One of the main problems in many big and crowded cities is finding parking spaces for vehicles. With IoT technology mobile applications, this paper, we propose a design development real smart system that can provide more than just information about vacant but also help user to locate space where vehicle be parked order reduce traffics area. Moreover, use computer vision detect plate number monitor vehicles area enhancing security find his/her car when he/she forgets parked. In our system,...

Purpose This paper presents a developed BIMxAR application, an integration of building information modeling (BIM) with augmented reality (AR) linked real-time online database to support the facility management work. The primary aim this research was develop and empirically examine applicability BIM-based AR (BIMxAR) application in management. Design/methodology/approach experimented maintenance work university laboratory building. experiment consisted comparison supportive tasks performed...

This study examines the spatiotemporal relationship between PM2.5 exposure and cardiorespiratory mortality across Thailand from 2015 to 2019, addressing a critical research gap in geographical coverage. Analysis of satellite-based data revealed significant correlations monthly levels mortality, with stronger effects observed central northern provinces. The association was most pronounced during dry season (November April), showing 6% increase compared other months. Areas 30.1–37.5 μg/m³...

Several methodologies have recently been proposed to enhance the performance of low-resource Neural Machine Translation (NMT). However, these techniques yet be explored thoroughly in Thai and Myanmar languages. Therefore, we first applied augmentation such as SwitchOut Ciphertext Based Data Augmentation (CipherDAug) improve NMT Second, enhanced by fine-tuning pre-trained Multilingual Denoising BART model (mBART), where denotes Bidirectional Auto-Regressive Transformer. We implemented three...

Due to the limitation of memory and computational power in embedded system, this work proposes a novel approach create useful set features for improving speech emotion recognition (SER) system. Typically, Mel Frequency Cepstral Coefficients ( MFCCs) i s w idely u sed f eatures SER In order reduce number parameters burden applications, average values MFCCs that are concatenated with delta delta-delta coefficients re t he or n rtificial neural network model (ANN) classification. The results...

For languages without word boundary delimiters, dictionaries are needed for segmenting running texts. This figure makes segmentation accuracy depend significantly on the quality of dictionary used analysis. If is not sufficiently good, it will lead to a great number unknown or unrecognized words. These words certainly reduce accuracy. To solve such problem, we propose method based decision tree models. Without use dictionary, specific information, called syntactic attribute, applied identify...

This study addresses the limited coverage of regulatory monitoring for particulate matter 2.5 microns or less in diameter (PM2.5) Thailand due to lack ground station data by developing a model estimate daily PM2.5 concentrations small regions using satellite at 1-km resolution. The employs multiple linear regression and three machine learning models finds that random forest performs best estimation over period 2011–2020. incorporates several factors such as Aerosol Optical Depth (AOD), Land...

This study addresses the limited coverage of regulatory monitoring for particulate matter 2.5 microns or less in diameter (PM2.5) Thailand due to lack ground station data by developing a model estimate daily PM2.5 concentrations small regions using satellite at 1-kilometer resolution. The employs multiple linear regression and three machine learning models finds that random forest performs best estimation over period 2011-2020. incorporates several factors such as Aerosol Optical Depth...

Driving in the wrong direction is one of main reasons that cause road accidents Thailand. To efficiently detect driving vehicles, we proposed a system can track those moving vehicles from CCTVs using deep learning and image processing techniques. Our composed two algorithms: Road Lane Boundary detection CCTV algorithm (RLB-CCTV) Majority-Based Correct Direction Detection (MBCDD). In this paper, introduced RLB-CCTV enhanced version MBCDD algorithms for detecting boundaries wrong-direction...

Creating an ontology from multidisciplinary knowledge is a challenge because it needs number of various domain experts to collaborate in construction and verify the semantic meanings cross-domain concepts. Confusions misinterpretations concepts during creation are usually caused by having different perspectives business goals experts. In this paper, we propose community-driven ontology-based application management (CD-OAM) framework that provides collaborative environment with supporting...

At present, speech emotion recognition is a challenging field of studies about emotions speakers. Speech also enhances interaction between humans and machines. In many situations (e.g. embedded systems), we have to detect in within limitation both computing memory resources. Even several previous works reported that reasonable rate can be achieved using transfer learning techniques with popular models, such as AlexNet, they suffered large model size not executed on an system. To address this...

When domain experts try to find a business solution, ambiguous terms arise within the context of discussion in multidisciplinary research group. Different meanings and relationships with various concepts cause semantics. This aims address complex problems collaborative approach presents framework based on network text analysis for detecting cross-disciplinary context. The recognizes (common presented multiple knowledge), these are visualized as network. A case study sustainable development...

In 2018, around 22,000 people were killed in road accidents Thailand and more than 80% of involved motorcycles. There are several reasons one them is motorcycles driving the wrong direction. Our paper proposes a system for surveillance to detect track moving vehicle's direction on two-way traffic roads from CCTV viewpoint using deep learning where roadside noise filtered out. The can determine whether vehicles drive correct their lane. this case, we will focus To set up system, there two...

Ontology describes concepts and relations in a specific domain-knowledge that are important for knowledge representation sharing. In the past few years, several tools have been introduced ontology modeling editing. To design develop an is one of challenge tasks its challenges quite similar to software development as it requires many collaborative activities from stakeholders (e.g. domain experts, engineers, application users, etc.) through cycle. Most existing do not provide feature support...

Around 1.3 million people worldwide die each year because of road traffic crashes. There are many reasons which cause accidents, and driving in the wrong direction is one them. In our research, we developed an autonomous framework called WrongWay-LVDC that detects wrong-way vehicles from closed-circuit television (CCTV) videos. The proposed provides several helpful features such as lane detection, correct validation, detecting vehicles, image capturing features. this work, three main...

Forex is an attractive choice for investors who admire any making profit challenges in the fluctuating market. But on other hand, it means can lose money at same time. Many look ways to reduce risks by finding price movement prediction tools. Therefore, this paper proposes Stacking Machine Learning Models predict future direction help decide and plan strategies. We experimented with comparing baseline models evaluate accuracy performance. In addition, we improve performance using Technical...

The Attention Deficit Hyperactivity Disorder (ADHD) is a complex mental health disorder that affects children's learning activities and also their relationships with other children. There are various types of ADHD symptoms, which some them can be easily recognized as indicators having difficult to specify symptoms. Generally, the average age for diagnosing in children around seven years old. It better early discover these symptoms classify so appropriate necessary treatments effectively...

It is indisputable that the process of knowledge construction and management require a lot collaborations from many stakeholders such as domain experts engineers. To effectively model in ontology representation, which can serve business applications organization's goals, we need tools to support facilitate collaborative works activities among stakeholders. In this paper, propose CD-OAM framework provides supportive environment based on development (COD) approach. framework, communicate share...