• Journal of the Korean Society for Precision Engineering
• /
• v.28 no.1
• /
• pp.56-62
• /
• 2011

Terrain recognition ability is crucial to the performance of legged robots in an outdoor environment. For instance, a robot will not easily walk and it will tumble or deviate from its path if there is no information on whether the walking surface is flat, rugged, tough, and slippery. In this study, the ground surface recognition ability of robots is discussed, and to enable walking robots to recognize the surface state and changes, a central moment method was used. The values of the sensor signals (load cell) of robots while walking were detected in the supported section and were analyzed according to signal variance, skewness, and kurtosis. Based on the results of such analysis, the surface state was detected and classified.

• Journal of the Korean Society of Industry Convergence
• /
• v.25 no.2_1
• /
• pp.169-176
• /
• 2022

Prognostics and health management (PHM) is recently converging throughout the industry, one of the trending issue is to detect abnormal conditions at decanter centrifuge during water treatment facilities. Wastewater treatment operation produces corrosive gas which results failures on attached sensors. This scenario causes frequent sensor replacement and requires highly qualified manager's visual inspection while replacing important parts such as bearings and screws. In this paper, we propose anomaly detection by measuring the vibration of the decanter centrifuge based on the video camera images. Measuring the vibration of the screw decanter by applying the optical flow technique, the amount of movement change of the corresponding pixel is measured and fed into the LST M model. As a result, it is possible to detect the normal/warning/dangerous state based on LSTM classification. In the future work, we aim to gather more abnormal data in order to increase the further accuracy so that it can be utilized in the field of industry.

• The Journal of Internal Korean Medicine
• /
• v.28 no.1
• /
• pp.106-114
• /
• 2007

Background : Mahuang (Ephedrae Herba, Ephedra sinica $S_{TAPE}$) has been widely used to treat respiratory disease in Asian over the past thousand years. The main ingredient of Mahuang is ephedrine, whose affects on the autonomic nervous system induce some adverse effects like vasoconstriction, hypertension, tachycardia, miosis, insomnia, dizziness, headache, etc. Although there were lots of reports about adverse effects of Mahuang, there were no clinical studies which evaluated the adverse effects of Mahuang on the autonomic nervous system by objective numerical value in the past decade. Objectives : The purpose of this report was to provide an objective assessment of state-trait anxiety that is caused by Mahuang, and to identify anxiety of Mahuang according to different Sasang constitution classifications. Methods : The study design was a double-blind randomized placebo-controlled trial. The subjects of this study were 79 adults aged between 20 to 40 who agreed to participate. Because 8 adults dropped out, a total of 71 subjects entered the study. They were allocated through randomization to a Mahuang group (N=50) and placebo group (N=21). Each group took three opaque capsules (every opaque capsule containing 2g of Mahuang or none) twice a day. To compare the state and trait anxiety before and after taking Mahuang, we checked the anxiety by using STAI-KYZ. Results : The following results were obtained. Short-term administration of Mahuang significantly increased state-anxiety, but in the placebo group, there were no significant changes in state-anxiety. In the Mahuang group except females, there was more significant increase in state-anxiety of Soeumin than Soyangin and Taeumin in the 2nd measurement. Conclusion : It is suggested that the ingestion of Mahuang can increase sympathetic activity and induce anxiety. There was a significant difference among Sasang constitution classification. Especially, the response is stronger in Soeumin than other constitutions. If we use Mahuang according to the Sasang constitution classification in clinic, we could not only minimize the anxiety but maximize the potential curative value.

• Journal of Institute of Control, Robotics and Systems
• /
• v.19 no.1
• /
• pp.15-26
• /
• 2013

This paper proposes a classification method of parallel, vertical parking states and pillars for parking assist system using ultrasonic sensors. Since, in general parking space detection module, the compressed amplitude of ultrasonic data are received, the analysis of them is difficult. To solve these problems, in preprocessing state, symmetric transform and noise removal are performed. In feature extraction process, four features, standard deviation of distance, reconstructed peak, standard deviation of reconstructed signal and sum of width, are proposed. Gaussian fitting model is used to reconstruct saturated peak signal and discriminability of each feature is measured. To find the best combination among these features, multi-class SVM and subset generator are used for more accurate and robust classification. The proposed method shows 92 % classification rate and proves the applicability to parking space detection modules.

