(1) Background: Spondylolisthesis, a common disease among older individuals, involves the displacement of vertebrae. The condition may gradually manifest with age, allowing for potential prevention by the research of predictive algorithms. However, one key issue that hinders research in spondylolisthesis prediction algorithms is the need for publicly available spondylolisthesis datasets. (2) Purpose: This paper introduces BUU-LSPINE, a new dataset for the lumbar spine. It includes 3600 patients’ plain film images annotated with vertebral position, spondylolisthesis diagnosis, and lumbosacral transitional vertebrae (LSTV) ground truth. (4) Methods: We established an annotation pipeline to create the BUU-SPINE dataset and evaluated it in three experiments as follows: (1) lumbar vertebrae detection, (2) vertebral corner points extraction, and (3) spondylolisthesis prediction. (5) Results: Lumbar vertebrae detection achieved the highest precision rates of 81.93% on the AP view and 83.45% on the LA view using YOLOv5; vertebral corner point extraction achieved the lowest average error distance of 4.63 mm on the AP view using ResNet152V2 and 4.91 mm on the LA view using DenseNet201. Spondylolisthesis prediction reached the highest accuracy of 95.14% on the AP view and 92.26% on the LA view of a testing set using Support Vector Machine (SVM). (6) Discussions: The results of the three experiments highlight the potential of BUU-LSPINE in developing and evaluating algorithms for lumbar vertebrae detection and spondylolisthesis prediction. These steps are crucial in advancing the creation of a clinical decision support system (CDSS). Additionally, the findings demonstrate the impact of Lumbosacral transitional vertebrae (LSTV) conditions on lumbar detection algorithms.

In handwriting recognition research, a public image dataset is necessary to evaluate algorithm correctness and runtime performance. Unfortunately, in existing Thai language script image datasets, there is a lack of variety of standard handwriting types. This paper focuses on a new offline Thai handwriting image dataset named Burapha-TH. The dataset has 68 character classes, 10 digit classes, and 320 syllable classes. For constructing the dataset, 1072 Thai native speakers wrote on collection datasheets that were then digitized using a 300 dpi scanner. De-skewing, detection box and segmentation algorithms were applied to the raw scans for image extraction. The experiment used different deep convolutional models with the proposed dataset. The result shows that the VGG-13 model (with batch normalization) achieved accuracy rates of 95.00%, 98.29%, and 96.16% on character, digit, and syllable classes, respectively. The Burapha-TH dataset, unlike all other known Thai handwriting datasets, retains existing noise, the white background, and all artifacts generated by scanning. This comprehensive, raw, and more realistic dataset will be helpful for a variety of research purposes in the future.

Air quality monitoring network (AQMN) plays an important role in air pollution management. However, setting up an initial network in a city often lacks necessary information such as historical pollution and geographical data, which makes it challenging to establish an effective network. Meanwhile, cities with an existing one do not adequately represent spatial coverage of air pollution issues or face rapid urbanization where additional stations are needed. To resolve the two cases, we propose four methods for finding stations and constructing a network using Euclidean distance and the k-nearest neighbor algorithm, consisting of Euclidean Distance (ED), Fixed Surrounding Sphere (FSS), Euclidean Distance + Fixed Surrounding Sphere (ED + FSS), and Euclidean Distance + Adjustable Surrounding Sphere (ED + ASS). We introduce and apply a coverage percentage and weighted coverage degree for evaluating the results from our proposed methods. Our experiment result shows that ED + ASS is better than other methods for finding stations to enhance spatial coverage. In the case of setting up the initial networks, coverage percentages are improved up to 22%, 37%, and 56% compared with the existing network, and adding a station in the existing one improved up by 34%, 130%, and 39%, in Sejong, Bonn, and Bangkok cities, respectively. Our method depicts acceptable results and will be implemented as a guide for establishing a new network and can be a tool for improving spatial coverage of the existing network for future expansions in air monitoring.

Our research proposes an approach to finding a suitable location for a motorcycle Battery Swapping Station (BSS) that considers multiple objectives. We developed a model based on Euclidean distance with K-NN, the AHP function, a desired number of stations, and GIS-based road infrastructure data. This model also considers the maximum coverage area and satisfies the number of stations and geographical features. Additionally, we consider the average driving distance of the battery swapping station location. To facilitate analysis, square grids form cells representing road type, environmental characteristics, places, and population density. Our proposed framework provides decision-makers with a multi-objective and visually optimized motorcycle BSS location, allowing for a more flexible selection of exact BSS locations shown on a map. Our demonstration can be used to resolve the uncertain problem related to finding a place for a motorcycle battery swapping station location. to finding a place for a motorcycle battery swapping station location.

Electric vehicles (EVs) are becoming an increasingly popular and competitive option for clean transportation. However, the improper location of battery charging or swapping stations has impeded the adoption of electric vehicles. In this paper, we propose a distance function using Geographic Information System (GIS) techniques to find the proper station locations in order to provide optimized area coverage. The feasibility of this model is verified by simulation of station locations in Phuket, Thailand. The set coverage model proposed is a new solution to discover the optimal location for electric vehicle charging stations across Thailand. This study aims to provide a theoretical basis for the deployment of these new charging stations.

This paper presents a speed testing platform designed to evaluate Thailand’s Internet broadband network experience. The platform measures internet speed at the ONT (Optical network terminal) as a signal source for the operator (or ISP) and the connected internet device at the user’s accommodation (fixed broadband internet). Scenario tests were conducted involving four major broadband network operators in Thailand, with our application collecting data from 30 devised-based operators and 200 internet users, resulting in a dataset of 25,000 records. The primary focus of our study was on assessing download and upload speeds, as well as latency. The proposed system was deployed in 8 provinces east of Thailand over two months. Results indicate that the Download Percentage Average (DPA) was 64.30%, while the Upload Percentage Average (UPA) was 71.84%. The average ping and jitter were 11.82 ms and 16.53 ms, respectively. Analysis revealed variations in average speed and latency values across different areas and period times, underscoring the efficacy of our system. Our proposed platform could serve NBTC as a central platform for evaluating future broadband internet services in Thailand.