Pour voir les autres types de publications sur ce sujet consultez le lien suivant : Prediction of Dropout behavior.
Articles de revues sur le sujet « Prediction of Dropout behavior »
Créez une référence correcte selon les styles APA, MLA, Chicago, Harvard et plusieurs autres
Consultez les 50 meilleurs articles de revues pour votre recherche sur le sujet « Prediction of Dropout behavior ».
À côté de chaque source dans la liste de références il y a un bouton « Ajouter à la bibliographie ». Cliquez sur ce bouton, et nous générerons automatiquement la référence bibliographique pour la source choisie selon votre style de citation préféré : APA, MLA, Harvard, Vancouver, Chicago, etc.
Vous pouvez aussi télécharger le texte intégral de la publication scolaire au format pdf et consulter son résumé en ligne lorsque ces informations sont inclues dans les métadonnées.
Parcourez les articles de revues sur diverses disciplines et organisez correctement votre bibliographie.
1
Yujiao, Zhang, Ling Weay Ang, Shi Shaomin et Sellappan Palaniappan. « Dropout Prediction Model for College Students in MOOCs Based on Weighted Multi-feature and SVM ». Journal of Informatics and Web Engineering 2, no 2 (13 septembre 2023) : 29–42. http://dx.doi.org/10.33093/jiwe.2023.2.2.3.
Texte intégralRésumé :
Due to the COVID -19 pandemic, MOOCs have become a popular form of learning for college students. However, unlike traditional face-to-face courses, MOOCs offer little faculty supervision, which may result in students being insufficiently motivated to continue learning, ultimately leading to a high dropout rate. Consequently, the problem of high dropout rates in MOOCs requires urgent attention in MOOC research. Predicting dropout rates is the first step to address this problem, and MOOCs have a large amount of behavioral data that can be used for such predictions. Most existing models for predicting MOOC dropout based on behavioral data assign equal weights to each behavioral characteristic, despite the fact that each behavioral characteristic has a different effect on predicting dropout. To address this problem, this paper proposes a dropout prediction model based on the fusion of behavioral data and Support Vector Machine (SVM). This innovative model assigns different weights to different behavior features based on Pearson principle and integrates them as data inputs to the model. Dropout prediction is essentially a binary problem, Support Vector Machine Classifier is then trained using the training dataset 1 and dataset 2. Experimental results on both datasets show that this predictive model outperforms previous models that assign the same weights to the behavior features.
2
Chi, Zengxiao, Shuo Zhang et Lin Shi. « Analysis and Prediction of MOOC Learners’ Dropout Behavior ». Applied Sciences 13, no 2 (13 janvier 2023) : 1068. http://dx.doi.org/10.3390/app13021068.
Texte intégralRésumé :
With the wide spread of massive open online courses ( MOOC ), millions of people have enrolled in many courses, but the dropout rate of most courses is more than 90%. Accurately predicting the dropout rate of MOOC is of great significance to prevent learners’ dropout behavior and reduce the dropout rate of students. Using the PH278x curriculum data on the Harvard X platform in spring 2013, and based on the statistical analysis of the factors that may affect learners’ final completion of the curriculum from two aspects: learners’ own characteristics and learners’ learning behavior, we established the MOOC dropout rate prediction models based on logical regression, K nearest neighbor and random forest, respectively. Experiments with five evaluation metrics (accuracy, precision, recall, F1 and AUC) show that the prediction model based on random forest has the highest accuracy, precision, F1 and AUC, which are 91.726%, 93.0923%, 95.4145%, 0.925341, respectively, its performance is better than that of the prediction model based on logical regression and that of the model based on K-nearest neighbor, whose values of these metrics are 91.395%, 92.8674%, 95.2337%, 0.912316 and 91.726%, 93.0923%, 95.4145% and 0.925341, respectively. As for recall metrics, the value of random forest is higher than that of KNN, but slightly lower than that of logistic regression, which are 0.992476, 0.977239 and 0.978555, respectively. Then, we conclude that random forests perform best in predicting the dropout rate of MOOC learners. This study can help education staff to know the trend of learners’ dropout behavior in advance, so as to put some measures to reduce the dropout rate before it occurs, thus improving the completion rate of the curriculum.
3
Shou, Zhaoyu, Pan Chen, Hui Wen, Jinghua Liu et Huibing Zhang. « MOOC Dropout Prediction Based on Multidimensional Time-Series Data ». Mathematical Problems in Engineering 2022 (28 avril 2022) : 1–12. http://dx.doi.org/10.1155/2022/2213292.
Texte intégralRésumé :
Massive open online courses have attracted millions of learners worldwide with flexible learning options. However, online learning differs from offline education in that the lack of communicative feedback is a drawback that magnifies high dropout rates. The analysis and prediction of student’s online learning process can help teachers find the students with dropout tendencies in time and provide additional help. Previous studies have shown that analyzing learning behaviors at different time scales leads to different prediction results. In addition, noise in the time-series data of student behavior can also interfere with the prediction results. To address these issues, we propose a dropout prediction model that combines a multiscale fully convolutional network and a variational information bottleneck. The model extracts multiscale features of student behavior time-series data by constructing a multiscale full convolutional network and then uses a variational information bottleneck to suppress the effect of noise on the prediction results. This study conducted multiple cross-validation experiments on KDD CUP 2015 data set. The results showed that the proposed method achieved the best performance compared to the baseline method.
4
Zhang, Tiancheng, Hengyu Liu, Jiale Tao, Yuyang Wang, Minghe Yu, Hui Chen et Ge Yu. « Enhancing Dropout Prediction in Distributed Educational Data Using Learning Pattern Awareness : A Federated Learning Approach ». Mathematics 11, no 24 (16 décembre 2023) : 4977. http://dx.doi.org/10.3390/math11244977.
Texte intégralRésumé :
Learning patterns are crucial for predicting student dropout in educational settings, providing insights into students’ behaviors and motivations. However, existing mainstream dropout prediction models have limitations in effectively mining these learning patterns and cannot mine these learning patterns in large-scale, distributed educational datasets. In this study, we analyze the representations of mainstream models and identify their inability to capture students’ distinct learning patterns and personalized variations across courses. Addressing these challenges, our study adopts a federated learning approach, tailoring the analysis to leverage distributed data while maintaining privacy and decentralization. We introduce the Federated Learning Pattern Aware Dropout Prediction Model (FLPADPM), which utilizes a one-dimensional convolutional neural network (CNN) and a bidirectional long short-term memory (LSTM) layer within a federated learning framework. This model is designed to effectively capture nuanced learning patterns and adapt to variations across diverse educational settings. To evaluate the performance of LPADPM, we conduct an empirical evaluation using the KDD Cup 2015 and XuetangX datasets. Our results demonstrate that LPADPM outperforms state-of-the-art models in accurately predicting student dropout behavior. Furthermore, we visualize the representations generated by LPADPM, which confirm its ability to effectively mine learning patterns in different courses. Our results showcase the model’s ability to capture and analyze learning patterns across various courses and institutions within a federated learning context.
5
Janosz, Michel, Marc LeBlanc et Bernard Boulerice. « Consommation de psychotropes et délinquance : de bons prédicteurs de l’abandon scolaire ? » Criminologie 31, no 1 (1 septembre 2005) : 87–107. http://dx.doi.org/10.7202/017413ar.
Texte intégralRésumé :
Although empirical links between deviant behavior and school dropout have been extensively demonstrated, the specific influence of drug use and delinquency on school dropout is still not clear and varies across studies. One reason for this lack of consistency may rests upon the way samples of dropouts have been analysed. Recently, Janosz, Le Blanc, Boulerice and Tremblay (1996) constructed and validated a typology of school dropout highlithing the social and psychological diversity of this population. Using a longitudinal sample of adolescents (N=791), we analyzed the predictive relationships of family rebelliousness, drug use and delinquency on school dropout. The results showed an important variability in the predictive relationships according to the type of dropouts. The necessity of considering the psychosocial heterogeneity of dropouts when conducting such studies is discussed.
6
Keijsers, Ger P. J., Mirjam Kampman et Cees A. L. Hoogduin. « Dropout prediction in cognitive behavior therapy for panic disorder ». Behavior Therapy 32, no 4 (2001) : 739–49. http://dx.doi.org/10.1016/s0005-7894(01)80018-6.
