Article Per Year (5 Year)
p-Index From 2021 - 2026
6.017
P-Index
This Author published in this journals
All Journal IAES International Journal of Artificial Intelligence (IJ-AI) Jurnal Ilmu Pertanian Indonesia Agromet MANAJEMEN IKM: Jurnal Manajemen Pengembangan Industri Kecil Menengah Jurnal Pustakawan Indonesia FORUM STATISTIKA DAN KOMPUTASI Seminar Nasional Aplikasi Teknologi Informasi (SNATI) Jurnal Ilmu Komputer dan Informasi Jurnal Pembangunan Wilayah dan Kota Agrikultura Jurnal Keteknikan Pertanian Proceedings of KNASTIK Jurnal Simetris TELKOMNIKA (Telecommunication Computing Electronics and Control) Jurnal Ilmu Komputer dan Agri-Informatika Forum Agribisnis SITEKIN: Jurnal Sains, Teknologi dan Industri Jurnal Teknologi Informasi dan Ilmu Komputer Journal of ICT Research and Applications Jurnal Pengelolaan Sumberdaya Alam dan Lingkungan (Journal of Natural Resources and Environmental Management) International Journal of Advances in Intelligent Informatics Jurnal Aplikasi Bisnis dan Manajemen (JABM) E-Journal Widyariset JOIN (Jurnal Online Informatika) Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Informatika Pertanian Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control BAREKENG: Jurnal Ilmu Matematika dan Terapan JITK (Jurnal Ilmu Pengetahuan dan Komputer) Jurnal Informatika Universitas Pamulang Jurnal ULTIMATICS CYBERNETICS BHUMI: Jurnal Agraria dan Pertanahan Komputasi: Jurnal Ilmiah Ilmu Komputer dan Matematika Aptisi Transactions on Technopreneurship (ATT) JURNAL METEOROLOGI DAN GEOFISIKA Building of Informatics, Technology and Science Journal of Robotics and Control (JRC) ILKOMNIKA: Journal of Computer Science and Applied Informatics Indonesian Journal of Electrical Engineering and Computer Science Computer Science and Information Technologies Jurnal Tanah dan Iklim Widyariset Aiti: Jurnal Teknologi Informasi Jurnal Ilmu Manajemen Terapan (JIMT) Computer Science (CO-SCIENCE) Jurnal Pustakawan Indonesia Jupiter Journal of Computer & Information Technology Makara Journal of Science Jurnal Ilmu Kehutanan Eduvest - Journal of Universal Studies J-Icon : Jurnal Komputer dan Informatika Jurnal Sistem Informasi Biodiversitas Journal of Biological Diversity
Agus Buono
School Of Data Science, Department Of Mathematics And Computer Science, IPB University, Indonesia
Aerospace Engineering Agriculture, Biological Sciences & Forestry Humanities Astronomy Automotive Engineering Biochemistry, Genetics & Molecular Biology Chemical Engineering, Chemistry & Bioengineering Chemistry Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Earth & Planetary Sciences Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Environmental Science Health Professions Immunology & microbiology Industrial & Manufacturing Engineering Law, Crime, Criminology & Criminal Justice Library & Information Science Materials Science & Nanotechnology Mathematics Mechanical Engineering Neuroscience Physics Social Sciences Transportation Other

Published : 89 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 89 Documents
Search

 5   6   7   8   9 
Enhancing FOMAML with Domain-Specific Residual Pretraining for Few-Shot Chili Disease Classification Rizal Amegia Saputra; Agus Buono; Karlisa Priandana; Samsuzana Abd Aziz; Muhamad Syukur
Computer Science (CO-SCIENCE) Vol. 6 No. 2 (2026): July 2026
Publisher : LPPM Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/co-science.v6i2.13101

