Pinyo Taeprasartsit
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Pinyo Taeprasartsit has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
William E. Higgins
The Pennsylvania State Univ. (USA)
4 shared publicationsAphinan Peerachaidacho
Silpakorn University,Faculty of Science,Dept. of Computing,Thailand
1 shared publicationArthi F.R.C.S.T. Kruavit
Bangkok, Thailand; and London, United Kingdom
1 shared publicationBoonnatee Sakboonyara
Department of Computing Faculty of Science, Silpakorn University, Nakhon Pathom, Thailand
1 shared publicationChalermpong F.R.C.S.T. Chatdokmaiprai
Bangkok, Thailand; and London, United Kingdom
1 shared publicationChanachai Puttaruksa
Department of Computing, Faculty of Science, Silpakorn University, Nakhon Pathom, Thailand
1 shared publication
Latest Publications
- Open Access
- 20 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 28582-28597
Robust Method for Non-Contact Vital Sign Measurement in Videos Acquired in Real-World Light Settings From Skin Less Affected by Blood Perfusion
Color fluctuations caused by blood perfusion on the skin are an essential tool for the success of imaging photoplethysmography (iPPG) methods. However, color fluctuation of the non-facial skin is less observable than that of the facial skin. Furthermore, some light sources may produce image artifacts obscuring vital signs that iPPG methods are aimed to observe. This work contributes to an iPPG domain in several ways. First, it systematically visualizes and evaluates the impact of light settings on the accuracy of heart-rate estimation. Three light settings were arranged, and Eulerian video magnification was applied to illustrate their underlying characteristics. This work showed that fluorescent tubes could produce stripe artifacts and failed existing iPPG methods. Second, techniques to strengthen blood perfusion signals and better estimate heart rates are proposed. They significantly improved the accuracy in three light settings and a wide range of skin types categorized by the Fitzpatrick standard. Lastly, this work presents a new public dataset acquired from the forearm skin of 83 human subjects. The proposed method utilizes the Savitzky–Golay filter to treat components obtained by independent component analysis (ICA). We apply normalized autocorrelation to evaluate signals’ period consistency and weigh ICA components accordingly. This method is a reliable way to accumulate weighted fast Fourier Transform spectra and compute the final frequency representing an estimated heart rate. In our experiments, the method significantly reduced the errors of prior methods in all of the three light settings, especially for ceiling fluorescent tubes where the errors were reduced by 83% on average.
- 20 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 28582-28597
Open AccessRobust Method for Non-Contact Vital Sign Measurement in Videos Acquired in Real-World Light Settings From Skin Less Affected by Blood Perfusion
Color fluctuations caused by blood perfusion on the skin are an essential tool for the success of imaging photoplethysmography (iPPG) methods. However, color fluctuation of the non-facial skin is less observable than that of the facial skin. Furthermore, some light sources may produce image artifacts obscuring vital signs that iPPG methods are aimed to observe. This work contributes to an iPPG domain in several ways. First, it systematically visualizes and evaluates the impact of light settings on the accuracy of heart-rate estimation. Three light settings were arranged, and Eulerian video magnification was applied to illustrate their underlying characteristics. This work showed that fluorescent tubes could produce stripe artifacts and failed existing iPPG methods. Second, techniques to strengthen blood perfusion signals and better estimate heart rates are proposed. They significantly improved the accuracy in three light settings and a wide range of skin types categorized by the Fitzpatrick standard. Lastly, this work presents a new public dataset acquired from the forearm skin of 83 human subjects. The proposed method utilizes the Savitzky–Golay filter to treat components obtained by independent component analysis (ICA). We apply normalized autocorrelation to evaluate signals’ period consistency and weigh ICA components accordingly. This method is a reliable way to accumulate weighted fast Fourier Transform spectra and compute the final frequency representing an estimated heart rate. In our experiments, the method significantly reduced the errors of prior methods in all of the three light settings, especially for ceiling fluorescent tubes where the errors were reduced by 83% on average.
