Article Per Year (5 Year)
p-Index From 2021 - 2026
9.65
P-Index
This Author published in this journals
All Journal Dinamik Pixel : Jurnal Ilmiah Komputer Grafis Jurnal Teknologi Informasi : Jurnal Keilmuan dan Aplikasi Bidang Teknik Informatika BERNAS: Jurnal Pengabdian Kepada Masyarakat Abdi Kami : Jurnal Pengabdian Kepada Masyarakat Infotek : Jurnal Informatika dan Teknologi Madaniya Media Aplikom Jurnal Bingkai Ekonomi (JBE) Brilliance: Research of Artificial Intelligence Jurnal Informasi Sains dan Teknologi (ISAINTEK) Jurnal Rekam Medis dan Manajemen Informasi Kesehatan Jurnal Cakrawala Informasi (JCI) Jurnal HUMMANSI (Humaniora, Manajemen, Akuntansi) Digital Transformation Technology (Digitech) Jurnal Ilmiah Sistem Informasi dan Ilmu Komputer Jurnal Pengabdian Teknik dan Ilmu Komputer (PETIK) Jurnal Pengabdian Kepada Masyarakat Magistrorum et Scholarium: Jurnal Pengabdian Masyarakat Community: Jurnal Pengabdian Pada Masyarakat Jurnal Manajemen Dan Bisnis Ekonomi SmartComp Jurnal Pengabdian Masyarakat (Jupemas) Jurnal Pengabdian Masyarakat Science Technology and Management Journal (STMJ) Scientific Journal of Informatics Bridge: Jurnal Publikasi Sistem Informasi dan Telekomunikasi ABDI KAMI: Jurnal Pengabdian Kepada Masyarakat Global Science: Journal of Information Technology and Computer Science Indonesian Journal of Infomatics Software Engineering in Computing Systems
Siska Narulita
Universitas Nasional Karangturi Semarang
Religion Aerospace Engineering Agriculture, Biological Sciences & Forestry Humanities Biochemistry, Genetics & Molecular Biology Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Dentistry Earth & Planetary Sciences Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Environmental Science Health Professions Immunology & microbiology Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Library & Information Science Mathematics Medicine & Pharmacology Neuroscience Nursing Public Health Social Sciences Veterinary Other

Published : 69 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 69 Documents
Search

 3   4   5   6   7 
Modeling Human Algorithm Interaction to Improve Trust and Reliability of Intelligent Decision Support Systems in Data Driven Organizations Siska Narulita; Prihati Prihati; Ahmad Nugroho
Indonesian Journal of Infomatics Vol. 1 No. 1 (2026): February: Indonesian Journal of Infomatics
Publisher : Asosiasi Pengelola Jurnal Informatika dan Komputer Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.66472/iji.v1i1.30

Abstract

This research explores the role of human algorithm interaction mechanisms in enhancing trust, reliability, and user confidence in Decision Support Systems (DSS). Traditional DSS models often focus solely on algorithmic accuracy and performance, neglecting crucial factors such as transparency and user engagement, which are essential for building trust. By incorporating explainable AI (XAI) techniques like SHAP and LIME, real-time feedback mechanisms, and user-friendly interfaces, the study develops structured interaction models that improve the interpretability of AI-driven decisions. The results show that transparent decision-making processes and interactive features significantly enhance user trust, making DSS more reliable and easier to adopt. Users interacting with systems that provide clear, understandable explanations of decisions, along with real-time updates on the system’s confidence, reported higher levels of decision-making confidence, especially in high-stakes scenarios. These improvements lead to greater user engagement and adoption of the system in various domains, including healthcare and finance. The study also highlights the importance of balancing interpretability with efficiency in user interface design to ensure both trust and usability. The findings contribute to the design of more user-centric DSS that prioritize trust, interpretability, and cognitive factors, providing a framework for the successful integration of intelligent decision support systems in complex decision-making environments. Future research should focus on refining interaction models and exploring the broader applicability of these systems in different sectors.
Evaluating the Impact of Model Driven Development on Verification and Validation Efficiency in Secure, Large Scale Enterprise Software Systems Sandy Suryady; Siska Narulita; Amna Amna
Software Engineering in Computing Systems Vol. 1 No. 1 (2026): February: Software Engineering in Computing Systems
Publisher : Asosiasi Pengelola Jurnal Informatika dan Komputer Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.66472/secons.v1i1.46

