IJCCS (Indonesian Journal of Computing and Cybernetics Systems)
Not a member yet
480 research outputs found
Sort by
Webcam-Based Bus Passenger Detection System Using Single Shot Detector Method
Full text linkBuses are one of the most widely chosen transportation methods to support the mobility of the Indonesian people. Mobility that is often found in addition to public transportation, is also often found in the mobility of tourism tour activities for a travel group. The number of tourist destinations to which passengers go up and down makes the assistant bus driver or group leader work hard to ensure that the number of passengers boarding the bus matches the number of groups. It often takes a long time to ensure the accuracy of the number of passengers before departure to the next destination. This conventional method results in the delay of the tourism tour schedule. In this research, the author designs a webcam-based bus passenger face detection system using the Single Shot Detector (SSD) method that can provide real-time information to bus drivers, assistant bus drivers or group leaders. The results obtained by the system obtained an achievement of 95% of the total system creation along with testing the detection of bus passenger faces in actual conditions resulted in an average accuracy of 77.5%
Anomaly Detection of Hospital Claim Using Support Vector Regression
No full textBPJS Kesehatan plays a crucial role in providing affordable access to healthcare services and reducing individual financial burdens. However, deficit issues can disrupt the sustainability of the program, making anomaly detection highly important to conduct. Previous research on unsupervised anomaly detection in BPJS Kesehatan revealed a limitation with Simple Linear Regression (SLR), which only accommodates linear relationships among independent variables and the target variable of BPJS Kesehatan claim values. Minister of Health Regulation No. 52 of 2016 identified eight influential non-linear independent variables, leading to the proposal of Support Vector Regression (SVR) to address SLR's shortcomings.Research findings demonstrate SVR's superior anomaly detection performance over SLR. Interestingly, the SVR model excels in anomaly detection but lacks in prediction. Optimal tuning of SVR hyperparameters (C=9, epsilon=90, gamma=0.009, residual anomaly definition > 0.5*RMSE for both datasets) yields impressive metrics: Accuracy=0.97, Precision=0.84, Recall=0.97, and F1-Score=0.90. The anomaly detection results are expected to greatly support the sustainability of the BPJS Kesehatan program in Indonesia
Comparing text classification algorithms with n-grams for mediation prediction
Full text linkTingkat keberhasilan mediasi perkara perdata di pengadilan negeri dari tahun ke tahun sangat rendah dan menyebabkan penumpukan perkara yang harus ditangani dengan persidangan. Sementara itu, pendaftaran perkara baru dengan klasifikasi perkara serupa terus bermunculan dan wajib dimediasi. Penelitian ini dilakukan dengan memanfaatkan data mediasi perkara terdahulu sebagai dataset untuk memprediksi hasil mediasi perkara baru. Ketika n-gram digunakan pada dataset yang telah di-preprocessing, hanya ditemukan nilai pada unigram (n=1). Pada penerapan model menggunakan algoritma machine learning, dihasilkan akurasi yang sama sebesar 0.6875 pada Algoritma Naïve Bayes, Logistic Regression dan Support Vector Machine (SVM), sedangkan algoritma Decision tree menghasilkan akurasi paling rendah sebesar 0,375. Rendahnya nilai dikarenakan Decision Tree lebih cenderung overfit untuk digunakan dengan teks berbahasa Indonesia. Pola kalimat formal pada dokumen mediasi berbahasa Indonesia tidak memenuhi unsur – unsur kata majemuk, imbuhan, variasi susunan kata, dan semantik leksikal. Untuk penelitian selanjutnya direkomendasikan penggunaan algoritma klasifikasi lain, pemanfaataannya pada dokumen – dokumen lain seperti putusan pengadilan, penentuan rangking mediator berdasarkan keberhasilan mediasi serta implementasi model pada aplikasi e-mediasi yang terintegrasi dengan sistem informasi manajemen perkar
STUDENT VIRTUAL CLASS ATTENDANCE BASED ON FACE RECOGNITION USING CNN MODEL
