KMITL

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

Browse

Search Results

Now showing 1 - 10 of 15

Some of the metrics are blocked by your
consent settings
Drought vulnerability assessment using morphometric features and extreme precipitation indicators to prioritize sub-basins: AI-based Fuzzy Logic approach
(2026-03-01)
Nigam, Utkarsh
;
Patel, Vinodkumar M.
;
Patel, Dhruvesh P.
;
Jodhani, Keval H.
;
Gupta, Nitesh
The identification of watersheds and extraction of drainage networks are essential for effective hydrological and geomorphological modelling. This study investigates the influence of morphometric factors and extreme precipitation events on the hydrological responses of the Sabarmati River Basin (SRB), India, to identify the drought-vulnerable sub-basins. Watershed prioritization was carried out using satellite remote sensing, GIS, and secondary data, including topographic sheets and ASTER DEM with a spatial resolution of 90 m. The SRB was divided into nine sub-watersheds, and 28 morphometric parameters were evaluated, comprising 07 linear, 15 areal, and 06 relief parameters. A compound factor (CF) was derived using multi-criteria decision-making techniques such as Weighted Sum Analysis (WSA), Principal Component Analysis (PCA), Analytic Hierarchy Process (AHP), Fuzzy-AHP (FAHP), and TOPSIS. Sub-watersheds were ranked based on CF value, where a lower CF indicated higher priority for runoff management strategies. Additionally, 42 years of precipitation data were analysed using the Standardized Precipitation Index (SPI) at timescales ranging from 3 to 24 months to assess trends in drought and extreme precipitation events. The analysis indicate decline in runoff potential in several sub-basins, however others (e.g., SB2, SB3, SB4, SB5) exhibit positive precipitation trends, making them suitable for runoff enhancement. This integrated methodology offers a comprehensive framework for managing sub-basins, optimizing runoff potential, and supporting sustainable water conservation. The results provide actionable insights for policymakers and planners to better utilize the SRB water resources based on its geomorphological and climatic characteristics.
Some of the metrics are blocked by your
consent settings
GC-MS Metabolite Profiling and Chemometric Analysis of Robusta Green Beans (Bantjah Coffee)
(2025-01-01)
Permatasari, Fitria Indah
;
Nazir, Novizar
;
Anggraini, Tuty
;
Hellyward, James
;
Techavuthiporn, Chairat
In this study, three types of Robusta green bean coffee developed in the Bantjah area were characterized. This study characterized three types of Robusta green coffee beans with potential for development in the Bantjah area. The three coffee beans were (A) Bantjah area and the two (B, C) selected from different altitudes of the West Sumatra area. The purpose of this study was to analyze metabolite profiling of Robusta green coffee green beans. The coffee beans were fermented using the natural method and then the extract was derivatized with N-Methyl-N-(trimethylsilyl) trifluoroacetamide before being analyzed by Gas chromatography-mass spectrometry (GCMS). The chromatogram obtained was then analyzed statistically using principle component analysis (PCA). GCMS analysis produced more than 60 chemical components in green beans of Robusta coffee. Principle component analysis determined the metabolite distribution of coffee samples as influenced by their geographical origin. Coffee originating from the highlands had different marker compounds than coffee grown in lower plains. A metabolomics approach provides a comprehensive explanation of this relationship.
Some of the metrics are blocked by your
consent settings
Source apportionment of PM2.5 in Thailand’s deep south by principal component analysis and impact of transboundary haze
(2023-08-01)
Chaisongkaew, Phatsarakorn
;
Dejchanchaiwong, Racha
;
Inerb, Muanfun
;
Mahasakpan, Napawan
;
Nim, Nobchonnee
