.High-fidelity CFD simulations were conducted on both clean and iced geometries,forming a multidimensional aerodynamic database.This 2D database feeds a nonlinear vortex lattice method to estimate 3D aerodynamic characteristics,following a'quasi-3D'approach.The resulting reduced-order model delivers fast aerodynamic performance estimates of iced tailplanes.To demonstrate its effectiveness,optimal ice-tolerant tailplane designs were selected from a range of feasible shapes based on a reference transport aircraft.The analysis validates the model's reliability,accuracy,and limitations concerning 3D ice shapes and aerodynamic characteristics.Most notably,the model offers near-zero computational cost compared to high-fidelity simulations,making it a valuable tool for efficient aircraft design.展开更多
External factors, such as social media and financial news, can have wide-spread effects on stock price movement. For this reason, social media is considered a useful resource for precise market predictions. In this pa...External factors, such as social media and financial news, can have wide-spread effects on stock price movement. For this reason, social media is considered a useful resource for precise market predictions. In this paper, we show the effectiveness of using Twitter posts to predict stock prices. We start by training various models on the Sentiment 140 Twitter data. We found that Support Vector Machines (SVM) performed best (0.83 accuracy) in the sentimental analysis, so we used it to predict the average sentiment of tweets for each day that the market was open. Next, we use the sentimental analysis of one year’s data of tweets that contain the “stock market”, “stocktwits”, “AAPL” keywords, with the goal of predicting the corresponding stock prices of Apple Inc. (AAPL) and the US’s Dow Jones Industrial Average (DJIA) index prices. Two models, Boosted Regression Trees and Multilayer Perceptron Neural Networks were used to predict the closing price difference of AAPL and DJIA prices. We show that neural networks perform substantially better than traditional models for stocks’ price prediction.展开更多
The vast amount of data generated by large-scale open online course platforms provide a solid foundation for the analysis of learning behavior in the field of education.This study utilizes the historical and final lea...The vast amount of data generated by large-scale open online course platforms provide a solid foundation for the analysis of learning behavior in the field of education.This study utilizes the historical and final learning behavior data of over 300000 learners from 17 courses offered on the edX platform by Harvard University and the Massachusetts Institute of Technology during the 2012-2013 academic year.We have developed a spike neural network to predict learning outcomes,and analyzed the correlation between learning behavior and outcomes,aiming to identify key learning behaviors that significantly impact these outcomes.Our goal is to monitor learning progress,provide targeted references for evaluating and improving learning effectiveness,and implement intervention measures promptly.Experimental results demonstrate that the prediction model based on online learning behavior using spiking neural network achieves an impressive accuracy of 99.80%.The learning behaviors that predominantly affect learning effectiveness are found to be students’academic performance and level of participation.展开更多
AIM： To study a more accurate quantification of hepatic fibrosis which would provide dinically useful information for monitoring the progression of chronic liver disease. METHODS： Using a cDNA microarray containing ...AIM： To study a more accurate quantification of hepatic fibrosis which would provide dinically useful information for monitoring the progression of chronic liver disease. METHODS： Using a cDNA microarray containing over 22000 clones, we analyzed the gene-expression profiles of non-cancerous liver in 74 patients who underwent hepatic resection. We calculated the ratio of azanstained： total area, and determined the morphologic fibrosis index （MFI）, as a mean of 9 section-images. We used the MFI as a reference standard to evaluate our method for assessing liver fibrosis. RESULTS： We identified 39 genes that collectively showed a good correlation （r 〉 0.50） between geneexpression and the severity of liver fibrosis. Many of the identified genes were involved in immune responses and cell signaling. To quantify the extent of liver fibrosis, we developed a new genetic fibrosis index （GFI） based on gene-expression profiling of 4 clones using a linear support vector regression analysis. This technique, based on a supervised learning analysis, correctly quantified the various degrees of fibrosis in both 74 training samples （r = 0.76, 2.2% vs 2.8%, P 〈 0.0001） and 12 independent additional test samples （r = 0.75, 9.8% vs 8.6%, P 〈 0.005）. It was far better in assessing liver fibrosis than blood markers such as prothrombin time （r = -0.53）, type IV collagen 7s （r = 0.48）, hyaluronic acid （r = 0.41）, and aspartate aminotransferase to platelets ratio index （APRI） （r = 0.38）. CONCLUSION： Our cDNA microarray-based strategy may help clinicians to precisely and objectively monitor the severity of liver fibrosis.展开更多
