Claim Missing Document
Check
Articles

Found 8 Documents
Search

Comparison of Latent Semantic Analysis (LSA) and Doc2Vec Algorithms of Thesis Similarity Detection Rita Wahyuni Arifin; Mardi Yudhi Putra; Dwi Ismiyana Putri
PIKSEL : Penelitian Ilmu Komputer Sistem Embedded and Logic Vol. 12 No. 2 (2024): September 2024
Publisher : LPPM Universitas Islam 45 Bekasi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33558/piksel.v12i2.9954

Abstract

This study aims to develop a system for detecting similarities in thesis titles and content to prevent plagiarism and support student originality. The high level of similarity in final projects is a significant concern in academic environments. Two text vectorization methods, Latent Semantic Analysis (LSA) and Doc2Vec, were compared to measure document similarity. Results showed that LSA achieved a very high cosine similarity (99.94%) due to dimensionality reduction that preserved semantic correlations. In contrast, Doc2Vec produced lower similarity scores, with 7.17% for PV-DM and 39.07% for PV-DBOW, indicating richer text representations. This study adopted the CRISP-DM model, which includes Business Understanding, Data Understanding, Data Preparation, Modelling, and Evaluation. The model is expected to strengthen academic integrity and encourage valuable scientific contributions.
Analysis of Information Systems Acceptance and Success Models in Higher Education Reni Haerani; Titik Khawa Abdul Rahman; Dwi Ismiyana Putri; Rika Apriani; Mardi Yudhi Putra
INTENSIF: Jurnal Ilmiah Penelitian dan Penerapan Teknologi Sistem Informasi Vol 10 No 1 (2026)
Publisher : Universitas Nusantara PGRI Kediri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29407/intensif.v10i1.24969

Abstract

Background: The integration of Information Systems (IS) in higher education has transformed interactions among students, lecturers, and administrative staff, making system acceptance and success essential for effective academic processes. Various evaluation frameworks have been developed, with the DeLone and McLean Information System Success Model being one of the most widely applied. Objective: This study aims to analyze factors influencing the adoption of academic information systems in higher education using the DeLone and McLean model and to evaluate system success from the perspectives of lecturers, students, and administrative personnel. Methods: A quantitative research approach was employed using questionnaire-based data collection. Data analysis was conducted using SmartPLS 3.0 to assess validity, reliability, and structural relationships among variables. A total of 252 respondents were selected using the Slovin formula and proportional stratified random sampling. The evaluated constructs included system quality, information quality, service quality, system use, user satisfaction, and benefits. Results: The results show that system quality, information quality, and service quality have a positive and significant effect on system use and user satisfaction. Furthermore, system use and user satisfaction contribute to perceived net benefits, such as improved learning outcomes, increased management efficiency, and academic productivity. High service quality also supports continued system usage. All measurement constructs met validity and reliability criteria, with loading factors above 0.7 and Average Variance Extracted (AVE) values exceeding 0.50. Conclusion: In conclusion, the DeLone and McLean model effectively explains academic information system success in higher education, highlighting the importance of system quality, user satisfaction, and generated benefits.
Sistem Pakar Diagnosis Hama dan Penyakit Tanaman Padi Menggunakan Metode Teorema Bayes Dwi Ismiyana Putri; Rini Sukma Ayu
Indonesian Journal of Multidisciplinary on Social and Technology Vol. 4 No. 3 (2026): Juli - Oktober
Publisher : PT Ilmu Data Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69693/ijmst.v4i3.12300

