Claim Missing Document
Check
Articles

Found 20 Documents
Search

Integrating SMOTE-Tomek and Fusion Learning with XGBoost Meta-Learner for Robust Diabetes Recognition Setiadi, De Rosal Ignatius Moses; Nugroho, Kristiawan; Muslikh, Ahmad Rofiqul; Iriananda, Syahroni Wahyu; Ojugo, Arnold Adimabua
Journal of Future Artificial Intelligence and Technologies Vol. 1 No. 1 (2024): June 2024
Publisher : Future Techno Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62411/faith.2024-11

Abstract

This research aims to develop a robust diabetes classification method by integrating the Synthetic Minority Over-sampling Technique (SMOTE)-Tomek technique for data balancing and using a machine learning ensemble led by eXtreme Gradient Boosting (XGB) as a meta-learner. We propose an ensemble model that combines deep learning techniques such as Bidirectional Long Short-Term Memory (BiLSTM) and Bidirectional Gated Recurrent Units (BiGRU) with XGB classifier as the base learner. The data used included the Pima Indians Diabetes and Iraqi Society Diabetes datasets, which were processed by missing value handling, duplication, normalization, and the application of SMOTE-Tomek to resolve data imbalances. XGB, as a meta-learner, successfully improves the model's predictive ability by reducing bias and variance, resulting in more accurate and robust classification. The proposed ensemble model achieves perfect accuracy, precision, recall, specificity, and F1 score of 100% on all tested datasets. This method shows that combining ensemble learning techniques with a rigorous preprocessing approach can significantly improve diabetes classification performance.
Outlier Detection Using Gaussian Mixture Model Clustering to Optimize XGBoost for Credit Approval Prediction Setiadi, De Rosal Ignatius Moses; Muslikh, Ahmad Rofiqul; Iriananda, Syahroni Wahyu; Warto, Warto; Gondohanindijo, Jutono; Ojugo, Arnold Adimabua
Journal of Computing Theories and Applications Vol. 2 No. 2 (2024): JCTA 2(2) 2024
Publisher : Universitas Dian Nuswantoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62411/jcta.11638

Abstract

Credit approval prediction is one of the critical challenges in the financial industry, where the accuracy and efficiency of credit decision-making can significantly affect business risk. This study proposes an outlier detection method using the Gaussian Mixture Model (GMM) combined with Extreme Gradient Boosting (XGBoost) to improve prediction accuracy. GMM is used to detect outliers with a probabilistic approach, allowing for finer-grained anomaly identification compared to distance- or density-based methods. Furthermore, the data cleaned through GMM is processed using XGBoost, a decision tree-based boosting algorithm that efficiently handles complex datasets. This study compares the performance of XGBoost with various outlier detection methods, such as LOF, CBLOF, DBSCAN, IF, and K-Means, as well as various other classification algorithms based on machine learning and deep learning. Experimental results show that the combination of GMM and XGBoost provides the best performance with an accuracy of 95.493%, a recall of 91.650%, and an AUC of 95.145%, outperforming other models in the context of credit approval prediction on an imbalanced dataset. The proposed method has been proven to reduce prediction errors and improve the model's reliability in detecting eligible credit applications.
Evaluasi Tata Kelola Sistem Informasi Arsip Digital (SIAD) Menggunakan Framework COBIT 2019 di Disdukcapil Kabupaten Malang Amelisa, Eka Puspita Roro; Marcus, Ronald David; Muslikh, Ahmad Rofiqul
Jurnal Pendidikan dan Teknologi Indonesia Vol 5 No 2 (2025): JPTI - Februari 2025
Publisher : CV Infinite Corporation