Texte intégral
7
Siebra, Clauirton Albuquerque, Ramon N. Santos et Natasha C. Q. Lino. « A Self-Adjusting Approach for Temporal Dropout Prediction of E-Learning Students ». International Journal of Distance Education Technologies 18, no 2 (avril 2020) : 19–33. http://dx.doi.org/10.4018/ijdet.2020040102.
Texte intégralRésumé :
This work proposes a dropout prediction approach that is able to self-adjust their outcomes at any moment of a degree program timeline. To that end, a rule-based classification technique was used to identify courses, grade thresholds and other attributes that have a high influence on the dropout behavior. This approach, which is generic so that it can be applied to any distance learning degree program, returns different rules that indicate how the predictions are adjusted along with academic terms. Experiments were carried out using four rule-based classification algorithms: JRip, OneR, PART and Ridor. The outcomes show that this approach presents better accuracy according to the progress of students, mainly when the JRip and PART algorithms are used. Furthermore, the use of this method enabled the generation of rules that stress the factors that mainly affect the dropout phenomenon at different degree moments.
8
Albán, Mayra, David Mauricio et . « Decision Trees for the Early Identification of University Students at Risk of Desertion ». International Journal of Engineering & ; Technology 7, no 4.44 (1 décembre 2018) : 51. http://dx.doi.org/10.14419/ijet.v7i4.44.26862.
Texte intégralRésumé :
The student's dropout at the universities is a topic that has generated controversy in Higher Education Institutions. It has negative effects which cause problems in the social, academic and economic context of the students. One of the alternatives used to predict the dropout at the universities is the implementation of machine learning techniques such as decision trees, known as prediction models that use logical construction diagrams to characterize the behavior of students and identify early students that at in risk of leaving university. Based on a survey of 3162 students, it was possible to obtain 10 variables that have influence into the dropout, that’s why, a CHAID decision tree model is proposed that presents the 97.95% of the accuracy in the prediction of the university students’ dropout. The proposed prediction model allows the administrators of the universities developing strategies for effective intervention in order to establish actions that allow students finishing their university careers successful.
9
De Souza, Vanessa Faria, et Gabriela Perry. « Identifying student behavior in MOOCs using Machine Learning ». International Journal of Innovation Education and Research 7, no 3 (31 mars 2019) : 30–39. http://dx.doi.org/10.31686/ijier.vol7.iss3.1318.
Texte intégralRésumé :
This paper presents the results literature review, carried out with the objective of identifying prevalent research goals and challenges in the prediction of student behavior in MOOCs, using Machine Learning. The results allowed recognizingthree goals: 1. Student Classification and 2. Dropout prediction. Regarding the challenges, five items were identified: 1. Incompatibility of AVAs, 2. Complexity of data manipulation, 3. Class Imbalance Problem, 4. Influence of External Factors and 5. Difficulty in manipulating data by untrained personnel.
10
Bremer, V., P. Chow, B. Funk, F. Thorndike et L. Ritterband. « 1204 Analyzing User Journey Data In Digital Health : Predicting Dropout From A Digital CBT-I Intervention ». Sleep 43, Supplement_1 (avril 2020) : A460. http://dx.doi.org/10.1093/sleep/zsaa056.1198.
Texte intégralRésumé :
Abstract Introduction Intervention dropout is an important factor for the evaluation and implementation of digital therapeutics, including in insomnia. Large amounts of individualized data (logins, questionnaires, EMA data) in these interventions can combine to create user journeys - the data generated by the path an individual takes to navigate the digital therapeutic. User journeys can provide insight about how likely users are to drop out of an intervention on an individual level and lead to increased prediction performance. Thus, the goal of this study is to provide a step-by-step guide for the analysis of user journeys and utilize this guide to predict intervention dropout, illustrated with an example from a data in a RCT of digital therapeutic for chronic insomnia, for which outcomes have previously been published. Methods Analysis of user journeys includes data transformation, feature engineering, and statistical model analysis, using machine learning techniques. A framework is established to leverage user journeys to predict various behaviors. For this study, the framework was applied to predict dropouts of 151 participants from a fully automated web-based program (SHUTi) that delivered cognitive behavioral therapy for insomnia. For this task, support vector machines, logistic regression with regularization, and boosted decision trees were applied at different points in 9-week intervention. These techniques were evaluated based on their predictive performance. Results After model evaluation, a decision tree ensemble achieved AUC values ranging between 0.6-0.9 based on application of machine earning techniques. Various handcrafted and theory-driven features (e.g., time to complete certain intervention steps, time to get out of bed after arising, and days since last system interaction contributed to prediction performance. Conclusion Results indicate that utilizing a user journey framework and analysis can predict intervention dropout. Further, handcrafted theory-driven features can increase prediction performance. This prediction of dropout could lead to an enhanced clinical decision-making in digital therapeutics. Support The original study evaluating the efficacy of this intervention has been reported elsewhere and was funded by grant R01 MH86758 from the National Institute of Mental Health.
11
Tang, Xingqiu, Hao Zhang, Ni Zhang, Huan Yan, Fangfang Tang et Wei Zhang. « Dropout Rate Prediction of Massive Open Online Courses Based on Convolutional Neural Networks and Long Short-Term Memory Network ». Mobile Information Systems 2022 (16 mai 2022) : 1–11. http://dx.doi.org/10.1155/2022/8255965.
Texte intégralRésumé :
Massive open online courses (MOOC) is characterized by large scale, openness, autonomy, and personalization, attracting increasingly students to participate in learning and gaining recognition from more and more people. This paper proposes a network model based on convolutional neural networks and long short-term memory network (CNN-LSTM) for MOOC dropout prediction task. The model selects 43-dimensional behavioral features as input from students’ learning activity logs and adopts the CNN model to automatically extract continuous features over a period of time from students’ learning activity logs. At the same time, considering the time sequence of students’ learning behavior characteristics, a MOOC dropout prediction model was established by using long short-term memory network to obtain students’ learning status at different time steps. The algorithm proposed in this chapter was trained and evaluated on the public dataset provided by the KDD Cup 2015 competition. Compared with the dropout prediction methods based on LSTM and CNN-RNN, the model improved the AUC by 2.7% and 1.4%, respectively. The result in this paper is a good predictor of dropout rates and is expected to provide teaching aid to teachers.
12
Kumar, Gaurav, Amar Singh et Ashok Sharma. « Ensemble Deep Learning Network Model for Dropout Prediction in MOOCs ». International journal of electrical and computer engineering systems 14, no 2 (27 février 2023) : 187–96. http://dx.doi.org/10.32985/ijeces.14.2.8.
Texte intégralRésumé :
In the online education field, Massive open online courses (MOOCs) have become popular in recent years. Educational institutions and Universities provide a variety of specialized online courses that helps the students to adapt with various needs and learning preferences. Because of this, institutional repositories creates and preserve a lot of data about students' demographics, behavioral trends, and academic achievement every day. Moreover, a significant problem impeding their future advancement is the high dropout rate. For solving this problem, the dropout rate is predicted by proposing an Ensemble Deep Learning Network (EDLN) model depending on the behavior data characteristics of learners. The local features are extracted by using ResNet-50 and then a kernel strategy is used for building feature relations. After feature extraction, the high-dimensional vector features are sent to a Faster RCNN for obtaining the vector representation that incorporates time series data. Then an attention weight is obtained for each dimension by applying a static attention mechanism to the vector. Extensive experiments on a public data set have shown that the proposed model can achieve comparable results with other dropout prediction methods in terms of precision, recall, F1 score, and accuracy.
13
Kustitskaya, T. A., M. V. Noskov et Y. V. Vainshtein. « Predicting learning success : research problems and challenges ». Science and School, no 4 (29 août 2023) : 71–83. http://dx.doi.org/10.31862/1819-463x-2023-4-71-83.
