Claim Missing Document
Check
Articles

Found 19 Documents
Search

The Investigation of Convolution Layer Structure on BERT-C-LSTM for Topic Classification of Indonesian News Headlines Fabillah, Dzakira; Auliarahmi, Rizka; Setiarini, Siti Dwi; Gelar, Trisna
Journal of Software Engineering, Information and Communication Technology (SEICT) Vol 4, No 2: Desember 2023
Publisher : Universitas Pendidikan Indonesia (UPI)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.17509/seict.v4i2.63742

Abstract

An efficient and accurate method for classifying news articles based on their topics is essential for various applications, such as personalized news recommendation systems and market research. Manual classification methods are tedious, prompting the use of deep learning techniques in this study to automate the process. The developed model, BERT-C-LSTM, combines BERT, the convolutional layer from CNN, and LSTM, leveraging their individual strengths. BERT excels at transforming text into context-dependent vector representations, The design of the classification model employs a blend of convolutional layers and LSTM, referred to as C-LSTM. The convolutional layer possesses the capability to extract salient elements, including keywords and phrases, from input data. On the other hand, the Long Short-Term Memory (LSTM) model exhibits the ability to comprehend the temporal context present in sequential data. This study aims to investigate the influence of the convolutional layer structure in BERT-C-LSTM on the classification of Indonesian news headline categorized into eight topics. The results indicate that there are no significant differences in accuracy between BERT-C-LSTM model architectures with a single convolutional layer and multiple parallel convolutional layers and the models using various filter sizes. Furthermore, the BERT-C-LSTM model achieves an accuracy that is not much different from the BERT-LSTM and BERT-CNN models, with accuracies reaching 92.6%, 92.1%, and 92.7%, respectively.
BLOCKCHAIN: TEKNOLOGI DAN IMPLEMENTASINYA Nanda Sari, Aprianti; Gelar, Trisna
Jurnal Mnemonic Vol 7 No 1 (2024): Mnemonic Vol. 7 No. 1
Publisher : Teknik Informatika, Institut Teknologi Nasional malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36040/mnemonic.v7i1.6961

Abstract

Bitcoin merupakan mata uang digital atau yang lebih dikenal sebagai cryptocurrency. Bitcoin diciptakan pada tahun 2008 oleh Satoshi Nakamoto sebagai alat pembayaran elektronik secara peer-to-peer. Sebagai konsekuensinya, transaksi dengan menggunakan Bitcoin tidak memerlukan pihak ketiga seperti institusi keuangan atau pemerintah. Meskipun demikian, teknologi dibalik Bitcoin tidaklah baru. Pada dasarnya, Bitcoin menggunakan teknik-teknik dasar kriptografi dan jaringan komputer seperti fungsi hash, blockchain, jaringan komputer peer-to-peer, dan mekanisme konsensus. Sejak dibuatnya Bitcoin, aplikasi dari blockchain semakin meluas di berbagai bidang. Pada penelitian ini akan dibahas mengenai pengetahuan dasar mengenai blockchain. Selain itu, penelitian ini juga menganalisa implementasi blockchain, algoritma dasar yang digunakan, dan keterkaitannya dengan karakteristik blockchain di enam bidang berbeda yaitu ekonomi, kesehatan, pendidikan, pengarsipan dan kepemilikan, media, serta rantai pasok. Dari hasil analisis diketahui bahwa setiap bidang memiliki kebutuhan yang berbeda sehingga arsitektur blockchain yang dibangun juga berbeda.
PENGEMBANGAN APLIKASI PENCATATAN IURAN PENGGUNAAN AIR BOR SWADAYA MANDIRI BORBIR BERBASIS WEBSITE Ridho Wiratama, Anshar; Ratna Wulan, Sri; Gelar, Trisna
JATI (Jurnal Mahasiswa Teknik Informatika) Vol. 8 No. 3 (2024): JATI Vol. 8 No. 3
Publisher : Institut Teknologi Nasional Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36040/jati.v8i3.9064