Air traffic complexity is an objective metric for evaluating the operational condition of the airspace. It has several applications, such as airspace design and traffic flow management.Therefore, identifying a reliabl...Air traffic complexity is an objective metric for evaluating the operational condition of the airspace. It has several applications, such as airspace design and traffic flow management.Therefore, identifying a reliable method to accurately measure traffic complexity is important. Considering that many factors correlate with traffic complexity in complicated nonlinear ways,researchers have proposed several complexity evaluation methods based on machine learning models which were trained with large samples. However, the high cost of sample collection usually results in limited training set. In this paper, an ensemble learning model is proposed for measuring air traffic complexity within a sector based on small samples. To exploit the classification information within each factor, multiple diverse factor subsets（FSSs） are generated under guidance from factor noise and independence analysis. Then, a base complexity evaluator is built corresponding to each FSS. The final complexity evaluation result is obtained by integrating all results from the base evaluators. Experimental studies using real-world air traffic operation data demonstrate the advantages of our model for small-sample-based traffic complexity evaluation over other stateof-the-art methods.展开更多
With the explosive increase in mobile apps, more and more threats migrate from traditional PC client to mobile device. Compared with traditional Win＋Intel alliance in PC, Android＋ARM alliance dominates in Mobile Int...With the explosive increase in mobile apps, more and more threats migrate from traditional PC client to mobile device. Compared with traditional Win＋Intel alliance in PC, Android＋ARM alliance dominates in Mobile Internet, the apps replace the PC client software as the major target of malicious usage. In this paper, to improve the security status of current mobile apps, we propose a methodology to evaluate mobile apps based on cloud computing platform and data mining. We also present a prototype system named MobSafe to identify the mobile app＇s virulence or benignancy. Compared with traditional method, such as permission pattern based method, MobSafe combines the dynamic and static analysis methods to comprehensively evaluate an Android app. In the implementation, we adopt Android Security Evaluation Framework （ASEF） and Static Android Analysis Framework （SAAF）, the two representative dynamic and static analysis methods, to evaluate the Android apps and estimate the total time needed to evaluate all the apps stored in one mobile app market. Based on the real trace from a commercial mobile app market called AppChina, we can collect the statistics of the number of active Android apps, the average number apps installed in one Android device, and the expanding ratio of mobile apps. As mobile app market serves as the main line of defence against mobile malwares, our evaluation results show that it is practical to use cloud computing platform and data mining to verify all stored apps routinely to filter out malware apps from mobile app markets. As the future work, MobSafe can extensively use machine learning to conduct automotive forensic analysis of mobile apps based on the generated multifaceted data in this stage.展开更多
Predictive maintenance is essential for the implementation of an innovative and efficient structural health monitoring strategy.Models capable of accurately interpreting new data automatically collected by suitably pl...Predictive maintenance is essential for the implementation of an innovative and efficient structural health monitoring strategy.Models capable of accurately interpreting new data automatically collected by suitably placed sensors to assess the state of the infrastructure represent a fundamental step,particularly for the railway sector,whose safe and continuous operation plays a strategic role in the well-being and development of nations.In this scenario,the benefits of a digital twin of a bonded insu-lated rail joint(IRJ)with the predictive capabilities of advanced classification algorithms based on artificial intelligence have been explored.The digital model provides an accurate mechanical response of the infrastructure as a pair of wheels passes over the joint.As bolt preload conditions vary,four structural health classes were identified for the joint.Two parameters,i.e.gap value and vertical displacement,which are strongly correlated with bolt preload,are used in different combinations to train and test five predictive classifiers.Their classification effectiveness was assessed using several performance indica-tors.Finally,we compared the IRJ condition predictions of two trained classifiers with the available data,confirming their high accuracy.The approach presented provides an interesting solution for future predictive tools in SHM especially in the case of complex systems such as railways where the vehicle-infrastructure interaction is complex and always time varying.展开更多
