KMITL

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

Browse

Search Results

Now showing 1 - 6 of 6

Some of the metrics are blocked by your
consent settings
DEVELOPING A MACHINE LEARNING FORECASTING FRAMEWORK FOR EXCHANGE RATES IN THE CONTEXT OF CROSS-BORDER BUSINESS
(2025-01-01)
Chen, Wei
;
Rojniruttikul, Nuttawut
Traditionally, this matter was regarded as a largely technical undertaking; however, recent market disruptions have demonstrated that the issue extends far beyond purely technical considerations. This study addresses the subject from two interconnected perspectives. The first concern centers upon the capacity of different Machine Learning (ML) models to maintain performance during periods in which financial markets deviate from conventional behavioural patterns. The second concern focuses on the way professionals who depend upon such predictive outputs interpret, evaluate, and integrate these forecasts into routine operational decision-making. The empirical findings revealed that several ML approaches, particularly Long Short-Term Memory (LSTM) architectures and selected ensemble-based methods, adapted more consistently to abrupt market fluctuations than the econometric benchmark models employed within the study. Such resilience became especially apparent throughout the COVID-19 crisis, when exchange-rate dynamics departed substantially from the assumptions underpinning traditional forecasting frameworks. The interview findings produced a somewhat different perspective. Although most practitioners recognised the practical potential associated with ML-driven forecasting systems, their evaluations remained notably cautious. Collectively, these findings suggest that high predictive performance alone is insufficient to secure widespread organisational acceptance of ML applications within cross-border commercial activities. For these systems to become genuinely effective, they must integrate smoothly into existing organisational procedures and risk-management cultures while remaining comprehensible to end users. Consequently, effective forecasting frameworks should not only possess strong technical capability but must also remain interpretable, adaptable, and sufficiently resilient to withstand major structural transformations within financial markets.
Some of the metrics are blocked by your
consent settings
Design of Blockchain Technology-based Transcript and Analyzing Management Model for International Students
(2022-01-01)
Ge, Dong
;
Wang, Tianyu
;
Lin, Wei
;
Chen, Wei
;
Chen, Jian
With globalization, asymmetric information among international students' academic performance and qualifications, lack information transparency, bloated management bodies, high verification costs, and difficulties in fraud risk management are currently limiting the advancement of internationalization and standardization. These risks and problems also raise questions about the development of IT systems in the education administration and industry as well. Thus, by combining the study of international students' study results and academic records, we design a blockchain-based study transcript and academic information system concept and architecture with the use of blockchain technology. The result helps to develop business models and authentication features in related fields, set up a rigorous environment, optimize existing processes and rules, and lay a technical and data foundation for the development of international students' study transcripts and academic authentication.
Some of the metrics are blocked by your
consent settings
RhIr@MoS2 nanohybrids based disposable microsensor for the point-of-care testing of NADH in real human serum
(2020-08-01)
Ji, Dongqing
;
Ying, Zi
;
Zhang, Yuan
;
Chen, Wei
;
Janyasupab, Metini
Dihydronicotinamide adenine dinucleotide (NADH) is an important enzyme in all living cells, which is found to be abnormally expressed in cancer cells. Since it is redox-active, an electrochemical detection method would be suitable for monitoring its concentration in biological fluids. Here we present a strategy for specific determination of NADH in real human serum by using RhIr@MoS<inf>2</inf> nanohybrids based microsensor. To implement the protocol, RhIr nanocrysrals are in-situ grown onto MoS<inf>2</inf> interlayers forming a nanohybrid structure (RhIr@MoS<inf>2</inf>). After being locally deposited on an electrochemical microsensor, it could be used for the analysis of NADH. The developed RhIr@MoS<inf>2</inf> nanohybrids based microsensor possesses the ability for analyzing NADH at the applied potential of 0.07 V (much lower than most reported values). The detection limit is evaluated as low as 1 nmol/L even in bovine serum albumin (BSA) media. In addition, the sampling analysis of human serum from cancer patients and health controls shows that the microsensor displays good diagnostic sensitivity and specificity, illustrating that this developed detection technique is a relatively accurate method for measuring NADH in biological fluids. The proposed electrochemical microsensor assay also owns the benefits of convenience, disposable and easy processing, which make it a great possibility for future point-of-care cancer diagnosis.
