Article Per Year (5 Year)
p-Index From 2021 - 2026
7.884
P-Index
This Author published in this journals
All Journal IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Jurnal Sains dan Teknologi Jurnal Buana Informatika Jurnal Edukasi dan Penelitian Informatika (JEPIN) JUITA : Jurnal Informatika Jurnal Sistem dan Informatika Journal of Information Systems Engineering and Business Intelligence E-Dimas: Jurnal Pengabdian kepada Masyarakat Format : Jurnal Imiah Teknik Informatika JOIV : International Journal on Informatics Visualization Tech-E Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Jurnal ULTIMA InfoSys Jurnal ULTIMATICS ComTech: Computer, Mathematics and Engineering Applications Jurnal Teknologi Komputer dan Sistem Informasi bit-Tech eCo-Buss Jurnal Informatika dan Rekayasa Perangkat Lunak Jurnal TIKOMSIN (Teknologi Informasi dan Komunikasi Sinar Nusantara) International Journal of Digital Entrepreneurship and Business (IDEB) Algor eCo-Fin Abdi-Dharma SATIN - Sains dan Teknologi Informasi Inovasi Gagasan Abdimas & Kuliah Kerja Nyata RUBINSTEIN JTKSI (Jurnal Teknologi Komputer dan Sistem Informasi)
Aditiya Hermawan
Universitas Buddhi Dharma
Agriculture, Biological Sciences & Forestry Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Environmental Science Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Materials Science & Nanotechnology Mathematics Social Sciences Other

Published : 60 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 60 Documents
Search

 2   3   4   5   6 
Implementasi Text-Mining untuk Analisis Sentimen pada Twitter dengan Algoritma Support Vector Machine Hermawan, Aditiya; Jowensen, Indrico; Junaedi, Junaedi; Edy
JST (Jurnal Sains dan Teknologi) Vol. 12 No. 1 (2023): April
Publisher : Universitas Pendidikan Ganesha

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23887/jstundiksha.v12i1.52358

Abstract

Setiap tahun, jumlah orang yang menggunakan media sosial bertambah seiring dengan jumlah orang yang menggunakan internet. Peningkatan tersebut diiringi dengan meningkatnya informasi pada internet yang tentunya informasi tersebut mempunyai nilai jika dilakukan analisa. Untuk menganalisa data dalam jumlah besar dapat menggunakan teknik text mining. Text mining mampu memproses untuk memperoleh informasi berkualitas tinggi dari teks. Text mining juga dapat digunakan untuk menganalisa informasi seperti sentimen dari sebuah kalimat dengan sangat cepat untuk memudahkan dalam mendapatkan informasi yang berkualitas. Informasi diproses berasal dari media sosial berbasis text yaitu twitter yang mana pengambilan data dilakukan dengan bantuan Application Programming Interface dan menggunakan kata kunci berupa sebuah kata atau hashtag. Kalimat tersebut akan dilakukan proses text mining dengan menggunakan algoritma Support Vector machine untuk menghasilkan klasifikasi dari sentimen suatu kalimat ke dalam sentiment positif, netral atau negatif. Tingkat akurasi yang dihasilkan oleh proses ini adalah sebesar 73% berdasarkan data sentimen yang dimiliki. Tingkat akurasi dalam melakukan text mining sangat dipengarui pada proses Pre-Processing karena terdapat banyak kata perlu dilakukan pengelolahan lebih lanjut.
Optimization of Multimodal Deep Learning for Depression Detection Hermawan, Aditiya; Daniawan, Benny; Edy, Edy; Nathaniel, Joese
IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Vol 19, No 4 (2025): October
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ijccs.111407