Gene expression is a critical process in biological system that is influenced and modulated by many factors including genetic variation. Expression Quantitative Trait Loci（e QTL） analysis provides a powerful way to ...Gene expression is a critical process in biological system that is influenced and modulated by many factors including genetic variation. Expression Quantitative Trait Loci（e QTL） analysis provides a powerful way to understand how genetic variants affect gene expression. For genome wide e QTL analysis, the number of genetic variants and that of genes are large and thus the search space is tremendous. Therefore, e QTL analysis brings about computational and statistical challenges. In this paper, we provide a comprehensive review of recent advances in methods for e QTL analysis in population-based studies. We first present traditional pairwise association methods, which are widely used in human genetics. To account for expression heterogeneity, we investigate the methods for correcting confounding factors. Next, we discuss newly developed statistical learning methods including Lasso-based models. In the conclusion, we provide an overview of future method development in analyzing e QTL associations. Although we focus on human genetics in this review, the methods are applicable to many other organisms.展开更多
The analysis on the learning behavior characteristics based on big data is beneficial for improving the learning resource construction,teaching mode and interactive mode of online course platforms.Multiple aspects of ...The analysis on the learning behavior characteristics based on big data is beneficial for improving the learning resource construction,teaching mode and interactive mode of online course platforms.Multiple aspects of analysis were conducted on nearly three million pieces of learning behavior data,which is from seven courses of 3,315 learners in the same major at a university.According to the quantity of course resources and policy of course scoring,four typical learning behaviors were selected,and the correlation between final exam results and learning behavior were analyzed.The analysis of behavior influences on the final exam results were also conducted.The analytical results give suggestions for online teaching and learning.展开更多
Personalized education,tailored to individual stu-dent needs,leverages educational technology and artificial intelligence(AI)in the digital age to enhance learning ef-fectiveness.The integration of AI in educational p...Personalized education,tailored to individual stu-dent needs,leverages educational technology and artificial intelligence(AI)in the digital age to enhance learning ef-fectiveness.The integration of AI in educational platforms provides insights into academic performance,learning pref-erences,and behaviors,optimizing the personal learning process.Driven by data mining techniques,it not only ben-efits students but also provides educators and institutions with tools to craft customized learning experiences.To offer a comprehensive review of recent advancements in person-alized educational data mining,this paper focuses on four primary scenarios:educational recommendation,cogni-tive diagnosis,knowledge tracing,and learning analysis.This paper presents a structured taxonomy for each area,compiles commonly used datasets,and identifies future re-search directions,emphasizing the role of data mining in enhancing personalized education and paving the way for future exploration and innovation.展开更多
Purpose-The objective is to develop a more effective model that simplifies and accelerates the news classification process using advanced text mining and deep learning(DL)techniques.A distributed framework utilizing B...Purpose-The objective is to develop a more effective model that simplifies and accelerates the news classification process using advanced text mining and deep learning(DL)techniques.A distributed framework utilizing Bidirectional Encoder Representations from Transformers(BERT)was developed to classify news headlines.This approach leverages various text mining and DL techniques on a distributed infrastructure,aiming to offer an alternative to traditional news classification methods.Design/methodology/approach-This study focuses on the classification of distinct types of news by analyzing tweets from various news channels.It addresses the limitations of using benchmark datasets for news classification,which often result in models that are impractical for real-world applications.Findings-The framework’s effectiveness was evaluated on a newly proposed dataset and two additional benchmark datasets from the Kaggle repository,assessing the performance of each text mining and classification method across these datasets.The results of this study demonstrate that the proposed strategy significantly outperforms other approaches in terms of accuracy and execution time.This indicates that the distributed framework,coupled with the use of BERT for text analysis,provides a robust solution for analyzing large volumes of data efficiently.The findings also highlight the value of the newly released corpus for further research in news classification and emotion classification,suggesting its potential to facilitate advancements in these areas.Originality/value-This research introduces an innovative distributed framework for news classification that addresses the shortcomings of models trained on benchmark datasets.By utilizing cutting-edge techniques and a novel dataset,the study offers significant improvements in accuracy and processing speed.The release of the corpus represents a valuable contribution to the field,enabling further exploration into news and emotion classification.This work sets a new standard for the analysis of news data,offering practical implications for the development of more effective and efficient news classification systems.展开更多