- 28 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 139-144
Explainable AI for Systematic Detection of Potential Problems in Natural Language Datasets
Quality of training data is a major issue in machine learning. In some domains, data samples may be hard to obtain, and detection of problematic samples becomes essential. This work proposes to use explainable AI to explore how text misclassification occurs and how to systematically identify whether the issue arises from a dataset. The proposed method finds similar samples and uses SHAP to calculate feature attributions. This approach helps to efficiently detect conflicts between samples and highly attributed features, allowing for the identification of many root causes of misclassification. This is particularly useful for rare samples and questionable labels. As a result, dataset quality can be improved with relatively little effort, which in turn enhances the predictive performance of a model. We validated the method on two datasets: Event Planner Survey and Wisesight Sentiment Corpus (WSC). Accuracy, precision, and recall were significantly improved in both sets. Especially, the accuracy in WSC was improved from 64.4 to 70.9% through data cleaning guided by the method.
- 28 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 139-144
Explainable AI for Systematic Detection of Potential Problems in Natural Language Datasets
Quality of training data is a major issue in machine learning. In some domains, data samples may be hard to obtain, and detection of problematic samples becomes essential. This work proposes to use explainable AI to explore how text misclassification occurs and how to systematically identify whether the issue arises from a dataset. The proposed method finds similar samples and uses SHAP to calculate feature attributions. This approach helps to efficiently detect conflicts between samples and highly attributed features, allowing for the identification of many root causes of misclassification. This is particularly useful for rare samples and questionable labels. As a result, dataset quality can be improved with relatively little effort, which in turn enhances the predictive performance of a model. We validated the method on two datasets: Event Planner Survey and Wisesight Sentiment Corpus (WSC). Accuracy, precision, and recall were significantly improved in both sets. Especially, the accuracy in WSC was improved from 64.4 to 70.9% through data cleaning guided by the method.
- 1 January 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 51-56
U-Net and Mean-Shift Histogram for Efficient Liver Segmentation from CT Images
Nowadays, 3D computed tomography (CT) data is commonly employed to diagnose liver cancer or to examine liver condition. This work proposes a method that can quickly find a location of the biggest CT slice of the liver. We also extend this method to demonstrate that it can work as an efficient algorithm for liver segmentation. The proposed method is based on a U-Net, fully convolutional neural network, to roughly segment the liver and employs a mean-shift clustering algorithm to enhance liver localization accuracy. This addition of mean-shift clustering on histogram data after rough segmentation by U-Net prevents oversegmentation of the liver and significantly improves the accuracy of a method solely relying on a U-Net. A novel image-enhancement technique based on statistical thresholding is also introduced to further increase accuracy. This hybrid method processed each slice in 0.35 seconds on average (75 seconds per image) and its median accuracy measured in Dice similarity index in 5-fold cross-validation was 95%.
- 1 January 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 51-56
U-Net and Mean-Shift Histogram for Efficient Liver Segmentation from CT Images
Nowadays, 3D computed tomography (CT) data is commonly employed to diagnose liver cancer or to examine liver condition. This work proposes a method that can quickly find a location of the biggest CT slice of the liver. We also extend this method to demonstrate that it can work as an efficient algorithm for liver segmentation. The proposed method is based on a U-Net, fully convolutional neural network, to roughly segment the liver and employs a mean-shift clustering algorithm to enhance liver localization accuracy. This addition of mean-shift clustering on histogram data after rough segmentation by U-Net prevents oversegmentation of the liver and significantly improves the accuracy of a method solely relying on a U-Net. A novel image-enhancement technique based on statistical thresholding is also introduced to further increase accuracy. This hybrid method processed each slice in 0.35 seconds on average (75 seconds per image) and its median accuracy measured in Dice similarity index in 5-fold cross-validation was 95%.
