Sinchai, Ananta

Preferred name

Sinchai, Ananta

Main Affiliation

Integrated Innovative Technology

ananta.sin@kmitl.ac.th

Now showing 1 - 10 of 17

Some of the metrics are blocked by your
consent settings
Time Series Forecasting Using Transfer Learning with an Attention-Revamped Transformer: A Case Study of Financial Instruments
(2025-12-01)
Feng, Ling
;
Sinchai, Ananta
Accurate financial time series forecasting is essential for informed investment and risk management decisions. Traditional methods, including statistical techniques such as SMA, ARIMA, VAR, and LASSO, and deep learning models like LSTM and Transformer, often fall short of capturing the complex seasonal and cyclical dynamics inherent in financial data. To overcome the noted shortcomings, this study introduces a transfer learning approach utilizing an enhanced Transformer model with correlation-based attention mechanisms. This proposed model significantly improves its capacity to capture long-term dependencies and perform robust cross-market predictions. Initially trained on the Dow Jones Index, it demonstrates superior transferability to diverse asset classes, including stock indices, commodities, and cryptocurrencies. Experimental evaluations across multiple metrics, including MSE, MAE, MHD, and R<sup>2</sup>, reveal that the proposed model consistently outperforms benchmarks. Notably, it achieves outstanding predictive accuracy in BTC (MSE: 0.0352) and SET (MSE: 0.1701), establishing a strong foundation for advanced transfer learning applications in financial forecasting across varied markets.
Some of the metrics are blocked by your
consent settings
Sustainable urban waste collection using a hybrid heuristic–genetic approach: a Bangkok case study
(2026-01-01)
Hamontree, Chaowalit
;
Koiwanit, Jarotwan
;
Sinchai, Ananta
Urban waste collection is a critical component of sustainable city development, directly influencing emissions reduction, resource efficiency, and public health. This study develops a hybrid optimization framework combining a Nearest Neighbor Heuristic with a Genetic Algorithm (GA) to optimize municipal waste collection routes in Bangkok, addressing the Vehicle Routing Problem (VRP) under real-world constraints such as vehicle capacity, time windows, and traffic conditions. The optimized algorithm reduced weekly travel distance by 8.51% and increased average vehicle utilization by 7.78%, translating into projected five-year economic benefits of over 4.7 million Baht and annual GHG emission reduction equivalent to planting approximately 1,750 trees. These findings demonstrate how algorithmic optimization can advance SDG 11 (sustainable cities and communities) and SDG 12 (responsible consumption and production) by aligning technical innovation with environmental and social outcomes. Beyond Bangkok, the framework is scalable to other rapidly urbanizing contexts, offering policymakers a data-driven pathway toward inclusive, low-carbon, and effective waste management systems.
Some of the metrics are blocked by your
consent settings
Simplified Derivative-Based Carrierless PPM Using VCO and Monostable Multivibrator
(2025-06-01)
Koseeyaporn, Jeerasuda
;
Wardkein, Paramote
;
Sinchai, Ananta
;
Kaew-in, Chanapat
;
Tuwanut, Panwit
This study proposes a derivative-based, carrierless pulse position modulation (PPM) scheme utilizing a voltage-controlled oscillator (VCO) and a monostable multivibrator. In contrast to conventional PPM systems that rely on reference carriers or complex demodulation methods, the proposed architecture simplifies signal generation by directly modulating the time derivative of the message signal. The modulated signal, when processed through standard analog demodulators, inherently yields the derivative of the original message. This behavior is first established through theoretical derivations and then confirmed by simulations and circuit-level experiments. The proposed method includes a differentiator feeding into a VCO, followed by a monostable multivibrator to generate a carrierless PPM waveform. Experimental validation confirms that, under all tested demodulation approaches—integrator-based, PLL-based, and quasi-FM—the recovered output aligns with the differentiated message signal. The integration of this output to retrieve the original message was not performed to maintain focus on verifying the modulation principle. Additionally, the study aimed to ensure the consistency of derivative recovery. Signal-to-noise ratio (SNR) expressions for each demodulator type are presented and discussed in the context of their relevance to the proposed system. Limitations and directions for further study are also identified.
Some of the metrics are blocked by your
consent settings
New pulse oximetry detection based on the light absorbance ratio as determined from amplitude modulation indexes in the time and frequency domains
(2022-05-01)
Kainan, Pattana
;
Sinchai, Ananta
;
Tuwanut, Panwit
;
