Article Per Year (5 Year)
p-Index From 2021 - 2026
2.42
P-Index
This Author published in this journals
All Journal IAES International Journal of Artificial Intelligence (IJ-AI) Jurnal Simetris TELKOMNIKA (Telecommunication Computing Electronics and Control) Indonesian Journal of Electrical Engineering and Informatics (IJEEI) Jurnal Edukasi dan Penelitian Informatika (JEPIN) Jurnal Pengelolaan Sumberdaya Alam dan Lingkungan (Journal of Natural Resources and Environmental Management) Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Jurnal Penelitian Pertanian Tanaman Pangan Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control Jurnal TAM (Technology Acceptance Model) JITK (Jurnal Ilmu Pengetahuan dan Komputer) Journal of Information Systems and Informatics Indonesian Journal of Electrical Engineering and Computer Science Computer Science and Information Technologies
Sitanggang, Imas S.
Bogor Agricultural University
Agriculture, Biological Sciences & Forestry Computer Science & IT Control & Systems Engineering Earth & Planetary Sciences Education Electrical & Electronics Engineering Energy Engineering Environmental Science

Published : 28 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 28 Documents
Search

 1   2   3 
Perbandingan Kinerja LSTM dan Prophet untuk Prediksi Deret Waktu (Studi Kasus Produksi Susu Sapi Harian) Alusyanti Primawati; Imas Sukaesih Sitanggang; Annisa Annisa; Dewi Apri Astuti
JEPIN (Jurnal Edukasi dan Penelitian Informatika) Vol 9, No 3 (2023): Volume 9 No 3
Publisher : Program Studi Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26418/jp.v9i3.72031

Abstract

Prediksi deret waktu dibutuhkan untuk menjawab pertanyaan bisnis dimasa depan  yang akurat sehingga perlunya membangun model prediksi yang memiliki kinerja bagus. Pendekatan machine learning seperti long short term memory (LSTM) dan Prophet menjadi popular saat ini untuk pemodelan prediksi deret waktu. Agribisnis susu segar saat ini salah satu studi kasus yang memerlukan peranan teknologi informasi seperti bisnis intelijen untuk memastikan ketersediaan pasokan susu dimasa depan. Upaya pertama yang perlu dilakukan adalah menyiapkan model prediksi yang tepat meskipun data awal yang dikumpulkan masih sedikit atau terbatas. Dataset produksi susu sapi selama 300 hari menjadi data penelitian yang dimodelkan kedalam LSTM dan Prophet. Keduanya dibandingkan kinerjanya terhadapa data terbatas. Hasilnya uji koefisien determinasi R2 keduanya yaitu 0.2, sehingga perlu dilakukan peningkatan kinerja melalui tahapan revise and enhance. Hasilnya, kedua model meningkat nilai R2 menjadi 0.3 dan LSTM lebih baik dari Prophet. Meskipun demikian perbedaan keduanya tidak terlalu signifikan dan peningkatan juga tidak berbeda terlalu jauh karena data susu memiliki pola multi-periode dengan tren berbeda signifikan. Periode 90 hari pertama adalah masa klimaks laktasi sedangkan periode kedua setelah 90 hari adalah masa intervensi peternak menurunkan hasil perah untuk persiapakan ternak kambing perah ke masa kawin dan bunting.
Classification of Pestalotiopsis sp. Leaf Fall Disease Severity in Rubber Plants using UAV Multispectral Vegetation Indices and 1-D Convolutional Neural Networks Solikin; Yeni Herdiyeni; Annisa; Lilik Budi Prasetyo; Tri Rapani Febbiyanti; Imas Sukaesih Sitanggang; Sri Nurdiati
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 10 No 3 (2026): June 2026
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v10i3.7601

