• Journal of Information Technology Services
• /
• v.22 no.1
• /
• pp.43-56
• /
• 2023

With the development of the e-commerce market, various types of products continue to be released. However, customers face an information overload problem in purchasing decision-making. Therefore, personalized recommendations have become an essential service in providing personalized products to customers. Recently, many studies on GCN-based recommender systems have been actively conducted. Such a methodology can address the limitation in disabling to effectively reflect the interaction between customer and product in the embedding process. However, previous studies mainly use implicit feedback data to conduct experiments. Although implicit feedback data improves the data scarcity problem, it cannot represent customers' preferences for specific products. Therefore, this study proposed a novel model combining explicit and implicit feedback to address such a limitation. This study treats the average ratings of customers and products as the features of customers and products and converts them into a high-dimensional feature vector. Then, this study combines ID embedding vectors and feature vectors in the embedding layer to learn the customer-product interaction effectively. To evaluate recommendation performance, this study used the MovieLens dataset to conduct various experiments. Experimental results showed the proposed model outperforms the state-of-the-art. Therefore, the proposed model in this study can provide an enhanced recommendation service for customers to address the information overload problem.

• The Journal of the Acoustical Society of Korea
• /
• v.33 no.4
• /
• pp.225-231
• /
• 2014

This paper suggests an algorithm to improve the tracking performance for an underwater acoustic target using the feedback information of acoustic feature of a target. While conventional tracking algorithms use detected acoustic signals only, the proposed algorithm uses detected acoustic signals and target feature information as well. Since the proposed algorithm tracks only the selected measurements using target feature information, it prevents onset of unnecessary tracks and improves tracking performance for target of interest. Furthermore, it optimizes tracking parameters for the target of interest and guarantees robustness and consistency of the track. Some simulations are performed to demonstrate the improved tracking performance of the proposed algorithm.

• Journal of Korea Multimedia Society
• /
• v.21 no.7
• /
• pp.745-754
• /
• 2018

Language is an essential tool for verbal and emotional communication among human beings, enabling them to engage in social interactions. Although a majority of hearing-impaired people can speak; however, they are unable to receive feedback on their pronunciation most of them can speak. However, they do not receive feedback on their pronunciation. This results in impaired communication owing to incorrect pronunciation, which causes difficulties in their social interactions. If hearing-impaired people could receive continuous feedback on their pronunciation and phonation through lip-reading training, they could communicate more effectively with people without hearing disabilities, anytime and anywhere, without the use of sign language. In this study, the mouth area is detected from videos of learners speaking monosyllabic words. The grayscale information of the detected mouth area is used to estimate a velocity vector using Optical Flow. This information is then quantified as feature values to classify vowels. Subsequently, a system is proposed that classifies monosyllables by algebraic computation of geometric feature values of lips using the characteristics of articulatory phonation. Additionally, the system provides feedback by evaluating the comparison between the information which is obtained from the sample categories and experimental results.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.3
• /
• pp.533-540
• /
• 2012

In this paper, we propose a document summarization method using the pseudo relevance feedback and the term weighting based on semantic features. The proposed method can minimize the user intervention to use the pseudo relevance feedback. It also can improve the quality of document summaries because the inherent semantic of the sentence set are well reflected by term weighting derived from semantic feature. In addition, it uses the semantic feature of term weighting and the expanded query to reduce the semantic gap between the user's requirement and the result of proposed method. The experimental results demonstrate that the proposed method achieves better performant than other methods without term weighting.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10b
• /
• pp.1253-1256
• /
• 1996

In this paper, a new nonlinear feedback linearization control scheme for induction motors is developed. The control scheme employs a fuzzy nonlinear identification scheme based on fuzzy basis function expansion to adoptively compensate the parameter variations, i.e. rotor resistance, mutual and self inductance etc. An important feature of the proposed control scheme is to incorporate the sliding mode controller into the scheme to speed up convergence rate. Simulation tests show the robust behavior of the proposed controller in the presence of the parameter uncertainties of the machine.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.10 no.3
• /
• pp.157-164
• /
• 2015

In this paper we propose a walking aid system for blind people by exploiting a haptic feedback equipment. The proposed system is a form of haptic feedback cane which is composed of MCU, communication module, sensing module and actuator. The proposed system recognizes obstacles around the blind by using ultrasonic sensors in the sensing module. Moreover, the system generates feedback information about the detected obstacle and then notifies the information to the blind through the actuator. The blind can notice the direction of the detected obstacle with the haptic feedback equipment and vibration motor. Futhermore, the proposed system controls a nearby IoT(Internet of Things) system by utilizing push buttons through the ZigBee communication. Finally, the blind can easily decide the direction of the obstacle without interference of terrain feature by using the proposed system.

• Journal of Korea Multimedia Society
• /
• v.8 no.10
• /
• pp.1306-1313
• /
• 2005

Relevance Feedback(RF), a method to use perceptual feedback in image retrieval, refines a query by the relevance information from a user. However, the user's feedback information is thrown away as soon as a search session ends. So, this paper proposes an enhanced version of RF, which is designed to accumulate human perceptual responses over time through relevance feedback and to dynamically combine the accumulated high-level relevance information with low-level features to further improve the retrieval effectiveness. Experimental results are presented to prove the potential of the proposed RF.

• ETRI Journal
• /
• v.29 no.5
• /
• pp.700-702
• /
• 2007

We present a relevance feedback approach based on multi-class support vector machine (SVM) learning and cluster-merging which can significantly improve the retrieval performance in region-based image retrieval. Semantically relevant images may exhibit various visual characteristics and may be scattered in several classes in the feature space due to the semantic gap between low-level features and high-level semantics in the user's mind. To find the semantic classes through relevance feedback, the proposed method reduces the burden of completely re-clustering the classes at iterations and classifies multiple classes. Experimental results show that the proposed method is more effective and efficient than the two-class SVM and multi-class relevance feedback methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.4
• /
• pp.692-710
• /
• 2013

Conventional interference alignment (IA) for a MIMO interference channel (IFC) requires global and perfect channel state information at transmitter (CSIT) to achieve the optimal degrees of freedom (DoF), which prohibits practical implementation. In order to alleviate the global CSIT requirement caused by the coupled relation among all of IA equations, we propose an IA scheme with a single feedback link of each receiver in a limited feedback environment for a three-user MIMO IFC. The main feature of the proposed scheme is that one of users takes out a fraction of its maximum number of data streams to decouple IA equations for three-user MIMO IFC, which results in a single link feedback structure at each receiver. While for the conventional IA each receiver has to feed back to all transmitters for transmitting the maximum number of data streams. With the assumption of a random codebook, we analyze the upper bound of the average throughput loss caused by quantized channel knowledge as a function of feedback bits. Analytic results show that the proposed scheme outperforms the conventional IA scheme in term of the feedback overhead and the sum rate as well.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.43 no.1 s.307
• /
• pp.13-20
• /
• 2006

In this paper, we propose a motion control scheme of robot manipulators based on visual feedback under camera-in-hand configuration. The desired joint velocity and acceleration for motion control is made by the feature-based visual data in the outer loop. The control input for tracking feature points on the image plane uses robot kinematics dynamic. The proposed control input consists of the image feature and the joint velocity error to achieve robustness to the parametric uncertainty. The stability of the closed-loop system is proved by Lyapunov approach. Computer simulations and experiments on a two degree of freedom manipulator with 5 links are presented to illustrate the performance of proposed control system.