Abstract

Depression is a complex and often underdiagnosed mental health condition that manifests through subtle verbal, acoustic, and behavioral cues. Traditional unimodal detection systems struggle to capture the full spectrum of depressive symptoms, often leading to inaccurate or incomplete assessments. This study proposes a multimodal deep learning framework that integrates textual, audio, and visual modalities to improve the robustness and reliability of automatic depression detection, achieving an overall classification accuracy of 74%. The approach prioritizes privacy and interpretability by using facial keypoints and gaze direction rather than raw video frames, and applies attention mechanisms to align and fuse features across modalities. Each modality is processed through dedicated neural architectures tailored to its data type, and their outputs are combined within a fusion model that learns to capture cross-modal emotional patterns. Experimental results demonstrate that the proposed multimodal system significantly outperforms its unimodal counterparts in terms of classification performance. The visual modality was found to contribute most strongly to detection accuracy, as confirmed by ablation analysis. These findings highlight the value of multimodal integration in capturing complex psychological signals and support the development of intelligent, non-invasive screening tools for use in digital mental health applications.
Optimizing Artificial Neural Network for Customer Churn: Advanced Data Balancing and Feature Selection Hermawan, Aditiya; Wijaya, Willy; Daniawan, Benny
JOIV : International Journal on Informatics Visualization Vol 9, No 3 (2025)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/joiv.9.3.3064

Abstract

Customers are valuable assets in the dynamic business world. However, service dissatisfaction often leads them to switch to competitors, a phenomenon known as customer churn. In the telecommunications industry, churn poses a significant challenge as it directly impacts revenue and influences other customers within their social networks to do the same. Consequently, predicting churn has become essential, with numerous researchers employing various methods to classify potential churners. This study builds upon prior research that utilized Artificial Neural Networks (ANN) or Deep Learning to predict churn, achieving an accuracy of 88.12%. To improve model performance, this research implements an Artificial Neural Network (ANN) as the primary algorithm, along with Random Over-Sampling (ROS) and Synthetic Minority Oversampling Technique (SMOTE) for data balancing, and three feature selection methods: Minimum Redundancy Maximum Relevance (mRMR), Lasso Regression, and XGBoost. The results demonstrate a 0.38% increase in accuracy compared to previous studies. The finding suggests opportunities for further exploration. Future studies can consider alternative feature selection techniques, such as Wrapper Methods or Heuristic/Metaheuristic approaches, which may produce more optimal feature combinations. Other data balancing methods, such as Undersampling techniques (e.g., Random Undersampling, Tomek Links) or Hybrid Methods (e.g., SMOTE combined with Tomek Links), could be explored to address imbalanced datasets effectively. These approaches are expected to provide better combinations and to improve overall prediction performance, enabling researchers to develop more robust and accurate models for customer churn prediction in subsequent studies.
Optimasi Penyediaan Internet Murah Dengan Kecepatan Yang Baik Guna Media Pembelajaran Jarak Jauh Riki, Riki; Yanti, Lia Dama; Oktari, Yunia; Hermawan, Aditiya; Kurnia, Yusuf; Giap, Yo Ceng; Aprilyanti, Rina
Abdi Dharma Vol. 1 No. 2 (2021): Jurnal Abdi Dharma (Jurnal Pengabdian Masyarakat)
Publisher : LP3kM Universitas Buddhi Dharma

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (259.707 KB) | DOI: 10.31253/ad.v1i2.699

Abstract

Kesadaran pendidikan secara umum, kemampuan panduan teknologi dan kemampuan pembelajaran online masih rendah, sehingga menyulitkan orang tua dan siswa (terutama siswa sekolah dasar) guna menggunakan fasilitas teknologi dan memperoleh informasi dari pembelajaran. Berdasarkan paparan di atas, berikut beberapa permasalahan yang dapat diidentifikasi: 1) Tidak semua warga di lingkungan RT 06 RW 07 Griya Sangiang Mas memiliki fasilitas Internet yang cepat dan murah. Sebagai warga dan pendidik, kami berinisiatif menyediakan fasilitas internet murah dan cepat kemudian memberikan pelatihan. Secara umum kegiatan ini telah berlangsung selama 1 tahun, dan terdapat pengguna aktif pembelajaran sebanyak 15 siswa SD dan SMP setiap harinya. Secara umum bagi warga Perumahan Griya Sangiang Mas, Internet di RT ini bisa menjadi alternatif internet yang murah
Pelatihan Desain Slide dengan Canva Junaedi; Wydiastuty Kusuma, Lianny; Ceng Giap, Yo; Suwitno; Hermawan, Aditiya; Rino; Daniawan, Benny; Riki
Abdi Dharma Vol. 2 No. 2 (2022): Jurnal Abdi Dharma (Jurnal Pengabdian Masyarakat)
Publisher : LP3kM Universitas Buddhi Dharma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31253/ad.v2i2.1737

