Prediction of the Academic Achievement of Pupils Using Data Mining Techniques

Introduction: During this epidemic, a problem in fundamental education affecting all globe is occurring, and we note that education and learning were online and conducted in students. Academic performance of students must be forecast, so that the instructor may better identify the missing pupils and offer teachers a proactive opportunity to develop additional resources for the student to maximize their chances of graduation. Students' academic achievement in higher learning (EH) has been extensively studied in addressing academic inadequacies, rising drop-out rates, graduation delays, and other difficult questions. Simply said, the performance of students refers to the amount to which short and long-term educational objectives are met. Academics nonetheless judge student achievement from different viewpoints, from grades, average grade points (GPAs) to prospective jobs. The literature encompasses numerous computing attempts to improve student performance in schools and colleges, primarily through data mining and analysis learning. However, the efficiency of current smart techniques and models is still unanimous. Method: This study employs multiple methods for machine learning to forecast student progress. With its accurate data sample prediction, five integrated classification algorithms have been created to forecast students' academic success (support vectors, decision-making trees algorithm and perceptron algorithm, logistic regression algorithm and a random forest algorithm). Results: Students' academic achievement has been reviewed and assessed. The performance of five learning machines mentioned in Section 4 is discussed here. First, we displayed the data after pre-processing by simply displaying distributions to form the data packet and then evaluated 5 important learning methods and described the variables in the data set. The entire series of 480 characteristics were examined.

Distance transform-watershed segmentation and multi-layer perceptron algorithm to separate touching orange fruit in digital images

An algorithm to separate touching oranges using a distance transform-watershed segmentation is presented. In this study, there are four classes of oranges, such as class A, B, C, and D, respectively. The size of each class is based on the Indonesian National Standard (SNI), the sample used is 168 oranges of which 140 are for training and 28 oranges are for testing. The image of citrus fruits was captured using Kinect v2 camera with a camera resolution of 1920 × 1080 pixels, the distance from the camera to the background is 23 cm. The images were captured in PNG format. The watersheds were computed based on the distance transformed by orange regions. The corresponding basins were finally used to split the falsely connected corn kernel by intersecting the basins with the corn kernel regions. Experimental results show that the multi-layer perceptrons have classification accuracy rates of 92.85%. The algorithm appears to be robust enough to separate most of the multiple touching scenarios.

