Claim Missing Document
Check
Articles

Found 10 Documents
Search

Real Time Face Recognition using Eigenface and Viola-Jones Face Detector Jacky Efendi; Muhammad Ihsan Zul; Wawan Yunanto
JOIV : International Journal on Informatics Visualization Vol 1, No 1 (2017)
Publisher : Politeknik Negeri Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1225.551 KB) | DOI: 10.30630/joiv.1.1.15

Abstract

Authentication is the process of verifying one’s identity, and one of its implementation is in taking attendances in university’s lectures. Attendance taking is a very important matter to every academic institution as a way to examine students’ performance. Signature based attendance taking can be manipulated. Therefore it has problems in verifying the attendance validity. In this final project, a real time eigenface based face recognition is implemented in an application to do attendance taking. The input face image is captured using a webcam. The application itself is built in C#, utilizing EmguCV library. The application is developed using Visual Studio 2015. Face detection is done with Viola-Jones algorithm. The eigenface method is used to do facial recognition on the detected face image. In this final project, a total of 8 testings are done in different conditions. From the testings, it is found that this application can recognize face images with accuracy as high as 90% and as low as 6.67%. This solution can be used as an alternative for real-time attendance taking in an environment with 170 lux light intensity, webcam resolution of 320 x 240 pixel, and the subject standing 1 meter away while not wearing spectacles. The average recognition time is 0.18125 ms.
Penambangan pola non-zero-rare sekuensial pada pengenalan aktifitas Mohammad Iqbal; Chandrawati Putri Wulandari; Wawan Yunanto; Ghaluh Indah Permata Sari
Jurnal Matematika MANTIK Vol. 5 No. 1 (2019): Mathematics and Applied Mathematics
Publisher : Mathematics Department, Faculty of Science and Technology, UIN Sunan Ampel Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (434.717 KB) | DOI: 10.15642/mantik.2019.5.1.1-9

Abstract

Discovering rare human activity patterns—from triggered motion sensors deliver peculiar information to notify people about hazard situations. This study aims to recognize rare human activities using mining non-zero-rare sequential patterns technique. In particular, this study mines the triggered motion sensor sequences to obtain non-zero-rare human activity patterns—the patterns which most occur in the motion sensor sequences and the occurrence numbers are less than the pre-defined occurrence threshold. This study proposes an algorithm to mine non-zero-rare pattern on human activity recognition called Mining Multi-class Non-Zero-Rare Sequential Patterns (MMRSP). The experimental result showed that non-zero-rare human activity patterns succeed to capture the unusual activity. Furthermore, the MMRSP performed well according to the precision value of rare activities.
PEMANFAATAN PROCESS MINING PADA E-COMMERCE Wawan Yunanto; Kartina Diah KW
Seminar Nasional Informatika (SEMNASIF) Vol 1, No 1 (2015): Informatika Dalam Pengelolaan Sumber Daya Alam
Publisher : Jurusan Teknik Informatika

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

Abstract

Organisasi menyimpan rekaman aktivitas proses bisnis yang terjadi pada proses di lapangan dalam log data dengan berbagai format. Rekaman aktivitas ini disimpan dalam rangka menghasilkan sebuah model proses bisnis berdasarkan aktivitas pengguna pada proses nyata di lapangan. Dari proses model yang dihasilkan dapat dilakukan analisis tentang kesesuaian antara proses bisnis yang terjadi pada proses nyata di lapangan dengan proses bisnis yang diharapakan oleh organisasi. Analisis ini disebut sebagai conformance checking yang bertujuan untuk mendeteksi deviasi yang terjadi antara proses bisnis yang diharapkan dengan proses bisnis dari proses nyata di lapangan dan sebaliknya. Suatu proses bisnis dikatakan sudah sesuai dengan regulasi (compliant) apabila tidak ada deviasi/nonconformance dalam eksekusinya dari proses bisnis yang telah didefinisikan mengikuti standar.
Desain Sistem Informasi Evaluasi Diri Program Studi Teknik Informatika Politeknik Caltex Riau Juni Nurma Sari; Wawan Yunanto
Seminar Nasional Teknologi Informasi Komunikasi dan Industri 2011: SNTIKI 3
Publisher : UIN Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (265.677 KB)