Texte intégralRésumé :
The article is devoted to the problems of learning success prediction. The aim of the work is to discuss current tasks and possible difficulties related to the development of services for predicting learning success in the digital environment of an educational institution. Among the variety of forecasting tasks arising in educational analytics, two main directions were identified and examined in detail: prediction of student dropout and prediction of academic performance for courses of the curriculum. The article discusses examples of creating and using predictive models in the educational process by secondary and higher education organizations. It is noted that despite the large number of studies in this problem field, there are only few examples of successfully implemented regional or at least organizational-level forecasting systems. The authors believe that the main obstacles to building a well-scalable system for supporting learning success based on predictive models are difficulties with data unification, lack of policy of using personal data in learning analytics, lack of feedback mechanisms and activities for correcting learning behavior. Solving each of these problems is a separate serious scientific task. The prospects for using the results of the research are indicated.
14
Tamada, Mariela Mizota, Rafael Giusti et José Francisco de Magalhães Netto. « Predicting Students at Risk of Dropout in Technical Course Using LMS Logs ». Electronics 11, no 3 (5 février 2022) : 468. http://dx.doi.org/10.3390/electronics11030468.
Texte intégralRésumé :
Educational data mining is a process that aims at discovering patterns that provide insight into teaching and learning processes. This work uses Machine Learning techniques to create a student performance prediction model, using academic data and records from a Learning Management System, that correlates with success or failure in completing the course. Six algorithms were employed, with models trained at three different stages of their two-year course completion. We tested the models with records of 394 students from 3 courses. Random Forest provided the best results with 84.47% on the F1 score in our experiments, followed by Decision Tree obtaining similar results in the first subjects. We also employ clustering techniques and find different behavior groups with a strong correlation to performance. This work contributes to predicting students at risk of dropping out, offers insight into understanding student behavior, and provides a support mechanism for academic managers to take corrective and preventive actions on this problem.
15
Chen, Jing, Jun Feng, Xia Sun, Nannan Wu, Zhengzheng Yang et Sushing Chen. « MOOC Dropout Prediction Using a Hybrid Algorithm Based on Decision Tree and Extreme Learning Machine ». Mathematical Problems in Engineering 2019 (18 mars 2019) : 1–11. http://dx.doi.org/10.1155/2019/8404653.
Texte intégralRésumé :
Massive Open Online Courses (MOOCs) have boomed in recent years because learners can arrange learning at their own pace. High dropout rate is a universal but unsolved problem in MOOCs. Dropout prediction has received much attention recently. A previous study reported the problem of learning behavior discrepancy leading to a wide range of fluctuation of prediction results. Besides, previous methods require iterative training which is time intensive. To address these problems, we propose DT-ELM, a novel hybrid algorithm combining decision tree and extreme learning machine (ELM), which requires no iterative training. The decision tree selects features with good classification ability. Further, it determines enhanced weights of the selected features to strengthen their classification ability. To achieve accurate prediction results, we optimize ELM structure by mapping the decision tree to ELM based on the entropy theory. Experimental results on the benchmark KDD 2015 dataset demonstrate the effectiveness of DT-ELM, which is 12.78%, 22.19%, and 6.87% higher than baseline algorithms in terms of accuracy, AUC, and F1-score, respectively.
16
Muthukumar, Vignesh, et Dr Bhalaji N. « MOOCVERSITY - Deep Learning Based Dropout Prediction in MOOCs over Weeks ». Journal of Soft Computing Paradigm 2, no 3 (27 juin 2020) : 140–52. http://dx.doi.org/10.36548/jscp.2020.3.001.
Texte intégralRésumé :
Massive Open Online Courses (MOOCs) has seen a dramatic increase of participants in the last few years with an exponential growth of internet users all around the world. MOOC allows users to attend lectures of top professors from world class universities. Despite flexible accessibility, the common trend observed in each course is that the number of active participants appears to decrease exponentially as the week’s progress. The structure and nature of the courses affects the number of active participants directly. A comprehensive review of the available literature shows that very little intensive work was done using the pattern of user interaction with courses in the field of MOOC data analysis. In this paper, we take an initial step to use the deep learning algorithm to construct the dropout prediction model and produce the predicted individual student dropout probability. Additional improvements are made to optimize the performance of the dropout prediction model and provide the course providers with appropriate interventions based on a temporal prediction mechanism. Our Exploratory Data Analysis demonstrates that there is a strong correlation between click stream actions and successful learner outcomes. Among other features, the deep learning algorithm takes the weekly history of student data into account and thus is able to notice changes in student behaviour over time.
17
Ismanto, Edi, et Noverta Effendi. « An LSTM-based prediction model for gradient-descending optimization in virtual learning environments ». Computer Science and Information Technologies 4, no 3 (9 mai 2024) : 199–207. http://dx.doi.org/10.11591/csit.v4i3.pp199-207.
Texte intégralRésumé :
A virtual learning environment (VLE) is an online learning platform that allows many students, even millions, to study according to their interests without being limited by space and time. Online learning environments have many benefits, but they also have some drawbacks, such as high dropout rates, low engagement, and students' self-regulated behavior. Evaluating and analyzing the students' data generated from online learning platforms can help instructors to understand and monitor students learning progress. In this study, we suggest a predictive model for assessing student success in online learning. We investigate the effect of hyperparameters on the prediction of student learning outcomes in VLEs by the long short-term memory (LSTM) model. A hyperparameter is a parameter that has an impact on prediction results. Two optimization algorithms, adaptive moment estimation (Adam) and Nesterov-accelerated adaptive moment estimation (Nadam), were used to modify the LSTM model's hyperparameters. Based on the findings of research done on the optimization of the LSTM model using the Adam and Nadam algorithm. The average accuracy of the LSTM model using Nadam optimization is 89%, with a maximum accuracy of 93%. The LSTM model with Nadam optimisation performs better than the model with Adam optimisation when predicting students in online learning.
18
Ismanto, Edi, et Noverta Effendi. « An LSTM-based prediction model for gradient-descending optimization in virtual learning environments ». Computer Science and Information Technologies 4, no 3 (1 novembre 2023) : 199–207. http://dx.doi.org/10.11591/csit.v4i3.p199-207.
Texte intégralRésumé :
A virtual learning environment (VLE) is an online learning platform that allows many students, even millions, to study according to their interests without being limited by space and time. Online learning environments have many benefits, but they also have some drawbacks, such as high dropout rates, low engagement, and students' self-regulated behavior. Evaluating and analyzing the students' data generated from online learning platforms can help instructors to understand and monitor students learning progress. In this study, we suggest a predictive model for assessing student success in online learning. We investigate the effect of hyperparameters on the prediction of student learning outcomes in VLEs by the long short-term memory (LSTM) model. A hyperparameter is a parameter that has an impact on prediction results. Two optimization algorithms, adaptive moment estimation (Adam) and Nesterov-accelerated adaptive moment estimation (Nadam), were used to modify the LSTM model's hyperparameters. Based on the findings of research done on the optimization of the LSTM model using the Adam and Nadam algorithm. The average accuracy of the LSTM model using Nadam optimization is 89%, with a maximum accuracy of 93%. The LSTM model with Nadam optimisation performs better than the model with Adam optimisation when predicting students in online learning.
19
Ye, Cheng, et Gautam Biswas. « Early Prediction of Student Dropout and Performance in MOOCs using Higher Granularity Temporal Information ». Journal of Learning Analytics 1, no 3 (23 décembre 2014) : 169–72. http://dx.doi.org/10.18608/jla.2014.13.14.
Texte intégralRésumé :
Our project is motivated by the early drop out and low completion rate problem in MOOCs. We have extended traditional features for MOOC analysis with richer granularity information to make more accurate predictions of dropout and performance. The results show that adding final-grained temporal or non-temporal information into behaviour features provides more predictive power in the early phases of a POSA MOOC. As a next step, we plan to determine if we could use these features to better profile students with unsupervised learning methods.
20
Kaensar, Chayaporn, et Worayoot Wongnin. « Analysis and Prediction of Student Performance Based on Moodle Log Data using Machine Learning Techniques ». International Journal of Emerging Technologies in Learning (iJET) 18, no 10 (23 mai 2023) : 184–203. http://dx.doi.org/10.3991/ijet.v18i10.35841.