Abstract

Leaf-fall disease caused by Pestalotiopsis sp. is a major threat to rubber (Hevea brasiliensis) plantations because it suppresses photosynthetic activity, accelerates defoliation, and reduces latex productivity. In operational practice, severity assessment is still dominated by visual field inspection, which is subjective, time-consuming, costly, and difficult to standardize across large plantation areas. This study develops a disease severity classification model for Pestalotiopsis sp. using a Convolutional Neural Network (CNN) based on vegetation-index features derived from UAV multispectral imagery. The model classifies disease severity into four levels: L1 (Light Infection), L2 (Moderate Infection), L3 (Severe Infection), and L4 (Very Severe Infection). To represent temporal and biological variability in disease expression, multispectral data were collected from multiple rubber clones over two observation periods. Feature construction focused on NDRE, LCI, CI, NDVI_NDRE_Interaction, and GCI_Ratio, which capture chlorophyll-related and canopy condition responses to infection. Because severity classes were imbalanced, the Synthetic Minority Over-sampling Technique (SMOTE) was applied before model training. A one-dimensional CNN was then trained to learn nonlinear patterns among index-based predictors for multilevel severity classification. Hyperparameter tuning improved overall accuracy from 85.30% to 90.00%. Class-wise F1-scores changed from 0.91 to 0.94 (L1), 0.83 to 0.84 (L2), 0.75 to 0.88 (L3), and 0.97 to 0.84 (L4), with the largest improvement in L3 recall (0.67 to 0.94). These results indicate that the selected vegetation indices and interaction terms are informative predictors for objective and scalable disease severity classification under heterogeneous plantation conditions.
Logistic Regression Modeling of Peatland Fire Hotspots in Bengkalis District Using Integrated Environmental and Anthropogenic Drivers Nur Hayati; Imas Sukaesih Sitanggang; Lilik Budi Prasetyo; Lailan Syaufina
Journal of Information System and Informatics Vol 8 No 2 (2026): April
Publisher : Asosiasi Doktor Sistem Informasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63158/journalisi.v8i2.1560

Abstract

Peatland fires occur almost annually in Bengkalis District, Riau Province, Indonesia, where peatlands cover about 65% of the area and contribute significantly to carbon emissions and regional haze, highlighting the need for improved fire risk prediction. This research aims to apply a probabilistic logistic regression approach to predict peatland fire hotspot occurrence and identify its key drivers. Hotspot data from 2015–2023 were derived from VIIRS satellite observations and classified into low (l), nominal (n), and high (h) confidence levels. Then hotspot confidence levels are classified into two scenarios: (1) the nh scenario (l = 0; n–h = 1) and (2) the h scenario (l–n = 0; h = 1), representing different fire thresholds. The predictor variable was modeled using anthropogenic and environmental, with multicollinearity testing to ensure model stability. The results show that the nh scenario performs better, with Nagelkerke R² = 0.0681, Hosmer–Lemeshow χ² = 5.7663, AUC = 0.69, and accuracy = 95.19%, indicating acceptable fit and moderate discrimination. Significant predictors include plantation land use, peat characteristics, and precipitation. These findings suggest that the approach can support peatland fire risk assessment, although further refinement is required.
Technical analysis model for stock prediction using a grammatical evolution algorithm Aditya Kusuma Setyanegara; Imas Sukaesih Sitanggang; Mushthofa Mushthofa
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 15, No 2: April 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v15.i2.pp1236-1246

Abstract

Stocks are a popular investment instrument but carry high risks, where investors may incur losses when stocks are bought at high prices and sold at lower prices. Technical analysis is used to study past stock price behavior to predict future prices. In this study, grammatical evolution (GE) is applied as an evolutionary computing technique to discover optimal functions or programs that represent historical stock price data. This study develops GE based prediction models by utilizing objective functions and search spaces defined through grammar. The model integrates technical indicators based on complex statistical models such as autoregressive integrated moving average (ARIMA), prophet, exponential smoothing, and Fibonacci retracements. Furthermore, this study employs GE to generate ensemble weights randomly, ensuring each model contributes equitably to the final prediction formula. Experiments were conducted using multiple stock datasets, including SMAR, S&P 500, the Johannesburg Stock Exchange (JSE), the New York Stock Exchange (NYSE), and Adani Enterprises (ADANIENT), to evaluate the model’s adaptability and generalization capability. The results demonstrate that the proposed GE model effectively captures complex market patterns and produces more reliable stock price predictions compared to deep learning-based approaches. Although GE requires greater computational time, the findings suggest that GE provides a flexible and effective framework for constructing hybrid stock price forecasting models in dynamic market environments.
Analysis of PM2.5 pollutant sources in Jakarta using deep learning models and back trajectory approach Hendro Pratama Saragih; Imas Sukaesih Sitanggang; Hendra Rahmawan
Indonesian Journal of Electrical Engineering and Computer Science Vol 43, No 1: July 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v43.i1.pp325-334

