Article Per Year (5 Year)
p-Index From 2021 - 2026
4.25
P-Index
This Author published in this journals
All Journal International Journal of Electrical and Computer Engineering Jurnal Teknologi Informasi dan Ilmu Komputer JOIV : International Journal on Informatics Visualization Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) International Journal of Artificial Intelligence Research Creative Information Technology Journal Jurnal Pilar Nusa Mandiri Syntax Literate: Jurnal Ilmiah Indonesia Technomedia Journal EXPLORE EDUMATIC: Jurnal Pendidikan Informatika M A T H L I N E : Jurnal Matematika dan Pendidikan Matematika Journal of Information Systems and Informatics Jurnal Informa: Jurnal Penelitian dan Pengabdian Masyarakat MEANS (Media Informasi Analisa dan Sistem) Jurnal Teknik Informatika (JUTIF) Journal of Electrical Engineering and Computer (JEECOM) Information System Journal (INFOS) SmartComp Intechno Journal : Information Technology Journal Scientific Journal of Informatics
Anggit Dwi Hartanto, Anggit Dwi
Unknown Affiliation
Humanities Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Education Electrical & Electronics Engineering Energy Engineering Environmental Science Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Mathematics Social Sciences Other

Published : 32 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 32 Documents
Search

 1   2   3   4 
Object Detection with YOLOv8 and Enhanced Distance Estimation Using OpenCV for Visually Impaired Accessibility Syahrudin, Erwin; Utami, Ema; Hartanto, Anggit Dwi
JOIV : International Journal on Informatics Visualization Vol 9, No 2 (2025)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/joiv.9.2.2826

Abstract

Accessibility challenges for the visually impaired are getting more serious yearly. To address this issue, this study presents an advanced object detection system that utilizes YOLOv8, enhanced with OpenCV for distance estimation. The methodology involves data preparation with diverse scenarios to test system accuracy, including environments like busy streets and indoor settings. Precision, recall, and F1-score metrics evaluate performance under varying lighting conditions. Results show a decrease in performance during low-light conditions, emphasizing the need for adequate lighting for effective detection. The system also includes a real-time implementation with a panic button feature, allowing immediate activation of object detection and distance estimation processes. The results are translated into Indonesian using a translation service and converted to speech, making the information accessible to users. By integrating YOLOv8 and OpenCV, the research achieves an average object detection accuracy of 91% with a low error rate of about 3.6%. Rigorous testing and evaluation under various conditions ensure reliability and effectiveness. The implications of this research extend to real-time applications like navigation assistance for the visually impaired, highlighting the potential for improved quality of life and independence. Future work will focus on optimizing detection in low-light conditions, incorporating additional sensors like infrared cameras, and enhancing real-time text translation services for accurate information delivery to visually impaired users. Additionally, continuous training with diverse datasets will be conducted further to improve the robustness and accuracy of the detection system.
Augmentation for Accuracy Improvement of YOLOv8 in Blind Navigation System Syahrudin, Erwin; Utami, Ema; Hartanto, Anggit Dwi
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 8 No 4 (2024): August 2024
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v8i4.5931

Abstract

This study addresses the critical need for enhanced accuracy in YOLOv8 models designed for visually impaired navigation systems. Existing models often struggle with consistency in object detection and distance estimation under varying environmental conditions, leading to potential safety risks. To overcome these challenges, this research implements a rigorous approach combining data augmentation and meticulous model optimization techniques. The process begins with the meticulous collection of a diverse dataset, essential for training a robust model. Subsequent preprocessing of images in the HSV color space ensures standardized input features, crucial for consistency in model training. Augmentation techniques are then applied to enrich the dataset, enhancing model generalization and robustness. The YOLOv8 model is trained using this augmented dataset, leading to significant enhancements in key performance metrics. Specifically, mean average precision (mAP) improved by 13.3%, from 0.75 to 0.85, precision increased by 10%, from 0.80 to 0.88, and recall rose by 10.3%, from 0.78 to 0.86. Further optimization efforts, including parameter tuning and the strategic integration of a Kalman Filter, notably improved object tracking and distance estimation capabilities. Final validation in real-world scenarios confirms the efficacy of the optimized model, demonstrating its readiness for practical deployment. This comprehensive approach showcases tangible advances in navigational assistance technology, significantly improving safety and reliability for visually impaired users.
Comparative analysis of YOLOv8 techniques: OpenCV and coordinate attention weighting for distance perception in blind navigation systems Utami, Ema; Syahrudin, Erwin; Hartanto, Anggit Dwi
International Journal of Electrical and Computer Engineering (IJECE) Vol 15, No 3: June 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijece.v15i3.pp3267-3278

