• The Journal of the Acoustical Society of Korea
• /
• v.41 no.2
• /
• pp.199-209
• /
• 2022

Typical anomaly detection algorithms are trained by using prior data. Thus the batch learning based algorithms cause inevitable performance degradation when characteristics of newly incoming normal data change over time. We propose an online anomaly detection algorithm which can consider the gradual characteristic changes of incoming normal data. The proposed algorithm based on one-class classification model includes both offline and online learning procedures. In offline learning procedure, the algorithm learns the prior data to be close to centroid of the latent space and then updates the centroid of the latent space incrementally by new incoming data. In the online learning, the algorithm continues learning by using the updated centroid. Through experiments using public underwater acoustic data, the proposed online anomaly detection algorithm takes only approximately 2 % additional learning time for the incremental centroid update and learning. Nevertheless, the proposed algorithm shows 19.10 % improvement in Area Under the receiver operating characteristic Curve (AUC) performance compared to the offline learning model when new incoming normal data comes.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.1
• /
• pp.13-19
• /
• 2019

The accuracy of machine learning is greatly affected by amount of learning data and quality of data. Collecting existing Web-based learning data has danger that data unrelated to actual learning can be collected, and it is impossible to secure data transparency. In this paper, we propose a method for collecting data directly in parallel by blocks in a block - chain structure, and comparing the data collected by each block with data in other blocks to select only good data. In the proposed system, each block shares data with each other through a chain of blocks, utilizes the All-reduce structure of Parallel-SGD to select only good quality data through comparison with other block data to construct a learning data set. Also, in order to verify the performance of the proposed architecture, we verify that the original image is only good data among the modulated images using the existing benchmark data set.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.38-40
• /
• 2021

Medical domain has a massive number of data records without the response value. Self-supervised learning is a suitable method for medical data since it learns pretext-task and supervision, which the model can understand the semantic representation of data without response values. However, since self-supervised learning performance depends on the expression learned by the pretext-task, it is necessary to define an appropriate Pretext-task with data feature consideration. In this paper, to actively exploit the unlabeled medical data into artificial intelligence research, experimentally find pretext-tasks that suitable for the medical data and analyze the result. We use the x-ray image dataset which is effectively utilizable for the medical domain.

• Journal of the Korean Data and Information Science Society
• /
• v.15 no.4
• /
• pp.707-716
• /
• 2004

Recently, many areas of application such as statistics and industrial engineering are interested in the effective education of databases. In this article we design and implement a database learning system based on learner management techniques. The system supports a personalized/ team-centered learning environment, monitoring the learning attitude of learners, and a method for the assessment.

• Proceedings of the Korean Society for Bioinformatics Conference
• /
• 2000.11a
• /
• pp.61-68
• /
• 2000

Now that the complete genomes of numerous organisms have been ascertained, key problems in molecular biology include determining the functions of the genes in each organism, the relationships that exist among these genes, and the regulatory mechanisms that control their operation. These problems can be partially addressed by using machine learning methods to induce predictive models from available data. My group is applying and developing machine learning methods for several tasks that involve characterizing gene regulation. In one project, for example, we are using machine learning methods to identify transcriptional control elements such as promoters, terminators and operons. In another project, we are using learning methods to identify and characterize sets of genes that are affected by tumor promoters in mammals. Our approach to these tasks involves learning multiple models for inter-related tasks, and applying learning algorithms to rich and diverse data sources including sequence data, microarray data, and text from the scientific literature.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.11
• /
• pp.1528-1533
• /
• 2020

Recently, indoor location recognition technology using Wi-Fi fingerprints has been applied and operated in various industrial fields and public services. Along with the interest in machine learning technology, location recognition technology based on machine learning using wireless signal data around a terminal is rapidly developing. At this time, in the process of collecting radio signal data required for machine learning, the accuracy of location recognition is lowered due to distorted or unsuitable data for learning. In addition, when location recognition is performed based on data collected at a specific location, a problem occurs in location recognition at surrounding locations that are not included in the learning. In this paper, we propose a learning data preprocessing technique to obtain an improved position recognition result through the preprocessing of the collected learning data.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.2
• /
• pp.225-230
• /
• 2020

Machine learning is an algorithm which learns a computer based on the data so that the computer can identify the trend of the data and predict the output of new input data. Machine learning can be classified into supervised learning, unsupervised learning, and reinforcement learning. Supervised learning is a way of learning a machine with given label of data. In other words, a method of inferring a function of the system through a pair of data and a label is used to predict a result using a function inferred about new input data. If the predicted value is continuous, regression analysis is used. If the predicted value is discrete, it is used as a classification. A result of analysis, no. 8 (5, 3.4, setosa), 27 (5, 3.4, setosa), 41 (5, 3.5, setosa), 44 (5, 3.5, setosa) and 40 (5.1, 3.4, setosa) in Table 3 were classified as the most similar Iris flower. Therefore, theoretical practical are suggested.

• Journal of the Korean Institute of Gas
• /
• v.27 no.2
• /
• pp.49-56
• /
• 2023

As AI (Artificial Intelligence)-related technologies are highly developed due to the 4th industrial revolution, cases of applying AI in various fields are increasing. The main reason is that there are practical limits to direct processing and analysis of exponentially increasing data as information and communication technology develops, and the risk of human error can be reduced by applying new technologies. In this study, after collecting the data received from the 'remote potential measurement terminal (T/B, Test Box)' and the output of the 'remote rectifier' at that time, AI was trained. AI learning data was obtained through data augmentation through regression analysis of the initially collected data, and the learning model applied the value-based Q-Learning model among deep reinforcement learning (DRL) algorithms. did The AI that has completed data learning is put into the actual city gas supply area, and based on the received remote T/B data, it is verified that the AI responds appropriately, and through this, AI can be used as a suitable means for electricity management in the future. want to verify.

• Journal of Information Technology Applications and Management
• /
• v.17 no.2
• /
• pp.71-90
• /
• 2010

Electronic learning(or e-learning) has created hype for companies, universities, and other educational institutions. It has led to the phenomenal growth in the use of web-based learning and experimentation with multimedia, video conferencing, and internet-based technologies. Many researchers are interested in the factors that affect to the performance of e-learning or e-learning services. In this sense, this study is aimed at proposing e-learning system reuse prediction models in which e-learner intention to reuse influence factors(i.e., system accessibility, system stability, information clarity, information validity, self-regulated efficacy, computer self-efficacy, perceived usefulness, perceived ease of use, flow, and parental expectation) affect e-learner intention to reuse positively. A web survey was conducted for the full members of the e-learning education institute A in Seoul, Republic of Korea, an exclusive e-learning company that provides real time video lectures via the desktop conferencing system. The web survey was conducted for 20 days from November 5, 2009, through the e-learning web site of the company A. In this study, three data mining techniques were used : the multivariate discriminant analysis, CART, and C5.0 algorithm. This study was conducted to provide the e-learning service providers, e-learning operators, and contents developers with marketing and management strategies for improving the e-learning service companies, based on the data mining analysis results.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.10a
• /
• pp.645-646
• /
• 2018

Recently, the concept of machine learning has been introduced as a decision making method through data processing. Machine learning uses the results of running based on existing data as a means of decision making. The data generated by the development of technology is vast. This data is called big data. It is important to extract the necessary data from these data. In this paper, we propose a method for extracting related data for constructing an ontology through machine learning. The results of machine learning can be given a relationship from a semantic perspective. it can be added to the ontology to support relationships depending on the needs of the application.