Abstract

PM2.5 concentrations in Jakarta frequently exceed World Health Organization (WHO) air quality guidelines, indicating the need for an integrated approach for pollution prediction and source assessment. This study develops a spatiotemporal prediction framework using a long short term memory (LSTM) model integrated with the hybrid single particle Lagrangian integrated trajectory (HYSPLIT) model for backward trajectory analysis. Daily PM2.5 data from five monitoring stations were combined with meteorological variables from ERA5, Visualcrossing, and the global data assimilation system, with spatial context evaluated using Sentinel-2 land cover maps. After hyperparameter tuning, the optimized model demonstrated robust predictive capabilities, achieving a peak coefficient of determination (R2) of 75.87% on the test data. The framework exhibited exceptional relative accuracy, particularly at the Jagakarsa and Kebun Jeruk stations, which recorded mean absolute percentage error (MAPE) values of 13.34% and 17.80%, respectively. Backward trajectory analysis during selected pollution episodes indicates two dominant regional transport pathways that may influence PM2.5 levels in Jakarta. These pathways are associated with air mass transport over industrial and built-up areas in eastern and northern regions surrounding Jakarta. Land cover analysis shows limited vegetation along these pathways. Overall, elevated PM2.5 events are associated with combined local emissions, regional transport, and meteorological conditions that limit pollutant dispersion near the surface.
Effects of hyperparameter tuning on random forest regressor in the beef quality prediction model Ridwan Raafi'udin; Yohanes Aris Purwanto; Imas Sukaesih Sitanggang; Dewi Apri Astuti
Computer Science and Information Technologies Vol 6, No 2: July 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/csit.v6i2.p159-168

Abstract

Prediction models for beef meat quality are necessary because production and consumption were significant and increasing yearly. This study aims to create a prediction model for beef freshness quality using the random forest regressor (RFR) algorithm and to improve the accuracy of the predictions using hyperparameter tuning. The use of near-infrared spectroscopy (NIRS) in predicting beef quality is an easy, cheap, and fast technique. This study used six meat quality parameters as prediction target variables for the test. The R² metric was used to evaluate the prediction results and compare the performance of the RFR with default parameters versus the RFR with hyperparameter tuning (RandomSearchCV). Using default parameters, the R-squared (R²) values for color (L*), drip loss (%), pH, storage time (hour), total plate colony (TPC in cfu/g), and water moisture (%) were 0.789, 0.839, 0.734, 0.909, 0.845, and 0.544, respectively. After applying hyperparameter tuning, these R² scores increased to 0.885, 0.931, 0.843, 0.957, 0.903, and 0.739, indicating an overall improvement in the model’s performance. The average performance increase for prediction results for all beef quality parameters is 0.0997 or 14% higher than the default parameters.
Model Klasifikasi Lahan Hijaun Pakan Ternak Ruminansia Dengan Algoritma Random Forest Pada Kabupaten Lumajang Dwi Marlina; Imas Sukaesih Sitanggang; Annisa Annisa; Dewi Apri Astuti
Simetris: Jurnal Teknik Mesin, Elektro dan Ilmu Komputer Vol. 16 No. 2 (2025): JURNAL SIMETRIS VOLUME 16 NO 2 TAHUN 2025
Publisher : Fakultas Teknik Universitas Muria Kudus