Abstract

Blindness is a very important issue to consider in research aimed at assisting vision. This condition requires further study to provide solutions for the blind. This study evaluates and compares the effectiveness of the you only look once v8 (YOLOv8) model integrated with OpenCV and the coordinate attention weighting (CAW) technique for distance estimation in a blind navigation system. Initially, YOLOv8 integrated with OpenCV produced less than optimal results, prompting further improvement efforts to surpass the performance of CAW. The goal is to enhance the accuracy and efficiency of distance perception without the need for additional sensors. The materials used include a variety of datasets annotated with distance information to train and evaluate the model. The methods employed include integrating YOLOv8 with OpenCV for baseline comparison and applying CAW to improve distance perception through enhanced feature attention. The results show that YOLOv8+OpenCV Improved achieves the lowest mean squared error (MSE) across the entire distance range: 0-1 m (0.44), 1-2 m (0.50), 2-3 m (0.58), 3-4 m (0.64), and 4-5 m (0.71). YOLOv8+CAW also outperforms YOLOv8+OpenCV original, demonstrating a notable enhancement in accuracy. The model achieves a detection accuracy of 95.7%, showcasing the effectiveness of computer vision techniques in supporting blind navigation systems, offering precise distance estimation capabilities and reducing the reliance on external sensors. The implications include improved real-time performance and accessibility for the blind, paving the way for more efficient and reliable navigation assistance technologies.
Perbandingan Algoritma Naïve Bayes dan K-Nearest Neighbor dalam Menentukan Kriteria Masyarakat Miskin Santoso, Arif; Utami, Ema; Hartanto, Anggit Dwi
Jurnal Informa : Jurnal Penelitian dan Pengabdian Masyarakat Vol 8 No 1 (2022): Juni
Publisher : Politeknik Indonusa Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46808/informa.v8i1.211

Abstract

Mewabahnya Virus Covid-19 memberikan dampak yang sangat besar dibidang ekonomi. Melemahnya ekonomi masyarakat menjadi permasalahan serius yang sangat perlu segera diatasi. Dalam upaya pemulihan ekonomi, pemerintah mengeluarkan kebijakan-kebijakan untuk pengentasan ekonomi antara lain penyaluran BLT. Akan tetapi kebijakan tersebut justru menimbulkan masalah baru yaitu penyaluran yang tidak tepat sasaran. Hal ini menibulkan gejolak dimasyarakat. Penelitian ini bertujuan untuk mengklasifikasikan data sesuai dengan kriteria dan memperoleh hasil terbaik dua metode yang akan digunakan. Penlitian ini menggunakan dua algoritma Naïve Bayes dan K-Nearest Neighbor dengan data yang diperoleh dari Data terpadu kesejahteraan Sosial (DTKS) dengan dua variabel yaitu mampu dan miskin. Hasil klasifikasi dengan dua algoritma Naïve Bayes dan K-Nearset Neighbor diperoleh hasil masing-masing 72.64% dan 95.40% dengan nilai AUC 0.836 dan 0.877. Berdasarkan nilai AUC yang diperoleh kedua algoritma tingkat akurasi termasuk good classification. Algoritma K-Nearset Neighbir lebih baik dalam klasifikasi masyarakat miskin dibandingkan algoritma Naïve Bayes dengan akurasi 95.40% dan nilai AUC 0.877.
Analisis Sentimen Terhadap Tokoh Publik Menggunakan Support Vector Machine Fitriyani, Nurul Khasanah; Hartanto, Anggit Dwi
MEANS (Media Informasi Analisa dan Sistem) Volume 5 Nomor 1
Publisher : LPPM UNIKA Santo Thomas Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (683.29 KB) | DOI: 10.54367/means.v5i1.615