Texte intégralRésumé :
During the COVID-19 Pandemic, many universities in Thailand were mostly locked down and classrooms were also transformed into a fully online format. It was challenging for teachers to manage online learning and especially to track student behavior since the teacher could not observe and notify students. To alleviate this problem, one solution that has become increasingly important is the prediction of student performance based on their log data. This study, therefore, aims to analyze student behavior data by applying Predictive Analytics through Moodle Log for approximately 54,803 events. Six Machine Learning Classifiers (Neural Network, Random Forest, Decision Tree, Logistic Regression, Linear Regression, and Support Vector Machine) were applied to predict student performance. Further, we attained a comparison of the effectiveness of early prediction for four stages at 25%, 50%, 75%, and 100% of the course. The prediction models could guide future studies, motivate self-preparation and reduce dropout rates. In the experiment, the model with 5-fold cross-validation was evaluated. Results indicated that the Decision Tree performed best at 81.10% upon course completion. Meanwhile, the SVM had the best result at 86.90% at the first stage, at 25% of the course, and Linear Regression performed with the best efficiency at the middle stages at 70.80%, and 80.20% respectively. The results could be applied to other courses and on a larger e-learning systems log that has similar student activity conditions and this could contribute to more accurate student performance prediction.
21
Mansi Choudhari, Saloni Rangari, Pratham Badge, Pratham Chopde et Atharva Paraskar. « Review On Educational Academic Performance Analysis and Dropout Visualization by Analyzing Grades of Student ». International Research Journal on Advanced Engineering and Management (IRJAEM) 2, no 05 (18 mai 2024) : 1408–22. http://dx.doi.org/10.47392/irjaem.2024.0194.
Texte intégralRésumé :
Education is a crucial aspect of a nation's development, and ensuring the success and retention of students is of paramount importance. The current studies show the need for an effective and efficient education prediction system. Education is a pivotal aspect of a country's development. It acts as a powerful tool to change the world. Education is the key to a literate society. In India, it is necessary to have an integrated web platform to analyze the academic performance and dropout rates across school, higher, and technical education. Student dropout is a significant problem for any nation. Discontinuing schooling due to financial, practical, and social reasons, as well as disappointment in examination results, is what is commonly referred to as student dropout. Educational Data Mining (EDM) techniques can help discover insights from data in educational environments, allowing tutors and researchers to predict future trends and student behavior. The use of machine learning and data mining techniques provides valuable tools for understanding the student learning environment. This literature review aims to synthesize the existing research findings on this topic and identify knowledge gaps for future research.
22
Shang, Xiaoran, Bangbo Huang et Hongbin Ma. « Multifeedback Behavior-Based Interest Modeling Network for Adaptive Click-Through Rate Prediction ». Mobile Information Systems 2022 (29 août 2022) : 1–9. http://dx.doi.org/10.1155/2022/3529928.
Texte intégralRésumé :
With the rapid development of the Internet, the recommendation system is becoming more and more important in people’s life. Click-through rate prediction is a crucial task in the recommendation system, which directly determines the effect of the recommendation system. Recently, researchers have found that considering the user behavior sequence can greatly improve the accuracy of the click-through rate prediction model. However, the existing prediction models usually use the user click behavior sequence as the input of the model, which will make it difficult for the model to obtain a comprehensive user interest representation. In this paper, a unified multitype user behavior sequence modeling framework named as MBIN, a.k.a. multifeedback behavior-based Interest modeling network, is proposed to cope with uncertainties in the noisy data. The proposed adaptive model uses deep learning technology, obtains user interest representation through multihead attention, denoises user interest representation using the vector projection method, and fuses the user interests using adaptive dropout technology. First, an interest denoising layer is proposed in the MBIN, which can effectively mitigate the noise problem in user behavior sequences to obtain more accurate user interests. Second, an interest fusion layer is introduced so as to effectively model and fuse various types of interest representations of users to achieve personalized interest fusion. Then, we used auxiliary losses based on behavior sequences to enhance the effect of behavior sequence modeling and improve the effectiveness of user interest characterization. Finally, we conduct extensive experiments based on real-world and large-scale dataset to validate the effectiveness of our approach in CTR prediction tasks.
23
Zheng, Yafeng, Zheng Shao, Mingming Deng, Zhanghao Gao et Qian Fu. « MOOC dropout prediction using a fusion deep model based on behaviour features ». Computers and Electrical Engineering 104 (décembre 2022) : 108409. http://dx.doi.org/10.1016/j.compeleceng.2022.108409.
Texte intégral
24
Morneau-Vaillancourt, Geneviève, Massimiliano Orri, Marie-Claude Geoffroy et Michel Boivin. « POLYGENIC PREDICTION OF DEPRESSIVE SYMPTOMS, PEER VICTIMIZATION, SCHOOL DROPOUT, AND SUICIDAL BEHAVIORS ». European Neuropsychopharmacology 75 (octobre 2023) : S37—S38. http://dx.doi.org/10.1016/j.euroneuro.2023.08.077.
Texte intégral
25
Noreen B. Fuentes, Et al. « Utilizing J48 Algorithm in Predicting Students Dropout in Higher Education Institution ». International Journal on Recent and Innovation Trends in Computing and Communication 11, no 9 (5 novembre 2023) : 2818–25. http://dx.doi.org/10.17762/ijritcc.v11i9.9371.
Texte intégralRésumé :
Dropout refers to students who voluntarily withdraw from a course or program prior to completion. University dropouts continue to be a major concern for educators and represent a substantial loss of human resources for society. At Cebu Technological University, it is always a challenge of the Department Chairperson the declining student population, which resulted in the reduction of the number of sections per year level and under loading of faculty.
This study centers on the creation of a student-dropout model that predicts a student's behavior toward his studies. This model utilized the J48 decision tree algorithm, which extract data from the Student Information System (SIS) portal of the existing institution. Nine hundred sixty-one (961) demographic and academic datasets from students enrolled in the two programs under the College of Computer, Information, and Communications Technology (CCICT) of Cebu Technological University (CTU) with nineteen (19) attributes. During the testing procedure, 10-fold cross-validation was utilized. The J48 pruned tree utilized an average of 3 foliage with 4 as the measure of the tree. The Kappa statistic yields a value of 0.8617 and its Correctly Classified Instances rate of 93.7%. This algorithm helps a lot to the institution in reducing the escalation of the attrition rate and providing proactive measures to address the issue.
26
de Vries, Marieke, Mathilde GE Verdam, Pier JM Prins, Ben A. Schmand et Hilde M. Geurts. « Exploring possible predictors and moderators of an executive function training for children with an autism spectrum disorder ». Autism 22, no 4 (19 mars 2017) : 440–49. http://dx.doi.org/10.1177/1362361316682622.
Texte intégralRésumé :
Previously, a total of 121 children with an autism spectrum disorder (ASD) performed an adaptive working memory (WM)-training, an adaptive flexibility-training, or a non-adaptive control (mock)-training. Despite overall improvement, there were minor differences between the adaptive and mock-training conditions. Moreover, dropout was relatively high (26%). In the current study we explored potential predicting and moderating factors to clarify these findings. The effects of intelligence, autism traits, WM, flexibility, reward sensitivity and Theory of Mind on dropout, improvement during training, and improvement in everyday executive functioning (EF), ASD-like behavior, and Quality of Life (QoL) were studied. None of the predictors influenced dropout or training improvement. However, 1) more pre-training autism traits related to less improvement in EF and QoL, and 2) higher reward sensitivity was related to more improvement in QoL and ASD-like behavior. These findings suggest that these EF-training procedures may be beneficial for children with fewer autism traits and higher reward sensitivity. However, the exploratory nature of the analyses warrant further research before applying the findings clinically.
27
Nache, Catalin M., Michael Bar-Eli, Claire Perrin et Louis Laurencelle. « Predicting dropout in male youth soccer using the theory of planned behavior ». Scandinavian Journal of Medicine and Science in Sports 15, no 3 (juin 2005) : 188–97. http://dx.doi.org/10.1111/j.1600-0838.2004.00416.x.
Texte intégral
28
Pan, Feng, Hanfei Zhang, Xuebao Li, Moyu Zhang et Yang Ji. « Achieving optimal trade-off for student dropout prediction with multi-objective reinforcement learning ». PeerJ Computer Science 10 (30 avril 2024) : e2034. http://dx.doi.org/10.7717/peerj-cs.2034.
