cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Bahar
Contact Email
bahararahman@gmail.com
Phone
-
Journal Mail Official
puslit.stmikbjb@gmail.com
Editorial Address
-
Location
Kota banjarmasin,
Kalimantan selatan
INDONESIA
Progresif: Jurnal Ilmiah Komputer
Published by Sekolah Tinggi Manajemen Informatika dan Komputer Banjarbaru
ISSN : 02163284     EISSN : 26850877     DOI : -
Core Subject : Science, Engineering,
Computer Science & IT Control & Systems Engineering
Progresif: Jurnal Ilmiah Komputer adalah Jurnal Ilmiah bidang Komputer yang diterbitkan secara periodik dua nomor dalam satu tahun, yaitu pada bulan Februari dan Agustus. Redaksi Progresif: Jurnal Ilmiah Komputer menerima Artikel hasil penelitian atau atau artikel konseptual bidang Komputer.
Arjuna Subject : -
Articles 542 Documents
 51   52   53   54   55 
Metode Hybrid SVR-GWO Untuk Prediksi Harga Saham PT. Aneka Tambang Tbk Muhammad Aditya Rahman; Taghfirul Azhima Yoga Siswa; Rofilde Hasudungan
Progresif: Jurnal Ilmiah Komputer Vol 22, No 2 (2026): April
Publisher : STMIK Banjarbaru

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35889/progresif.v22i2.3586

Abstract

Fluctuating and unpredictable stock price movements pose a challenge for investors in their decision-making. This study aims to apply and analyze the performance of a hybrid Support Vector Regression (SVR)–Grey Wolf Optimizer (GWO) model in predicting the stock price of PT Aneka Tambang Tbk. The data used consists of daily stock prices from September 11, 2020, to September 11, 2025, totaling 1,202 data points, with a division of 70% training data and 30% testing data. The research stages include pre-processing, basic SVR modeling, and parameter optimization using GWO. The evaluation was carried out using RMSE, MAE, and MAPE. The results show that GWO optimization improved the model's performance from RMSE 99.78, MAE 55.70, and MAPE 2.61% to RMSE 77.27, MAE 48.97, and MAPE 2.37%. Thus, the SVR–GWO model is capable of improving the accuracy of stock price predictions and has the potential to support investment decision-making.Keyword: Grey Wolf Optimizer; Machine Learning; Prediction; Stock Price; Support Vector Re-gression AbstrakPergerakan harga saham yang fluktuatif dan sulit diprediksi menjadi tantangan bagi investor dalam pengambilan keputusan. Penelitian ini bertujuan menerapkan dan menganalisis kinerja model hybrid Support Vector Regression (SVR)–Grey Wolf Optimizer (GWO) dalam memprediksi harga saham PT Aneka Tambang Tbk. Data yang digunakan berupa harga saham harian periode 11 September 2020 hingga 11 September 2025 sebanyak 1202 data, dengan pembagian 70% data pelatihan dan 30% data pengujian. Tahapan penelitian meliputi pre-processing, pemodelan SVR dasar, serta optimasi parameter menggunakan GWO. Evaluasi dilakukan menggunakan RMSE, MAE, dan MAPE. Hasil menunjukkan bahwa optimasi GWO meningkatkan kinerja model dari RMSE 99.78, MAE 55.70, dan MAPE 2.61% menjadi RMSE 77.27, MAE 48.97, dan MAPE 2.37%. Dengan demikian, model SVR–GWO mampu meningkatkan akurasi prediksi harga saham dan berpotensi mendukung pengambilan keputusan investasi.Kata Kunci: Grey Wolf Optimizer; Harga Saham; Machine Learning; Prediksi; Support Vector Regression
Sistem Informasi E-Voting Berbasis Blockchain Untuk Meningkatkan Transparansi Data Tri Haryanti; Nurus Syarifatul Ngaeni
Progresif: Jurnal Ilmiah Komputer Vol 22, No 2 (2026): April
Publisher : STMIK Banjarbaru