Abstract

Perkembangan di era sekarang banyak sekali perubahan dari segi teknologi. Perkembangan teknologi ini meliputi desain grafis, pemrograman, aplikasi dan sebagainya. Hal inilah yang membuat penulis sebagai pendidik untuk melakukan pengabdian kepada masyarakat dengan cara melakukan sebuah workshop dengan tema “Pelatihan Desain Slide dengan Canva” yang bertujuan untuk memperkenalkan membuat sebuah desain pada slide presentasi dengan baik, rapih dan interaktif sebagai media penyampaian pembelajarannya. Pelatihan Desain Slide dengan Canva ini juga didukung oleh Universitas Buddhi Dharma sebagai tempat dilaksanakannya pelatihan ini. Para peserta dari Pelatihan Desain Slide dengan Canva ini diikuti oleh para romo dan rahmani dari Magabudhi Kota Tangerang. Hasil dari pelatihan ini akan di implementasikan dalam pembuatan presentasi sebagai media pembelajaran.
Penyuluhan E-Commerce untuk Mendorong Ekonomi Digital Dalam Rangka Pengabdian Kepada Masyarakat pada Pemuda Tridharma Indonesia Cabang Wihara Dharma Pala Kurnia, Yusuf; Riki; Giap, Yo Ceng; Hermawan, Aditiya; Gustayo, Teven
Abdi Dharma Vol. 3 No. 1 (2023): Jurnal Abdi Dharma (Jurnal Pengabdian Masyarakat)
Publisher : LP3kM Universitas Buddhi Dharma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31253/ad.v3i1.2069

Abstract

Perkembangan teknologi informasi di era revolusi 4.0 memberikan dampak yang signifikan terhadap perekonomian Indonesia. Platform digital dalam mendukung kegiatan perekonomian dan pemenuhan kebutuhan masyarakat bertumbuh dengan cepat dengan dukungan internet. dengan diterapkannya teknologi baru akan berdampak pada produkvitas dan menurunkan biaya produksi yang akan meningkatkan daya beli sehingga akan tercipta lapangan kerja baru. Metode kegiatan Pengabdian Kepada Masyarakat ini dilakukan melalui 4 tahapan (metode) yaitu metode sosialisasi, metode demonstrasi, metode praktek/latihan, evaluasi kegiatan. Pelaksanaan PkM ini melibatkan mitra kerjasama, yaitu Wihara Dharma Pala yang beralamat di Jl. Ir. Soekarno Kp, Jl. Raya Rawa Kompeni No.66, RT.003/RW.008, Benda, Kec. Benda, Kota Tangerang, Banten 15125. Tim pelaksana kegiatan Pengabdian kepada Masyarakat (PkM) terdiri dari 4 orang dosen & 1 orang mahasiswa. Tim dosen pelaksana Pkm terdiri atas dosen-dosen yang memiliki keterampilan & kemampuan dibidang teknologi informasi yang sesuai dengan tema PkM yang dilaksanakan serta memiliki kualifikasi akademik. Dari hasil hasil evaluasi yang dilakukan oleh Tim Pelaksana, dapat disimpulkan hal bahwa mayoritas peserta yang mengikuti kegiatan ini, sudah mengetahui tentang E-Commerce dan peserta masih kurang pengalaman dalam menggunakan layanan E-commerce seperti Market Place.
Optimization of CNN and Vision Transformer Models in Addressing Long-Tailed Data Imbalance for Satellite Cloud Image Classification Nandivadhano, Revatta Manggala; Aditiya Hermawan; Lidya Lunardi
Tech-E Vol. 9 No. 2 (2026): TECH-E (Technology Electronic)
Publisher : Fakultas Sains dan Teknologi-Universitas Buddhi Dharma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31253/te.v9i2.4256

