Noppadol Maneerat

Feature extraction from retinal fundus image for early detection of diabetic retinopathy

Automated detection of lesions in retinal fundus image can be aid in the detection of diabetic retinopathy. Exudates are the early sign of diabetic retinopathy so the proper detection of these lesions is an essential task in an automatic retinal screening. On the research work leading to automatic analysis of exudate detection, the knowledge of Optic Disk (OD) location is very useful. An efficient algorithm is presented to detect the OD and exudate which are the most important features for early detection of diabetic retinopathy. From a retinal fundus image, the proposed method first preprocesses and estimates the histogram of retinal background, then filters out the bright pixels in intensity image. They include OD, and non-OD (exudates and noise). Next, an OD boundary is determined and eliminated after applying blob boundary measurement and morphological reconstruction. Finally, exudates are extracted by applying the maximum entropy thresholding to filter out the bright pixels from the green component of retinal image which OD region inside is eliminated. The proposed technique has been tested first on 100 images from hospital. Experimental results show that 93% and 89% of OD and exudate were detected correctly, respectively.

Ontology-based daily menu assistance system

The daily useful nutrition needs become important information to be given to the society. Occurrence of many nutrition cases, such as obesity, overweight or even underweight, shows that the society have not been given an appropriate information about their recommended daily values for key nutrients and also the suggestion of their daily menus. In this paper, we design ontology-based daily menu assistance system using the Indonesian food as a case study. The ontology is a simple methodology to describe the concept of an expert system. We have used it to model a nutrition needs domain in the information of health control system. This methodology is used to advise the appropriate Indonesian food menus to anyone based on their personal data, calories needed, activity factor, and abstinence.

Automatic exudate extraction for early detection of Diabetic Retinopathy

Diabetic Retinopathy (DR) is the most common cause of blindness in diabetic patients, but early detection and timely treatment can prevent this problem. Exudates have been found to be one of the signs and serious DR anomalies so the proper detection of these lesions and the treatment should be done immediately to prevent loss of vision. The aim of this study is to automatically detect these lesions in fundus images. To achieve this goal, the proposed method first preprocesses to improve the quality of fundus image, and then Optic Disc (OD) is detected and eliminated to prevent the interference to the result of exudate detection by combination of 3 methods; image binarization, Region Of Interest (ROI) based segmentation and Morphological Reconstruction (MR). Next, exudates are detected by applying the maximum entropy thresholding to filter out the bright pixels from the result of OD region eliminated. Since the result contains some noises which appear as bright light at the edge of fundus area in some images, that affect is considered and eliminated to improve the result of false positive. Finally, exudates are extracted by using MR. The proposed technique has been tested on 100 fundus images from hospital. Experimental results show that 91 % of exudate is extracted correctly with the average process of 3.92 second per image.

Provision of Thai herbal recommendation based on an ontology

In Thailand, most of people like to use Thai herbs for their traditional medical treatments. However, since there are various sorts of Thai herbs, and the Thai herbal knowledge is complicated, it is difficult to find an appropriate one for each health condition. In order to help people to find suitable Thai herbs to cure the diseases, we have developed a system to provide herbal recommendations to users regarding their symptoms. In the development, we represented the Thai herbal knowledge in an ontology, and extracted new facts based on the ontology. Finally, the system provides appropriate herbal recommendations to users based on extracted facts and the ontology. This paper shows how we represented Thai herbal knowledge in an ontology, and how we extract the new facts based on the ontology, as well as how the system provides herbal recommendations to users.

Application of Protégé, SWRL and SQWRL in fuzzy ontology-based menu recommendation

We develop a daily menu assistance system which is built to give a suggested daily menu based on daily calories need. In this paper, we design a recommendation feature using fuzzy ontology to give menu recommendation by few factors, such as price, rate, vote and taste, since so many menus are suggested. Protégé, SWRL (Semantic Web Rule Language) and SQWRL (Semantic Query-Enhanced Web Rule Language) are used to show that this feature provides user the more specific, recommended and preferable menus. Protégé, an open-source ontology design software, is used to develop menu recommendation ontology. SWRL is used to build fuzzy ontology classes and properties mapping, and also calculations. SQWRL performs a query in menu recommendation results.

Composition method of communication system specifications in asynchronous model and its support system

One of the most important methods in communication system design, especially in protocol design, is the composition method. We propose a method for simultaneously composing service specifications and protocol specifications based on the LOTOS language. In this method, an asynchronous communication model is adopted which is more realistic in actual communication networks. We use the concept of the weak bisimulation equivalence to represent the correctness of composition. A software support system based on the proposed composition method is also described.

Automatic microaneurysms detection through retinal color image analysis

This paper proposes an automatic system to diagnose the diabetic retinopathy symptom, which can cause a loss of vision by analysis the abnormality in retinal image. Digital image processing system is developed for the retinal image analysis which helps ophthalmologists to identify diabetic patients. The retinal images derived from ophthalmologists are used to analysis by using HSV, area identification and eccentricity techniques to distinguish diabetic retinopathy symptoms from normal diabetic patients. First color bar is evaluated by using HSV method and then using the eccentricity technique with area of pixel to find out the abnormality of Microaneurysms (MAs). The accuracy result of experiment is around 93% when compares to the analysis of ophthalmologists.

Anomaly detection through packet header data

Intrusion Detection System (IDS) is a crucial part of network security area and is widely employed. Signature-based matching mechanisms require a completed analysis of attack patterns and the availability of knowledge detection beforehand. To cope with new attacks, IDS tools require to be continuously updated with the signature rules. In this paper, we present anomaly detection technique by using Complex Gaussian Coefficient to calculate the threshold for detecting unknown flooding attacks. The Network traffics are generated for three types of situations in the normal light traffic period, during the attacking period and in the heavy traffic period. The numbers of packets in time domain are transformed to complex Gaussian coefficient. The variances of the complex wavelet magnitude in each derivative level significantly describe network situation. This technique can be applied to detect unknown DDoS flooding patterns.

Ontology-Based Nutrient Solution Control System for Hydroponics

This paper presents the Ontology-based Nutrient Solution Control System for Hydroponics with Protégé. We consider variables of electrical conductivity (EC), Potential of Hydrogen ion (pH), intensity of solution, species of plants and the relation of the device in the system for supporting to make the suitable decisions with the control system of hydroponic nutrient solution.

A “Dual-acceptor Channel” Membraneless Gas-diffusion Unit for Simultaneous Determination of Ethanol and Acetaldehyde in Liquors Using Reverse Flow Injection

A new design of membraneless gas-diffusion unit with dual acceptor channels for separation, collection and simultaneous determination of two volatile analytes in liquid sample is presented. The unit is comprised of three parallel channels in a closed module. A sample is aspirated into the central channel and two kinds of reagents are introduced into the other two channels. Two analytes are isolated from the sample matrix by diffusion into head-space and absorbed into the specific reagents. Non-absorbed vapor is released by opening the programmable controlled lid. The unit was applied to liquors for measurement of ethanol and acetaldehyde using reverse flow injection. Dichromate and nitroprusside were exploited as reagents for colorimetric detection of ethanol and acetaldehyde, respectively. Good linearity ranges (r2 >0.99) with high precision (RSD <2%) and high accuracy (recovery: 90 - 105%) were achieved. The results were compared to the results by GC-FID and no significant difference was observed by paired t-test (95% confidence).