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35889/progresif.v22i2.3587

Abstract

Elections that are held in person are vulnerable to fraud, for example, adding votes, miscounting votes and voting more than once, which will be very detrimental to the parties involved, both interested parties and voters. Based on the results of data collection obtained from observations and interviews, an application is needed that allows the above fraud to be avoided. This research develops a blockchain-based E-Voting application to reduce fraud that occurs and to increase transparency of election results data. System development uses the Waterfall method, while system testing uses black boxes. Test results show that by using the blockchain model, voters can only use their NIK once to enter E-Voting to give their voting rights, and refuse to enter their NIK a second time. Blockchain functions to store NIK and lock it so that there is no data duplication so that fraud can be resolved.                                                                                                                                                                  Keywords: Application; E-Voting; Blockchain; Election AbstrakPemilu yang dilakukan secara langsung berpotensi akan kecurangan, seperti penambahan suara, salah menghitung suara dan mencoblos lebih dari satu kali ini akan sangat merugikan pihak terkait baik pihak yang berkepentingan maupun pihak pemilih. Berdasarkan hasil observasi dan wawancara, dibutuhkan aplikasi yang memungkinkan kecurangan dapat dihindari. Penelitian ini mengembangkan aplikasi E-Voting berbasis blockchain untuk mengurangi kecurangan yang terjadi, sehingga dapat meningkatkan transparansi data hasil pemilu. Pengembangan sistem menggunakan metode Waterfall, sedangkan pengujian sistem menggunakan blackbox. Hasil pengujian menunjukkan dengan penggunaan model blockchain, pemilih hanya dapat menggunakan NIK satu kali masuk ke E-Voting untuk memberikan hak pilihnya, dan menolak bilamana memasukkan NIK keduia kalinya. Blockchain berfungsi untuk menyimpan NIK dan menguncinya agar tidak ada kerangkapan data sehingga kecurangan dapat teratasi.Kata Kunci: Apilkasi; E-Voting; Blockchain; Pemilu
Deteksi Diabetes Menggunakan Analisis Citra Kuku Berbasis Vision Transformer CNN-LSTM Annas Prasetio; Sri Handayani
Progresif: Jurnal Ilmiah Komputer Vol 22, No 3 (2026): Juli
Publisher : STMIK Banjarbaru

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35889/progresif.v22i3.3941

Abstract

Diabetes mellitus is a chronic metabolic disease that requires early detection to prevent complications. However, commonly used diagnostic methods are still invasive and require laboratory testing. This study aims to develop a diabetes detection model based on nail image analysis using the Hybrid Vision Transformer–Convolutional Neural Network–Long Short-Term Memory (Vision Transformer–CNN–LSTM) method as a non-invasive approach. The study included dataset collection, image preprocessing, including resizing, normalization, segmentation, dataset partitioning, model training, and evaluation using a confusion matrix. The Vision Transformer was used to capture a global image representation, the Convolutional Neural Network extracted local features, and the Long Short-Term Memory enhanced the feature representation before the classification process. Test results showed that the model achieved 93.33% accuracy, 91.89% precision, 94.44% recall, 93.13% F1-score, and an Area Under the Curve of 0.972. These results demonstrate that the proposed model is capable of accurately detecting diabetes and has the potential to be a fast, easy, and non-invasive alternative for initial screening based on nail images.Keywords: Diabetes mellitus; nail image; Vision Transformer; Convolutional Neural Network–Long Short-Term Memory; Early detection. AbstrakDiabetes mellitus menjadi penyakit metabolik kronis yang memerlukan deteksi dini untuk mencegah terjadinya komplikasi, namun metode diagnosis yang umum digunakan masih bersifat invasif dan memerlukan pemeriksaan laboratorium. Penelitian ini bertujuan mengembangkan model deteksi diabetes berbasis analisis citra kuku menggunakan metode Hybrid Vision Transformer–Convolutional Neural Network–Long Short-Term Memory (Vision Transformer–CNN–LSTM) sebagai pendekatan noninvasif. Penelitian dilakukan melalui tahapan pengumpulan dataset, preprocessing citra berupa resize, normalisasi, segmentasi, pembagian dataset, pelatihan model, dan evaluasi menggunakan confusion matrix. Vision Transformer dimanfaatkan untuk menangkap representasi global citra, Convolutional Neural Network mengekstraksi fitur lokal, sedangkan Long Short-Term Memory memperkuat representasi fitur sebelum proses klasifikasi. Hasil pengujian menunjukkan bahwa model menghasilkan accuracy 93,33%, precision 91,89%, recall 94,44%, F1-score 93,13%, dan Area Under Curve sebesar 0,972. Hasil tersebut menunjukkan bahwa model yang diusulkan mampu mendeteksi diabetes secara akurat serta berpotensi menjadi alternatif skrining awal berbasis citra kuku yang cepat, mudah, dan noninvasif.Kata kunci: Diabetes mellitus; citra kuku; Vision Transformer; Convolutional Neural Network–Long Short-Term Memory; Deteksi dini
Pengembangan Sistem Informasi Prediksi Risiko Dropout Mahasiswa Berbasis Web Menggunakan Algoritme CatBoost Tania Aurellia; Genrawan Hoendarto; Thommy Willay
Progresif: Jurnal Ilmiah Komputer Vol 22, No 2 (2026): April
Publisher : STMIK Banjarbaru