Abstract

This study investigates long-tailed satellite cloud image classification by comparing CNN and Vision Transformers (ViT) built upon vision–language foundation models. A large-scale satellite cloud dataset with 11 highly imbalanced classes, including a dominant non-phenomenon category, is used to represent realistic atmospheric variability. The data are split using stratified sampling, standardized to a fixed resolution, and used to fine-tune CLIP-based backbones from RemoteCLIP and GeoRSCLIP through parameter-efficient adaptation. Several loss functions Cross Entropy, Logit Adjustment, Focal, Class-Balanced, and label-distribution–aware variants are evaluated, along with experiments examining majority-class removal and adapter bottleneck adjustments. Initial results show that Logit Adjustment causes majority-class collapse under default settings. After optimization, ViT-based models consistently outperform CNN models, achieving higher accuracy and more balanced macro-level performance. Class-Balanced loss emerges as the most effective objective, offering a strong trade-off between overall accuracy and per-class fairness. Increasing the adapter bottleneck dimension further boosts ViT performance, enabling the best configuration to match or exceed prior benchmarks while improving minority-class recognition. The final optimized model is deployed in a web-based prediction system, demonstrating the practical potential of foundation-model approaches for satellite-driven weather analysis.
Optimizing Virtual Culinary Tours Using Character-based Interaction and Finite State Machine (FSM) Margaretha Natalya; Aditiya Hermawan; Riki Riki
bit-Tech Vol. 7 No. 2 (2024): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v7i2.1886

Abstract

This research focuses on the development of a Virtual Tour application utilizing Finite State Machine (FSM) to enhance the interaction of a Non-Playable Character (NPC) as a tour guide in a 3D virtual environment. The primary issue addressed is the significant impact of the COVID-19 pandemic on the tourism industry, which led to travel restrictions and limited opportunities for visitors to explore tourist destinations physically. The aim of the study is to create a virtual tourism experience as an alternative solution, enabling users to explore historical sites like Pasar Lama Tangerang remotely through Google Cardboard VR. To achieve this, the NPC’s behavior is controlled using FSM, allowing the character to transition between states—idle, walking, and talking—based on user interactions. Data was collected through user testing with a Likert scale questionnaire, evaluating user satisfaction and the effectiveness of the FSM method. The results revealed a 74.35% positive user rating, categorized as Good, demonstrating the potential of FSM to provide an interactive, engaging, and educational virtual tour experience. These findings highlight the effectiveness of FSM in creating a dynamic and user-responsive virtual tour, offering significant benefits to the tourism sector by providing an innovative, accessible, and immersive way for potential visitors to explore destinations during travel restrictions. This research contributes to the growing field of e-tourism, showcasing the potential of virtual reality and FSM to transform the tourism industry in times of crisis.
Enhancing Stock Price Forecasting: Optimizing Neural Networks with Moving Average Data Aditiya Hermawan; Stanley Ananda; Junaedi; Edy; Riki Riki
bit-Tech Vol. 7 No. 3 (2025): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v7i3.2196

Abstract

This research focuses on optimizing a neural network model for stock price prediction using Particle Swarm Optimization (PSO), considering the inherent risks and potential high returns associated with stock investment. Given the challenges posed by stock price volatility, this study combines Moving Average (MA) a fundamental statistical technique in stock market analysis with advanced data mining approaches, specifically neural networks and PSO, to enhance prediction accuracy. The primary objective is to improve the efficiency of neural networks by minimizing error rates and equipping investors with more reliable tools for financial decision-making. The proposed methodology involves converting historical stock price data into a Simple Moving Average (SMA) over a 5-day period, followed by optimizing a neural network model using PSO. This optimization process fine-tunes key parameters, particularly the weight distributions of various stock market indicators, including Open SMA, High SMA, Low SMA, and Close SMA. Model performance is evaluated using Root Mean Square Error (RMSE) as a validation metric. The findings indicate a significant enhancement in the predictive accuracy of the neural network model after PSO optimization. The optimal configuration is identified in a two-layer neural network with a specific node arrangement. This optimized model not only improves stock price forecasting precision but also has practical implications for investors and financial analysts in risk management and profit maximization.
Evaluating Latent Emotional Structures through Unsupervised Semantic Text Clustering Edy, Edy; Junaedi, Junaedi; Hermawan, Aditiya; Kurnia, Yusuf; Maranto, Ardiane Rossi Kurniawan
IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Vol 20, No 2 (2026): April
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ijccs.116764