Texte intégralRésumé :
Student dropout prediction (SDP) in educational research has gained prominence for its role in analyzing student learning behaviors through time series models. Traditional methods often focus singularly on either prediction accuracy or earliness, leading to sub-optimal interventions for at-risk students. This issue underlines the necessity for methods that effectively manage the trade-off between accuracy and earliness. Recognizing the limitations of existing methods, this study introduces a novel approach leveraging multi-objective reinforcement learning (MORL) to optimize the trade-off between prediction accuracy and earliness in SDP tasks. By framing SDP as a partial sequence classification problem, we model it through a multiple-objective Markov decision process (MOMDP), incorporating a vectorized reward function that maintains the distinctiveness of each objective, thereby preventing information loss and enabling more nuanced optimization strategies. Furthermore, we introduce an advanced envelope Q-learning technique to foster a comprehensive exploration of the solution space, aiming to identify Pareto-optimal strategies that accommodate a broader spectrum of preferences. The efficacy of our model has been rigorously validated through comprehensive evaluations on real-world MOOC datasets. These evaluations have demonstrated our model’s superiority, outperforming existing methods in achieving optimal trade-off between accuracy and earliness, thus marking a significant advancement in the field of SDP.
29
Klotz, Daniel, Frederik Kratzert, Martin Gauch, Alden Keefe Sampson, Johannes Brandstetter, Günter Klambauer, Sepp Hochreiter et Grey Nearing. « Uncertainty estimation with deep learning for rainfall–runoff modeling ». Hydrology and Earth System Sciences 26, no 6 (31 mars 2022) : 1673–93. http://dx.doi.org/10.5194/hess-26-1673-2022.
Texte intégralRésumé :
Abstract. Deep learning is becoming an increasingly important way to produce accurate hydrological predictions across a wide range of spatial and temporal scales. Uncertainty estimations are critical for actionable hydrological prediction, and while standardized community benchmarks are becoming an increasingly important part of hydrological model development and research, similar tools for benchmarking uncertainty estimation are lacking. This contribution demonstrates that accurate uncertainty predictions can be obtained with deep learning. We establish an uncertainty estimation benchmarking procedure and present four deep learning baselines. Three baselines are based on mixture density networks, and one is based on Monte Carlo dropout. The results indicate that these approaches constitute strong baselines, especially the former ones. Additionally, we provide a post hoc model analysis to put forward some qualitative understanding of the resulting models. The analysis extends the notion of performance and shows that the model learns nuanced behaviors to account for different situations.
30
Adnan, Muhammad, Duaa H. AlSaeed, Heyam H. Al-Baity et Abdur Rehman. « Leveraging the Power of Deep Learning Technique for Creating an Intelligent, Context-Aware, and Adaptive M-Learning Model ». Complexity 2021 (13 juillet 2021) : 1–21. http://dx.doi.org/10.1155/2021/5519769.
Texte intégralRésumé :
Machine learning (ML) and deep learning (DL) algorithms work well where future estimations and predictions are required. Particularly, in educational institutions, ML and DL algorithms can help instructors in predicting the learning performance of learners. Furthermore, the prediction of the learning performance of learners can assist instructors and intelligent learning systems (ILSs) in taking preemptive measures (i.e., early engagement or early intervention measures) so that the learning performance of weak learners could be increased thus reducing learners’ failures and dropout rates. In this study, we propose an intelligent learning system (ILS) powered by the mobile learning (M-learning) model that predicts learners’ performance and classify them into various performance groups. Subsequently, adaptive feedback and support are provided to those learners who struggle in their studies. Four M-learning models were created for different learners considering their learning features (study behavior) and their weight values. The M-learning model was based on the artificial neural network (ANN) algorithm with the aim to predict learners’ performance and classify them into five performance groups, whereas the random forest (RF) algorithm was used to determine each feature’s importance in the creation of the M-learning model. In the last stage of this study, we performed an early intervention/engagement experiment on those learners who showed weak performance in their study. End-user computing satisfaction (EUCS) model questionnaire was adopted to measure the attitude of learners towards using an ILS. As compared to traditional machine learning algorithms, ANN achieved the highest prediction accuracy for all four learning models, i.e., model 1 = 90.77%, model 2 = 87.69%, model 3 = 83.85%, and model 4 = 80.00%. Moreover, the five most important features that significantly affect the students’ final performance were MP3 = 0.34, MP1 = 0.26, MP2 = 0.24, NTAQ = 0.05, and AST = 0.018.
31
Gómez-Pulido, Juan A., Young Park et Ricardo Soto. « Advanced Techniques in the Analysis and Prediction of Students’ Behaviour in Technology-Enhanced Learning Contexts ». Applied Sciences 10, no 18 (5 septembre 2020) : 6178. http://dx.doi.org/10.3390/app10186178.
Texte intégralRésumé :
The development and promotion of teaching-enhanced learning tools in the academic field is leading to the collection of a large amount of data generated from the usual activity of students and teachers. The analysis of these data is an opportunity to improve many aspects of the learning process: recommendations of activities, dropout prediction, performance and knowledge analysis, resources optimization, etc. However, these improvements would not be possible without the application of computer science techniques that have demonstrated a high effectiveness for this purpose: data mining, big data, machine learning, deep learning, collaborative filtering, and recommender systems, among other fields related to intelligent systems. This Special Issue provides 17 papers that show advances in the analysis, prediction, and recommendation of applications propelled by artificial intelligence, big data, and machine learning in the teaching-enhanced learning context.
32
Yin, Hua, Hong Wu et Sang-Bing Tsai. « Innovative Research on the Construction of Learner’s Emotional Cognitive Model in E-Learning by Big Data Analysis ». Mathematical Problems in Engineering 2021 (25 octobre 2021) : 1–9. http://dx.doi.org/10.1155/2021/1460172.
Texte intégralRésumé :
This article first addresses the problem that the unstructured data in the existing e-learning education data is difficult to effectively use and the problem that the coarser granularity of sentiment analysis results in traditional sentiment analysis methods and proposes multipolarized sentiment based on fine-grained sentiment analysis evaluation model. Then, an algorithm for behavior prediction and course recommendation based on emotional change trends is proposed, and the established multiple linear regression equation is solved with an improved algorithm. Finally, the method in this paper is verified by a comprehensive example with algorithm comparison analysis and cross-validation evaluation method. The research method proposed in this article provides new research ideas for evaluating and predicting the learning behavior of e-learners, which is conducive to timely discovering learners’ dropout tendency and recommending relevant courses of interest to improve their graduation rate, so as to optimize the learning experience of learners, promote the development of personalized education and effective teaching of the e-learning teaching platform, and provide a certain reference value for accelerating the reform process of education informatization. In order to improve the speed of searching for parameters and the best parameters, this paper proposes a particle swarm algorithm (to improve the support vector machine parameters in a sense) and finds the best parameters which also achieved the goal from academic expression to academic performance.
33
BOHON, CARA, JUDY GARBER et JASON L. HOROWITZ. « Predicting School Dropout and Adolescent Sexual Behavior in Offspring of Depressed and Nondepressed Mothers ». Journal of the American Academy of Child & ; Adolescent Psychiatry 46, no 1 (janvier 2007) : 15–24. http://dx.doi.org/10.1097/01.chi.0000246052.30426.6e.
Texte intégral
34
Lorenzo de Reizábal, Margarita, et Manuel Benito Gómez. « Learning Analytics and Higher Music Education : Perspectives and Challenges ». ARTSEDUCA, no 34 (7 décembre 2022) : 219–28. http://dx.doi.org/10.6035/artseduca.6831.
