Article Per Year (5 Year)
p-Index From 2020 - 2025
2.696
P-Index
This Author published in this journals
All Journal Semantik Techno.Com: Jurnal Teknologi Informasi Prosiding SNATIF Jurnal Transformatika Scientific Journal of Informatics Seminar Nasional Informatika (SEMNASIF) Journal of Information System Sinkron : Jurnal dan Penelitian Teknik Informatika Journal of Information Technology and Computer Science Jurnal Pilar Nusa Mandiri Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control IKRA-ITH Informatika : Jurnal Komputer dan Informatika Abdimasku : Jurnal Pengabdian Masyarakat Jurnal Sistem Komputer dan Informatika (JSON) Jurnal Pengabdian Literasi Digital Indonesia Prosiding Seminar Riset Mahasiswa
Fahmi Amiq
Fakultas Ilmu Komputer, Universitas Dian Nuswantoro, Semarang 50131
Computer Science & IT Control & Systems Engineering Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Health Professions Industrial & Manufacturing Engineering Social Sciences Other

Published : 42 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 42 Documents
Search

 1   2   3   4   5 
Peningkatan Fitur Ekstraksi Berbasis Discrete Wavelet Transform dan Principal Component Analysis Pada Pengenalan Citra Batik Sugiarto, Edi; Budiman, Fikri; Muslih, Muslih; Arifin, Zaenal; Fahmi, Amiq; Hendriyanto, Novi
Jurnal Transformatika Vol. 20 No. 2 (2023): January 2023
Publisher : Jurusan Teknologi Informasi Universitas Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26623/transformatika.v20i2.5613

Abstract

Pengenalan pola batik menjadi penting karena batik sebagai warisan budaya bangsa perlu dilestarikan kepada generasi ke generasi. Salah satu upaya untuk memperkenalkan pola batik ini yaitu dengan memperkenalkan keragaman motif atau polanya. Penelitian ini bertujuan untuk mengoptimalisasi metode fitur ekstraksi dengan menggunakan metode Discrete Wavelet Transform (DWT) dan Principal Component Analysis (PCA) untuk mereduksi hasil fitur ekstraksi yang diperoleh dari DWT berdasarkan fitur-fitur yang memiliki korelasi yang baik. Tahapan dilakukan dengan menggunakan 310 data berupa citra batik yang terdiri dari 7 motif dengan komposisi 240 untuk data training dan 70 untuk data testing. Pada tahap fitur ekstraksi dengan menambahkan metode PCA pada DWT mampu mereduksi fitur dari 20 menjadi 5 fitur. Selanjutnya fitur tersebut diuji dengan melakukan klasifikasi menggunakan metode KNN dan SVM. Hasil dari klasifikasi dapat dibuktikan bahwa dengan menggunakan metode PCA dan DWT pada tahap fitur ekstraksi mampu meningkatkan klasifikasi hingga 5%.
Implementation of Deep Learning Based on Convolution Neural Network for Batik Pattern Recognition Sugiarto, Edi; Budiman, Fikri; Fahmi, Amiq
Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control Vol. 10, No. 1, February 2025
Publisher : Universitas Muhammadiyah Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22219/kinetik.v10i1.2019

Abstract

Batik as a cultural heritage is one of the heritages that needs to be preserved so that it continues to be recognized from generation to generation. Efforts to preserve batik can be made by using technology that can recognize batik motifs. Pattern recognition is a branch of science related to the identification, classification, and interpretation of patterns. Deep learning is one of the technologies that can be used very well for pattern recognition, especially for syllable and image recognition. Convolutional neural network (CNN) is one of the most popular deep learning methods and the most established algorithm for deep learning models. The main advantage of CNN over the preceding methods is its ability to automatically detect features, making the feature extraction and classification process highly organized. This study aims to apply CNN for batik pattern recognition. The batik patterns used were geometric patterns, divided into 7 batik classes. Experiments were conducted on 3100 data, consisting of 3000 for training set and 100 for testing set. At the preprocessing stage, the batik image was resized to 28x28, and the color was changed to grayscale. Training was carried out on 100, 200, and 300 epochs. The classification results prove that CNN can recognize batik patterns well with an accuracy rate of 95%.
AHP-SPIRE: Edukasi Pemilu Sehat dan Bertanggung Jawab Untuk Pemilih Pemula Fahmi, Amiq; Mulyanto, Edy; Sugiarto, Edi; Pramudi, Yuventius Tyas Catur; Budiman, Fikri
Jurnal Pengabdian Literasi Digital Indonesia Vol. 3 No. 2 (2024): December
Publisher : Puslitbang Akademi Relawan TIK Indonesia (ARTIKA)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57119/abdimas.v3i2.120