PENGENALAN AKTIVITAS MANUSIA DAN PEMBUATAN LOG OTOMATIS DARI REKAMAN VIDEO MENGGUNAKAN MULTILAYER PERCEPTRON

Advances in technology have made it easier to surveillance purpose by installing recording equipment that can be placed in certain strategic locations. The existence of this technology also brings changes in the analysis phase of video recordings and images that have been obtained. The processing of recorded videos no longer uses manual methods but can be done automatically using image processing and artificial intelligence algorithms. Based on the obtained video recordings, analysis can be carried out for surveillance purpose, object tracking, human activity recognition, etc. This paper discusses the development of an automatic human activity recognition system based on video recordings using Multilayer Perceptron method. The recorded video will be transformed into a collection of images which are then processed with the Multilayer Perceptron algorithm for the recognition process. The output of the designed system is the recognition of activities carried out by humans at a certain time and saved them in a log with a certain timestamp. In this paper, there are five types of human activities that can be recognized automatically by the system, namely raising hands, clapping, standing, sitting, and studying. The experimental results show that the accuracy rate of the proposed system achieved 97.45% for image datasets obtained freely from the internet, while 100% accuracy was obtained for image datasets collected with IP Cameras. Keywords: Human activity recognition; video recording; Multilayer PerceptronAbstrakKemajuan teknologi memungkinkan kegiatan pengawasan terhadap lingkungan menjadi lebih mudah yaitu dengan melakukan pemasangan peralatan rekam yang dapat ditempatkan pada lokasi-lokasi strategis tertentu. Keberadaan peralatan teknologi ini juga membawa perubahan dalam proses analisis terhadap rekaman video maupun gambar yang telah didapatkan. Proses pengolahan terhadap video rekaman tidak lagi menggunakan cara manual, namun dapat dilakukan secara otomatis dengan menggunakan teknologi pengolahan citra dan kecerdasan buatan. Berdasarkan rekaman video maupun gambar yang diperoleh, analisis dapat dilakukan untuk mengawasi keamanan lokasi, mencatat perubahan kondisi objek tertentu, mengenali aktivitas manusia pada saat tertentu, dan lain sebagainya. Makalah ini membahas pengembangan sebuah sistem pengenalan aktivitas manusia secara otomatis berdasarkan rekaman video menggunakan metode Multilayer Perceptron. Rekaman video sebelumnya akan dicacah menjadi kumpulan citra yang kemudian diproses dengan algoritma Multilayer Perceptron untuk proses pengenalannya. Luaran dari sistem aplikasi yang dirancang berupa pengenalan aktivitas yang dilakukan manusia pada waktu tertentu dan pencatatan aktivitas tersebut dalam sebuah log dengan timestamp tertentu. Dalam makalah ini, terdapat lima jenis aktivitas manusia yang dapat dikenali secara otomatis oleh sistem, yaitu mengangkat tangan, bertepuk tangan, berdiri, duduk, dan belajar. Hasil pengujian menunjukkan bahwa keberhasilan pendeteksian aktivitas manusia dengan metode Multilayer Perceptron memiliki tingkat akurasi 97.45% untuk dataset citra yang diperoleh secara bebas dari internet, sedangkan untuk dataset citra yang dikumpulkan dengan IP Camera memiliki tingkat akurasi sebesar 100%.

Unraveling City-Specific Microbial Signatures and Identifying Sample Origins for the Data From CAMDA 2020 Metagenomic Geolocation Challenge

The composition of microbial communities has been known to be location-specific. Investigating the microbial composition across different cities enables us to unravel city-specific microbial signatures and further predict the origin of unknown samples. As part of the CAMDA 2020 Metagenomic Geolocation Challenge, MetaSUB provided the whole genome shotgun (WGS) metagenomics data from samples across 28 cities along with non-microbial city data for 23 of these cities. In our solution to this challenge, we implemented feature selection, normalization, clustering and three methods of machine learning to classify the cities based on their microbial compositions. Of the three methods, multilayer perceptron obtained the best performance with an error rate of 19.60% based on whether the correct city received the highest or second highest number of votes for the test data contained in the main dataset. We then trained the model to predict the origins of samples from the mystery dataset by including these samples with the additional group label of “mystery.” The mystery dataset compromised of samples collected from a subset of the cities in the main dataset as well as samples collected from new cities. For samples from cities that belonged to the main dataset, error rates ranged from 18.18 to 72.7%. For samples from new cities that did not belong to the main dataset, 57.7% of the test samples could be correctly labeled as “mystery” samples. Furthermore, we also predicted some of the non-microbial features for the mystery samples from the cities that did not belong to main dataset to draw inferences and narrow the range of the possible sample origins using a multi-output multilayer perceptron algorithm.

Prevention Is Better Than Cure: Machine Learning Approach to Conflict Prediction in Sub-Saharan Africa

This article offers policymakers and researchers pragmatic and sustainable approaches to identify and mitigate conflict threats by looking beyond p-values and plausible instruments. We argue that predicting conflict successfully depends on the choice of algorithms, which, if chosen accurately, can reduce economic and social instabilities caused by post-conflict reconstruction. After collating data with variables linked to conflict, we used a grid level dataset of 5928 observations spanning 48 countries across sub-Saharan Africa to predict civil conflict. The goals of the study were to assess the performance of supervised classification machine learning (ML) algorithms in comparison with logistic model, assess the implication of selecting a specific performance metric on policy initiatives, and evaluate the value of interpretability of the selected model. After comparing class imbalance resampling methods, the synthetic minority over-sampling technique (SMOTE) was employed to improve out-of-sample prediction for the trained model. The results indicate that if our selected performance metric is recall, gradient tree boosting is the best algorithm; however, if precision or F1 score is the selected metric, then the multilayer perceptron algorithm produces the best model.