- 1 July 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Color Data Augmentation through Learning Color-Mapping Parameters between Cameras
In order to achieve a more accurate deep learning model, we need large amount of data. For imaging application, color data augmentation is usually required. Color jittering is a common current practice for such augmentation where color values in image are slightly adjusted. Unfortunately, color values between two cameras may be significantly different. This makes the current practice ineffective. This work proposes to map color values among cameras by using deep learning to learn color-mapping parameters. In this way, we can augment color data by converting an image from one camera to another image whose colors seemingly are taken from another camera. This allows a machine to learn a model that can deal with input images from multiple cameras without actually using training data from multiple cameras. These parameters can also be employed to calibrate colors in order that all cameras produce the same color tone. The proposed neural network architecture which employs fully connected layers and batch normalization outperforms an existing method and can be systematically performed for any camera pairs to extend its applications in other scenarios.
- 1 July 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Color Data Augmentation through Learning Color-Mapping Parameters between Cameras
In order to achieve a more accurate deep learning model, we need large amount of data. For imaging application, color data augmentation is usually required. Color jittering is a common current practice for such augmentation where color values in image are slightly adjusted. Unfortunately, color values between two cameras may be significantly different. This makes the current practice ineffective. This work proposes to map color values among cameras by using deep learning to learn color-mapping parameters. In this way, we can augment color data by converting an image from one camera to another image whose colors seemingly are taken from another camera. This allows a machine to learn a model that can deal with input images from multiple cameras without actually using training data from multiple cameras. These parameters can also be employed to calibrate colors in order that all cameras produce the same color tone. The proposed neural network architecture which employs fully connected layers and batch normalization outperforms an existing method and can be systematically performed for any camera pairs to extend its applications in other scenarios.
- 1 July 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Study of Chronic Wound Image Segmentation: Impact of Tissue Type and Color Data Augmentation
Chronic wound segmentation is an essential task for evaluating wound and its recovery progress. A physician usually measures a wound area to choose proper treatment according to wound conditions. However, precise measurement needs accurate image-region segmentation. With the advent of deep learning for semantic image segmentation, accuracy of region segmentation is dramatically higher than traditional methods. Unfortunately, semantic segmentation in prior work did not produce satisfactory outputs in wound image segmentation, even with a large training dataset. This work, therefore, rethinks about the challenge and aims at not only improving segmentation accuracy, but also studying the impact of wound tissue types and color on accuracy. Since an end-to-end approach of semantic segmentation in prior work performed relatively poorly, the proposed method employs both image processing and deep learning techniques. The experiments indicated that slough was the most challenging tissue to be segmented. Also, properly increasing color variety of wound images significantly improved segmentation performance. The accuracy of the proposed method was 72%, 40% and 53% in terms of intersection over union for granulation, necrosis, and slough wound tissue types, respectively. The proposed method outperformed a prior end-to-end approach, even though this method employed particularly simpler neural network models and much smaller number of training images.
- 1 July 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Study of Chronic Wound Image Segmentation: Impact of Tissue Type and Color Data Augmentation
Chronic wound segmentation is an essential task for evaluating wound and its recovery progress. A physician usually measures a wound area to choose proper treatment according to wound conditions. However, precise measurement needs accurate image-region segmentation. With the advent of deep learning for semantic image segmentation, accuracy of region segmentation is dramatically higher than traditional methods. Unfortunately, semantic segmentation in prior work did not produce satisfactory outputs in wound image segmentation, even with a large training dataset. This work, therefore, rethinks about the challenge and aims at not only improving segmentation accuracy, but also studying the impact of wound tissue types and color on accuracy. Since an end-to-end approach of semantic segmentation in prior work performed relatively poorly, the proposed method employs both image processing and deep learning techniques. The experiments indicated that slough was the most challenging tissue to be segmented. Also, properly increasing color variety of wound images significantly improved segmentation performance. The accuracy of the proposed method was 72%, 40% and 53% in terms of intersection over union for granulation, necrosis, and slough wound tissue types, respectively. The proposed method outperformed a prior end-to-end approach, even though this method employed particularly simpler neural network models and much smaller number of training images.
