Article Per Year (5 Year)
p-Index From 2021 - 2026
4.671
P-Index
This Author published in this journals
All Journal Jurnas Nasional Teknologi dan Sistem Informasi JOURNAL OF APPLIED INFORMATICS AND COMPUTING Jurnal Telematika JIEMS (Journal of Industrial Engineering and Management Systems) Indonesian Journal of Applied Informatics JOISIE (Journal Of Information Systems And Informatics Engineering) Jurnal Tekno Kompak Zonasi: Jurnal Sistem Informasi JATI (Jurnal Mahasiswa Teknik Informatika) INFORMASI (Jurnal Informatika dan Sistem Informasi) Journal of Business and Audit Information System (JBASE) OISAA Journal of Indonesia Emas Jurnal Pengabdian dan Kewirausahaan Computer Science (CO-SCIENCE) JURNAL ILMIAH GLOBAL EDUCATION Jurnal Minfo Polgan (JMP) Jurnal Sistem Informasi Triguna Dharma (JURSI TGD) Journal of Information Technology Jurnal Teknoinfo
Bhustomy Hakim
Universitas Bunda Mulia
Agriculture, Biological Sciences & Forestry Arts Humanities Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Environmental Science Health Professions Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Library & Information Science Mathematics Mechanical Engineering Public Health Social Sciences Other

Published : 31 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 31 Documents
Search

 1   2   3   4 
Klasifikasi Terawasi Anomali Suara Kipas Industri Menggunakan Jaringan Saraf Tiruan dan Fitur Akustik Rekayasa Thenata, Angelina Pramana; ., Ranny; Hakim, Bhustomy; Kaunang, Fergie Joanda
Jurnal Telematika Vol. 20 No. 1 (2025)
Publisher : Yayasan Petra Harapan Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61769/telematika.v20i1.772

Abstract

Penelitian ini menggunakan pendekatan supervised learning berbasis jaringan saraf untuk deteksi anomali pada sistem kipas industry. Dengan subset data FAN dari MIMII (malfunctioning industrial machine investigation and inspection) dataset dengan 530 rekaman berlabel (383 normal dan 147 abnormal), penelitian ini mengekstraksi fitur akustik yang meliputi mel-frequency cepstral coefficients (MFCC), spectral descriptor (centroid, roll off), serta temporal measures (zero-crossing rate, autocorrelation). Uji statistik univariat menunjukkan sejumlah koefisien MFCC dan fitur domain waktu berbeda signifikan antar kelas (p < 0,05). Model jaringan saraf feed-forward dengan dua lapisan tersembunyi berukuran 64 unit (aktivasi ReLU) dan regularisasi dropout dilatih menggunakan stratified cross validation dengan 5-fold sehingga menghasilkan nilai F1 rata-rata sebesar 89,9%. Penggunaan beberapa nilai ambang (τ ∈ {0,3–0,7}) menegaskan kekokohan model yang terlihat pada hasil data uji dengan nilai ambang terpilih adalah τ = 0,5 yang mencapai precision sebesar 100%, recall = 93,10%, F1 = 96,43%, dan akurasi = 98,11% (hasil identik diperoleh pada τ = 0,6–0,7; sementara τ = 0,3 memberikan recall lebih tinggi). Model juga menghasilkan nilai AUC-ROC sebesar 0,9978 yang mendekati ideal dan menunjukkan daya diskriminasi lintas-ambang yang sangat baik. Temuan ini memperlihatkan bahwa penggabungan fitur akustik yang dapat diinterpretasikan dengan pengklasifikasi saraf yang ringkas memungkinkan deteksi anomali non-invasif yang akurat untuk penerapan Industri 4.0 dengan kebutuhan perangkat keras minimal.
Sistem Pendukung Keputusan dengan Algoritma Branch&Bound dan Naive Approach pada Beberapa Pemesanan Makanan Online Hakim, Bhustomy; Fendyanto, Fendyanto
Jurnal Nasional Teknologi dan Sistem Informasi Vol 8 No 2 (2022): Agustus 2022
Publisher : Departemen Sistem Informasi, Fakultas Teknologi Informasi, Universitas Andalas

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25077/TEKNOSI.v8i2.2022.44-51