Background:There is an unmet need for accurate non-invasive methods to diagnose non-alcoholic steatohepatitis(NASH).Since impedance-based measurements of body composition are simple,repeatable and have a strong associ...Background:There is an unmet need for accurate non-invasive methods to diagnose non-alcoholic steatohepatitis(NASH).Since impedance-based measurements of body composition are simple,repeatable and have a strong association with non-alcoholic fatty liver disease(NAFLD)severity,we aimed to develop a novel and fully automatic machine learning algorithm,consisting of a deep neural network based on impedance-based measurements of body composition to identify NASH[the bioeLectrical impEdance Analysis foR Nash(LEARN)algorithm].Methods:A total of 1,259 consecutive subjects with suspected NAFLD were screened from six medical centers across China,of which 766 patients with biopsy-proven NAFLD were included in final analysis.These patients were randomly subdivided into the training and validation groups,in a ratio of 4:1.The LEARN algorithm was developed in the training group to identify NASH,and subsequently,tested in the validation group.Results:The LEARN algorithm utilizing impedance-based measurements of body composition along with age,sex,pre-existing hypertension and diabetes,was able to predict the likelihood of having NASH.This algorithm showed good discriminatory ability for identifying NASH in both the training and validation groups[area under the receiver operating characteristics(AUROC):0.81,95%CI:0.77-0.84 and AUROC:0.80,95%CI:0.73-0.87,respectively].This algorithm also performed better than serum cytokeratin-18 neoepitope M30(CK-18 M30)level or other non-invasive NASH scores(including HAIR,ION,NICE)for identifying NASH(P value<0.001).Additionally,the LEARN algorithm performed well in identifying NASH in different patient subgroups,as well as in subjects with partial missing body composition data.Conclusions:The LEARN algorithm,utilizing simple easily obtained measures,provides a fully automated,simple,non-invasive method for identifying NASH.展开更多
基金This work was partially supported by the National Natural Science Foundation of China(61876089,61876185,61902281,61375121)the Opening Project of Jiangsu Key Laboratory of Data Science and Smart Software(No.2019DS301)+1 种基金the Engineering Research Center of Digital Forensics,Ministry of Education,the Key Research and Development Program of Jiangsu Province(BE2020633)the Priority Academic Program Development of Jiangsu Higher Education Institutions.
文摘Recently,online learning platforms have proven to help people gain knowledge more conveniently.Since the outbreak of COVID-19 in 2020,online learning has become a mainstream mode,as many schools have adopted its format.The platforms are able to capture substantial data relating to the students’learning activities,which could be analyzed to determine relationships between learning behaviors and study habits.As such,an intelligent analysis method is needed to process efficiently this high volume of information.Clustering is an effect data mining method which discover data distribution and hidden characteristic from uncharacterized online learning data.This study proposes a clustering algorithm based on brain storm optimization(CBSO)to categorize students according to their learning behaviors and determine their characteristics.This enables teaching to be tailored to taken into account those results,thereby,improving the education quality over time.Specifically,we use the individual of CBSO to represent the distribution of students and find the optimal one by the operations of convergence and divergence.The experiments are performed on the 104 students’online learning data,and the results show that CBSO is feasible and efficient.
文摘AIM： To use the cumulative sum analysis score（CUSUM） to construct objectively the learning curve of phacoemulsification competency.METHODS： Three second-year residents and an experienced consultant were monitored for a series of 70 phacoemulsification cases each and had their series analysed by CUSUM regarding posterior capsule rupture（PCR） and best-corrected visual acuity. The acceptable rate for PCR was 〈5%（lower limit h） and the unacceptable rate was 〉10%（upper limit h）. The acceptable rate for bestcorrected visual acuity worse than 20/40 was 〈10%（lower limit h） and the unacceptable rate was 〉20%（upper limit h）. The area between lower limit h and upper limit h is called the decision interval. RESULTS： There was no statistically significant difference in the mean age, sex or cataract grades between groups. The first trainee achieved PCR CUSUM competency at his 22 nd case. His best-corrected visual acuity CUSUM was in the decision interval from his third case and stayed there until the end, never reaching competency. The second trainee achieved PCR CUSUM competency at his 39^ th case. He could reach best-corrected visual acuity CUSUM competency at his 22 ^nd case. The third trainee achieved PCR CUSUM competency at his 41 st case. He reached bestcorrected visual acuity CUSUM competency at his 14 ^th case.CONCLUSION： The learning curve of competency in phacoemulsification is constructed by CUSUM and in average took 38 cases for each trainee to achieve it.