Wardkein, Paramote
The Pandemic COVID-19 situation, a pulse Oximetry is significant to detect a varying blood oxygen saturation of a patient who needed the device to operate with continuous, rapid, high accuracy, and immune of moving artifacts. In this article, three main schemes for low-complexity pulse oximetry detection are proposed. In the first scheme, the light absorbance ratio (R) is obtained by separating the red and infrared photoplethysmography (PPG) amplitude modulation (AM) signals from the frequency-division multiplexing (FDM) signal with two different bandpass filters (BPFs), determining the ratio of modulation index of red and infrared PPG AM signals. In the second scheme, the output PPG AM signals for the red and infrared light wavelengths from the BPFs are transformed into the frequency domain such that the AC components of both PPG AM signals are the magnitudes of the highest peaks in their respective sidebands, while the DC components are the magnitude of their carrier frequencies; then, the AC/DC ratio of the red PPG AM signal is divided by the AC/DC ratio of the infrared PPG AM signal is R. In the last scheme, the FDM signal is transformed into the frequency domain without being passed through any BPF, and R is obtained in the same way as in the same second scheme. Experimental results obtained by using the first scheme have an average error of about 0.7138%, for the second and the last scheme have an average error of about 1%, and all the methods agree with the corresponding mathematical model.
Some of the metrics are blocked by your
consent settings
Pulse Oximetry Based on Quadrature Multiplexing of the Amplitude Modulated Photoplethysmographic Signals
(2023-07-01)
Koseeyaporn, Jeerasuda
;
Wardkein, Paramote
;
Sinchai, Ananta
;
Kainan, Pattana
;
Tuwanut, Panwit
In this research, a pulse oximeter based on quadrature multiplexing of AM-PPG signals is proposed. The oximeter is operated by a microcontroller and employs a simple amplitude modulation technique to mitigate noise interference during SpO<inf>2</inf> measurement. The two AM-PPG signals (RED and IR) are quadrature multiplexed using carrier signals with equal frequencies but a 90-degree phase difference. The study focused on noise interference caused by light intensity and hand movement. The experiment was conducted under three different levels of light intensity: 200 Lux, 950 Lux, and 2200 Lux. For each light intensity level, the SpO<inf>2</inf> level was measured under three scenarios: hand still, shadow movement over the hand, and hand shaking. A comparison between the proposed technique and the conventional method reveals that the proposed technique offers a superior performance. The relative error of the measured SpO<inf>2</inf> level using the proposed technique was less than 3.1% overall. Based on the study, the proposed technique is less affected by noise interference caused by light intensity and hand movement compared to the conventional method. In addition, the proposed technique has an advantage over contemporary methods in terms of computational complexity. Consequently, the proposed technique can be applied to wearable devices that include SpO<inf>2</inf> measurement functionality.
Some of the metrics are blocked by your
consent settings
A Practical Circuit of Cyclic Chirp Spread Spectrum Modulation for Long Range Communication
(2022-01-01)
Sinchai, Ananta
;
Saelim, Nopparut
;
Pornavalai, Chotipat
;
Wardkein, Paramote
;
Tuwanut, Panwit
Various technologies have been utilized in long range communication to satisfy increasing usage of the internet of things in a wide large area. Recently, a modulating technique called cyclic chirp spread spectrum (CSS) modulation has attracted attention due to its low power usage and long-range coverage. However, a cyclic CSS circuit is complex to build. Hence, the objective of the work is to propose a practical circuit of cyclic CSS modulation. The proposed circuit is designed to complicated-free creation. To prove that the presented circuit is pragmatic, a simulation test is performed. The simulation results have illustrated that the designed circuit well generates a chirp modulating signal. Also, the proposed circuit is flexibly configurable.
Some of the metrics are blocked by your
consent settings
An Image Resizing Function Embedded in an Inverse Discrete Cosine Transform
(2022-01-01)
Sinchai, Ananta
;
Tuwanut, Panwit