Abstract

Anies Baswedan adalah seorang gubernur DKI Jakarta yang menjabat pada masa bakti 2017-2022. Pada bulan Desember 2019 ini nama Anies Baswedan hangat diperbincangkan di berbagai media karena pemberian penghargaan Adikarya Wisata 2019 sebuah diskotek yaitu ke Diskotek Colosseum meskipun pada akhirnya penghargaan tersebut dicabut kembali. Namanya juga hangat diperbincangkan karena dianggap cuci tangan setelah mencopot dua pejabat karena dua masalah yang berbeda. Kemudian juga mengenai masalah banjir yang terjadi di Jakarta, namanya juga disebut belum bisa menangani dengan baik banjir yang selalu terjadi di Jakarta. Media twitter memiliki tampilan simpel, topik terupdate, terbuka dalam mengakses tweet dan cepat dalam menyampaikan opini. Dari berbagai komentar dan tanggapan di Twitter diperlukan teknik untuk membagi ke dalam kelas opini negatif atau positif. Penelitian ini, menggunakan preprocessing dan melabeli opini kedalam kelas positif dan negatif. Sedangkan untuk klasifikasinya menggunakan metode Support Vector Machine. Data yang digunakan berupa opini tentang seseorang Anies Baswedan dari media sosial Twitter yang berjumlah 1000 tweet yang diambil pada tanggal 17 Desember 2019. Dari hasil pelabelan didapatkan banyaknya komentar positif berjumlah 429 dan yang berkomentar negatif berjumlah 530. Sedangkan klasifikasi metode Support Vector Machine mendapatkkan nilai akurasi sebesar 95,9%, nilai presisis sebesar 94,49%, dan nilai recall sebesar 96,4%.
Analysis of the Similiarity Level of Source Code in the Kotlin Programming Language using Winnowing Algorithm Astica, Yustikamasy; Utami, Ema; Hartanto, Anggit Dwi
International Journal of Artificial Intelligence Research Vol 7, No 1 (2023): June 2023
Publisher : Universitas Dharma Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29099/ijair.v7i1.902

Abstract

Plagiarism is an act of imitating the work of others directly or indirectly. In an academic environment, plagiarism applies not only to textual documents but also to source code documents. Source code plagiarism in academia usually occurs when students copy another student's code and submit it as if it were the student's work. So that an automatic plagiarism check is needed, the winnowing algorithm will be used to help detect similarities in source code as a way to detect an act of plagiarism. The Winnowing algorithm, which is usually used to detect document plagiarism, this research detects the source code. The results produced in this study are that the degree of similarity in the two source codes will produce different similarity values if the dataset used has gone through the text preprocessing stage or without preprocessing. If the dataset has gone through the text preprocessing stage, the similarity value will be pretty low because the number of characters used is significantly reduced. The Winnowing and Jaccard Similarity algorithms quickly detect plagiarism in source code and can be used to minimize plagiarism.
Modifikasi Fonem Vokal Pada Stemming Kata Tidak Baku Iskandar, Ahmad Fikri; Utami, Ema; Hidayat, Wahyu; Budi, Agung Prasetio; Hartanto, Anggit Dwi
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 10 No 1: Februari 2023
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jtiik.2023105028