• Journal of Information Management
• /
• v.36 no.4
• /
• pp.51-69
• /
• 2005

High-speed classification method becomes an important research issue in text categorization systems. A fast text categorization technique, named feature value voting, is introduced recently on the text categorization problems. But the classification accuracy of this technique is not good as its classification speed. We present a novel approach for feature selection, named document-side feature selection, and apply it to feature value voting method. In this approach, there is no feature selection process in learning phase; but realtime feature selection is executed in classification phase. Our results show that feature value voting with document-side feature selection can allow fast and accurate text classification system, which seems to be competitive in classification performance with Support Vector Machines, the state-of-the-art text categorization algorithms.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.24 no.4
• /
• pp.23-51
• /
• 2013

The purpose of the study is to examine the potentialities and limits of Business Reference Model (BRM) as records classification schemes in Korean central state institutions. The analysis is based on the data collected through focus group interviews of three times, in which six records professionals from central government agencies participate. This paper begins with inquiring the framework of records classification based BRM, required by Public Records Management Act. It explores the types of benefit of BRM application to government records classification. Based on the collected data from the interviews, it investigates how records are aggregated, and how transaction level (Danwi-Gwaje) of BRM is applied in the course of records aggregation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.1
• /
• pp.364-380
• /
• 2016

The most popular approach in object classification is based on the bag of visual-words model, which has several fundamental problems that restricting the performance of this method, such as low time efficiency, the synonym and polysemy of visual words, and the lack of spatial information between visual words. In view of this, an object classification based on weakly supervised E2LSH and saliency map weighting is proposed. Firstly, E2LSH (Exact Euclidean Locality Sensitive Hashing) is employed to generate a group of weakly randomized visual dictionary by clustering SIFT features of the training dataset, and the selecting process of hash functions is effectively supervised inspired by the random forest ideas to reduce the randomcity of E2LSH. Secondly, graph-based visual saliency (GBVS) algorithm is applied to detect the saliency map of different images and weight the visual words according to the saliency prior. Finally, saliency map weighted visual language model is carried out to accomplish object classification. Experimental results datasets of Pascal 2007 and Caltech-256 indicate that the distinguishability of objects is effectively improved and our method is superior to the state-of-the-art object classification methods.

• Journal of Information Processing Systems
• /
• v.16 no.3
• /
• pp.663-676
• /
• 2020

Plant leaf classification is a significant application of image processing techniques in modern agriculture. In this paper, a multi-granular angle description method is proposed for plant leaf classification and retrieval. The proposed method can describe leaf information from coarse to fine using multi-granular angle features. In the proposed method, each leaf contour is partitioned first with equal arc length under different granularities. And then three kinds of angle features are derived under each granular partition of leaf contour: angle value, angle histogram, and angular ternary pattern. These multi-granular angle features can capture both local and globe information of the leaf contour, and make a comprehensive description. In leaf matching stage, the simple city block metric is used to compute the dissimilarity of each pair of leaf under different granularities. And the matching scores at different granularities are fused based on quotient space theory to obtain the final leaf similarity measurement. Plant leaf classification and retrieval experiments are conducted on two challenging leaf image databases: Swedish leaf database and Flavia leaf database. The experimental results and the comparison with state-of-the-art methods indicate that proposed method has promising classification and retrieval performance.

• Journal of Intelligence and Information Systems
• /
• v.28 no.3
• /
• pp.45-55
• /
• 2022

Recently, large-scale language models (LPLM) have been shown state-of-the-art performances in various tasks of natural language processing including intent classification. However, fine-tuning LPLM requires much computational cost for training and inference which is not appropriate for dialog system. In this paper, we propose compressed intent classification model for multi-agent in low-resource like CPU. Our method consists of two stages. First, we trained sentence encoder from LPLM then compressed it through knowledge distillation. Second, we trained agent-specific adapter for intent classification. The results of three intent classification datasets show that our method achieved 98% of the accuracy of LPLM with only 21% size of it.

• International Journal of Computer Science & Network Security
• /
• v.22 no.9
• /
• pp.403-413
• /
• 2022

Classification and analysis are improved factors for the realtime automation system. In the field of agriculture, the cultivation of different paddy crop depends on the atmosphere and the soil nature. We need to analyze the moisture level in the area to predict the type of paddy that can be cultivated. For this process, Ensemble Modulation Pattern system and Block Probability Neural Network based classification models are used to analyze the moisture and temperature of land area. The dataset consists of the collections of moisture and temperature at various data samples for a land. The Ensemble Modulation Pattern based feature analysis method, the extract of the moisture and temperature in various day patterns are analyzed and framed as the pattern for given dataset. Then from that, an improved neural network architecture based on the block probability analysis are used to classify the data pattern to predict the class of paddy crop according to the features of dataset. From that classification result, the measurement of data represents the type of paddy according to the weather condition and other features. This type of classification model assists where to plant the crop and also prevents the damage to crop due to the excess of water or excess of temperature. The result analysis presents the comparison result of proposed work with the other state-of-art methods of data classification.