Data Mining - Concepts and Techniques.

1. Interaction. The interactions learners have with each other build interpersonal skills, such as listening, politely interrupting, expressing ideas, raising questions, disagreeing, paraphrasing, negotiating, and asking for help. 2. Interdependence. Learners must depend on one another to accomplish a common objective. Each group member has specific tasks to complete, and successful completion of each member’s tasks results in attaining the overall group objective.

将“Cooperative Learning”融入课堂——浅谈英语素质教育

The student’s performance prediction is an important research topic because it can help teachers prevent students from dropping out before final exams and identify students that need additional assistance. The objective of this study is to predict the difficulties that students will encounter in a subsequent digital design course session. We analyzed the data logged by a technology-enhanced learning (TEL) system called digital electronics education and design suite (DEEDS) using machine learning algorithms. The machine learning algorithms included an artificial neural networks (ANNs), support vector machines (SVMs), logistic regression, Naive bayes classifiers and decision trees. The DEEDS system allows students to solve digital design exercises with different levels of difficulty while logging input data. The input variables of the current study were average time, total number of activities, average idle time, average number of keystrokes and total related activity for each exercise during individual sessions in the digital design course; the output variables were the student(s) grades for each session. We then trained machine learning algorithms on the data from the previous session and tested the algorithms on the data from the upcoming session. We performed k-fold cross-validation and computed the receiver operating characteristic and root mean square error metrics to evaluate the models’ performances. The results show that ANNs and SVMs achieve higher accuracy than do other algorithms. ANNs and SVMs can easily be integrated into the TEL system; thus, we would expect instructors to report improved student’s performance during the subsequent session.

Using machine learning to predict student difficulties from learning session data

Data mining offers strong techniques for different sectors involving education. In the education field the research is developing rapidly increasing due to huge number of student’s information which can be used to invent valuable pattern pertaining learning behavior of students. The institutions of education can utilize educational data mining to examine the performance of students which can support the institution in recognizing the student’s performance. In data mining classification is a familiar technique that has been implemented widely to find the performance of students. In this study a new prediction algorithm for evaluating student’s performance in academia has been developed based on both classification and clustering techniques and been ested on a real time basis with student dataset of various academic disciplines of higher educational institutions in Kerala, India. The result proves that the hybrid algorithm combining clustering and classification approaches yields results that are far superior in terms of achieving accuracy in prediction of academic performance of the students.

Predicting Academic Performance of Students Using a Hybrid Data Mining Approach

In today's world, due to the advancement of technology, predicting the students' performance is among the most beneficial and essential research topics. Data Mining is extremely helpful in the field of education, especially for analyzing students' performance. It is a fact that predicting the students' performance has become a severe challenge because of the imbalanced datasets in this field, and there is not any comparison among different resampling methods. This paper attempts to compare various resampling techniques such as Borderline SMOTE, Random Over Sampler, SMOTE, SMOTE-ENN, SVM-SMOTE, and SMOTE-Tomek to handle the imbalanced data problem while predicting students' performance using two different datasets. Moreover, the difference between multiclass and binary classification, and structures of the features are examined. To be able to check the performance of the resampling methods better in solving the imbalanced problem, this paper uses various machine learning classifiers including Random Forest, K-Nearest-Neighbor, Artificial Neural Network, XG-boost, Support Vector Machine (Radial Basis Function), Decision Tree, Logistic Regression, and Naive Bayes. Furthermore, the Random hold-out and Shuffle 5-fold cross-validation methods are used as model validation techniques. The achieved results using different evaluation metrics indicate that fewer numbers of classes and nominal features will lead models to better performance. Also, classifiers do not perform well with imbalanced data, so solving this problem is necessary. The performance of classifiers is improved using balanced datasets. Additionally, the results of the Friedman test, which is a statistical significance test, confirm that the SVM-SMOTE is more efficient than the other resampling methods. Moreover, The Random Forest classifier has achieved the best result among all other models while using SVM-SMOTE as a resampling method.

/pdf/comparing-different-resampling-methods-in-predicting-3clup1ms0e.pdf

Comparing Different Resampling Methods in Predicting Students’ Performance Using Machine Learning Techniques

Anal Acharya, Department of Computer Science, St Xavier’s College, Kolkata, India. Devadatta Sinha, Department of Computer Science and Engineering, University of Calcutta, Kolkata, India. ABSTRACT In recent years Educational Data Mining (EDM) has emerged as a new field of research due to the development of several statistical approaches to explore data in educational context. One such application of EDM is early prediction of student results. This is necessary in higher education for identifying the “weak” students so that some form of remediation may be organized for them. In this paper a set of attributes are first defined for a group of students majoring in Computer Science in some undergraduate colleges in Kolkata. Since the numbers of attributes are reasonably high, feature selection algorithms are applied on the data set to reduce the number of features. Five classes of Machine Learning Algorithm (MLA) are then applied on this data set and it was found that the best results were obtained with the decision tree class of algorithms. It was also found that the prediction results obtained with this model are comparable with other previously developed models.