Abstract

Dengan berkembangnya teknologi saat ini, cara manusia menjalani hidupnya juga mengalami pergeseran seperti dalam memenuhi kebutuhannya untuk makan. Pemesanan makanan online menjadi suatu aktivitas yang menjamur. Gofood dan Grabfood merupakan salah satu platform terbesar yang mendominasi pasar pemesanan online di Indonesia. Mereka mendapatkan kurang lebih 160 miliar rupiah dengan 3 juta order-an perbulan untuk hanya melayani pesanan makanan online saja. Namun dalam menangani pemesanan tersebut, mereka masih menggunakan system one-o-one dimana driver hanya melakukan pemesanan dan pengantara ekslusif ke satu pelanggan. Dengan waktu tunggu yang cukup panjang yaitu 30-60 menit, hal ini dirasa tidak efektif dari sisi kinerja. Oleh karena itu, multiple pesanan diajukkan di penelitian ini. Traveling Salesman Problem (TSP) digunakan untuk menggambarkan permasalahan multiple pesanan untuk menentukan rute terbaik yang memiliki nilai keefektifan terbaik. Dalam penelitian ini, dua algoritma untuk memecahkan masalah TSP telah dibandingkan satu sama lain. Dua algoritma tersebut yaitu Brand Bound Strategy dan Naïve Approach. Jalur rute yang memiliki titik awal dan akhir yang sama dan memiliki berat minimal. Berat dari masing-masing rute akan didapatkan dari kriteria; jarak, tingkat kesibukkan, dan prioritas, lalu didapatkan berat ideal dengan menggunakan Simple Additive Weighting (SAW). Kriteria evaluasi dalam laporan ini adalah jalur/rute terbaik, kompleksitas waktu dan biaya masing-masing algoritma. Dan ada empat kondisi yang berbeda dalam ukuran yang telah digunakan sebagai masalah untuk evaluasi dua algoritma dalam penelitian ini. Dari penelitian ini, ditemukan hasil bahwa algoritma Branch and Bound menunjukan performa lebih efisien daripada Naive Aproach dimana hanya membutuhkan kurang dari satu detik untuk menemukan rute jalan terbaik dengan bobot tertinggi sebagai bahan pengambilan keputusan dengan biaya algoritma O(n3).
Sentiment Analysis of Indonesian Citizen Tweets Using Support Vector Machine on the Rebranding of Twitter to X Hakim, Bhustomy; Kinasih, Putri Rindu
Jurnal Tekno Kompak Vol 18, No 2 (2024): AGUSTUS
Publisher : Universitas Teknokrat Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33365/jtk.v18i2.4293

Abstract

How other people see the world and assess it affects their opinions, their understanding of it, and the choices they make. As a result, when we need to make a choice, we frequently ask for other people's opinions. Sentiment analysis, also known as opinion mining, is a cost-effective way for businesses and individuals to gather information about public sentiment. In this research, the writers aimed to study Indonesian netizen’s sentiment towards the rebranding of Twitter to X. Obviously, it is impossible to ignore the name and logo changes. The blue and white bird logo on Twitter has become a symbol of the network's culture and lexicon for over ten years. The verb "tweet" has evolved to refer to a post. With 14.75 million Twitter users, which ranks Indonesia sixth in the world, the writer is intrigued to study more about how Indonesian citizens see the rebranding issue. The data scrapping which collects the tweets about Twitter rebranding into X is collected from July 23rd, 2023, when the rebranding news appeared, and July 31st, 2023, which focuses on the day of rebranding that occurred. And, for the feature extraction, we will be using the TD-IDF method and Support Vector Machine using Gaussian Radial Basis Function Kernel as the model. Afterward, in the evaluation phase, we are using Confusion Matrix to find accuracy, f1-score. Lastly, the sentiment will also be analyzed by using rebranding theory. The result of this research shows that the Indonesian netizens' neutral sentiments. This result is also strengthened by the word cloud results which mostly show general words such as rebranding, twitter, https, jadi, yang, and X.
Analisis Pengaruh E-Sport Tourism pada Pokemon Go Terhadap Peningkatan Wisatawan di Kabupaten Tangerang Sarudin, Rendy; Hakim, Bhustomy
Jurnal Ilmiah Global Education Vol. 5 No. 1 (2024): JURNAL ILMIAH GLOBAL EDUCATION, Volume 5 Nomor 1, Maret 2024
Publisher : LPPM Institut Pendidikan Nusantara Global

