Garuda - Garba Rujukan Digital

TOWARDS OPTIMIZATION: A DATA-DRIVEN APPROACH USING K-MEDOIDS CLUSTERING ALGORITHM FOR REGIONAL EDUCATION QUALITY ASSESSMENT Harun Al Azies; Fawwaz Atha Rohmatullah; Hani Brilianti Rochmanto; Devi Putri Isnarwaty
Jurnal Informatika dan Teknik Elektro Terapan Vol 12, No 3 (2024)
Publisher : Universitas Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/jitet.v12i3.4862

This study applies the k-medoids clustering machine learning approach to assess regional clustering in Indonesia based on educational quality. Data on the quality of education, including indicators of school enrollment rate (APS), gross enrollment rate (APK), and pure participation rate (APM), is gathered and processed from all provinces in Indonesia. The k-medoids clustering technique is used to carry out the clustering process, while metrics like Dunn's index, connection coefficient, and silhouette score are used to evaluate the results. The study's findings indicate that three clusters are the ideal amount, with a silhouette score of 0.2388, a connectivity coefficient of 7.1405, and a Dunn's index value of 0.1651. Cluster homogeneity is likewise moderate, despite the regions' moderate distances from one another. This assessment offers a thorough understanding of Indonesia's educational quality clustering pattern, which can serve as a foundation for developing education strategies in different areas

ANALISIS SENTIMEN OPINI PUBLIK TERHADAP ATURAN PENGHAPUSAN KELAS BPJS PADA PLATFROM X MENGGUNAKAN MULTI-LAYER PERCEPTRON Ratu Bunga Prawesti Arie Salim; Dwi Cahya Julia Kartikasari; Muhammad Athoillah; Hani Brilianti Rochmanto
Seminar Nasional Hasil Riset dan Pengabdian Vol. 6 (2024): Seminar Nasional Hasil Riset dan Pengabdian (SNHRP) Ke 6 Tahun 2024
Publisher : LPPM Universitas PGRI Adi Buana

Show Abstract | Download Original | Original Source | Check in Google Scholar

Analisis sentimen adalah bidang studi yang menganalisis opini dan sentimen seseorang terhadap suatu masalah. Penelitian ini menganalisis sentimen opini publik terhadap aturan penghapusan kelas BPJS yang akan diganti dengan KRIS menggunakan data dari platform X. Metode yang digunakan adalah Multi-Layer Perceptron (MLP), sebuah jenis neural network yang mampu menangani data kompleks dan hubungan non-linear. Fitur extraction dilakukan dengan Term Frequency – Inverse Document Frequency (TF-IDF), dan validasi menggunakan Confusion Matrix. Hasil penelitian menunjukkan bahwa model MLP mampu mengkategorikan sentimen dengan rata-rata akurasi 84.06%, menunjukkan efektivitas metode ini untuk analisis sentimen opini publik pada platform X. Kata kunci: Analisis sentimen; Multi-Layer Perceptron (MLP); Confusion Matrix

ANALISIS SENTIMEN ULASAN WHATSAPP DI GOOGLE PLAY STORE MENGGUNAKAN ALGORITMA SINGLE-LAYER PERCEPTRON (SLP) Pretesya Septiliani Syukur; Izequela De Jesus Madeira; Hani Brilianti Rochmanto; Muhammad Athoillah
Seminar Nasional Hasil Riset dan Pengabdian Vol. 6 (2024): Seminar Nasional Hasil Riset dan Pengabdian (SNHRP) Ke 6 Tahun 2024
Publisher : LPPM Universitas PGRI Adi Buana

