KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Search Results

Now showing 1 - 10 of 18

Some of the metrics are blocked by your
consent settings
Library Seat Hogging Detection Using Hybrid Real and AI-Generated Data
(2026-01-01)
Viwatanawatanakarn, Natchanon
;
Cooharojananone, Nagul
;
Muangsin, Veera
;
Tea-Makorn, Pin Pin
;
Atchariyachanvanich, Kanokwan
Efficient management of library seating resources is a critical challenge in educational institutions, often hindered by 'seat hogging' behaviors where users occupy spaces with personal belongings without actual occupancy. Traditional manual inspections are labor-intensive and inefficient. This paper proposes an automated seat occupancy detection system utilizing existing CCTV infrastructure and Computer Vision techniques. We employ YOLOv8, a state-of-the-art object detection model, to identify two key classes: persons and belongings. To address the challenge of limited real-world datasets for specific library environments, we introduce a data augmentation strategy using AI-generated synthetic data produced by a generative model (Gemini 2.5 Pro). A rule-based algorithm is integrated to analyze the spatiotemporal relationship between detected persons and belongings, enabling the system to distinguish between 'occupied,' 'vacant,' and 'hogged' states effectively. Experimental results demonstrate that the proposed hybrid dataset approach enhances detection performance, providing a scalable and cost-effective solution for smart library management. Furthermore, a pilot system evaluation yielded an overall accuracy of 91.62%, validating the system's effectiveness for real-world deployment.
Some of the metrics are blocked by your
consent settings
Improvement of a Machine Learning Model Using a Sentiment Analysis Algorithm to Detect Fake News: A Case Study of Health and Medical Articles on Thai Language Websites
(2024-01-01)
Atchariyachanvanich, Kanokwan
;
Saengkhunthod, Chotipong
;
Kerdnoonwong, Parischaya
;
Chanlekha, Hutchatai
;
Cooharojananone, Nagul
These days, the problem of fake news has grown to be a major social and personal concern. With the amount of information generated through social media, it is very crucial to be able to detect and properly take care of that fake information. Previous studies proposed a machine learning model to detect fake news in online Thai health and medical articles. Still, the problem of detecting fake news with similar content but different objectives exists, and the accuracy of the model needs improvement. Therefore, this study aims to solve these problems by adding 33 new features, including textual features, sentiment-based features, and lexicon features, i.e., herbs, fruits, and vegetables, to identify the objective of an article. We trained and tested the model’s prediction accuracy on a new dataset containing 582 reliable and 435 unreliable (fake news) articles from eight Thai websites. Our improved classification model using XGBoost with Lasso, the best feature selection method, achieved an accuracy of 97.76% without over-fitting, reflecting a 7.16% improvement over our earlier model.
Some of the metrics are blocked by your
consent settings
BMA for the BMA: Boosting Mobility Analysis for the Bangkok Metropolitan Administration via Automated Pedestrian Counting from CCTV
(2024-01-01)
Kujareanpaisal, Poonnaphop
;
Mayhasap, Rujira
;
Tea-Makorn, Pin Pin
;
Jindahra, Pavitra
;
Starita, Stefano
The objective of detecting and counting people using the CCTV camera on the footpath is to facilitate and reduce the time required to count the number of people traveling in pedestrian areas without having to actually visit the area. This paper uses the head detection technique to solve the problem of overlapping objects, YOLOv8n for detection and BoT-SORT for object tracking. A program was developed to assist the Bangkok Metropolitan Administration in counting the number of people within the region of interest and visualizing the statistics. Users can view statistics in the form of visual charts to compare the maximum number of people in each period by importing the video into the program. Users can also view historical statistics from previously imported videos. This program enables users to monitor pedestrian traffic in each area, providing valuable insights for urban planning decisions.
Some of the metrics are blocked by your
consent settings
Comparative Foot Traffic Analysis During Normal Periods and Firework Events Using Wi-Fi Sensors
(2024-01-01)
Traganmaturapot, Peerada
;
Sonehara, Noboru
;
Hiruma, Nobuharu
;
Cooharojananone, Nagul
;
Kodate, Akihisa
Recent observations indicate an increase in the frequency of crowd crush incidents, highlighting the urgent need for effective mitigation strategies. Addressing this issue necessitates a comprehensive understanding of the factors influencing visitor decision-making to prevent adverse outcomes such as crowd crushes. This study introduces a Streamlit dashboard designed to visualize foot traffic data in the Sendagaya area and integrates contextual data from 10 key factors, including events and locations, points of interest (POIs), periods of time, online search activity, height of buildings, temperature and weather conditions, currency exchange rates, earthquakes, number of international flight arrivals, and hotel room rates. This integration facilitates comparative analysis of foot traffic patterns during standard periods versus periods coinciding with significant events, such as the 2023 Jingu Gaien Fireworks Festival, to assess their impact on congestion levels. Conducted exclusively in Sendagaya, the study utilized 8 Wi-Fi sensors throughout August 2023, encompassing 3 key stages: data collection, preprocessing, and dashboard development. The analysis revealed significant determinants-including events, points of interest, time periods, and online activity-that influence visitor foot traffic, while other factors exhibited no discernible impact. These findings have important implications for enhancing decision-making processes, preparedness measures, risk management strategies, and data-driven policymaking for sustainable tourism development.
