Green Intelligent Systems and Applications

Literature Review: Biomedical Information of Animal Treadmill Speed Control Using Proportional Integral Derivative Controller

Cut Nanda Nurbadriani — 2024-12-12

The use of treadmill exercise in cardiovascular research played a vital role in assessing heart health and determining appropriate exercise regimens for patients. Before applying these regimens to humans, experiments on animals, such as white rats or mice, were conducted to simulate human cardiovascular responses. A specialized treadmill designed for experimental animals was required to determine exercise doses based on individual abilities. This process involved controlling the treadmill speed, which was generated by a conveyor driven by a DC motor. The motor speed was regulated through PID (Proportional Integral Derivative) control, while encoder sensors monitored the motor’s rotation speed, and limit switch sensors determined the exercise duration. This article reviewed the design and implementation of treadmill systems used for animal-based cardiovascular research, focusing on the control of DC motor speed using PID controllers. Previous studies that contributed to the development of such systems were discussed, with an emphasis on the precise control mechanisms required to simulate exercise conditions tailored to the subject's abilities. The treadmill system also incorporated sensors to accurately adjust motor speed and track exercise duration, ensuring alignment with the physiological capabilities of the test subjects. Furthermore, this review explored the potential for advancing research on treadmill control systems, offering insights into how this technology could support medical experts in determining optimal exercise regimens for white rats. These developments helped bridge the gap between animal-based studies and human applications, facilitating improved cardiovascular research outcomes.

Radiation Performance Comparison and Analysis of Ku-band Microstrip Antennas with Diamond, Octagonal, and Circular Array Configurations

Muhammad Athallah Adriansyah — 2024-11-16

Phased array antennas are essential in modern communication systems, particularly within the Ku-band, which is widely used for satellite communications and radar applications due to its high data rate capabilities. This paper explores the radiation characteristics of Ku-band microstrip antennas arranged in diamond, octagonal, and circular arrays, focusing on uniform excitation to ensure consistency across evaluations. Using CST Microwave Studio 2024 for simulations, the study found that the rectangular array provides the highest gain and narrowest beamwidth, making it suitable for applications where directional accuracy is critical. However, this configuration also resulted in higher sidelobe levels, which can be problematic in environments where minimal interference is required. The diamond array, while exhibiting lower gain, achieved superior sidelobe suppression, making it ideal for scenarios where reducing interference is prioritized over maximizing directivity. The octagonal and circular arrays provided balanced performance across all metrics, offering versatile options for various operational needs. These results provide valuable guidance for optimizing phased array designs to meet specific requirements in Ku-band applications.

Comparative Study of Base Transceiver Stations Infrastructure Planning Using Machine Learning for Under Construction Area: A Case Study of Ibu Kota Nusantara

Alfiyah Shaldzabila Yustin — 2024-08-13

Communication is a fundamental human need that occurs directly or through technologies like telephones and signal transmitters such as BTS and satellites. Satellites, including Starlink, serve as additional solutions for internet access needs, particularly in remote areas, albeit higher costs remain a factor necessitating conventional BTS infrastructure development. Telecommunication operators face challenges in constructing BTS in areas with limited access and complex financial considerations due to low demand in rural areas, requiring careful planning. This study utilizes several supporting variables with the aid of machine learning techniques such as Linear Regression, SVR, Random Forest, and Gradient Boosting to forecast BTS requirements. Comparative analysis shows that the random forest machine learning method provides the best modeling results compared to linear regression, Gradient Boosting, and SVR methods. Despite the superior performance of the random forest method, further fine-tuning is still needed through parameter adjustments and evaluation of variables used to achieve an even better model. The modeling results can be utilized to predict the BTS infrastructure needs in IKN, estimated at 61,135 units. In BTS development planning, mobile operators can collaborate both among themselves and with Internet Service Providers (ISPs) utilizing satellite media. Utilizing shared towers can be an option for cost-efficient BTS infrastructure development.

Design of IoT-Based Battery Monitoring for DC Backup

Yunidar Yunidar — 2024-12-09

The battery monitoring process for the DC backup power supply at the Banda Aceh Main Substation was previously performed manually using a multimeter, leading to inefficiencies. This study aimed to develop an automated battery monitoring system based on the Internet of Things (IoT) to enhance operational efficiency. The proposed system integrated a DC voltage sensor (voltage divider) connected to the battery and an INA219 sensor to measure current flow during battery usage. A NodeMCU ESP8266 microcontroller, programmed with the Arduino IDE, served as the main data processor and internet interface. Monitoring data was transmitted to officers via an IoT-based cloud server on the Blynk platform. The system was tested using eight NiCd 1.2 V battery cells arranged to simulate the substation setup. The resulting prototype automated daily battery monitoring, significantly improving the efficiency and effectiveness of the monitoring process.

Artificial Neural Network for Benchmarking the Dimensional Accuracy of the PLA Fused Flament Fabrication Process

Kevin Stephen Setiawan — 2024-11-17

Fused Deposition Modeling (FDM) is an additive manufacturing technique that uses a 3D printer to extrude molten filament through a nozzle, which moves along the X, Y, and Z axes to create parts with the desired geometry. FDM offers numerous advantages, especially for producing parts with complex shapes, due to its ability to enable rapid and cost-effective manufacturing compared to traditional methods. This study implemented an Artificial Neural Network (ANN) to optimize process parameters aimed at minimizing dimensional inaccuracies in the FDM process. Key parameters considered for optimization included the number of shells, infill percentage, and nozzle temperature. The ANN utilized three algorithms: Scaled Conjugate Gradient, Bayesian Regularization, and Levenberg-Marquardt. Model performance was evaluated based on dimensional deviations along the X and Y axes, with a hidden layer of 25 neurons. Among the algorithms, Scaled Conjugate Gradient provided the most accurate results in minimizing dimensional errors.

A Sentiment Analysis of Hate Speech in Philippine Election-Related Posts Using BERT Combined with Convolutional Neural Networks and Model Variations Incorporating Hashtags and ALL-CAPS

Micah Collette O. Mendoza — 2024-10-24

As the number of people who use X continually increases, the same thing is true for hate speech. A pressing need exists for automatic detection of posts that promote hate speech. The datasets gathered and validated from the base study were used to categorize posts as either hate or non-hate and classify them as positive, negative, or neutral using Conventional Neural Networks. The partitioning of the labeled data into training and testing sets adhered to a ratio scheme: 70%-30%, 80%-20%, and 90%-10%. The model of this study, BERT-CNN, had an overall better performance than the base study, fastText CNN. Notably, among the three splits, the BERT-CNN model for binary classification without the features of Hashtags and ALL-CAPS with the 90:10 split achieved the best performance with an accuracy of 93.55%, precision of 93.59%, and F1-score of 93.55%. For multi-label classification, the BERT-CNN model demonstrated its optimal performance when incorporating hashtags, specifically with the 90:10 split, achieving an accuracy of 69.14%, precision of 68.44%, recall of 68.40%, and an F1-score of 67.41%. The innovative use of BERT word embeddings paired with CNN proved to excel in classifying Philippine election-related posts as hate or non-hate.