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstrak Di era digital ini, media sosial seperti WhatsApp, telah menjadi bagian penting dari kehidupan masyarakat modern di Indonesia. Popularitasnya menjadikan ulasan di Google Play Store sebagai sumber informasi berharga untuk memahami persepsi pengguna. Penelitian ini menganalisis sentimen ulasan WhatsApp menggunakan algoritma Single-Layer Perceptron (SLP). Dari 2000 ulasan yang dikumpulkan, 1700 digunakan setelah proses labeling dan pre-processing. Hasil menunjukkan bahwa model SLP memiliki rata-rata akurasi 76%, presisi 76%, recall 76%, dan f1-score 76%. Penelitian bertujuan memberikan kontribusi pada bidang analisis sentimen dengan menunjukkan efektivitas algoritma SLP dalam mengkategorikan sentimen ulasan pengguna aplikasi Whatsapp. Kata kunci: WhatsApp; Analisis Sentimen; Single-Layer Perceptron; Jaringan Syaraf Tiruan

Eksplorasi Data Sains dalam Pendidikan: Membuka Wawasan Baru untuk Siswa SMA Athoillah, Muhammad; Rochmanto, Hani Brilianti; Wae, Maria Yohana Vianey; Rokhmania, Nina Anggraini Junet
Journal of Community Service and Society Empowerment Том 3 № 01 (2025): Journal of Community Service and Society Empowerment
Publisher : PT. Riset Press International

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59653/jcsse.v3i01.1350

Data science literacy is an important skill in the digital era, but high school students' understanding of this concept is still limited. This study aims to improve students' data science literacy through interactively designed training, including theory delivery and discussion sessions. This study was conducted in Surabaya involving 32 students from five partner schools. The research instruments included a pre-training questionnaire to measure the level of initial understanding, training materials in the form of presentations and educational case studies, and a post-training questionnaire to evaluate the results. The analysis was carried out quantitatively based on the results of the pre-test and post-test, and qualitatively through observation and discussion. The results showed a significant increase in student understanding, with the average post-test score increasing from 45% to 80%. Positive responses from students and teachers indicated that the case study-based training approach was relevant and effective. However, obstacles such as differences in student understanding levels and limited training duration were obstacles to implementation in maximizing knowledge for participants.

Pemetaan Program Indonesia Sehat dengan Pendekatan Keluarga (PIS PK) di Kabupaten Bondowoso dengan K-Medoids Hermanto, Elvira Mustikawati Putri; Rochmanto, Hani Brilianti; Agustin, Risca
Jurnal Statistika dan Komputasi Vol. 2 No. 2 (2023): Jurnal Statistika dan Komputasi
Publisher : Universitas Nahdlatul Ulama Sunan Giri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32665/statkom.v2i2.2307

Latar Belakang: Kesehatan merupakan indikator pertama kesejahteraan masyarakat yang diukur dengan Usia Harapan Hidup (UHH). Semakin tinggi UHH mencerminkan dimensi umur panjang dan hidup sehat yang terus meningkat dari tahun ke tahun. Program Indonesia Sehat dengan Pendekatan Keluarga (PIS PK) digagas pemerintah sebagai bentuk tanggung jawab untuk meningkatkan derajat kesehatan. Tahun 2022, Kabupaten Bondowoso merupakan kabupaten yang memiliki UHH terendah di Provinsi Jawa Timur. Tujuan: Merekomendasikan program kesehatan yang disusun dalam PIS PK sebagai program prioritas berdasarkan hasil klaster (kelompok) dengan K-Medoids. Metode: Pengelompokkan kecamatan-kecamatan berdasarkan sepuluh indikator kesehatan PIS PK yang diperoleh dari Kabupaten Bondowoso Profil Kesehatan Tahun 2022. Pengelompokkan dilakukan dengan menerapkan algoritma K-Medoids. Hasil: Berdasarkan metode Silhouette diperoleh lima klaster optimal yang dapat dibentuk. Pengelompokkan dengan K-Medoids menghasilkan 5 kecamatan mengelompok pada klaster 1, 7 kecamatan mengelompok pada klaster 2, 3 kecamatan mengelompok pada klaster 3, 7 kecamatan mengelompok pada klaster 4, dan hanya ada 1 kecamatan pada klaster 5. Kesimpulan: Rekomendasi peningkatan kesehatan yang dapat diberikan untuk klaster 1 adalah peningkatan pelayanan kesehatan ODGJ (X8), untuk klaster 3 adalah peningkatan gizi, kesehatan ibu dan anak, serta peningkatan perilaku dan lingkungan sehat, dan untuk klaster 4 adalah peningkatan Pengendalian Penyakit Menular dan Tidak Menular.

