The 2011 flood in Thailand exposed significant vulnerabilities in industrial areas, highlighting the necessity for enhanced disaster risk management through Area-Business Continuity Management (Area-BCM). This preliminary study focuses on identifying how stakeholders rely on information from each other to improve disaster preparedness and response. The research involves systematically identifying Area-BCM stakeholders and designing interview questions, which are evaluated by experts using the Index of Item-Objective Congruence (IOC) to ensure relevance and clarity. All interview questions surpassed the IOC threshold of 0.5, confirming their effectiveness in capturing information interdependencies. Expert feedback led to refinements in the questions, underscoring the importance of tailored data collection. This initial plan provides a critical foundation for understanding information interdependence and highlights the importance of well-designed data collection methods. The findings have significant implications for developing more resilient disaster management strategies in industrial areas, emphasizing the need for precise and relevant stakeholder communication to enhance Area-BCM effectiveness.
In the medical field, the “respiratory rate” of hospitalized patients is measured as one of the vital signs. Respiratory rate is one of the most important items. However, measurement respiratory rate is many burdens of medical personnel because it is done visually. We investigate a method to automatically measure respiratory rate to reduce the burden of medical personnel. An object detection algorithm is applied to the images obtained from the video camera. It is found that it is possible to measure respiratory rate by detecting the width of the subjects bounding box obtained by this method. We propose a method for measuring respiratory rate using this method.
Depression among university students is a critical mental health issue that significantly impacts their academic performance, social interactions, and overall well-being. This study investigates the efficacy of machine learning (ML) and deep learning (DL) models in measuring depression, a significant global mental health concern. Leveraging depression data (PHQ-9) from a survey conducted in the 15 top-ranked universities, our research aims to contribute to students' mental health awareness and support systems with cutting-edge technology. A wide range of ML and DL models are evaluated for this task. Performance is assessed using conventional metrics (e.g., accuracy, precision, and recall), as well as using explainable AI (XAI) to measure the feature extraction capabilities of the models in relation to their prediction accuracy across different dataset sizes. It has revealed that DL models focused more on clinically relevant features in the case of measuring depression. Considering feature importance and performance metrics, different models are applicable for different scenarios, however, overall LSTM, CNN, and SVM are the three top-performing models. Additionally, we found that a hybrid approach, using CNN for feature selection followed by SVM for classification helps to improve the overall accuracy from 0.979 to 0.984. By investigating and bench-marking both ML and DL models, this research establishes a comprehensive basis for the development of effective and easy-to-use AI-based depression measurement tools. Therefore, this study contributes to the early detection and prevention of students' academic depression and supports the well-being of society at large.
This research employed music information retrieval to develop a system for recognizing and classifying Philippine Indigenous Musical Instruments using Custom CNN and VGG-16 architectures. Audio samples were collected from the Katunog database, UPCE archives, and a live recording. The VGG-16 model consistently achieved higher accuracy and F1-scores than the Custom CNN for both individual and family instrument classification, regardless of whether Mel Spectrogram or MFCC data were used. Mel Spectrogram performed better on both CNN architectures. Additionally, most models exhibited higher performance metrics at a k-value of 10 for k-fold cross-validation. The PIMIs were then characterized in terms of timbre and pitch to explore their uniqueness. When using Self-Organizing Maps, MFCC and Mel Spectrogram data showed strong clustering, explaining the high performance of CNN models in recognition and classification tasks.
Recent advancements in artificial intelligence (AI) have led to the development of innovative personalized intelligent assistants such as Google Home and Siri. Despite these technological strides, the integration of established design frameworks and user experience (UX) principles in user-centric AI applications remains insufficiently explored. This study utilizes the design thinking methodology-emphasizing empathy, ideation, and prototype testing-and existing UX laws to develop ‘TimeSync,’ an AI-based smart time management application university students in Thailand. ‘TimeSync’ employs a machine learning model to customize schedules and alarms by incorporating variables such as preparation time, weather, and traffic conditions, ensuring users arrive on time. Usability testing based on specific user satisfaction and usability metrics revealed that ‘TimeSync’ offers an intuitive interface and enhances user experience, promoting consistent utilization for effective time management. These findings demonstrate the significant potential of design thinking and UX principles in crafting user-centric AI applications, providing valuable insights and a robust framework for future AI development.