Abstract

Swadaya Mandiri Borbir menyediakan air bersih dari sumur bor untuk warga yang tinggal di Komplek Perumahan Batu Indah Regency, Kelurahan Cilame, Kecamatan Ngamprah, Kabupaten Bandung Barat, Provinsi Jawa Barat. Swadaya perlu mencatatkan penggunaan air yang digunakan anggota swadaya setiap bulannya. Data penggunaan air akan digunakan untuk memberitahukan iuran penggunaan air kepada anggota dan laporan penggunaan air untuk swadaya. Sistem yang berjalan dalam pencatatan penggunaan air adalah anggota mengirimkan data penggunaan air, nama, dan alamat kepada pengelola swadaya untuk dikelola di dalam aplikasi spreadsheet. Kekurangan aplikasi spreadsheet adalah data dalam jumlah banyak dilakukan berulang kali oleh pengelola akan mengurangi keefektifan dalam mengelola data penggunaan air. Aplikasi Pencatatan Penggunaan Air berbasis Web dibangun dengan tujuan untuk membantu pengelola dalam mencatat iuran penggunaan air anggota. Aplikasi dibangun dengan metode pengembangan aplikasi menggunakan SDLC waterfall. Penggunaan teknologi Laravel, livewire, dan MySQL. Hasilnya adalah aplikasi wbsite yang dikembangkan memiliki fitur authentikasi, pengelolaan pengguna, pencatatan penggunaan air, dan pengumuman terkait dengan swadaya
Transcription of Informatics Final Project Seminar Recordings via Speech-to-Text Gelar, Trisna; Sari, Aprianti Nanda; Lieharyani, Djoko Cahyo Utomo; Naylassana, Fauza; Hamdani, Nisrina Wafa Zakiya
Jurnal Pendidikan Multimedia (Edsence) Volume 6 No 2 (December 2024)
Publisher : Universitas Pendidikan Indonesia (UPI)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.17509/edsence.v6i2.74660

Abstract

Bandung State Polytechnic has implemented project-oriented problem-based learning as its new educational approach. Project 6, or Final Project, is a course that communicates student learning results. Documenting seminar events is crucial as it provides valuable resources for students to analyze seminar outcomes and address any inquiries from teachers. However, not all students are inherently proactive in documenting or recording these activities. The task of transcribing learning outcomes becomes distinct when the emphasis is placed on students. This study aims to develop and evaluate a speech-to-text model utilizing DeepSpeech for transcribing seminar presentations related to final year projects, tackling the difficulties presented by spontaneous speech patterns and specialized technical terminology in software engineering. The model is trained and assessed utilizing Word Error Rate (WER) and Character Error Rate (CER) measures. The results of this study are the development of speech-to-text systems for educational purposes, especially within project-based student-centered learning. These resulting transcriptions could benefit both students and educators by offering a searchable and analyzable account of seminar presentations and improving feedback.
Morphological Grayscale Pre-processing to SAR Images for Reducing Noise in Ship Detection Based on YOLOv8 Pratidina, Caturiani; Safira, Decia; Gelar, Trisna; Permana, Heru; Suprihanto, Suprihanto; Syakrani, Nurjannah; Fauzi, Cholid
Journal of Software Engineering, Information and Communication Technology (SEICT) Vol 5, No 2: December 2024
Publisher : Universitas Pendidikan Indonesia (UPI)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.17509/seict.v5i2.75970

Abstract

The development of a ship detection system using SAR pictures loaded with noise poses issues for pictures Intelligence (IMINT). The YOLOv8 model is utilized for ship identification. The preprocessing approaches entail employing a fusion of grayscale morphology techniques and image restoration using a harmonic mean filter and a bandpass. This technique is designed to assess the effect of noise reduction to enhance the accuracy of detecting objects in SAR images. The preprocessing technique is categorized into two methods: basic grayscale morphology (GM1-GM6) and a fusion of image restoration with grayscale morphology (GHB1-GHB6). The model's performance is assessed using mAP and IoU criteria. This research discovered that ship objects were not detected successfully in the presence of several types of noise. These failures were attributed to factors such as tiny ship size, low picture quality, and inadequate preprocessing techniques for noise handling. The findings indicate a substantial enhancement in ship detection, specifically in synthetic aperture radar (SAR) images affected by sidelobe noise. There were noticeable enhancements in the accuracy of images that underwent preprocessing using GHB5. GHB5 employs a combination of image restoration, closure, and erosion techniques.
Serverless Named Entity Recognition untuk Teks Instruksional Pertanian Kota Trisna Gelar; Aprianti Nanda; Akhmad Bakhrun
Jurnal Teknik Informatika dan Sistem Informasi Vol 8 No 3 (2022): JuTISI
Publisher : Maranatha University Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28932/jutisi.v8i3.5447