Klasifikasi Opini Publik terhadap Kenaikan PPN 12% di Platform X menggunakan Multinomial Naïve Bayes Rochmanto, Hani Brilianti; Al Azies, Harun
UJMC (Unisda Journal of Mathematics and Computer Science) Vol 10 No 2 (2024): Unisda Journal of Mathematics and Computer Science
Publisher : Mathematics Department, Faculty of Mathematics and Sciences Unisda Lamongan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52166/ujmc.v10i2.9120

The increase in Value-Added Tax to 12% in 2025 has sparked diverse public opinions on the social media platform X (Twitter). This study aims to classify public sentiment toward the policy using Multinomial Naïve Bayes with a Term Frequency-Inverse Document Frequency (TF-IDF) approach. Multinomial Naïve Bayes is a probabilistic classification algorithm that assumes feature independence. Data were collected through web crawling using the keyword "ppn 12%" and underwent pre-processing, including text normalization, stopword removal, and stemming. To address class imbalance, the Synthetic Minority Over-sampling Technique (SMOTE) was applied. The best-performing model was obtained by tuning the alpha hyperparameter to 0.01, achieving an average accuracy of 83.37%, precision of 83.32%, recall of 83.38%, and an F1-score of 82.99% using 10-fold cross-validation. The findings indicate that Multinomial Naïve Bayes, combined with SMOTE and hyperparameter tuning, effectively classifies public sentiment and provides insights into public responses regarding the Value-Added Tax policy.

Integrative Bioinformatics and Statistical Approaches for Identifying Prognostic Biomarkers and Therapeutic Targets in Breast Cancer Zulhan Widya Baskara; Anuraga, Gangga; Anurogo, Dito; Fitriani, Fenny; Rochmanto, Hani Brilianti; Baskara, Zulhan Widya
Eigen Mathematics Journal Vol 8 No 1 (2025): June
Publisher : University of Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/emj.v8i1.277

Breast cancer is a leading cause of cancer-related mortality worldwide, necessitating the identification of reliable biomarkers for prognosis and targeted therapy. This study employed an integrative bioinformatics and statistical approach to analyze differentially expressed genes (DEGs) in breast cancer using datasets GSE70947 and GSE22820 from the gene expression omnibus (GEO). A protein-protein interaction (PPI) network was constructed to identify hub genes, followed by functional enrichment analysis to determine their biological significance. Survival analysis using the KMplot database revealed that CDC45, KIF2C, CCNB1, KIF4A, CENPE, CHEK1, KIF15, AURKB, NCAPG, and HJURP were significantly associated with poor prognosis. These genes were primarily enriched in cell cycle regulation, mitotic spindle organization, and DNA damage response, highlighting their role in tumor progression. Among them, CCNB1, CHEK1, and AURKB were strongly linked to cell cycle progression and checkpoint regulation, while KIF2C and CENPE played essential roles in mitotic division. High expression levels of these genes correlated with reduced overall survival, suggesting their potential as prognostic biomarkers and therapeutic targets in breast cancer.These discoveries help us better understand how breast cancer develops and point to potential targets for tailored treatments.

