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
Investigation of physiological disorder classification in mangosteen fruit using visible and shortwave near-infrared spectroscopy combined with machine learning
(2025-12-01)
Ruttanadech, Nuttapong
;
Momin, Abdul
;
Phetpan, Kittisak
;
Chaichanyut, Montree
;
Thongphut, Chitwadee
Accurate classification of physiological disorders in mangosteen fruit is crucial for ensuring production quality, safety, sustainability, and economic viability. This study investigates the application of visible and shortwave near-infrared (Vis/SWNIR) reflectance spectroscopy, combined with machine learning algorithms, to classify three primary disorders: normal fruit (NF), translucent flesh disorder (TFD), and TFD with yellow gummy latex (TFD & YGL). The study specifically examines the effects of light intensity, spectral pretreatments, and machine learning models on classification performance. Spectral data were collected using two light intensities (50 % and 100 % of a 150 W light source) and processed with three pretreatments: standard normal variate (SNV), second derivative Savitzky-Golay (SGD2), and a combination of SNV and SGD2. Random forest (RF), support vector machine (SVM), and multi-layer perceptron (MLP) algorithms were used for classification. The SGD2 method improved differentiation, especially for the TFD & YGL class, in the 700–725 nm wavelength range, which is associated with xanthone content in the fruit's pericarp. Higher light intensity (100 %) significantly improved classification accuracy, achieving an overall accuracy of 0.71 and an average F1 score of 0.61 with the RF model. Despite these improvements, the model struggled to distinguish the TFD class from NF due to their similar spectral profiles. Overall, the Vis/SWNIR spectroscopy and machine learning combination shows strong potential for the non-destructive classification of mangosteen fruit disorders. Both light intensity and spectral pretreatments play critical roles in enhancing performance. Future studies should focus on improving spectral sensitivity to better capture internal fruit characteristics.
Some of the metrics are blocked by your
consent settings
Analysis of effects of surface roughness on sensing performance of surface plasmon resonance detection for refractive index sensing application
(2021-09-01)
Treebupachatsakul, Treesukon
;
Shinnakerdchoke, Siratchakrit
;
Pechprasarn, Suejit
This paper provides a theoretical framework to analyze and quantify roughness effects on sensing performance parameters of surface plasmon resonance measurements. Rigorous coupled-wave analysis and the Monte Carlo method were applied to compute plasmonic reflectance spectra for different surface roughness profiles. The rough surfaces were generated using the low pass frequency filtering method. Different coating and surface treatments and their reported root‐mean-square roughness in the literature were extracted and investigated in this study to calculate the refractive index sensing performance parameters, including sensitivity, full width at half maximum, plasmonic dip intensity, plasmonic dip position, and figure of merit. Here, we propose a figure‐of-merit equation considering optical intensity contrast and signal‐to‐noise ratio. The proposed figure-of‐merit equation could predict a similar refractive index sensing performance compared to experimental results reported in the literature. The surface roughness height strongly affected all the performance parameters, resulting in a degraded figure of merit for surface plasmon resonance measurement.
Some of the metrics are blocked by your
consent settings
Performance analysis of non‐interferometry based surface plasmon resonance microscopes
(2021-08-01)
Tontarawongsa, Sorawit
;
Visitsattapongse, Sarinporn
;
Pechprasarn, Suejit
Surface plasmon microscopy has been of interest to the science and engineering commu-nity and has been utilized in broad aspects of applications and studies, including biochemical sensing and biomolecular binding kinetics. The benefits of surface plasmon microscopy include label‐free detec-tion, high sensitivity, and quantitative measurements. Here, a theoretical framework to analyze and com-pare several non‐interferometric surface plasmon microscopes is proposed. The scope of the study is to (1) identify the strengths and weaknesses in each surface plasmon microscopes reported in the literature; (2) quantify their performance in terms of spatial imaging resolution, imaging contrast, sensitivity, and measurement accuracy for quantitative and non‐quantitative imaging modes of the microscopes. Six types of non‐interferometric microscopes were included in this study: annulus aperture scanning, half annulus aperture scanning, single‐point scanning, double‐point scanning, single‐point scanning, at 45 degrees azimuthal angle, and double‐point scanning at 45 degrees azimuthal angle. For non‐quantitative imaging, there is a substantial tradeoff between the image contrast and the spatial resolution. For the quantitative imaging, the half annulus aperture provided the highest sensitivity of 127.058 rad/μm2 RIU−1, followed by the full annulus aperture of 126.318 rad/μm2 RIU−1. There is a clear tradeoff between spatial resolution and sensitivity. The annulus aperture and half annulus aperture had an optimal resolution, sensitivity, and crosstalk compared to the other non‐interferometric surface plasmon resonance micro-scopes. The resolution depends strongly on the propagation length of the surface plasmons rather than the numerical aperture of the objective lens. For imaging and sensing purposes, the recommended mi-crofluidic channel size and protein stamping size for surface plasmon resonance experiments is at least 25 μm for accurate plasmonic measurements.