Abstract

In Indonesia, general elections are a fundamental democratic process to elect leaders, both the President and Regional Heads, such as Governors, Mayors, and Regents. The selection of suitable and qualified leaders determines the success of a nation, state, and region in welcoming Golden Indonesia 2045. This community service program aims to provide healthy and responsible election education to permanent voters registered and verified by the KPU, especially novice voters with the right to vote. This community service proposes the application of the Analytic Hierarchy Process (AHP) with SPIRE (Spiritual, Physical, Intellectual, Relationship, and Emotional) criteria as an effective tool for selecting suitable and ideal leadership candidates, both President and Regional Head, among novice voters in grades XI and XII SMA. AHP-SPIRE is a multi-criteria method that allows structured and measurable decision-making based on consideration of various important factors for presidential, Governor, Regent, or Mayor candidates. Ultimately, novice voters, especially students in grades XI and XII, have better decision-making techniques based on the expected criteria.
Implementation of Discrete Wavelet Transform and Directed Acyclic Graph SVM for Batik Pattern Recognition Sugiarto, Edi; Budiman, Fikri; Fahmi, Amiq; Sulistyono, MY Teguh; Rohmani, Asih
JOINS (Journal of Information System) Vol. 10 No. 1 (2025): Edisi Mei 2025
Publisher : Fakultas Ilmu Komputer, Universitas Dian Nuswantoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33633/joins.v10i1.12576

Abstract

Batik as a heritage of the ancestors of the Indonesian nation certainly needs to be preserved so that it continues to be recognized from generation to generation, one of which is by introducing the diversity of its patterns. Efforts to introduce batik patterns can be made, one of which is by implementing technology that can recognize batik patterns automatically based on batik patterns, namely pattern recognition technology. This study aims to optimize batik pattern recognition using the discrete wavelet transform (DWT) and directed acyclic graph SVM (DAGSVM) methods. The stages start from preprocessing, feature extraction, and classification. The study used 310 batik images of 7 different patterns and divided into 240 images for training data and 70 for testing data. DWT method is used in the feature extraction stage while DAG SVM is used in the classification stage. The study was conducted by comparing the accuracy between standard DAG SVM and DAG SVM that has been optimized with DWT and the results of the accuracy test can be proven that adding the DWT method with DAG SVM can increase accuracy by 3%.
AGGLOMERATIVE HIERARCHICAL CLUSTERING FOR REGIONAL GROUPING IN CENTRAL JAVA BASED ON WELFARE INDICES Kurnia Desita, Raafi; Fahmi, Amiq; Rohmani, Asih; Sulistyono, MY. Teguh
Jurnal Pilar Nusa Mandiri Vol. 21 No. 1 (2025): Pilar Nusa Mandiri : Journal of Computing and Information System Publishing Pe
Publisher : LPPM Universitas Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/pilar.v21i1.6445

Abstract

Central Java Province comprises 35 regencies/cities with diverse welfare characteristics. These variations present challenges for the government in formulating targeted development policies. This study aims to group regions in Central Java based on welfare indices to support more effective policy planning. The Agglomerative Hierarchical Clustering method with the Average Linkage approach is applied to cluster the regions based on three attributes: Human Development Index, Uninhabitable Houses, and Economic Growth Rate. Data were obtained from the Central Java Provincial Social Service and the official website of the Central Statistics Agency (BPS) and processed using the proposed method. Experimental results indicate three clusters with proportions: 32 regions in cluster 1 (91.4%), 2 regions in cluster 2 (5.7%), and 1 region in cluster 3 (2.9%). Regions with higher welfare dominate the first cluster, while the second and third clusters include regions facing more significant welfare challenges. Clustering results were evaluated using the Silhouette Score (0.535) and Davies-Bouldin Index Score (0.610), demonstrating that the applied method effectively grouped regions based on the specified attributes. The findings of this study are anticipated to lay the groundwork for more directed and effective development policies.
Strategic Clustering of Poverty Areas in Central Java Using K-Means and Silhouette Evaluation Tacharri, Chusnuut; Rohmani, Asih; Fahmi, Amiq
Sinkron : jurnal dan penelitian teknik informatika Vol. 9 No. 2 (2025): Research Articles April 2025
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v9i2.14734

