KMITL

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

Browse

Search Results

Now showing 1 - 10 of 68

Some of the metrics are blocked by your
consent settings
A Method for Road Spectrum Identification in Real-Vehicle Tests by Fusing Time-Frequency Domain Features
(2026-02-01)
Qiu, Biao
;
Jettanasen, Chaiyan
Most unpaved roads are subjectively classified as Class D roads. However, significant variations exist across different sites and environments (e.g., mining areas). A major challenge in the engineering field is how to quickly correct the Power Spectral Density (PSD) of the unpaved road in question using existing equipment and limited sensors. To address this issue, this study combines real-vehicle test data with a suspension dynamics simulation model. It employs time-domain reconstruction via Inverse Fast Fourier Transform (IFFT) and wavelet processing methods to construct an optimized model that fuses time-frequency domain features. With the help of a surrogate optimization method, the model achieves the best approximation of the actual road surface, corrects the PSD parameters of the unpaved road, and provides a reliable input basis for vehicle dynamics simulation, fatigue life prediction, and performance evaluation.
Some of the metrics are blocked by your
consent settings
Evaluation of the Climate Influence on the Thermal Characteristics of Residential Buildings in Thailand
(2026-01-01)
Lertwanitrot, Praikanok
;
Thongsuk, Surakit
;
Jettanasen, Chaiyan
;
Yoomak, Suntiti
;
Ananwattanaporn, Santipont
An increasing population causes more energy demand, resulting in an increased rate of electricity production. Thus, increasing the electricity production rate wastes more fuel resources. These limited resources are depleted if not used properly. Therefore, energy conservation is an essential point that we should be aware of. In addition, weather and geography are significant factors that directly affect the energy consumption rate. Fundamentally, cold regions use more energy for heating, while tropical areas use more energy for air conditioning. Therefore, if the energy used for these fundamental needs can be saved, it will effectively reduce the overall rate of energy use. Consequently, environmental factors that affect energy consumption, such as wind flow direction, building orientation, and pressure, were observed. The observation was done by simulating in a Computational Fluid Dynamics (CFD) program. At the same time, an energy-saving method is also proposed in this paper. The results showed that the proposed method can reduce the energy consumption rate, which is beneficial for the development of energy management systems in the future.
Some of the metrics are blocked by your
consent settings
An Evaluation Study on Electric Appliance Characteristics and Load Patterns in Residential Buildings
(2026-01-01)
Thongsuk, Surakit
;
Songsukthawan, Panapong
;
Ananwattanaporn, Santipont
;
Sottiyaphai, Chayanut
;
Ngaopitakkul, Atthapol
Energy usage in residential buildings has been constantly increasing as work-from-home trends continue to maintain popularity. To improve energy efficiency, the load profile and electric appliances in households need to be established and analyzed. This study aims to evaluate the characteristics of electric appliances that are commonly used in residential buildings under various operating conditions. An experimental setup with household electric appliances was built, and power quality meters were installed to assess the patterns under various operating conditions. In addition, the usage patterns were used to construct the daily load profile and analyze the energy consumption in residential buildings. The results demonstrate that load patterns constructed from actual measurements can achieve an accurate depiction of energy usage in residential buildings. The obtained load profile can be used in load control to improve energy efficiency and the application of renewable energy in demand reduction.
Some of the metrics are blocked by your
consent settings
Comparative Study between On- and Off-Grid Photovoltaic to Reduce Peak Demand in Residential Houses
(2026-01-01)
Jettanasen, Chaiyan
;
Sottiyaphai, Chayanut
;
Bunjongjit, Sulee
;
Songsukthawan, Panapong
;
Phannil, Natthanon
This study proposes a programmable logic controller (PLC)-based energy management system integrated with an off-grid photovoltaic (PV) system and battery storage to reduce residential peak demand. The proposed system dynamically manages power supply between the distribution grid, PV generation, and battery storage based on real-time power demand measurements. When the measured power exceeds a predefined threshold, stored renewable energy is utilized to support high-load conditions and mitigate peak demand. Experimental results obtained from a residential-scale test system demonstrate that the proposed off-grid PV system with PLC control can reduce peak demand by up to 29.68% and 15.57% under office-working and work-from-home scenarios, respectively, compared with conventional grid supply and on-grid PV systems without storage. In addition, the system achieves electricity cost reductions of up to 13.63% under Time-of-Use tariffs and up to 11.42% under normal electricity rates, depending on load behavior. These results indicate that integrating PLC-based control with off-grid PV and battery storage can effectively mitigate residential peak demand and reduce electricity expenses under realistic operating conditions.