Abstract

Tanaman padi merupakan komoditas pangan utama di Indonesia, namun produksi padi dipengaruhi oleh serangan Organisme Pengganggu Tumbuhan (OPT) atau disebut juga Hama dan Penyakit Tanaman (HPT) padi. Di BPP Kecamatan Cibarusah, keterbatasan jumlah Pengendali Organisme Pengganggu Tumbuhan (POPT) serta kesulitan petani dalam mengenali gejala awal serangan OPT menyebabkan proses diagnosis belum dapat dilakukan secara cepat, penelitian ini bertujuan mengembangkan sistem pakar diagnosis hama dan penyakit tanaman padi berbasis website menggunakan metode teorema bayes untuk membantu diagnosis awal berdasarkan gejala yang dipilih, pengembangan sistem dilakukan menggunakan metode Rapid Application Development (RAD), sedangkan basis pengetahuan diperoleh melalui Observasi, Wawancara dengan POPT Kecamatan Cibarusah dan POPT Penyelia BBPOPT, serta studi literatur. Sistem mengimplementasikan metode teorema bayes dengan nilai bobot yang ditentukan berdasarkan expert judgement untuk menghitung probabilitas setiap jenis OPT. Hasil penelitian menghasilkan sistem pakar yang mampu mendiagnosis lima jenis OPT berdasarkan 22 gejala serta memberikan rekomendasi penanganan sesuai hasil diagnosis. Validasi dilakukan dengan membandingkan hasil diagnosis sistem terhadap diagnosis pakar menggunakan 30 kasus oleh POPT Kecamatan Cibarusah dan 31 kasus oleh POPT Penyelia BBPOPT. Seluruh hasil diagnosis sistem sesuai dengan hasil diagnosis pakar sehingga diperoleh tingkat kesesuian sebesar 100%. Hasil tersebut menunjukan bahwa sistem pakar yang dikembangkan mampu memberikan diagnosis yang konsisten dengan pengetahuan pakar dan layak digunakan sebagai alat bantu konsultasi OPT tanaman padi untuk memperoleh diagnosis awal.
Comparative Study of Machine Learning Algorithms Using Bagging and XGBoost Techniques for Breast Cancer Classification Rully Pramudita; Dwi Ismiyana Putri; Bambang Kriswantara; Vina Zahrotun Nazah; Rahmat Budiarto
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 10 No 4 (2026): August 2026
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v10i4.7216

Abstract

Machine learning (ML) has become an important data-driven approach for classification and prediction, including applications in medical diagnosis. Ensemble methods can improve classifier performance by combining complementary learning mechanisms. However, systematic evidence on the sequential use of Bagging and XGBoost across different classifier architectures remains limited. This study develops a staged ensemble framework in which five classifiers—Support Vector Machine (SVM), Neural Network (NN), Logistic Regression (LR), Decision Tree (DT), and K-Nearest Neighbours (KNN)—are first optimized through Bagging and subsequently enhanced using XGBoost. The experiments were conducted on the Breast Cancer Wisconsin (Diagnostic) dataset under a consistent 70:30 train–test protocol. Performance was assessed using accuracy, confusion matrices, ROC curves, and Area Under the Curve (AUC), while repeated experiments were used to examine statistical significance. The results show that the staged Bagging–XGBoost approach improves both predictive accuracy and class discrimination across the evaluated classifier types. Neural Network achieved the largest improvement, with mean accuracy increasing from 93.1% to 97.0% across repeated experiments. The findings demonstrate that the sequential framework can improve non-tree-based as well as tree-based classifiers, providing empirical evidence for broader use of staged ensemble integration in breast cancer classification.
Integrasi Workflow Jurnal Keuangan Berbasis Website Menggunakan Analisis Pieces dan Metode Agile Scrum Andrasatria Dewa; Dwi Ismiyana Putri
Jejak digital: Jurnal Ilmiah Multidisiplin Vol. 2 No. 6 (2026): OKTOBER-NOVEMBER
Publisher : INDO PUBLISHING

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63822/ek7p9543

Abstract

Hospital financial governance depends on how well the journal approval workflow is recorded and traced. The desktop-based Financial Information System (SIMKEU) used by the hospital under study supports journal entry and posting, but examination, approval, and endorsement are still handled through physical documents outside the system, so access is inflexible and the process status is not digitally documented. This study analyses the running system and develops a website-based financial information system that integrates the tiered journal workflow. Data were collected through observation, interviews with finance staff, the assistant finance manager, and the finance manager, and a literature study. The running system was analysed using the PIECES framework, while development applied the Agile approach with Scrum over approximately three months, with the researcher acting as a single full-stack developer. The system was built on CodeIgniter 3 and combines the existing Oracle database as the journal data source with MySQL as the workflow, access-rights, and activity-log store, so the legacy schema remains unchanged. Alpha testing of twenty function groups using black-box testing produced conforming results, and User Acceptance Testing with five respondents produced an acceptance rate of 76.89% in the Good category.
An Android-Based Expert System for Smartphone Damage Diagnosis Using the Forward Chaining Method Dhivan Asda Kurnianto; Dwi Ismiyana Putri
Journal of Engineering and Science Application Vol. 3 No. 2 (2026): Mei-Oktober
Publisher : Institute Of Advanced Knowledge and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69693/jesa.v3i2.80