Word stressing and spacing to convey the meaning is an important part of speaking English. Audiences are more likely to engage with a speaker who uses proper word stress and spacing. Stress can be observed from louder pronunciation, and higher frequency. Space can be observed from breathing and the length of time before starting a new sentence. These things, if those who would like to practice English are inexperienced or do not listen to native speakers often, they may not be able to remember the points of stressing and spacing correctly. As a result, speech does not flow smoothly. Nowadays, there are no tutorials or visualizations that clearly point out where the spacing is. For this reason, the organizer decided to create a program that would identify word stress and spacing to display on a dashboard that would be developed into a website in the future.
Reconstructing a Business Process Model (BPM) diagram automatically from an existing one is crucial. This task can be done using a robust similarity measurement method. The similarity of BPM diagrams can be measured in semantic and structural aspects. BPM diagrams are typically divided into two main components: properties and relationships. This study proposes a method that determines weighted metadata using the pairwise comparison (PWC) method to measure the similarity of BPM diagrams. These weights will calculate lexical and vector information similarity from each BPM diagram metadata. In implementing this method, parameter weights were determined in 10 BPM diagram similarity measurement cases. The results indicated a property weight value of 0.56 and a relationship weight value of 0.44. This study experimented with the method on three instances ofBPM diagram similarity, which yielded 61 %, 68%, and 79% similarity results. Based on the results, our proposed method indicates that property and relationship weighting could be used to measure the similarity between BPM diagrams.
Recommender systems are essential for enhancing user experiences on digital platforms, but they often struggle with suggesting items lacking interaction data, known as the cold-start problem. This study introduces “LLM-search,” a novel method combining language models (PaLM -2) with data augmentation techniques to address this challenge. LLM -search analyzes users' interactions to identify an item most likely to be the next purchase. It then employs the BM25 search engine to find relevant cold items based on the items identified, which effectively creates synthetic cold item interactions for training the recommender model. The effectiveness of this method is demonstrated through experiments on the 2018 Amazon review dataset in the sports and outdoor category. The method improved recommendations for cold items at various recall values. However, there was a slight decrease in performance for warm items in some cases. This study demonstrates that the LLM -search method can enhance cold item recommendation recall, offering a novel solution to the persistent cold-start problem in recommender systems.
Forest fires have a significant impact on ecosystems and human life, especially in northern Thailand, where Chiang Mai is severely affected. Traditional methods for detecting forest fires have limitations, so there is a need for advanced simulation models. This research uses Agent-Based Modeling (ABM) to develop a forest fire simulation for Chiang Mai. The methodology involves collecting historical data, performing Multiple Regression Analysis, designing the simulation, and testing it. Data from 1998 to 2021, including temperature, relative humidity, wind speed/direction, burn area, and slope, were collected from various sources. Multiple regression analysis identified wind speed as the most significant factor affecting burn area. The forest fire simulation, designed using ZF Wang's spread model and tested with AnyLogic, showed that wind direction and speed are crucial in fire spread. The simulation accurately predicted high-risk areas, helping in proactive planning and response. This study confirms that wind is a critical factor in forest fire spread, providing a valuable tool for fire districts to improve preparedness and management. Future research should focus on refining the model with localized data and integrating real-time detection to improve its accuracy and applicability.
Multiple-input multiple-output (MIMO) wireless communication systems are susceptible to the intermodulation of the multiple signals received and strong blockers, neces-sitating high in-band and out-of-band (OOB) linearity. This work introduces a mixer-first front-end architecture that in-corporates a trans-impedance amplifier (TIA) with a capacitive positive feedback technique to leverage second-order filtering, thus improving the resilience of the receiver (RX) to spectral blockers. The RX is designed using 22-nm FD-SOI technology and demonstrates excellent input matching across the frequency range of 60–90 GHz. Moreover, the RX achieves a conversion gain of 19 dB while maintaining a moderate noise figure (NF). This gain is accomplished by cascading an amplifier to the TIA and employing the complementary derivative superposition technique to enhance the in-band input third-order intercept point (IIP3). The RX exhibits minimum in-band IIP3 of 4.9 dBm and OOB IIP3 of 42 dBm. indica ting improved linearity performance.