- 23 February 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Rice-root cortex segmentation using graph optimization and multi-resolution analysis
Rice (Oryza sativa) breeders usually need to quantify the progress of their work by examining certain anatomical traits in the roots. These traits can be observed via a microscope. However, an efficient, accurate algorithm for image segmentation is required for quantitative analysis in a large dataset. This work proposes an automatic method based on graph optimization and multi-resolution analysis to segment and compute the area of the rice-root cortex from its cross-section image. This method extracts a rough region of the cortex in a coarse scale and locates likely boundary pixels in a fine scale. Each of these pixels is treated as a node in a graph. The method, then, selects some of these pixels to form an optimal cycle representing a cortex boundary. Optimality is mainly quantified by edge strength and curvature of a cycle and can be obtained by Dijkstra's shortest path algorithm. This formulation leads to a highly accurate and efficient algorithm (Dice similarity coefficient > 0.99 against manual segmentation and < 11 seconds of computation time per image on average).
- 23 February 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Rice-root cortex segmentation using graph optimization and multi-resolution analysis
Rice (Oryza sativa) breeders usually need to quantify the progress of their work by examining certain anatomical traits in the roots. These traits can be observed via a microscope. However, an efficient, accurate algorithm for image segmentation is required for quantitative analysis in a large dataset. This work proposes an automatic method based on graph optimization and multi-resolution analysis to segment and compute the area of the rice-root cortex from its cross-section image. This method extracts a rough region of the cortex in a coarse scale and locates likely boundary pixels in a fine scale. Each of these pixels is treated as a node in a graph. The method, then, selects some of these pixels to form an optimal cycle representing a cortex boundary. Optimality is mainly quantified by edge strength and curvature of a cycle and can be obtained by Dijkstra's shortest path algorithm. This formulation leads to a highly accurate and efficient algorithm (Dice similarity coefficient > 0.99 against manual segmentation and < 11 seconds of computation time per image on average).
- 21 November 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Using FFT range-power spectrum to improve accuracy for contact-free pulse measurement
Independent Component Analysis (ICA) on a color model can be applied to measure heart rate without physical contact with subjects. Unfortunately, current non-contact systems need accuracy improvements to make them suitable for some medical applications. While others employed the most dominant frequency calculated by FFT as a heart rate, we propose to accumulate power spectrums across frequencies and compute weighted average. This is highly effective when a subject's heart rate significantly changes during data acquisition. This work also systematically studied impacts of color models and found that straightforward combination of color models could lower performance. Yet, combining power spectrums from each color models marginally increases accuracy. Finally, impacts of time-window length were examined and the proposed method demonstrates improved robustness on most time-window lengths.
- 21 November 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Using FFT range-power spectrum to improve accuracy for contact-free pulse measurement
Independent Component Analysis (ICA) on a color model can be applied to measure heart rate without physical contact with subjects. Unfortunately, current non-contact systems need accuracy improvements to make them suitable for some medical applications. While others employed the most dominant frequency calculated by FFT as a heart rate, we propose to accumulate power spectrums across frequencies and compute weighted average. This is highly effective when a subject's heart rate significantly changes during data acquisition. This work also systematically studied impacts of color models and found that straightforward combination of color models could lower performance. Yet, combining power spectrums from each color models marginally increases accuracy. Finally, impacts of time-window length were examined and the proposed method demonstrates improved robustness on most time-window lengths.