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35889/progresif.v22i2.3656

Abstract

The problem addressed was the limited use of dropout prediction models, which had generally focused on algorithm performance and had not been integrated into an academic monitoring system design.This study aimed to develop a web-based prototype information system for predicting student dropout risk using the CatBoost algorithm to support academic monitoring. The development method used was Prototyping, while the prediction model was built from the Predict Students Dropout and Academic Success dataset, which was reduced to 3,399 records with two classes, namely dropout and graduate. The results showed that the developed prototype included manual prediction, CSV import, prediction monitoring, and role-based reporting features. The CatBoost model achieved 90.29% accuracy, 85.33% precision, 88.76% recall, and 87.01% F1-score. These findings indicated that the prototype had the potential to serve as a basis for developing an early detection system for students at risk of dropout. Keywords: Academic monitoring; CatBoost; Dropout prediction; System prototype; Web-based information system AbstrakPermasalahan yang diangkat adalah keterbatasan pemanfaatan model prediksi dropout yang umumnya masih berfokus pada performa algoritme dan belum terintegrasi ke dalam rancangan sistem pemantauan akademik. Penelitian ini bertujuan mengembangkan prototype sistem informasi prediksi risiko dropout mahasiswa berbasis web menggunakan algoritme CatBoost untuk mendukung pemantauan akademik. Metode pengembangan yang digunakan adalah Prototyping, sedangkan model prediksi dibangun dari dataset Predict Students Dropout and Academic Success yang diseleksi menjadi 3.399 data dengan dua kelas, yaitu dropout dan graduate. Hasil penelitian menunjukkan bahwa prototype yang dikembangkan memuat fitur prediksi manual, impor file CSV, monitoring hasil prediksi, dan laporan berbasis peran pengguna. Model CatBoost memperoleh accuracy 90,29%, precision 85,33%, recall 88,76%, dan F1-score 87,01%. Temuan ini menunjukkan bahwa prototype tersebut berpotensi menjadi dasar pengembangan sistem deteksi dini mahasiswa berisiko dropout. Kata kunci: Pemantauan akademik
Peran Artificial Intelligence Dalam Mendorong Inovasi Dunia Bisnis Untuk Mencapai Keunggulan Yang Kompetitif Jelna Anggreni; Turlia Indah Sapitri; Ryan Randy Suryono
Progresif: Jurnal Ilmiah Komputer Vol 22, No 2 (2026): April
Publisher : STMIK Banjarbaru