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24176/simet.v16i2.15967

Abstract

Informasi mengenai ketersediaan lahan hijauan pakan ternak ruminansia pada tutupan lahan memerlukan data spasial yang akurat, salah satunya dapat diperoleh melalui teknologi penginderaan jauh. Citra satelit Landsat 8 mampu menyediakan informasi mengenai tutupan lahan, termasuk lahan hijauan, badan air, pemukiman, industri, dan jalan. Citra satelit tidak hanya menginformasikan lahan hijauan saja tetapi dapat menginformasikan tutupan lahan seperti badan air, pemukinan, industri, dan jalan. Oleh karena itu, diperlukan proses klasifikasi tutupan lahan untuk mengindentifikasi area yang berfungsi sebagai sumber hijauan pakan ternak ruminansia. Identifikasi ini penting untuk mengetahui ketersediaan pakan, yang selanjutnya dapat digunakan sebagai dasar dalam memprediksi biomassa vegetasi. Penelitian ini bertujuan untuk mengklasifikasi tutupan lahan hijauan yang berperan sebagai pakan ternak ruminansia. Metode yang digunakan adalah algoritma random forest dengan memanfaatkan citra satelit Landsat 8 untuk wilayah , Kabupaten Lumajang pada periode tahun 2018 hingga 2022. Hasil klasifikasi menghasilkan tiga kelas utama lahan hijaua, yaitu perkebunan, pertanian/sawah, dan semak belukar. Model klasifikasi yang dibangun mencapai tingkat akurasi sebesai 93%. Berdasarkan hasil analisis, rat-rata lahan hijauan di Kabupaten Lumajang terdiri atas lahan perkebunan sebuas 23.865,78 ha, pertanian/sawah seluas 18.363,21 ha, dan semak belukar seluas 949,98 ha. Hasil penelitian menunjukkan bahwa lahan hijauan di Kabupaten Lumajang didominasi oleh perkebunan, sehingga daerah ini memiliki potensi yang baik untuk pengembangan hijauan sebagai pakan ternak ruminansia. Ketersediaan lahan yang luas diharapkan dapat mendukung usaha peternakan dan pengelolaan sumber daya pakan di wilayah tersebut.
Integration of Voting-Based Statistical Ensembles and Rule Mining for Anomaly Detection in Microsatellite Power System Rizki Permala; Imas Sukaesih Sitanggang; Hendra Rahmawan; Wahyudi Hasbi
Indonesian Journal of Electrical Engineering and Informatics (IJEEI) Vol 14, No 2: June 2026
Publisher : IAES Indonesian Section

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52549/ijeei.v14i2.7561

Abstract

This study aims to detect anomalies, types of anomalies, and identify attributes that contribute to the cause of anomalies in the LAPAN-A2 microsatellite power system. Anomaly detection is cumulative-based, where the first year's dataset is added to the datasets of subsequent years for eight years. Anomaly detection uses a voting-based statistical ensemble (VBSE) approach and a combination of Apriori-Close to find associations and reduce rules. The VBSE obtained an average recall value of 86.49 and an average F1-score of 70.49. The F1-score value of VBSE increased by 4.2-fold compared with IForest (16.95), by 12.6-fold compared with ECOD (5.57), and by 5.6-fold compared with LOF (12.65). VBSE showed an increase in performance as the dataset complexity increased (DS1 → DS8), whereas IForest, LOF, and ECOD tended to decrease. The combination of metrics minSupp. 0.02%, minConf. 0.9, and lift is proven to be effective in capturing rare, reliable anomalies and significant association relationships. A strong correlation was observed between batteries (VBatt1–VBatt3) and a causal relationship between U_UMPB and VBatt. The types of anomalies detected included single, contextual, and correlation anomalies.
Co-Authors Aditya Cipta Raharja Aditya Kusuma Setyanegara Agus Buono Agus Buowo Ainuddin A. N Ainuddin A. N. Akhmad Faqih Alusyanti Primawati Andi Nurkholis Anissa Rezainy Annisa Annisa Annisa Annisa Puspa Kirana Baba Barus Deden Sumirat Hidayat Deny Ramdhany DEWI APRI ASTUTI Dwi Marlina Fitri Insani GONO SEMIADI Hendra Rahmawan Hendra Rahmawan Hendro Pratama Saragih Heru Sukoco Ikhsan Kurniawan Irman Hermadi Kahfi Heryandi Suradiradja Khaira, Ulfa Koentjoro, Bambang S. Lailan Syaufina Lailan Syaufina LILIK BUDIPRASETYO Luki Abdullah Makarim, Abdul Karim Marimin , Mushthofa Mushthofa Norwati Mustapha Norwati Mustapha Nur Hayati Prima Trie Wijaya Putri Thariqa Razali Yaakob Razali Yaakob Ridwan Raafi'udin Rizki Permala Ruhul Amin Sanusi Sanusi Sobir Sobir Solikin Sri Nurdiati Suci Sri Utami Sutjipto Taufik Djatna Tri Rapani Febbiyanti Wahyudi Hasbi Widyawati, Dewi Kania Wulandari Wulandari Yazid Aufar