Claim Missing Document
Check
Articles

Found 11 Documents
Search

Effect of Epoch on Accuracy using Convolutional Neural Network to Classification of fashion and furniture Muhammad Wasil; Harianto Harianto; Fathurrahman Fathurrahman
Infotek: Jurnal Informatika dan Teknologi Vol 5, No 1 (2022): Infotek : Jurnal Informatika dan Teknologi
Publisher : Fakultas Teknik Universitas Hamzanwadi

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (527.171 KB) | DOI: 10.29408/jit.v5i1.4393

Abstract

Fashion dan furniture menjadi kebutuhan untuk setiap individu. Pemilihan fashion terkadang juga bisa menjadi penilaian orang lain terhadap karakter yang dimiliki tiap individu. Begitupun pemilihan furniture juga bisa menggambarkan identitas dari tiap individu. Namun fashion dan furniture memiliki berbagai macam model, untuk itu dibutuhkan teknologi informasi yang bisa membedakan antara model a dan model b. Klasifikasi adalah salah satu model yang mengelompokkan berdasarkan kriteria yang sama. Penggunaan klasifikasi haruslah didukung dengan metode yang tepat dan penggunaan epoch agar akurasi yang dihasilkan dapat maksimal. Metode Convolutional Neural Network (CNN) adalah metode yang sangat tepat untuk klasifikasi gambar karena terdapat banyak arsitektur yang bisa digunakan.Hasil penelitian ini menunjukkan bahwa akurasi terbaik pada furniture=94.18% dengan penggunaan epoch=500, dan fashion =99.15% dengan penggunaan epoch=1500
Pelatihan penggunaan media pembelajaran interaktif Sistem Informasi Geografis mata pelajaran Pemrograman Web Aris Sudianto; Imam Fathurrahman; Hamzan Ahmadi; Mahpuz Mahpuz; Muhamad Sadali; Indra Gunawan; Baiq Andriska Candra Permana; Muhammad Wasil; Lalu Kerta Wijaya; Suhartini Suhartini; Harianto Harianto
ABSYARA: Jurnal Pengabdian Pada Masayarakat Vol 2 No 2 (2021): ABSYARA: Jurnal Pengabdian Pada Masyarakat
Publisher : Universitas Hamzanwadi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29408/ab.v2i2.4029

Abstract

Interactive learning media is one of the tools in the learning process. With interactive learning media, it will help students understand the learning material better, especially subjects that require practice to better understand the theory being taught. Web programming subjects in vocational schools are one of the subjects that have a lot of practicums. Therefore, to support the delivery of the subject matter, good interactive learning media are needed and are following the needs of students. This PKM aims to provide training on the use of web-based interactive learning media for Geographic Information Systems (GIS) that have been developed so that students understand more about designing web-based applications. This activity was carried out at SMKN 1 Selong, with 25 participants from the Software Engineering department. The activity lasted for 4 months. The method used is lectures and direct practice on WEB-based software engineering with lecturers from the Informatics Engineering study program, Hamzanwadi University. The material presented is in the form of steps to make simple software by utilizing existing technology and seeing some examples that have been prepared previously by the resource person to be used by students. For this method use a computer with a local network. The results of the activity show that students can master basic techniques for WEB-based software and students are also able to make simple WEB-based applications by applying the concept of good system analysis
Sosialisasi dan pelatihan aplikasi Sistem Informasi Data dan Pembayaran Iuran Bulanan warga Indra Gunawan; Muhammad Sadali; Baiq Andriska Candra Permana; Hamzan Ahmadi; Imam Fathurrahman; Aris Sudianto; Suhartini Suhartini; Lalu Kertawijaya; Mahpuz Mahpuz; Muhammad Wasil; Harianto Harianto
ABSYARA: Jurnal Pengabdian Pada Masayarakat Vol 3 No 2 (2022): ABSYARA: Jurnal Pengabdian Pada Masyarakat
Publisher : Universitas Hamzanwadi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29408/ab.v3i2.5754