Abstract

Meta-learning is an approach designed to address data limitations in few-shot learning scenarios. The performance of meta-learning is influenced by the quality of the initial weights used during the meta-training process. Initial weights derived from a relevant domain have the potential to produce more informative feature representations, thereby enabling the adaptation process to new tasks to proceed more effectively. This study analyzes the impact of domain-specific pretrained initialization on classification performance, learning stability, convergence behavior, and computational trade-offs within the First-Order Model-Agnostic Meta-Learning (FOMAML) framework using an enhanced ResNet-50 backbone. Experiments were conducted on a 3-way classification scenario with 1-shot, 5-shot, and 10-shot configurations. Model evaluation was performed using accuracy, precision, recall, and F1-score, while learning stability was analyzed using standard deviation (Std) and coefficient of variation (CV). The experimental results show that a chili-domain pretrained initialization consistently yields better performance than random initialization. Accuracy reached 95.33%, 95.60%, and 95.94% in the 1-shot, 5-shot, and 10-shot scenarios, respectively an increase of 17.20, 12.61, and 17.49 percentage points compared to random initialization. In terms of stability, the CV values decreased to 1.00%, 0.59%, and 1.03%, compared to 1.10%, 3.66%, and 2.42% with random initialization. These performance improvements were achieved with relatively small differences in training time 0.056 minutes, 0.170 minutes, and 0.876 minutes for the 1-shot, 5-shot, and 10-shot scenarios, respectively. Domain-specific pretrained initialization produces more relevant initial feature representations, thereby improving the effectiveness and stability of FOMAML adaptation while maintaining computational requirements comparable to those of random initialization
Digital Marketing Alliance on Small Medium Enterprises (SMES): A Systematic Literature Review Trukan Sri Bahukeling; Arif Imam Suroso; Agus Buono; Popong Nurhayati
Jurnal Aplikasi Bisnis dan Manajemen Vol. 10 No. 1 (2024): JABM, Vol. 10 No. 1, January 2024
Publisher : School of Business, Bogor Agricultural University (SB-IPB)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.17358/jabm.10.1.199

Abstract

The development of digital marketing continues to grow and increase rapidly. Strengthening digital marketing by SMEs encourages marketing alliances with other parties. Simultaneously, the digital marketing alliance literature accumulated with this growth, but research is still few and not consistently integrated. SMEs are widely regarded as engines of economic growth and a vital contributor to a country's GDP. A brief comprehensive review is needed to help researchers and practitioners understand the adoption of digital marketing alliance systems. This study aims to analyze and classify the literature on digital marketing alliances in SMEs. Design/methodology by conducting literature studies published between 2016-2021 in the journal listed in the Journal Citation Report. It is then analyzed according to a systematic literature review approach involving interpretation-based assessments of research methodologies and critical findings in the study. The direction of this research is expected in the future to have implications for academics and practitioners. The authors' conclusions develop a theoretical model of digital marketing alliance between government and private that is applied to SMEs, impacting to create excellence in the era of digitalization. The originality /value of this research is the first expected to take a holistically integrated approach to study the digital marketing alliance of SMEs. Keywords: digital marketing, marketing alliance, small medium enterprises (smes), literature studies
Text summarization: BART, RF, and hybrid BART-RF algorithm comparison Muhammad Adib Zamzam; Agus Buono; Toto Haryanto
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 15, No 1: February 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v15.i1.pp929-940

Abstract

Data and information accumulate quantitatively and qualitatively. Abundant text data are posted on the internet. The number correlates to the complexity of the summarization. Automatic text summarization (ATS) is one of the most challenging tasks in natural language processing (NLP). ATS approached in three ways: extractive, abstractive, and hybrid. Hybrid approach combines both extractive and abstractive. This research tests and compares performance of bidirectional auto-regressive transformer (BART) and random forest (RF) individually and the performance combination of hybrid BART and RF in ATS. The research shows that individually, BART and RF recall-oriented understudy for gisting evaluation (ROUGE) scores are having quite differences. Consecutively, ROUGE RF scores in R1, R2, and RL are 51.45, 45.52, and 54.58 respectively. Meanwhile, ROUGE BART scores are 32.78, 16.17, and 32.19. Consecutively, average ROUGE RF, BART, and RF×BART F-measure are 45.73, 21.38, and 31.31. RF has the highest average score. ATS hybrid RF×BART is shown to be performed better than the default BART. The average ROUGE F-measures for RF×BART obtain moderate score at 31.31. This score is better than the default BART’s ROUGE score. RF×BART can be an alternative to the effective hybrid approach.
Electronic Word of Mouth dan Theory of Planned Behavior dalam Keputusan Memilih Program Studi: Sebuah Tinjauan Pustaka Sistematis Farahnugraha Makkuraga; Hartoyo Hartoyo; Agus Buono; Lilik Noor Yuliati
Jurnal Ilmu Manajemen Terapan Vol. 7 No. 6 (2026): Jurnal Ilmu Manajemen Terapan (Juli - Agustus 2026)
Publisher : Dinasti Review Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.38035/jimt.v7i6.9284

