• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.6
• /
• pp.271-278
• /
• 2004

In this paper, we propose a content-based audio genre classification algorithm that automatically classifies the query audio into five genres such as Classic, Hiphop, Jazz, Rock, Speech using digital sign processing approach. From the 20 seconds query audio file, the audio signal is segmented into 23ms frame with non-overlapped hamming window and 54 dimensional feature vectors, including Spectral Centroid, Rolloff, Flux, LPC, MFCC, is extracted from each query audio. For the classification algorithm, k-NN, Gaussian, GMM classifier is used. In order to choose optimum features from the 54 dimension feature vectors, SFS(Sequential Forward Selection) method is applied to draw 10 dimension optimum features and these are used for the genre classification algorithm. From the experimental result, we can verify the superior performance of the proposed method that provides near 90% success rate for the genre classification which means 10%∼20% improvements over the previous methods. For the case of actual user system environment, feature vector is extracted from the random interval of the query audio and it shows overall 80% success rate except extreme cases of beginning and ending portion of the query audio file.

• The Journal of the Korea Contents Association
• /
• v.12 no.5
• /
• pp.22-31
• /
• 2012

A Smartphone is an intelligent device combined mobile phone and pc's support functions, and can perform multiple functions to satisfy the demands of users. It has excellent processing power and communication modules(DMB, Wi-Fi, Bluetooth, NFC etc) to carry out the demands of users. But continuous using of battery power on processor and equipped modules causes acceleration of battery consumption. This means that effective power management in devices like smartphone is important. Therefore, the management of power consumption on system execution and communication module is a serious issue in this field of study. In this paper, we would like to propose a communication module selection algorithm based on energy consumption parameter of each communication module and data transfer time. Our scheme automatically select appropriate communication system to reduce high energy consumption on bluetooth sleep mode so that this scheme is more efficient and effective thus improving user convenience in longer usage time. Experimental results showed the 20% energy saving.

• Journal of the Korean Society for Library and Information Science
• /
• v.27
• /
• pp.161-181
• /
• 1994

As information technologies are applied to the libraries in information society, the library services have been changing its feature. Therefore, the purpose of this paper is to explore and to establish a paradigm of the library services in information society. It is hypothesized that the application of information technologies leads to the change of the library services in information society. To prove the hypothesis, the data were collected from various research results carried out in the developed countries and by observing various libraries where the information technologies are extensively applied. The findings are as follows: 1. As information technologies are applied to the library, many new library services emerge for the society. 2. As the electronic data replace the paper data, the collection of a library becomes the collection of the libraries in the world. Therefore, the accessibility to the information network is more important than to own information in the library. Librarians select various electronic data according to the library policy which distinguishes their own library collection from others. The policy also solves the various problems related to weeding and preserving library collection. And the use of CD-ROM selection tools enable library users to select their own data. Now, the censorship becomes the concems of the library users, not the library. 3. The catalogs are reorganized for the electronic data for the international use. The most important information in the catalog is the location of the data and the multi access to the data are necessary. 4. As the information technologies are applied in book selection, cataloguing, information retreival and circulation, the library users are enable to service themselves in the library. And most of the routine works related to the information service are taken over by the library staffs. Professional librarians engage in user education, information marketing and fund raising. 5. Public libraries in information society serves those who have no access to the information. They help the illiterates. patients in the hospital, prisoners, and homeless in the city. Therefore, the information technologies enhance the role of librarians in professional work in the library as well as in the information society.

• Journal of Distribution Science
• /
• v.7 no.1
• /
• pp.71-90
• /
• 2009

Recently, highway service becomes a very important service in highways. Highway service is considered as a positive interaction method between highway service companies and customers. From this perspective, this study was to investigate the relationships between influencing factors of highway service and user satisfaction. And, this research was to examine the differences between importance and performance of highway service factors using IPA (Importance-Performance Analysis). The result of this study has categorised the 22 highway service attributes into seven highway service selection factors: food, culture, kindness and health, products, large space, employee and Phone, facility. Using IPA, this study has compared the importance and performance of highway service selection factors, as perceived highway service customers. The empirical findings suggest that strategic framework using IPA gives guidelines that improve effectiveness of highway service.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.1
• /
• pp.20-26
• /
• 2008