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55681/jige.v5i1.2242

Abstract

This research aims to determine the influence of the E-Sport Tourism game Pokemon Go on Interest in Visiting Tangerang Regency through the Tangerang Serpong Raider Community. The results of this research show that: (1) if E-sports tourism in Pokemon Go is equal to zero (0), then the increase in tourists in Tangerang Regency will be 7,178 as evidenced by the constant value obtained which is 7,178. (2) E-sports Tourism in Pokemon Go positively influences increasing tourists in Tangerang Regency as evidenced by the regression coefficient value of 0.600. (3) E-sports Tourism in Pokemon Go influences the number of tourists by 60.0% while the remaining 40.0% is influenced by other variables as evidenced by the R square result which is 0.600.
Perancangan Sistem Manajemen Dropship Berbasis Web untuk PT Xarana Djaya Motor Theresia Gabriella; Bhustomy Hakim
J-INTECH ( Journal of Information and Technology) Vol 13 No 02 (2025): 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.v13i02.2146

Abstract

Indonesia’s online retail is expanding alongside the national digital economy: 56.1% of global internet users shop on weekends, with Indonesia ranking ninth at 59.3%. The digital economy is projected to reach IDR 5,800 trillion by 2030 (USD 360 billion), and in 2023 Indonesia accounted for 40% of ASEAN’s e-commerce market. In this context, PT Xarana Djaya Motor, a multi-brand motorcycle spare-parts distributor, runs a dropshipping model with multiple online sellers. Yet orders and shipment confirmations are still coordinated via chat and reentered manually, causing duplicate entries, processing delays, and limited real-time stock visibility. This study designs and implements a web-based Dropship Management Application that centralizes catalog, order, shipment, and return workflows. Analysis uses UML/ERD; implementation employs Laravel (PHP) and MySQL. Alpha/black-box testing validates key rules (one shipment per order) with multiple items and partial returns at the order-item level. Results indicate reduced manual handling, improved data accuracy, and clearer status visibility as supported by centralized workflows and functional (black-box) acceptance tests. The work contributes a reusable reference architecture for SMEs, with future extensions to marketplace API integration, automated label generation, analytics dashboards, and mobile access.
OPTIMISING BEAUTY BRAND COMMUNITY MANAGEMENT THROUGH A LARAVEL-BASED WEB SYSTEM Hanna Mariana Angelika; Bhustomy Hakim
Jurnal Teknoinfo Vol. 19 No. 2 (2025): July 2025 Period
Publisher : Universitas Teknokrat Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33365/teknoinfo.v19i2.481

Abstract

Globalisation has accelerated advancements in technology, communication, and information systems, intensifying competition across industries. In response, companies are adopting marketing communication strategies to build stronger relationships with consumers. One such strategy involves establishing brand communities, particularly within the beauty industry. In Indonesia, several beauty brands have established brand communities to enhance customer interaction and strengthen brand loyalty. One such brand, referred to here as DRS, specifically targets individuals aged 17 to 30. These communities typically offer initiatives such as point rewards, educational webinars, interactive challenges, product sampling, and early access to new products. However, DRS continues to manage its community manually through messaging platforms and basic data records. This manual approach results in several operational inefficiencies, including disorganised communication, data entry errors, and delays in programme validation, all of which undermine administrative performance and reduce overall member satisfaction and engagement. To address these issues, this study proposes a web-based brand community management system with two main components. The first is a management interface used by administrators and superadministrators. The second is a user platform accessed by account users and members. Key features include programme management, discussion forums, point redemption, leaderboards, and reporting functionalities. The system also incorporates principles from learning management systems to support continuous interaction, progress tracking, and sustained member engagement. It is developed using the Waterfall model of the software development life cycle, which supports structured planning and documentation. Laravel is selected as the development framework because of its efficiency, scalability, and model-view-controller architecture. The system is tested using the Black Box Testing method, and the results show that all functionalities operate according to the defined specifications. This system is expected to improve operational efficiency, enhance member experience and engagement, strengthen brand loyalty, enhance brand awareness and brand image, and support sustainable growth for beauty brands in Indonesia, particularly for brand DRS.
PERANCANGAN HUMAN RESOURCE INFORMATION SYSTEM BERBASIS WEB PADA CV. CIPTA SARANA MAKMUR Abednego Marcello; Bhustomy Hakim
Jurnal Teknoinfo Vol. 19 No. 2 (2025): July 2025 Period
Publisher : Universitas Teknokrat Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

