Innovation in Engineering

Analysis of trends and variability in frequency and intensity indices of precipitation over Myanmar during 1985-2020

Min Khaing — 2025-05-22

In this study, an analysis of long-term extreme precipitation indices was conducted using daily observation data from 38 stations in Myanmar spanning from 1985 to 2020. Three frequency indices and six intensity indices of precipitation were analyzed using RClimDex software. The Mann-Kendall test, along with Sen’s slope method, was employed to determine the trends and magnitude of extreme indices. The spatial distribution patterns varied across different physiographic regions, with 63% to 76% of the stations displaying increasing trends in various indices. The consecutive dry days showed increasing trends in the hilly regions, whereas the consecutive wet days exhibited decreasing trends in those areas. For the maximum 1-day precipitation, 45% of stations displayed increasing trends, with 5% of those being statistically significant. The Western Hilly Region exhibited rising trends in extremely wet days, whereas other regions have experienced mixed trends. These findings highlight the need for adaptive water resources engineering and management to address the localized changes of precipitation trends that affect floods and droughts in Myanmar.

Localization of car license plate using adaptive Euler-template matching method

Nay Zar Aung — 2025-05-22

License plate (LP) detection plays an important role in intelligent transportation systems smart traffic control systems of today. Although it is simple and easy to implement for LP detection, traditional template matching method is less favorable compared to state-of-the-art methods due to its processing cost. Thus, this study proposes an innovative template matching method called “adaptive Euler-template matching method” for detection of LP. Two different models of Euler-template and a new matching concept are proposed. The proposed method is evaluated by detecting LP in a total of 150 test images. Then, the performance of proposed method is compared with the performances of some exiting methods. The proposed method gives accuracies of 96% using Euler-template(model-A) and 96.7% using Euler-template(model-B). The average processing time of proposed method is 0.303 s. The results show that Euler-template(model-B) is more effective for LP detection. More distinct observations are presented and finally recommendations for further works are given in this study.

Design and development of a PID-controlled home air quality monitoring and purification system

Josamae Salas — 2025-08-16

Asthma continues to be a major health concern in the Philippines, with about one in ten people living with the condition. Among its common triggers are fine airborne particles such as PM2.5 and PM10, which can easily aggravate symptoms and affect day-to-day living. In response to this problem, we developed a home-based air quality management system intended to help individuals with asthma maintain safer indoor conditions. The system was equipped with a Proportional-Integral-Derivative (PID) controller, which allowed the purifier to respond more intelligently by tracking air quality in real time and adjusting its operation before conditions became unsafe. To test this feature, we set up a prototype in a bedroom and introduced small amounts of smoke to simulate pollution. In both setups—one with PID control and one without—the purifier successfully reduced particle levels and brought the Air Quality Index (AQI) back to its baseline of 79–81. The key difference, however, was that the PID-controlled system reacted ahead of time, activating the purifier before the thresholds were crossed. This shortened the period of exposure to poor air quality and produced more stable results overall. These findings demonstrate that incorporating a PID controller can enhance the reliability and effectiveness of home-based air purifiers, providing practical support for individuals managing asthma at home.

A mobile application based on object detection algorithm for classifying robusta coffee cherry ripeness

Natasha Marie D. Relampagos — 2025-08-26

Accurate classification of coffee cherries based on ripeness is essential for enhancing the efficiency of harvesting and ensuring high-quality coffee production. Traditional manual sorting is labor-intensive and inconsistent, necessitating an automated solution. This study addresses the challenge by developing a mobile application that uses an object detection algorithm to classify Coffea canephore (Robusta) cherries into four ripeness categories: unripe, semi-ripe, ripe, and overripe. The application leverages a smartphone camera to capture images, which are then analyzed by a deep learning model trained on 1,200 annotated images, and classify coffee cherries in real-time. Model performance of the YOLOv5 computer vision was evaluated using a validation dataset (400 images) and a test dataset (400 images), ensuring balanced representation across ripeness levels. The application achieved an overall classification accuracy of 95.63%, with the highest accuracy for unripe cherries (98.50%), followed by semi-ripe (94.75%), ripe (94.75%), and overripe (94.50%) cherries. These results demonstrate the effectiveness of integrating mobile technology with object detection algorithm for field-based classification of coffee cherry ripeness. The developed application is potential for improving harvesting efficiency, optimizing quality control, and supporting decision-making in the coffee industry. Future work should focus on expanding the dataset, refining the classification model, and implementing the system in microcontrollers to enable an automatic sorting hardware, thereby reducing farmers’ workload and providing a comprehensive solution for our local stakeholders in the Bukidnon areas.

Detection of missing components on a PCB using image processing

Dominic O. Cagadas — 2025-09-01

Manual inspection of PCB components is often inaccurate and inefficient due to human error, posing a significant risk to quality control in electronic systems. This study used YOLOv8, a state-of-the-art object detection model, for PCB inspections. The system, known for its speed and accuracy, achieved an impressive of 98.3% accuracy rate across 773 instances on six component classes. The system performance was evaluated under various conditions, with 98% accuracy under ideal conditions and 96% under non-ideal conditions. Error rates rose from 1% in ideal conditions to 3% in non-ideal conditions, indicating their sensitivity to environmental factors. Feedback from students, technicians, and instructors praised the system's potential, with mean rating of 4.8 for accuracy, 4.7 for functionality, 4.8 for reliability, and 4.7 for user-friendliness. The results reveal that the system is a reliable tool for PCB verification. However, optimal camera resolution and size limits are crucial for effective inspections and component identification. This research is potential to significantly enhance efficiency and accuracy in quality control processes within the electronics manufacturing industry.