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jpti.583

Abstract

Kemajuan teknologi informasi (TI) memberikan peluang besar bagi instansi pemerintah untuk meningkatkan kualitas layanan publik. Namun, Dinas Kependudukan dan Pencatatan Sipil Kabupaten Malang masih menghadapi tantangan dalam mengoptimalkan tata kelola Sistem Informasi Arsip Digital (SIAD). Hal ini memengaruhi efektivitas dan efisiensi pengelolaan arsip, serta layanan administrasi kependudukan. Penelitian ini menggunakan framework COBIT 2019 untuk mengevaluasi tingkat kapabilitas tata kelola pada SIAD. Fokus penelitian mencakup lima domain utama, yaitu APO12 - Manajemen Risiko, BAI09 - Manajemen Aset, DSS03 - Manajemen Masalah, DSS05 - Manajemen Keamanan Layanan, dan MEA03 - Kepatuhan terhadap Regulasi. Data dikumpulkan melalui kuesioner berbasis skala Guttman dan dianalisis menggunakan model capability level ISACA. Hasil penelitian menunjukkan bahwa seluruh domain telah mencapai Level 4 (Predictable) dengan kategori Largely Achieved, yang berarti proses telah terdokumentasi dan berjalan sistematis. Namun, ditemukan kesenjangan pada pemantauan real-time, analisis prediktif, dan otomatisasi proses. Penelitian ini merekomendasikan penerapan teknologi pendukung, pelatihan sumber daya manusia, serta evaluasi dan audit berkala untuk meningkatkan tata kelola TI. Penelitian ini memberikan panduan strategis bagi Disdukcapil untuk mencapai tata kelola TI yang lebih efisien dan berkelanjutan.
Analisis Pemilihan Media Promosi UMKM untuk Meningkatkan Volume Penjualan Menggunakan Metode Analytical Hierarchy Process (AHP) Subiyantoro, Edi; Muslikh, Ahmad Rofiqul; Andarwati, Mardiana; Swalaganata, Galandaru; Pamuji, Fandi Yulian
Jurnal Teknologi dan Manajemen Informatika Vol. 8 No. 1 (2022): Juni 2022
Publisher : Universitas Merdeka Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26905/jtmi.v8i1.6760

Abstract

The increase in the number of creative industry entrepreneurs on the scale of UMKMs in Indonesia must be supported by several factors so that these businesses can develop. These factors range from business conditions, environment, facilities, and infrastructure, to technology. In terms of the use of technology, UMKM business actors can use it in various fields including the procurement of raw materials, the production process to the marketing and promotion stages of the products produced. This analysis aims to determine the weight the importance of the criteria to create an element of UMKM sales volume. In addition, it also helps UMKM actors in making decisions in choosing and using which alternative best suits their needs. Based on the results of the analysis of this study, it can be concluded that alternative social media is a priority criterion in increasing the sales volume of UMKM actors. Based on the overall average weight value, the alternative for social media is to expand the market by increasing the intensity of promotions with various social media. Such as WhatsApp Business, Instagram, Facebook, YouTube, and others to increase product sales for UMKM actors.
COMPARATIVE ANALYSIS OF PERFORMANCE AND EFFICIENCY OF LOAD BALANCING ALGORITHMS ON INGRESS CONTROLLER Khamdani, Ahmad Rizal; Muslikh, Ahmad Rofiqul; Affandi, Arif Saivul
Jurnal Teknik Informatika (Jutif) Vol. 6 No. 1 (2025): JUTIF Volume 6, Number 1, February 2025
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2025.6.1.4040

Abstract

Kubernetes has become the dominant container orchestration platform in production environments, with the ingress controller playing a critical role in managing external traffic to services within the cluster. This study aims to provide recommendations for optimal load balancing algorithms for Kubernetes production environments by analyzing and comparing the performance of four algorithms namely round robin, static-rr, least connection, and random on the HAProxy ingress controller. The research method is conducted through observation using k6 and Grafana performance test tools, as well as literature studies, with measurements including total requests, throughput, latency, CPU usage, and memory at various levels of user load. The data was analyzed using descriptive statistical techniques, normality test, homogeneity test, and tests for group differences using one-way ANOVA or Kruskal-Wallis H. The results show that static-rr excels in throughput, total requests, and CPU and memory efficiency at high load, while least connection is more effective for latency at low load. Round robin and random showed stable performance at low load but less optimal at high load. The conclusion of this study is that choosing the right load balancing algorithm depends on the load characteristics and desired performance metrics, to ensure optimal Kubernetes performance under various load scenarios in production environments.
Analisis Kepuasaan Pengguna Aplikasi GRAB Sebagai Transportasi Online Dengan Metode TAM Elan, Melania Seindang; Muslikh, Ahmad Rofiqul
J-INTECH (Journal of Information and Technology) Vol 12 No 02 (2024): J-Intech : Journal of Information and Technology
Publisher : LPPM STIKI MALANG