Abstract

Bahasa Indonesia termasuk bahasa yang paling populer digunakan di dunia. Bahasa Indonesia dapat berupa bahasa baku dan tidak baku. Bahasa tidak baku dapat dikarenakan oleh penyerapan dari bahasa asing atau bahasa daerah. Penyerapan ini dapat terjadi perganti huruf vokal. Kontribusi pada penelitian ini adalah melakukan modifikasi fonem pada huruf vokal untuk mengembalikan kata tidak baku ke dalam bentuk kata dasar yang baku disebut sebagai Modified Vocal Phonemes Non Formal. Percobaan dilakukan dengan 60 kata tidak baku yang sudah dilakukan preprocessing pada penelitian sebelumnya terlebih dahulu. Penelitian ini membandingkan hasil algoritma dengan algoritma pada penelitian sebelumnya. Algoritma Modified Vocal Phonemes Non Formal telah berhasil melakukan stemming dengan presisi 90.00% dengan 54 kata tidak baku yang sukses dikonversi ke kata dasar sesuai dengan Kamus Besar Bahasa Indonesia (KBBI) dan 6 kata masih belum berhasil dikonversi. AbstractIndonesian is one of the most popular languages spoken in the world. Indonesian can be standard and non-standard language. Non-standard language can be caused by absorption of foreign languages or village languages. This absorption can occur as a substitute for vowels. The contribution to this research is to modify the phonemes of vowels to return non-formal words into formal root forms known as Modified Vocal Phonemes in Non-Formal. The experiment was carried out with 60 non-formal words that have been preprocessed in the previous research. This research will compare the results of the algorithm with the algorithm in previous research. Algorithm Modified Vocal Phenomes Non-Formal has succeeded in performing stemming with 90.0% precision with 54 words that were successfully converted to base words according to the Big Indonesian Dictionary and 6 words were still not converted.
Studi Literatur Mengenai Klasifikasi Citra Kucing Dengan Menggunakan Deep Learning: Convolutional Neural Network (CNN) Linda, Kumara Dewi; Kusrini, Kusrini; Hartanto, Anggit Dwi
Journal of Electrical Engineering and Computer (JEECOM) Vol 6, No 1 (2024)
Publisher : Universitas Nurul Jadid

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33650/jeecom.v6i1.7480

Abstract

Deep learning merupakan bagian dari machine learning yang memiliki kemampuan untuk mengenali pola gambar, suara, teks dan data lainnya yang kompleks sehingga dapat menghasilkan prediksi yang akurat. Salah satu kemampuan deep learning adalah klasifikasi citra pada objek. CNN adalah salah satu metode dalam machine learning yang digunakan untuk mengklasifikasikan citra objek. Algoritma Convolutional Neural Network (CNN) adalah bagian dari deep learning network yaitu jenis jaringan saraf tiruan yang saat ini banyak digunakan untuk pengenalan suatu citra. Dalam penelitian ini, algoritma yang digunakan adalah CNN karena akurasinya yang cukup baik. Deep learning dengan convolutional neural network (CNN) yang banyak digunakan untuk melakukan deteksi, klasifikasi, dan prediksi pada gambar. Citra objek dalam penelitian ini adalah kucing yang terdiri dari berbagai macam jenis. Tujuan dari penelitian ini adalah untuk mengklasifikasikan citra kucing sesuai dengan jenisnya. Jurnal ini merupakan tinjauan literatur untuk menambah pengetahuan berharga mengenai penelitian terbaru tentang klasifikasi citra kucing menggunakan CNN. Jurnal ini membahas studi literatur tentang variabel input, metode yang digunakan dan hasil literatur dari penelitian sebelumnya. Metode yang paling banyak digunakan pada penelitian sebelumnya adalah CNN
COMPARISON OF ACCURACY LEVELS OF RANDOM FOREST AND K-NEAREST NEIGHBOR (KNN) ALGORITHMS FOR CLASSIFYING SMOOTH BANK CREDIT PAYMENTS Aji Santoso, Bayu; Kusrini, Kusrini; Hartanto, Anggit Dwi
Jurnal Teknik Informatika (Jutif) Vol. 5 No. 1 (2024): JUTIF Volume 5, Number 1, February 2024
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2024.5.1.1195