The process of collecting and managing human resource data—such as attendance records, employee information, job assignments, and payroll—at CV. Cipta Sarana Makmur is currently carried out manually. This manual approach has resulted in several significant operational issues, including a high risk of data damage or loss, administrative delays, and increased workloads due to the lack of an integrated system. Furthermore, the conventional method often leads to data duplication and input errors, which negatively affect the accuracy of information, time efficiency, and the reliability of managerial decision-making. To address the identified issues, this study focuses on designing and developing a web-based Human Resource Information System (HRIS) capable of automating and integrating all human resource data management processes in an efficient and effective manner. The system development process adopts the Software Development Life Cycle (SDLC) methodology using the Waterfall model, which consists of five key phases: requirements analysis, system design, implementation, testing, and maintenance. Each phase is carried out in a structured and sequential manner to ensure the accuracy and completeness of the system being developed. Laravel was selected as the development framework due to its modular structure based on the Model-View-Controller (MVC) architecture, comprehensive documentation, and flexibility that supports efficient programming and long-term system scalability. The results demonstrate that the developed HRIS successfully meets the company’s operational needs by centralising and integrating various human resource functions. The system enables digital and structured processes for attendance tracking, employee data management, job assignment handling, and payroll processing. Its implementation significantly reduces data processing errors, avoids information redundancy, and accelerates administrative workflows that previously required considerable time when performed manually. Additionally, the system enhances data transparency and facilitates real-time information tracking, which supports better managerial oversight and decision-making. In conclusion, the HRIS developed in this study effectively addresses the core issues faced by CV. Cipta Sarana Makmur in managing human resource operations. To maximise the system’s potential, it is recommended that comprehensive training be provided to system users. For future system enhancements, the integration of more advanced technologies—such as facial recognition-based attendance systems—is advised to further improve accuracy, efficiency, and overall data security. Keyword: laravel, human resource information system, SDLC waterfall, data management, HRIS.
Sistem Pendukung Keputusan Pemilihan Supplier Barang Elektronik Dengan Metode Assemble AHP-SAW Bhustomy Hakim; Talarice Felicia Elvinata Happy Clarissa; Peter Nolasco Jong; Leoflavianus Jang Carlos; Yemima Monica Geasela
Jurnal Sistem Informasi Triguna Dharma (JURSI TGD) Vol. 5 No. 1 (2026): EDISI JANUARI 2026
Publisher : STMIK Triguna Dharma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.53513/jursi.v5i1.12344

Abstract

Pemilihan supplier merupakan salah satu aspek strategis dalam manajemen rantai pasok karena berpengaruh langsung terhadap kualitas bahan baku, kelancaran produksi, serta efisiensi biaya operasional. Namun, praktik di lapangan sering menghadapi tantangan berupa keterlambatan pengiriman, ketidaksesuaian kualitas produk, maupun biaya tambahan yang berdampak negatif terhadap produktivitas perusahaan. Untuk mengatasi permasalahan tersebut, diperlukan sebuah pendekatan yang sistematis dan objektif melalui pemanfaatan Sistem Pendukung Keputusan (SPK). Penelitian ini mengusulkan pengembangan SPK dengan mengombinasikan metode Analytical Hierarchy Process (AHP) dan Simple Additive Weighting (SAW). AHP digunakan untuk menentukan bobot prioritas setiap kriteria melalui perbandingan berpasangan dan pengujian konsistensi, sedangkan SAW dimanfaatkan untuk menghitung skor akhir alternatif supplier berdasarkan bobot yang telah ditentukan. Kombinasi kedua metode ini diharapkan mampu memberikan peringkat alternatif yang lebih akurat, transparan, dan mudah dipahami oleh pengambil keputusan. Tahapan penelitian meliputi identifikasi masalah, studi literatur, pengumpulan data terkait kriteria penilaian supplier, implementasi sistem berbasis metode AHP-SAW, serta evaluasi hasil perhitungan. Kriteria yang digunakan dalam penelitian ini antara lain kualitas produk, ketahanan, garansi, harga, kecepatan respon komunikasi, waktu pengiriman, dan biaya pengiriman. Hasil yang diharapkan adalah sebuah sistem yang mampu memberikan rekomendasi supplier terbaik secara objektif, sehingga dapat membantu perusahaan meminimalkan risiko operasional dan meningkatkan daya saing. Penggabungan metode Analytical Hierarchy Process (AHP) dan Simple Additive Weighting (SAW) terbukti efektif dalam meningkatkan akurasi pemilihan supplier secara objektif dan terstruktur. Sistem ini memberikan rekomendasi yang sistematis dan efisien sesuai dengan standar perusahaan, sehingga membantu mengurangi risiko kesalahan dan mendukung pengambilan keputusan yang lebih bijak.
Pengaruh Game Shopee Cocoki Sebagai Media Gamifikasi Terhadap Minat Beli Pengguna Bhustomy Hakim; Ferdian Aditya Pratama; Jonathan Mikhael Anthony
IJAI (Indonesian Journal of Applied Informatics) Vol 9, No 2 (2025)
Publisher : Universitas Sebelas Maret