- 1 July 2014
- Published by Wolters Kluwer Health in Plastic and Reconstructive Surgery
- Vol. 134 (1) , 130-139
The First Smartphone Application for Microsurgery Monitoring
Background: Postoperative monitoring of free flap tissue perfusion is vital. Devices available are expensive and complex to operate. Most surgeons rely on direct clinical observation. A monitoring system that is reliable, inexpensive, and easy to operate is needed. Using mobile phone technology, the authors developed and evaluated a new free flap monitoring system: SilpaRamanitor. Methods: Software was developed for Android-operated mobile phones. Forty-two normal subjects were recruited to assess its effectiveness. Varying degrees of pressure were applied around the index finger to produce partial venous occlusion, partial arterial occlusion, complete venous occlusion, and complete arterial occlusion sequentially. Photographs of each subject’s index and middle fingers were taken using the smartphone camera. To detect the abnormal perfusion presented on the index finger, the application was instructed to analyze photographs for color difference, with the unoccluded middle finger serving as the control. Results: The sensitivity, specificity, accuracy, false-negative results, and false-positive results were 94, 98, 95, 6, and 1 percent, respectively. The accuracy of the application in grading occlusion severity was also evaluated. Thirty-nine cases (93 percent) were correctly identified as venous occlusion. The occlusion severity was correctly identified in 33 cases (85 percent). Likewise, for the 40 cases (95 percent) correctly identified as arterial occlusion, the method correctly categorized its severity in 33 cases (83 percent). Conclusions: The authors developed a new, accurate, and reliable diagnostic system for postoperative microsurgery monitoring using a smartphone application. SilpaRamanitor is inexpensive and easy to use, making it applicable in many microsurgical settings. CLINICAL QUESTION/LEVEL OF EVIDENCE: Diagnostic, IV.
- 1 July 2014
- Published by Wolters Kluwer Health in Plastic and Reconstructive Surgery
- Vol. 134 (1) , 130-139
The First Smartphone Application for Microsurgery Monitoring
Background: Postoperative monitoring of free flap tissue perfusion is vital. Devices available are expensive and complex to operate. Most surgeons rely on direct clinical observation. A monitoring system that is reliable, inexpensive, and easy to operate is needed. Using mobile phone technology, the authors developed and evaluated a new free flap monitoring system: SilpaRamanitor. Methods: Software was developed for Android-operated mobile phones. Forty-two normal subjects were recruited to assess its effectiveness. Varying degrees of pressure were applied around the index finger to produce partial venous occlusion, partial arterial occlusion, complete venous occlusion, and complete arterial occlusion sequentially. Photographs of each subject’s index and middle fingers were taken using the smartphone camera. To detect the abnormal perfusion presented on the index finger, the application was instructed to analyze photographs for color difference, with the unoccluded middle finger serving as the control. Results: The sensitivity, specificity, accuracy, false-negative results, and false-positive results were 94, 98, 95, 6, and 1 percent, respectively. The accuracy of the application in grading occlusion severity was also evaluated. Thirty-nine cases (93 percent) were correctly identified as venous occlusion. The occlusion severity was correctly identified in 33 cases (85 percent). Likewise, for the 40 cases (95 percent) correctly identified as arterial occlusion, the method correctly categorized its severity in 33 cases (83 percent). Conclusions: The authors developed a new, accurate, and reliable diagnostic system for postoperative microsurgery monitoring using a smartphone application. SilpaRamanitor is inexpensive and easy to use, making it applicable in many microsurgical settings. CLINICAL QUESTION/LEVEL OF EVIDENCE: Diagnostic, IV.
- 3 March 2011
- Published by SPIE-Intl Soc Optical Eng
- p. 796237-796237-17
Robust method for extracting the pulmonary vascular trees from 3D MDCT images
Segmentation of pulmonary blood vessels from three-dimensional (3D) multi-detector CT (MDCT) images is important for pulmonary applications. This work presents a method for extracting the vascular trees of the pulmonary arteries and veins, applicable to both contrast-enhanced and unenhanced 3D MDCT image data. The method finds 2D elliptical cross-sections and evaluates agreement of these cross-sections in consecutive slices to find likely cross-sections. It next employs morphological multiscale analysis to separate vessels from adjoining airway walls. The method then tracks the center of the likely cross-sections to connect them to the pulmonary vessels in the mediastinum and forms connected vascular trees spanning both lungs. A ground-truth study indicates that the method was able to detect on the order of 98% of the vessel branches having diameter ≥ 3.0 mm. The extracted vascular trees can be utilized for the guidance of safe bronchoscopic biopsy.