Some of the metrics are blocked by your
consent settings
Low-cost instrumentation of Automated Whole - Slide Microscope for Biomedical Imaging
(2019-01-10)
Pechprasarn, Suejit
;
Sukkasem, Chayanisa
;
Suvarnaphaet, Phitsini
;
Thongchoom, Rujirada
;
Chuwittaya, Suteeboon
Microscope is one of the essential devices in medical profession. It is usually used for finding out types of abnormal cells or tissues, detecting the diseases, and defining a range treatment option for patient. Recently, there is a new technology of whole-slide imaging (WSI) which has been developed in the microscope. The technology provides the scanning of conventional glass slides to produce digital images of cumulative data. Since the WSI is a complex system and very expensive price, hence we aim to implement the prototype of a cost- effective whole - slide imaging system based on the principle of microscopic design. The implemented prototype consisting of optical and mechanical parts was developed using 3D printing. The optical system employed a 40x objective lens aligning with the digital camera for imaging the specimen on the standard slide. The mechanical system was designed for the movement of the slide in 3 dimensions automatically and controlled by stepper motors and microcontrollers based on controlling computer program. To accumulate the whole- slide image, the slide was scanned and captured in the X-Y axes and the focal (Z) axis in a sequence. The cumulative data was then analyzed and rendered the whole- slide image. The implemented device would be advantageous to cytologists and doctors for the biomedical imaging and recording numerous medical data of the patients.
Some of the metrics are blocked by your
consent settings
A Study on Influences of Metal Materials on Electromagnetic Field Generated by Pure DC and Combined DC
(2018-10-15)
Sriratana, Witsarut
;
Kaewnamchai, Vanisara
;
Sriratana, Erdlekha
This paper presents the classification of metals materials by application of Hall Effect sensor based on the eddy current method with non-destructive testing. The electromagnetic field was generated by winding an SWG 22 wire onto the ferrite core to create a solenoid. Two measurement systems are used. One uses a Pure DC supply as the excitation voltage of the electromagnetic field of the Hall Effect sensor system; while the other uses a combination of AC and DC supply, which is amplified through an integrated Class-A amplifier circuit, as the excitation voltage. Three different metal samples, namely, steel, aluminum and stainless steel were used as specimen. Current test conducted to determine the suitable current level revealed that a 0.8 A current is safe to allow tests to be conducted. Results show that the Combined DC system is capable to classify conductive materials, where the Pure DC system lacks in this functionality. The Output voltage of Hall Effect sensor to test with steel, aluminum and stainless steel is 4.68 V, 1.74 V and 3.63 V, respectively. Furthermore, the use of the Combined DC system enables aluminum thickness to be distinguished. The tolerance of the system measuring the materials when using the Pure DC and Combined DC are pm 0.0697% and pm 0.58530% respectively.
Some of the metrics are blocked by your
consent settings
Artificial neural networks for predicting the maximum surface settlement caused by EPB shield tunneling
(2006-03-01)
Suwansawat, Suchatvee
;
Einstein, Herbert H.
Numerous empirical and analytical relations exist between shield tunnel characteristics and surface and subsurface deformation. Also, 2-D and 3-D numerical analyses have been applied to such tunneling problems. Similar but substantially fewer approaches have been developed for earth pressure balance (EPB) tunneling. In the Bangkok MRTA project, data on ground deformation and shield operation were collected. The tunnel sizes are practically identical and the subsurface conditions over long distances are comparable, which allow one to establish relationships between ground characteristics and EPB - Operation on the one hand, and surface deformations on the other hand. After using the information to identify which ground- and EPB-characteristic have the greatest influence on ground movements, an approach based on artificial neural networks (ANN) was used to develop predictive relations. Since the method has the ability to map input to output patterns, ANN enable one to map all influencing parameters to surface settlements. Combining the extensive computerized database and the knowledge of what influences the surface settlements, ANN can become a useful predictive method. This paper attempts to evaluate the potential as well as the limitations of ANN for predicting surface settlements caused by EPB shield tunneling and to develop optimal neural network models for this objective. © 2005 Elsevier Ltd. All rights reserved.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results