One of the problems faced by engineering and science students is focusing solely on technical knowledge while needing more cultural context. In today's interconnected world, addressing global challenges necessitates collaborative efforts from individuals across nations. Accordingly, a joint course between Chulalongkorn University in Thailand and the Tokyo Institute of Technology in Japan has been established. The recent theme of the course, “Gamification towards Sustainable Development Goals (SDGs),” aimed to foster global citizenship and address SDGs through multicultural collaboration. This study examines the similarities and differences in problem identification between Thai and Japanese student groups participating in the course. Data was collected from discussions, presentations, and group assignments throughout the course. The findings indicate that while both groups share common concerns, such as waste management, language barriers, and transportation issues, their perspectives and proposed solutions are influenced by cultural characteristics. Thai students emphasized infrastructural inadequacies and local traditions, whereas Japanese students focused on efficiency and the impacts of tourism. The study highlights the importance of understanding cultural nuances in collaborative international projects to achieve effective and innovative solutions to global challenges.
The integration of cognitive radio (CR) technology within dual satellite networks presents a compelling solution for dynamic spectrum sharing. When a geostationary (GEO) satellite is the primary user, spectrum sensing can be conducted either on the ground or by a Low Earth Orbit (LEO) satellite. When utilising a LEO satellite for sensing, it becomes imperative for it to detect multiple GEO spot beams concurrently, given that a LEO footprint covers multiple GEO spot beams on the ground. A dedicated spectrum sensing platform is developed to investigate this capability, enabling synchronised sensing at two locations within Australia, which are served by two distinct GEO spot beams. This research aims to explore the feasibility and advantages of LEO-centric spectrum sensing within cognitive dual GEO-LEO satellite networks.
The IP Multimedia Subsystem (IMS) refers to the standard for a telecommunication system that controls multimedia services accessing different networks. IMS is integrated in both 4G and 5G networks to enable packet-switched voice calls service. The design of the IMS system always needs to be completed before developing any functions of the system. Choosing of database model is an important part of designing the system, and there are some models of database implementation, such as centralized databases and distributed databases. Moreover, both centralized and distributed databases have some advantages and drawbacks. Each type of database requires different techniques to store and search the users' information. The database implementation and these techniques are described in detail in the manuscript. Besides, simulation of each database implementation is also conducted to evaluate the databases' performance. With the performance comparison between centralized and distributed databases, the IMS system can be optimized by choosing a suitable database model.
Comparator-based active rectifier is often used in piezoelectric energy harvesting applications. However, it has mismatch problems and leakage current or oscillation that degrades its power conversation efficiency (PCE). This paper proposes a new active rectifier that is based on an Op-amp operational amplifier to address these issues. The proposed operational amplifier in the active rectifier for piezoelectric acoustic energy harvesting applications operates as a comparator but there is no oscillation or leakage current compared to the comparator as active diodes. The rectifier is designed in 22nm FDSOI technology. Simulation shows that the novel active rectifier attains a maximum power efficiency of 94.1% at 1.2V peak-to-peak AC input voltage amplitude and 300Ω loading resistor and an output voltage of 1.18V. The rectifier achieves full chip integration without the need for any external components.
The deployment of Internet of Things (IoT) systems encompasses a wide range of applications, each with its own specific requirements. Among the hardware options, the Raspberry Pi, a single-board computer known for its affordability and adequate computing resources, has become widely adopted in these IoT applications. Raspbian, the default and most popular operating system (OS) for the Raspberry Pi, provides efficient and general management of software and hardware. However, specific IoT applications may require an OS tailored to particular needs, such as compatibility with touch screens. LineageOS, an Android-based OS, can be run on the Raspberry Pi while retaining Android features, yet its performance on this platform has not been extensively studied. This research aims to compare Raspbian and LineageOS on Raspberry Pi 4 Model B hardware. By creating a simple IoT application scenario, we investigated power consumption and system performance. The evaluation results demonstrate that Raspbian outperforms LineageOS in both power consumption and system performance.
