Penelitian ini bertujuan membangun model klasifikasi kondisi lalu lintas menggunakan data dari sosial media (Instagram dan Facebook) serta data ETLE dengan arsitektur Recurrent Neural Network. Dari total 1.251 data sosial media yang dikumpulkan, sebanyak 719 data dipilih berdasarkan kemunculan kata kunci “macet”, “sedang”, dan “lancar”. Data ini kemudian dibagi menjadi data latih (5…
Traffic congestion is a serious issue that requires data-driven solutions and intelligent technologies. This study proposes a congestion detection system and alternative route recommendation based on a combination of Decision Tree (DT) algorithms optimized using Bayesian Optimization (BO) for classifying traffic conditions, and Ant Colony Optimization (ACO) for determining optimal routes. Input…
Instagram has become one of the most popular platforms, with 86.5% of users making it the second most accessed social media platform in the country by 2024. Almost all government agencies in Indonesia have Instagram accounts to interact with the public, because Instagram is considered one of the effective social media to disseminate information in optimizing government work systems, and improvi…
This study aims to analyze the factors influencing the use of the SIGNAL application for two-wheeled motor vehicle tax payments at the Palembang City Samsat Office 01. The research adopts the Unified Theory of Acceptance and Use of Technology 2 (UTAUT2) model with a quantitative approach. Data were collected through questionnaires and analyzed using the Partial Least Squares Structural Equation…
This study aims to develop a system capable of identifying and classifying medical entities from unstructured biomedical texts, thereby supporting Clinical analysis and health research. The author trained and evaluated three BERT-based models: BioBERT, Clinical BERT, and BlueBERT, for the task of Clinical Named Entity Recognition (CNER). Model performance was measured using precision, recall, a…
The academic administration system at the Faculty of Computer Science, Sriwijaya University, remains semi-digital and fragmented, causing inefficiency, human error risks, and lack of transparency and document authenticity. This research designs a blockchain-based academic administration system using a Proof-of-Authority (PoA) consensus mechanism to enhance efficiency, transparency, and security…
The Environmental Complaint Information System (SiPeduli) is a complaint application managed by the Environmental Agency of Palembang City, designed to receive public complaints regarding environmental issues in the city. These issues include environmental cleanliness, illegal waste disposal, hazardous and toxic waste (B3 waste), environmental pollution, and retribution. Complaints submitted by…
Nowadays, video games are getting popular due to the rapid growth of technology, especially mobile technology. Video games are now able to be played on mobile devices whether in single or multiplayer mode by using the internet and it's free and available everywhere. Understanding player experience in mobile video games is essential for developers and researchers. This research evaluates player …
Zalora is an E-Commerce application founded in 2012 in Singapore and now operates in various countries, including Indonesia. Although widely known, this application still has a number of complaints from users such as product incompatibility, delays in process updates, and less than optimal application performance. This study aims to evaluate the level of user satisfaction of the Zalora applicat…
This study aims to improve the performance of arrhythmia classification in deep learning models using the Teaching Learning Based Optimization (TLO) algorithm for feature optimization. The features used are extracted from the time domain of RR intervals obtained during the preprocessing stage. The NIFEA-DB and NIFECG datasets are utilized in this study, with R-peaks extracted using the Heartpy …
The healthcare industry in Indonesia is rapidly developing, particularly in addressing myocardial infarction (heart attack), a medical emergency that requires prompt detection. Common examinations such as ECG, blood tests, and clinical symptom analysis still rely heavily on manual assessment, which can be time-consuming. As a solution, a Machine Learning (ML)-based approach offers more efficien…
This study developed an arrhythmia classification model based on electrocardiogram (ECG) signals using time-domain RR-interval feature extraction techniques and the implementation of Teaching-Learning-Based Optimization (TLO) for feature selection. The datasets employed include the MIT-BIH Arrhythmia Database, MIT-BIH Normal Sinus Rhythm Database, MIT-BIH Atrial Fibrillation Database, Lobachevs…
Advancements in Natural Language Processing (NLP) have improved the extraction of information from unstructured biomedical text, particularly in recognizing clinical named entities like diseases, genes, and proteins. This study evaluates the performance of Bi-LSTM and Bi-LSTM-CRF models for Clinical Named Entity Recognition (CNER) using three benchmark datasets: NCBI-Disease, BC2GM, and JNLPBA.…
Tujuan dari penelitian ini adalah untuk mengetahui dan menganalisis sentiment konsumen terhadap produk ZALORA di Google Play Store, dan menganalisis keakuratan metode random forest dalam klasifikasi sentiment. ini menggunakan jenis penelitian kuantitatif, yang didasarkan pada filsafat positivisme dan menggunakan data konkret dan objektif. Jenis penelitian ini digunakan untuk mempelajari populas…
Cardiac abnormalities are disorders in heart function that can be detected through electrocardiogram (ECG) signals. This research uses a frequency domain-based feature extraction method with Fast Fourier Transform (FFT), using ten features which then the data will be classified using machine learning algorithms, such as SVM, Random Forest, Decision Tree, and K-Nearest Neighbors (KNN). Results s…