基金Supported by the National Natural Science Foundation of China(61272451,61572380,61772383 and 61702379)the Major State Basic Research Development Program of China(2014CB340600)
文摘The global growth of the Internet and the rapid expansion of social networks such as Facebook make multilingual sentiment analysis of social media content very necessary. This paper performs the first sentiment analysis on code-mixed Bambara-French Facebook comments. We develop four Long Short-term Memory（LSTM）-based models and two Convolutional Neural Network（CNN）-based models, and use these six models, Na？ve Bayes, and Support Vector Machines（SVM） to conduct experiments on a constituted dataset. Social media text written in Bambara is scarce. To mitigate this weakness, this paper uses dictionaries of character and word indexes to produce character and word embedding in place of pre-trained word vectors. We investigate the effect of comment length on the models and perform a comparison among them. The best performing model is a one-layer CNN deep learning model with an accuracy of 83.23 %.
文摘Dear Sir,Iam Dr.Kavitha S,from the Department of Electronics and Communication Engineering,Nandha Engineering College,Erode,Tamil Nadu,India.I write to present the detection of glaucoma using extreme learning machine(ELM)and fractal feature analysis.Glaucoma is the second most frequent cause of permanent blindness in industrial
文摘This study investigated the Chinese learning motivation,learning goals and learning strategies of 26 international students majoring in MBA and MPA at a university with The belt and road college,mainly by questionnaire and interview method,supplemented by classroom observation method.The survey found that 20 of the 24 international students were zero-start Chinese learners,and their learning motivation was mainly"instrumental"and"intrinsic",and they had high enthusiasm for Chinese language and Chinese culture.They have a high enthusiasm for Chinese language and culture,and will actively solve the difficulties they encounter in learning Chinese.At the same time,this study conducted a questionnaire survey on the needs of international students in terms of curriculum and content,teaching materials,teaching assessment and extracurricular activities,combined with the results of individual and group interviews and classroom observations,to summarize the real needs of international students in various aspects of Chinese language learning,so as to provide teaching reference for teachers teaching international students,and to provide a reference for colleges and universities to develop Chinese teaching programs.The survey will provide a basis for the colleges and universities to formulate Chinese teaching programs and coordinate teaching activities,so as to help international students learn Chinese better.
文摘This study innovatively built an intelligent analysis platform for learning behavior,which deeply integrated the cutting-edge technology of big data and Artificial Intelligence(AI),\mined and analyzed students’learning data,and realized the personalized customization of learning resources and the accurate matching of intelligent learning partners.With the help of advanced algorithms and multi-dimensional data fusion strategies,the platform not only promotes positive interaction and collaboration in the learning environment but also provides teachers with comprehensive and in-depth students’learning portraits,which provides solid support for the implementation of precision education and the personalized adjustment of teaching strategies.In this study,a recommender system based on user similarity evaluation and a collaborative filtering mechanism is carefully designed,and its technical architecture and implementation process are described in detail.
基金funding from the Department of Industrial Engineering,University of Naples FedericoⅡ,Italy。
文摘This study presents a data-driven approach to predict tailplane aerodynamics in icing conditions,supporting the ice-tolerant design of aircraft horizontal stabilizers.The core of this work is a low-cost predictive model for analyzing icing effects on swept tailplanes.The method relies on a multi-fidelity data gathering campaign,enabling seamless integration into multidisciplinary aircraft design workflows.A dataset of iced airfoil shapes was generated using 2D inviscid methods across various flight conditions.High-fidelity CFD simulations were conducted on both clean and iced geometries,forming a multidimensional aerodynamic database.This 2D database feeds a nonlinear vortex lattice method to estimate 3D aerodynamic characteristics,following a'quasi-3D'approach.The resulting reduced-order model delivers fast aerodynamic performance estimates of iced tailplanes.To demonstrate its effectiveness,optimal ice-tolerant tailplane designs were selected from a range of feasible shapes based on a reference transport aircraft.The analysis validates the model's reliability,accuracy,and limitations concerning 3D ice shapes and aerodynamic characteristics.Most notably,the model offers near-zero computational cost compared to high-fidelity simulations,making it a valuable tool for efficient aircraft design.
文摘External factors, such as social media and financial news, can have wide-spread effects on stock price movement. For this reason, social media is considered a useful resource for precise market predictions. In this paper, we show the effectiveness of using Twitter posts to predict stock prices. We start by training various models on the Sentiment 140 Twitter data. We found that Support Vector Machines (SVM) performed best (0.83 accuracy) in the sentimental analysis, so we used it to predict the average sentiment of tweets for each day that the market was open. Next, we use the sentimental analysis of one year’s data of tweets that contain the “stock market”, “stocktwits”, “AAPL” keywords, with the goal of predicting the corresponding stock prices of Apple Inc. (AAPL) and the US’s Dow Jones Industrial Average (DJIA) index prices. Two models, Boosted Regression Trees and Multilayer Perceptron Neural Networks were used to predict the closing price difference of AAPL and DJIA prices. We show that neural networks perform substantially better than traditional models for stocks’ price prediction.
