Somrawee Aramkul

Particulate pollution (PM2.5) is an important concern in Asian countries because of its health hazards. When planning outdoor activities, understanding the PM2.5 concentration measurement is essential. Because of the lower number of government-run Air Quality Monitoring Stations, other options for obtaining location-specific PM2.5 concentration values are sought.This paper proposes using photo image processing to estimate the PM2.5 concentration. This research aims to improve the efficacy and reduce the computational complexity of the PM2.5 concentration estimation process. The proposed Efficient PM2.5 estimation framework uses EfficientNet-B1 and BiLSTM to estimate PM2.5 concentrations. The Met-EfficientNet-B1-BiLSTM has been designed and implemented to incorporate the Meteorological features, temperature, wind speed, and humidity to improve the estimation accuracy further. The EfficientNet-B1 neural network is applied in the image feature vector extraction process.EfficientNet-B1, with a resolution of 240 x 240 pixels, is determined to be the optimal EfficientNet variant for a small dataset of images needed for PM2.5 concentration value estimation. The BiLSTM is used for the regression of these image features with PM2.5 concentration values to obtain the estimated PM2.5 concentration.A dataset comprising HDR and non-HDR images was explicitly created for this study to compare the types of images that improve the accuracy of PM2.5 concentration estimation and the feature extraction process. The proposed Efficient PM2.5 estimation framework reduces computational complexity and outperforms the ResNet-18-LSTM by improving efficacy by 5.75% in MAE and 11.43% in SMAPE matrices. The proposed Efficient PM2.5 estimation framework demonstrates that the mobile image can be efficiently used for PM2.5 concentration estimation. Compared to the ResNet models, the proposed Efficient PM2.5 estimation framework outperforms them in terms of computational complexity and accuracy when estimating PM2.5 concentration values using photo images.

The manufacturing industry is always exploring techniques to optimize processes, increase product quality, and more accurately identify defects. The technique of deep learning is the strategy that will be used to handle the issues presented. However, the challenge of using AI in this domain is the small and imbalanced dataset for training affected by the severe shortage of defective data. Moreover, data acquisition requires significant labor, time, and resources. In response to these demands, this research presents an intelligent internet of things (IoT) framework enriched by generative adversarial network (GAN). This framework was developed in response to the needs outlined above. The framework applies the IoT for real‐time data collection and communication, while GAN are utilized to synthesize high‐fidelity images of manufacturing defects. The quality of the GAN‐synthesized image is quantified by the average FID score of 8.312 for non‐defective images and 7.459 for defective images. As evidenced by the similarity between the distributions of synthetic and real images, the proposed generative model can generate visually authentic and high‐fidelity images. As demonstrated by the results of the defect detection experiments, the accuracy can be enhanced to the maximum of 96.5% by integrating the GAN‐synthesized images with the real images. Concurrently, this integration reduces the occurrence of false alarms.

Floods are the most frequent type of natural disaster. Flash floods are one of the most common types of floods, caused by rapid and excessive rainfall. Normally, when a flash flood occurs, the water of the upstream river increases rapidly and flows to the downstream watersheds. The overflow of water increasingly submerges villages in the drainage basins. Flash flood early warning systems are required to mitigate losses. Water level monitoring stations can be installed at upstream river areas. However, telemetry stations face several challenges because the upstream river areas are far away and lack of public utilities (e.g., electric power and telephone lines). This research proposes hybrid effortless resilient operation stations, named HERO stations, in the flash flood early warning system. The HERO station was designed and developed with a modular design concept to be effortlessly customized and maintained. The HERO station adapts its working operation against the environmental changes to maintain a long working period with high data sensing accuracy. Moreover, the HERO station can switch its communication mode between the centralized and decentralized communication modes to increase availability. The network of the HERO stations has already been deployed in the northern part of Thailand. It results in improvements of the telemetry station’s availability. The HERO stations can adapt to environmental changes. The flash flood early warning messages can be disseminated to the villagers to increase the flood preparation time and to reduce flash flood damage.