Abstract

Model driven Development (MDD) has emerged as an efficient software engineering methodology that focuses on using high-level models as primary artifacts throughout the software development process. The methodology involves transforming abstract models into detailed designs, and eventually into executable code, with the assistance of automated tools. This study evaluates the impact of MDD on the Verification and Validation (V&V) processes within secure enterprise software systems. By comparing MDD-based projects with traditional code-centric development approaches, the study highlights the advantages of MDD in reducing verification time, minimizing defect leakage, and improving the traceability of security requirements. MDD significantly enhances V&V efficiency by automating key processes, which allows for earlier error detection and better resource utilization. Additionally, MDD strengthens security compliance by integrating security requirements early in the development lifecycle, ensuring better alignment between system requirements and their implementation. Despite the clear benefits, challenges such as the lack of standardized tools and the need for specialized expertise in model development were also encountered during the study. The findings of this research offer important insights for enterprise software development teams looking to adopt MDD for more efficient and secure V&V processes. Future research should focus on the long-term impact of MDD on security compliance, as well as its adoption across different industries, to fully understand the practical benefits and challenges of implementing MDD in diverse real-world environments.
Implementasi Metode Backward Chaining pada Sistem Pakar Analisis Risiko Penularan Demam Berdarah Dengue (DBD) dan Penilaian Kesiapan Program Wolbachia Ing Kota (WINGKO) Semarang Vic Jeremy Prajogo; Siska Narulita; Aerrosa Murenda Mayadilanuari
Dinamik Vol 31 No 2 (2026)
Publisher : Universitas Stikubank

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35315/dinamik.v31i2.10430

Abstract

The high number of Demam Berdarah Dengue (DBD) cases poses a challenge to public health. The successful implementation of Wolbachia technology innovation depends on the analysis of transmission risks and community readiness. This research aims to develop an integrated expert system capable of performing both assessments using research and development methods. This expert system is designed to implement the backward chaining inference method as its primary reasoning mechanism in constructing a structured diagnostic flow. System testing was conducted using the blackbox testing method based on equivalence partitioning to test the system's functionality. The testing results involving users yielded a success rate of 99.28%. This indicates that all the test cases designed were successfully executed, but there was still a 0.72% discrepancy in features or functions.
Prediksi Bed Occupancy Rate (BOR) Rumah Sakit Jiwa dengan Metode SARIMA: Perbandingan Seasonal Pattern Mingguan dan Bulanan Reynard Adelard; Siska Narulita
Dinamik Vol 31 No 2 (2026)
Publisher : Universitas Stikubank

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35315/dinamik.v31i2.10446

Abstract

The ideal bed occupancy rate (BOR) not only represents or reflects the efficiency of facility utilization, but also directly affects the quality of patient care, distribution of medical resources, and financial stability of healthcare institutions. The Abepura Specialized Hospital (RSK), which functions as a referral hospital in the field of mental health in the Papua region, faces its own challenges in managing bed capacity and the flow of inpatient facility usage. Unlike general hospitals, which have high patient turnover rates, RSK Abepura shows a pattern of much longer hospital stays with low basic occupancy rates and more planned patient visits. To address issues related to increasing hospital BOR values, researchers proposed a BOR prediction model using the time series forecasting method, the Seasonal Autoregressive Integrated Moving Average (SARIMA) method for predicting seasonal patterns tailored to RSK characteristics, comparing the performance of the model built with baseline methods, and validating the model's accuracy. This study successfully developed a SARIMA model for BOR prediction at RSK Abepura with unique RSJ characteristics. The SARIMA (0, 1, 2)(1, 1, 2)7 model with a weekly seasonal period proved to provide the best prediction performance with a WAPE of 52.26%, MAE of 5.54%, and RMSE of 6.81%, outperforming the monthly SARIMA model (s = 30).
Faktor-Faktor Penentu Keberhasilan UMKM di Era Digital: Pendekatan Pemodelan Prediktif Menggunakan Gradient Boosting Galuh Aditya; Siska Narulita; Agus Fitri Yanto; Andreas Tigor Oktaga
JURNAL MANAJEMEN DAN BISNIS EKONOMI Vol. 4 No. 3 (2026): Juli: JURNAL MANAJEMEN DAN BISNIS EKONOMI
Publisher : Institut Teknologi dan Bisnis (ITB) Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54066/jmbe-itb.v4i3.4180

Abstract

This study aims to compare the performance of three boosting algorithms, namely XGBoost, LightGBM, and CatBoost, to predict the success of MSMEs. The data used consists of 250 entries with 13 attributes that include business actor characteristics, initial capital, industry experience, financial record-keeping, internet utilization, business planning, partnerships, and the target variable success. The pre-processing stage includes checking for missing values, standardizing numerical attributes, and splitting the data into 80% training data and 20% test data. The evaluation results show that XGBoost provides the best performance with an accuracy of 0.92, precision of 0.8333, recall of 0.8333, F1-score of 0.8333, and ROC-AUC of 0.9715. LightGBM has an accuracy of 0.88, while CatBoost achieves an accuracy of 0.90. The research results show that XGBoost has the best ability to classify successful and unsuccessful MSMEs. The feature importance results also show that the success of MSMEs is influenced by a combination of several key factors. This research emphasizes that boosting algorithms are effectively used as predictive models to support the analysis of MSME success.
Analysis of Fashion Business Customer Segmentation Based on Age Using the X-Means Algorithm Approach Gafgarion Sudradjat Budi Darminto; Siska Narulita
Science Technology and Management Journal Vol. 6 No. 1 (2026): Januari 2026
Publisher : Fakultas Sains dan Teknologi, Universitas Nasional Karangturi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.53416/stmj.v6i1.489