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35889/progresif.v22i2.3506

Abstract

The development of Artificial Intelligence (AI) has revolutionized various aspects of the business sector, particularly in driving innovation and creating competitive advantage. This study aims to analyze the contribution of AI to business innovation through a Systematic Literature Review (SLR) approach. The SLR approach was employed to identify, review, evaluate, and synthesize relevant literature related to the research topic. The findings indicate that AI plays an important role in transforming business processes, supporting data-driven decision-making, improving operational efficiency, and strengthening marketing strategies and customer service. In addition, AI enables organizations to become more adaptive and innovative through predictive capabilities and advanced automation. Nevertheless, AI implementation also raises ethical challenges, technological dependence, and the need for adequate organizational capabilities. This study provides both theoretical and practical implications for business practitioners, academics, and policymakers in optimizing the role of AI as an enabler of innovation and the creation of competitive value.Keywords: Artificial Intelligence; Business innovation; Competitive advantage; SLR; Digital transformationAbstrakPerkembangan Artificial Intelligence (AI) telah merevolusi berbagai aspek dalam dunia bisnis, terutama dalam mendorong inovasi dan menciptakan keunggulan kompetitif. Tujuan dari Penelitian ini bertujuan menganalisis kontribusi AI terhadap inovasi bisnis melalui pendekatan Systematic Literature Review (SLR). Pendekatan SLR diterapkan untuk mengidentifikasi, menelaah, mengevaluasi, serta menyusun sintesis dari berbagai literatur yang relevan dengan judul penelitian. Hasil kajian menunjukkan bahwa AI berperan penting dalam hal transformasi mengenai proses sebuah bisnis, serta pengambilan keputusan berbasis data, peningkatan efisiensi operasional, serta penguatan strategi pemasaran dan layanan pelanggan. Selain itu, AI juga mendorong organisasi untuk lebih adaptif dan inovatif melalui kemampuan prediktif dan otomatisasi yang canggih. Namun, implementasi AI juga menimbulkan tantangan etis, ketergantungan teknologi, dan kebutuhan kapabilitas organisasi yang memadai. Studi ini memberikan implikasi teoretis dan praktis bagi pelaku bisnis, akademisi, dan pembuat kebijakan dalam mengoptimalkan peran AI sebagai enabler inovasi dan pencipta nilai kompetitif.Kata kunci: Artificial Intelligence; Inovasi bisnis; Keunggulan kompetitif; SLR; Transformasi digital
Implementasi Transfer Learning Model InceptionV3 Untuk Deteksi Penyakit Daun Jagung Berbasis Mobile Dion Danianto; Salamun Rohman Nudin
Progresif: Jurnal Ilmiah Komputer Vol 22, No 3 (2026): Juli
Publisher : STMIK Banjarbaru

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35889/progresif.v22i3.3842

Abstract

Maize represents a highly crucial agricultural staple within the Indonesian nation, where productivity is often affected by leaf diseases. Diseases like blight, common rust, and gray leaf spot prove hard to recognize by hand since the task demands time and risks personnel mistakes. Current research constructs a maize leaf disease classification model applying transfer learning based on InceptionV3 and evaluates the capabilities of three optimizing algorithms, specifically Adam, Stochastic Gradient Descent (SGD), and RMSProp. The dataset consists of 8,040 images collected from Kaggle and Mendeley, separated into four categories: blight, common rust, gray leaf spot, and healthy. Model training was executed using three dataset scenarios to assess the generalization ability of this suggested method. The empirical findings indicate that the Adam optimizer implemented on the merged dataset attained the highest effectiveness, reaching an exactness of 97.26%, as well as the highest precision, recall, and F1-score compared to SGD and RMSProp. The best-performing model was then converted to TensorFlow Lite and launched within a Flutter-driven Android software to help individuals with the initial spotting of maize leaf diseases.Keywords: Maize; Leaf Disease; Convolutional Neural Network (CNN); InceptionV3 AbstrakJagung adalah salah satu komoditas pangan penting di Indonesia yang kerap mengalami kendala produksi akibat serangan penyakit pada daunnya. Penyakit seperti hawar, karat, dan bercak daun abu-abu sukar dikenali secara manual karena memerlukan waktu yang lama dan berisiko mengalami kesalahan. Studi ini mengembangkan model klasifikasi penyakit daun jagung menggunakan transfer learning berbasis InceptionV3 dengan membandingkan kinerja tiga algoritma optimasi, yaitu Adam, SGD, dan RMSProp. Dataset yang digunakan terdiri dari 8.040 citra dari Kaggle dan Mendeley yang terbagi ke dalam empat kelas, yaitu blight, common rust, gray leaf spot, dan healthy. Pelatihan dilakukan pada tiga skenario dataset untuk mengevaluasi kemampuan generalisasi model. Temuan memperlihatkan bahwa algoritma Adam pada data kombinasi memberikan performa tertinggi dengan akurasi 97,26% serta nilai precision, recall, dan F1-score tertinggi dibandingkan SGD dan RMSProp. Model terbaik dikonversi ke TensorFlow Lite dan diimplementasikan ke dalam aplikasi Android berbasis Flutter sebagai alat bantu mengenali gejala awal penyakit tanaman jagung.Kata kunci: Jagung; Penyakit Daun; CNN; InceptionV3 
Pengembangan Framework Monolithic-SPA Hybrid Berbasis Mobile Web Menggunakan CodeIgniter 3 dan Angular Tony Wijaya
Progresif: Jurnal Ilmiah Komputer Vol 22, No 2 (2026): April
Publisher : STMIK Banjarbaru

