<span>Research Productivity (RP) is the key element in the establishment of ranking and rating system in the Higher Education (HE) sector. Despite of the many initiatives taken to enliven the research culture among academic staff, there are still constraints and resistance towards conducting research. Therefore, this study attempts to identify the factors affecting RP and develop an appropriate model to determine the RP of an academic staff in Universiti Teknologi MARA (UiTM). In this study, 5 research related indicators were used in the determination of RP. Since the population size of UiTM is large, the primary data was collected by using questionnaire survey and stratified random sampling. The variables that were found to be significant in determining RP of an academic staff were age cohort, highest qualification, cluster and track emphasis. Satisfaction towards annual KPI, UiTM current policy and monthly income were also found to influence the RP of an academic staff. In addition, perceiving the role of principal investigator as a chore and burden and supervising and graduating a PhD student perception as burden and pleasure were also found to be affecting RP. Using these variables, Logistic Regression Model was used to determine the RP of an academic staff in UiTM. In conclusion, personal, environmental and behavioural factors were found to have influence on the RP among academic staff of UiTM. Therefore, generally it is possible to maximize the RP of academic staff by identifying the factors influencing RP followed by strategic management and proper monitoring system.</span>
Today, predictive analytics applications became an urgent desire in higher educational institutions. Predictive analytics used advanced analytics that encompasses machine learning implementation to derive high-quality performance and meaningful information for all education levels. Mostly know that student grade is one of the key performance indicators that can help educators monitor their academic performance. During the past decade, researchers have proposed many variants of machine learning techniques in student grade prediction. However, there is a lack of studies in identifying the effective predictive model, especially in addressing imbalanced multi-classification for student grade prediction. Therefore, this paper presents a comprehensive analysis of machine learning techniques to predict the final student grades in the first semester courses by providing better prediction accuracy. Two modules will be highlighted in this paper. First, we compare the accuracy performance of five well-known machine learning techniques, namely Decision Tree (J48), Support Vector Machine (SVM), Naïve Bayes (N.B.), K-Nearest Neighbor (kNN), and Logistic Regression (L.R.), to our real dataset. Second, we proposed a multi-class prediction model for an imbalanced multi-class dataset using two types of data-level solutions to improve the prediction accuracy performance. The obtained results indicate that the proposed Synthetic Minority Oversampling Technique (SMOTE) and wrapper-based feature selection (F.S.) integrates with kNN shows significant improvement with the highest accuracy of 99.6%. In contrast, all F.S. algorithms perform 99.4% robust performance when working with SVM independently. These findings indicate that the proposed model generally discovers various F.S. algorithms and SMOTE in addressing imbalanced multi-classification, which will help the researcher to improve the performance for student grade prediction.
The use of back-error propagation neural networks f o r the automatic modulation recognition ( A M R ) of an intercepted signal is demonstrated. In all, 10 modulation types are considered and a variety of spectral preprocessors are investigated for feature e d r a c t i o n . For the given training and test sets, the Welch periodogram is found t o give the best results. For classification, experimental results show that neural networks match and even outdo the performance of the conventional k-Nearest Neighbour (k-NN) classifier f o r this preprocessor. Moreover, optimization of selected neural networks is demonstrated using the optimal brain damage (OBD) pruning technique.0-7803-0953-7/93$03.00 0 1993 IEEE 111
<span>The curse of dimensionality and the empty space phenomenon emerged as a critical problem in text classification. One way of dealing with this problem is applying a feature selection technique before performing a classification model. This technique helps to reduce the time complexity and sometimes increase the classification accuracy. This study introduces a feature selection technique using K-Means clustering to overcome the weaknesses of traditional feature selection technique such as principal component analysis (PCA) that require a lot of time to transform all the inputs data. This proposed technique decides on features to retain based on the significance value of each feature in a cluster. This study found that k-means clustering helps to increase the efficiency of KNN model for a large data set while KNN model without feature selection technique is suitable for a small data set. A comparison between K-Means clustering and PCA as a feature selection technique shows that proposed technique is better than PCA especially in term of computation time. Hence, k-means clustering is found to be helpful in reducing the data dimensionality with less time complexity compared to PCA without affecting the accuracy of KNN model for a high frequency data.</span>
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.