Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userUsing a Binary Classification Model to Predict the Likelihood of Enrolment to the Undergraduate Program of a Philippine University
67
0
0.0
(
0
)
Added by
Joseph Esquivel Esquivel
Publication date
2020
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
With the recent implementation of the K to 12 Program, academic institutions, specifically, Colleges and Universities in the Philippines have been faced with difficulties in determining projected freshmen enrollees vis-a-vis decision-making factors for efficient resource management. Enrollment targets directly impacts success factors of Higher Education Institutions. This study covered an analysis of various characteristics of freshmen applicants affecting their admission status in a Philippine university. A predictive model was developed using Logistic Regression to evaluate the probability that an admitted student will pursue to enroll in the Institution or not. The dataset used was acquired from the University Admissions Office. The office designed an online application form to capture applicants details. The online form was distributed to all student applicants, and most often, students, tend to provide incomplete information. Despite this fact, student characteristics, as well as geographic and demographic data based on the students location are significant predictors of enrollment decision. The results of the study show that given limited information about prospective students, Higher Education Institutions can implement machine learning techniques to supplement management decisions and provide estimates of class sizes, in this way, it will allow the institution to optimize the allocation of resources and will have better control over net tuition revenue.
rate research
Read More
The sudden change in the landscape of Philippine education, including the implementation of K to 12 program, Higher Education institutions, have been struggling in attracting freshmen applicants coupled with difficulties in projecting incoming enrollees. Private HEIs Enrolment target directly impacts success factors of Higher Education Institutions. A review of the various characteristics of freshman applicants influencing their admission status at a Philippine university were included in this study. The dataset used was obtained from the Admissions Office of the University via an online form which was circulated to all prospective applicants. Using Logistic Regression, a predictive model was developed to determine the likelihood that an enrolled student would seek enrolment in the institution or not based on both students and institutions characteristics. The LR Model was used as the algorithm in the development of the Decision Support System. Weka was utilized on selection of features and building the LR model. The DSS was coded and designed using R Studio and R Shiny which includes data visualization and individual prediction.
Administering standardized examinations is a challenging task, especially for those universities for which colleges affiliated to it are geographically distributed over a wide area. Some of the challenges include maintaining integrity and confidentiality of examination records, preventing mal-practices, issuing unique identification numbers to a large student population and managing assets required for the smooth conduct of examinations. These challenges aggravate when colleges affiliated to universities demand academic and administrative autonomy by demonstrating best practices consistently over a long period. In this chapter, we describe a model for decentralized and autonomous examination system to provide the necessary administrative support. The model is based on two emerging technologies of Blockchain Technology and Internet of Things (IoT). We adopt a software architecture approach to describe the model. The prescriptive architecture consists of {em architectural mappings} which map functional and non-functional requirements to architectural elements of blockchain technology and IoT. In architectural mappings, first, we identify common use-cases in administering standardized examinations. Then we map these use-cases to the core elements of blockchain, i.e. distributed ledgers, cryptography, consensus protocols and smart-contracts and IoT. Such kind of prescriptive architecture guide downstream software engineering processes of implementation and testing
This paper describes some of the results of a National Science Foundation Nanotechnology Undergraduate Education project that aims to establish a nanoscience and nanotechnology program at the University of North Dakota. The goal is to generate new interest in nanoscience and nanotechnology among engineering and science students and prepare them with the knowledge and skills necessary for the next generation of graduates to compete in the global market and contribute to the nanoscience and nanotechnology field. The project explored several aspects of student learning, including students motivations for investigating nanotechnology through interdisciplinary coursework. To collect this information, a survey was administered to students who enrolled to two nanoscience and nanotechnology courses. Data collected from the survey will be used to improve the design and delivery of future courses as part of constructing a complete nanoscience and nanotechnology curriculum.
When students write programs, their program structure provides insight into their learning process. However, analyzing program structure by hand is time-consuming, and teachers need better tools for computer-assisted exploration of student solutions. As a first step towards an education-oriented program analysis toolkit, we show how supervised machine learning methods can automatically classify student programs into a predetermined set of high-level structures. We evaluate two models on classifying student solutions to the Rainfall problem: a nearest-neighbors classifier using syntax tree edit distance and a recurrent neural network. We demonstrate that these models can achieve 91% classification accuracy when trained on 108 programs. We further explore the generality, trade-offs, and failure cases of each model.
In this report, we discribe the submission of Tongji University undergraduate team to the CLOSE track of the VoxCeleb Speaker Recognition Challenge (VoxSRC) 2020 at Interspeech 2020. We applied the RSBU-CW module to the ResNet34 framework to improve the denoising ability of the network and better complete the speaker verification task in a complex environment.We trained two variants of ResNet,used score fusion and data-augmentation methods to improve the performance of the model. Our fusion of two selected systems for the CLOSE track achieves 0.2973 DCF and 4.9700% EER on the challenge evaluation set.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