- 3 March 2011
- Published by SPIE-Intl Soc Optical Eng
- p. 796237-796237-17
Robust method for extracting the pulmonary vascular trees from 3D MDCT images
Segmentation of pulmonary blood vessels from three-dimensional (3D) multi-detector CT (MDCT) images is important for pulmonary applications. This work presents a method for extracting the vascular trees of the pulmonary arteries and veins, applicable to both contrast-enhanced and unenhanced 3D MDCT image data. The method finds 2D elliptical cross-sections and evaluates agreement of these cross-sections in consecutive slices to find likely cross-sections. It next employs morphological multiscale analysis to separate vessels from adjoining airway walls. The method then tracks the center of the likely cross-sections to connect them to the pulmonary vessels in the mediastinum and forms connected vascular trees spanning both lungs. A ground-truth study indicates that the method was able to detect on the order of 98% of the vessel branches having diameter ≥ 3.0 mm. The extracted vascular trees can be utilized for the guidance of safe bronchoscopic biopsy.
- 27 February 2011
- Published by Springer Nature in International Journal of Computer Assisted Radiology and Surgery
- Vol. 6 (4) , 539-555
Automatic definition of the central-chest lymph-node stations
Purpose Lung cancer remains the leading cause of cancer death in the United States. Central to the lung-cancer diagnosis and staging process is the assessment of the central-chest lymph nodes. This assessment requires two steps: (1) examination of the lymph-node stations and identification of diagnostically important nodes in a three-dimensional (3D) multidetector computed tomography (MDCT) chest scan; (2) tissue sampling of the identified nodes. We describe a computer-based system for automatically defining the central-chest lymph-node stations in a 3D MDCT chest scan. Methods Automated methods first construct a 3D chest model, consisting of the airway tree, aorta, pulmonary artery, and other anatomical structures. Subsequent automated analysis then defines the 3D regional nodal stations, as specified by the internationally standardized TNM lung-cancer staging system. This analysis involves extracting over 140 pertinent anatomical landmarks from structures contained in the 3D chest model. Next, the physician uses data mining tools within the system to interactively select diagnostically important lymph nodes contained in the regional nodal stations. Results Results from a ground-truth database of unlabeled lymph nodes identified in 32 MDCT scans verify the system’s performance. The system automatically defined 3D regional nodal stations that correctly labeled 96% of the database’s lymph nodes, with 93% of the stations correctly labeling 100% of their constituent nodes. Conclusions The system accurately defines the regional nodal stations in a given high-resolution 3D MDCT chest scan and eases a physician’s burden for analyzing a given MDCT scan for lymph-node station assessment. It also shows potential as an aid for preplanning lung-cancer staging procedures.
- 27 February 2011
- Published by Springer Nature in International Journal of Computer Assisted Radiology and Surgery
- Vol. 6 (4) , 539-555
Automatic definition of the central-chest lymph-node stations
Purpose Lung cancer remains the leading cause of cancer death in the United States. Central to the lung-cancer diagnosis and staging process is the assessment of the central-chest lymph nodes. This assessment requires two steps: (1) examination of the lymph-node stations and identification of diagnostically important nodes in a three-dimensional (3D) multidetector computed tomography (MDCT) chest scan; (2) tissue sampling of the identified nodes. We describe a computer-based system for automatically defining the central-chest lymph-node stations in a 3D MDCT chest scan. Methods Automated methods first construct a 3D chest model, consisting of the airway tree, aorta, pulmonary artery, and other anatomical structures. Subsequent automated analysis then defines the 3D regional nodal stations, as specified by the internationally standardized TNM lung-cancer staging system. This analysis involves extracting over 140 pertinent anatomical landmarks from structures contained in the 3D chest model. Next, the physician uses data mining tools within the system to interactively select diagnostically important lymph nodes contained in the regional nodal stations. Results Results from a ground-truth database of unlabeled lymph nodes identified in 32 MDCT scans verify the system’s performance. The system automatically defined 3D regional nodal stations that correctly labeled 96% of the database’s lymph nodes, with 93% of the stations correctly labeling 100% of their constituent nodes. Conclusions The system accurately defines the regional nodal stations in a given high-resolution 3D MDCT chest scan and eases a physician’s burden for analyzing a given MDCT scan for lymph-node station assessment. It also shows potential as an aid for preplanning lung-cancer staging procedures.