As they have more and more intelligence robots or computers these days, so the interaction between intelligence robot(computer) - human is getting more and more important also the emotion recognition and expression are indispensable for interaction between intelligence robot(computer) - human. In this paper, firstly we extract emotional features at speech signal and facial image. Secondly we apply both BL(Bayesian Learning) and PCA(Principal Component Analysis), lastly we classify five emotions patterns(normal, happy, anger, surprise and sad) also, we experiment with decision fusion and feature fusion to enhance emotion recognition rate. The decision fusion method experiment on emotion recognition that result values of each recognition system apply Fuzzy membership function and the feature fusion method selects superior features through SFS(Sequential Forward Selection) method and superior features are applied to Neural Networks based on MLP(Multi Layer Perceptron) for classifying five emotions patterns. and recognized result apply to 2D facial shape for express emotion.

• Journal of KIISE:Software and Applications
• /
• v.31 no.7
• /
• pp.859-868
• /
• 2004

We propose a method of selecting initial training examples for active learning so that it can reach high accuracy faster with fewer further queries. Our method is based on the assumption that an active learner can reach higher performance when given an initial training set consisting of diverse and typical examples rather than similar and special ones. To obtain a good initial training set, we first cluster examples by using k-means clustering algorithm to find groups of similar examples. Then, a representative example, which is the closest example to the cluster's centroid, is selected from each cluster. After these representative examples are labeled by querying to the user for their categories, they can be used as initial training examples. We also suggest a method of using the centroids as initial training examples by labeling them with categories of corresponding representative examples. Experiments with various text data sets have shown that the active learner starting from the initial training set selected by our method reaches higher accuracy faster than that starting from randomly generated initial training set.

• Journal of Biosystems Engineering
• /
• v.39 no.1
• /
• pp.1-10
• /
• 2014

Purpose: This research was conducted to evaluate feasibility of a crank-type walking cultivators for weeding in furrowed upland. Methods: A walking cultivator developed by RDA was selected and evaluated with its working speed (S), cultivation depth (CD) and weeding performance (WP). The evaluation was performed in upland field on July and August, 2012. Also kinematic analysis of the machine was performed to draw out design improvements. Results: S in flat, uphill and downhill were about 0.11 m $s^{-1}$, 0.11 m $s^{-1}$, and 0.13 m $s^{-1}$ respectively. It was found that S had a low relevance with user conditions. The CD was 35 ~ 40 mm which was satisfied with the RDA guide for weeding machine. A wide variation was observed in values of WP depending on the growth stages of weeds and field conditions. The cultivator showed low performance in eliminating the well-grown weeds. Kinematic simulation revealed that high forward speed caused a high ratio of un-weeded area. Conclusions: The weeding performance of the cultivator was satisfactory for weeds in early growth stage but it showed difficulties in handling on up-slope and in entering up-land. Specifically, the weight of the cultivator was judged as overweight for female workers. The crank-hoe type cultivator was judged as unsuitable for small walking type machine due to weight of the four-bar linkage system. Kinematic analysis revealed that the ratio of crank speed to the ground speed must be 850 rpm s $m^{-1}$ (255 rpm based on 0.3 m $s^{-1}$) or greater to avoid uncultivated area. Selection of forward speed is a decisive factor in designing the weeding cultivator.

• Journal of Intelligence and Information Systems
• /
• v.19 no.2
• /
• pp.39-54
• /
• 2013