Abstract

The evolution of document documentation, classification, and information retrieval includes named entity recognition (NER). The implementation of NER in the agricultural domain, in particular instructional texts or transcriptions of tutorial videos, will make it easier for the general public to understand the specific concepts and terms of urban agricultural activities such as crop production processes and procedures, agricultural methods and tools, harvest cycles, and handling plant pests or diseases. Spacy is an NLP tool, has two methods of developing NER models, namely with Toc2Vec and Transformer. Both methods have advantages and disadvantages, namely different sizes, performance and prediction speeds according to needs. The NER model can be implemented into a Serverless application, using the Functional as Services (FaaS) and Backend as Services (BaaS) approaches. For the subtopic of cultivating fruit crops in agricultural instructional literature, three NER models have been built in this study. First, the IndoBERT-based model, the Toc2Vec-based model with efficiency optimization, and the Toc2Vec-based model with accuracy optimization. The most efficient toc2vec model, with a f1-score of 0.71, is followed by the effective toc2vec model, with a f1-score of 0.60. The COUNT, PERIOD, and VERIETAS entities are consistently predicted incorrectly by the Toc2Vec model, which is unable to forecast numeric entities well. In addition, the Toc2Vec Model's better efficiency optimization directly relates the size of the model to the speed of word prediction per second, and the model is simple to integrate into a FaaS- and BaaS-based Serverless. The capabilities of Serverless M have been successfully tested using the black box method.
A Systematic Literature Review of YOLO and IoT Applications in Smart Waste Management Gelar, Trisna; Fitriani, Sofy; Rachmat, Setiadi
Green Intelligent Systems and Applications Volume 5 - Issue 2 - 2025
Publisher : Tecno Scientifica Publishing

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.53623/gisa.v5i2.706

Abstract

The increase in urbanization and global population expansion resulted in increased garbage production, causing considerable environmental and public health issues that exceeded traditional waste management approaches. To tackle these challenges, automated waste detection and analysis integrated computer vision, especially deep learning, with the Internet of Things (IoT) in intelligent waste management applications. This comprehensive literature review investigated a wide range of You Only Look Once (YOLO) applications in IoT-based waste detection and management, demonstrating its efficacy in addressing global waste issues. Employing specific keywords and Boolean operators, the review followed a rigorous methodology to explore reputable electronic databases for peer-reviewed articles published from 2019 to 2025. The primary findings indicated that different iterations of YOLO (v3 to v12) were integrated with diverse IoT devices and computing setups, including edge and centralized systems. These integrations facilitated four crucial applications: hazardous waste management, monitoring of smart bins, classification of waste types, and detection of litter in public spaces. This integration enhanced sustainability through improved waste management practices, increased efficiency in waste processes, and reduced manual labor requirements. Challenges included precise waste identification in complex scenarios, adaptation to fluctuating environmental conditions, and ensuring dependable, low-power operation of IoT devices. To sum up, the integration of YOLO and IoT established a robust basis for intelligent waste management, transforming reactive approaches into proactive strategies. Moving forward, research should prioritize enhancing the integration and power management of IoT sensors, optimizing edge deployment, and developing more resilient YOLO models.
Pelatihan Pembelajaran Computational Thinking Untuk Guru SMP 1 Negeri Baleendah Sari, Aprianti Nanda; Gelar, Trisna; Hayati, Hashri; Firdaus, Lukmannul Hakim; Hodijah, Ade; Alifi, Muhammad Riza
Jurnal Pengabdian Masyarakat IPTEK Vol. 4 No. 1 (2024): Edisi Januari 2024
Publisher : STMIK Triguna Dharma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.53513/abdi.v4i1.9570