Abstract

Apart from being in the general community group, residents are also in a complex residential environment. There are housing complexes for the community in subsidized and commercial housing. The large number of citizen data in one housing complex raises many problems, both harmony problems, and administrative problems. The most fundamental problem is how the system records valid citizens and whether the contribution payment system is accountable, valid, and transparent. The team of lecturers from Hamzanwadi University's Informatics Engineering Study Program is doing this service to help the management of RT 005 Lingkar Pratama build a free application system and collect data from citizens. So, it can help RT administrators record and manage complex residential residents' contributions. The method in this service is carried out in stages, starting with problem data analysis, socialization, and training. The results of this service are in the form of implementing applications that can already be used and assist RT admin officers in managing financial reports and information management of citizen data. Of the fourteen administrators who attended the training, on average, they had mastered the application
Analisa Data Transaksi Penjualan Barang Menggunakan Algoritma Apriori Dan FP-Growth hariantao harianto; Aris Sudianto; Hariman Bahtiar
Jurnal SISKOM-KB (Sistem Komputer dan Kecerdasan Buatan) Vol. 6 No. 2 (2023): Volume VI - Nomor 2 - Maret 2023
Publisher : Teknik Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47970/siskom-kb.v6i2.371

Abstract

Abstract—Transaksi penjualan barang pada sebuah perusahaan terjadi setiap hari mengakibatkan semakin bertambah banyaknya catatan transaksi penjualan. Tidak banyak dari perusahaan menjadikan transaksi penjualan itu hanya sebagai arsip belaka, akibatnya perusahaan mengalami kekurangan stok barang. Tentunya hal demikian terjadi karena transaksi penjualan barang tidak dianalisa dan dipelajari polanya. Pada penelitian ini, bertujuan untuk menemukan pola pembelian barang secara bersamaan berdasarkan bulan selama satu tahun. Ada banyak metode data mining yang digunakan untuk menganalisa pola pembelian barang secara bersamaan oleh pembeli. Diantara metode yang sering sekali digunakan adalah Apriori dan FP-Growth. Untuk menemukan pola pembelian tersebut digunakan algoritma Apriori dan FP-Growth kemudian membandingkan hasil dalam menemukan pola kombinasi yang dihasilkan. Algoritma mana yang lebih banyak menghasilkan pola dengan waktu yang sedikt. Analisis prilaku pelanggan untuk transaksi pembelian selama satu tahun,Algoritma FP-Growth lebih banyak menampilkan pola yang dihasilkan dibandingkan dengan algoritma Apriori baik pada Rules Support >=0.5 paling banyak Apriori menghasilkan 5 Rules dan FP-Growth 338 Rules sedangkan pada Rules Lift Apriori 14 Rules 0.0051 detik dan FP-Growth 137 Rules 0.0068 detik.
Rancang Bangun Sistem Informasi Penjualan Baju Thriff Dalam Meningkatkan Mutu Palayanan dan Jumlah Transaksi Hamzan Ahmadi; Lalu Kerta Wijaya; Harianto Harianto
Infotek: Jurnal Informatika dan Teknologi Vol. 6 No. 2 (2023): Infotek : Jurnal Informatika dan Teknologi
Publisher : Fakultas Teknik Universitas Hamzanwadi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29408/jit.v6i2.19032

Abstract

The development of information technology is growing very rapidly, so it has a very important role in various fields, one of which is in the business field, there are still many companies or businessmen who need information systems to support all activities ranging from marketing, data and information management. Queen thrift is a shop engaged in the fashion or clothing business located in Masbagek, Masbagek sub-district, East Lombok. So far, for promotional or marketing media carried out by Queen Thrift shop owners, namely using social media. With this, new innovations are urgently needed, and convenience in the promotion process, as well as online services in the form of information systems. so that these products can be seen by consumers quickly without having to come to the store.  With this, it is necessary to update the old system to the new system, namely by creating an online sales information system. With the hope to facilitate monitoring, storage, calculations and reports. In order to be able to provide the right information needed by customers and the store itself.
Peningkatan kompetensi siswa SMK melalui pelatihan desain grafis dan animasi Mahpuz Mahpuz; Muhammad Wasil; Aris Sudianto; Muhamad Sadali; Baiq Andriska Candra Permana; Hamzan Ahmadi; Suhartini Suhartini; Indra Gunawan; Imam Fathurrahman; Lalu Kerta Wijaya; Harianto Harianto; Moh. Farid Wajdi
ABSYARA: Jurnal Pengabdian Pada Masayarakat Vol 4 No 1 (2023): ABSYARA: Jurnal Pengabdian Pada Masyarakat
Publisher : Universitas Hamzanwadi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29408/ab.v4i1.18793