Abstract

The rapid development of the fashion industry in Indonesia requires business practitioners to understand customer behavior more deeply and efficiently in order to formulate targeted marketing strategies. One approach that can be used to identify customer behavior patterns is customer segmentation. This study aims to perform customer segmentation in the fashion business based on age using the X-Means algorithm. The data used were obtained from a sales transaction dataset consisting of customer, order, product, and sales information. The variables analyzed include customer age and total expenditure. To evaluate the performance of the method, the X-Means algorithm was compared with K-Means and K-Medoids. Algorithm performance was measured using the Davies–Bouldin Index (DBI). The experimental results show that X-Means produced the best performance with the lowest DBI value of 0.404 at k = 5 clusters, indicating a more representative grouping of differences in purchasing behavior based on age. The segmentation results can be utilized by fashion business practitioners to design more appropriate promotional strategies and product recommendations tailored to the characteristics of each age group. Furthermore, this study recommends the use of the Deep Embedded Clustering (DEC) approach in future research when large-scale datasets (more than 1,000 customer records) are available, as deep learning-based methods are more capable of capturing non-linear patterns and improving cluster representation quality.
ANALISIS FORECASTING EKSPOR BATIK INDONESIA DENGAN ALGORITMA X-MEANS Gracia Stefani Suharyadi; Siska Narulita
Science Technology and Management Journal Vol. 6 No. 1 (2026): Januari 2026
Publisher : Fakultas Sains dan Teknologi, Universitas Nasional Karangturi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.53416/stmj.v6i1.490

Abstract

Batik is one of Indonesia's cultural heritages that has high economic value because it is a leading export product. In recent years, the value of batik exports has varied considerably each year. This study was conducted to analyze Indonesian batik export data using the X-Means algorithm as a development of previous studies that used forecasting methods. The difference in this study lies in the approach used. While forecasting emphasizes future predictions, the X-Means algorithm is used to see the clustering patterns of existing data. The data used comes from the 2010-2021 batik export dataset obtained from Kaggle and the Indonesian Batik and Handicraft Center. Data processing was carried out using the RapidMiner application with several cluster tests to determine the best results. The results showed that the test with 3 clusters produced a Davies Bouldin Index (DBI) value of 0.029. A low DBI value indicates that the clustering results are very good and there is a clear distance between clusters. From these results, the countries with the highest batik export values were the United States, Germany, and Japan, while the countries with the lowest exports included Slovenia and Portugal. These results prove that the X-Means algorithm can be used to analyze Indonesian batik export patterns effectively.
Optimasi Algoritma K-Nearest Neighbor (k-NN) dengan Wrapper Forward Selection untuk Deteksi Penderita Breast Cancer Oei Joviano Matthew Wijaya; Siska Narulita
Jurnal Rekam Medis & Manajemen Infomasi Kesehatan Vol. 5 No. 1 (2025): Juni 2025
Publisher : Universitas Nasional Karangturi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.53416/jurmik.v5i1.324

Abstract

Breast cancer atau kanker payudara adalah penyakit yang disebabkan karena adanya pertumbuhan sel-sel tubuh yang tidak normal dan mengambil alih sel yang masih sehat pada daerah payudara. Breast cancer sangat diperlukan penanganan dini agar sel kanker pada payudara tidak menyebar secara luas, karena breast cancer dapat menyebabkan kematian. Data mining dapat menjadi salah satu opsi solusi dalam membantu diagnosis kanker payudara. Data mining dapat berperan dalam membantu pengambilan keputusan, karena data yang sudah diolah dapat digunakan dalam analisis sebelum pengambilan keputusan. Analisis data dalam penelitian ini menggunakan algoritma klasifikasi k-Nearest Neighbor (k-NN) yang dioptimasi menggunakan teknik feature selection, yaitu wrapper forward selection. Hasil penelitian menunjukkan bahwa data mining sangat berguna dan bermanfaat dalam menganalisis dan mendiagnosis penyakit breast cancer. Hasil penelitian menunjukkan bahwa nilai persentase akurasi, presisi, dan recall pada model yang menggunakan forward selection menghasilkan persentase yang lebih tinggi daripada yang tidak menggunakan forward selection, yaitu sebesar 96,19%. Sedangkan model yang tidak menggunakan teknik forward selection menghasilkan tingkat akurasi sebesar 84,16%. Sehingga dalam penelitian ini, teknik forward selection sangat berpengaruh dalam meningkatkan akurasi pada model yang terbentuk.
Deteksi Penderita Diabetes dengan Algoritma Random Forest dan Backward Elimination Vic Jeremy Prajogo; Siska Narulita
Jurnal Rekam Medis & Manajemen Infomasi Kesehatan Vol. 5 No. 1 (2025): Juni 2025
Publisher : Universitas Nasional Karangturi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.53416/jurmik.v5i1.334

