Article Per Year (5 Year)
p-Index From 2021 - 2026
2.902
P-Index
This Author published in this journals
All Journal TELKOMNIKA (Telecommunication Computing Electronics and Control) Sinkron : Jurnal dan Penelitian Teknik Informatika Angkasa: Jurnal Ilmiah Bidang Teknologi Jurnal Ilmiah Inovasi G-Tech : Jurnal Teknologi Terapan International Journal of Industrial Optimization (IJIO) Jurnal Sistem Informasi dan Sains Teknologi Jurnal Media Informatika Co-Value : Jurnal Ekonomi, Koperasi & Kewirausahaan Jurnal Sistem Informasi Triguna Dharma (JURSI TGD) Jurnal Komputer Teknologi Informasi Sistem Komputer (JUKTISI) SWARNA Journal of Information Technology and Cyber Security Journal of Information Technology Journal of Vocational, Informatics and Computer Education Jurnal Esensi Infokom : Jurnal Esensi Sistem Komputer dan Informasi
Setiawan, Akas Bagus
Jurusan Teknologi Informasi, Politeknik Negeri Jember
Religion Agriculture, Biological Sciences & Forestry Humanities Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Other

Published : 18 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 18 Documents
Search

 1   2 
BERT Sentimen: Fine-Tuning Multibahasa untuk Ulasan Bahasa Indonesia Khen Dedes; Fatimatuzzahra; Mas'ud Hermansyah; Akas Bagus Setiawan; Reza Putra Pradana; Annisa Fitri Maghfiroh Harvyanti
Jurnal Komputer Teknologi Informasi Sistem Komputer (JUKTISI) Vol. 4 No. 2 (2025): September 2025
Publisher : LKP KARYA PRIMA KURSUS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62712/juktisi.v4i2.585

Abstract

Penelitian ini mengevaluasi pengaruh teknik augmentasi dan fine‑tuning terhadap kinerja model BERT multibahasa pada tugas klasifikasi sentimen ulasan film berbahasa Indonesia. Dataset awal terdiri dari 1.200 ulasan; 80% digunakan untuk pelatihan dan validasi (n = 960) dan 20% untuk pengujian (n = 240). Data pelatihan diperluas melalui augmentasi menjadi 2.880 sampel sintetis untuk keperluan fine‑tuning. Model kemudian di‑fine‑tune pada korpus yang diperluas dan dievaluasi menggunakan metrik akurasi, precision, recall, dan F1. Pada set pengujian diperoleh akurasi 82,5%, precision untuk kelas positif 76,0%, recall 95,0%, dan F1‑score 84,44%. Matriks kebingungan menunjukkan TP = 114, FN = 6, FP = 36, dan TN = 84, yang mengindikasikan sensitivitas tinggi terhadap ulasan positif namun terdapat proporsi false positive yang relatif besar. Temuan ini mengindikasikan bahwa augmentasi meningkatkan kemampuan model dalam menangkap sinyal positif (tingginya recall), namun memerlukan penyesuaian lebih lanjut untuk mengurangi kesalahan prediksi positif (meningkatkan precision). Secara keseluruhan, hasil penelitian menyediakan bukti bahwa BERT multibahasa mampu menangani tugas sentimen berbahasa Indonesia dengan performa memadai apabila didukung strategi augmentasi dan prosedur validasi yang tepat.
Sistem Penunjang Keputusan Pemilihan Guru Terbaik Melalui Penilaian Administrasi Pembelajaran dengan Metode TOPSIS Mas’ud Hermansyah; Akas Bagus Setiawan; M. Faiz Firdausi; Mujiono Mujiono; David Juli Ariyadi
Jurnal Esensi Infokom : Jurnal Esensi Sistem Informasi dan Sistem Komputer Vol 9 No 1 (2025)
Publisher : Institut Bisnis Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55886/infokom.v9i1.969