Atmospheric particulate matter smaller than 2.5 micron (PM<inf>2.5</inf>) was evaluated at four sites in the lower southern part of Thailand during 2019–2020 to understand the impact of PM<inf>2.5</inf> transport from peatland fires in Indonesia on air quality during the southwest monsoon season. Mass concentration and chemical bound-PM, including carbon composition, e.g., organic carbon (OC) and elemental carbon (EC), polycyclic aromatic hydrocarbons (PAHs), and inorganic elements, were analyzed. The PM<inf>2.5</inf> emission sources were identified by principal components analysis (PCA). The average mass concentrations of PM<inf>2.5</inf> in the normal period, which represents clean background air, from four sites was 3.5–5.1 µg/m3, whereas during the haze period, it rose to 5.4–13.5 µg/m3. During the haze period, both OC and EC were 3.5 times as high as in the normal period. The average total PAHs and BaP-TEQ of PM<inf>2.5</inf> during the haze period were ~ 1.3–1.7 and ~ 1.2–1.9 times higher than those in the normal period. The K concentrations significantly increased during haze periods. SO<inf>4</inf>2− dominated throughout the year. The effects of external sources, especially the transboundary haze from peatland fires, were significantly enhanced, because the background air in the study locations was generally clean. PCA indicated that vehicle emission, local biomass burning, and secondary particles played a key role during normal period, whereas open biomass burning dominated during the haze phenomena. This was consistent with the OC/EC and PAH diagnostic ratios. Backward trajectories confirmed that the sources of PM during the haze period were predominantly peatland fires in Sumatra, Indonesia, due to southwest wind.
Some of the metrics are blocked by your
consent settings
Growth and Yield of Watermelon (Citrullus lanatus) in Plastic House in Response to White LED Supplementary Lighting
(2023-01-01)
Chamchum, Wasinee
;
Glahan, Somchai
;
Kramchote, Somsak
;
Maniwara, Phonkrit
;
Suwor, Patcharaporn
Watermelon plants cultivar ‘Kinaree 457’ were grown in plastic house under natural daylight only (control) or with nightly LED supplementary lighting for 6 h (6:00 pm-12:00 pm) or 12 h (6:00 pm-6:00 am) starting from transplanting up to fruit harvest. Plant height, leaf chlorophyll content and fruit yield significantly increased in response to 6 h supplementary LED lighting. Fruit mass, size (length x width) and flesh thickness at 6 h LED treatment were about 2.3 kg, 19.3 ×15.7 cm, and 15.7 cm, respectively, while the fruit of control had 1.7 kg, 16.0 × 14.3 cm, and 13.8 cm, respectively. No significant treatment effect was obtained on peel thickness, flesh color L* and b* values, juice pH and total soluble solids. However, 6 h LED treatment resulted in lower reddening flesh (lower a* values), firmness and higher titratable acidity relative to the control, suggesting the need for improvement in cultural management. Furthermore, multivariate statistics of principal component analysis (PCA) performed on physico-chemical quality revealed the variations among watermelons from lighting and control treatments regardless of lighting hour.
Some of the metrics are blocked by your
consent settings
Heart Rate Estimation by PCA with LSTM from Video-based Plethysmography Under Periodic Noise
(2022-01-01)
Traivinidsreesuk, Chetsadaporn
;
Yodrabum, Nutcha
;
Chaikangwan, Irin
;
Titijaroonroj, Taravichet
A remote photoplethysmography (rPPG) analysis can extract vital signs from the source video, including heart rate estimation. One of the problems of heart rate estimation is periodic noise embedded in the source video. It is difficult for an rPPG analysis to discriminate between vital signal information and noise, increasing prediction error. To alleviate this problem, this paper used principal component analysis (PCA) to extract rPPG signals from the input video before forwarding the signal to Long Short Term Memory (LSTM) to estimate heart rate. The experimental results show that, among discrete Fourier Transform method, neural networks, and neural network with LSTM, the proposed method accomplished a much lower MAEP at 15.05, 13.90, and 17.90 in the cases of overall, with no periodic noise, and with periodic noise, respectively.
Some of the metrics are blocked by your
consent settings
Hand Movement Classification Base on EEG Signals using Deep Learning and Dimensional Reduction Technique
(2019-11-01)
Boonme, Phattraporn
;
Thongserm, Petchanon
;
Arunsuriyasak, Peerachai
;
Phasukkit, Pattarapong
This research is presented the bio-signal activities of arm movements by using deep learning for classification between right-arm and left-arm. It's well-known that Electroencephalography (EEG) shows neural oscillation behaviors in electrical voltage form. Also, Brain-Computer Interface (BCI) is direct communication between neural oscillation and computer to control machines without physical movements. So, this paper aims to present the classification method of EEG signals data to develop a BCI in the future. By using deep learning to classification data is classified into raise the right arm, raise the left arm. And decrease EEG signal data by using Principal Component Analysis (PCA). PCA can reduce the data size of EEG signal from 1000x28 to 28x28. Experimental result of classification has accuracy 90.86% and 94.71%