Image resizing is an everyday activity and can be done in either a spatial domain or a transform domain. This work realizes that an image is commonly stored in the transform domain and the transformed image must be converted back to the spatial domain to display. This work hence proposes embedding an image resizing function based on a scaled frequency (SF) in a matrix operation of inverse discrete cosine transform (IDCT) for the sake of convenience. By adopting the proposed technique called as the SF-IDCT is not only capable of resizing the transformed image to a given resolution, but also acquiring the IDCT as a by-product. Image data can be shortened or lengthened in proportion to their frequencies by varying the frequencies of the DCT basis functions. Besides, the effects of modifying the pattern of the image data are also studied. The experimental results indicate that the SF-IDCT functions well. The proposed technique reconstructs an upsized image of equal or better visual quality than those produced by existing methods. For a downsized image, the performance of the presented approach is competitive with other available methods.
Some of the metrics are blocked by your
consent settings
Using of an Arithmetic Sequence to Estimate Undetected Existing Circle Choice Locations
(2022-01-01)
Sinchai, Ananta
;
Tuwanut, Panwit
Handling an optical mark recognition (OMR) answer sheet faces a problem of shape detection due to defections of color, resolution and shape. A typical method of shape detection thus creates false detection. The false detecting problem is that the general detecting approach fails to detect the locations of the filled shape or detects only the previous detected locations. For this work focuses on a circle choice shape. To solve such problem, an arithmetic sequence is proposed to estimate the existing circle-shaped locations undetected by the common detecting scheme. The proposed technique is verified by experimenting the OMR answer sheet having thirteen options per item. Two conditions are experimented. The first condition arbitrarily fills a circle in each item and the other one leaves the circle in each item unfilled. The experimental results have revealed that the average success rate of the proposed approach in locating the undetected existing circle shapes is 100% for both conditions.
Some of the metrics are blocked by your
consent settings
Development of a Low-Cost Automated Injection Molding Device for Sustainable Plastic Recycling and Circular Economy Applications
(2024-12-01)
Sinchai, Ananta
;
Boonyang, Kunthorn
;
Simmala, Thanakorn
In response to the critical demand for innovative solutions to tackle plastic pollution, this research presents a low-cost, fully automated plastic injection molding system designed to convert waste into sustainable products. Constructed entirely from repurposed materials, the apparatus focuses on processing high-density polyethylene (HDPE) efficiently without hydraulic components, thereby enhancing eco-friendliness and accessibility. Performance evaluations identified an optimal molding temperature of 200 °C, yielding consistent products with a minimal weight deviation of 4.17%. The key operational parameters included a motor speed of 525 RPM, a gear ratio of 1:30, and an inverter frequency of 105 Hz. Further tests showed that processing temperatures of 210 °C and 220 °C, with injection times of 15 to 35 s, yielded optimal surface finish and complete filling. The surface finish, assessed through image intensity variation, had a low coefficient of variation (≤5%), while computer vision evaluation confirmed the full filling of all specimens in this range. A laser-based overflow detection system has minimized material waste, proving effective in small-scale, community recycling. This study underscores the potential of low-cost automated systems to advance the practices of circular economies and enhance localized plastic waste management. Future research will focus on automation, temperature precision, material adaptability, and emissions management.
1
Some of the metrics are blocked by your
consent settings
Low–cost IoT–enabled organic pH control system for smart aquaponic production in urban agriculture
(2026-02-15)
Sinchai, Ananta
;
Ardkaew, Chitsanucha
;
Jaiyen, Tontrakan
This study presents a smart aquaponic system integrating low–cost IoT monitoring, automated organic pH control using food–grade orange juice, and computer vision–based plant growth assessment to enhance sustainable urban lettuce production. Two experimental rounds compared uncontrolled pH conditions with active regulation across 15 plants per group, with sample size adequacy confirmed through power analysis for large observed effects. The system maintained optimal pH (5.8–7.0) through automated feedback control of orange juice within a defined range, producing 13–30 % higher growth rates, supported by t-tests, effect sizes, confidence intervals, and regression analysis. Performance and cost efficiency were assessed against established control strategies, showing competitive outcomes under resource–limited conditions. Economic evaluation indicated a payback period of 9–59 months depending on local market factors. Overall, results demonstrate the feasibility of combining natural pH buffers with IoT feedback to reduce chemical inputs, sustain growth improvements, and enable scalable adoption in small– to medium–scale aquaponics.
1

Sinchai, Ananta

Filters

Settings

Sort By

Results per page