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35889/progresif.v22i2.3630

Abstract

This study aimed to develop a hybrid framework integrating CodeIgniter 3 as the backend and Angular as the frontend based on a Single Page Application architecture. The problem addressed was the limited scalability and poor separation of concerns found in conventional monolithic web architectures. The proposed solution employed a RESTful architecture approach, in which CodeIgniter 3 acted as a service provider and Angular managed the user interface layer. The research methodology consisted of requirements analysis, hybrid system architecture design, implementation, and functional testing. The results indicated that the developed hybrid framework improved system modularity, maintainability, and user experience through more responsive page rendering. The novelty of this study lay in the structured implementation of a hybrid framework concept combining CodeIgniter 3 and Angular within an integrated development framework.Keywords: Hybrid framework; CodeIgniter 3; Angular; SPA; RESTful API AbstrakPenelitian ini bertujuan mengembangkan framework Monolithic-SPA Hybrid yang mengintegrasikan CodeIgniter 3 sebagai backend dan Angular sebagai frontend. Pendekatan ini menyatukan hasil kompilasi Angular ke dalam direktori aset CodeIgniter untuk menciptakan satu kesatuan sistem yang efisien namun tetap mempertahankan pemisahan tanggung jawab pada arsitektur web konvensional monolitik. Pendekatan yang digunakan adalah pengembangan perangkat lunak dengan arsitektur RESTful, di mana CodeIgniter 3 berfungsi sebagai penyedia layanan aplikasi dan Angular sebagai pengelola antarmuka pengguna. Metodologi penelitian meliputi analisis kebutuhan, perancangan arsitektur sistem hybrid, implementasi, serta pengujian fungsional sistem. Hasil penelitian menunjukkan bahwa framework hybrid yang dikembangkan mampu meningkatkan modularitas, kemudahan pemeliharaan, serta pengalaman pengguna melalui pemuatan halaman yang lebih responsif. Unsur kebaruan penelitian ini terletak pada penerapan konsep hybrid secara terstruktur pada CodeIgniter 3 dan Angular dalam satu kerangka kerja terpadu.Kata kunci: Framework hybrid; CodeIgniter 3; Angular; SPA; RESTful API 
Evolusi dan Tipologi Data OpenStreetMap di Daerah Istimewa Yogyakarta Tahun 2015–2025 Totok Wahyu Wibowo; Purwanto Purwanto; Ahmad Haikal
Progresif: Jurnal Ilmiah Komputer Vol 22, No 2 (2026): April
Publisher : STMIK Banjarbaru