Some of the metrics are blocked by your
consent settings
Phase-Regulated Sensing Mechanism of MoS2 Based Nanohybrids toward Point-of-Care Prostate Cancer Diagnosis
(2020-05-01)
Ying, Zi
;
Feng, Lingyan
;
Ji, Dongqing
;
Zhang, Yuan
;
Chen, Wei
Alpha-methylacyl-CoA racemase (AMACR) has been proven to be consistently overexpressed in prostate cancer epitheliums, and is expected to act as a positive biomarker for the diagnosis of prostate carcinoma in clinical practice. Here, a strategy for specific determination of AMACR in real human serum by using an electrochemical microsensor system is presented. In order to implement the protocol, a self-organized nanohybrid consisting of metal nanopillars in a 2D MoS<inf>2</inf> matrix is developed as material for the sensing interface. The testing signal outputs are strongly enhanced with the presence of the nanohybrids owing to that the metal pillars provide an efficient mass difussion and electron transfer path to the MoS<inf>2</inf> film surface. Furthermore, the phase-regulated sensing mechanism over MoS<inf>2</inf> is noticed and demonstrated by density functional theory calculation and experiments. The explored MoS<inf>2</inf> based nanohybrids are employed for the fabrication of an electrochemical microsensor, presenting good linear relationship in both ng µL<sup>−1</sup> and pg µL<sup>−1</sup> ranges for AMACR quantification. The sampling analysis of human serum indicates that this microsensor has good diagnostic specificity and sensitivity toward AMACR. The proposed electrochemical microsensor system also demonstrates the advantages of convenience, cost-effectiveness, and disposability, resulting in a potential integrated microsystem for point-of-care prostate cancer diagnosis.
Some of the metrics are blocked by your
consent settings
The dynamics of wetland cover change using a state estimation technique applied to time-series remote sensing imagery
(2017-12-15)
Insom, Patcharin
;
Cao, Chunxiang
;
Boonsrimuang, Pisit
;
Torteeka, Peerapong
;
Boonprong, Sornkitja
Monitoring the dynamics of inundation areas in wetlands over contiguous years is important because it influences wetland ecosystem monitoring. However, because the variable nature of wetlands tends to hamper monitoring change analyses, the potential for misinterpretation increases. The Kalman filter (KF) or extended Kalman filter (EKF), which uses recursive processing based on the former information, can be applied to time-series remote sensing imagery. In the experiment, a periodic triangle function of two modulated parameters is treated as the system model, and Normalized Difference Vegetation Index (NDVI) time-series data are used for the measurement model in the correction processes of the state estimation. A decision metric is computed from the mean and amplitude sequence, which results from the state estimation filter. Consequently, an optimal threshold is calculated using a minimum error thresholding algorithm based on a pre-labelled sample. NDVI time-series data from Poyang Lake, China–derived from 250-m Moderate Resolution Imaging Spectroradiometer satellite data obtained from January 2009 to December 2013–are applied to monitor the dynamics of inundation changes. The results show that the EKF achieves satisfactory results, with 85.52% accuracy in the year 2009, while the KF has an accuracy of 84.16% during that same time.
Some of the metrics are blocked by your
consent settings
A support vector machine-based particle filter for improved land cover classification applied to MODIS data
(2016-11-01)
Insom, Patcharin
;
Cao, Chunxiang
;
Boonsrimuang, Pisit
;
Bao, Shanning
;
Chen, Wei
There are two important factors to improve the accuracy of the support vector machine(SVM) classifier. First, selected training samples should uniquely represent each class. Second, SVM training parameters which are pre-defined by the user should be suitable for training samples to obtain satisfied results of the SVM classifier. The proposed method of this paper presents a technique to adjust the SVM training parameters by particle filter algorithm. The parameters were tuned based on the weight of particles in each iteration time of particle filter processes. An experiment implemented annual mean of Normalized Difference Vegetation Index and Enhanced Vegetation Index extracted from the Moderate Resolution Imaging Spectroradiometer data with 250-m resolution in a study area of Poyang Lake, China, during the year of 2009. The proposed method for adjusting the SVM training parameters provided the an improved performance SVM classification model.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results