Abstract

Diabetes merupakan salah satu penyakit kronis yang membutuhkan deteksi dini secara akurat untuk penanganan yang tepat. Penelitian ini bertujuan untuk mengoptimalkan proses deteksi penderita diabetes menggunakan kombinasi algoritma Random Forest dengan teknik Backward Elimination sebagai salah satu metode feature selection. Dataset yang digunakan berasal dari database publik yang diambil dari Kaggle, terdiri dari 768 sampel dengan 9 atribut, termasuk kadar glukosa, tekanan darah, indeks massa tubuh, dan faktor risiko lainnya. Metodologi penelitian meliputi empat tahap utama, data preparation untuk memastikan kualitas dataset, pre-processing menggunakan Backward Elimination untuk seleksi fitur optimal, implementasi algoritma Random Forest untuk klasifikasi, dan evaluasi performa menggunakan confusion matrix. Hasil penelitian menunjukkan peningkatan signifikan dalam performa model setelah implementasi Backward Elimination, dengan peningkatan accuracy dari 83,08% menjadi 99,78%, precision dari 79,37% menjadi 99,67%, sementara recall tetap konsisten pada 100%. Optimasi menggunakan Backward Elimination terbukti efektif dalam mengeliminasi fitur-fitur yang kurang berkontribusi terhadap akurasi prediksi, menghasilkan model yang lebih efisien dan akurat. Temuan ini mengindikasikan bahwa kombinasi Random Forest dengan Backward Elimination tidak hanya meningkatkan akurasi deteksi penderita diabetes secara substansial, tetapi juga berpotensi untuk diimplementasikan dalam sistem pendukung keputusan klinis untuk membantu diagnosis dini diabetes.
Co-Authors Aditya Eka Widyantoro Aerrosa Murenda Mayadilanuari Agus Fitri Yanto Agus Wantoro Ahmad Jurnaidi Wahidin Ahmad Nugroho Ahmad Nugroho Aji Priyambodo Amaliyah, Shofwatun Amna Andreas Heri Kurniawan Andreas Tigor Oktaga, Andreas Aries Alfian Prasetyo Aries Alfian Prasetyo, Aries Alfian Aulia Noveesa Allanda Bambang Widjanarko Susilo Bayu Praharsena Calisto, Calvin Deny Prasetyo Dhieo Kurniawan Diah Ayu Fatmasari Dimas Adi Wicaksono Dody Indra Sumantiawan Dyah Ardyani Rizqi Azizah Adha Evan Setiawan Wicaksono Faqih Ahyar Prayoga Gafgarion Sudradjat Budi Darminto Gafgarion Sudrajat Budi Darminto Galuh Aditya Gati Gati Ghani Ayang Arjuna Giyantolin, Giyantolin Gracia Stefani Suharyadi Gracia Stefani Suharyadi Heru Yulianto Hikmal Adi Wibowo Ika Susanti Indradno, Jasman Jasman Indradno Jawade Hafidz Arsyad Kholilurrahman, Muhammad Kristiawan Nurdianto Kurniawan, Dhieo Laurentius Kenneth V Luther Aldo Christian M. Zakki Abdillah Marsiska Ariesta Putri Martinus Apun Heses Martinus Apun Heses Mayadilanuari, Aerrosa Murenda Michael Fernando Putra S Mudjiyono Munadi Munadi Nanik Qosidah Nugroho, Ahmad Oei Joviano Matthew Wijaya Oei Joviano Matthew Wijaya Petra Valentino Praharsena, Bayu Prihati Prihati . Prihati Prihati Prihati Prihati Priyo Nugroho Adi Priyo Nugroho Adi Priyo Wibowo Putri Novianingrum, Milka Rengga Pratama Putra Retno Ginanjar Reynard Adelard Reynard Adelard Richo Muthicahya Safari, Teti Sandy Suryady Sekarlangit Sekarlangit Sekarlangit Sekarlangit, Sekarlangit setiawan, very dwi Silvia Nurvita, Silvia Sri Danar Dono Sudradjat Budi Darminto, Gafgarion Suhaji Suhaji Suharmanto, Abraham Yano Sumantiawan, Dody Indra Suprapedi Suprapedi Suprapedi Suprapedi Suyahman Suyahman Teguh Khristianto Vic Jeremy Prajogo Vic Jeremy Prajogo Widiastuti, Rosalina Yani