Claim Missing Document
Check
Articles

Found 16 Documents
Search

Sistem Penunjang Keptusan Pemilihan Internet Service Provider Di Salatiga Dengan Menggunakan Metode Fuzzy MADM Dwi Agus Diartono; Teguh Khristianto; THD. Wismarini; Hari Murti; R. Soelistijadi
Kesatria : Jurnal Penerapan Sistem Informasi (Komputer dan Manajemen) Vol 4, No 3 (2023): Edisi Juli
Publisher : LPPM STIKOM Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/kesatria.v4i3.207

Abstract

The Fuzzy MADM method is used to deal with uncertainty and ambiguity in decision-making. This method considers several relevant attributes in the selection of an Internet Service Provider (ISP), such as internet speed, package price, service availability, and network reliability. Each attribute is assigned a weight based on its level of importance determined by the user. In this study, data on the performance of different ISPs were collected and analyzed. Fuzzy MADM was used to process the data and provide recommendations for selecting the most suitable ISP according to user preferences. The developed decision support system allows users to adjust attribute weights according to their needs and preferences. The decision support system for selecting an Internet Service Provider using the Fuzzy MADM method identifies three alternatives and four evaluation criteria: price, security, satisfaction, and credibility. This system can be used to recommend an Internet Service Provider in Salatiga based on the needs and desires of the users, employing the Fuzzy MADM method to find the appropriate ISP
Rancang Bangun Sistem Informasi Event Pariwisata Kota Semarang Menggunakan Metode UML Muhammad Alif Samudera; Edy Supriyanto; Hari Murti; Rara Sri Artati Redjeki; Handoko Handoko
INTECOMS: Journal of Information Technology and Computer Science Vol 6 No 2 (2023): INTECOMS: Journal of Information Technology and Computer Science
Publisher : Institut Penelitian Matematika, Komputer, Keperawatan, Pendidikan dan Ekonomi (IPM2KPE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31539/intecoms.v6i2.7009

Abstract

Tujuan dari penelitian ini adalah untuk menggunakan metode Unified Modeling Language (UML) untuk merancang dan membangun sebuah sistem informasi event pariwisata di Kota Semarang. Dengan Semarang sebagai ibu kota Provinsi Jawa Tengah, sektor pariwisata Indonesia berkembang pesat. Namun, kendala penyelenggaraan acara pariwisata masih ada, seperti kurangnya informasi yang tersedia secara terpusat dan sulit bagi pengguna untuk mendapatkan informasi tersebut.Dalam penelitian ini, sistem informasi yang efisien dan efektif dirancang untuk membantu pengguna mendapatkan informasi tentang peristiwa pariwisata Kota Semarang. Metode UML adalah pendekatan utama untuk mendesain sistem ini karena merupakan metode yang sistematis dan terstruktur untuk menunjukkan, merancang, dan mencatat sistem berbasis objek.Sistem informasi akan dirancang dengan fokus pada pemodelan konsep awal hingga perincian detail tentang lokasi acara, tema event, agenda kegiatan, logistik yang diperlukan, serta tim pelaksana. Penelitian ini diharapkan dapat membantu pertumbuhan sektor pariwisata Kota Semarang dengan menyediakan sebuah platform yang berguna untuk memberikan informasi tentang acara pariwisata.Diharapkan bahwa sistem ini akan membantu masyarakat umum dan pihak-pihak terkait seperti wisatawan lokal dan internasional, penyelenggara acara, dan pemerintah daerah dalam memperoleh informasi yang lengkap dan akurat tentang acara pariwisata di Kota Semarang. Sistem ini juga akan membantu mengoptimalkan upaya pemasaran destinasi wisata Semarang. Kata kunci : Sistem Informasi ,Event Pariwisata , Kota Semarang
Digitalisasi Pembukuan Kas Berbasis Aplikasi Mobile Menggunakan Pendekatan Desain Thinking Redjeki, Rara Sriartati; Murti, Hari; Supriyanto, Edy; Ardhianto, Eka; Wahyudi, Eko Nur
STRING (Satuan Tulisan Riset dan Inovasi Teknologi) Vol 9, No 3 (2025)
Publisher : Universitas Indraprasta PGRI Jakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30998/string.v9i3.26024

Abstract

Cash recording plays an important role in the sustainability of MSME businesses. The problems faced by MSMEs are the lack of good cash recording and the lack of ability to learn difficult accounting science. This study provides a solution in the form of creating a mobile application-based cash recording. The method used is the design thinking approach. The form of evaluation used is using the Technology Acceptance Model technique. The results obtained are that the design thinking approach is able to solve MSME problems in recording cash from the user's side, and the results of the application usage survey state that the acceptance of the implemented technology shows a good value with an average of 9.4 agreeing that the application is acceptable
Pemodelan Sentimen Komentar YouTube Berbasis Naive Bayes Hari Murti; Rara Sriartati Redjeki; Novita Mariana; Agus Prasetyo Utomo; Widiyanto Tri Handoko
Jurnal Informatika Dan Tekonologi Komputer (JITEK) Vol. 6 No. 1 (2026): Maret : Jurnal Informatika dan Tekonologi Komputer
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/jitek.v6i1.8767

