• Journal of the Korea Convergence Society
• /
• v.12 no.1
• /
• pp.99-104
• /
• 2021

In this paper, we propose health risk management using feature extraction and cluster analysis considering time flow. The proposed method proceeds in three steps. The first is the pre-processing and feature extraction step. It collects user's lifelog using a wearable device, removes incomplete data, errors, noise, and contradictory data, and processes missing values. Then, for feature extraction, important variables are selected through principal component analysis, and data similar to the relationship between the data are classified through correlation coefficient and covariance. In order to analyze the features extracted from the lifelog, dynamic clustering is performed through the K-means algorithm in consideration of the passage of time. The new data is clustered through the similarity distance measurement method based on the increment of the sum of squared errors. Next is to extract information about the cluster by considering the passage of time. Therefore, using the health decision-making system through feature clusters, risks able to managed through factors such as physical characteristics, lifestyle habits, disease status, health care event occurrence risk, and predictability. The performance evaluation compares the proposed method using Precision, Recall, and F-measure with the fuzzy and kernel-based clustering. As a result of the evaluation, the proposed method is excellently evaluated. Therefore, through the proposed method, it is possible to accurately predict and appropriately manage the user's potential health risk by using the similarity with the patient.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.6
• /
• pp.157-165
• /
• 2020

Aiming at the development of neural network and self-driving data set, it is also an idea to improve the performance of network model to detect moving objects by dividing the data set. In Darknet network framework, the YOLOv4 (You Only Look Once v4) network model was used to train and test Udacity data set. According to 7 proportions of the Udacity data set, it was divided into three subsets including training set, validation set and test set. K-means++ algorithm was used to conduct dimensional clustering of object boxes in 7 groups. By adjusting the super parameters of YOLOv4 network for training, Optimal model parameters for 7 groups were obtained respectively. These model parameters were used to detect and compare 7 test sets respectively. The experimental results showed that YOLOv4 can effectively detect the large, medium and small moving objects represented by Truck, Car and Pedestrian in the Udacity data set. When the ratio of training set, validation set and test set is 7:1.5:1.5, the optimal model parameters of the YOLOv4 have highest detection performance. The values show mAP50 reaching 80.89%, mAP75 reaching 47.08%, and the detection speed reaching 10.56 FPS.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.10
• /
• pp.363-372
• /
• 2022

Since the recent COVID-19 Pandemic, the ransomware fandom has intensified along with the expansion of remote work. Currently, anti-virus vaccine companies are trying to respond to ransomware, but traditional file signature-based static analysis can be neutralized in the face of diversification, obfuscation, variants, or the emergence of new ransomware. Various studies are being conducted for such ransomware detection, and detection studies using signature-based static analysis and behavior-based dynamic analysis can be seen as the main research type at present. In this paper, the frequency of ".text Section" Opcode and the Native API used in practice was extracted, and the association between feature information selected using K-means Clustering algorithm, Cosine Similarity, and Pearson correlation coefficient was analyzed. In addition, Through experiments to classify and detect worms among other malware types and Cerber-type ransomware, it was verified that the selected feature information was specialized in detecting specific ransomware (Cerber). As a result of combining the finally selected feature information through the above verification and applying it to machine learning and performing hyper parameter optimization, the detection rate was up to 93.3%.

• Journal of KIISE:Software and Applications
• /
• v.28 no.2
• /
• pp.179-191
• /
• 2001

Comparison shopping is a merchant brokering process that finds the best price for the desired product from several Web-based online stores. To get a scalable comparison shopper, we need an agent that automatically constructs a simple information extraction procedure, called a wrapper, for each semi-structured store. Automatic construction of wrappers for HTML-based Web stores is difficult because HTML only defines how information is to be displayed, not what it means, and different stores employ different ways of manipulating customer queries and different presentation formats for displaying product descriptions. Wrapper induction has been suggested as a promising strategy for overcoming this heterogeneity. However, previous scalable comparison-shoppers such as ShopBot rely on a strong bias in the product descriptions, and as a result, many stores that do not confirm to this bias were unable to be recognized. This paper proposes a more scalable comparison-shopping agent named MORPHEUS. MORPHEUS presents a simple but robust inductive learning algorithm that antomatically constructs wrappers. The main idea of the proposed algorithm is to recognize the position and the structure of a product description unit by finding the most frequent pattern from the sequence of logical line information in output HTML pages. MORPHEUS successfully constructs correct wtappers for most stores by weakening a bias assumed in previous systems. It also tolerates some noises that might be present in production descriptions such as missing attributes. MORPHEUS generates the wrappers rapidly by excluding the pre-processing phase of removing redundant fragments in a page such as a header, a tailer, and advertisements. Eventually, MORPHEUS provides a framework from which a customized comparison-shopping agent can be organized for a user by facilitating the dynamic addition of new stores.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.19 no.1
• /
• pp.154-166
• /
• 2016

This study aims to contribute to better understanding the effects of the changes in the parameter values of GroundFilter algorithm(GF), which performs filtering process, and of GridsurfaceCreate algorithm(GC), which creates regular grid, provided in Fusion software on the accuracy of elevation of the final LiDAR-DEM products through comparative analysis. In order to test whether there are significant effects on the accuracy of the final LiDAR-DEM products due to the changes of GF(1, 3, 5, 7, 9) parameter levels and GC(1, 3, 5, 7, 9) parameter levels, two-way ANOVA is conducted based on residuals. The residuals are calculated using the differences between each sample plot's paired field-measured and DEM-derived elevation values given each individual GF and GC level. After that, Tukey HSD test is conducted as a post hoc test for grouping the levels. As a result of two-way ANOVA test, it is found that the change in the GF levels significantly affects the accuracy of LiDAR-DEM elevations(F-value : 27.340, p < 0.01), while the change in the GC levels does not significantly affect the accuracy of LiDAR-DEM elevations(F-value : 0.457). It is also found that the interaction effect between GF and GC levels is not likely to exist(F-value : 0.247). From the results of the Tukey HSD test in the GF levels, GF levels can be divided into two groups('7', '5', '9', '3' vs '1') by the differences of means of residuals. Given the current conditions, LiDAR-DEM can achieve the best accuracy when the level '7' and '3' are given as GF and GC level, respectively.