文摘The vast amount of data generated by large-scale open online course platforms provide a solid foundation for the analysis of learning behavior in the field of education.This study utilizes the historical and final learning behavior data of over 300000 learners from 17 courses offered on the edX platform by Harvard University and the Massachusetts Institute of Technology during the 2012-2013 academic year.We have developed a spike neural network to predict learning outcomes,and analyzed the correlation between learning behavior and outcomes,aiming to identify key learning behaviors that significantly impact these outcomes.Our goal is to monitor learning progress,provide targeted references for evaluating and improving learning effectiveness,and implement intervention measures promptly.Experimental results demonstrate that the prediction model based on online learning behavior using spiking neural network achieves an impressive accuracy of 99.80%.The learning behaviors that predominantly affect learning effectiveness are found to be students’academic performance and level of participation.
基金Supported partly by Grants-in-Aid for Scientific Research (S) (17109013) and for Scientific Research (C) (17591411 and 15591411)a Health and Labor Sciences Research Grant on Hepatitis and BSE (14230801)the Uehara Memorial Foundation, Yasuda Medical Research Foundation, Japanese Foundation for Multidisciplinary Treatment of Cancer, and Princes Takamatsu Cancer research Fund
文摘AIM： To study a more accurate quantification of hepatic fibrosis which would provide dinically useful information for monitoring the progression of chronic liver disease. METHODS： Using a cDNA microarray containing over 22000 clones, we analyzed the gene-expression profiles of non-cancerous liver in 74 patients who underwent hepatic resection. We calculated the ratio of azanstained： total area, and determined the morphologic fibrosis index （MFI）, as a mean of 9 section-images. We used the MFI as a reference standard to evaluate our method for assessing liver fibrosis. RESULTS： We identified 39 genes that collectively showed a good correlation （r 〉 0.50） between geneexpression and the severity of liver fibrosis. Many of the identified genes were involved in immune responses and cell signaling. To quantify the extent of liver fibrosis, we developed a new genetic fibrosis index （GFI） based on gene-expression profiling of 4 clones using a linear support vector regression analysis. This technique, based on a supervised learning analysis, correctly quantified the various degrees of fibrosis in both 74 training samples （r = 0.76, 2.2% vs 2.8%, P 〈 0.0001） and 12 independent additional test samples （r = 0.75, 9.8% vs 8.6%, P 〈 0.005）. It was far better in assessing liver fibrosis than blood markers such as prothrombin time （r = -0.53）, type IV collagen 7s （r = 0.48）, hyaluronic acid （r = 0.41）, and aspartate aminotransferase to platelets ratio index （APRI） （r = 0.38）. CONCLUSION： Our cDNA microarray-based strategy may help clinicians to precisely and objectively monitor the severity of liver fibrosis.
基金co-supported by the State Key Program of National Natural Science Foundation of China (No. 91538204)the National Science Fund for Distinguished Young Scholars (No. 61425014)the National Key Technologies R&D Program of China (No. 2015BAG15B01)
文摘Air traffic complexity is an objective metric for evaluating the operational condition of the airspace. It has several applications, such as airspace design and traffic flow management.Therefore, identifying a reliable method to accurately measure traffic complexity is important. Considering that many factors correlate with traffic complexity in complicated nonlinear ways,researchers have proposed several complexity evaluation methods based on machine learning models which were trained with large samples. However, the high cost of sample collection usually results in limited training set. In this paper, an ensemble learning model is proposed for measuring air traffic complexity within a sector based on small samples. To exploit the classification information within each factor, multiple diverse factor subsets（FSSs） are generated under guidance from factor noise and independence analysis. Then, a base complexity evaluator is built corresponding to each FSS. The final complexity evaluation result is obtained by integrating all results from the base evaluators. Experimental studies using real-world air traffic operation data demonstrate the advantages of our model for small-sample-based traffic complexity evaluation over other stateof-the-art methods.