Abstract

Multimedia is a crucial field of study in the present era, as all professional domains require its application to aid individuals in effectively completing their tasks. However, the Multimedia field is contributing significantly to unemployment rates today. This issue partly arises from the fact that graduates in Multimedia lack the required proficiency, skills, and knowledge sought by various companies and institutions. SMK NW Kembang Kerang is a private vocational school located in East Lombok, which offers a multimedia program attracting a substantial number of students each year. Despite graduating students in this field annually, many face the challenge of inadequate competencies upon completion of their education. The lack of practical exposure during their school years hinders the alumni's ability to compete in the job market. Although numerous photo and video editing services are available in the Kembang Kerang region, it is observed that few SMK graduates are employed in this area. The school's teachers and principal comprehend this issue, attributing it to the limited opportunities for practical training experienced by the students. Consequently, to address this concern, the author conducted a competence training activity for students at SMK NW Kembang Kerang, with a specific focus on multimedia and graphic design. The objective of this training program is to enhance the students' multimedia and graphic design skills, empowering them with competent capabilities that will prove beneficial both for their personal growth and the broader community. Through this initiative, it is anticipated that upon completing their vocational education, students will possess the necessary competencies to thrive in the professional realm and contribute positively to society at large.
Pendampingan LMS Berbasis Outcome-Based Education dan Conditional Access pada Dosen PGSD Universitas Hamzanwadi Hirmayanti; Harianto; Zaenul Amri
Jurnal Teknologi Informasi untuk Masyarakat Vol. 4 No. 1 (2026): Jurnal Teknologi Informasi untuk Masyarakat (Teknokrat)
Publisher : Universitas Hamzanwadi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29408/jt.v4i1.35087

Abstract

The advancement of digital technology in higher education has encouraged the utilization of Learning Management Systems (LMS) not only as platforms for delivering learning materials but also as tools for supporting competency-based and adaptive learning. However, LMS implementation in the Elementary School Teacher Education Program at Hamzanwadi University has primarily focused on basic learning features and has not fully utilized adaptive learning functionalities such as conditional access. This community service program aimed to enhance lecturers’ competencies in developing and managing an Outcome-Based Education LMS integrated with conditional access features to support adaptive learning. The program was conducted through several stages, including needs assessment, training material development, workshops, digital course design practices, LMS implementation mentoring, and activity evaluation. The results indicated that all participants successfully developed Outcome-Based Education courses within the LMS, while 15 lecturers successfully implemented the conditional access feature in their courses. In addition, 85% of participants reported that the mentoring activities improved their ability to develop digital assessments, design adaptive learning activities, and utilize LMS features more effectively. The implementation of the Outcome-Based Education LMS also facilitated more systematic and measurable monitoring of student learning outcomes. Therefore, the mentoring program contributed positively to strengthening lecturers’ digital competencies and supporting the development of adaptive learning environments oriented toward student learning outcomes
Pengembangan Aplikasi Web Pembelajaran Matematika Terintegrasi Fitur Evaluasi Otomatis Zaenul Amri; Harianto; Handayani; M. Nurul Wathani
Infotek: Jurnal Informatika dan Teknologi Vol. 9 No. 2 (2026): Infotek : Jurnal Informatika dan Teknologi
Publisher : Fakultas Teknik Universitas Hamzanwadi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29408/jit.v9i2.35281