Abstract

Self Evaluation is part of qualty assurance proses of high education institution. The objective of self evaluation is continous improvement. There are two kind evaluation that is internal evaluation and external evaluation. Internal evaluation done by civitas academica inside department. External evaluation done by Badan Akreditasi Nasional Perguruan Tinggi (BAN-PT). Internal evaluation is preparation for external evaluation. Self evaluation need three years academic record. That data must be collected from BAAK (Badan Administration Akademik dan Kemahasiswaan) , IT deparment, staf and human resource department. It is difficult, because sometimes data is not consistent. Self Evaluation Information System would be a solution. It can make self evaluation process more easier also complitness of acreditation standard, because data already prepared. This Information System is development of Academic Information System PCR, with another data adds on such as facility, lecturer, quality assurance, alumni etc. That data appropriate with standar acreditation(borang akreditasi)  which used as reference Self Evaluation Information System design. Information System will be build using My SQL and PHP. Hopefully, Self Evaluation Information System can make the proses of self evaluation internal or external more effisien, so the continous improvement will be reached faster.  Keyword : Information System, Sel Evaluation, Acreditation Standard, My SQL, PHP
Price Difference Embedded Multivariate Long Sort-Term Memory for Stock Movement Prediction Wawan Yunanto
International ABEC 2021: Proceeding International Applied Business and Engineering Conference 2021
Publisher : International ABEC

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (335.556 KB)

Abstract

The course of the capital market is complicated, unpredictable, and volatile for investors to formulate. Fundamental and technical analysis are the main common approaches to predict stock prices used by the economic experts nowadays. The fundamental aspect is determined by the internal factor of the companies, but the technical one is clearly represented on a daily basis in the stock market. Stock price is not the only important item for investors to make investment policy. The fluctuation in the trading floor has become the most important issue to be considered. In this research, we propose a prediction framework, namely Price Difference Embedded Multivariate Long Sort-Term Memory (PDEM-LSTM), to combine stock price and movement prediction into a single pipeline. We employ recurrent deep learning modeling technics into stock market forecasting since there are sequential properties in the technical components. Our work solely based on these sequences or timeseries features to simplify the experimental setting and more focus on the improvement compared to most previous studies. Our benchmark compares results from univariate scheme on the same sequences with 3 difference features which are current day and next day price along with the price difference between those days. We use 5 stock issuers from 5 different stock indices and the market data taken from January 1, 2000, to December 31, 2020. The results showed that price difference feature embedded into LSTM in multivariate setting greatly improve stock movement prediction without degrading stock price forecasting too much. It is simple and robust; it can be attached on most stock prediction techniques in the feature engineering phase.
Manajemen Pengetahuan Melalui Web 2.0 (Wikipedia) pada Organisasi Delfi Angela; Wawan Yunanto; Yohana Dewi Lulu Widyasari
JURNAL INFOTEL Vol 9 No 3 (2017): August 2017
Publisher : LPPM INSTITUT TEKNOLOGI TELKOM PURWOKERTO