Abstract

Salah satu misi dari SMP Negeri 1 Baleendah adalah melaksanakan proses belajar dan bimbingan secara efektif yang dapat menggali seluruh potensi yang dimiliki siswa sehingga dapat menghasilkan siswa yang berprestasi. Peningkatan prestasi siswa dapat diraih dengan berbagai cara, salah satunya dengan peningkatan kompetensi Computational Thinking (CT). Aktifitas CT dengan format permainan dan multidisiplin dapat meningkatakan kreativitas dari siswa. Pemberian pelatihan aktifitas CT Unlugged seperti Lego-Clone dan Educational Robot dan Plugged dengan pengembangan games, animasi, dan video dengan media Scratch dapat meningkatan kompetensi guru dalam membuat bahan ajar dan media pembelajaran yang kreatif dan menarik. Tahapan pengabdian terdiri dari analisa situasi dan kebutuhan, perancangan bahan ajar pelatihan, pelaksanaan pelatihan, pendampingan peserta pelatihan, evaluasi dan capstone project. Dari hasil evaluasi, kemampuan CT guru yang mengikuti pelatihan meningkat. Selain itu, guru-guru yang mengajar mata Pelajaran berbeda berhasil berkolaboarsi mengembangkan bahan ajar sederhana berbasis CT yang multidisiplin menggunakan Scratch. Selain melakukan pelatihan, Guru berhasil menyelesaikan Capstone Project yang berupa Implementasi CT untuk bahan ajar mulai dari inisiasi ide, pembuatan bahan ajar dan implementasi pada kegiatan belajar mengajar pada masing-masing kelas.
Pelatihan Peningkatan Kompetensi Guru melalui Media Board Game sebagai Inovasi Pembelajaran Computational Thinking di Pondok Pesantren Darul Fithrah Kabupaten Bandung Fitriani, Sofy; Rachmat, Setiadi; Sari, Aprianti Nanda; Syakrani, Nurjannah; Hidayatullah, Priyanto; Soewono, Eddy Bambang; Widhiyasana, Yudi; Abdillah, Trisna Gelar; Setiarini, Siti Dwi; Sholahuddin, Muhammad Rizqi
Jurnal ABDINUS : Jurnal Pengabdian Nusantara Vol 10 No 1 (2026): Volume 10 Nomor 1 Tahun 2026
Publisher : Universitas Nusantara PGRI Kediri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29407/ja.v10i1.27180

Abstract

Kegiatan Pengabdian kepada Masyarakat (PKM) ini dilatarbelakangi oleh keterbatasan guru pesantren dalam memahami dan mengimplementasikan keterampilan computational thinking dalam pembelajaran. Di Pondok Pesantren Darul Fithrah, media pembelajaran inovatif berupa board game berbasis Unplugged Computational Thinking dirancang untuk menjembatani kebutuhan tersebut sekaligus memberikan alternatif metode pembelajaran yang lebih interaktif. Metode pelaksanaan meliputi perancangan board game, penyusunan instrumen pelatihan, pelaksanaan pre-test, pemberian materi dan simulasi board game, serta post-test dan observasi implementasi di kelas. Hasil kegiatan menunjukkan adanya peningkatan signifikan pada pemahaman guru mengenai computational thinking, terlihat dari kenaikan skor rata-rata pre-test dan post-test, khususnya pada aspek pengenalan pola, penyusunan langkah pemecahan masalah, dan pemahaman istilah computational thinking. Respon kuesioner dan feedback guru juga menunjukkan bahwa board game dipandang interaktif, mudah digunakan, serta potensial untuk diterapkan dalam pembelajaran di pesantren. Dengan demikian, kegiatan PKM ini berhasil mendorong guru lebih siap mengintegrasikan keterampilan abad 21 ke dalam praktik pendidikan