Abstract

The current development of information technology provides a significant opportunity for digital transformation in the education sector, particularly to address difficulties in understanding concepts in Mathematics at the elementary school level. Based on observations at SDN Loang Tuna, the material delivery process is still dominated by conventional teaching methods utilizing textbooks and whiteboards. The limitations of these teaching aids result in low levels of interactivity and independent learning interest among students. The purpose of this study is to design and develop an information system in the form of a web-based Mathematics e-learning application that comprehensively integrates interactive material modules with an automatic evaluation feature. The software development methodology used in this study adopts the ADDIE (Analysis, Design, Development, Implementation, and Evaluation) model. The stages of this methodology include the identification of system requirements, the design of interface and database architectures, programming with multi-user access rights management, and software functionality testing using the Black-Box Testing method. The results of the study indicate that the application was successfully built according to the specifications. Based on the Black-Box Testing, the system demonstrates a functionality success rate of 88%, which is categorized as highly feasible. The automatic evaluation feature is proven to have high accuracy in processing real-time grade calculations, which significantly reduces the administrative workload of teachers and provides instant feedback for students. Therefore, the interactive interface of this application is effective in increasing user engagement, making it an innovative and measurable technological solution to advance the quality of Mathematics learning.
Prediksi Kegagalan Build Real-Time Pada Pipeline CI/CD Menggunakan Pendekatan Machine Learning Berbasis Data Streaming Hirmayanti Hirmayanti; Harianto Harianto; Rooy Marthen Thaniket
Jurnal Sistem Informasi dan Sistem Komputer Vol 11 No 2 (2026): Vol 11 No 2 - 2026
Publisher : STIMIK Bina Bangsa Kendari

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51717/simkom.v11i2.1414

Abstract

Kegagalan proses build pada lingkungan Continuous Integration/Continuous Deployment (CI/CD) dapat menghambat rilis perangkat lunak, meningkatkan biaya perbaikan, dan menurunkan efisiensi pengembangan. Hal ini menunjukkan perlunya sistem prediksi yang cepat, adaptif, serta mampu menangani data yang terus mengalir secara real-time. Penelitian ini bertujuan untuk menganalisis dan membandingkan kinerja beberapa algoritma online machine learning dalam memprediksi kegagalan build pada pipeline CI/CD. Dataset yang digunakan berasal dari TravisTorrent yang mencakup aktivitas repositori, perubahan kode, metrik pengujian, serta riwayat build. Tahapan penelitian meliputi preprocessing data, pembentukan skema data streaming, penerapan model Hoeffding Tree, Adaptive Random Forest (ARF), dan Online Logistic Regression, serta evaluasi menggunakan metrik accuracy. Hasil eksperimen menunjukkan model terbaik mencapai accuracy 97,35%, lebih tinggi dibandingkan penelitian sebelumnya sebesar 95,9%. Peningkatan absolut sebesar 1,45 poin persentase atau sekitar 1,51% ini membuktikan bahwa pendekatan yang digunakan lebih efektif dalam mengenali pola kegagalan build pada lingkungan CI/CD berbasis streaming data.
Improving Imbalanced Polycystic Ovary Syndrome Classification Using a Leakage-Free Machine Learning Pipeline Baiq Andriska Candra Permana; Zulkipli; Muhammad Wasil; Harianto
JOURNAL OF INFORMATICS AND TELECOMMUNICATION ENGINEERING Vol. 9 No. 2 (2026): Issues January 2026
Publisher : Universitas Medan Area

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31289/jite.v9i2.16752

Abstract

Polycystic Ovarian Syndrome (PCOS) is a complex endocrine disorder affecting women of reproductive age and poses challenges for early diagnosis due to heterogeneous clinical presentations and imbalanced clinical datasets. This study aims to develop a data leakage–free machine learning pipeline to enhance the accuracy and reliability of PCOS classification using clinical data. The dataset underwent preprocessing and normalization, followed by stratified data splitting with an 80:20 ratio to maintain class proportions. The proposed pipeline was implemented within a unified computational framework integrating feature selection based on the ANOVA F-test, class imbalance handling using the Synthetic Minority Over-sampling Technique (SMOTE), and classification using a Support Vector Machine (SVM) with a Radial Basis Function (RBF) kernel. Hyperparameter tuning was performed using GridSearchCV combined with K-Fold Cross-Validation to ensure model robustness and consistency. The experimental results indicate that the proposed model achieved an accuracy of 0.9074, with precision, recall, and F1-score values of 0.8378, 0.8857, and 0.8611, respectively. Furthermore, ten dominant clinical features were identified, primarily related to hormonal profiles and ovarian morphology. These results demonstrate that the data leakage–free pipeline improves the validity and stability of PCOS prediction. The findings suggest that this approach may serve as a supportive tool for clinical decision-making, particularly in facilitating early and objective identification of PCOS.