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20961/ijai.v9i2.98132

Abstract

Abstrak : Di era 4.0 ini, 88% masyarakat Indonesia menggunakan aplikasi e-commerce untuk melakukan jual beli. Banyak aplikasi e-commerce yang tersedia seperti Shopee, Tokopedia, BliBli, BukaLapak, dan Lazada. Gamifikasi merupakan salah satu cara tim pengembang aplikasi untuk membuat strategi agar e-commerce dapat bersaing dan tetap digunakan dan menambah customer engagement. Shopee merupakan aplikasi e-commerce yang aktif mengembangan gamifikasi seperti adanya Goyang Shopee, Shopee Tanam, dan yang terbaru adalah Shopee Cocoki. Shopee Cocoki merupakan permainan mencocokan 3 kartu gambar dengan beberapa opsi bantuan langkah sebagai strategi untuk menyelesaikannya. Gameplay-nya mungkin terdengar mudah, akan tetapi Shopee Cocoki viral karena kesulitannya yang membuat pemain stress dan tertantang untuk memainkannya. Namun dengan opsi bantuan langkah seperti shuffle, revive, undo, dan mengeluarkan 3 kartu gambar dari slot, permainan menjadi mungkin dapat dimenangkan. Uniknya, pemain harus membagikan pesan tentang permainan ke pengguna lain atau melihat-lihat katalog barang atau produk yang disediakan untuk mendapatkan opsi bantuan tersebut. Mekanisme ini jelas sejalan dengan tujuan gamifikasi Shopee Cocoki: untuk meningkatkan niat pembelian di antara pengguna. Mengingat fenomena ini, sebuah penelitian dilakukan untuk menguji pengaruh Shopee Cocoki sebagai fitur gamifikasi terhadap niat pembelian pengguna. Metode Intrinsic Motivation Inventory (IMI) digunakan, dengan fokus pada kriteria seperti Minat/Kenikmatan, Upaya/Pentingnya, Pilihan yang Dirasakan, dan Nilai/Kegunaan. Pengumpulan data dilakukan dengan menggunakan kuesioner, dan hasilnya divalidasi menggunakan rumus Cronbach's Alpha. Nilai kritis ditetapkan sebesar 0,7, dan skor Cronbach's Alpha untuk setiap indikator adalah sebagai berikut: 0,898 untuk Minat/Kenikmatan, 0,915 untuk Upaya/Pentingnya, 0,923 untuk Pilihan yang Dirasakan, dan 0,883 untuk Nilai/Kegunaan. Gamifikasi Shopee Cocoki meningkatkan minat pembelian secara signifikan, tercermin dalam kenaikan rasio konversi (rasio penambahan barang ke keranjang belanja) sebesar 13,82%, yang merupakan peningkatan penting.==================================================Abstract : In the 4.0 era, 88% of Indonesians use e-commerce applications for buying and selling activities. Various e-commerce platforms are available, such as Shopee, Tokopedia, BliBli, BukaLapak, and Lazada. Gamification has become a key strategy for app development teams to keep e-commerce platforms competitive, increase customer engagement, and maintain user retention. Shopee, in particular, actively incorporates gamification features like Goyang Shopee, Shopee Tanam, and its latest addition, Shopee Cocoki. Shopee Cocoki is a game where players match three picture cards using several assist options to complete the challenge. While the gameplay may seem simple, Shopee Cocoki has gone viral due to its high difficulty, which leaves players feeling stressed yet challenged to keep playing. Assistance options such as shuffle, revive, undo, and removing three cards from the slot make the game winnable. However, players must share game-related messages with other users or browse through product catalogs to obtain these assistance options. This mechanism clearly aligns with the gamification objective of Shopee Cocoki: to boost purchase intention among users. Given this phenomenon, a study was conducted to examine the influence of Shopee Cocoki as a gamification feature on users’ purchase intentions. The Intrinsic Motivation Inventory (IMI) method was employed, focusing on criteria such as Interest/Enjoyment, Effort/Importance, Perceived Choice, and Value/Usefulness. Data collection was carried out using questionnaires, and the results were validated using the Cronbach’s Alpha formula. The critical value was set at 0.7, and the Cronbach's Alpha scores for each indicator were as follows: 0.898 for Interest/Enjoyment, 0.915 for Effort/Importance, 0.923 for Perceived Choice, and 0.883 for Value/Usefulness. Gamification of Shopee Cocoki significantly increased purchase intention, reflected in a 13.82% rise in conversion rate (the rate of adding items to the shopping cart), which is a notable improvement.
KLASIFIKASI ENGINE FAILURE BERDASARKAN BUNYI MOBIL MENGGUNAKAN MFCC DAN STFT DENGAN MACHINE LEARNING ; Bhustomy Hakim; Fergie Joanda Kaunang; Angelina Pramana Thenata; Ranny Ranny
JOISIE (Journal Of Information Systems And Informatics Engineering) Vol. 9 No. 1 (2025)
Publisher : Institut Bisnis dan Teknologi Pelita Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35145/joisie.v9i1.4936