Some of the metrics are blocked by your
consent settings
Transient Analysis to Distinguish Mechanically Switched Capacitors Using Discrete Wavelet Transform and Artificial Intelligence
(2026-01-01)
Thongsuk, Surakit
;
Bunjongjit, Sulee
;
Yoomak, Suntiti
;
Ananwattanaporn, Santipont
;
Jettanasen, Chaiyan
Capacitor banks are widely used in modern power systems for reactive power compensation and voltage regulation. However, switching operations of mechanically switched capacitors (MSCs) can generate transient phenomena, such as inrush currents, which may resemble fault currents and lead to misoperation of protection systems. Therefore, accurate detection and classification of transient events are essential for reliable system operation. This study proposes a hybrid approach for transient signal analysis and classification by integrating the discrete wavelet transform (DWT) with artificial intelligence (AI) techniques, including probabilistic neural networks and fuzzy inference systems (FIS). The DWT performs time–frequency analysis to extract multi-scale wavelet features from three-phase current signals. The proposed method enables both discrimination between inrush and fault currents and multi-class classification of transient events among six capacitor switching conditions, namely base case, pre-insertion resistor, pre-insertion inductor, current limiting reactor, 6% reactor, and synchronous closing. The methodology is validated using PSCAD/EMTDC simulations under isolated and back-to-back capacitor switching scenarios. The results demonstrate that the proposed DWT–AI approach achieves high classification accuracy exceeding 95%, outperforming conventional methods based on DWT alone and DWT combined with FIS. Furthermore, the proposed method improves protection system performance by reducing false tripping caused by transient inrush currents, while maintaining reliable fault detection capability. The findings confirm that integrating time–frequency signal processing with AI-based classification provides an effective and practical solution for transient event discrimination in MSC capacitor bank systems.
Some of the metrics are blocked by your
consent settings
Research on YOLOv5s-Based Multimodal Assistive Gesture and Micro-Expression Recognition with Speech Synthesis
(2025-12-01)
Li, Xiaohua
;
Jettanasen, Chaiyan
Effective communication between deaf–mute and visually impaired individuals remains a challenge in the fields of human–computer interaction and accessibility technology. Current solutions mostly rely on single-modal recognition, which often leads to issues such as semantic ambiguity and loss of emotional information. To address these challenges, this study proposes a lightweight multimodal fusion framework that combines gestures and micro-expressions, which are then processed through a recognition network and a speech synthesis module. The core innovations of this research are as follows: (1) a lightweight YOLOv5s improvement structure that integrates residual modules and efficient downsampling modules, which reduces the model complexity and computational overhead while maintaining high accuracy; (2) a multimodal fusion method based on an attention mechanism, which adaptively and efficiently integrates complementary information from gestures and micro-expressions, significantly improving the semantic richness and accuracy of joint recognition; (3) an end-to-end real-time system that outputs the visual recognition results through a high-quality text-to-speech module, completing the closed-loop from “visual signal” to “speech feedback”. We conducted evaluations on the publicly available hand gesture dataset HaGRID and a curated micro-expression image dataset. The results show that, for the joint gesture and micro-expression tasks, our proposed multimodal recognition system achieves a multimodal joint recognition accuracy of 95.3%, representing a 4.5% improvement over the baseline model. The system was evaluated in a locally deployed environment, achieving a real-time processing speed of 22 FPS, with a speech output latency below 0.8 s. The mean opinion score (MOS) reached 4.5, demonstrating the effectiveness of the proposed approach in breaking communication barriers between the hearing-impaired and visually impaired populations.
Some of the metrics are blocked by your
consent settings
An approach to energy conservation in lighting systems using luminaire-based sensor for automatic dimming
(2025-12-01)
Jettanasen, Chaiyan
;
Thongsuk, Surakit
;
Sottiyaphai, Chayanut
;
Songsukthawan, Panapong
;
Chiradeja, Pathomthat
Lighting systems account for a significant proportion of energy consumption in buildings. Therefore, energy conservation within these systems can greatly enhance overall building energy efficiency. This study proposes a control strategy for LED lamps by adjusting lighting intensity and improving the performance of electric luminaires. The approach involves implementing an automated dimming system that adapts lighting intensity based on surrounding light levels. A system comprising an ambient light sensor, microcontroller, power supply module, dimming controller, and lamp was developed. The sensors measure brightness within a specified range in real time, and the microcontroller analyzes and compares this data against the brightness settings for specific areas. The designed control system was tested in a laboratory setup to demonstrate its effectiveness in a controlled environment. Results showed a 75.65% reduction in power consumption compared to standard lamps in a simulated environment, highlighting its potential for significant energy savings in buildings and its contribution to environmental sustainability.