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35889/progresif.v22i2.3937

Abstract

OpenStreetMap (OSM) data in the Special Region of Yogyakarta grew rapidly during 2015–2025, but the distribution of this growth across object types and administrative areas remains insufficiently understood. This study aims to examine the evolution of road networks, buildings, and points of interest (POIs), develop a cross-object growth typology, and evaluate the relative structure of OSM data. Historical data were obtained through the ohsome API and aggregated at the subdistrict/kemantren level. The analysis covered absolute change, growth rates, percentile-rank scores, and the Road–Building Ratio (RBR), Building–POI Ratio (BPR), and Amenity–Tourism Ratio (ATR). Buildings showed the strongest growth, roads developed through coverage expansion and segment refinement, while POIs grew more moderately despite sharp increases in shop and tourism features. The typology identified multi-object growth, road-dominant, building-dominant, POI-dominant, and low-growth patterns. Structural ratios indicated the growing dominance of buildings and an imbalance between physical objects and functional information.Keywords: Special Region of Yogyakarta; spatio-temporal evolution; OpenStreetMap; POI; growth typologyAbstrakData OpenStreetMap (OSM) di Daerah Istimewa Yogyakarta berkembang pesat selama 2015–2025, tetapi pemerataan pertumbuhan antarobjek dan antarwilayah belum dipahami secara sistematis. Penelitian ini bertujuan menganalisis evolusi jaringan jalan, bangunan, dan points of interest (POI), menyusun tipologi pertumbuhan lintas objek, serta mengevaluasi struktur relatif data OSM. Data historis diperoleh melalui ohsome API dan diagregasikan pada tingkat kecamatan/kemantren. Analisis mencakup perubahan absolut, laju pertumbuhan, skor percentile rank, serta Road–Building Ratio (RBR), Building–POI Ratio (BPR), dan Amenity–Tourism Ratio (ATR). Hasil menunjukkan bahwa bangunan tumbuh paling kuat, jaringan jalan berkembang melalui perluasan cakupan dan pendetailan segmen, sedangkan POI tumbuh lebih moderat meskipun kategori shop dan tourism meningkat tajam. Tipologi menghasilkan pola multi-object growth, road-dominant, building-dominant, POI-dominant, dan low-growth. Rasio struktural menunjukkan penguatan dominasi bangunan dan ketidakseimbangan antara objek fisik dan informasi fungsi ruang.Kata kunci: Daerah Istimewa Yogyakarta; evolusi spasio-temporal; OpenStreetMap; POI; tipologi pertumbuhan 
Rancang Bangun Sistem Informasi Sirkulasi Data Perpustakaan SMAN 2 Subang Caca Arif Herdian; Maya Destriani; Tazkia Salsabila Ardan; Lia Kartika
Progresif: Jurnal Ilmiah Komputer Vol 22, No 3 (2026): Juli
Publisher : STMIK Banjarbaru

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35889/progresif.v22i3.3861

Abstract

Library administration management at Sekolah Menengah Atas Negeri 2 Subang previously relied on conventional paper-based records, which caused data inaccuracies and service inefficiencies. This study aimed to develop a web-based library data circulation information system as an integrated solution to these problems. The software development methodology applied was the sequential waterfall model with an Object Oriented Analysis and Design approach. The novelty of this research focused on the integration of a dynamic business rules engine for automated fine calculations and the provision of a real time visual analysis dashboard. Functional testing results using the blackbox testing method demonstrated an absolute success rate of 100%. System implementation successfully reduced circulation transaction time from the initial 3 to 5 minutes to less than 50 seconds. In conclusion, this information system effectively resolved administrative constraints and provided a valid decision support instrument for school management.Keywords: Library information system; Waterfall model; Data circulation; Fine automation AbstrakPengelolaan administrasi perpustakaan di Sekolah Menengah Atas Negeri 2 Subang sebelumnya masih mengandalkan pencatatan konvensional berbasis kertas sehingga memicu ketidakakuratan data dan inefisiensi pelayanan. Penelitian ini bertujuan untuk membangun sistem informasi sirkulasi data perpustakaan berbasis web sebagai solusi terintergrasi atas permasalahan tersebut. Metode pengembangan perangkat lunak yang diterapkan adalah model waterfall dengan pendekatan Object Oriented Analysis and Design. Kebaruan penelitian ini terletak pada integrasi mesin aturan bisnis dinamis untuk otomatisasi perhitungan denda serta penyediaan dashboard analisis visual secara real time. Hasil pengujian fungsional menggunakan metode blackbox testing menunjukkan tingkat keberhasilan mutlak sebesar 100%. Implementasi sistem terbukti berhasil memangkas waktu transaksi sirkulasi dari semula 3 hingga 5 menit menjadi kurang dari 50 detik. Simpulannya, sistem informasi ini efektif mengatasi kendala administrasi serta menyajikan instrumen pendukung keputusan yang valid bagi pihak sekolah.Kata Kunci: Sistem informasi perpustakaan; model waterfall; sirkulasi data; otomatisasi denda
Pengembangan Sistem Informasi Deteksi Dini Penyakit Ginjal Kronis Berbasis Web dengan TabNet Jessen Hero Pratama; Genrawan Hoendarto
Progresif: Jurnal Ilmiah Komputer Vol 22, No 2 (2026): April
Publisher : STMIK Banjarbaru