Some of the metrics are blocked by your
consent settings
Exploring User Attitudes and Innovative System Design for Remote Lighting Control Systems in Thailand's Creative Industries
(2024-01-01)
Jeerasottikule, Thammanoon
;
Cooharojananone, Nagul
;
Atchariyachanvanich, Kanokwan
In this paper, the authors investigate the current state of the lighting design and control sector in Thailand's creative industry. The government aims to promote the creative industry as a key source of income, but there needs more skilled professionals in the industry. The authors have found that successful cases have used the Internet for remote controlling in the creative industry in other countries. Therefore, the paper will explore the potential of using technology to improve professional efficiency and assess the feasibility of implementing remote lighting control systems via the Internet with Thai lighting designers and lighting console operators. Data will be collected through qualitative in-depth interviews and quantitative surveys. The results have shown a promising acceptance rate of wireless devices for lighting control due to their mobility, flexibility, cost-effectiveness, and positive attitudes toward adopting Internet technology. The authors have also proposed a concept design for an internet-based control system tailored to Thai users, focusing on simplicity, ease of connection, and user-friendliness to accommodate those with limited network configuration knowledge. The proposed system aims to reduce professionals, save time, and increase convenience, leveraging Thailand's extensive wireless internet coverage. These systems could significantly benefit Thailand's creative industry by addressing the shortage of skilled professionals and improving efficiency.
Some of the metrics are blocked by your
consent settings
Foot Traffic Analysis Using Wi-Fi Sensor During the Tokyo 2020 Olympics and Paralympics
(2023-01-01)
Traganmaturapot, Peerada
;
Sonehara, Noboru
;
Hiruma, Nobuharu
;
Cooharojananone, Nagul
;
Jirapongwanich, Jirakit
Various real-world factors, such as time, weather, distance, environment, the COVID-19 pandemic, or even protests, can all impact human decision-making. However, restrictions and unexpected occurrences may also influence people's decisions regarding their path at any given time. These factors can lead to challenges in managing foot traffic at largescale events. In response to these challenges, this paper proposes a data-driven web-based foot traffic management supporting dashboard for large-scale events based on limited pedestrian count data, consisting of sensor name, latitude, longitude, MAC address, Datetime, and RSSI, collected by Wi-Fi sensors around the Sendagaya area during the Tokyo 2020 Olympics and Paralympics. The results confirmed that our proposed web-based dashboard contributes to human behavior understanding and decision-supporting policymaking for foot traffic management, which improves the design of spectator movement between transportation and venues in large-scale events. Furthermore, the dashboard is valuable from various perspectives, including preventing crowd crushing, redesigning areas to increase engagement in the shopping district, and improving traffic management.
Some of the metrics are blocked by your
consent settings
Adaptive big data maturity model using latent class analysis for small and medium businesses in Thailand
(2022-11-15)
Limpeeticharoenchot, Santisook
;
Cooharojananone, Nagul
;
Chavarnakul, Thira
;
Charoenruk, Nuttirudee
;
Atchariyachanvanich, Kanokwan
Big data analytics (BDA) is widely adopted in large enterprises. However, very few small- and medium-sized enterprises (SMEs) have adopted BDA because they lack the relevant knowledge, which makes BDA development expensive and unsuitable. A big data maturity model (BDMM) is a tool for assessing the stage for using big data in a company, and it acts as a guide for improvement. However, most BDMMs are designed for large enterprises using rule-based scoring, which is static over time. Developing a suitable BDMM for SMEs is a challenging task for professionals in terms of acquiring small-scale expertise owing to the lack of case studies for verifying the maturity level. This study proposes a new BDMM for Thai SMEs and a new methodology for developing a dynamic model using latent class analysis (LCA), which explains the behaviour of each latent class and provides non-rule-based scoring. We define four types of capabilities in SMEs: organizational and attitude factors, information technology, technology, and people readiness. Data are collected from 135 SMEs in Thailand. We introduce a methodology for developing multiple building stages of the BDMM. Further, we experiment with several clusters suitable for SMEs using statistic-based and data visualization approaches. The proposed BDMM is validated via a secondary evaluation of 11 firms, nine months after the initial evaluation. Further, we introduce a web-based application for respondents to obtain their firm's assessment results. The visualization-based result helps the respondents compare their business with other companies at the same or higher maturity level. In summary, SMEs can use the proposed BDMM to plan for continuous self-improvement and thus optimize their business using BDA to maximize its value to the organization.