Texte intégralRésumé :
Continually monitoring student learning, improving tutoring, predicting academic risks such as performance drops or dropouts, assessing more objectively or understanding the behavior of student groups are some of the tasks that have been beyond the reach of music teachers. The current technology of massive data processing (Big Data) and its analysis (Learning Analytics-LA) allows to achieve these goals with relative ease. The possibility of extracting individual behavior patterns facilitates attention to diversity, reduces school dropout and failure, and opens the possibility of implementing new educational strategies. The phenomenon of data-based education has led to different types of studies. This paper reflects on three trends or fundamental perspectives in the use of the collection of massive information applied to learning and teaching. We offer an overview of research and applications of Learning Analytics specifically in the field of music education, as well as a reflection on its possible practical uses in higher music education in conservatories. For this purpose, we discuss some practical examples of how this technological methodology could be incorporated into music and music education research, and its influence on possible new educational paradigms that lead to innovation on teaching-learning process through new technological resources.
35
Hewapathirana, Isuru. « Utilizing Prediction Intervals for Unsupervised Detection of Fraudulent Transactions : A Case Study ». Asian Journal of Engineering and Applied Technology 11, no 2 (28 octobre 2022) : 1–10. http://dx.doi.org/10.51983/ajeat-2022.11.2.3348.
Texte intégralRésumé :
Money laundering operations have a high negative impact on the growth of a country’s national economy. As all financial sectors are increasingly being integrated, it is vital to implement effective technological measures to address these fraudulent operations. Machine learning methods are widely used to classify an incoming transaction as fraudulent or non-fraudulent by analyzing the behaviour of past transactions. Unsupervised machine learning methods do not require label information on past transactions, and a classification is made solely based on the distribution of the transaction. This research presents three unsupervised classification methods: ordinary least squares regression-based (OLS) fraud detection, random forest-based (RF) fraud detection and dropout neural network-based (DNN) fraud detection. For each method, the goal is to classify an incoming transaction amount as fraudulent or non-fraudulent. The novelty in the proposed approach is the application of prediction interval calculation for automatically validating incoming transactions. The three methods are applied to a real-world dataset of credit card transactions. The fraud labels available for the dataset are removed during the model training phase but are later used to evaluate the performance of the final predictions. The performance of the proposed methods is further compared with two other unsupervised state-of-the-art methods. Based on the experimental results, the OLS and RF methods show the best performance in predicting the correct label of a transaction, while the DNN method is the most robust method for detecting fraudulent transactions. This novel concept of calculating prediction intervals for validating an incoming transaction introduces a new direction for unsupervised fraud detection. Since fraud labels on past transactions are not required for training, the proposed methods can be applied in an online setting to different areas, such as detecting money laundering activities, telecommunication fraud and intrusion detection.
36
So, Chi Chiu, Tsz On Li, Chufang Wu et Siu Pang Yung. « Differential Spectral Normalization (DSN) for PDE Discovery ». Proceedings of the AAAI Conference on Artificial Intelligence 35, no 11 (18 mai 2021) : 9675–84. http://dx.doi.org/10.1609/aaai.v35i11.17164.
Texte intégralRésumé :
Partial differential equations (PDEs) play a prominent role in many disciplines for describing the governing systems of interest. Traditionally, PDEs are derived based on first principles. In the era of big data, the needs of uncovering PDEs from massive data-set are emerging and become essential. One of the latest advance in PDE discovery models is PDE-Net, which has shown promising predictive power with its moment-constrained convolutional filters, but may suffer from noisy data and numerical instability intrinsic in numerical differentiation. We propose a novel and robust regularization method tailored for moment-constrained convolutional filters, namely, Differential Spectral Normalization (DSN), to allow accurate estimation of coefficient functions and stable prediction of dynamics in a long time horizon. We investigated the effectiveness of DSN against batch normalization, dropout, spectral normalization, weight decay, weight normalization, jacobian regularization and orthonormal regularization and supported with empirical evidence that DSN owns the highest effectiveness by learning the convolutional filters in a robust manner. Numerical experiments further reveal that with DSN there is a substantial potential to uncover the hidden PDEs in a scarce data setting and predict the dynamical behavior for a long time horizon, even in a noisy environment where all data samples are contaminated with noise.
37
Leote, Ana Carolina, Xiaohui Wu et Andreas Beyer. « Regulatory network-based imputation of dropouts in single-cell RNA sequencing data ». PLOS Computational Biology 18, no 2 (17 février 2022) : e1009849. http://dx.doi.org/10.1371/journal.pcbi.1009849.
Texte intégralRésumé :
Single-cell RNA sequencing (scRNA-seq) methods are typically unable to quantify the expression levels of all genes in a cell, creating a need for the computational prediction of missing values (‘dropout imputation’). Most existing dropout imputation methods are limited in the sense that they exclusively use the scRNA-seq dataset at hand and do not exploit external gene-gene relationship information. Further, it is unknown if all genes equally benefit from imputation or which imputation method works best for a given gene. Here, we show that a transcriptional regulatory network learned from external, independent gene expression data improves dropout imputation. Using a variety of human scRNA-seq datasets we demonstrate that our network-based approach outperforms published state-of-the-art methods. The network-based approach performs particularly well for lowly expressed genes, including cell-type-specific transcriptional regulators. Further, the cell-to-cell variation of 11.3% to 48.8% of the genes could not be adequately imputed by any of the methods that we tested. In those cases gene expression levels were best predicted by the mean expression across all cells, i.e. assuming no measurable expression variation between cells. These findings suggest that different imputation methods are optimal for different genes. We thus implemented an R-package called ADImpute (available via Bioconductor https://bioconductor.org/packages/release/bioc/html/ADImpute.html) that automatically determines the best imputation method for each gene in a dataset. Our work represents a paradigm shift by demonstrating that there is no single best imputation method. Instead, we propose that imputation should maximally exploit external information and be adapted to gene-specific features, such as expression level and expression variation across cells.
38
Brodeur, Normand, Gilles Rondeau, Serge Brochu, Jocelyn Lindsay et Jason Phelps. « Does the Transtheoretical Model Predict Attrition in Domestic Violence Treatment Programs ? » Violence and Victims 23, no 4 (août 2008) : 493–507. http://dx.doi.org/10.1891/0886-6708.23.4.493.
Texte intégralRésumé :
Attrition in intervention programs for domestically violent men is considered to be a serious and enduring problem. Researchers have found a number of sociodemographic variables that partially explain this phenomenon; however, models based on these variables have a limited predictive power. Scott (2004) argues that a firm theoretical base is needed in future investigations of the problem and suggests the use of the transtheoretical model of behavior change (TTM), which was found to predict dropout with accuracy in other areas of behavioral change. This study investigated the relationship between four TTM constructs (Stages of Change, Decisional Balance, Self-Efficacy, and Processes of Change) and premature termination with a sample of Canadian French-speaking men (N = 302) in five domestic violence treatment programs. Contrary to the initial hypotheses, the TTM constructs did not predict dropout. Discussion investigates how social desirability bias affects results being obtained by current TTM measures and whether more motivation to change at intake necessarily relates to involvement in treatment for longer periods of time.
39
Raines, Susan J., R. C. Force et Charles A. Burdsal. « Early identification of boys at risk for treatment dropout in a residential treatment center ». Multivariate Experimental Clinical Research Journal 12, no 1 (2000) : 1–11. http://dx.doi.org/10.62704/10057/18883.
Texte intégralRésumé :
This study introduces the Early Adaptation Measure (EAM), an instrument for early prediction of treatment completion in residential treatment facilities. The EAM is based on clinicians' observations of clients' behaviors during the first six weeks of residence. An exploratory factor analysis was conducted on EAM data collected on 266 residents of a residential treatment center serving male adolescents. The following six factors were extracted: Rule Conformant, Peer Conflict, Treatment Plan Endorser, Sociopathy, and Positive Attitude. Factor scores were computed for each youth on these factors, and a discriminant function analysis was performed on the data. Results of this analysis showed that the EAM has some ability to identify which boys will and will not complete treatment. The implications of using the EAM to improve treatment planning are discussed.
40
Khan, Mansoor, Tianqi Liu et Farhan Ullah. « A New Hybrid Approach to Forecast Wind Power for Large Scale Wind Turbine Data Using Deep Learning with TensorFlow Framework and Principal Component Analysis ». Energies 12, no 12 (12 juin 2019) : 2229. http://dx.doi.org/10.3390/en12122229.
