• Proceedings of the KSRS Conference
• /
• 1999.11a
• /
• pp.429-432
• /
• 1999

Vegetation cover classification is examined based on a time series NOAA/AVHRR data. Time series data analysis methods including Fourier transform, Auto-Regressive (AR) model and temporal signature similarity matching are developed to extract phenological features of vegetation from a time series NDVI data from NOAA/AVHRR and to classify vegetation types. In the Fourier transform method, typical three spectral components expressing the phenological features of vegetation are selected for classification, and also in the AR model method AR coefficients are selected. In the temporal signature similarity matching method a new index evaluating the similarity of temporal pattern of the NDVI is introduced for classification.

• Journal of information and communication convergence engineering
• /
• v.16 no.3
• /
• pp.173-178
• /
• 2018

Accurate classification of cloud images is a challenging task. Almost all the existing methods rely on hand-crafted feature extraction. Their limitation is low discriminative power. In the recent years, deep learning with convolution neural networks (CNNs), which can auto extract features, has achieved promising results in many computer vision and image understanding fields. However, deep learning approaches usually need large datasets. This paper proposes a deep learning approach for classification of cloud image patches on small datasets. First, we design a suitable deep learning model for small datasets using a CNN, and then we apply data augmentation and dropout regularization techniques to increase the generalization of the model. The experiments for the proposed approach were performed on SWIMCAT small dataset with k-fold cross-validation. The experimental results demonstrated perfect classification accuracy for most classes on every fold, and confirmed both the high accuracy and the robustness of the proposed model.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2002.05a
• /
• pp.632-638
• /
• 2002

In novelty detection, one attempts to discriminate abnormal patterns from normal ones. Novelty detection is quite difficult since, unlike usual two class classification problems, only normal patterns are available for training. Auto-Associative Multi-Layer Perceptron (AAMLP) has been shown to provide a good performance based upon the property that novel patterns usually have larger auto-associative errors. In this paper, we give a mathematical analysis of 2-layer AAMLP's output characteristics and empirical results of 2-layer and 4-layer AAMLPs. Various activation functions such as linear, saturated linear and sigmoid are compared. The 2-layer AAMLPs cannot identify non-linear boundaries while the 4-layer ones can. When the data distribution is multi-modal, then an ensemble of AAMLPs, each of which is trained with pre-clustered data is required. This paper contributes to understanding of AAMLP networks and leads to practical recommendations regarding its use.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2000.11a
• /
• pp.409-412
• /
• 2000

A high performance EEG signal measurement system is fabricated. It consists of high precision pre-amplifier and auto identification bandwidth unit. High precision pre-amplifier is composed of signal generator, signal amplifier with a impedance converter, body driver and isolation amplifier. The pre-amplifier is designed for low noise characteristics, high CMRR, high input impedance, high IMRR and safety, Auto identification bandwidth unit is composed of AD-converter and PIC micro-controller for real time processing EEG signal. The performance of EEG signal measurement system has been shown the classified bandwidth through the clinical demonstrations.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.11
• /
• pp.4246-4267
• /
• 2020

As the network goes deep into all aspects of people's lives, the number and the complexity of network traffic is increasing, and traffic classification becomes more and more important. How to classify them effectively is an important prerequisite for network management and planning, and ensuring network security. With the continuous development of deep learning, more and more traffic classification begins to use it as the main method, which achieves better results than traditional classification methods. In this paper, we provide a comprehensive review of network traffic classification based on deep learning. Firstly, we introduce the research background and progress of network traffic classification. Then, we summarize and compare traffic classification based on deep learning such as stack autoencoder, one-dimensional convolution neural network, two-dimensional convolution neural network, three-dimensional convolution neural network, long short-term memory network and Deep Belief Networks. In addition, we compare traffic classification based on deep learning with other methods such as based on port number, deep packets detection and machine learning. Finally, the future research directions of network traffic classification based on deep learning are prospected.