• Journal of Biomedical Engineering Research
• /
• v.16 no.4
• /
• pp.507-516
• /
• 1995

The nonstationary identifier in the DCT domain is suggested in this study for the identification of AR parameters of above-lesion upper-trunk electromyographic (EMG) signals as a means of developing a reliable real time signal to control functional electrical stimulation (FES) in paraplegics to enable primitive walking. As paraplegic shifts his posture from one attitude to another, there is transition period where the signal is clearly nonstationary. Also as muscle fatigues, nonstationarities become more prevalent even during stable postures. So, it requires a develpment of time varying nonstationary EMG signal identifier. In this paper, time varying nonstationary EMG signals are transformed into DCT domain and the transformed EMG signals are modeled and analyzed in the transform domain. In the DCT domain, we verified reduction of condition number and increment of the smallest eigenvalue of input correlation matrix that influences numerical properties and mean square error were compared with SLS algorithm, and the proposed algorithm is implemented using IMS T-805 parallel processing computer for real time application.

• Journal of the Korean Society for Railway
• /
• v.17 no.3
• /
• pp.171-177
• /
• 2014

PWM converter trains exhibit excellent load characteristics in comparison with conventional phase-controlled trains with low power factors, as they can be operated at power factors which are close to unity by means of a voltage vector control method. However, in the case of a high track density or extended feeding, significant line losses and voltage drops can occur. Instead of operating these trains at a fixed unity power factor, this paper suggests a continuous optimal power factor control scheme for each train in an effort to minimize line losses and improve voltage drops according to varying load conditions. The proposed method utilizes the steepest descent algorithm targeting each car in the same feeding section to establish the optimized reactive power compensation levels that can minimize the reactive power loss of the feeder. The results from a simulation of a sample system show that voltage drops can be improved and line losses decreased.

• Journal of Advanced Navigation Technology
• /
• v.11 no.4
• /
• pp.359-370
• /
• 2007

Lane tracking and obstacle avoidance are considered two of the key technologies on an unmanned ground vehicle system. In this paper, we propose a method of lane tracking and obstacle avoidance, which can be expressed as vehicle control, modeling, and sensor experiments. First, obstacle avoidance consists of two parts: a longitudinal control system for acceleration and deceleration and a lateral control system for steering control. Each system is used for unmanned ground vehicle control, which notes the vehicle's location, recognizes obstacles surrounding it, and makes a decision how fast to proceed according to circumstances. During the operation, the control strategy of the vehicle can detect obstacle and perform obstacle avoidance on the road, which involves vehicle velocity. Second, we explain a method of lane tracking by means of a vision system, which consists of two parts: First, vehicle control is included in the road model through lateral and longitudinal control. Second, the image processing method deals with the lane tracking method, the image processing algorithm, and the filtering method. Finally, in this paper, we propose a method for vehicle control, modeling, lane tracking, and obstacle avoidance, which are confirmed through vehicles tests.

• Journal of Digital Contents Society
• /
• v.14 no.4
• /
• pp.419-428
• /
• 2013

Real-time accessibility and agility are required in u-commerce under ubiquitous computing environment. Most of the existing recommendation techniques adopt the method of evaluation based on personal profile, which has been identified with difficulties in accurately analyzing the customers' level of interest and tendencies, as well as the problems of cost, consequently leaving customers unsatisfied. Researches have been conducted to improve the accuracy of information such as the level of interest and tendencies of the customers. However, the problem lies not in the preconstructed database, but in generating new and diverse profiles that are used for the evaluation of the existing data. Also it is difficult to use the unique recommendation method with hierarchy of each customer who has various characteristics in the existing recommendation techniques. Accordingly, this dissertation used the implicit method without onerous question and answer to the users based on the data from purchasing, unlike the other evaluation techniques. We applied FRAT technique which can analyze the tendency of the various personalization and the exact customer.

• Journal of Digital Convergence
• /
• v.16 no.9
• /
• pp.405-412
• /
• 2018

When a film company decides whether to invest or not in a scenario is the appropriate time to predict box office success. In response to market demands, AI based scenario analysis service has been launched, yet the algorithm is by no means perfect. The purpose of this study is to present a prediction model of movie scenario's box office hit based on human brain processing mechanism. In order to derive patterns of visual, auditory, and cognitive stimuli on the time spectrum of box office animation hit, this study applied Weber's law and brain mechanism. The results are as follow. First, the frequency of brain stimulation in the biggest box office movies was 1.79 times greater than that in the failure movies. Second, in the box office success, the cognitive stimuli codes are spread evenly, whereas in the failure, concentrated among few intervals. Third, in the box office success movie, cognitive stimuli which have big cognition load appeared alone, whereas visual and auditory stimuli which have little cognitive load appeared simultaneously.