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35889/progresif.v22i2.3669

Abstract

Chronic kidney disease is a global health problem that requires early detection to prevent the progression of more serious conditions. This study aims to design and implement a web-based early detection information system for chronic kidney disease integrated with a prediction model. The system was developed using the Prototyping method with TabNet as the classification model and Class-Conditional Conformal Prediction (CCP) to provide prediction confidence information. The study used secondary dummy data representing clinical attributes and risk factors for chronic kidney disease. Data were processed using median imputation, soft class weighting, and train–validation–calibration–test splitting. Prediction labels were determined using a CKD probability threshold of 0.75. Evaluation results showed accuracy of 0.8614, precision of 0.9448, recall of 0.9013, and F1-score of 0.9226. CCP enables the system to display a prediction set, making early detection results more informative and structured.Keywords: Chronic kidney disease; Conformal prediction; Early detection; Information systems; TabNet algorithmAbstrakPenyakit ginjal kronis merupakan masalah kesehatan global yang memerlukan deteksi dini untuk mencegah perkembangan kondisi yang lebih serius. Penelitian ini bertujuan merancang dan mengimplementasikan sistem informasi deteksi dini penyakit ginjal kronis berbasis web yang terintegrasi dengan model prediksi. Sistem dikembangkan menggunakan metode Prototyping dengan TabNet sebagai model klasifikasi dan Class-Conditional Conformal Prediction (CCP) untuk menyajikan informasi keyakinan prediksi. Data penelitian menggunakan data sekunder berbentuk data dummy yang merepresentasikan atribut klinis dan faktor risiko penyakit ginjal kronis. Data diproses menggunakan median imputation, soft class weighting, dan pembagian train–validation–calibration–test. Label prediksi ditentukan berdasarkan threshold probabilitas CKD sebesar 0,75. Hasil pengujian menunjukkan accuracy 0,8614, precision 0,9448, recall 0,9013, dan F1-score 0,9226. Penerapan CCP memungkinkan sistem menampilkan prediction set, sehingga hasil deteksi dini menjadi lebih informatif dan terstruktur.Kata kunci: penyakit ginjal kronis; conformal prediction; deteksi dini; sistem informasi; algoritma TabNet

Page 53 of 55 | Total Record : 542

 51   52   53   54   55 

Filter by Year

2006 2026


Reset
Filter By Issues
All Issue Vol. 22 No. 3 (2026): Juli Vol 22, No 3 (2026): Juli Vol 22, No 2 (2026): April Vol 22, No 1 (2026): Januari Vol 21, No 2 (2025): Agustus Vol 21, No 1 (2025): Februari Vol 20, No 2: Agustus 2024 Vol 20, No 1: Februari 2024 Vol 19, No 2: Agustus 2023 Vol 19, No 1: Februari 2023 Vol 18, No 2: Agustus 2022 Vol 18, No 1: Februari 2022 Vol 17, No 2: Agustus 2021 Vol 17, No 1: Februari 2021 Vol 16, No 2: Agustus 2020 Vol 16, No 1: Februari 2020 Vol 15, No 2: Agustus 2019 Vol 15, No 1: Februari 2019 Vol 14, No 2: Agustus 2018 Vol 14, No 1: Februari 2018 Vol 13, No 2: Agustus 2017 Vol 13, No 1: Pebruari 2017 Vol 12, No 2: Agustus 2016 Vol 12, No 1: Pebruari 2016 Vol 11, No 2: Agustus 2015 Vol 11, No 1: Pebruari 2015 Vol 10, No 2: Agustus 2014 Vol 10, No 1: Pebruari 2014 Vol 9, No 2: Agustus 2013 Vol 9, No 1: Pebruari 2013 Vol 7, No 2: Agustus 2011 Vol 6, No 2: Agustus 2010 Vol 6, No 1: Pebruari 2010 Vol 4, No 1: Pebruari 2008 Vol 2, No 2: Agustus 2006 More Issue