Abstract

Electronic word of mouth (eWOM) menjadi sumber informasi penting bagi calon mahasiswa, sementara Theory of Planned Behavior (TPB) merupakan kerangka yang mapan untuk menjelaskan niat dan keputusan. Namun, kedua literatur ini cenderung berkembang terpisah, khususnya pada tingkat program studi. Tinjauan pustaka sistematis ini bertujuan memetakan bagaimana eWOM dihubungkan dengan keputusan memilih program studi melalui konstruk TPB. Penelusuran mengikuti protokol PRISMA 2020 pada basis data Scopus, Garuda, dan Google Scholar untuk rentang 2015–2025; sebanyak 38 artikel disertakan dan disintesis dengan kerangka Theory–Context–Characteristics. Tiga temuan utama: pertama, irisan eWOM dan TPB sangat langka; ketika keduanya muncul bersama, eWOM diperlakukan sebagai padanan norma subjektif, prediktor sejajar, atau moderator—belum sebagai jalur sebab-akibat yang membentuk norma subjektif. Kedua, ketika eWOM dimodelkan dalam pilihan pendidikan tinggi, pengaruhnya umumnya mengalir melalui citra merek, kesadaran merek, atau minat. Ketiga, unit analisis masih didominasi tingkat perguruan tinggi. Berdasarkan kesenjangan tersebut, kajian mengusulkan model integratif eWOM → TPB → keputusan pada tingkat program studi, dengan jalur eWOM → norma subjektif sebagai proposisi sentral.
SOIL MOISTURE PREDICTION USING LSTM AND GRU: UNIVARIATE AND MULTIVARIATE DEEP LEARNING APPROACHES Jemsri Stenli Batlajery; Agus Buono; Mushthofa -Mushthofa
BAREKENG: Jurnal Ilmu Matematika dan Terapan Vol 20 No 2 (2026): BAREKENG: Journal of Mathematics and Its Application
Publisher : PATTIMURA UNIVERSITY

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30598/barekengvol20iss2pp1659-1674

Abstract

Soil moisture is an important indicator in the management of water resources, precision agriculture, and disaster mitigation, such as drought and land fires. Fluctuations in soil moisture are influenced by various climate variables, requiring a reliable predictive approach essential. This research develops a daily soil moisture prediction model using Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) algorithms with univariate and multivariate approaches. Soil moisture data were obtained from Google Earth Engine, while climate data were collected from 10 BMKG stations in East Java for the period 2019–2024. Data preprocessing includes cubic spline interpolation to handle missing values and Min-Max normalization to achieve uniform feature scaling. Models were built using a direct forecasting approach for horizons to and five evaluation metrics: MAE, MSE, RMSE, MAPE, and R². The results show that the multivariate GRU model performs best at horizon with MAE = 0.05455, MSE = 0.00604, RMSE = 0.07539, MAPE = 0.19280, and R² = starting from 0.9626 on day 1 (t), then decreasing to 0.8075 on day 10 The univariate LSTM model excelled in training time efficiency (<400 seconds) at most stations. The multivariate GRU model demonstrates the highest accuracy and stability, making it suitable for medium- to long-term forecasting, while the univariate LSTM excels in training speed, making it effective for daily predictions. The model’s performance remains limited to the dataset's spatial and temporal scope. Therefore, future research should test the model in other regions and under extreme climate conditions, as well as apply transfer learning in data-scarce areas. The novelty of this study lies in comparing LSTM and GRU performance for daily soil moisture prediction in both univariate and multivariate scenarios, using complete climate variables from multiple stations.
Structural stability analysis of rain trees (Samanea saman) subjected to dead, live, and wind loads combination SITI CHUROTUL AINI; ULFA ADZKIA; EFFENDI TRI BAHTIAR; M. MIFTAH RAHMAN; AGUS BUONO; LINA KARLINASARI
Biodiversitas Journal of Biological Diversity Vol. 25 No. 10 (2024)
Publisher : Society for Indonesian Biodiversity