Some of the metrics are blocked by your
consent settings
Constrained Nonlinear Control of Semi-Active Hydro-Pneumatic Suspension System
(2025-09-01)
Qiu, Biao
;
Jettanasen, Chaiyan
Aiming at the characteristics of limited actuation capability of the semi-active control system and strong nonlinearity of the hydro-pneumatic suspension, a constrained nonlinear control strategy of a semi-active hydro-pneumatic suspension system is proposed. According to the mathematical model of nonlinear hydro-pneumatic suspension, the static stiffness and linear damping coefficient based on the equivalent energy are calculated, and then the control-oriented dynamic equation whose expression minimizes the nonlinear term is constructed. Combined with actuation capacity constraints, an optimization model with constraints is established to minimize the deviation between the actual overall control force and the expected optimal control force, and the optimal approximation from nonlinear control to linear quadratic optimal control is realized. The control simulation results of various methods show that the nonlinear control with constraints of the semi-active hydro-pneumatic suspension system, which effectively combines the actuation capacity constraints and nonlinear characteristics of the system, achieves a good comprehensive control effect for the nonlinear suspension control with constraints.
Some of the metrics are blocked by your
consent settings
Sign Language Sentence Recognition Using Hybrid Graph Embedding and Adaptive Convolutional Networks
(2025-03-01)
Chiradeja, Pathomthat
;
Liang, Yijuan
;
Jettanasen, Chaiyan
Sign language plays a crucial role in bridging communication barriers within the Deaf community. Recognizing sign language sentences remains a significant challenge due to their complex structure, variations in signing styles, and temporal dynamics. This study introduces an innovative sign language sentence recognition (SLSR) approach using Hybrid Graph Embedding and Adaptive Convolutional Networks (HGE-ACN) specifically developed for single-handed wearable glove devices. The system relies on sensor data from a glove with six-axis inertial sensors and five-finger curvature sensors. The proposed HGE-ACN framework integrates graph-based embeddings to capture dynamic spatial–temporal relationships in motion and curvature data. At the same time, the Adaptive Convolutional Networks extract robust glove-based features to handle variations in signing speed, transitions between gestures, and individual signer styles. The lightweight design enables real-time processing and enhances recognition accuracy, making it suitable for practical use. Extensive experiments demonstrate that HGE-ACN achieves superior accuracy and computational efficiency compared to existing glove-based recognition methods. The system maintains robustness under various conditions, including inconsistent signing speeds and environmental noise. This work has promising applications in real-time assistive tools, educational technologies, and human–computer interaction systems, facilitating more inclusive and accessible communication platforms for the deaf and hard-of-hearing communities. Future work will explore multi-lingual sign language recognition and real-world deployment across diverse environments.
Some of the metrics are blocked by your
consent settings
Exploration of Sign Language Recognition Methods Based on Improved YOLOv5s
(2025-03-01)
Li, Xiaohua
;
Jettanasen, Chaiyan
;
Chiradeja, Pathomthat
Gesture is a natural and intuitive means of interpersonal communication. Sign language recognition has become a hot topic in scientific research, holding significant importance and research value in fields such as deep learning, human–computer interaction, and pattern recognition. The sign language recognition process needs to ensure real-time performance and ease of deployment. Based on these two requirements, this paper proposes an improved YOLOv5s-based sign language recognition algorithm. Firstly, the lightweight concept from ShuffleNetV2 was applied to achieve lightweight characteristics and improve the model’s deployability. The specific improvements are as follows: The algorithm achieved model size reduction by removing the Focus layer, using the ShuffleNetv2 algorithm, and then channel pruning YOLOv5 at the head of the neck layer. All the convolutional layers and the cross-stage partial bottleneck layer with three convolutional layers in the backbone network were replaced with ShuffleBlock, the spatial pyramid pooling layer and a subsequent cross-stage partial bottleneck layer structure with three convolutional layers were removed, and the cross-stage partial bottleneck layer module with three convolutional layers in the detection header section was replaced with a depth-separable convolutional module. Experimental results show that the parameters of the improved YOLOv5 algorithm decreased from 7.2 M to 0.72 M, and the inference speed decreased from 3.3 ms to 1.1 ms.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results