Traffic density is a complex issue in Palembang City that impacts time efficiency, fuel consumption, and environmental quality. This study aims to predict traffic density using Electronic Traffic Law Enforcement (ETLE) data as an objective source and Instagram social media data as a representation of public perception, applying the Random Forest method with an eliminating skewed distribution te…
Masalah: Identifikasi batas jantung dan rongga dada pada citra USG jantung janin masih dilakukan secara manual sehingga berpotensi menimbulkan variabilitas hasil. Selain itu, karakteristik citra USG seperti speckle noise, kontras yang rendah, serta dominasi intensitas abu-abu membuat proses segmentasi struktur anatomi menjadi lebih menantang. Tujuan: Penelitian ini bertujuan mengimplementasikan…
-
The development of text processing technology allows for automated data classification using machine learning methods. In the case classification process, manual text grouping is often time-consuming and error-prone. This study aims to build a text classification system capable of automatically grouping case descriptions into specific categories. The methods used in this study are Support Vecto…
Information systems in the Faculty of Computer Science, Sriwijaya University generally have separate authentication and user management mechanisms in each application. This condition causes repeated login processes, decentralized role management, and less efficient application integration. This research aims to develop a role-based Single Sign-On (SSO) system as a centralized authentication and…
Air quality is one of the environmental issues that affects human health and ecosystems, making it necessary to have an air quality monitoring system that can provide accurate and consistent information. This study aims to implement a multi-parameter air quality monitoring system dashboard that covers carbon monoxide (CO), ammonia (NH3), ultraviolet (UV) radiation, temperature, and humidity par…
This study aims to implement a system for monitoring carbon monoxide (CO), ultraviolet (UV) intensity, and air quality parameters—specifically temperature and humidity—in outdoor environments using an ESP32 microcontroller. The system employs MQ-7, GY-ML8511, and BME680 sensors to collect real-time environmental data. Test results show that the MQ-7 sensor is capable of detecting carbon mon…
Air quality is an important factor that affects human health and comfort; therefore, a monitoring system capable of operating continuously is required. This study developed an Internet of Things (IoT)-based air quality monitoring device using the ESP32 as the main controller. Measurements were carried out using the Sharp GP2Y1010AU0F sensor to detect PM2,5 particles, the MQ-135 sensor to monito…
Outdoor environmental quality is influenced by several key parameters, such as ammonia (NH₃) levels, ultraviolet (UV) radiation intensity, temperature, and humidity. This study aims to implement an Internet of Things (IoT)-based outdoor environmental monitoring system using an ESP32 microcontroller with MQ-135, GY-ML8511, and BME680 sensors. Sensor readings are processed by the ESP32 and tran…
Real-time health condition monitoring is an important requirement in supporting more effective and efficient healthcare services. The development of the Internet of Medical Things (IoMT) enables medical devices to be connected to the internet, allowing health data to be monitored remotely. This study aims to design and implement an IoMT-based patient health monitoring system using the MAX30102 …
Data distribution changes over time have become one of the main challenges in the application of machine learning to intelligent transportation systems. This phenomenon, known as concept drift, can lead to performance degradation when the testing data exhibit characteristics that differ from those of the training data. This study aims to analyze the robustness of machine learning algorithms aga…
The self-attention mechanism in Large Language Models (LLMs) is computationally intensive and memory-bound, posing significant challenges for inference on consumer-grade hardware. This research proposes a memory-aware optimization of CUDA kernels for the self-attention mechanism within the GPT-2 architecture, integrating Shared Memory Tiling, Streaming Softmax, and Kernel Fusion to minimize glo…
Reverse HTTPS attacks conceal malware communication within encrypted traffic. This research detects these threats using the Logistic Regression method on raw data from the Mobile-Trojan Metasploit Traffic. The data flow feature extraction results obtained through the CICFlowMeter tool are crucial for preserving the dataset's overall quality. Modeling was conducted without resampling techniques …
Integrasi Industrial Internet of Things (IIoT) dalam sistem gardu listrik telah meningkatkan efisiensi operasional tetapi juga meningkatkan kerentanan terhadap ancaman siber, khususnya serangan Man-in-the-Middle (MITM) di mana informasi diubah dan stabilitas jaringan terpengaruh. Tulisan ini menyajikan struktur Deep Neural Network (DNN) yang didedikasikan untuk mengidentifikasi serangan Man-in-…
Indicator of Compromise (IoC) merupakan artefak digital penting dalam Cyber Threat Intelligence (CTI), seperti IP address, domain, URL, hash file, dan nama malware, yang digunakan untuk membantu identifikasi aktivitas berbahaya. Ekstraksi IoC dari teks CTI masih menjadi tantangan karena data umumnya bersifat semi-terstruktur serta mengandung variasi istilah teknis yang kompleks. Penelitian ini …
The rapid growth of social media has enabled the misuse of comment sections as a medium for promoting online gambling. The high volume of comments makes manual moderation ineffective, thus requiring an automated classification system. This study aims to develop a classification system for online gambling comments using the IndoBERT model and to evaluate its performance based on accuracy, precis…
Medical metal waste such as syringes and scalpels are Hazardous and Toxic Waste (B3) which has the potential to cause injury, infection, and environmental pollution if not managed properly. This study aims to design and build a medical metal waste classification system based on ESP32-CAM with integrated inductive metal sensors to assist the automatic waste sorting process. The research method u…
Air quality is an important environmental element that needs to be continuously monitored, especially in urban areas. Air quality data collected from sensors is often not displayed in a website format that is easily accessible and understandable by users. This research aims to design and develop a website-based air quality dashboard using the Laravel framework. Data is obtained from various air…
3D video streaming services require a network infrastructure capable of supporting large-scale data transmission in a stable and efficient manner. A Content Delivery Network (CDN) plays an important role in improving content distribution performance by bringing servers closer to end users. This study aims to analyze the performance of the Cloudflare CDN in terms of Quality of Service (QoS) and …
The internship application process at the Management Informatics Study Program of Sriwijaya University still uses Google Form with document management that is not yet integrated, causing the administration and monitoring process to become less effective. This study aims to develop a web-based Internship Application Information System (SIKP) that can support the internship submission, verificati…
Medical waste is a type of waste that requires special handling because it can affect health and the environment if not properly managed. One important stage in managing medical waste is sorting it by type. However, sorting, which is still done manually, can be prone to errors in categorising waste. Therefore, a monitoring system for sorting wet, dry, and metal medical waste based on the Intern…
Medical waste generated from operating rooms has the potential to pose risks to health and the environment if not properly managed. One of the important stages in medical waste management is the waste sorting process based on its characteristics. However, the sorting process is still largely carried out manually, which risks causing sorting errors and increasing direct contact with infectious w…
Flooding is one Malware is one of the major threats to cybersecurity and continues to evolve, making it increasingly difficult to detect using conventional methods. This study aims to implement and analyze the State-Action-Reward-State-Action (SARSA) and Deep Q-Network (DQN) algorithms for binary malware classification based on static features extracted from the dataset. Data preprocessing, fea…
The development of Internet of Things (IoT) technology has encouraged the creation of monitoring systems capable of transmitting and displaying sensor data quickly and in real-time. Web-based sensor data streaming systems have become one of the solutions to simplify the process of monitoring environmental conditions through internet networks. This research focuses on the design and development …