Abstract

Proses memilih guru paling berprestasi merupakan bagian penting sebagai upaya untuk meningkatkan mutu pendidikan di sekolah. Di SMAS Sultan Agung Puger, penilaian guru selama ini masih bersifat subjektif dan belum menggunakan sistem yang terstruktur. Dengan demikian, studi ini memiliki tujuan untuk merancang serta mengembangkan sebuah Sistem Pendukung Keputusan (SPK) untuk membantu proses pemilihan guru terbaik berdasarkan kriteria evaluasi administrasi pembelajaran yang telah ditetapkan oleh sekolah. Metode yang digunakan dalam penelitian ini adalah Technique for Order Preference by Similarity to Ideal Solution (TOPSIS), karena metode ini mampu memberikan hasil peringkat yang objektif berorientasi pada tingkat kemiripan dengan solusi ideal. TOPSIS memiliki keunggulan dalam memperhitungkan nilai positif dan negatif dari masing-masing alternatif secara simultan. Hasil dari implementasi sistem menunjukkan bahwa guru dengan alternatif A4 memperoleh nilai preferensi tertinggi sebesar 1, sehingga terpilih sebagai guru terbaik. Sistem ini telah berhasil membantu memberikan hasil evaluasi yang lebih transparan, sistematis, dan objektif. Dengan demikian, sistem yang dibangun menggunakan metode TOPSIS terbukti efektif dalam mendukung proses pengambilan keputusan pemilihan guru terbaik berdasarkan data administrasi pembelajaran.
Decision Support System for Selecting the Best Rental House with Weight Product in Sidokare District, Sidoarjo Regency Akas Bagus Setiawan; Eka Yuniar; Mas'ud Hermansyah; Mujiono Mujiono; David Juli Ariyadi
G-Tech: Jurnal Teknologi Terapan Vol 10 No 1 (2026): G-Tech, Vol. 10 No. 1 January 2026
Publisher : Universitas Islam Raden Rahmat, Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70609/g-tech.v10i1.8865

Abstract

The demand for rental housing in high-mobility areas such as Sidokare District, Sidoarjo Regency, continues to increase along with the region's economic development. However, prospective tenants often face difficulties in selecting the right rental house due to unstructured information and subjective decision-making processes. This study aims to develop a web-based Decision Support System (DSS) capable of providing objective and measurable rental housing recommendations. The method used is the Weighted Product (WP), a multicriteria decision-making technique that normalizes weights through multiplication operations. This system evaluates five rental housing alternatives based on eight main criteria, including price, location, facilities, security, and comfort. The results show that Sukun Rental House is the best alternative with the highest preference value of 0.0769. The practical implication of this study is the availability of an efficient digital tool for residents and students in Sidokare to compare various housing options transparently and quickly. This system successfully minimizes subjectivity in housing selection and helps users find the housing that best suits their financial priorities and functional needs.
Privacy-preserving messaging for medical device networks Rachmad Andri Atmoko; Salnan Ratih Asriningtias; Akas Bagus Setiawan; Devasis Pradhan; Ismail Rakip Karas
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 24, No 4: August 2026
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v24i4.27794

Abstract

Internet of medical things (IoMT) deployments rely on lightweight messaging, but the message queuing telemetry transport (MQTT) protocol still exposes sensitive metadata through plaintext topic names and stable client identifiers. In healthcare settings, this visibility can reveal patient identity, location, and monitored condition even when payloads are encrypted. This paper presents a gateway-based privacy architecture that replaces semantic MQTT topics and client identifier (ClientIDs) with rotating pseudonyms managed by a topic and ID privacy manager (TPM). The design uses hash-based message authentication code using secure hash algorithm 256-bit (HMAC-SHA256) for pseudonym generation, advanced encryption standard-galois/counter mode (AES-GCM) for payload protection, and a short overlap phase that preserves message delivery during rotation without modifying the broker. Experiments from 5 to 10,000 patients show a consistent 5.0x increase in topic diversity, 2.50 μs per message cryptographic overhead, 0.063 ms maximum latency overhead, and zero packet loss. These results indicate that practical IoMT deployments can improve metadata privacy while still meeting real-time clinical communication requirements.
Studi Efektifitas Lampu Perangkap Hama Padi Tenaga Surya dalam Konteks Ekologi Pertanian Khen Dedes; Fatimatuzzahra Fatimatuzzahra; David Juli; Akas Bagus Setiawan; Mujiono Mujiono
SWARNA: Jurnal Pengabdian Kepada Masyarakat Vol. 4 No. 12 (2025): SWARNA : Jurnal Pengabdian Kepada Masyarakat, Desember 2025
Publisher : LPPM Sekolah Tinggi Ilmu Ekonomi 45 Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55681/swarna.v4i12.1830