基金the National Key Basic Research and Development (973) Program of China (Nos. 2012CB315801 and 2011CB302805)the National Natural Science Foundation of China (Nos. 61161140320 and 61233016)Intel Research Council with the title of Security Vulnerability Analysis based on Cloud Platform with Intel IA Architecture
文摘With the explosive increase in mobile apps, more and more threats migrate from traditional PC client to mobile device. Compared with traditional Win＋Intel alliance in PC, Android＋ARM alliance dominates in Mobile Internet, the apps replace the PC client software as the major target of malicious usage. In this paper, to improve the security status of current mobile apps, we propose a methodology to evaluate mobile apps based on cloud computing platform and data mining. We also present a prototype system named MobSafe to identify the mobile app＇s virulence or benignancy. Compared with traditional method, such as permission pattern based method, MobSafe combines the dynamic and static analysis methods to comprehensively evaluate an Android app. In the implementation, we adopt Android Security Evaluation Framework （ASEF） and Static Android Analysis Framework （SAAF）, the two representative dynamic and static analysis methods, to evaluate the Android apps and estimate the total time needed to evaluate all the apps stored in one mobile app market. Based on the real trace from a commercial mobile app market called AppChina, we can collect the statistics of the number of active Android apps, the average number apps installed in one Android device, and the expanding ratio of mobile apps. As mobile app market serves as the main line of defence against mobile malwares, our evaluation results show that it is practical to use cloud computing platform and data mining to verify all stored apps routinely to filter out malware apps from mobile app markets. As the future work, MobSafe can extensively use machine learning to conduct automotive forensic analysis of mobile apps based on the generated multifaceted data in this stage.
文摘Predictive maintenance is essential for the implementation of an innovative and efficient structural health monitoring strategy.Models capable of accurately interpreting new data automatically collected by suitably placed sensors to assess the state of the infrastructure represent a fundamental step,particularly for the railway sector,whose safe and continuous operation plays a strategic role in the well-being and development of nations.In this scenario,the benefits of a digital twin of a bonded insu-lated rail joint(IRJ)with the predictive capabilities of advanced classification algorithms based on artificial intelligence have been explored.The digital model provides an accurate mechanical response of the infrastructure as a pair of wheels passes over the joint.As bolt preload conditions vary,four structural health classes were identified for the joint.Two parameters,i.e.gap value and vertical displacement,which are strongly correlated with bolt preload,are used in different combinations to train and test five predictive classifiers.Their classification effectiveness was assessed using several performance indica-tors.Finally,we compared the IRJ condition predictions of two trained classifiers with the available data,confirming their high accuracy.The approach presented provides an interesting solution for future predictive tools in SHM especially in the case of complex systems such as railways where the vehicle-infrastructure interaction is complex and always time varying.
基金supported in part by a Faculty Research Grant from the University of North Carolina at Charlotte
文摘Gene expression is a critical process in biological system that is influenced and modulated by many factors including genetic variation. Expression Quantitative Trait Loci（e QTL） analysis provides a powerful way to understand how genetic variants affect gene expression. For genome wide e QTL analysis, the number of genetic variants and that of genes are large and thus the search space is tremendous. Therefore, e QTL analysis brings about computational and statistical challenges. In this paper, we provide a comprehensive review of recent advances in methods for e QTL analysis in population-based studies. We first present traditional pairwise association methods, which are widely used in human genetics. To account for expression heterogeneity, we investigate the methods for correcting confounding factors. Next, we discuss newly developed statistical learning methods including Lasso-based models. In the conclusion, we provide an overview of future method development in analyzing e QTL associations. Although we focus on human genetics in this review, the methods are applicable to many other organisms.
基金Humanities and Social Sciences Research and Planning Fund Project ofMinistry of Education – ‘On Training Mode of Academic Degree Linking Artificial IntelligenceApplied Talents Based on ‘1+X’ Certificate System’, Project No. 20YJA880086SpecialResearch Project of Open University of China: Research on the Training Mode of ModernApprenticeship VR Technical Talents Based on Credit BankResearch and Cultivation Teamof Yunnan Open University-’Research Team for Intelligent Programming, Production andTeaching Integration’.
文摘The analysis on the learning behavior characteristics based on big data is beneficial for improving the learning resource construction,teaching mode and interactive mode of online course platforms.Multiple aspects of analysis were conducted on nearly three million pieces of learning behavior data,which is from seven courses of 3,315 learners in the same major at a university.According to the quantity of course resources and policy of course scoring,four typical learning behaviors were selected,and the correlation between final exam results and learning behavior were analyzed.The analysis of behavior influences on the final exam results were also conducted.The analytical results give suggestions for online teaching and learning.