Abstract

Providing credit is one of the bank offers offered to customers, but extending credit to customers who are not appropriate can cause problems such as customers who do not pay installments on time and even delay payment of installments for several months until bad credit occurs so that this can be detrimental to the bank. Therefore, in this study a comparative method will be carried out to find out which method is the best in classifying the smoothness of bank credit payments. It is hoped that the results of the research can be used as material for consideration by the bank in the selection of bank credit customers. In this study using a dataset from the UCI Machine Learning Repository, the credit payment data totaled 29,998. The dataset is split by dividing 70% train data and 30% test data with the amount of each data, namely 24000 train data and 6000 test data. Meanwhile, the labels used are Eligible and Ineligible. In this study, implementing the data mining process using the CRISP-DM framework and using the Python programming language. From the results of the evaluation using the confusion matrix, the best accuracy value was obtained for the random forest algorithm, namely 82.22%, precision of 80.44%, recall of 82.22% and f1-score of 80.0%. Meanwhile, the KNN algorithm obtains an accuracy value of 81.55%, a precision of 79.5%, a recall of 81.55% and an f1-score of 79.11%. Based on the results of this evaluation, the Random Forest algorithm has the best accuracy compared to the KNN algorithm in classifying bank credit payments.
Comparative Performance of SVM and Multinomial Naïve Bayes in Sentiment Analysis of the Film 'Dirty Vote' Iedwan, Aisha Shakila; Mauliza, Nia; Pristyanto, Yoga; Hartanto, Anggit Dwi; Rohman, Arif Nur
Scientific Journal of Informatics Vol. 11 No. 3: August 2024
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v11i3.10290

Abstract

Purpose: The purpose of this research is to analyze and compare the performance of two machine learning models, Support Vector Machine (SVM) and Multinomial Naive Bayes, in conducting sentiment analysis on YouTube comments related to the film "Dirty Vote." Methods: The study involved collecting YouTube comments and preprocessing the data through cleaning, labeling, and feature extraction using TF-IDF. The dataset was then divided into training and testing sets in an 80:20 ratio. Both the SVM and Multinomial Naive Bayes models were trained and tested, with their performance evaluated using accuracy, precision, recall, and F1-score metrics. Result: The results revealed that both models performed well in classifying sentiments, with SVM slightly outperforming Multinomial Naive Bayes in terms of accuracy and precision. Particularly, SVM showed superior performance in detecting positive comments, making it a more reliable model for this specific sentiment analysis task. Novelty: This study contributes to the field of sentiment analysis by providing a detailed comparative analysis of SVM and Multinomial Naive Bayes models on YouTube comments in the context of an Indonesian film. The findings highlight the strengths and weaknesses of each model, offering insights into their applicability for sentiment analysis tasks, particularly in analyzing social media content. This research also suggests potential future directions, including the exploration of advanced NLP techniques and different models to enhance sentiment analysis performance.
Co-Authors Adiatma, Biva Candra Lutfi Aji Santoso, Bayu Ananda, Fadhilah Dwi arif nur rohman Arif Santoso Astica, Yustikamasy ATIK NURMASANI Budi, Agung Prasetio Christyawan, Fajar Ema Utami Fajri, Ika Nur Febriyanti, Nada Rizki Fiardin, Tsintani Tisaga Fitriyani, Nurul Khasanah Hartatik Hedy Leoni Hendrawan, Ivan Rifky Hidayat, Jati Arif Iedwan, Aisha Shakila Iskandar, Ahmad Fikri Julianto, M. Rayhan Wahyu Kencana, Adi Kresna Khairullah, Irfan Khalil Kurniawan, Aas Andri Kurniawan, Febri Dwi Kusnawi Kusnawi Kusrini Linda, Kumara Dewi Mauliza, Nia Pratama, Jibran Yoga Purwoko, Joshua Dwi Giovani Ramadhan, Muhammad Jauharul Ramadhani, Zanuarestu Rasyid, Muhammad Khulqi Safira, Livia salisah, Tuhfatus Sari, Bunga Permata Setiadi F., A. Farhan Setiawan, Annas Setiawanda, Yongky Budi Syahrudin, Erwin Tara, Yudi Tuhpatussania, Siti Wahyu Hidayat wahyuni, wenti ayu Wasistha, Dyah Wicaksono, Anggito Whiku Wisnu Nugroho Aji, Wisnu Nugroho Yoga Pristyanto Yulianto, Yogi Yusa, Aldo