Texte intégralRésumé :
Wind power forecasting plays a vital role in renewable energy production. Accurately forecasting wind energy is a significant challenge due to the uncertain and complex behavior of wind signals. For this purpose, accurate prediction methods are required. This paper presents a new hybrid approach of principal component analysis (PCA) and deep learning to uncover the hidden patterns from wind data and to forecast accurate wind power. PCA is applied to wind data to extract the hidden features from wind data and to identify meaningful information. It is also used to remove high correlation among the values. Further, an optimized deep learning algorithm with a TensorFlow framework is used to accurately forecast wind power from significant features. Finally, the deep learning algorithm is fine-tuned with learning error rate, optimizer function, dropout layer, activation and loss function. The algorithm uses a neural network and intelligent algorithm to predict the wind signals. The proposed idea is applied to three different datasets (hourly, monthly, yearly) gathered from the National Renewable Energy Laboratory (NREL) transforming energy database. The forecasting results show that the proposed research can accurately predict wind power using a span ranging from hours to years. A comparison is made with popular state of the art algorithms and it is demonstrated that the proposed research yields better predictions results.
41
Wang, Xinzheng, Bing Guo et Yan Shen. « Predicting the At-Risk Online Students Based on the Click Data Distribution Characteristics ». Scientific Programming 2022 (20 mars 2022) : 1–12. http://dx.doi.org/10.1155/2022/9938260.
Texte intégralRésumé :
High fail and dropout rates are the major problems in distance education. Due to a large number of online learners and limited teacher resources, it is essential to accurately identify these potential at-risk students in advance and provide timely aids, which will help to improve the educational outcome. In the online learning environment, students’ online learning behaviors can be recorded easily, with the click data being the most common one. Students’ learning behavior can reflect their learning situation and may differ among different students and periods. This paper proposed a model that uses the short-period activity characteristic and long-term changing pattern to predict the potential at-risk students. The model contains two stages: information extraction and information utilization. The first stage extracts data from the log files and organizes it in a form suitable for the model. In the second stage, according to the different characteristics of students’ short-term and long-term learning behavior, a convolution residual recurrent neural network (CRRNN) model is proposed. The convolutional neural network is used to obtain the representation of the student’s learning behavior in a certain period. Then, the residual recurrent neural network is used to get the behavior changing pattern over the periods. The experimental results indicate that the proposed model has higher performance than the three widely used baseline methods on the OULA dataset and has good practical application value for teaching and management.
42
Praveena, T. Lakshmi, et N. V. Muthu Lakshmi. « Perception of Autism Spectrum Disorder Children by Envisaging Emotions from the Facial Images ». International Journal of Engineering and Advanced Technology 10, no 2 (30 décembre 2020) : 1–5. http://dx.doi.org/10.35940/ijeat.b1960.1210220.
Texte intégralRésumé :
Image processing is a rapidly growing technology and is one among the thrust areas of research in Medical Fields, various Engineering disciplines, life Sciences and Scientific applications. Many technical applications have already adopted image processing and it plays a key role in predicting unknown or hidden facts easily and efficiently. Facial image processing is an innovative application of image processing and is being widely used in many applications successfully. Some of the applications are used for person identification, identifying authorized persons, identifying criminals and so on. As we all know that person’s emotion shows personality & behavior, moods where he or she expresses feelings by emotions maximum on face only. Facial expression can also be used in various fields like emotion recognition, market analysis, prediction neurological disorder percentage, psychological problems and so on. So, it has become an emerging research area to study. Neurological disorder is a more complicated disease because it affects both physical body and mental body. In this paper a new methodology is proposed using optimized deep learning methods to predict ASD in children of age 1 to 10 years. Proposed model performance is tested on ASD children and normal children facial image dataset collected from Kaggle datasets and also tested on dataset collected from autism parents’ face book group. Convolutional Neural Networks (CNN) is applied on extracted face landmarks using optimization techniques, dropout, batch normalization and parameter updating. Most significant six types of emotions are considered for analysis in predicting ASD children accurately.
43
Sun, J., C. Ju, Y. Yue, K. L. Gunter, D. J. Michalek et J. W. Sutherland. « Character and Behavior of Mist Generated by Application of Cutting Fluid to a Rotating Cylindrical Workpiece, Part 2 : Experimental Validation ». Journal of Manufacturing Science and Engineering 126, no 3 (1 août 2004) : 426–34. http://dx.doi.org/10.1115/1.1765151.
Texte intégralRésumé :
In Part 1 of this paper a model was developed to describe the formation mechanisms and dynamic behavior of cutting fluid mist. This part of the paper focuses on an experimental investigation of the mist generated by the interaction of the fluid with the rotating cylindrical workpiece during a turning operation and the simulation of the dynamic behavior of the mist droplets, resulting in the prediction of the droplet size distribution and the mass concentration within the machining environment. These simulation results are compared to experimental measurements in order to validate the theoretical model presented in Part 1 of the paper. It is observed that the model predictions accurately characterize the observed experimental behavior.
44
Wang, Qian, Wenfang Zhao et Jiadong Ren. « Intrusion detection algorithm based on image enhanced convolutional neural network ». Journal of Intelligent & ; Fuzzy Systems 41, no 1 (11 août 2021) : 2183–94. http://dx.doi.org/10.3233/jifs-210863.
Texte intégralRésumé :
Intrusion Detection System (IDS) can reduce the losses caused by intrusion behaviors and protect users’ information security. The effectiveness of IDS depends on the performance of the algorithm used in identifying intrusions. And traditional machine learning algorithms are limited to deal with the intrusion data with the characteristics of high-dimensionality, nonlinearity and imbalance. Therefore, this paper proposes an Intrusion Detection algorithm based on Image Enhanced Convolutional Neural Network (ID-IE-CNN). Firstly, based on the image processing technology of deep learning, oversampling method is used to increase the amount of original data to achieve data balance. Secondly, the one-dimensional data is converted into two-dimensional image data, the convolutional layer and the pooling layer are used to extract the main features of the image to reduce the data dimensionality. Thirdly, the Tanh function is introduced as an activation function to fit nonlinear data, a fully connected layer is used to integrate local information, and the generalization ability of the prediction model is improved by the Dropout method. Finally, the Softmax classifier is used to predict the behavior of intrusion detection. This paper uses the KDDCup99 data set and compares with other competitive algorithms. Both in the performance of binary classification and multi-classification, ID-IE-CNN is better than the compared algorithms, which verifies its superiority.
45
Chen, Chin-Chih, Sheng-Lun Cheng, Yaoying Xu, Kathleen Rudasill, Reed Senter, Fa Zhang, Melissa Washington-Nortey et Nikki Adams. « Transactions between Problem Behaviors and Academic Performance in Early Childhood ». International Journal of Environmental Research and Public Health 19, no 15 (4 août 2022) : 9583. http://dx.doi.org/10.3390/ijerph19159583.
Texte intégralRésumé :
This study aimed to further the understanding of transactional relationships that exist between problem behaviors and academic performance in early childhood. Early academic and behavior difficulties increase the risk of school disengagement, academic failure, and dropout. Although children’s academic and behavioral difficulties have been shown to be intercorrelated, little research has focused on how the relationship reciprocates and progresses in early childhood. This study investigated how problem behaviors (i.e., externalizing and internalizing) influence and are influenced by academic performance (i.e., poor reading and math) from kindergarten to third grade. Participants included 18,135 students (51.22% boys) derived from a nationally representative sample in the Early Childhood Longitudinal Study, Kindergarten Class of 2011 (ECLS-K: 2011). Teacher ratings of children’s internalizing (low self-esteem, anxiety, loneliness, or sadness) and externalizing (fighting, arguing, showing anger, impulsively acting, and disruptive behaviors) problem behaviors, as well as direct assessments of children’s academic performance (reading and math), were collected yearly. Cross-lagged panel modeling (CLPM) was employed to examine reciprocal relationships between problem behaviors and academic performance over time from kindergarten to third grade. The results supported the transactional relationships in early childhood, with higher externalizing as well as internalizing problem behaviors predicting lower academic performance and lower academic performance predicting higher externalizing and internalizing problem behaviors. The implications for research, prevention, and early intervention regarding the progression of academic and behavioral problems are discussed.
