• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.4
• /
• pp.97-113
• /
• 2023

Swift and appropriate responses in emergency situations like objects falling on the road can bring convenience to road users and effectively reduces secondary traffic accidents. In Korea, current intelligent transportation system (ITS)-based detection systems for emergency road situations mainly rely on loop detectors and CCTV cameras, which only capture road data within detection range of the equipment. Therefore, a new detection method is needed to identify emergency situations in spatially shaded areas that existing ITS detection systems cannot reach. In this study, we propose a ResNet-based algorithm that detects and classifies emergency situations from vehicle camera footage. We collected front-view driving videos recorded on Korean highways, labeling each video by defining the type of emergency, and training the proposed algorithm with the data.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.23 no.1
• /
• pp.182-196
• /
• 2024

This study introduces driving pattern analysis and change detection methods using smartphone sensors, based on contrastive learning. These methods characterize driving patterns without labeled data, allowing accurate classification with minimal labeling. In addition, they are robust to domain changes, such as different vehicle types. The study also examined the applicability of these methods to smartphones by comparing them with six lightweight deep-learning models. This comparison supported the development of smartphone-based driving pattern analysis and assistance systems, utilizing smartphone sensors and contrastive learning to enhance driving safety and efficiency while reducing the need for extensive labeled data. This research offers a promising avenue for addressing contemporary transportation challenges and advancing intelligent transportation systems.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.1
• /
• pp.77-92
• /
• 2020

When automatic speech recognition (ASR) is provided as a cloud service, it is easy to collect voice and application domain data from users. Harnessing these data will facilitate the provision of more personalized services. In this paper, we demonstrate our transfer learning-based knowledge service that built with the user-generated data collected through our novel system that deliveries personalized ASR service. First, we discuss the motivation, challenges, and prospects of building up such a knowledge-based service-oriented system. Second, we present a Quadruple Transfer Learning (QTL) method that can learn a classification model from a source domain and transfer it to a target domain. Third, we provide an overview architecture of our novel system that collects voice data from mobile users, labels the data via crowdsourcing, utilises these collected user-generated data to train different machine learning models, and delivers the personalised real-time cloud services. Finally, we use the E-Book data collected from our system to train classification models and apply them in the smart TV domain, and the experimental results show that our QTL method is effective in two classification tasks, which confirms that the knowledge transfer provides a value-added service for the upper-layer mobile applications in different domains.

• Korean Journal of Human Ecology
• /
• v.12 no.4
• /
• pp.539-552
• /
• 2003

The purpose of this study was to find out the proper evaluative words and colors according to various fashion images and to classify the fashion images according to certain criteria. 13 books which included the content of the fashion images were selected to draw evaluative words and colors. Evaluative words and colors were found out as follows: classic image-traditional, classical, conservative and brown, wine, dark yellow, modem image-intelligent, rational, westernized and achromatic color, cool colors, elegance image-dignified, graceful, chic and greyish tone, pale tone, romantic image-cute, lovely, girlish, natural image-natural, comfortable, gently and brown, ivory beige, khaki, casual image-energetic, comfortable, active and red, yellow, blue family. The classification of fashion images according to various criteria were as follows. According to sex: feminine-elegance, romantic, pretty and masculine-mannish, dandy, military. According to time: past-conservative, traditional, classical, and present-modern, contemporary, sophisticate. According to formality: formal-formal wear of classic, elegance, mannish, dandy style and informal-natural, casual. According to intelligence, the elite style-modern, elegance, classic, sophisticate and the public style-casual, natural.

• Journal of Intelligence and Information Systems
• /
• v.7 no.1
• /
• pp.149-159
• /
• 2001

There have been lots of researches for providing a personalized service to a customer using one-to-one marketing and collaborative filtering techniques in E-Commerce. However, there are technical difficulties for providing the recommendation of products far users, which often involve high complexity of computation. In this paper, we have presented an integrated method of classification problem solving method and constraint based configuration techniques. This method can reduce a complexity of computation by classifying a solution domain space that has a higher complexity of composition. Thereafter, we have modeled customers constraints and the components of products to configure a complete system by passing it to constraint processing module in Constraint Satisfaction Problems. Constraint-based configuration uses the constraint propagation using the constraints of buyers and the constraints among PC components to configure a proper product for a customer. We have transformed and applied vector space modeling method in the field of information retrieval to consider a customer satisfaction in addition to the CSP. Finally, we have applied our system to test data fur evaluating a customers satisfaction and performance of the proposed system.