Abstract

The increasing intensity of pest attacks on rice plants is one of the major factors contributing to the decline in productivity and quality of yields in Indonesia’s agricultural sector. Farmers’ excessive dependence on chemical pesticides not only leads to pest resistance but also poses negative impacts on human health, the environment, and the ecological balance of paddy fields. Therefore, there is an urgent need for innovative, environmentally friendly, efficient, and sustainable pest control technologies. This study proposes the implementation of a solar-powered pest trap lamp integrated with an Internet of Things (IoT)-based system as an alternative solution within an integrated pest management (IPM) framework. The device is designed to utilize solar energy as its primary power source to support energy-efficient operations while reducing dependence on conventional electricity. The IoT connectivity enables real-time data transmission to a cloud-based server for remote monitoring, data analysis, and evidence-based decision-making. Through this approach, pest control can be carried out more precisely, efficiently, and adaptively according to field conditions. Moreover, the application of this technology has the potential to minimize the use of chemical pesticides, enhance agroecosystem health, and promote the principles of sustainable agriculture and national food security. This study emphasizes that the integration of solar energy and IoT technology in pest trap systems can serve as a significant innovation in the digital modernization of agriculture in Indonesia. Further research recommendations include large-scale field trials, quantitative analysis of pest population reduction effectiveness, and evaluation of the economic, social, and adoption aspects among farmers. Hence, this study is expected to provide a substantial contribution to the development of intelligent, efficient, and sustainable pest management systems.
Optimization of real-time forest monitoring system using yolo v9 object detection and 2.4 ghz wireless network: resource allocation, energy efficiency, and industrial deployment strategies Rachmad Andri Atmoko; Rifqi Rahmat Hidayatullah; Septian Ghuslal Nur Na’im; Akas Bagus Setiawan
International Journal of Industrial Optimization Vol. 7 No. 1 (2026)
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/ijio.v7i1.11899

Abstract

Large forest areas are increasingly exposed to illegal activities and environmental threats, while conventional monitoring systems suffer from limited coverage, high energy consumption, and delayed response. To address these challenges, this study proposes an optimized real-time forest monitoring system designed for industrial-scale deployment in remote environments. The primary objective is to enhance surveillance efficiency by integrating AI-based object detection, long-range wireless communication, and resource-efficient system design. The proposed system employs ESP32-CAM sensor nodes integrated with 2.4 GHz CPE wireless links and a gateway-based YOLOv9 object detection framework. Bandwidth utilization is optimized through selective transmission of processed detection metadata instead of raw images, while deployment parameters are optimized using simulation-based planning. A web-based monitoring platform with an optimized REST API supports real-time visualization and alert generation. Experimental results show that the system achieves reliable communication up to 500 m with packet loss below 5% and latency under 50 ms at distances up to 300 m. Human detection accuracy reaches 98.5% under optimal conditions, with performance degradation observed in dense vegetation and low-light environments. Energy evaluation confirms sustainable operation, with ESP32 nodes consuming 160 mA and the gateway operating at 3.7 W. Comparative analysis indicates reductions of 37% in deployment cost, 24% in energy consumption, and 51% in latency compared to similar systems. This study concludes that the proposed architecture effectively balances accuracy, scalability, cost, and energy efficiency. The novelty lies in the integrated optimization of edge-based AI detection, selective data transmission, and simulation-driven deployment for industrial forest monitoring.
OTOMATISASI PENJADWALAN DAN PENGINGAT TUGAS BERBASIS GOOGLE FORM, APPS SCRIPT, DAN GOOGLE CALENDAR UNTUK EFISIENSI MANAJEMEN PROYEK Akas Bagus Setiawan; Mas'ud Hermansyah
Jurnal Sistem Informasi dan Sains Teknologi Vol 7, No 2 (2025): Jurnal Sistem Informasi dan Sains Teknologi
Publisher : Universitas Trilogi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31326/sistek.v7i2.2425

Abstract

Manajemen tugas yang efektif menjadi tantangan utama dalam organisasi modern, terutama dalam mengelola tenggat waktu dan kolaborasi antar anggota tim. Penelitian ini mengembangkan sistem otomatisasi penjadwalan dan pengingat tugas berbasis Google Form, Google Apps Script, dan Google Calendar. Sistem ini memungkinkan data tugas yang diinput melalui Google Form secara otomatis dijadwalkan ke Google Calendar, lengkap dengan pengingat sebelum deadline. Metode penelitian meliputi perancangan form digital, pemrograman Apps Script untuk integrasi data, serta pengujian sistem pada lingkungan kerja nyata. Hasil implementasi menunjukkan peningkatan kepatuhan terhadap deadline dan efisiensi monitoring tugas. Integrasi ini juga mengurangi beban administratif dan potensi human error dalam penjadwalan manual. Sistem yang diusulkan dapat diadopsi oleh berbagai organisasi untuk meningkatkan efektivitas manajemen tugas dan kolaborasi tim.
Smart Reminder: Sistem Pengingat Tugas Berbasis ReactJS dan Google Apps Script untuk Manajemen Proyek Tim: No Akas Bagus Setiawan; Mas’ud Hermansyah
Jurnal Media Informatika Vol. 6 No. 6 (2025): Edisi Desember 2025
Publisher : Lembaga Dongan Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55338/jumin.v6i6.7461