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20895/infotel.v9i3.245

Abstract

Himpunan mahasiswa merupakan wadah bagi setiap mahasiswa program studi tertentu yang bertujuan untuk menampung aspirasi setiap anggotanya. Proses berbagi pengetahuan biasanya dilakukan melalui pertemuan langsung yang dilakukan di dalam kelas, diskusi, dan rapat. Sistem manajemen pengetahuan dapat mengelola dan mendokumentasikan semua pengetahuan setiap anggotanya agar proses berbagi pengetahuan tidak terhambat. Penelitian ini mengembangkan sebuah sistem manajemen pengetahuan web 2.0 dengan konsep Wikipedia. Konsep Wikipedia diterapkan untuk memungkinkan setiap anggota organisasi dalam menambah, menghapus, dan memperbaiki isi dari website. Informasi dan pengetahuan yang ada dapat dimanfaatkan dan diperbaharui secara terus menerus oleh sesama anggota organisasi. Proses manajemen pengetahuan yang digunakan pada sistem ini adalah knowledge discovery, knowledge capture dan knowledge sharing. Hasil dari pengujian User Acceptance Test yang telah dilakukan bahwa sistem manajemen pengetahuan telah dapat diterima oleh organisasi dalam membantu anggota organisasi mengembangkan pengetahuan serta mendapatkan pengetahuan yang baru.
Heuristics Miner for E-Commerce Visitor Access Pattern Representation Wardhani, Kartina Diah Kesuma; Yunanto, Wawan
Communications in Science and Technology Vol 2 No 1 (2017)
Publisher : Komunitas Ilmuwan dan Profesional Muslim Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21924/cst.2.1.2017.21

Abstract

E-commerce click stream data can form a certain pattern that describe visitor behavior while surfing the e-commerce website. This pattern can be used to initiate a design to determine alternative access sequence on the website. This research use heuristic miner algorithm to determine the pattern. σ-Algorithm and Genetic Mining are methods used for pattern recognition with frequent sequence item set approach. Heuristic Miner is an evolved form of those methods. σ-Algorithm assume that an activity in a website, that has been recorded in the data log, is a complete sequence from start to finish, without any tolerance to incomplete data or data with noise. On the other hand, Genetic Mining is a method that tolerate incomplete data or data with noise, so it can generate a more detailed e-commerce visitor access pattern. In this study, the same sequence of events obtained from six-generated patterns. The resulting pattern of visitor access is that visitors are often access the home page and then the product category page or the home page and then the full text search page.
Impact of Hyperparameter Tuning on ResNet-UNet Models for Enhanced Brain Tumor Segmentation in MRI Scans Pamungkas, Yuri; Triandini, Evi; Yunanto, Wawan; Thwe, Yamin
International Journal of Robotics and Control Systems Vol 5, No 2 (2025)
Publisher : Association for Scientific Computing Electronics and Engineering (ASCEE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31763/ijrcs.v5i2.1802

Abstract

Brain tumor segmentation in MRI scans is a crucial task in medical imaging, enabling early diagnosis and treatment planning. However, accurately segmenting tumors remains a challenge due to variations in tumor shape, size, and intensity. This study proposes a ResNet-UNet-based segmentation model using LGG dataset (from 110 patients), optimized through hyperparameter tuning to enhance segmentation performance and computational efficiency. The proposed model integrates different ResNet architectures (ResNet18, ResNet34, ResNet50, ResNet101, and ResNet152) with UNet, evaluating their performance under various learning rates (0.01, 0.001, 0.0001), optimizer types (Adam, SGD, RMSProp), and activation functions (Sigmoid). The methodology involves training and evaluating each model using Loss Function, Mean Intersection over Union (mIoU), Dice Similarity Coefficient (DSC), and Iterations per Second as performance metrics. Experiments were conducted on MRI brain tumor datasets to assess the impact of hyperparameter tuning on model performance. Results show that lower learning rates (0.0001 and 0.001) improve segmentation accuracy, while Adam and RMSProp outperform SGD in minimizing segmentation errors. Deeper models (ResNet50, ResNet101, and ResNet152) achieve the highest mIoU (up to 0.902) and DSC (up to 0.928), but at the cost of slower inference speeds. ResNet50 and ResNet34 with RMSProp or Adam provide an optimal trade-off between accuracy and computational efficiency. In conclusion, hyperparameter tuning significantly impacts MRI segmentation performance, and selecting an appropriate learning rate, optimizer, and model depth is crucial for achieving high segmentation accuracy with minimal computational cost.
Enhancing Diabetic Retinopathy Classification in Fundus Images using CNN Architectures and Oversampling Technique Pamungkas, Yuri; Triandini, Evi; Yunanto, Wawan; Thwe, Yamin
Journal of Robotics and Control (JRC) Vol. 6 No. 1 (2025)
Publisher : Universitas Muhammadiyah Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18196/jrc.v6i1.25331