Integrating counseling with technology: An evaluation of the Bicarakan.id application through user review analysis with machine learning Al Azies, Harun; Rochmanto, Hani Brilianti; Pravesti, Cindy Asli; Fitriani, Fenny
KONSELI: Jurnal Bimbingan dan Konseling (E-Journal) Vol 11 No 2 (2024): KONSELI : Jurnal Bimbingan dan Konseling (E-journal)
Publisher : Universitas Islam Negeri Raden Intan Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24042/kons.v11i2.24357

Online counseling has transformed mental health services by offering a convenient and cost-effective alternative to traditional in-person therapy. This study investigates the role of technology in counseling by analyzing user reviews of the Bicarakan.id app from the Google Play Store. A machine learning approach was employed to identify critical patterns and themes within the reviews. Text pre-processing methods such as tokenization, stop-word removal, and TF-IDF vectorization were applied to a dataset of 125 user reviews. The Elbow method helped determine the optimal number of clusters, which was three. Clustering performance was assessed using the Silhouette score, with three clusters yielding the highest average score of 0.4939, indicating a moderate level of clustering effectiveness. Cluster 1 primarily contained positive reviews, emphasizing user satisfaction with the app's services. Cluster 2 included more specific feedback on users' experiences with counselors and app features. Cluster 3 focused on the app's accessibility and ease of use while raising concerns about data privacy and the lack of offline consultation options. The study underscores the significance of using user feedback to enhance and improve technology-driven mental health solutions.

SELECTING OPTIMAL PROCESS PARAMETERS OF Al2O3/C COMPOSITE USING GRA WITH PCA AND TAGUCHI’S QLF APPROACH Syahzaqi, Idrus; Rochmanto, Hani Brilianti; Ahsan, Muhammad
BAREKENG: Jurnal Ilmu Matematika dan Terapan Vol 16 No 3 (2022): BAREKENG: Journal of Mathematics and Its Applications
Publisher : PATTIMURA UNIVERSITY

The aim of this study is to find the controlled factors affecting the mass density of the combined Al2O3/Cu. All experiments were carried out using powder metallurgy. Experiments were carried out with four controllable powder processing parameters, namely milling time, compaction pressure, sintering temperature, and holding time. The L18 mixed-level Taguchi Orthogonal Array was used for experimental because it is the basis for the analysis of the Taguchi method. In this research, statistical analysis is carried out using GRA with PCA and Quality Loss Function. The result was the best model based on the Quality Loss Function, because the method has the biggest determination coefficient value is 99,97% where the results is better than GRA with PCA. From the main effect table study, the optimal combination of parameters for response: mass density and hardness are A2B3C3D2 powder metallurgical process parameters, namely milling time of 360 minutes, compacting powder of 200 MPa, sintering of 7000C, and holding time of 20 minutes. The ANOVA results show that the compaction pressure has the most influential parameter that affects the response. The percentage contribution of compaction pressure is 87.09%. Based on ANOVA, the R-squared value is 99.97%, which means the tested factor variables can explain the density of the Al2O3/Cu composite by 99.70%. Therefore, only 18 experimental trials are needed to discover the reality of what will happen in the process.

TOWARDS OPTIMIZATION: A DATA-DRIVEN APPROACH USING K-MEDOIDS CLUSTERING ALGORITHM FOR REGIONAL EDUCATION QUALITY ASSESSMENT Al Azies, Harun; Rohmatullah, Fawwaz Atha; Rochmanto, Hani Brilianti; Isnarwaty, Devi Putri
Jurnal Informatika dan Teknik Elektro Terapan Vol. 12 No. 3 (2024)
Publisher : Universitas Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/jitet.v12i3.4862

This study applies the k-medoids clustering machine learning approach to assess regional clustering in Indonesia based on educational quality. Data on the quality of education, including indicators of school enrollment rate (APS), gross enrollment rate (APK), and pure participation rate (APM), is gathered and processed from all provinces in Indonesia. The k-medoids clustering technique is used to carry out the clustering process, while metrics like Dunn's index, connection coefficient, and silhouette score are used to evaluate the results. The study's findings indicate that three clusters are the ideal amount, with a silhouette score of 0.2388, a connectivity coefficient of 7.1405, and a Dunn's index value of 0.1651. Cluster homogeneity is likewise moderate, despite the regions' moderate distances from one another. This assessment offers a thorough understanding of Indonesia's educational quality clustering pattern, which can serve as a foundation for developing education strategies in different areas

Title

Found 10 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 10 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 10 Documents
Search