Abstract

Manajemen tugas yang efisien merupakan tantangan utama dalam organisasi modern, terutama dalam mengelola tenggat waktu serta memastikan kolaborasi yang optimal antaranggota tim. Penelitian ini bertujuan mengembangkan sistem otomatisasi penjadwalan dan pengingat tugas berbasis cloud dengan mengintegrasikan ReactJS sebagai frontend untuk input data, serta Google Apps Script dan Google Calendar sebagai backend. Melalui sistem ini, data tugas yang dimasukkan melalui formulir ReactJS dikirim secara real-time ke endpoint Google Apps Script, kemudian dijadwalkan secara otomatis ke Google Calendar lengkap dengan notifikasi pengingat sebelum batas waktu penyelesaian. Metodologi penelitian mencakup perancangan antarmuka pengguna berbasis prinsip UI/UX, pengembangan skrip pemrosesan otomatis di Apps Script, serta pengujian sistem dalam lingkungan kerja nyata. Hasil pengujian menunjukkan adanya peningkatan signifikan dalam kepatuhan terhadap tenggat waktu dan efisiensi pemantauan tugas, disertai penurunan beban administratif dan potensi human error pada proses penjadwalan manual. Berdasarkan hasil survei kepuasan pengguna, 87% responden menyatakan sistem ini mempermudah pengelolaan tugas dan membantu dalam mengingat deadline. Sebagian besar responden juga menilai bahwa formulir input berbasis ReactJS mudah digunakan dan validasi datanya berjalan efektif dalam meminimalkan kesalahan input. Dengan hasil tersebut, sistem berbasis ReactJS dan Apps Script ini dapat dijadikan solusi inovatif dan skalabel untuk mendukung manajemen tugas dan kolaborasi tim berbasis cloud di berbagai lingkungan organisasi.
Co-Authors Aji Seto Arifianto Annisa Fitri Maghfiroh Harvyanti Annisa Fitri Maghfiroh Harvyanti Atmoko, Rachmad Beni Widiawan, Beni David Juli Ariyadi Devasis Pradhan Dwi Putro Sarwo Setyohadi Dwi Putro Sarwo Setyohadi, Dwi Putro Sarwo Eka Yuniar Eka Yuniar Fatimatuzzahra Fatimatuzzahra Fatimatuzzahra Hendra Yufit Riskiawan Hendra Yufit Riskiawan Hermansyah, Mas'ud Hermansyah, Masud Hermansyah, Mas’ud Hermawan Arief Putranto I Gede Wiryawan Ismail Rakip Karas Izzun Ni`am, Muhammad Jannah, Annisa Nurul Hidayati Khen Dedes M Faiz Firdausi M. Faiz Firdausi Mas'ud Hermansyah Mas'ud Hermansyah Mas’ud Hermansyah Mas’ud Hermansyah Maulana Firmansyah, Akbar Mujiono Mujiono Mujiono Mujiono Mujiono Mujiono Mujiono Mujiono Nasyatha Adlin, Dzakiyyan Nur Na’im, Septian Ghuslal Pascawati Savitri Universitasari Rachmad Andri Atmoko Rachmad Andri Atmoko Rachmad Andri Atmoko Rahmat Hidayatullah, Rifqi Resya , Fachmi Reza Putra Pradana Rifqi Rahmat Hidayatullah Rizal Setya Perdana Saiful Anwar Salnan Ratih Asriningtias, Salnan Ratih Septian Ghuslal Nur Na’im Setyo Wibowo, Nugroho Sherin Ramadhania Syamsul Arifin Taufiq Rizaldi Taufiq Rizaldi Vindarosita, Babylina Wijaya, Fariz Rizky Yudhistira, Prillinaya Yuniar, Eka