Abstract

The increasing use of Android-based smartphones has been accompanied by a growing need for repair services to address various hardware and software problems. At Alfa Cell Randan Batu, the diagnosis process is still conducted manually based on technicians’ experience and information provided by customers. This process requires considerable time, is less efficient, and may result in inconsistent diagnoses. This study aimed to design and develop an expert system to assist in the initial diagnosis of Android smartphone damage in a faster, more efficient, and structured manner, while also supporting the reduction of customer queues. The study employed the Prototype method, consisting of communication, quick planning, quick design modeling, Prototype construction, and deployment and feedback. Data were collected through observation, interviews with Alfa Cell technicians, and literature studies. The system was developed as a web-based application using PHP, MySQL, XAMPP, and Bootstrap, with the Forward chaining method as the inference engine. The knowledge base consisted of 37 symptoms, 13 damage categories, 13 recommended solutions, and 13 diagnostic rules using IF–THEN structures with the OR operator. The evaluation results showed that all 13 diagnostic cases produced results consistent with technician validation. Black-box testing demonstrated that all tested system functions operated successfully. User testing involving 30 respondents obtained an overall mean score of 4.41, equivalent to 88.10%, categorized as strongly agree. In conclusion, the developed Forward chaining-based expert system can assist in the initial diagnosis of Android smartphone damage in a more structured and consistent manner, support faster diagnosis, and provide recommended solutions based on selected symptoms. The results should still be confirmed by a technician through direct device examination.
Penerapan Metode TOPSIS pada Sistem Pendukung Keputusan Kelayakan Pembelian Unit AC Bekas Berbasis Web Febrianto Febrianto; Dwi Ismiyana Putri
Jejak digital: Jurnal Ilmiah Multidisiplin Vol. 2 No. 6 (2026): OKTOBER-NOVEMBER
Publisher : INDO PUBLISHING

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63822/rapswa11

Abstract

CV Ziyad Aircond Indonesia determines the feasibility of used air-conditioning (AC) units manually, relying on technician experience without a standardized assessment procedure. This may lead to inconsistent assessments and suboptimal purchasing decisions. This study develops a web-based decision support system using the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) method. Data were collected through observation, interviews, and literature study, while the system was developed using the Prototype model. Six criteria were applied: compressor condition (weight 0.20), evaporator condition (0.15), condenser condition (0.15), unit age (0.15), brand (0.15), and price (0.20). TOPSIS processing includes decision matrix normalization, weighting, positive and negative ideal solutions, distance calculation,  preference values, and ranking. The calculation used ten used AC units with the same cooling capacity. AC010 achieved the highest preference value of 0.7393, followed by AC003 (0.6633) and AC001 (0.6418), while AC007 ranked last with 0.3556. Functional testing reported that tested features worked as expected, and user evaluation reached an overall score of 84.44%, categorized as very good in the thesis. The system provides structured recommendations to  support, rather than replace, the company’s final purchasing decision. 
Canva dan Strategi Warna: Inovasi Pembelajaran Kreatif di Era Digital Dwi Ismiyana Putri; Rully Pramudita; Bambang Kriswantara; Inayah Ainina Mawardi; Salshabella Olivia Hendriadi
Jnanadharma Vol. 3 No. 2 (2025): Vol. 03 No. 02 Edisi Juli 2025
Publisher : Universitas AKPRIND Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34151/jafst.v3i2.5205

Abstract

Penelitian ini membahas topik Pelatihan Transformasi Kemampuan Desain Siswa Melalui Canva dan Strategi Warna: Membangun Kreativitas di Era Digital oleh Siswa SMK Tinta Emas Indonesia (YATINDO) Kota Bekasi. Tujuan dari pelatihan ini adalah agar siswa dapat memahami dan membangun kreativitas menggunakan Canva dan strategi warna. Pelatihan dilakukan dengan metode interaktif dan praktik, dengan memberikan pelatihan dan demonstrasi kepada peserta dalam penggunaan Aplikasi Canva dengan dukungan media online untuk dokumentasi pelatihan berupa Link Google Drive. Hasil tersebut menunjukkan bahwa adanya pelatihan ini dinyatakan berhasil, sebanyak 53,33% peserta menunjukkan minat terhadap kegiatan pelatihan yang dilakukan. Hal ini juga dibuktikan dengan antusiasme peserta yang memberikan respon baik terhadap kejelasan materi yaitu sebesar 73,33% atau 11 dari 15 peserta. Hasil positif yang didapat dari pelatiha ini diharapkan dapat memberikan kontribusi terhadap pengembangan keterampilan siswa terhadap teknologi.