• Journal of the Korean Society for information Management
• /
• v.23 no.2
• /
• pp.167-183
• /
• 2006

This paper describes a metadata extraction technique based on natural language processing (NLP) which extracts personalized information from email communications between financial analysts and their clients. Personalized means connecting users with content in a personally meaningful way to create, grow, and retain online relationships. Personalization often results in the creation of user profiles that store individuals' preferences regarding goods or services offered by various e-commerce merchants. We developed an automatic metadata extraction system designed to process textual data such as emails, discussion group postings, or chat group transcriptions. The focus of this paper is the recognition of emotional contents such as mood and urgency, which are embedded in the business communications, as metadata.

• Journal of KIISE
• /
• v.41 no.9
• /
• pp.633-641
• /
• 2014

This paper proposes algorithms to detect jump motion and automatically take a picture when the jump reaches its top. Based on the algorithms, we build jump-shot system by using accelerometer-equipped smart phones. Since the jump motion may vary depending on one's physical condition, gender, and age, it is critical to figure out common features which are independent from such differences. Also it is obvious that the detection algorithm needs to work in real-time because of the short duration of the jump. We propose two different algorithms considering these requirements and develop the system as a smart phone application. Through a series of experiments, we show that the system is able to successfully detect the jump motion and take a picture when it reaches the top.

• Journal of Multimedia Information System
• /
• v.6 no.4
• /
• pp.209-216
• /
• 2019

Over the past decade, researchers were able to solve complex medical problems as well as acquire deeper understanding of entire issue due to the availability of machine learning techniques, particularly predictive algorithms and automatic recognition of patterns in medical imaging. In this study, a technique called transfer learning has been utilized to classify Magnetic Resonance (MR) images by a pre-trained Convolutional Neural Network (CNN). Rather than training an entire model from scratch, transfer learning approach uses the CNN model by fine-tuning them, to classify MR images into Alzheimer's disease (AD), mild cognitive impairment (MCI) and normal control (NC). The performance of this method has been evaluated over Alzheimer's Disease Neuroimaging (ADNI) dataset by changing the learning rate of the model. Moreover, in this study, in order to demonstrate the transfer learning approach we utilize different pre-trained deep learning models such as GoogLeNet, VGG-16, AlexNet and ResNet-18, and compare their efficiency to classify AD. The overall classification accuracy resulted by GoogLeNet for training and testing was 99.84% and 98.25% respectively, which was exceptionally more than other models training and testing accuracies.

• Journal of Korea Technical Association of The Pulp and Paper Industry
• /
• v.36 no.1
• /
• pp.1-8
• /
• 2004

One of the most frequently used method for measurement of the degree of sizing (viz., hydrophobicity) is the Stockigt test. However, the Stockigt test was influenced by various factors such as dropping height, dropping amount, dropping speed and viewing angle. The resultant data of the sizing degree on the same specimen also varied according to different testers. Thus, the Stockigt test should be modified to be regarded as a highly reliable and reproducible standard method. For modifying the Stockigt test, it was required to quantify red coloration by reaction between 1％ ferric chloride and 2％ ammonium thiocyante during Stockigt testing. The cameras capturing the serial images during the red coloration process were the CMOS (Complementary Metal Oxide Semiconductor)-type and CCD (Charge Coupled Device)-type cameras. For measurement based on KS M 7025, the CCD-type camera must be used due to its high resolution, and on the other hand, for measurement based on Tappi Useful Method 429, the CMOS-type camera may be used owing to its low resolution. It was needed to covert the RGB values of a droplet image into HSV(Hue, Saturation, and Value) values because the human eyes are much closer to HSV than RGB. Among HSV values, the Hue value was accepted as the most reliable index consistent with the red coloration process by excluding the surrounding conditions such as light, tester's movement etc.