This paper presents a design of a D-band transmission line-based power amplifier (LB-PA) which employed a pseudo-differential topology technique and utilizes the Coupled Slow-Wave Waveguides (CS-CPW) type of transmission line for impedance matching in 22nm Fully Depleted Silicon-on-Insulator (FDSOI) technology. In order to improve amplifiers' power gain for a close to $\mathrm{f}_{\max}$ operation, a differential amplifier circuit featuring two transistors connected in a common-source configuration, with capacitors that cancel out internal feedback $\mathrm{C}_{\mathrm{N}}$ is used which also enhances stability of the differential mode by counteracting the influence of parasitic gate-to-drain capacitance $\mathrm{C}_{\text{gd}}$ . The LB-PA achieves a power amplification gain $\mathrm{G}_{\mathrm{p}}$ of 32.1 dB with a PAE of 10.3% for a power consumption of 48 mW correspondingly at a 0.8V DC voltage supply. The acquired $\mathrm{P}_{\text{sat}}$ reaches 6.8 dBm while achieving a 3-dB-bandwidth of 20 GHz.
Industries in the electronics and communication sector are constantly pushing for increased device functionality. For researchers working in this field tuneability and compactness have become the critical parameter. In this study, a gyrator based Active Inductor (AI) for wide tuning range has been proposed. The design of proposed AI is based on differential configuration which can also provide high-Quality Factor (QF). By utilizing feedback coupled transconductors, the noise performance of the active inductors is improved without compromising its quality factor or increasing power consumption. Due to its strong transconductance, the differential design of the proposed AI lowers series resistance and boosts overall inductance. The proposed AI is deigned using 28 nm CMOS technology for mmWave frequency band ranging from 23–27 GHz and having the inductance of 15 nH. At a 1 V supply, it consumes 28 m W of power.
Due to the daily commutes of people by MRT trains, following the shooting incident at Paragon, the MRT system has implemented bag searches before entering the stations to look for concealed or hidden weapons. These searches are conducted manually, which sometimes may not be thorough enough and can take a significant amount of time. Especially during peak hours when many people are using the MRT, it is possible for some individuals to pass through the station without being searched. Such actions can render the security measures ineffective. Therefore, this paper proposes a study to find ways to address these issues. From the study and comparison of object detection processes for risky items, such as sharp objects or guns, in X-ray images of luggage, it was found that models such as CNN, RCNN, Detectron, RetinaNet, and Yolo achieved excellent results in object detection and recognition. The organizers plan to apply object detection techniques and improve the existing methods for detecting objects in X-ray images to be more efficient and accurate, capable of identifying a variety of risky items.
The recommendation system can help people filter out the data that users may like from the massive data, and the recommendation algorithm based on content and collaborative filtering has been widely used in the current recommendation field. Still, the recommendation result of the content-based algorithm is single and lacks innovation. However, the collaborative filtering algorithm reduces the recommendation accuracy due to the sparsity problem. In this paper, we propose a movie recommendation system based on the knowledge graph and a mixture of content-based and collaborative filtering, which will wander the path of the knowledge graph and calculate the recommendation index of movies to users in each path. Get the recommended list of the top N movies by sorting and calculating the Hit Rate and Average Reciprocal Hit Rank. The results show that the proposed recommendation model has good recommendation efficiency, where the best Hit rate and Average Reciprocal Hit Rank are 0.74 and 0.44.
Thailand's ageing population is increasingly facing challenges related to social isolation, physical and mental health, and overall life satisfaction. While digital systems such as interactive games show potential, the application of effective design frameworks and principles for elderly-friendly systems remains limited. This paper introduces “WangJung,” a mobile application developed using the design thinking methodology to assist elderly people in leveraging their skills for post-retirement services. The application facilitates meaningful activities and income generation, thereby improving community integration and quality of life for elderly people. We evaluated how design thinking fosters user-centric designs and the applicability of established UX laws and heuristics to elderly-centric digital systems. Initial usability test results indicate that “WangJung” is user-friendly, easy to use, and effective in helping elderly people find part-time jobs aligned with their interests and potentially re-integrate into society. These findings support the efficacy of design thinking in enhancing elderly user experiences and affirm the relevance of existing UX principles. The study's design recommendations can inform future research in aging and technology. Longitudinal studies are recommended to assess the long-term impact and engagement with design thinking among elderly people.