• Journal of Intelligence and Information Systems
• /
• v.15 no.3
• /
• pp.1-15
• /
• 2009

In a classification problem, data imbalance occurs when the number of instances in one class greatly outnumbers the number of instances in the other class. Such data sets often cause a default classifier to be built due to skewed boundary and thus the reduction in the classification accuracy of such a classifier. This paper proposes a Geometric Mean-based Boosting (GM-Boost) to resolve the problem of data imbalance. Since GM-Boost introduces the notion of geometric mean, it can perform learning process considering both majority and minority sides, and reinforce the learning on misclassified data. An empirical study with bankruptcy prediction on Korea companies shows that GM-Boost has the higher classification accuracy than previous methods including Under-sampling, Over-Sampling, and AdaBoost, used in imbalanced data and robust learning performance regardless of the degree of data imbalance.

• Journal of Intelligence and Information Systems
• /
• v.16 no.2
• /
• pp.95-108
• /
• 2010

In this paper, we present a hybrid neural network model for dynamic hand gesture recognition. The model consists of two modules, feature extraction module and pattern classification module. We first propose a modified CNN(convolutional Neural Network) a pattern recognition model for the feature extraction module. Then we introduce a weighted fuzzy min-max(WFMM) neural network for the pattern classification module. The data representation proposed in this research is a spatiotemporal template which is based on the motion information of the target object. To minimize the influence caused by the spatial and temporal variation of the feature points, we extend the receptive field of the CNN model to a three-dimensional structure. We discuss the learning capability of the WFMM neural networks in which the weight concept is added to represent the frequency factor in training pattern set. The model can overcome the performance degradation which may be caused by the hyperbox contraction process of conventional FMM neural networks. From the experimental results of human action recognition and dynamic hand gesture recognition for remote-control electric home appliances, the validity of the proposed models is discussed.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.11
• /
• pp.2039-2044
• /
• 2006

Since the bio-information now even exceeds the capability of human brain, the techniques of data mining and artificial intelligent are needed to deal with the information in this field. There are many researches about using DNA microarray technique which can obtain information from thousands of genes at once, for developing new methods of analyzing and predicting of diseases. Discovering the mechanisms of unknown genes by using these new method is expecting to develop the new drugs and new curing methods. In this Paper, We tested accuracy on classification of microarray in Bayesian method to compare normalization method's Performance after dividing data in two class that is a feature abstraction method through a normalization process which reduce or remove noise generating in microarray experiment by various factors. And We represented that it improve classification performance in 95.89% after Lowess normalization.

• Journal of Korea Spatial Information System Society
• /
• v.10 no.3
• /
• pp.31-43
• /
• 2008

Travel time prediction is an indispensable to many advanced traveler information systems(ATIS) and intelligent transportation systems(ITS). In this paper we propose a method to predict travel time using $Na{\ddot{i}}ve$ Bayesian classification method which has exhibited high accuracy and processing speed when applied to classily large amounts of data. Our proposed prediction algorithm is also scalable to road networks with arbitrary travel routes. For a given route, we consider time-varying average segment velocity to perform more accuracy of travel time prediction. We compare the proposed method with the existing prediction algorithms like link-based prediction algorithm [1] and Micro T* algorithm [2]. It is shown from the performance comparison that the proposed predictor can reduce MARE (mean absolute relative error) significantly, compared with the existing predictors.

• Journal of Internet Computing and Services
• /
• v.20 no.1
• /
• pp.1-10
• /
• 2019

Since big-data text mining extracts many features and data, clustering and classification can result in high computational complexity and low reliability of the analysis results. In particular, a term document matrix obtained through text mining represents term-document features, but produces a sparse matrix. We designed an advanced genetic algorithm (GA) to extract features in text mining for detection model. Term frequency inverse document frequency (TF-IDF) is used to reflect the document-term relationships in feature extraction. Through a repetitive process, a predetermined number of features are selected. And, we used the sparsity score to improve the performance of detection model. If a spam mail data set has the high sparsity, detection model have low performance and is difficult to search the optimization detection model. In addition, we find a low sparsity model that have also high TF-IDF score by using s(F) where the numerator in fitness function. We also verified its performance by applying the proposed algorithm to text classification. As a result, we have found that our algorithm shows higher performance (speed and accuracy) in attack mail classification.