• Progress in Medical Physics
• /
• v.26 no.1
• /
• pp.52-58
• /
• 2015

The automated dental cavity detection program for a new concept intra-oral dental x-ray imaging device, an auxiliary diagnosis system, which is able to assist a dentist to identify dental caries in an early stage and to make an accurate diagnosis, was to be developed. The primary theory of the automatic dental cavity detection program is divided into two algorithms; one is an image segmentation skill to discriminate between a dental cavity and a normal tooth and the other is a computational method to analyze feature of an tooth image and take an advantage of it for detection of dental cavities. In the present study, it is, first, evaluated how accurately the DRLSE (Direct Regularized Level Set Evolution) method extracts demarcation surrounding the dental cavity. In order to evaluate the ability of the developed algorithm to automatically detect dental cavities, 7 tooth phantoms from incisor to molar were fabricated which contained a various form of cavities. Then, dental cavities in the tooth phantom images were analyzed with the developed algorithm. Except for two cavities whose contours were identified partially, the contours of 12 cavities were correctly discriminated by the automated dental caries detection program, which, consequently, proved the practical feasibility of the automatic dental lesion detection algorithm. However, an efficient and enhanced algorithm is required for its application to the actual dental diagnosis since shapes or conditions of the dental caries are different between individuals and complicated. In the future, the automatic dental cavity detection system will be improved adding pattern recognition or machine learning based algorithm which can deal with information of tooth status.

• Journal of KIISE:Software and Applications
• /
• v.37 no.6
• /
• pp.455-463
• /
• 2010

In this paper, we present an approach to sentence boundary detection for web documents that builds on statistical-based methods and uses rule-based correction. The proposed system uses the classification model learned offline using a training set of human-labeled web documents. The web documents have many word-spacing errors and frequently no punctuation mark that indicates the end of sentence boundary. As sentence boundary candidates, the proposed method considers every Ending Eomis as well as punctuation marks. We optimize engine performance by selecting the best feature, the best training data, and the best classification algorithm. For evaluation, we made two test sets; Set1 consisting of articles and blog documents and Set2 of web community documents. We use F-measure to compare results on a large variety of tasks, Detecting only periods as sentence boundary, our basis engine showed 96.5% in Set1 and 56.7% in Set2. We improved our basis engine by adapting features and the boundary search algorithm. For the final evaluation, we compared our adaptation engine with our basis engine in Set2. As a result, the adaptation engine obtained improvements over the basis engine by 39.6%. We proved the effectiveness of the proposed method in sentence boundary detection.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.11
• /
• pp.206-216
• /
• 2013

The emotion plays a critical role in human's daily life including learning, action, decision and communication. In this paper, emotion discrimination classifier is designed to reduce system complexity through reduced selection of dominant features from biosignals. The photoplethysmography(PPG), skin temperature, skin conductance, fontal and parietal electroencephalography(EEG) signals were measured during 4 types of movie watching associated with the induction of neutral, sad, fear joy emotions. The genetic algorithm with support vector machine(SVM) based fitness function was designed to determine dominant features among 24 parameters extracted from measured biosignals. It shows maximum classification accuracy of 96.4%, which is 17% higher than that of SVM alone. The minimum error features selected are the mean and NN50 of heart rate variability from PPG signal, the mean of PPG induced pulse transit time, the mean of skin resistance, and ${\delta}$ and ${\beta}$ frequency band powers of parietal EEG. The combination of parietal EEG, PPG, and skin resistance is recommendable in high accuracy instrumentation, while the combinational use of PPG and skin conductance(79% accuracy) is affordable in simplified instrumentation.

• Journal of Korea Multimedia Society
• /
• v.16 no.6
• /
• pp.764-781
• /
• 2013

In this paper, we propose a highly precise vehicle detection method with low false alarm using billboard sweep stereo matching and multi-stage hypothesis generation. First, we capture stereo images from cameras established in front of the vehicle and obtain the disparity map in which the regions of ground plane or background are removed using billboard sweep stereo matching algorithm. And then, we perform the vehicle detection and tracking on the labeled disparity map. The vehicle detection and tracking consists of three steps. In the learning step, the SVM(support vector machine) classifier is obtained using the features extracted from the gabor filter. The second step is the vehicle detection which performs the sobel edge detection in the image of the left camera and extracts candidates of the vehicle using edge image and billboard sweep stereo disparity map. The final step is the vehicle tracking using template matching in the next frame. Removal process of the tracking regions improves the system performance in the candidate region of the vehicle on the succeeding frames.