Recent explosive increase of electronic commerce provides many advantageous purchase opportunities to customers. In this situation, customers who do not have enough knowledge about their purchases, may accept product recommendations. Product recommender systems automatically reflect user's preference and provide recommendation list to the users. Thus, product recommender system in online shopping store has been known as one of the most popular tools for one-to-one marketing. However, recommender systems which do not properly reflect user's preference cause user's disappointment and waste of time. In this study, we propose a novel recommender system which uses data mining and multi-model ensemble techniques to enhance the recommendation performance through reflecting the precise user's preference. The research data is collected from the real-world online shopping store, which deals products from famous art galleries and museums in Korea. The data initially contain 5759 transaction data, but finally remain 3167 transaction data after deletion of null data. In this study, we transform the categorical variables into dummy variables and exclude outlier data. The proposed model consists of two steps. The first step predicts customers who have high likelihood to purchase products in the online shopping store. In this step, we first use logistic regression, decision trees, and artificial neural networks to predict customers who have high likelihood to purchase products in each product group. We perform above data mining techniques using SAS E-Miner software. In this study, we partition datasets into two sets as modeling and validation sets for the logistic regression and decision trees. We also partition datasets into three sets as training, test, and validation sets for the artificial neural network model. The validation dataset is equal for the all experiments. Then we composite the results of each predictor using the multi-model ensemble techniques such as bagging and bumping. Bagging is the abbreviation of "Bootstrap Aggregation" and it composite outputs from several machine learning techniques for raising the performance and stability of prediction or classification. This technique is special form of the averaging method. Bumping is the abbreviation of "Bootstrap Umbrella of Model Parameter," and it only considers the model which has the lowest error value. The results show that bumping outperforms bagging and the other predictors except for "Poster" product group. For the "Poster" product group, artificial neural network model performs better than the other models. In the second step, we use the market basket analysis to extract association rules for co-purchased products. We can extract thirty one association rules according to values of Lift, Support, and Confidence measure. We set the minimum transaction frequency to support associations as 5%, maximum number of items in an association as 4, and minimum confidence for rule generation as 10%. This study also excludes the extracted association rules below 1 of lift value. We finally get fifteen association rules by excluding duplicate rules. Among the fifteen association rules, eleven rules contain association between products in "Office Supplies" product group, one rules include the association between "Office Supplies" and "Fashion" product groups, and other three rules contain association between "Office Supplies" and "Home Decoration" product groups. Finally, the proposed product recommender systems provides list of recommendations to the proper customers. We test the usability of the proposed system by using prototype and real-world transaction and profile data. For this end, we construct the prototype system by using the ASP, Java Script and Microsoft Access. In addition, we survey about user satisfaction for the recommended product list from the proposed system and the randomly selected product lists. The participants for the survey are 173 persons who use MSN Messenger, Daum Caf$\acute{e}$, and P2P services. We evaluate the user satisfaction using five-scale Likert measure. This study also performs "Paired Sample T-test" for the results of the survey. The results show that the proposed model outperforms the random selection model with 1% statistical significance level. It means that the users satisfied the recommended product list significantly. The results also show that the proposed system may be useful in real-world online shopping store.

• Journal of Internet Computing and Services
• /
• v.21 no.4
• /
• pp.1-8
• /
• 2020

In order to reach Ultra-Reliable Low-Latency communication, one of 5G aims, Multi-access Edge Computing paradigm was born. The idea of this paradigm is to bring cloud computing technologies closer to the network edge. User services are hosted in multiple Edge Clouds, deployed at the edge of the network distributedly, to reduce the service latency. For mobile users, migrating their services to the most proper Edge Clouds for maintaining a Quality of Service is a non-convex problem. The service migration problem becomes more complex in high mobility scenarios. The goal of the study is to observe how user mobility affects the selection of Edge Cloud during a fixed mobility path. Mobility-Aware Service Migration (MASM) is proposed to optimize service migration based on two main parameters: routing cost and service migration cost, during a high mobility scenario. The performance of the proposed algorithm is compared with an existing greedy algorithm.

• Journal of Broadcast Engineering
• /
• v.16 no.6
• /
• pp.977-985
• /
• 2011

Recent works on multiuser transmission techniques have shown that the linear growth of capacity in single user MIMO system can be translated to the multiuser MIMO scenario as well. In this paper, we propose a method pursuing performance gain of vector perturbation in multiuser downlink systems. Instead of employing maximum number of mobile users for communication, we use small part of them as virtual users for improving reliability of users participating communication. By controlling parameters of virtual users including information and perturbation vector, we obtain considerable improvement in the effective SNR, resulting in large gain in bit error rate performance. Simulation results on the realistic multiuser downlink systems show that the proposed method brings substantial performance gain over the standard vector perturbation with marginal overhead in computations.