• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.9
• /
• pp.4317-4335
• /
• 2018

Semi-supervised multi-view latent space learning is gaining considerable popularity recently in many machine learning applications due to the high cost and difficulty to obtain the large amount of label information of data. Although some semi-supervised multi-view latent space learning methods have been presented, there is still much space for improvement: 1) How to learn latent discriminant intact feature representations by employing data of multiple views; 2) How to exploit the manifold structure of both labeled and unlabeled point in the learned latent intact space effectively. To address the above issues, we propose an approach called semi-supervised multi-view manifold discriminant intact space learning ($SM^2DIS$) for image classification in this paper. $SM^2DIS$ aims to seek a manifold discriminant intact space for data of different views by making use of both the discriminant information of labeled data and the manifold structure of both labeled and unlabeled data. Experimental results on MNIST, COIL-20, Multi-PIE, and Caltech-101 databases demonstrate the effectiveness and robustness of our proposed approach.

• Journal of the Ergonomics Society of Korea
• /
• v.36 no.3
• /
• pp.197-211
• /
• 2017

Objective: We propose to apply color information to facilitate finding books in the library. Background: Currently, books are classified in the basis of a decimal classification system and a call number in the library. Users find a book using the call number. However, this classification system causes various difficulties. Method: In a process analysis and survey study, we identify what the real problem is and where the problem is occurred. To solve the real problems, we derived a new search method using color information. We conducted a comparative experiment with 48 participants to see whether the new method can show higher performance. Results: The new method using color information showed faster time and higher subjective rating scores than current call number method. Also, the new method showed faster time regardless of the skill level while the call number method showed time differences in terms of the skill level. Conclusion: The effectiveness of the proposed method was verified by experiments. Users will be able to find the desired book without difficulty. This method can improve the quality of service and satisfaction of library use. Application: Our book search method can be applied as a book search tool in a real public library. We hope that the method can provide higher satisfaction to users.

• International journal of advanced smart convergence
• /
• v.8 no.3
• /
• pp.115-122
• /
• 2019

Recent and ongoing discoveries of mycoviruses with new properties demand the development of an appropriate research infrastructure to analyze their evolution and classification. In particular, the discovery of negative-sense single-stranded mycoviruses is worth noting in genome types in which double-stranded RNA virus and positive-sense single-stranded RNA virus were predominant. In addition, some genomic properties of mycoviruses are more interesting because they have been reported to have similarities with the pathogenic virus family that infects humans and animals. Genetic information on mycoviruses continues to accumulate in public repositories; however, these databases have some difficulty reflecting the latest taxonomic information and obtaining specialized data for mycoviruses. Therefore, in this study, we developed a bioinformatics-based pipeline to efficiently utilize this genetic information. We also designed a schema for data processing and database construction and an algorithm to keep taxonomic information of mycoviruses up to date. The pipeline and database (termed 'mycoVDB') presented in this study are expected to serve as useful foundations for improving the accuracy and efficiency of future research on mycoviruses.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.53 no.4
• /
• pp.293-299
• /
• 2004

This paper is about the extraction of basis function for ECG signal processing. In the first step, it is assumed that ECG signal consists of linearly mixed independent source signals. 12 channel ECG signals, which were sampled at 600sps, were used and the basis function, which can separate and detect source signals - QRS complex, P and T waves, - was found by applying the fast fixed point algorithm, which is one of learning algorithms in independent component analysis(ICA). The possibilities of significant point detection and classification of normal and abnormal ECG, using the basis function, were suggested. Finally, the proposed method showed that it could overcome the difficulty in separating specific frequency in ECG signal processing by wavelet transform. And, it was found that independent component analysis(ICA) could be applied to ECG signal processing for detection of significant points and classification of abnormal beats.