Segmentation of heart holes and septum in pediatric medical images presents a major challenge in medical image analysis to support the diagnosis of congenital heart disease. Congenital heart defects such as Atrial Septal Defect (ASD), Ventricular Septal Defect (VSD), Atrioventricular Septal Defect (AVSD), and normal conditions require accurate detection to ensure proper diagnosis. This study em…
Early detection of fetal heart anomalies, such as cardiomegaly, is critical in prenatal diagnosis. However, manual segmentation of ultrasound (USG) images requires specialized expertise and is time-consuming, highlighting the need for an efficient automated solution. This research aims to perform automatic segmentation of fetal thorax and heart areas using You Only Look Once (YOLO) version 8 an…
Kemajuan teknologi komputasi kuantum telah menimbulkan ancaman serius terhadap keamanan sistem kriptografi konvensional seperti RSA dan ECC yang saat ini digunakan secara luas dalam aplikasi komunikasi. Sebagai respons terhadap tantangan ini, penelitian ini bertujuan untuk mengimplementasikan dan mengevaluasi algoritma NTRU sebagai solusi Post-Quantum Cryptography untuk pengamanan pesan. Hasil …
The rapid advancement of digital technology has encouraged telecommunication companies to provide services that are not only functional but also offer an optimal user experience. BIMA+, a digital application developed by Tri Indonesia, serves as a key platform for users to access various services and engaging features. The BIMA+ app holds a rating of 4.6 on Play Store of Android. This study aim…
Traffic congestion is a major problem in Palembang City due to the significant growth in the number of vehicles. This study aims to develop an artificial intelligence-based system in detecting vehicle density and predicting optimal routes. Vehicle number detection is carried out using the YOLOv11 method based on CCTV data at 15 intersections in Palembang City with training results showing an ac…
Cervical cancer is one of the leading causes of death among women, particularly in developing countries. Early detection through Visual Inspection with Acetic Acid (VIA) is considered effective, but it still presents a high rate of false positives due to the limitations of visual observation. This study aims to develop and evaluate the YOLOv8 model for accurate and efficient segmentation of pre…
Penelitian ini membahas segmentasi citra ultrasonography jantung anak untuk mendeteksi lubang (hole) dan septum jantung menggunakan pendekatan deep learning, khususnya model YOLO (You Only Look Once). Penelitian ini menggunakan dataset citra ultrasonography non-doppler yang diambil dari rekaman smartphone, kemudian dilakukan segmentasi dengan berbagai varian model YOLOv8 (nano, small, medium, d…
Heart disease, particularly myocardial infarction (IM), is a leading cause of global death that requires early and accurate detection to prevent fatal outcomes. This study aims to develop a deep learning-based IM multi-class classification system using ECG signals from the PTB-XL dataset. The model was built with a combination architecture of Convolutional Neural Network (CNN) and Long Short-Te…
This study aims to evaluate the performance of a solar power generation system in producing electrical energy and its capability to meet the energy demands of a smart home. The methodology involves data exploration, predictive modeling using linear regression, and energy sufficiency analysis. Preprocessing results indicate that the dataset is clean and suitable for analysis. Exploratory analysi…
Blackhole Attack Detection on 6LoWPAN Networks Still Has Several Disadvantages, Such as Limited Detection Accuracy Because It Only Depends on One Parameter, High Communication Overhead Due to the Use of Encryption or IDS, and Lack of Adaptation to Heterogeneous IoT Network Characteristics. The Threshold Method Offers a More Efficient Solution by Combining Packet Delivery Ratio (PDR), Packet Los…
Salah satu perusahaan BUMN pertambangan adalah PT Bukit Asam Tbk. PT Bukit Asam Tbk jelas menghadapi tantangan dalam proses bisnisnya selama pandemi COVID-19. Beberapa kegiatan yang melibatkan banyak orang harus ditangguhkan. Hal ini berdampak pada kinerja karyawan, masalah seperti ini pasti membutuhkan sumber daya manusia berkualitas tinggi. Tujuan penelitian ini menganalisis pengaruh knowledg…
Reverse HTTPS Exploit is a type of malware attack technique used by attackers to exploit vulnerabilities in the HTTPS layer of an application or system, aiming to steal sensitive data from the target. This study utilized raw dataset files in .pcap format provided by the COMNETS Research Lab at Sriwijaya University. The data was collected through realistically designed experimental scenarios to …
Penelitian ini menganalisis pengaruh cuaca dan kondisi jalan terhadap kecelakaan lalu lintas menggunakan K-Means, serta membandingkannya dengan Gaussian Mixture Model (GMM) dan Spherical K-Means. Data mencakup variabel cuaca, kondisi jalan, dan karakteristik kecelakaan 2018–2023. Hasilnya, cuaca hujan dan jalan basah meningkatkan risiko kecelakaan. GMM unggul dalam evaluasi metrik, tetapi K-M…
University has adapted internet into almost every activities. The implementation and utilization of the internet itself have effectively improved students’ academic performance. However, their access to a stable internet still remains as an issue. This condition also happened to Universitas Sriwijaya’s students. The campus Wi-Fi conditions that are not yet able to fully support student acti…
The Academic Information System (SIMAK) at Sriwijaya University frequently encounters access issues, unstable servers, and a less intuitive interface, which adversely affects user experience. Sentiment analysis utilizing Naïve Bayes on data from social media platform X (Twitter) reveals that 64% of sentiments are negative, primarily concerning technical problems and navigation difficulties. Co…