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32664/j-intech.v12i02.1304

Abstract

Grab is a company that provides digital-based transportation services that continues to improve the quality of its services. Grab offers a variety of service options, from transportation, goods delivery, to food delivery. Problems with the Grab application, such as usage problems, inaccurate location points, and fictitious orders, have an impact on consumer satisfaction. Analysis of aspects that impact satisfaction is needed to assess application performance and consumer satisfaction levels. The goal of this observation is to measure user satisfaction which can ultimately provide an overview of the success of implementing the system based on user perceptions using the TAM method. This research method uses TAM. The use of TAM in this research uses 5 variables in TAM including Perceived Ease of Use, Perceived Usefulness, Behavioral Intention, Actual Use, and Attitude Toward Using. The results obtained from this research in the form of independent variables have a contribution of 74.8% to user satisfaction, while the remaining 25.2% has an impact from other variables that are not present in this form of linear regression. This means that the independent variable has a contribution of 74.8% to user satisfaction, while the remaining 25.2% has an impact from other variables that are not present in this form of linear regression.
Aspect-Based Sentiment Analysis on E-commerce Reviews using BiGRU and Bi-Directional Attention Flow Setiadi, De Rosal Ignatius Moses; Warto, Warto; Muslikh, Ahmad Rofiqul; Nugroho, Kristiawan; Safriandono, Achmad Nuruddin
Journal of Computing Theories and Applications Vol. 2 No. 4 (2025): JCTA 2(4) 2025
Publisher : Universitas Dian Nuswantoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62411/jcta.12376

Abstract

Aspect-based sentiment Analysis (ABSA) is vital in capturing customer opinions on specific e-commerce products and service attributes. This study proposes a hybrid deep learning model integrating Bi-Directional Gated Recurrent Units (BiGRU) and Bi-Directional Attention Flow (BiDAF) to perform aspect-level sentiment classification. BiGRU captures sequential dependencies, while BiDAF enhances attention by focusing on sentiment-relevant segments. The model is trained on an Amazon review dataset with preprocessing steps, including emoji handling, slang normalization, and lemmatization. It achieves a peak training accuracy of 99.78% at epoch 138 with early stopping. The model delivers a strong performance on the Amazon test set across four key aspects: price, quality, service, and delivery, with F1 scores ranging from 0.90 to 0.92. The model was also evaluated on the SemEval 2014 ABSA dataset to assess generalizability. Results on the restaurant domain achieved an F1-score of 88.78% and 83.66% on the laptop domain, outperforming several state-of-the-art baselines. These findings confirm the effectiveness of the BiGRU-BiDAF architecture in modeling aspect-specific sentiment across diverse domains.
Optimization of Application Deployment Architecture in Container Orchestration Fachrudin, Mochamad Rizal; Muslikh, Ahmad Rofiqul
Journal of Applied Informatics and Computing Vol. 9 No. 2 (2025): April 2025
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v9i2.8972

Abstract

Container orchestration has become a widely adopted standard for application deployment among medium to large-scale organizations. Docker Swarm is one of the popular container orchestration tools due to its relatively simple configuration. However, if the Docker Swarm cluster architecture is not properly designed, the goal of container orchestration, which is availability, cannot be achieved optimally. Challenges such as centralized traffic on a single node and service dependency on a single node are critical issues that need to be addressed. This study proposes solutions through an experimental approach involving the design, implementation, testing, and evaluation of a Docker Swarm cluster architecture to address these challenges. The results of this study demonstrate that the proposed architecture successfully resolves these issues. Traffic can be distributed more evenly across all nodes. When only one node is available, 5 out of 10 requests can be handled with a response latency of 197.4 ms. With two nodes available, the number of requests handled increases to 7 out of 10, with a response latency of 534.86 ms. The greater the number of available nodes, the more requests can be successfully processed. Services also become more flexible, and capable of running on any node, while offering additional benefits such as dual load balancing through DNS-based load balancing and the default load balancing provided by Docker Swarm's routing mesh. However, limitations such as the need for more complex adjustments and configurations should be considered, especially when implementing this architecture in on-premise environments, to ensure the best adoption and results.
Perancangan Desain UI/UX Berbasis Aplikasi pada Perumda Air Minum Tirta Komodo Kabupaten Manggarai Menggunakan Metode Design Thinking Jehadu, Yustina Vania Ghaisani; Muslikh, Ahmad Rofiqul
Jurnal Vokasi Teknik Informatika Vol 4 No 1 (2024)
Publisher : Universitas Negeri Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24036/javit.v4i1.166