• Journal of Internet Computing and Services
• /
• v.24 no.5
• /
• pp.17-27
• /
• 2023

Today, as AI (Artificial Intelligence) technology develops and its practicality increases, it is widely used in various application fields in real life. At this time, the AI model is basically learned based on various statistical properties of the learning data and then distributed to the system, but unexpected changes in the data in a rapidly changing data situation cause a decrease in the model's performance. In particular, as it becomes important to find drift signals of deployed models in order to respond to new and unknown attacks that are constantly created in the security field, the need for lifecycle management of the entire model is gradually emerging. In general, it can be detected through performance changes in the model's accuracy and error rate (loss), but there are limitations in the usage environment in that an actual label for the model prediction result is required, and the detection of the point where the actual drift occurs is uncertain. there is. This is because the model's error rate is greatly influenced by various external environmental factors, model selection and parameter settings, and new input data, so it is necessary to precisely determine when actual drift in the data occurs based only on the corresponding value. There are limits to this. Therefore, this paper proposes a method to detect when actual drift occurs through an Anomaly analysis technique based on XAI (eXplainable Artificial Intelligence). As a result of testing a classification model that detects DGA (Domain Generation Algorithm), anomaly scores were extracted through the SHAP(Shapley Additive exPlanations) Value of the data after distribution, and as a result, it was confirmed that efficient drift point detection was possible.

• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.1-23
• /
• 2018

From the 21st century, various high-quality services have come up with the growth of the internet or 'Information and Communication Technologies'. Especially, the scale of E-commerce industry in which Amazon and E-bay are standing out is exploding in a large way. As E-commerce grows, Customers could get what they want to buy easily while comparing various products because more products have been registered at online shopping malls. However, a problem has arisen with the growth of E-commerce. As too many products have been registered, it has become difficult for customers to search what they really need in the flood of products. When customers search for desired products with a generalized keyword, too many products have come out as a result. On the contrary, few products have been searched if customers type in details of products because concrete product-attributes have been registered rarely. In this situation, recognizing texts in images automatically with a machine can be a solution. Because bulk of product details are written in catalogs as image format, most of product information are not searched with text inputs in the current text-based searching system. It means if information in images can be converted to text format, customers can search products with product-details, which make them shop more conveniently. There are various existing OCR(Optical Character Recognition) programs which can recognize texts in images. But existing OCR programs are hard to be applied to catalog because they have problems in recognizing texts in certain circumstances, like texts are not big enough or fonts are not consistent. Therefore, this research suggests the way to recognize keywords in catalog with the Deep Learning algorithm which is state of the art in image-recognition area from 2010s. Single Shot Multibox Detector(SSD), which is a credited model for object-detection performance, can be used with structures re-designed to take into account the difference of text from object. But there is an issue that SSD model needs a lot of labeled-train data to be trained, because of the characteristic of deep learning algorithms, that it should be trained by supervised-learning. To collect data, we can try labelling location and classification information to texts in catalog manually. But if data are collected manually, many problems would come up. Some keywords would be missed because human can make mistakes while labelling train data. And it becomes too time-consuming to collect train data considering the scale of data needed or costly if a lot of workers are hired to shorten the time. Furthermore, if some specific keywords are needed to be trained, searching images that have the words would be difficult, as well. To solve the data issue, this research developed a program which create train data automatically. This program can make images which have various keywords and pictures like catalog and save location-information of keywords at the same time. With this program, not only data can be collected efficiently, but also the performance of SSD model becomes better. The SSD model recorded 81.99% of recognition rate with 20,000 data created by the program. Moreover, this research had an efficiency test of SSD model according to data differences to analyze what feature of data exert influence upon the performance of recognizing texts in images. As a result, it is figured out that the number of labeled keywords, the addition of overlapped keyword label, the existence of keywords that is not labeled, the spaces among keywords and the differences of background images are related to the performance of SSD model. This test can lead performance improvement of SSD model or other text-recognizing machine based on deep learning algorithm with high-quality data. SSD model which is re-designed to recognize texts in images and the program developed for creating train data are expected to contribute to improvement of searching system in E-commerce. Suppliers can put less time to register keywords for products and customers can search products with product-details which is written on the catalog.