• Industrial Engineering and Management Systems
• /
• v.11 no.2
• /
• pp.134-141
• /
• 2012

It is difficult to find an appropriate ordering policy for a many types of items. One of the reasons for this difficulty is that each item has a different demand trend. We will classify items by shipment trend and then decide the ordering policy for each item category. In this study, we indicate that categorizing items from their statistical characteristics leads to an ordering policy suitable for that category. We analyze the ordering policy and shipment trend and propose a new method for selecting the ordering policy which is based on finding the strongest relation between the classification of the items and the ordering policy. In our numerical experiment, from actual shipment data of about 5,000 items over the past year, we calculated many statistics that represent the trend of each item. Next, we applied the canonical correlation analysis between the evaluations of ordering policies and the various statistics. Furthermore, we applied the cluster analysis on the statistics concerning the performance of ordering policies. Finally, we separate items into several categories and show that the appropriate ordering policies are different for each category.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.10
• /
• pp.3608-3626
• /
• 2021

The detection of bolts is an important task in high-speed train inspection systems, and it is frequently performed to ensure the safety of trains. The difficulty of the vision-based bolt inspection system lies in small sample defect detection, which makes the end-to-end network ineffective. In this paper, the problem is resolved in two stages, which includes the detection network and cascaded classification networks. For small bolt detection, all bolts including defective bolts and normal bolts are put together for conducting annotation training, a new loss function and a new boundingbox selection based on the smallest axis-aligned convex set are proposed. These allow YOLOv3 network to obtain the accurate position and bounding box of the various bolts. The average precision has been greatly improved on PASCAL VOC, MS COCO and actual data set. After that, the Siamese network is employed for estimating the status of the bolts. Using the convolutional Siamese network, we are able to get strong results on few-shot classification. Extensive experiments and comparisons on actual data set show that the system outperforms state-of-the-art algorithms in bolt inspection.

• Journal of Applied Reliability
• /
• v.16 no.2
• /
• pp.134-146
• /
• 2016

Purpose: Many domestic companies have to make out quantitative evaluation table in their proposal when they conduct the software R&D project. However, most of companies have a difficulty to select the evaluation items and criteria, also to derive a quantitative results. Therefore, we propose a method to derive the quantitative evaluation index by utilizing the ISO/IEC 9126-2. Methods: Analyzing ISO/IEC 9126-2, and we classify the quality metrics as high-classification and sub-classification for Web/App software, Embedded software and Installation software. Next, Conduct the metrics selection survey depending on importance and necessity. Then, carry out the case study. Verify the correspondence between evaluation items and criteria from original suggestion of company and from outcome by utilizing the ISO/IEC 9126-2 quality metrics. Results: It is possible to classify into two metrics, one for common software or one another for only special software. Furthermore, there is quality metrics that is more important and more necessary depending upon characteristics of the software. Conclusion: ISO/IEC 9126-2 quality metrics can be used to make an evaluation items and criteria for quantitative evaluation table of software product.

• Proceedings of the IEEK Conference
• /
• summer
• /
• pp.237-243
• /
• 2004

A multichannel smart sound sensor capable to detect and identify sound events in noisy conditions is presented in this paper. Sound information extraction is a complex task and the main difficulty consists is the extraction of high­level information from an one-dimensional signal. The input of smart sound sensor is composed of data collected by 5 microphones and its output data is sent through a network. For a real time working purpose, the sound analysis is divided in three steps: sound event detection for each sound channel, fusion between simultaneously events and sound identification. The event detection module find impulsive signals in the noise and extracts them from the signal flow. Our smart sensor must be capable to identify impulsive signals but also speech presence too, in a noisy environment. The classification module is launched in a parallel task on the channel chosen by data fusion process. It looks to identify the event sound between seven predefined sound classes and uses a Gaussian Mixture Model (GMM) method. Mel Frequency Cepstral Coefficients are used in combination with new ones like zero crossing rate, centroid and roll-off point. This smart sound sensor is a part of a medical telemonitoring project with the aim of detecting serious accidents.

• Journal of Intelligence and Information Systems
• /
• v.7 no.1
• /
• pp.47-61
• /
• 2001

Lazy loaming methods including CBR have relative advantages in comparison with eager loaming methods such as artificial neural networks and decision trees. However, they are very sensitive to irrelevant features. In other words, when there are irrelevant features, larry learning methods have difficulty in comparing cases. Therefore, their performance can be degraded significantly. To overcome this disadvantage, feature weighting methods for lazy loaming methods have been studied. Most of the existing researches, however, were focused on global feature weighting. In this research, we propose a new local feature weighting method, which we shall call CBDFW. CBDFW stores classification performance of randomly generated feature weight vectors. Then, given a new query case, CBDFW retrieves the successful feature weight vectors and designs a feature weight vector fur the query case. In the test on credit evaluation domain, CBDFW showed better classification accuracy when compared to the results of previous researches.

