Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal ILKOM Jurnal Ilmiah Jambura Journal of Electrical and Electronics Engineering
Bengnga, Amiruddin
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Energy Engineering

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
Optimizing of IndoBERT Embedding with Ditto Whitening for Measuring Research Title Similarity Ishak, Rezqiwati; Bengnga, Amiruddin
Jambura Journal of Electrical and Electronics Engineering Vol 8, No 1 (2026): Januari - Juni 2026
Publisher : Electrical Engineering Department Faculty of Engineering State University of Gorontalo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37905/jjeee.v8i1.35554

Abstract

Measuring the semantic similarity of research titles is a crucial component in maintaining academic originality and preventing topic duplication in higher education. However, IndoBERT embeddings, as a pretrained Indonesian language model, are known to suffer from anisotropy, causing many titles to exhibit high similarity scores despite being semantically distinct. This study aims to optimize the quality of IndoBERT embeddings through Ditto Whitening and to evaluate its impact on research title similarity measurement. The dataset comprises 7.785 undergraduate thesis titles collected from six disciplinary domains and processed using mean pooling and L2 normalization before and after whitening. An intrinsic evaluation was conducted by assessing embedding isotropy, cosine similarity distribution, global bias toward the mean vector, and hubness phenomena, supported by embedding space visualizations using t-SNE, UMAP, and cosine similarity heatmaps. Experimental results demonstrate substantial improvements in embedding quality, indicated by a reduction in Cosine Pair Mean from 0.559 to −0.000145, a decrease in MeanCos-to-Mean from 0.748 to 0.0068, and a reduction in Hubness Skew from 1.60 to 0.68. The isotropy of the embeddings also increased markedly, reflecting a more uniform vector distribution. These findings confirm that Ditto Whitening effectively improves the isotropy of IndoBERT embeddings and directly enhances the accuracy of research title similarity detection and academic document retrieval systems, thereby supporting topic management and research quality assurance in higher education.
Prediksi Jumlah Mahasiswa Registrasi Per Semester Menggunakan Linier Regresi Pada Universitas Ichsan Gorontalo Bengnga, Amiruddin; Ishak, Rezqiwati
ILKOM Jurnal Ilmiah Vol 10, No 2 (2018)
Publisher : Prodi Teknik Informatika FIK Universitas Muslim Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33096/ilkom.v10i2.274.136-143

Abstract

Improving the quality of education, service quality and accreditation value increase is the hope of all universities, especially at Ichsan University of Gorontalo. One of the factors to achieve this is the increasing number of students who make the payment registration every semester. Based on the report in PDPT Dikti reporting year 2017/2018 has the number of students ± 9,000 people, from the analysis of the last 4 years the number of unregistered students tends to increase and students registerasi tends to decrease, if this is not considered, it will have an impact on the achievement of the above expectations. To overcome these problems, need to be done prediction technique using Linear Regression and MAPE method. The purpose of this research is to build an application to predict the number of registration students. Based on the results of research from 2 selected study program of Informatics Engineering, the result of error rate is 4.24% or the accuracy level is 95.76%, and for the Law Study program, the error rate is 7.69% or the accuracy level is 92.31%, thus the application already built is feasible to use.
SISTEM PENDUKUNG KEPUTUSAN PEMILIHAN PESERTA KAPAL PEMUDA NUSANTARA DENGAN MENGGUNAKAN METODE WEIGHTED PRODUCT (WP) Bengnga, Amiruddin; Pakaya, Noprin
ILKOM Jurnal Ilmiah Vol 9, No 3 (2017)
Publisher : Prodi Teknik Informatika FIK Universitas Muslim Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33096/ilkom.v9i3.170.331-337

Abstract

Pemilihan peserta Kapal Pemuda Nusantara merupakan program Kementerian Pemuda dan Olahraga yang mana proses pemilihannya diberikan hak kepada setiap Provinsi untuk memilih pemuda terbaik di daerah masing-masing, sebanyak 5 orang yang terdiri dari (2 putra, 2 putri) dan 1 orang calon peserta (1 putra atau 1 putri). Proses penyeleksian pemilihan peserta Kapal Pemuda Nusantaramasih terdapat masalah yang dihadapi, diantaranyasulitnya memilih peserta  yang tepat dan berkualitaskarena banyaknya peserta yang ikut seleksidan banyaknya kriteria yang digunakan serta masih adanya unsur penilaian secara subyektif sehingga membutuhkan ketelitian dalam pengambilan keputusan. Tujuan dari penelitian ini adalah membangun sebuah aplikasi sistem pendukung keputusan dengan menggunakan metodeWeighted Product.Berdasarkan hasil penelitian aplikasi yang sudah dibangun dapat membantu pihak pengambil keputusan dalam menentukan alternatif terbaik peserta Kapal Pemuda Nusantarauntuk kategori Laki-Laki dengan nilai tertinggi 0,22327 dan untuk kategori Perempuan dengan nilai tertinggi 0,21771dan proses pemilihannya menjadi lebih obyektif.
Co-Authors Ishak, Rezqiwati Pakaya, Noprin