Abstract

Emotion analysis in textual data is an important topic in natural language processing, as emotions play a crucial role in understanding public opinion, psychological states, and dynamics of digital interaction. However, most existing studies rely heavily on supervised classification approaches based on predefined emotion labels, which may overlook latent semantic structures and emotional overlap inherent in natural language. This study aims to evaluate latent emotional structures in text using an unsupervised semantic clustering approach. The proposed method involves text preprocessing, feature representation using Term Frequency–Inverse Document Frequency (TF–IDF), dimensionality reduction through Singular Value Decomposition (SVD), and clustering using K-Means and Hierarchical Agglomerative algorithms. Both internal and post-hoc external evaluation metrics are employed to assess cluster quality and examine their correspondence with available emotion labels. The results indicate that K-Means clustering produces more compact and interpretable clusters than the hierarchical approach, while both methods reveal substantial emotional overlap across clusters. These findings suggest that emotional expressions in text exhibit a continuous semantic structure rather than discrete categorical boundaries. This study highlights the importance of unsupervised semantic clustering as an analytical tool for gaining deeper insight into latent emotional patterns in textual data.
Co-Authors A Damiyati Abidin Abidin Adith Aulia Rahman Agus Setiawan Alvin Rahayu Amin Suyitno Andre Sahulata Andri Wijaya Andrie Suak Tiwa Anton Halim Anwan Chailes Aprilyanti, Rina Ardiane Rossi Kurniawan Maranto Ardie Halim Arvin Lawistra Benny Daniawan Berlian, Pio Putra Budi Susilo Ceng Giap, Yo Culadi, Rafael Daniel Daniawan, Benny Dera Susilawati Deviastati Putri Sugiarta Karlim edy Edy Edy Edy Edy Edy Edy Edy Ellysha Dwiyanthi Kusuma Eva Eva Evan - Evien Fadeli Muhammad Habibie Fernando, Albert Gustayo, Teven Halim Wijaya, Ardie Hargiani, Fransisca Xaveria Hartana Wijaya Henry Henry Indrawan Intan Anjali Putri Jelvin Putra Halawa Jessen Laorenza Suwandi Joese Nathaniel Johan Santoso Jowensen, Indrico JUNAEDI Junaedi Junaedi Junaedi Kevin Ivone Sim Kevin Kevin Khanti Kusuma Dewi Kumala, Sonya Ayu Kurniawan Maranto, Ardiane Rossi Leonardo Lianata Lianny Wydiastuty Lianny Wydiastuty Kusuma Lidya Lunardi Luis Alpianto Lunardi, Lidya Mampow, Vanessa Keysa Immanuela Maranto, Ardiane Rossi Kurniawan Margaretha Natalya Mariana Purnamasari Mesakh Septiadi Simijaya michael vernannes marpaung Nandivadhano, Revatta Manggala Nathaniel Felix Fraderic Nathaniel, Joese Nazzua Azzahra Niki Destiandi Oscar Hasan Putra Philip Kristy Wijaya Qurrohman, Taufik Raditya Rimbawan O Raditya Rimbawan Oprasto Ramadhani, Tyas Ayu Rheza Vincentius Riki Riki Riki RIKI RIKI, RIKI Rino Rossi Kurniawan Maranto, Ardiane Rossi Salman Alfarisi Samuel Rhesa Santa Margita Sevtian Ferdian Shofa, Ghina Zahira Siska Damayanti Stanley Ananda Sutopo, Prihantoro Syahdu Suwitno Tia Nurapriyanti Wicaksono, Baghas Budi Willy Wijaya, Willy Wiyono Wydiastuty Kusuma, Lianny Yan Everhard Riwurohi Yance Gusnadi Yanti, Lia Dama Yo Ceng Giap Yo Ceng Giap Yuliastati Putri Sugiarta Karlim Yunia Oktari Yusuf Kurnia Yusuf Kurnia, Yusuf