• Journal of Korean Academy of Nursing
• /
• v.23 no.4
• /
• pp.569-584
• /
• 1993

This study was done to verify validity of nursing diagnoses related to difficulty in respiratory function. First, content validity was examined by an expert group considering the etiology and the signs / symptoms of three nursing diagnoses - ineffective airway clearance, ineffective breathing pattern, impaired gas exchange. Second, clinical validity was examined by comparing the frequencies of the etiologies and signs / symptoms of the three nursing diagnoses in clinical case studies with the results of the content validity. This study was a descriptive study. The sample consisted of 23 experts (professors, head nurses and clinical instructors) who had had a variety of experiences using nursing diagnoses in clinical practice, and 102 case reports done by senior student nurses of the college of nursing of Y-university. These reports were part of their clinical practice in the ICU. The instrument used for this study was a checklist for etiologies and signs and symptoms based on the literature, Doenges and Moorhouse (1988), Kim, McFarland, McLane (1991), Lee Won Hee et al. (1987), Kim Cho Ja et at. (1988). The data was collected over four month period from May 1992 to Aug. 1992. Data were analyzed using frequencies done with the SPSS / PC＋ package. The results of this study are summarized as follows : 1. General Characteristics of the Expert Group A bachelor degree was held by 43.5% and a master or doctoral degree by 56.5% of the expert group. The average age of the expert group was 35.3 years. Their average clinical experience was 9.3 years and their average experience in clinical practice was 5.9 years. The general characteristics of the patients showed that there were more women than men, that the age range was from 1 to over 80. Most of their medical diagnoses were diagnoses related to the respiratory. system, circulation or neurologic system, and 50% or more of them had a ventilator with intubation or a tracheostomy. The number of cases for each nursing diagnoses was : · Ineffective airway clearance, 92 cases. · Ineffective breathing pattern, 18 cases. · Impaired gas exchange, 22 cases. 2. The opinion of the expert group as to the classification of the etiology, and signs and symptoms of the three nursing diagnoses was as follows : · In 31.8% of the cases the classification of etiology was clear. · In 22.7%, the classification of signs and symptoms was clear. · In 17.4%, the classification of nursing interventions was clear. 3. In the expert group 80% or mere agreed to ‘dysp-nea’as a common sign and symptom of the three nursing diagnoses. The distinguishing signs and symptoms of (Ineffective airway clearance) were ‘sputum’, ‘cough’, ‘abnormal respiratory sounds : rales’. The distinguishing sings and symptoms of (Ineffective breathing pattern) were ‘tachypnea’, ‘use of accessory muscle of respiration’, ‘orthopnea’ and for (Impaired gas exchange) it was ‘abnormal arterial blood gas’, 4. The distribution of etiology, and signs and symptoms of the three nursing diagnoses was as follows : · There was a high frequency of ‘increased secretion from the bronchus and trachea’ in both the expert group and the case reports as the etiology of ineffective airway clearance. · For the etiologies for ineffective breathing pat-tern, ‘rain’, ‘anxiety’, ‘fear’, ‘obstructions of the tract, ca and bronchus’ had a high ratio in the ex-pert group and ‘decreased expansion of lung’ in the case reports. · For the etiologies for impaired gas exchanges, ‘altered oxygen -carrying capacity of the blood’ and ‘excess accumulation of interstitial fluid in lung’ had a high ratio in the expert group and ‘altered oxygen supply’ in the case reports. · For signs and symptoms for ineffective airway clearance, ‘dyspnea’, ‘altered amount and character of sputum’ were included by 100% of the expert group. ‘Abnormal respiratory. sound(rate, rhonchi)’ were included by a high ratio of the expert group. · For the signs and symptoms for ineffective breathing pattern. ‘dyspnea’, ‘shortness of breath’ were included by 100% of the expert group. In the case reports, ‘dyspnea’ and ‘tachypnea’ were reported as signs and symptoms. · For the sign and symptoms for impaired gas exchange, ‘hypoxia’ and ‘cyanosis’ had a high ratio in the expert group. In the case report, ‘hypercapnia’, ‘hypoxia’ and ‘inability to remove secretions’ were reported as signs and symptoms. In summary, the similarity of the etiologies and signs and symptoms of the three nursing diagnoses related to difficulty in respiratory function makes it difficult to distinguish among them But the clinical validity of three nursing diagnoses was established through this study, and at last one sign and symp-tom was defined for each diagnosis.