Abstract

Deteksi kerusakan mobil sangat penting untuk meningkatkan keselamatan berkendara dan mengurangi biaya perbaikan. Salah satu metode yang umum digunakan oleh mekanik adalah mendiagnosis kerusakan melalui suara yang dihasilkan oleh komponen kendaraan. Namun, proses ini masih bergantung pada keahlian manual dan dapat menyebabkan kesalahan atau keterlambatan diagnosa. Oleh karena itu, penelitian ini bertujuan untuk mengembangkan model klasifikasi kerusakan mobil berbasis suara menggunakan teknik data science, terutama machine learning. Data suara dikumpulkan dari berbagai sumber dari kerjasama bengkel-bengkel di Indonesia berupa file suara mesin dengan format wav dengan label berbeda, kemudian diolah menggunakan metode Mel Frequency Cepstral Coefficients (MFCC) dan Short-Time Fourier Transformation (STFT) untuk mengekstrak fitur penting dari sinyal suara. Selanjutnya, dengan algoritma Multilayer Perceptron diimplementasikan untuk membangun model prediksi kerusakan. Penelitian ini mengevaluasi model berdasarkan nilai akurasi dari confusion matrix untuk menemukan model terbaik dalam mendeteksi jenis kerusakan berdasarkan suara. Model dengan MFCC sebagai metode ekstraksi fitur terbukti menghasilkan akurasi tertinggi sebesar 83,35% ketimbang STFT yang hanya memiliki akurasi sebesar 78,82% dengan konfigurasi fungsi aktivasi ReLU dan layer dengan 512 neuron.
Co-Authors ., Ranny Abednego Marcello Akhmat Fauzi Anak Agung Ayu Putri Ardyanti Asvian Sulaeman Carlos Hia, Juan Chandra, Michelle Mei Diana Chang, Jennefer Febiola, Febiola Fendyanto Fendyanto Fendyanto, Fendyanto Ferdian Aditya Pratama Fergie Joanda Kaunang Fraderic, Fedelis Franclin, Marcell Gabriella, Theresia Geasela, Yemima Monica Geasela, Yemima Monica Hanna Mariana Angelika Hansen Handoko, Hie Hansen, Yoel Hartono, Sherren Hazimah, Malahayati Hendri, Glenda Jocelyn Hon, Peter Raymond Jen, Phangestin Johanes Shane Jonathan Mikhael Anthony Kaunang, Fergie Joanda Kaunang, Fergie Joanda Kinasih, Putri Rindu Kosasi Kosasi Leoflavianus Jang Carlos Lirungan, Maria Carol Stephanie Lukman, Nicholas Merryana Lestari Michael Wijaya Monica Geasela, Yemima Mulyanto, Andrew Kristanto Peter Nolasco Jong Petrisa, Sisilia Ranny Ranny Ranny, Ranny Rarasati, Dionisa Bhisetya Reji Darmawan Rendy Sarudin Rendy Sarudin Sophia Reni Susilo Talarice Felicia Elvinata Happy Clarissa Thenata, Angelina P. Thenata, Angelina Pramana Theresia Gabriella Vinsensius Sugito Lein Wendy, Albert Widjaja, Florence Aurelia Wijayanti, Theresia Puspa Yemima Monica Geasela