Abstract

Diabetic Retinopathy (DR) is a severe complication of diabetes mellitus that affects the retinal blood vessels and is a leading cause of blindness in productive-age individuals. The global increase in diabetes prevalence requires an effective DR classification system for early detection. This study aims to develop a DR classification system using several CNN architectures, such as EfficientNet-B4, ResNet-50, DenseNet-201, Xception, and Inception-ResNet-v2, with the application of the SMOTE oversampling technique to address data class imbalance. The dataset used is APTOS 2019, which has an unbalanced class distribution. Two scenarios were tested, the first without data balancing and the second with SMOTE implementation. The test results show that in the first scenario, Xception achieved the highest accuracy at 80.61%, but model performance was still limited due to majority class dominance. The application of SMOTE in the second scenario significantly improved model accuracy, with EfficientNet-B4 achieving the highest accuracy of 97.78%. Additionally, precision and recall increased dramatically in the second scenario, demonstrating SMOTE's effectiveness in enhancing the model's ability to detect minority classes and reduce prediction errors. DenseNet-201 achieved the highest precision at 99.28%, while Inception-ResNet-v2 recorded the highest recall at 98.57%. Overall, this study proves that the SMOTE method effectively addresses class imbalance in the fundus dataset and significantly improves CNN model performance. Although data balancing can help improve model quality by dealing with data imbalances, it comes at a higher computational cost. Using data balancing techniques with SMOTE significantly increased the iteration time per round on all tested CNN architectures.
A Comprehensive Review of EEGLAB for EEG Signal Processing: Prospects and Limitations Pamungkas, Yuri; Rangkuti, Rahmah Yasinta; Triandini, Evi; Nakkliang, Kanittha; Yunanto, Wawan; Uda, Muhammad Nur Afnan; Hashim, Uda
Journal of Robotics and Control (JRC) Vol. 6 No. 4 (2025)
Publisher : Universitas Muhammadiyah Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18196/jrc.v6i4.27084

Abstract

EEGLAB is a MATLAB-based software that is widely used for EEG signal processing due to its complete features, analysis flexibility, and active open-source community. This review aims to evaluate the use of EEGLAB based on 55 research articles published between 2020 and 2024, and analyze its prospects and limitations in EEG processing. The articles were obtained from reputable databases, namely ScienceDirect, IEEE Xplore, SpringerLink, PubMed, Taylor & Francis, and Emerald Insight, and have gone through a strict study selection stage based on eligibility criteria, topic relevance, and methodological quality. The review results show that EEGLAB is widely used for EEG data preprocessing such as filtering, ICA, artifact removal, and advanced analysis such as ERP, ERSP, brain connectivity, and activity source estimation. EEGLAB has bright prospects in the development of neuroinformatics technology, machine learning integration, multimodal analysis, and large-scale EEG analysis which is increasingly needed. However, EEGLAB still has significant limitations, including a high reliance on manual inspection in preprocessing, low spatial resolution in source modeling, limited multimodal integration, low computational efficiency for large-scale EEG data, and a high learning curve for new users. To overcome these limitations, future research is recommended to focus on developing more accurate automation methods, increasing the spatial resolution of source analysis, more efficient multimodal integration, high computational support, and implementing open science with a standardized EEG data format. This review provides a novel contribution by systematically mapping EEGLAB’s usage trends and pinpointing critical technical and methodological gaps that must be addressed for broader neurotechnology adoption.