Abstract

Perkembangan teknologi informasi dan komunikasi telah mengubah cara manusia berinteraksi dengan informasi, termasuk dalam sektor pelayanan publik seperti Perusahaan Daerah Air Minum (PDAM). PDAM adalah singkatan dari Perusahaan Daerah Air Minum, yang merupakan badan usaha milik pemerintah daerah yang menyediakan air bersih kepada warga di Indonesia. Tugas utama PDAM adalah menyediakan air bersih, membangun infrastruktur dan menyediakan saluran air bagi masyarakat. Penelitian ini bertujuan untuk meningkatkan kualitas pelayanan pada Perumda Air Minum Tirta Komodo Kabupaten Manggarai dalam penyediaan air bersih kepada masyarakat. Dalam hal ini, peneliti akan menganalisis kebutuhan pelanggan terkait layanan yang diberikan oleh Perumda Air Minum Tirta Komodo Kabupaten Manggarai. Metode yang digunakan peneliti yaitu Metode Design Thinking. Peneliti menggunakan kuisioner untuk mencapai tujuan dari penelitian ini. Dan dari penelitian ini, peneliti menemukan permasalahan yaitu, masyarakat masih kesulitan dalam melakukan pembayaran secara manual, pihak PDAM sendiri juga masih sulit untuk pemantauan konsumsi, pemberitahuan dan peringatan, pelaporan masalah maupun informasi dan edukasi. Jadi, solusi dari permasalahan ini yaitu, peneliti menghasilkan sebuah rancangan desain UI/UX yang diharapkan dapat mengatasi masalah yang ada yang dihadapi oleh masyarakat maupun pihak Perumda Air Minum Tirta Komodo Kabupaten Manggarai.
Komparasi Metode Mean dan KNN Imputation dalam Mengatasi Missing Value pada Dataset Kecil Yulian Pamuji, Fandi; Ahmad Rofiqul Muslikh; Rizza Muhammad Arief; Delviana Muti
Jurnal Informatika Polinema Vol. 10 No. 2 (2024): Vol 10 No 2 (2024)
Publisher : UPT P2M State Polytechnic of Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33795/jip.v10i2.5031

Abstract

Missing value pada dataset yang kecil akan mengakibatkan berkurangnya data yang dapat digunakan untuk pembelajaran sehingga prediksi hasil klasifikasi dari data tersebut akan berkurang. Metode Imputasi sebagai solusi metode yang paling umum digunakan untuk menangani masalah dataset yang tidak lengkap. Metode Imputasi proses di mana beberapa teknik statistik digunakan untuk mengganti data yang hilang dengan nilai pengganti. Tujuan penelitian ini dengan kinerja klasifikasi yang dapat dipertahankan dengan metode imputasi missing value, karena metode ini dapat menghindari berkurangnya jumlah dataset yang digunakan dalam proses klasifikasi pada dataset dan meningkatkan kinerja klasifikasi pada dataset yang tidak ideal terutama untuk jumlah dataset yang kecil. Berdasarkan hasil eksperimen yang telah dilakukan dari penelitian ini yaitu bahwa pengujian metode imputasi Mean dan KNN Imputation dengan metode klasifikasi mampu menangani data kosong dengan jumlah missing value sedikit maupun banyak dengan menghasilkan nilai accuracy mencapai kinerja prediksi yang lebih besar dibandingkan dengan menggunakan missing value nilai 0. Kemudian untuk dataset Hepatitis nilai Accuracy tinggi menggunakan metode imputasi KNN Imputasi dengan nilai 0,79 menggunakan metode Logistic Regression dan dataset Ginjal Kronis nilai Accuracy tinggi menggunakan metode imputasi Mean dengan nilai 0,97 dengan menggunakan metode Naïve Bayes. Hal tersebut menunjukkan bahwa proses metode imputasi terhadap nilai kosong disetiap column dataset kecil pada tahap data preprocessing memberikan pengaruh terhadap nilai Accuracy metode Mean dan KNN Imputation pada metode klasifikasi.