/pdf/early-prediction-of-students-performance-using-machine-24evqbzmb9.pdf

Early Prediction of Students Performance using Machine Learning Techniques

recent years, web based learning has emerged as a new field of research due to growth of network and communication technology. These learning systems generate a large volume of student data. Data mining algorithms may be applied on this data set to study interesting patterns. As an example, student enrollment data and his past examination records could be used to predict his grades in the term end examination. However this prediction could mean examining a lot of features of the student data resulting in creation of a model with high computational complexity. In this context this work first defines a student data set with 309 records and 14 features collected by a survey from various graduation level students majoring in Computer Science under University of Calcutta. Different feature selection algorithms are applied on this data set. The best results are obtained by Correlation Based Feature Selection algorithm with 8 features. Subsequently classification algorithms may be applied on this feature subset for predicting student grades.

/pdf/application-of-feature-selection-methods-in-educational-data-1riol1p9kf.pdf

Application of Feature Selection Methods in Educational Data Mining

A popular choice for lateral epicondylitis (LE), corticosteroid injections have been associated with prominent side effects, which has led to the conception of modalities like platelet-rich plasma (PRP). This randomised trial aimed to evaluate and compare the 6-week, 3-month and 1-year outcomes with PRP and corticosteroid injections in LE. We hypothesised that PRP would prove more effective in relieving pain and improving function. At the sports medicine unit of our tertiary care teaching centre, 80 patients with LE were randomised into either receiving PRP (group A) or corticosteroids (group B) injections. Pre-injection visual analogue scale (VAS), disabilities of the arm, shoulder and hand (DASH) score, Mayo elbow performance score (MEPS) and grip strength score (GSS) were recorded. Common extensor origins were identified and infiltrated with 3 ml of either PRP or corticosteroid (triamcinolone in 2% xylocaine) using a peppering technique. Follow-up scores and extent of pain relief were recorded and compared. At 6 weeks, there were greater improvements in group B versus A in mean VAS (13.8 vs. 44.5; p < 0.001), DASH (64.2 vs. 53.3; p < 0.001), MEPS (88.0 vs. 74.5; p = 0.004) and GSS (89.3 vs. 73.4; p = 0.039). These scores showed a reversed pattern at 3 months when group A outcomes superseded group B (VAS p = 0.002; DASH p < 0.001; MEPS p = 0.002; GSS p = 0.045). At 1-year follow-up, group A continued to enjoy better pain relief and function (VAS p = 0.024; DASH p < 0.001; MEPS p = 0.009; GSS p = 0.028). Albeit corticosteroid injections show good short-term results at 6 weeks, patients receiving PRP injections fare better at 3 and 12 months.

PRP versus steroids in a deadlock for efficacy: long-term stability versus short-term intensity-results from a randomised trial.

This study uses homogeneity in personal learning styles and heterogeneity in subject knowledge for collaborative learning group decomposition indicating that groups are “mixed” in nature. Homogenei...

A “Mixed” Strategy for Collaborative Group Formation and Its Learning Outcomes:

The present study examines the geotechnical properties of Indian bentonite clays for their suitability as
buffer material in deep geological repository for high-level nuclear wastes. The bentonite samples are characterized for index properties, compaction, hydraulic conductivity and swelling characteristics. Evaluation of geotechnical properties of the compacted bentonite-sand admixtures, from parts of NW India reveals swelling potentials and hydraulic conductivities in the range of 55 % - 108 % and 1.2 X 10 –10 cm/s to 5.42x 10 –11 cm/s respectively. Strong correlation was observed between ESP (exchangeable sodium percentage) and liquid limit/swell potential of tested specimens. Relatively less well-defined trends emerged between ESP and swell pressure/hydraulic conductivity. The Barmer-1 bentonite despite possessing relatively lower montmorillonite content of 68 %, developed higher Atterberg limit and swell potential, and exhibited comparable swelling pressure and hydraulic conductivity as other bentonites with higher montmorillonite contents (82 to 86 %). The desirable geotechnical properties of Barmer clay as a buffer material is attributed to its large ESP (63 %) and, EMDD (1.17 Mg/m3) attained at the experimental compactive stress(5 MPa).

Anal Acharya

Papers

Early Prediction of Students Performance using Machine Learning Techniques

Application of Feature Selection Methods in Educational Data Mining

PRP versus steroids in a deadlock for efficacy: long-term stability versus short-term intensity-results from a randomised trial.

A “Mixed” Strategy for Collaborative Group Formation and Its Learning Outcomes:

Geotechnical Characterization of Some Indian Bentonites for their Use as Buffer Material in Geological Repository