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.13057/biodiv/d251050

Abstract

Abstract. Aini SC, Adzkia U, Bahtiar ET, Rahman MM, Buono A, Karlinasari L. 2024. Structural stability analysis of rain trees (Samanea saman) subjected to dead, live, and wind loads combination. Biodiversitas 25: 3899-3908. Tree failure can arise from factors associated with load resistance and structural stability at sites of environmental growth. In this study, an investigation was conducted into the structural analysis of standing trees, considering the combination of compression and flexure loads in the adoption of building code guidelines. The objective of this study is to determine the safety factor based on a combined load combination governing the Euler and Ylinen Buckling Stress Method. The study used 50 rain trees (Samanea saman (Jacq.) Merr.). Therefore, to assess the impact of various load combinations on standing trees, including dead, live, and wind loads, three analyses were performed: (1) D + L + W, (2) D + L, and (3) D only. The dead load (D) represents the weight of the crown and stem above the observed section, the live load (L) accounts for activities such as climbing or hanging, and W represents wind loads. The D + L + W load combination induced both compression and bending stresses on the trees, whereas the D + L and D only focused on compression loads. Determining the minimum critical height is crucial in assessing the safety factor and categorizing trees into three groups: unsafe, safe, and very safe. The results indicated that the combined load of D + L + W demonstrated that the minimum critical height resulted from the superposition of compression and bending stresses. This finding underscores the significant role of the wind in the safety of standing trees. Structural stability analysis revealed that 18 trees were unsafe, 30 were safe, and 2 were classified as very safe. This research contributes valuable insights into understanding tree biomechanics and tree characteristics, offering a distinct approach compared to existing methods.
Neural Network Innovation for Analyzing Physiological Changes in Cattle Within Modern Transportation Systems Harry Dhika; Agus Buono; Shelvie Nidya Neyman; 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.v16i2.16007

Abstract

The distribution of cattle before Eid al-Adha often leads to transport-induced stress, negatively affecting livestock performance and economic value. This study aims to develop a predictive model of post-transport cattle performance using Artificial Neural Networks (ANN). The dataset includes physiological parameters (rectal temperature, heart rate, and respiration) and blood metabolites (glucose and creatinine) collected before and after transportation. Data augmentation and feature selection were applied using Pearson correlation to address class imbalance. The ANN model was tuned with regularisation and dropout techniques to prevent overfitting. Evaluation results show that the model achieved 91% accuracy, with F1-scores of 0.90 (Increase), 0.97 (Stable), and 0.87 (Decrease). These findings demonstrate that ANN can capture complex patterns of physiological conditions in cattle and provide reliable predictions. This model has the potential to serve as the basis for developing an early warning system to minimize the risk of performance decline in cattle due to transport stress more adaptively and efficiently.
Penentuan Kerapatan Massa Tajuk Pohon Decurrent Berdasarkan Analisis Keragaan Fisik Siti Churotul Aini; Ulfa Adzkia; Agus Buono; Iskandar Zulkarnaen Siregar; Lina Karlinasari
Jurnal Ilmu Kehutanan Vol 20 No 1 (2026): March
Publisher : Universitas Gadjah Mada

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/jik.v20i1.22134

Abstract

Self-weight calculation was identified as an essential step in tree structural analysis. In practice, this calculation included estimating stem weight based on wood density, while crown density was expressed as a percentage of crown area. However, previous research had not provided explicit methodologies for determining crown density as a function of crown mass and volume. Therefore, this research aimed to establish a proper method and corresponding conversion factors for translating area-based crown density estimates to those derived from crown weight and volume. A total of 15 healthy decurrent trees were selected to assess crown volume and density through physical attribute analysis. The new crown area density was calculated after pruning, where all pruned crown biomass was collected and weighed to determine crown mass. Mathematical analyses were developed to convert crown density values. The results showed that decurrent trees had a mean crown density of approximately 2.95 kg/m3, exceeding the value reported in reference research for excurrent trees (1.9 kg/m3). Since this research focused on tropical tree species, the results could serve as a reference for subsequent research on tropical tree structural characteristics.
Deep Learning Modeling for Subseasonal to Seasonal Rainfall Prediction Lumalessil, Ferry Lodewik; Kustiyo, Aziz; Buono, Agus; Faqih, Akhmad
ILKOMNIKA Vol 8 No 2 (2026): Volume 8, Number 2, August 2026
Publisher : Lembaga Penelitian dan Pengabdian Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28926/ilkomnika.v8i2.922