Abstract

Indonesia is one of several developing nations that struggle with poverty. Central Java is one of Indonesia's provinces with the third-highest percentage of the country's inadequate. This study aims to explore and improve the application of the K-Means Algorithm in investigating socioeconomic disparities. In this study, the Elbow method is used to determine the optimal number of clusters to overcome the weaknesses in determining the number of clusters in conventional K-Means. Model evaluation using the silhouette coefficient shows the effectiveness of this method approach with a value of 0.504 and several clusters (K = 3), which meets the medium structure category. The Human Development Index (HDI) and Uninhabitable Households (RTLH) were two criteria used to categorize poverty areas using the K-Means Algorithm optimization successfully. According to the clustering results, there were 12 regions in Cluster 0, 2 in Cluster 1, and 21 in Cluster 2. These findings are anticipated to offer the Central Java Provincial Government critical insights, facilitating the development of precise and well-targeted initiatives to address deprivation issues effectively. Furthermore, a more systematic and structured optimization of the K-Means algorithm has the potential to significantly improve both the accuracy and practical relevance of studies on socioeconomic inequality in Central Java Province. This enhanced methodological approach can provide more in-depth results on data-driven regional disparities to reduce these disparities comprehensively.
Implementation of DBSCAN Algorithm for Grouping Poverty Levels in Central Java Province Fahmi, Amiq; Tsani, Maulida Aristia
Jurnal Sistem Komputer dan Informatika (JSON) Vol 6, No 4 (2025): Juni 2025
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v6i4.8553

Abstract

Poverty is a complex problem that hampers socio-economic development in Indonesia, especially in Central Java Province, which encounters significant challenges, with a poverty rate reaching 10.77% in 2023. This study aims to identify spatial patterns of poverty in 35 districts/cities in Central Java Province by grouping areas based on the number of poor individuals reported by the Central Java Province Statistics Agency (BPS) in 2023. The Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm groups districts/cities based on poverty data density with optimized parameters to produce statistically significant clusters. The results of the analysis reveal four clusters, specifically cluster 0 (moderate poverty), cluster 1 (high poverty), cluster 2 (very high poverty), and cluster 3 (low poverty). Model validation was executed using the Silhouette Score (0.447) and Davies-Bouldin Index (0.441), which showed the validity of the clustering. This study is anticipated to provide strategic implications for the Central Java Provincial Government in formulating more effective poverty alleviation policies, such as resource allocation adjusted to each cluster's characteristics. In addition, this study enables future exploration of additional socio-economic factors influencing poverty, such as the Human Development Index, education, health, infrastructure, resource accessibility, and comparative analysis of clustering algorithms for enhanced accuracy.
Penerapan K-Nearest Neighbors (KNN) untuk Klasifikasi Aset dalam Upaya Menentukan Aset Wakaf Produktif Sugiarto, Edi; Fahmi, Amiq; Muslih, Muslih; Hendriyanto, Novi
Jurnal Transformatika Vol. 19 No. 2 (2022): January 2022
Publisher : Jurusan Teknologi Informasi Universitas Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26623/transformatika.v19i2.3356

Abstract

aset wakaf berupa tanah yang tersebar di Indonesia terbilang cukup besar, sehingga aset wakaf yang besar ini perlu dikelola dengan baik agar tidak menimbulkan banyak permasalahan yang pada akhirnya tanah wakaf tidak sesuai dengan tujuannya dan tidak dapat digunakan untuk kepentingan umat. Instrument pengamanan aset wakaf telah memenuhi, namun masih banyak muncul persoalan mengenai aset wakaf seperti menguapnya bondo wakaf, sengketa, alih fungsi, dll, sehingga dalam hal ini menunjukan bahwa banyak persoalan terkait pengelolaan aset wakaf yang harus dipecahkan. potensi wakaf sangat besar, bahkan diperkirakan potensi tanah wakaf di indonesia mencapai lima kali luas singapura, namun saat ini belum dikelola secara profesional dan lebih produktif. Penggunaan tanah wakaf di indonesia masih identik dengan masjid dan makam, padahal wakaf dapat juga dikelola menjadi aset-aset ekonomi yang menghasilkan keuntungan sehingga hasil dari wakaf produktif tersebut dapat digunakan untuk kepentingan umat. K-Nearest Neighbors (KNN) merupakan algoritma klasifikasi yang didasarkan pada analogi yaitu membandingkan data uji dengan data latih yang berada dekat dengan dan memiliki kemiripan dengan data uji tersebut, dalam penelitian ini KNN digunakan sebagai metode untuk klasifikasi aset wakaf guna mengidentifikasi aset wakaf tersebut berpotensi produtif atau tidak produktif. Penelitian dilakukan dengan menggunakan 57 data aset wakaf yang diperoleh dengan membagi menjadi 45 data untuk training dan 12 untuk testing. Hasil pengujian yang telah dilakukan membuktikan metode KNN ini memiliki akurasi yang baik untuk klasifikasi aset wakaf yaitu mencapai 93% pada data training dan 83% pada data testing.
Fairer Public Complaint Classification on LaporGub: Integrating XLM-RoBERTa with Focal Loss for Imbalance Data Zahro, Azzula Cerliana; Alzami, Farrikh; Sani, Ramadhan Rakhmat; Fahmi, Amiq; Megantara, Rama Aria; Naufal, Muhammad; Azies, Harun Al; Iswahyudi, Iswahyudi
Sinkron : jurnal dan penelitian teknik informatika Vol. 9 No. 4 (2025): Articles Research October 2025
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v9i4.15260

