Visitsattapongse, Sarinporn
Loading...
Preferred name
Visitsattapongse, Sarinporn
Alternative Name
Visitsattapongse, S.
Main Affiliation
Email
sarinporn.vi@kmitl.ac.th
25 results
Now showing 1 - 10 of 25
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, A Novel Approach for Optimizing Molecularly Imprinted Polymer Composition in Electrochemical Detection of Collagen Peptides(2025-11-01); - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Smart wheelchair based on eye tracking(2017-02-21); - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Automated segmentation of infarct lesions in t1‐weighted mri scans using variational mode decomposition and deep learning(2021-03-02); ; ; Automated segmentation methods are critical for early detection, prompt actions, and immediate treatments in reducing disability and death risks of brain infarction. This paper aims to develop a fully automated method to segment the infarct lesions from T1‐weighted brain scans. As a key novelty, the proposed method combines variational mode decomposition and deep learning-based segmentation to take advantages of both methods and provide better results. There are three main technical contributions in this paper. First, variational mode decomposition is applied as a pre-processing to discriminate the infarct lesions from unwanted non‐infarct tissues. Second, overlapped patches strategy is proposed to reduce the workload of the deep‐learning‐based segmentation task. Finally, a three‐dimensional U‐Net model is developed to perform patch‐wise segmentation of infarct lesions. A total of 239 brain scans from a public dataset are utilized to develop and evaluate the proposed method. Empirical results reveal that the proposed automated segmentation can provide promising performances with an average dice similarity coefficient (DSC) of 0.6684, intersection over union (IoU) of 0.5022, and average symmetric surface distance (ASSD) of 0.3932, respectively. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Automatic detection of pulmonary nodules using three-dimensional chain coding and optimized random forest(2020-04-01); ; ; The detection of pulmonary nodules on computed tomography scans provides a clue for the early diagnosis of lung cancer. Manual detection mandates a heavy radiological workload as it identifies nodules slice-by-slice. This paper presents a fully automated nodule detection with three significant contributions. First, an automated seeded region growing is designed to segment the lung regions from the tomography scans. Second, a three-dimensional chain code algorithm is implemented to refine the border of the segmented lungs. Lastly, nodules inside the lungs are detected using an optimized random forest classifier. The experiments for our proposed detection are conducted using 888 scans from a public dataset, and achieves a favorable result of 93.11% accuracy, 94.86% sensitivity, and 91.37% specificity, with only 0.0863 false positives per exam. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Emergency Blower-Based Ventilator with Novel-Designed Ventilation Sensor and Actuator(2022-03-01); - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Optical-based foot plantar pressure measurement with application in human postural balance, gait and recognition analysis(2020-07-01); ; ; Aoyama, HisayukiIn this research, we purposed the design of real-time low-cost marker-free optical-based plantar-pressure measurement with application in human postural control, gait and recognition analysis. The system consists of a series of digital cameras capture installed underneath the acrylic-top platform. Light of LED strip mounted along the side of the acrylic plate deflected by the pressure exerted between the glossy white paper installed in the top of acrylic and the acrylic plate to the digital cameras provides the color-coded plantar pressure image of the subject standing on the platform. The system can provide both static features and dynamic features. Our hybrid system consists of a series of USB cameras aligned under the acrylic-plate walking platform. The mosaic image processing is used to concatenate the captured image to increase the sensing area. Captured the image data in video mode, various dynamic parameters can be derived for further dynamic analysis. The image capturing in one specific frame can be used for static analysis. Application in human-postural measurement, gait analysis, and person identification indicate that our system is an all-in-one system for plantar pressure measurement. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Ultrasensitive Label-Free Electrochemical Detection of Pseudomonas aeruginosa Using a Surface Molecularly Imprinted Polymer-Modified Screen-Printed Electrode(2026-06-01); ; Pseudomonas aeruginosa is a major opportunistic pathogen frequently associated with nosocomial infections, such as pneumonia, urinary tract infections, and wound infections, particularly in immunocompromised or hospitalized patients. These infections are often difficult to treat due to the pathogen’s intrinsic antibiotic resistance and biofilm-forming ability. Therefore, rapid and selective detection of P. aeruginosa is essential for early diagnosis and effective infection control. In this study, a novel surface-imprinted MIP design uniquely combines methacrylamide (MAM), acrylamide (AAM), and vinylpyrrolidone (VP) monomers to generate recognition cavities that are complementary to the surface morphology and physicochemical properties of Pseudomonas aeruginosa cells. Unlike traditional MIP approaches, this surface imprinting strategy provides improved stability and reproducibility, without relying on biological recognition elements like antibodies or aptamers. This novel approach enabled us to achieve an ultralow LOD of 1 CFU/mL over a linear range of 1–10<sup>4</sup> CFU/mL, demonstrating excellent analytical performance. In addition, the sensor exhibited good reproducibility with an RSD of 5–12%. The novelty of this work lies in the use of a surface-imprinted MIP strategy combined with a multi-monomer system to enhance bacterial recognition and sensing performance. Overall, the proposed MIP-based electrochemical biomimetic sensor offers a rapid, cost-effective, and portable platform with strong potential for the detection of P. aeruginosa in clinical and environmental applications. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Electrochemical Characterization of a Molecularly Imprinted Polymer Sensor for the Selective Recognition of Type II Collagen in Joint Degeneration Monitoring(2026-02-01); ; Type II collagen is a primary fibrillar component of articular cartilage, and its early degradation is a key biomarker of joint-degenerative disorders such as osteoarthritis, rheumatoid arthritis, gout, etc. Reliable detection at low concentrations remains challenging due to limited assay accessibility, complex analytical procedures, and nonspecific responses in multicomponent biological matrices. This research reports the development of a Molecularly Imprinted Polymer (MIP)–based electrochemical sensor engineered for the selective recognition of type II collagen. A series of monomer formulations were evaluated, and the 1AAM:2VP composition produced a well-defined imprinted layer on screen-printed carbon electrodes, yielding the highest electrochemical sensitivity and linearity. The optimized sensor exhibited strong anodic and cathodic responses proportional to increasing collagen concentrations, with a calibration slope corresponding to an R<sup>2</sup> value of 0.9394. Minimal signal interference was observed, confirming high molecular selectivity. The limit of detection (LOD) was calculated to be approximately 0.065 µg/mL. These characteristics demonstrate that the proposed MIP sensor provides a low-cost, accessible, and highly selective analytical platform suitable for early-stage cartilage degeneration monitoring. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Biosensors for Klebsiella pneumoniae with Molecularly Imprinted Polymer (MIP) Technique(2022-06-01); - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Study of ECG variation in daily activity(2017-12-19); Electrocardiogram (ECG) records electrical activity of the heart spreading through the heart muscle to make the heart contract. Recently ECG has been captured attention as biometric feature due to its uniqueness and large reliabilities for human identifications. In this study we aimed to verify the conservative ECG of human in their activities to ensure whether it is suitable to be used as biometric devices. Experiment studies involved 6 participants of which the age ranges is between 21 and 23. We test the robustness of ECG under various situation including health condition, emotional state and heart rate variation. The recorded ECG signal is forwarded for analysis using Matlab. Correlation coefficient of ECG Fourier transform is used as criterion to validate the ECG robustness. The result indicates that ECG is not stable and seems to vary with daily activity and emotional state. This will hampers ECG to be used as Biometric.