Abstract

Rainfall variability has a major impact on the agricultural sector because conditions that are too wet or too dry can increase the risk of flooding, drought, crop disturbances, and changes in the planting calendar. Subseasonal to Seasonal (S2S) forecasting is important because it is located between short-term weather forecasts and seasonal predictions, so that it can provide early information for decision-making in the agriculture, water management, and disaster mitigation sectors. This study aims to develop a deep learning-based S2S rainfall prediction model using the CNN–LSTM and CNN–GRU hybrid architecture by utilizing ECMWF atmospheric variables, as well as CHIRPS rainfall as predictors. CNNs are used to extract spatial features, while LSTM and GRU model temporal dynamics. The model generates predictions at a lead time of 0–45 or up to 46 days ahead for each ECMWF release. The results of the evaluation showed spatial variation in performance on the island of Java. CNN–LSTM showed the best performance, especially in the central Java region with an RMSE of 3.286, a correlation of 0.944, a BSS of 0.414, and a CRPSS of 0.775. CNN-GRU also showed good performance in the central to southern regions with an RMSE of 2.939, a correlation of 0.954, a BSS of 0.406, and a CRPSS of 0.631. In general, CNN-LSTM provides a more stable performance, especially in probabilistic evaluations, while the western Java region still shows greater prediction challenges.
Co-Authors Ade Fruandta Adi Rakhman Aditya Cipta Raharja Agung Prajuhana Putra Akhmad Faqih Akhmad Faqih Alif Kurniawan Alvin Fatikhunnada Anang Kurnia Angga Wahyu Pratama Aries Maesya Arif Imam Suroso Arini Aha Pekuwali Arini Pekuwali Astuti, Indah Puji Atik Pawestri Sulistyo Aziz Kustiyo Aziz Rahmad Bahukeling, Trukan Sri Benyamin Kusumoputro Bib Paruhum Silalahi Budi Nugroho Cece Sumantri DEWI APRI ASTUTI Dhany Nugraha Ramdhany Dian Kartika Utami Edi Santosa EFFENDI TRI BAHTIAR Ekowati Handharyani Endang Purnama Giri Erliza Hambali Erliza Noor Ernan Rustiadi Fadhilah Syafria Fajar Delli Wihartiko Farahnugraha Makkuraga Fildza Novadiwanti Firdaus, Husni Firdaus, Nova Fredicia Fredicia Galih Kurniawan Sidik Galih Kurniawan Sidik Galih Kurniawan Sidik Gendut Suprayitno Gita Adhani GUNARSO GUNARSO Hardhienata, Medria Kusuma Dewi Harry Dhika Hartoyo Hartoyo Hastuadi Harsa Herianto Herianto Heru Sukoco Hidayat Hidayat Hidayat I Wayan Astika Ibrahim, Firmansyah Iis Rodiah Imas Sukaesih Sitanggang Indah Prasasti Indah Puji Astuti Indra Jaya Inggih Permana Irman Hermadi Irmansyah . Irsal Las Irsal Las ISKANDAR ZULKARNAEN SIREGAR Jemsri Stenli Batlajery Kana Saputra S Karlisa Priandana Kikin H Mutaqin Kudang Boro Seminar Laila Sari Lubis Laila Sari Lubis Lailan Syaufina Lidya Ningsih Lilik Noor Yuliati Lina Karlinasari Liyantono Luh Kesuma Wardhani Lumalessil, Ferry Lodewik Luthfan Almanfaluthi M. Cholid Mawardi M. MIFTAH RAHMAN M. Mukhlis Marcelita, Faldiena Mindara, Gema Parasti Mohamad Solahudin Muhammad Adib Zamzam Muhammad Ardiansyah Muhammad Rafi Muttaqin Mushthofa Mushthofa Mustakim Mustakim Mustakim Mustakim Muttaqin, Muhammad Rafi Niswati, Za'imatun Noviyanti, Inna Nurhayati, Yosi Popong Nurhayati Pratistya, Sayu Desty Puspita Kartika Sari Puspita Kartika Sari Putri Yuli Utami Raehan, Siti Raharja, Aditya Cipta Rahmat Hidayat Rangga Pebrianto Rangga Rizal Amegia Saputra Rizal Syarief Rizaldi Boer Rizki, Arviani RR. Ella Evrita Hestiandari Samsuzana Abd Aziz Santo, Deni Sanusi Sanusi Sari Agustini Hafman Savitri, Siska Shelvie Nidya Neyman Sholihah, Walidatush Sidik, Galih Kurniawan Siregar, Ardinsyah Sitanggang, Imas S. SITI CHUROTUL AINI Siti Churotul Aini Siti Kania Kushadiani Sony Hartono Wijaya Sri Dianing Asri SRI HENDRASTUTI HIDAYAT Sri Nurdiati Sri Wahjuni Stephane Douady Suharno Suharno Suharno Sumanto Sumanto Syeiva Nurul Desylvia Taufik Djatna Thoyyibah Tanjung Toto Haryanto Trukan Sri Bahukeling ULFA ADZKIA Ulfa Adzkia Uliniansyah, Mohammad Teduh Vicky Zilvan Wisnu Ananta Kusuma Wisnu Jatmiko Woro Estiningtyas Woro Estiningtyas Woro Estiningtyas Yan Mitha Djaksana Yandra Arkeman Yani Nurhadryani Yenni Vetrita Yoanda, Sely