Full text linkAttendance records are an important tool that can be used to include and broadcast member participation in an activity, including the learning process. In online learning classrooms, the process of recording attendance becomes challenging to do manually, thus an automatic attendance recording system is needed. The authentication process is important in developing an existing recording system to guarantee the correctness of the recorded data. In this research, a face authentication system was built to create a system for recording online class attendance to help integrate participant activities and participation in online class learning. The face recognition approach uses a Convolutional Neural Network (CNN) model specifically designed to automate student attendance in virtual classes. Student image data is taken from virtual classroom sessions and used to train a CNN model. This model can recognize and verify student identity in various lighting conditions and head positions. This research consists of several stages, namely data collection, artificial neural networks, use of facial recognition, dataset application stage, and facial recognition in video frames. The experimental results showed that there were 11193 samples studied and of these 11193 samples the distribution was even, namely 6.7%. In addition, the model performance results show an accuracy of 76.28%
Analysis and Prediction of the Occurrence of an Earthquake Using ARIMA and Statistical Tests
Full text linkEarthquakes present significant risks to both human safety and infrastructure, emphasizing the need for precise prediction models to minimize their adverse effects. This study seeks to tackle the challenge of accurately forecasting the occurrence time of earthquakes by utilizing the LANL Earthquake dataset, which comprises seismic signals from a laboratory model emulating tectonic faults. In this study, we employed the ARIMA model and compared it with Linear Regression to predict earthquake occurrences. Our findings demonstrate that the ARIMA (1,1,1) model surpasses other models, achieving the lowest MAE of 0.110628. The validity of the model's assumptions is confirmed through the Ljung-Box and Jarque-Bera tests, which verify the absence of autocorrelation and the normal distribution of residuals, respectively
Analysis of the Implementation of ISO 27001: 2022 and KAMI Index in Enhancing the Information Security Management System in Consulting Firms
Full text linkKeamanan Informasi Elektronik ini kini sudah menjadi hal yang perlu diperhatikan oleh seluruh perusahaan agar aset penting perusahaan tetap terjaga dan mendapatkan kepercayaan dari pelanggan atau klien. Dalam operasional sehari-hari, banyak aktivitas dan data pribadi yang dikirimkan ke perusahaan untuk melakukan transaksi. Akan tetapi, belum banyak perusahaan yang memiliki kesadaran akan keamanan informasi, yang apabila tidak dilakukan akan merugikan perusahaan. Selain itu, dapat menurunkan nilai kompetitif karena dinilai tidak mampu melindungi data pribadi pelanggan atau klien. Setiap kebocoran data dan pelanggaran keamanan informasi dapat merusak reputasi organisasi [1]. Oleh karena itu, penting untuk memiliki ISMS yang efektif sesuai dengan standar ISO 27001:2022 yang merupakan standar keamanan informasi internasional yang telah diterapkan pada banyak perusahaan di seluruh dunia. ISO 27001:2022, standar internasional untuk manajemen keamanan informasi, memberikan panduan dan persyaratan yang jelas untuk membangun, menerapkan, dan memelihara sistem keamanan informasi yang efektif. Dalam makalah ini, penulis akan menilai tingkat kematangan sistem manajemen keamanan informasi berdasarkan ISO 27001: 2022. Berdasarkan penilaian tersebut, perusahaan masih mampu mencapai standar ISO 27001:2022 dan Index KAMI. Beberapa perbaikan harus dilakukan untuk mencapai tingkat kematangan minimum III+ dari penilaian Index KAMI. Selain itu, berdasarkan ISO/IEC 27001:2022, skor hasil yang diperoleh adalah 39% yang dapat disimpulkan bahwa sebagian besar perusahaan belum menerapkan prosedur apa pun dan beberapa kontrol telah diterapkan. Oleh karena itu, rekomendasi perbaikan diperlukan bagi perusahaan, mulai dari penerapan kebijakan dan prosedur terkait manajemen keamanan informasi
Feasibility Study of Using Blockchain Technology for Criminal Records in Central Java
Full text linkA criminal record is an official document filed with the police that contains a person's criminal history. In practice, managing criminal record data is not easy, the complex challenge is the risk of data manipulation. Data manipulation is carried out for various purposes, one of which is deleting or changing data for certain purposes. The increase in cyber crime in Indonesia does not rule out the possibility that criminal record data will be hacked. Blockchain technology, through smart contracts, is an innovative solution to overcome the problem of data manipulation. Blockchain as an immutable distributed digital ledger, provides guarantees of data security and integrity. By adopting smart contracts in data collection, it can increase the speed of information access, reduce the risk of manipulation and provide a high level of transparency. A feasibility study regarding the importance of implementing Blockchain technology for storing criminal records needs to be carried out before deciding to realize this technology. The aim of this research is to analyze how important it is that criminal record data must be secured using Blockchain technology in Central Java. Qualitative methods were used in this research, data collection was carried out using interview techniques with predetermined source
