Supapom Kiattisin

Bio: Supapom Kiattisin is an academic researcher from Mahidol University. The author has contributed to research in topics: Service provider & Information technology. The author has an hindex of 2, co-authored 6 publications receiving 37 citations.

Automated classification between age-related macular degeneration and Diabetic macular edema in OCT image using image segmentation

Abstract: Age-related macular degeneration (AMD) and Diabetic macular edema (DME) are to lead causes to make a visual loss in people. People are suffered from the use of many time to diagnose and to wait for treatment both of diseases. This paper proposes a step of image segmentation to be divided the optical coherence tomography (OCT) to find the retinal pigment epithelium (RPE) layer and to detect a shape of drusen in RPE layer. Then, the RPE layer is used for finding retinal nerve fiber layer (RNFL) and for detecting a bubble of blood area in RNFL complex. Finally, this method uses a binary classification to classify two diseases characteristic between AMD and DME. We use 16 OCT images of a case study to segmentation and classify two diseases. In the experimental results, 10 images of AMD and 6 images of DME can be detected and classified to accuracy of 87.5%.

Air quality classification in Thailand based on decision tree

Abstract: The paper presents a model for management classifier air quality by algorithm of decision tree using air quality index in Thailand including a pollutant's concentration e.g. O 3 , NO 2 , CO, SO 2 , PM 10 and levels of healthy concern. The purpose of this research is to establish rules of separated air quality classification by levels of healthy concern. The results of this study are correctly classified into instances of training set of 96.80% and testing set of 91.07%. The ROC curve shows that the training set data and testing set data are similar to such results. The algorithm of decision tree can use to become rules of separated air quality classification by levels of healthy concern.

Atom-Task Precondition Technique to Optimize Large Scale GUI Testing Time based on Parallel Scheduling Algorithm

Abstract: The modern software development mostly aims to reduce a development time. The product time to market must be fast for quick gathering feedback from the user. DevOps brings the continuous practice to improve software development process on both continuous integration and continuous delivery. In continuous processes, software testing is the most time-consuming part which significant for overall process especially graphic user interface or GUI. Several techniques can reduce GUI testing time such as a distributed testing which is help UI testing running in parallel on a distributed machine. By running distributed GUI testing initially without experience or knowledge from an expert lead to the un-optimized speed of running test or even the future problem such as an unpredictable number of worker, the bottleneck of the worker node. This paper has purpose the Atom-Task precondition technique, the technique for filtering the test before running the parallel testing process to optimize the testing time and avoiding worker bottleneck problem and also remain an ability to scale the worker process for desired testing time with predictable resource for large-scale testing in the distributed environment.

A header encryption of ultrasound image using absolute-value chaotic map

Abstract: this paper presents a partial encryption scheme using absolute-value chaotic map for secure electronic health records (EHR). The HER system has been an emerging technology that allows medical personals to create, manage, and control medical data electronically through specific database or even web browsers. The proposed encryption scheme realizes XOR operations between separated planes of binary gray-scale image and a binaty image generated by an absolute-value chaotic map. The proposed is relatively simple containning a single absolute-value function with two constants and offers complex and robust dynamical behaviors in terms of random output values. Experiments have been performed in MATLAB using a magnetic resonance image which is divided into 64 sub-blocks and 13th iterations were proceeded for encryption. Encryption qualitative performances are evaluated through pixel density histograms, 2-dimensional power spectral density, and vertical, horizontal, and diagonal correlation plots. For the encryption quantitative measures, correlation coefficients, entropy, NPCR and UACI are realized. Demonstrations of wrong-key decrypted image are also included. The proposed encryption scheme offers a potential alternative to a secure medical data records and web browsing through cloud computing systems.

A Perspective of Thai Government information Service

Abstract: Information is an important and vital thing for a citizen to raise awareness and understanding. The increasing growth factor of information technology has made information become an indispensable part of supporting citizen’s lives. The role of the government sector defines the purpose of the form of government information services. The service is the needs of the government service providers rather than the needs of the citizen who are the service recipients. Therefore, the development of data services should focus on increasing the quality of the information, choosing the type of service through a partner that the public can access easily, including presenting the information that the people want.

Comparing different methods for statistical modeling of particulate matter in Tehran, Iran

Abstract: Particulate matter has major impacts on human health in urban regions, and Tehran is one of the most polluted metropolitan cities in the world, struggling to control this pollutant more than any other contaminant. PM2.5 concentrations were predicted by three statistical modeling methods: (i) decision tree (DT), (ii) Bayesian network (BN), and (iii) support vector machine (SVM). Collected data for three consecutive years (January 2013 to January 2016) were used to develop the models. Data from the initial 2 years were employed as the training data, and measurements from the last year were used for testing the models. Twelve parameters, covering meteorological variables and concentrations of several chemical species, were explored as potential predictors of PM2.5. According to the sensitivity analysis of PM2.5 by SVM and derived explicit equations from BN and DT, PM10, NO2, SO2, and O3 are the most important predictors. Furthermore, the impacts of the predictors on the PM2.5 were assessed which the chemical precursors’ influences indicated more in comparison with meteorological parameters. Capabilities of the models were compared to each other and the support vector machine was found to be the best performing, based on evaluation criteria. Nonetheless, the decision tree and Bayesian network methods also provided acceptable results. We suggest more studies using the SVM and other methods as hybrids would lead to improved models.

Fully Automated Robust System to Detect Retinal Edema, Central Serous Chorioretinopathy, and Age Related Macular Degeneration from Optical Coherence Tomography Images.

Abstract: Maculopathy is the excessive damage to macula that leads to blindness. It mostly occurs due to retinal edema (RE), central serous chorioretinopathy (CSCR), or age related macular degeneration (ARMD). Optical coherence tomography (OCT) imaging is the latest eye testing technique that can detect these syndromes in early stages. Many researchers have used OCT images to detect retinal abnormalities. However, to the best of our knowledge, no research that presents a fully automated system to detect all of these macular syndromes is reported. This paper presents the world's first ever decision support system to automatically detect RE, CSCR, and ARMD retinal pathologies and healthy retina from OCT images. The automated disease diagnosis in our proposed system is based on multilayered support vector machines (SVM) classifier trained on 40 labeled OCT scans (10 healthy, 10 RE, 10 CSCR, and 10 ARMD). After training, SVM forms an accurate decision about the type of retinal pathology using 9 extracted features. We have tested our proposed system on 2819 OCT scans (1437 healthy, 640 RE, and 742 CSCR) of 502 patients from two different datasets and our proposed system correctly diagnosed 2817/2819 subjects with the accuracy, sensitivity, and specificity ratings of 99.92%, 100%, and 99.86%, respectively.