基金supported by the National Natural Science Foundation of China(No.62377002).
文摘Personalized education,tailored to individual stu-dent needs,leverages educational technology and artificial intelligence(AI)in the digital age to enhance learning ef-fectiveness.The integration of AI in educational platforms provides insights into academic performance,learning pref-erences,and behaviors,optimizing the personal learning process.Driven by data mining techniques,it not only ben-efits students but also provides educators and institutions with tools to craft customized learning experiences.To offer a comprehensive review of recent advancements in person-alized educational data mining,this paper focuses on four primary scenarios:educational recommendation,cogni-tive diagnosis,knowledge tracing,and learning analysis.This paper presents a structured taxonomy for each area,compiles commonly used datasets,and identifies future re-search directions,emphasizing the role of data mining in enhancing personalized education and paving the way for future exploration and innovation.
文摘Purpose-The objective is to develop a more effective model that simplifies and accelerates the news classification process using advanced text mining and deep learning(DL)techniques.A distributed framework utilizing Bidirectional Encoder Representations from Transformers(BERT)was developed to classify news headlines.This approach leverages various text mining and DL techniques on a distributed infrastructure,aiming to offer an alternative to traditional news classification methods.Design/methodology/approach-This study focuses on the classification of distinct types of news by analyzing tweets from various news channels.It addresses the limitations of using benchmark datasets for news classification,which often result in models that are impractical for real-world applications.Findings-The framework’s effectiveness was evaluated on a newly proposed dataset and two additional benchmark datasets from the Kaggle repository,assessing the performance of each text mining and classification method across these datasets.The results of this study demonstrate that the proposed strategy significantly outperforms other approaches in terms of accuracy and execution time.This indicates that the distributed framework,coupled with the use of BERT for text analysis,provides a robust solution for analyzing large volumes of data efficiently.The findings also highlight the value of the newly released corpus for further research in news classification and emotion classification,suggesting its potential to facilitate advancements in these areas.Originality/value-This research introduces an innovative distributed framework for news classification that addresses the shortcomings of models trained on benchmark datasets.By utilizing cutting-edge techniques and a novel dataset,the study offers significant improvements in accuracy and processing speed.The release of the corpus represents a valuable contribution to the field,enabling further exploration into news and emotion classification.This work sets a new standard for the analysis of news data,offering practical implications for the development of more effective and efficient news classification systems.
基金supported by grants from the National Natural Science Foundation of China(82070588)High Level Creative Talents from Department of Public Health in Zhejiang Province(S2032102600032)+2 种基金Project of New Century 551 Talent Nurturing in Wenzhousupported in part by grants from the University School of Medicine of Verona,Verona,Italysupported in part by the Southampton NIHR Biomedical Research Centre(IS-BRC-20004),UK.
文摘Background:There is an unmet need for accurate non-invasive methods to diagnose non-alcoholic steatohepatitis(NASH).Since impedance-based measurements of body composition are simple,repeatable and have a strong association with non-alcoholic fatty liver disease(NAFLD)severity,we aimed to develop a novel and fully automatic machine learning algorithm,consisting of a deep neural network based on impedance-based measurements of body composition to identify NASH[the bioeLectrical impEdance Analysis foR Nash(LEARN)algorithm].Methods:A total of 1,259 consecutive subjects with suspected NAFLD were screened from six medical centers across China,of which 766 patients with biopsy-proven NAFLD were included in final analysis.These patients were randomly subdivided into the training and validation groups,in a ratio of 4:1.The LEARN algorithm was developed in the training group to identify NASH,and subsequently,tested in the validation group.Results:The LEARN algorithm utilizing impedance-based measurements of body composition along with age,sex,pre-existing hypertension and diabetes,was able to predict the likelihood of having NASH.This algorithm showed good discriminatory ability for identifying NASH in both the training and validation groups[area under the receiver operating characteristics(AUROC):0.81,95%CI:0.77-0.84 and AUROC:0.80,95%CI:0.73-0.87,respectively].This algorithm also performed better than serum cytokeratin-18 neoepitope M30(CK-18 M30)level or other non-invasive NASH scores(including HAIR,ION,NICE)for identifying NASH(P value<0.001).Additionally,the LEARN algorithm performed well in identifying NASH in different patient subgroups,as well as in subjects with partial missing body composition data.Conclusions:The LEARN algorithm,utilizing simple easily obtained measures,provides a fully automated,simple,non-invasive method for identifying NASH.