Some of the metrics are blocked by your
consent settings
A Study of Using the IoT-based Angklung Smart Band System to Support Music Group Activities for the Elderly in Nursing Homes
(2022-01-01)
Cooharojananone, Nagul
;
Phoasavadi, Pornprapit
;
Hiranpanthaporn, Saranya
;
Wongratanapitak, Paphutsorn
;
Atchariyachanvanich, Kanokwan
Angklung, the Indonesian musical instrument, has been used to promote the well-being of the elderly with music group activities. This leads to a shortage of hand sign angklung music experts in the city. This musical group activity is not widely utilized. The 'Angklung Smart Band' is an IoT-based solution designed to assist angklung music experts or nursing home caregivers in Thailand in supporting angklung music group activities for the elderly. The system consists of a web application, Internet of Things devices, and angklung musical instruments linked through a wireless network. In this study, we evaluated the use of the angklung smart band to facilitate music group activities for the elderly in nursing homes. We compared the outcomes to the conventional hand sign method for promoting music group activities. We assessed the use of a smart band system with two groups of the elderly: a home group and a bedridden group. The results revealed that this approach is more appropriate for the home group than the bedridden group, since they can independently participate in music group activities. Consequently, the expert can focus on interaction with other elderly in order to ensure that all the elderly are always engaged in activities. A statistical analysis of the playing accuracy percentage showed that the smart band system can execute angklung music group activities as well as the hand sign method.
Some of the metrics are blocked by your
consent settings
Innovative Mobile Application for Measuring Big Data Maturity: Case of SMEs in Thailand
(2020-01-01)
Limpeeticharoenchot, Santisook
;
Cooharojananone, Nagul
;
Chavarnakul, Thira
;
Tuaycharoen, Nuengwong
;
Atchariyachanvanich, Kanokwan
A Big Data maturity model (BDMM) is one of the key tools for Big Data assessment and monitoring, and a guideline for maximizing the usage and opportunity of Big Data in organizations. The development of a BDMM for SMEs is a new concept and is challenging in terms of development, application, and adoption. This article aims to create the novel online adaptive BDMM via responsive web application for SMEs. We develop the BDMM API and a responsive web application for easy access via mobile phone. We developed a model by analyzing the factors impacting the success of implementing Big Data Analytics (BDA) in SMEs based on literature reviews. The model was verified by conducting a survey of 180 SMEs in Thailand, interviewed against four extracted domains. Then, the scoring and classified levels for the model was developed through Latent Class Analysis (LCA) to depict four levels of each domain and four final maturity levels to create an adaptive model. As the experimental results with 33 users including executive officers, managers, IT, and data analytic officers. The user acceptance for our mobile application using TAM indicates that executive officer's group and non-executive group satisfied perceived usefulness, perceived ease of use, and intention to use factor. Use cases of the application include SMEs monitoring for their Big Data Analytics capability for improvement, and the Government Agency providing proper support on SMEs’ level of competency.
Some of the metrics are blocked by your
consent settings
Bridge Sub Structure Defect Inspection Assistance by using Deep Learning
(2019-10-01)
Kruachottikul, Pravee
;
Cooharojananone, Nagul
;
Phanomchoeng, Gridsada
;
Chavarnakul, Thira
;
Kovitanggoon, Kittikul
Road transportation is the most popular transportation in Thailand, which the top two highest traffic are the region-to-region highways; and then inter-city highways. Therefore, the regular maintenance is required to maintain the good condition due to road safety. The most significant process of bridge inspection procedures is sub structure inspection, which requires visual inspection as an initial step. This process is used to quick determine the damage severity i.e. appearance and crack that may cause damage to the structure strength. The current process requires that the experienced maintenance engineer to be on the field in order to visual inspect and estimate whether the maintenance is required. Yet, due to the limitation of number of expert engineers to be on the field, the photo verification is introduced to assist them so that they are no need on every inspection site. However, using human to verify has no standard and uncontrollable. They need to have experience and good knowledge. As well as it is highly depended on individual decision-making skill. Thus, in this paper, the deep learning technique will be presented to assist the expert for quality inspection process of bridge sub structure images. That is using image enhancement and then image splitting and overlapping for image pre-processing. After that applying CNNs for object classification. As a result, the total accuracy is 89% based on 3926 dataset.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results