Abstract

Social Network Analysis (SNA) is a crucial quantitative methodology for mapping relationships and identifying connectivity structures within a group. This research specifically explores the use of the NetworkX library in Python as an effective tool for analyzing social networks. The primary objective of this study is to apply the Degree Centrality method to measure the level of connectivity and identify the most popular actors in a social network. The methodology employed is the quantitative analysis of an undirected graph modeled from the us_edgelist.csv dataset, which contains a list of relationships among political figures in an edge list format. Data processing utilized pandas, and the graph object was constructed using NetworkX. Degree Centrality was calculated for each node, with the results being normalized to provide a relative value. This normalization allows for a direct comparison of how active each actor is within the network. The centrality results were then visualized, with node sizes adjusted based on their Degree Centrality score. The results of the analysis indicate that figures like Bush and Obama possess the highest Degree Centrality score, 0.25, suggesting they have the greatest number of direct connections in this network. This high value confirms their role as the most active or central actors in the exchange and interaction within the political network studied. This finding validates the effectiveness of Degree Centrality as an indicator of high involvement. The study concludes that the implementation of Social Network Analysis using NetworkX provides a robust framework for understanding political relationship structures. Therefore, Degree Centrality is a reliable metric for quantifying actor activity and accurately identifying individuals who form the center of connections within the network.
Penerapan Teknologi Produksi dan Pemasaran Digital pada Home Industri Kerupuk Gendar Next GEN-DAR di Magetan Hari Murti; Herny Februariyanti; Imam Husni Al Amin
Abdimas Galuh Vol 8, No 2 (2026): September 2026
Publisher : Universitas Galuh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25157/ag.v8i2.25990

Abstract

Home industri kerupuk gendar Next GEN-DAR di Desa Sukowinangun, Kabupaten Magetan, menghadapi kendala berupa pengadukan dan pemotongan adonan secara manual, kemasan yang belum memiliki identitas kuat, serta pemasaran yang masih berorientasi lokal. Kegiatan pengabdian ini bertujuan meningkatkan kesiapan produksi dan daya saing mitra melalui penerapan teknologi tepat guna, inovasi kemasan, dan pemasaran digital. Program dilaksanakan pada 12-14 Juni 2026 menggunakan pendekatan partisipatif melalui FGD dan sosialisasi, pelatihan, penerapan teknologi, evaluasi praktik, dan rencana keberlanjutan. Teknologi yang diterapkan meliputi mesin pengaduk adonan gendar, mesin pemotong gendar, dan alat press kemasan. Intervensi nonfisik mencakup penyusunan logo dan label Next GEN-DAR, pembuatan akun Instagram dan TikTok, serta pelatihan pembuatan konten. Data diperoleh melalui observasi proses, FGD, praktik langsung, wawancara, dan dokumentasi, kemudian data dianalisis secara deskriptif untuk memetakan kondisi awal, output kegiatan, perubahan kemampuan dasar, dan kesiapan adopsi teknologi oleh mitra. Hasil menunjukkan bahwa mitra telah memperoleh akses terhadap tiga perangkat produksi dan pengemasan, mampu melakukan pengoperasian dasar dengan pendampingan, memahami fungsi kemasan sebagai pelindung dan media komunikasi, serta memiliki kanal pemasaran digital yang aktif. Program juga menghasilkan video impact dan publikasi media massa. Dampak kuantitatif terhadap kapasitas, waktu proses, dan penjualan masih memerlukan monitoring beberapa siklus produksi.
Comparative Evaluation of TensorFlow Lite Quantization Variants for MobileNetV2-Based Batik Motif Classification: Accuracy, Model Size, and Inference Latency Dewi Handayani Untari Ningsih; Eri Zuliarso; Jati Sasongko Wibowo; Dwi Budi Santoso; Hari Murti
JURIKOM (Jurnal Riset Komputer) Vol. 13 No. 5 (2026): Oktober 2026
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/jurikom.v15i5.10047

Abstract

Convolutional Neural Network (CNN) models achieve high accuracy in visual recognition, but their size and computational cost limit deployment on mobile devices, so batik motif recognition remains difficult to bring to artisans and small creative enterprises. This study evaluates how post-training quantization with TensorFlow Lite affects the classification accuracy, model size, and inference latency of a MobileNetV2 transfer-learning model for batik motif recognition, in order to identify the deployment configuration that offers the best balance among the three. The experimental workflow adapted a pre-trained MobileNetV2 network to the Batik Wastra Nusantara dataset, which covers batik designs originating from different parts of Indonesia with substantial variation in color, ornamentation, and pattern complexity, converted the trained model into Dynamic Range, Float16, and Int8 TensorFlow Lite variants, and compared them under identical conditions. Evaluation on 644 valid images from 14 motif classes produced a test accuracy of 43.08%, corresponding to 28 of the 65 test images, a macro F1-score of 41.65%, and a weighted F1-score of 40.39%. Across the four model formats the accuracy spans only three test images, from 41.54% to 46.15%, a range that lies well inside the confidence interval implied by a 65-image test subset, so the variants cannot be separated on accuracy at this sample size. The deployment metrics differ substantially: relative to the unquantized reference, the Float16 variant reduced model size from 19.04 MB to 4.29 MB (77.47%) and inference latency from 205.52 ms to 28.60 ms (86.08%), while the Int8 variant was the fastest at 14.87 ms and the Dynamic Range variant the smallest at 2.41 MB. These findings indicate that the benefit of TensorFlow Lite optimization lies in storage and latency rather than in accuracy, and that the accuracy attainable on this dataset is constrained by its limited size and the visual similarity among motifs. The study contributes the deployment measurements, namely model size and inference latency for each quantization variant, that comparable batik classification studies do not report, and identifies dataset expansion as the prerequisite for reaching production-level accuracy in AI-based digital innovation for Indonesia’s creative industries.