• Journal of Institute of Control, Robotics and Systems
• /
• v.17 no.8
• /
• pp.747-752
• /
• 2011

HMMs (Hidden Markov Models) are widely used for biological signal, such as EEG (electroencephalogram) sequence, analysis because of their ability to incorporate sequential information in their structure. A recent trends of research are going after the biological interpretable HMMs, and we need to control the complexity of the HMM so that it has good generalization performance. So, an automatic means of optimizing the structure of HMMs would be highly desirable. In this paper, we described a procedure of classification of motor imagery EEG signals using HMM. The motor imagery related EEG signals recorded from subjects performing left, right hand and foots motor imagery. And the proposed a method that was focus on the validation of the HSA (Harmony Search Algorithm) based optimization for HMM. Harmony search algorithm is sufficiently adaptable to allow incorporation of other techniques. A HMM training strategy using HSA is proposed, and it is tested on finding optimized structure for the pattern recognition of EEG sequence. The proposed HSA-HMM can performs global searching without initial parameter setting, local optima, and solution divergence.

• Journal of the Korea Society of Computer and Information
• /
• v.3 no.3
• /
• pp.73-81
• /
• 1998

In this paper suggest for methods disease region feature extraction of medical image using wavelet. In the preprocessing, the shape informations of medical image are selected by performing the discrete wavelet transform(DWT) with four level coefficient matrix. In this approach, based on the characteristics of the coefficient matrix, 96 feature parameters are calculated as follows: Firstly. obtaining 32 feature parameters which have the characteristics of low frequency from the parameters according to the horizontal high frequency are calculated from the coefficient matrix of horizontal high frequency. In the third place, 16 vertical feature parameters are also calculated using the same kind of procedure with respect to the vertical high frequency. Finally, 32 feature parameters of diagonal high frequency are obtained from the coefficient matrix of diagonal high frequency. Consequently, 96 feature aprameters extracted. Using suggest algorithm in this paper will, implamentation can automatic recognition system, increasing efficiency of picture achieve communication system.

• IEIE Transactions on Smart Processing and Computing
• /
• v.6 no.1
• /
• pp.21-26
• /
• 2017

In this paper, we suggest an automated sleep scoring method using machine learning algorithms on accelerometer data from a wristband device. For an experiment, 36 subjects slept for about eight hours while polysomnography (PSG) data and accelerometer data were simultaneously recorded. After the experiments, the recorded signals from the subjects were preprocessed, and significant features for sleep stages were extracted. The extracted features were classified into each sleep stage using five machine learning algorithms. For validation of our approach, the obtained results were compared with PSG scoring results evaluated by sleep clinicians. Both accuracy and specificity yielded over 90 percent, and sensitivity was between 50 and 80 percent. In order to investigate the relevance between features and PSG scoring results, information gains were calculated. As a result, the features that had the lowest and highest information gain were skewness and band energy, respectively. In conclusion, the sleep stages were classified using the top 10 significant features with high information gain.

• Journal of IKEEE
• /
• v.6 no.2 s.11
• /
• pp.169-177
• /
• 2002

In this paper, we introduce a new technology to extract the unique features from an iris image, which uses scale-space filtering. Resulting iris code can be used to develop a system for rapid and automatic identification of persons, with high reliability and confidence levels. First, an iris part is separated from the whole image. Then the radius and center of the iris are obtained. Once the regions that have a high possibility of being noise are discriminated, the features presented in the highly detailed pattern is then extracted from the iris image. Scale-space filtering technique is applied for feature extraction.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.7 no.3
• /
• pp.537-543
• /
• 2012

Smart home System is shirt-sleeve, the automatic control systems, computer network system and network communication technology in the integration of network intelligent home control system. Intelligent household will let users have a more convenient means to management of domestic equipment, for example, through the house, wireless remote control, touch screen phone and Internet or speech recognition control household devices, more can perform scene operation, make more equipment form linkage. In this paper, we propose the intelligent household various kinds of equipment within each other can communication, do not need to user command according to different state interactive operation, thus to bring the greatest degree of user efficient and convenient, comfortable and safe.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.2
• /
• pp.407-412
• /
• 2009

Recently, in Weld Processing field, unmanned and automatic system construction has experienced the rapid growth, and diverse signal processing has been employed in order to translate the exact weld pattern. In this paper, We will suggest the effective neural network which can decide the weld quality in arc weld and monitoring system in real time. In addition, We will present the pre-processing for selecting the study data, and the method to evaluate the wave of weld more precisely and accurately through known Neural Network.