46
Points, Laurie J., James Ward Taylor, Jonathan Grizou, Kevin Donkers et Leroy Cronin. « Artificial intelligence exploration of unstable protocells leads to predictable properties and discovery of collective behavior ». Proceedings of the National Academy of Sciences 115, no 5 (16 janvier 2018) : 885–90. http://dx.doi.org/10.1073/pnas.1711089115.
Texte intégralRésumé :
Protocell models are used to investigate how cells might have first assembled on Earth. Some, like oil-in-water droplets, can be seemingly simple models, while able to exhibit complex and unpredictable behaviors. How such simple oil-in-water systems can come together to yield complex and life-like behaviors remains a key question. Herein, we illustrate how the combination of automated experimentation and image processing, physicochemical analysis, and machine learning allows significant advances to be made in understanding the driving forces behind oil-in-water droplet behaviors. Utilizing >7,000 experiments collected using an autonomous robotic platform, we illustrate how smart automation cannot only help with exploration, optimization, and discovery of new behaviors, but can also be core to developing fundamental understanding of such systems. Using this process, we were able to relate droplet formulation to behavior via predicted physical properties, and to identify and predict more occurrences of a rare collective droplet behavior, droplet swarming. Proton NMR spectroscopic and qualitative pH methods enabled us to better understand oil dissolution, chemical change, phase transitions, and droplet and aqueous phase flows, illustrating the utility of the combination of smart-automation and traditional analytical chemistry techniques. We further extended our study for the simultaneous exploration of both the oil and aqueous phases using a robotic platform. Overall, this work shows that the combination of chemistry, robotics, and artificial intelligence enables discovery, prediction, and mechanistic understanding in ways that no one approach could achieve alone.
47
TLANEPANTLA PANTOJA, DANIEL, SILVIA SOLEDAD MORENO GUTIERREZ, SOCRATES LOPEZ PEREZ et HÉCTOR HUGO SILICEO CANTERO. « APRENDIZAJE AUTOMÁTICO PARA EL DIGANÓSTICO PREDICTIVO, APLICACIÓN EN ZONAS INDUSTRIALES ». DYNA DYNA-ACELERADO (11 janvier 2024) : 1p. http://dx.doi.org/10.6036/11135.
Texte intégralRésumé :
Environmental pollution is a risk factor for chronic diseases (CD), which today are identified as the main cause of death in the world, 80% in low- and middle-income countries, in people of all ages. Given that industrial areas maintain a high rate of air pollution, their inhabitants are considered highly vulnerable, such is the case of the Metropolitan Area of Tula Hgo., in Mexico. At the request of the World Health Organization to integrate vulnerable populations to the quality of life through innovative strategies, the present study aims to build prediction models for CD of higher frequency in the area, to support predictive diagnosis through machine learning algorithms, recognized for their high performance in health areas. Based on the CRISP-DM methodology, requirements, characteristics and data behavior were analyzed, exhaustive cleaning and minmax scaler normalization were performed, the models were trained and validated with 80% - 20% of records, dropout and early stopping were applied to combat overtraining. The comparative analysis between 9 built models demonstrated the best performance of 3 of them, one for each EC; the Artificial Neural Network (ANN) for respiratory diseases and Random Forest (RF) for diabetes and high blood pressure. Its results of accuracy, precision, sensitivity, specificity and F1-score were 99%, 99%, 100%, 99% and 99.49% respectively for ANN, the RF model for diabetes obtained 98%, 100%, 97%, 100% and 98.7% and for arterial hypertension 95%, 97%, 94, 97% and 95.47%, these models were integrated into a graphical interface. The proposal constitutes a high-precision technological strategy for prevention and early diagnosis of CD in industrial areas, aimed at reducing mortality and improving the quality of life of the inhabitants.
48
He, Yanbai, Rui Chen, Xinya Li, Chuanyan Hao, Sijiang Liu, Gangyao Zhang et Bo Jiang. « Online At-Risk Student Identification using RNN-GRU Joint Neural Networks ». Information 11, no 10 (9 octobre 2020) : 474. http://dx.doi.org/10.3390/info11100474.
Texte intégralRésumé :
Although online learning platforms are gradually becoming commonplace in modern society, learners’ high dropout rates and serious academic performance require more attention within the virtual learning environment (VLE). This study aims to predict students’ performance in a specific course as it is continuously running, using the statistic personal biographical information and sequential behavior data with VLE. To achieve this goal, a novel recurrent neural network (RNN)-gated recurrent unit (GRU) joint neural network is proposed to fit both static and sequential data, where the data completion mechanism is also adopted to fill the missing stream data. To incorporate the sequential relationship of learning data, three kinds of time-series deep neural network algorithms: simple RNN, GRU, and LSTM are first taken into consideration as baseline models. Their performances are compared in identifying at-risk students. Experimental results on Open University Learning Analytics Dataset (OULAD) show that simple methods like GRU and simple RNN have better results than the relatively complex LSTM model. The results also reveal that different models have different peak performance time, which results in the proposed joint model that achieves over 80% prediction accuracy of at-risk students at the end of the semester.
49
Sujith, R. I., G. A. Waldherr, J. I. Jagoda et B. T. Zinn. « An Experimental Investigation of the Behavior of Droplets in Axial Acoustic Fields ». Journal of Vibration and Acoustics 119, no 3 (1 juillet 1997) : 285–92. http://dx.doi.org/10.1115/1.2889722.
Texte intégralRésumé :
This paper describes an experimental investigation of the behavior of water droplets in axial acoustic fields. It was motivated by the increasing interest in the use of pulsations to improve the performance of energy intensive, industrial processes. The presence of an acoustic field is believed to enhance heat and mass transfer to and from the droplets, probably because of the relative motion between the droplets and the gas phase. This relative motion is characterized by the ratio of the amplitude of the oscillatory droplet velocity to that of the acoustic velocity (entrainment factor), and by the phase between the droplet and gas phase oscillations. An experimental set-up was developed to investigate the effect of acoustic oscillations on the motion of individual droplets. In these experiments a droplet produced by a piezo-ceramic droplet generator is allowed to fall through a transparent test section in which an acoustic field has been set up using a pair of acoustic drivers. Images of the droplets in the test section acquired at consecutive instants using a high speed, intensified imaging system were used to determine the time dependent droplet trajectory and velocity. The acoustic velocity was calculated from measured acoustic pressure distributions. The entrainment factor and the phase difference were then determined from these data. The results show how the entrainment factor decreases and the phase difference increases with increasing droplet diameter and frequency, indicating that larger diameters and higher frequencies reduce the “ability” of the droplets to follow the gas phase oscillations. The measured data are in excellent agreement with the prediction of the Hjelmfelt and Mockros model. Both theoretical predictions and measured data were correlated with the Stokes number, which accounts for the effects of droplet diameter and frequency. It was also shown that acoustic oscillations decrease the mean terminal velocity of the droplets.
50
Lv, Haicheng, Zhirong Yang, Jing Zhang, Gang Qian, Xuezhi Duan, Zhongming Shu et Xinggui Zhou. « Liquid Flow and Mass Transfer Behaviors in a Butterfly-Shaped Microreactor ». Micromachines 12, no 8 (27 juillet 2021) : 883. http://dx.doi.org/10.3390/mi12080883.
Texte intégralRésumé :
Based on the split-and-recombine principle, a millimeter-scale butterfly-shaped microreactor was designed and fabricated through femtosecond laser micromachining. The velocity fields, streamlines and pressure fields of the single-phase flow in the microreactor were obtained by a computational fluid dynamics simulation, and the influence of flow rates on the homogeneous mixing efficiency was quantified by the mixing index. The flow behaviors in the microreactor were investigated using water and n-butanol, from which schematic diagrams of various flow patterns were given and a flow pattern map was established for regulating the flow behavior via controlling the flow rates of the two-phase flow. Furthermore, effects of the two-phase flow rates on the droplet flow behavior (droplet number, droplet size and standard deviation) in the microreactor were investigated. In addition, the interfacial mass transfer behaviors of liquid–liquid flow were evaluated using the standard low interfacial tension system of “n-butanol/succinic acid/water”, where the dependence between the flow pattern and mass transfer was discussed. The empirical relationship between the volumetric mass transfer coefficient and Reynold number was established with prediction error less than 20%.