Some of the metrics are blocked by your
consent settings
FPGA-based odor classification system using principal component analysis
(2018-08-13)
Tongyoo, Titiwoot
;
Ariyakul, Yossiri
Odor classification has been increasingly applied in various applications. The types of odors can be identified by analyzing the output pattern obtained from the odor sensors with different sensitivities to the targeted odor. Therefore, the use of reconfigurable hardware offers advantage for the flexibility to work with a number of sensors with various characteristics. In this study, the FPGA was employed in the development of an odor classification system using principal component analysis (PCA). The soft processor system was developed so that the odor classification based on PCA can be performed standalone. A number of experiments in the closed system were conducted to evaluate the validity of the proposed odor classification system and its capability to identify the kinds of odors. The effectiveness to classify the odor samples was confirmed.
Some of the metrics are blocked by your
consent settings
Building Minimal Classification Rules for Breast Cancer Diagnosis
(2018-08-06)
Douangnoulack, Phonethep
;
Boonjing, Veera
A rule based classifier is widely applied in breast cancer diagnosis. The classifier with a good performance of disease classification have been developed and highly required over the past decades. Since classification rules are derived from previous diagnosis with a large amount of features, it challenges to build a minimal number of rules with high performance while retaining all diagnosis information. The Principal Component Analysis (PCA) is known as a lossless data reduction technique with good classification performance. Therefore, this paper aims at finding the best performance classifier giving minimal classification rules by employing PCA. Based on experiment result on Wisconsin Breast Cancer data set, the J48 decision tree classifier is found to be the best among the three classifiers: J48 decision tree, Reduced Error Pruning Tree, and Random Tree.
Some of the metrics are blocked by your
consent settings
An improved 2DPCA for face recognition under illumination effects
(2015-01-01)
Woraratpanya, Kuntpong
;
Sornnoi, Monmorakot
;
Leelaburanapong, Savita
;
Titijaroonroj, Taravichet
;
Varakulsiripunth, Ruttikorn
Principal component analysis (PCA) is one of the successful techniques for applying to face recognition, but its challenge still remains for solving an illumination effect condition. This paper proposes an improved 2DPCA (I-2DPCA) for overwhelming the illumination effect in face recognition. The proposed method is based on two assumptions. The first assumption is to create the covariance matrix that can effectively decompose the components of illumination effects from the eigenfaces. This avoids the illumination effect problem. The second assumption is to select the suitable eigenvectors that can significantly improve the recognition rate. Based on the Extended Yale Face Database B+ containing 60 illumination conditions, the experimental results show that not only does the proposed method decrease the computing time, but it also improves the recognition rate up to 95.93%.
Some of the metrics are blocked by your
consent settings
Monitoring of draft beer fermentation process by electronic nose
(2014-01-01)
Phetchakul, Toempong
;
Sutthinet, Chalin
The draft beer fermentation process was monitored by using electronic nose. The system used the seven types of generally commercial metal oxide gas sensor in array. The selected process was one of the commercial processes and the data were gathered every hour for 10 day process which was 240 steps. It was processed for monitoring the chemical reaction for quality control. The results showed the good difference of the chemical reaction of the each day very clearly. The signature processing showed the variance 98.78%, 96.55% of the first component (PC1) and 2.3% of the second component (PC2), which was sufficiency for data explanation in 2D plot. It would be useful for production process to ensure a quality standard. © (2014) Trans Tech Publications, Switzerland.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results