Garuda - Garba Rujukan Digital

Hybrid Filtering for Student Major Recommendation: A Comparative Study Nurtriana Hidayati; Titin Winarti; Alauddin Maulana Hirzan
Advance Sustainable Science Engineering and Technology Vol. 7 No. 1 (2025): November-January
Publisher : Science and Technology Research Centre Universitas PGRI Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26877/asset.v7i1.1250

Choosing the right university major is an important decision for students, as delays or incorrect choices can harm their future careers and cause problems for academic departments. High dropout rates, which are frequently the result of poorly informed decisions, can be a considerable burden on faculty. This project aims to address these challenges by creating a recommendation system that provides individualized counsel to students based on their psychological profiles. A quantitative method was used, with questionnaires distributed to a large number of students. To verify the data's authenticity, replies were sought from students who were pleased with their selected majors rather than those who regretted their choices. The collected data formed the basis for a hybrid recommendation system that integrated Content-based Filtering and Collaborative Filtering methods. The system was then compared against standalone implementations of each filtering method to determine its usefulness in increasing suggestion accuracy. The results showed that the Hybrid Filtering strategy obtained a recommendation accuracy of 84.29%, outperforming Content-based Filtering at 81.43% and Collaborative Filtering at 78.57%. The proposed model is easy to implement in a school or a university, as long as the required data is available. Thus, the model can help a school or university to reduce dropout rates and boost academic outcomes.

Web-based Secure Degree Certificate Legalization System Using Advanced Encryption Standard Algorithm Henny Indriyawati; Titin Winarti; Vensy Vydia
International Journal of Information Technology and Business Vol. 7 No. 1 (2024): November: International Journal of Information Techonology and Business
Publisher : Universitas Kristen Satya Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24246/ijiteb.712024.17-21

Degree certificate legalization system with encryption security feature using Advanced Encryption Standard (AES) in Semarang University has a purpose to support academic to do online document legalization through a system. The main problem which occurs in academic administration is a long document legalization process that causes an ineffective and inefficient legalization process. To solve the problem, a system that can encrypt a document for better security is required. This system is built with the Advanced Encryption Standard algorithm with a 128-bit sized key to encrypt confidential information inside the document. During the encryption process, this algorithm operates using 4x4 bit array blocks and passing many encryption processes for at least 10 (ten) times. The application is analyzed with object-oriented analysis and modeled with Unified Modeling Language. The result of this research is a system which can secure document with AES algorithm with a 256-bit sized key. The security element in this algorithm will make easier to identify the owner of the document. The secured document is easily accessible through PHP-based web or available QR code. When decrypting the document, the application will activate the camera function and decrypt the information document.

Data Mining Modeling Feasibility Patterns of Graduates Ability with Stakeholder Needs Using Apriori Algorithm Henny Indriyawati; Titin Winarti
International Journal of Information Technology and Business Vol. 5 No. 2 (2023): April : International Journal of Information Technology and Business
Publisher : Universitas Kristen Satya Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24246/ijiteb.522023.12-17

This The speed of information, the accuracy of data, the ease of information services, and accountability are very important reasons for the implementation of the system. Semarang University (USM) is a private university in Semarang that has the most 2 students in Central Java. Based on the 2019 USM tracer data showing horizontal alignment, namely how close the relationship between the field of study and alumni work is, it appears that there is still a discrepancy in the ability of graduates with stakeholders. The Apriori algorithm is the best-known algorithm for finding high-frequency patterns Rules that state associations between attributes are often called affinity analysis or market basket analysis. The use of the Apriori Algorithm in data mining calculations using data from the Semarang University tracer that the limit of the minimum support is 50% and the minimum confidence is 100% so that it forms 4 rules. From the four rules produced that modeling using the Apriori Algorithm can produce several rule formations so that it can provide an evaluation to the University for compiling steps, this can be seen because the resulting rules are different because each graduate relationship with the desired desires and different styles.

Penguatan Branding Sekolah melalui Literasi Digital dan Virtual Reality Buana, Pratama Angga; Widodo, Edi; Winarti, Titin; Ma’arif, Daffa Nurin Nabil; Wardani, Kasa Kusuma
ABDIMASKU : JURNAL PENGABDIAN MASYARAKAT Vol 8, No 2 (2025): MEI 2025
Publisher : LPPM UNIVERSITAS DIAN NUSWANTORO

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62411/ja.v8i2.2913

SMK Kristen Surakarta menghadapi tantangan dalam meningkatkan daya tarik dan memperkuat citra sekolah akibat persaingan ketat dengan SMK lain serta persepsi negatif masyarakat. Untuk mengatasi hal tersebut, dilakukan pengabdian masyarakat dengan strategi penguatan branding melalui sosialisasi literasi digital dan pelatihan teknologi Virtual Reality (VR). Kegiatan ini bertujuan untuk meningkatkan pemahaman digital siswa serta kemampuan mereka dalam menggunakan VR sebagai media promosi sekolah. Metode yang diterapkan meliputi penyuluhan interaktif, pelatihan teknis, dan evaluasi dengan pretest serta posttest. Hasil kegiatan menunjukkan peningkatan pemahaman siswa terhadap literasi digital sebesar 92%, integrasi VR dalam promosi sebesar 94%, dan kemampuan berpikir kritis sebesar 96%. Kesimpulannya, kegiatan ini efektif dalam meningkatkan keterampilan digital dan pemanfaatan teknologi VR, yang diharapkan berdampak pada citra positif dan daya tarik SMK Kristen Surakarta di masyarakat.

Hybrid Filtering for Student Major Recommendation: A Comparative Study Hidayati, Nurtriana; Winarti, Titin; Hirzan, Alauddin Maulana
Advance Sustainable Science Engineering and Technology Vol. 7 No. 1 (2025): November-January
Publisher : Science and Technology Research Centre Universitas PGRI Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26877/asset.v7i1.1250

Choosing the right university major is an important decision for students, as delays or incorrect choices can harm their future careers and cause problems for academic departments. High dropout rates, which are frequently the result of poorly informed decisions, can be a considerable burden on faculty. This project aims to address these challenges by creating a recommendation system that provides individualized counsel to students based on their psychological profiles. A quantitative method was used, with questionnaires distributed to a large number of students. To verify the data's authenticity, replies were sought from students who were pleased with their selected majors rather than those who regretted their choices. The collected data formed the basis for a hybrid recommendation system that integrated Content-based Filtering and Collaborative Filtering methods. The system was then compared against standalone implementations of each filtering method to determine its usefulness in increasing suggestion accuracy. The results showed that the Hybrid Filtering strategy obtained a recommendation accuracy of 84.29%, outperforming Content-based Filtering at 81.43% and Collaborative Filtering at 78.57%. The proposed model is easy to implement in a school or a university, as long as the required data is available. Thus, the model can help a school or university to reduce dropout rates and boost academic outcomes.

Title

Found 25 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 25 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 25 Documents
Search