Abstract

The advancement of digital technology has provided opportunities for governments to improve the quality of public services through citizen complaint channels. One example of this implementation in Indonesia is Lapor Gub, managed by the Dinas Komunikasi dan Informasi Provinsi Jawa Tengah (Communication and Information Agency of Central Java Province). This platform receives thousands of complaints daily, ranging from infrastructure, social issues, to illegal levies. However, the large volume of data and the imbalanced distribution of categories pose significant challenges for both manual and automated processing. This study aims to classify citizen complaint texts using XLM-RoBERTa combined with Focal Loss as an approach to handle data imbalance. The dataset consists of 53,774 complaints after data cleaning and text preprocessing. The training process applied a stratified split (78% training, 18% validation, 10% testing) and fine-tuning for 10 epochs. Model performance was evaluated using accuracy, precision, recall, and macro F1-score. The results show that the model without Focal Loss achieved 78.1% accuracy with a macro F1-score of 0.606, while the model with Focal Loss improved the macro F1-score to 0.625 with 78.5% accuracy. These findings demonstrate that the application of Focal Loss enhances the model’s ability to recognize minority categories without reducing performance on majority classes. Therefore, the combination of RoBERTa and Focal Loss offers an effective solution to support faster, fairer, and more transparent public complaint management.
Explainable Machine Learning for Poverty Prediction in Central Java Regencies and Cities Fhaldian, Wahyu; Fahmi, Amiq
Sinkron : jurnal dan penelitian teknik informatika Vol. 9 No. 4 (2025): Articles Research October 2025
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v9i4.15312

Abstract

Poverty remains a multidimensional challenge in Central Java, necessitating robust data-driven approaches to identify its socioeconomic determinants. This study applied six machine learning models, specifically Extreme Gradient Boosting (XGBoost), Random Forest, CatBoost, LightGBM, Elastic Net Regression, and a Stacking ensemble using district-level data from Statistics Indonesia covering demographics, education, labor, infrastructure, and household welfare. Model evaluation combined an 80:20 hold-out split, 10-fold cross-validation, and noise perturbation tests. Results show that XGBoost achieved the best individual performance (MAE = 2,180.01; RMSE = 3,512.07; R² = 0.931), while the Stacking ensemble surpassed all single learners (MAE = 2,640.99; RMSE = 3,202.79; R² = 0.942). Interpretability was ensured through SHAP (Shapley Additive Explanations), Partial Dependence Plots (PDP), and Accumulated Local Effects (ALE), consistently identifying Number of Households, Per Capita Expenditure, and Uninhabitable Houses as the most influential predictors. Counterfactual simulations indicated that increasing per capita expenditure by 10% could reduce the poverty index by 9.9%, while reducing household size by 10% lowered it by 11.3%. Robustness checks revealed Brebes as an influential district shaping model stability. Overall, the findings demonstrate that boosting and stacking ensembles, when combined with explainable AI tools, not only enhance predictive accuracy but also provide transparent, policy-relevant evidence to strengthen poverty alleviation programs in Central Java. This study contributes both methodological advances in explainable machine learning and practical insights for targeted poverty reduction strategies.
Co-Authors Abdul Rohim Abu Salam Agus Winarno Agus Winarno, Agus Alzami, Farrikh Ardianda Aryo Prakoso Ariel Bagus Nugroho Asih Rohmani, Asih Budi Harjo Budiono Budiono Candra Irawan Catur Supriyanto Diana Purwitasari Edi Faisal Edi Sugiarto Edi Sugiarto Edi Sugiarto Edi Sugiarto Edi Sugiarto Edi Sugiarto Fhaldian, Wahyu Fikri Budiman Hadi, Heru Pramono Harun Al Azies Hindarto, Aris Nur Husna, Farida Amila Indra Gamayanto ISWAHYUDI ISWAHYUDI Karis Widyatmoko Kurnia Desita, Raafi Lalang Erawan Lintang Mekar Tanjung Maurensa, Giacinta Mauridhi Hery Purnomo Megantara, Rama Aria Moch. Eko Rustiyono Muhammad Naufal, Muhammad Mulyanto, Edy Muslih Muslih MY. Teguh Sulistyono Nova Rijati Novi Hendriyanto, Novi Pujiono Pujiono Pujiono Pujiono Pujiono Ramadhan Rakhmat Sani Ridha Rahmawati Ridho Pambudi Rizky Adrianto Sasono Wibowo Sidharta, Bayu Adjie Sihombing, Drigo Alexander Sri Winarno Suhariyanto - Suharnawi Suharnawi Suryo Adi Nugroho Tacharri, Chusnuut Tsani, Maulida Aristia Yuventius Tyas Catur Pramudi Zaenal Arifin Zahro, Azzula Cerliana