Measurement and Analysis of Detecting Fish Freshness Levels Using Deep Learning Method
Full text linkSubjective and objective tests used to determine the fish deterioration process require specialized skills and time, making them inefficient for use by the general public in markets. The quality of fish products in markets is not always guaranteed, so consumers must determine their suitability. Deep learning can be used to analyze images and automatically and accurately detect the freshness of fish. This study aims to evaluate the efficiency of deep learning models in detecting fish freshness and implementing them into an Android application for public use. "Image datasets and pH tests were collected as references for the postmortem phase over a 24-hour period, with hourly checks on three fish species (Rachycentron canadum, Trachinotus blochi, and Lates calcarifer). Data were classified into three classes, pre-rigor/fresh, rigor mortis/semi-fresh, and post-rigor/not fresh. The dataset was divided using the 10-fold cross-validation method and analyzed using YOLOv5 and Faster R-CNN algorithms. The study results showed that YOLOv5 had higher average values for each metric compared to Faster R-CNN. Dataset 8 in YOLOv5 showed precision of 99.4%, recall of 98.1%, f1-score of 98.7%, accuracy of 99.3%, and mAP of 99.3%. The YOLOv5 model for dataset 8 was selected for implementation in the Android application due to its high metric values. This application effectively provides information on fish freshness detection and confidence scores
APPLICATION OF DATA MINING USING THE C4.5 ALGORITHM AND THE K-NEAREST NEIGHBOR (KNN)
Full text linkDirect cash assistance is a governmental or social institution intervention that provides financial aid directly to individuals or families in need. To streamline this process, a system is necessary to convert data into predictive information regarding eligibility for direct cash assistance. This research utilizes the C4.5 algorithm and the K-Nearest Neighbor algorithm for predicting eligibility based on factors such as housing status, employment, income, and eligibility status. Using the C4.5 algorithm, Microsoft Excel calculations identified 238 individuals as eligible and predicted 62 as ineligible who were eligible, out of a total of 300 recipients. The accuracy rate from RapidMiner calculations was 93.00%. Regarding the K-Nearest Neighbor method, Microsoft Excel calculations identified 226 eligible and 74 ineligible recipients out of 300. RapidMiner analysis showed an accuracy rate of 76.55% for the 226 eligible recipients and 98.23% for the 74 ineligible recipients
Machine Translation Indonesian Bengkulu Malay Using Neural Machine Translation-LSTM
Full text linkThe machine translator is an application in Natural Language Processing (NLP) that focuses on translating between languages. Several previous research have used Statistical Machine Translation (SMT) with a parallel corpus of Indonesian and Bengkulu Malay totaling 3000 data points. However, SMT performs poorly when confronted with limited data and infrequent language pairs. Therefore, this study aims to build a machine translation model from Indonesian to Bengkulu Malay using an NMT approach with Long Short-Term Memory (LSTM), and to create a parallel corpus of 5261 data pairs between Indonesian and Bengkulu Malay. The research was conducted in three stages: data collection, data preprocessing, training and modeling, and evaluation. The performance of the machine translator was evaluated using the Bilingual Evaluation Understudy (BLEU). The evaluation results show that this model achieved the highest average score of 0.6016332 on BLEU-1 and the lowest average score of 0.3680788 on BLEU-4. These results indicate that considering the natural linguistic structural differences between Indonesian and Bengkulu Malay can be suggested as the best solution for translating from Indonesian to Bengkulu Malay