• Journal of the Korean Society of Radiology
• /
• v.82 no.5
• /
• pp.1196-1206
• /
• 2021

Purpose To construct a standard dataset of contrast-enhanced CT images of liver tumors to test the performance and safety of artificial intelligence (AI)-based algorithms for clinical decision support systems (CDSSs). Materials and Methods A consensus group of medical experts in gastrointestinal radiology from four national tertiary institutions discussed the conditions to be included in a standard dataset. Seventy-five cases of hepatocellular carcinoma, 75 cases of metastasis, and 30-50 cases of benign lesions were retrieved from each institution, and the final dataset consisted of 300 cases of hepatocellular carcinoma, 300 cases of metastasis, and 183 cases of benign lesions. Only pathologically confirmed cases of hepatocellular carcinomas and metastases were enrolled. The medical experts retrieved the medical records of the patients and manually labeled the CT images. The CT images were saved as Digital Imaging and Communications in Medicine (DICOM) files. Results The medical experts in gastrointestinal radiology constructed the standard dataset of contrast-enhanced CT images for 783 cases of liver tumors. The performance and safety of the AI algorithm can be evaluated by calculating the sensitivity and specificity for detecting and characterizing the lesions. Conclusion The constructed standard dataset can be utilized for evaluating the machine-learning-based AI algorithm for CDSS.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.31 no.1
• /
• pp.83-97
• /
• 2021

Wireless sensors that make up the Wireless Sensor Network generally have extremely limited power and resources. The wireless sensor enters the sleep state at a certain interval to conserve power. The Sleep deflation attack is a deadly attack that consumes power by preventing wireless sensors from entering the sleep state, but there is no clear countermeasure. Thus, in this paper, using clustering-based binary search tree structure, the Sleep deprivation attack detection model is proposed. The model proposed in this paper utilizes one of the characteristics of both attack sensor nodes and normal sensor nodes which were classified using machine learning. The characteristics used for detection were determined using Long Short-Term Memory, Decision Tree, Support Vector Machine, and K-Nearest Neighbor. Thresholds for judging attack sensor nodes were then learned by applying the SVM. The determined features were used in the proposed algorithm to calculate the values for attack detection, and the threshold for determining the calculated values was derived by applying SVM.Through experiments, the detection model proposed showed a detection rate of 94% when 35% of the total sensor nodes were attack sensor nodes and improvement of up to 26% in power retention.

• KIISE Transactions on Computing Practices
• /
• v.23 no.1
• /
• pp.57-64
• /
• 2017

Short message service (SMS) is one of the most important communication methods for people who use mobile phones. However, illegal advertising spam messages exploit people because they can be used without the need for friend registration. Recently, spam message filtering systems that use machine learning have been developed, but they have some disadvantages such as requiring many calculations. In this paper, we implemented a spam message filtering system using the set-based POI search algorithm and sentence similarity without servers. This algorithm can judge whether the input query is a spam message or not using only letter composition without any server computing. Therefore, we can filter the spam message although the input text message has been intentionally modified. We added a specific preprocessing option which aims to enable spam filtering. Based on the experimental results, we observe that our spam message filtering system shows better performance than the original set-based POI search algorithm. We evaluate the proposed system through extensive simulation. According to the simulation results, the proposed system can filter the text message and show high accuracy performance against the text message which cannot be filtered by the 3 major telecom companies.

• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.11
• /
• pp.537-542
• /
• 2017

Aggressive driving is a major cause of car accidents. Previous studies have mainly analyzed young driver's aggressive driving tendency, yet they were only done through pure clustering or classification technique of machine learning. However, since elderly people have different driving habits due to their fragile physical conditions, it is necessary to develop a new method such as enhancing the characteristics of driving data to properly analyze aggressive driving of elderly drivers. In this study, acceleration data collected from a smartphone of a driving vehicle is analyzed by a newly proposed ECA(Enhanced Clustering method for Acceleration data) technique, coupled with a conventional clustering technique (K-means Clustering, Expectation-maximization algorithm). ECA selects high-intensity data among the data of the cluster group detected through K-means and EM in all of the subjects' data and models the characteristic data through the scaled value. Using this method, the aggressive driving data of all youth and elderly experiment participants were collected, unlike the pure clustering method. We further found that the K-means clustering has higher detection efficiency than EM method. Also, the results of K-means clustering demonstrate that a young driver has a driving strength 1.29 times higher than that of an elderly driver. In conclusion, the proposed method of our research is able to detect aggressive driving maneuvers from data of the elderly having low operating intensity. The proposed method is able to construct a customized safe driving system for the elderly driver. In the future, it will be possible to detect abnormal driving conditions and to use the collected data for early warning to drivers.