• Journal of Korean Library and Information Science Society
• /
• v.19
• /
• pp.35-57
• /
• 1992

This study is an attempt to provide some helpful data for the design and the implementation of the expert system for the book-classification based on the analysis of various cases of the classification-expert system models. Following the introduction, the concepts and some features of an expert system were overviewed in the second chapter, on the basis of which the following concrete cases were introduced and analyzed in the third chapter : (1) ACN System for NC, (2) Expert System for NDC, (3) Expert System for UDC, (4) Herba Medica System, (5) Expert System for IPC, (6) Stratcyclode Project, (7) Expert System for Classification of INIS Database, (8) AutoBC System, and etc. In the conclusion, for the development of the classification-expert system, it was turned out that constructing a new system by using an AI language such as Prolog or LISP is more desirable than employing any one of expert system shells. Together it is necessary for the following requirements to be met : (1) The subject concept of a document elicited should be accurate. (2) Not only a domain knowledge but also the knowledge covering all the subjects should be represented in the knowledge-bases. (3) The knowledge-bases should be organized in such a way that the characteristics of the knowledge about classification should be well defined. (4) rule-base consisting of accurate rules about classification should be made. (5) It should be possible for classification code wanted to be generated immediately.

• International Journal of Automotive Technology
• /
• v.7 no.2
• /
• pp.195-199
• /
• 2006

According to the United States FMVSS 208, every passenger car on the market after September of 2006 must install a safety system, which can deploy the airbag with different intensity or suppression based on the passenger type, to reduce infant and child injuries from airbag deployments. The Weight Classification System, which has been developed by Hyundai Autonet, is a system that classifies the person occupying the passenger seat. To overcome sensing problems due to the weight sensors small voltage, the Distributed Systems Interface is adopted.

• Journal of Internet Computing and Services
• /
• v.20 no.1
• /
• pp.57-65
• /
• 2019

In the case of Domeggook B2B online shopping malls, it has a market share of over 70% with more than 2 million members and 800,000 items are sold per one day. However, since the same or similar items are stored and registered in different catalog entries, it is difficult for the buyer to search for items, and problems are also encountered in managing B2B large shopping malls. Therefore, in this study, we developed a catalog entry auto classification and recommendation system for products by using semi-supervised machine learning method based on previous huge shopping mall purchase information. Specifically, when the seller enters the item registration information in the form of natural language, KoNLPy morphological analysis process is performed, and the Naïve Bayes classification method is applied to implement a system that automatically recommends the most suitable catalog information for the article. As a result, it was possible to improve both the search speed and total sales of shopping mall by building accuracy in catalog entry efficiently.

• Journal of Advanced Navigation Technology
• /
• v.26 no.6
• /
• pp.528-535
• /
• 2022

Although the domestic aviation industry has made rapid progress with the development of aircraft manufacturing and transportation technologies, aviation safety accidents continue to occur. The supervisory agency classifies hazards and risks based on risk-based aviation safety data, identifies safety trends for each air transportation operator, and conducts pre-inspections to prevent event and accidents. However, the human classification of data described in natural language format results in different results depending on knowledge, experience, and propensity, and it takes a considerable amount of time to understand and classify the meaning of the content. Therefore, in this journal, the fine-tuned KoBERT model was machine-learned over 5,000 data to predict the classification value of new data, showing 79.2% accuracy. In addition, some of the same result prediction and failed data for similar events were errors caused by human.

• Journal of Internet Computing and Services
• /
• v.22 no.3
• /
• pp.9-16
• /
• 2021

This study aims to develop a human activity recognition (HAR) system as a Deep-Learning (DL) classification model, distinguishing various human activities. We solely rely on the signals from a wristband accelerometer worn by a person for the user's convenience. 3-axis sequential acceleration signal data are gathered within a predefined time-window-slice, and they are used as input to the classification system. We are particularly interested in developing a Deep-Learning model that can outperform conventional machine learning classification performance. A total of 13 activities based on the laboratory experiments' data are used for the initial performance comparison. We have improved classification performance using the Convolutional Neural Network (CNN) combined with an auto-encoder feature reduction and parameter tuning. With various publically available HAR datasets, we could also achieve significant improvement in HAR classification. Our CNN model is also compared against Recurrent-Neural-Network(RNN) with Long Short-Term Memory(LSTM) to demonstrate its superiority. Noticeably, our model could distinguish both general activities and near-identical activities such as sitting down on the chair and floor, with almost perfect classification accuracy.