• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.2
• /
• pp.538-561
• /
• 2020

Recommender Systems (RecSys) have a major role in e-commerce for recommending products, which they may like for every user and thus improve their business aspects. Although many types of RecSyss are there in the research field, the state of the art RecSys has focused on finding the user similarity based on sequence (e.g. purchase history, movie-watching history) analyzing and prediction techniques like Recurrent Neural Network in Deep learning. That is RecSys has considered as a sequence prediction problem. However, evaluation of similarities among the customers is challenging while considering temporal aspects, context and multi-component ratings of the item-records in the customer sequences. For addressing this issue, we are proposing a Deep Learning based model which learns customer similarity directly from the sequence to sequence similarity as well as item to item similarity by considering all features of the item, contexts, and rating components using Dynamic Temporal Warping(DTW) distance measure for dynamic temporal matching and 2D-GRU (Two Dimensional-Gated Recurrent Unit) architecture. This will overcome the limitation of non-linearity in the time dimension while measuring the similarity, and the find patterns more accurately and speedily from temporal and spatial contexts. Experiment on the real world movie data set LDOS-CoMoDa demonstrates the efficacy and promising utility of the proposed personalized RecSys architecture.

• Journal of Korea Multimedia Society
• /
• v.21 no.7
• /
• pp.772-778
• /
• 2018

We have previously proposed a preliminary cut-off indoor positioning scheme considering the reference point with the same signal similarity. This scheme estimates the position using the relative rank of the peak of received signal strength from the beacons around user. However, this scheme has a weak point with lower accuracy when there are more than one nearest reference points having the same signal similarity. In order to tackle this, we propose a weighted preliminary cut-off indoor positioning scheme. Firstly, if the above problem occurs, the similarity to the peak of signal strength is considered as well as the relative rank. Next, weights are assigned to the nearest reference points using the similarity to the peak of the received signal strength. Finally, the user's position is estimated by applying the weights. As a result, the weighted preliminary cut-off scheme improves the positioning accuracy by about 7.9% compared to the previous scheme.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.4
• /
• pp.17-22
• /
• 2020

Behavior-based authentication technology, which is currently being researched a lot, requires a long extraction of a lot of data to increase the recognition rate of authentication compared to other authentication technologies. This paper uses the touch sensor and the gyroscope embedded in the smartphone in the Android environment to measure five times to the user to use only the minimum data that is essential among the behavior feature data used in the behavior-based authentication study. By requesting, a total of six behavior feature data were collected by touching the five touch screen, and the mean value was calculated from the changes in data during the next touch measurement to measure the cosine similarity between the value and the measured value. After generating the allowable range of cosine similarity by performing, we propose a user behavior based authentication method that compares the cosine similarity value of the authentication attempt data. Through this paper, we succeeded in demonstrating high performance from the first EER of 37.6% to the final EER of 1.9% by adjusting the threshold applied to the cosine similarity authentication range even in a small number of feature data and experimenter environments.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.11 no.2
• /
• pp.181-188
• /
• 2018

In this paper, we propose an analysis scheme of customer spending pattern using text mining. In proposed consumption pattern analysis scheme, first we analyze user's rating similarity using Pearson correlation, second we analyze user's review similarity using TF-IDF cosine similarity, third we analyze the consistency of the rating and review using Sendiwordnet. And we select the nearest neighbors using rating similarity and review similarity, and provide the recommended list that is proper with consumption pattern. The precision of recommended list are 0.79 for the Pearson correlation, 0.73 for the TF-IDF, and 0.82 for the proposed consumption pattern. That is, the proposed consumption pattern analysis scheme can more accurately analyze consumption pattern because it uses both quantitative rating and qualitative reviews of consumers.

• Journal of the Korean Data and Information Science Society
• /
• v.17 no.3
• /
• pp.775-784
• /
• 2006

This study is to investigate the effect of the number of co-rated users to the MAE. User based collaborative algorithm generally uses similarity weight to compute the relation of active user and other users. The original estimation algorithm of the GroupLens used the Pearson's correlation coefficient, soon after other researchers used various weighting. The Pearson’s correlation coefficient and Vector similarity, which is used in the field of information retrieval, are commonly used to the estimation algorithm. In prediction, we analyze the effect of the number of co-rated users on the user based recommender system.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.9
• /
• pp.4771-4787
• /
• 2019

Aimed at the disclosure risk of mobile terminal user's location privacy in location-based services, a location-privacy protection scheme based on similar trajectory substitution is proposed. On the basis of the anonymized identities of users and candidates who request LBS, this scheme adopts trajectory similarity function to select the candidate whose trajectory is the most similar to user's at certain time intervals, then the selected candidate substitutes user to send LBS request, so as to protect user's privacy like identity, query and trajectory. Security analyses prove that this scheme is able to guarantee such security features as anonymity, non-forgeability, resistance to continuous query tracing attack and wiretapping attack. And the results of simulation experiment demonstrate that this scheme remarkably improve the optimal candidate' trajectory similarity and selection efficiency.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.1986-1989
• /
• 2003

This paper proposes the information retrieval improvement for the Web using the structure and hyperlinks of HTML documents along with user profile. The method bases on the rationale that terms appearing in different structure of documents may have different significance in identifying the documents. The method partitions the occurrence of terms in a document collection into six classes according to the tags in which particular terms occurred (such as Title, H1-H6 and Anchor). We use genetic algorithm to determine class importance values and expand user query. We also use this value in similarity computation and update user profile. Then a genetic algorithm is used again to select some terms from user profile to expand the original query. Lastly, the search engine uses the expanded query for searching and the results of the search engine are scored by similarity values between each result and the user profile. Vector space model is used and the weighting schemes of traditional information retrieval were extended to include class importance values. The tested results show that precision is up to 81.5%.

• Journal of Korea Multimedia Society
• /
• v.13 no.10
• /
• pp.1453-1462
• /
• 2010

In this paper, a new program recommendation system is proposed to recommend user preferred VOD program in IPTV environment. A proposed system is implemented with collaborative filtering method. For a user profile which describes user program preference, a program preference, sub-genre preference, and US(user similarity) weight of the user neighborhood is averaged and updated every week. In order to evaluate system performance, real 24-weeks cable TV watching data provided by Nilson Research Corp. are modified to fit for IPTV broadcasting environment and the simulation result shows quite comparative quality of recommendation. The experimental results optimum performance when user similarity based weighting, five person per group and five recommendation programs are used.

• Archives of design research
• /
• v.16 no.4
• /
• pp.101-110
• /
• 2003

This paper is focused on the similarity of GUI design and proposes checklists for evaluating similarity of GUI design in quantitative way and more important factors in this checklists. On the first, consideration of similarity and analysis of GUI properties are made, and from these results, the categories that affect the evaluation of similarity are extracted. The categories are consisted of 5 factors, which are concept, shape, color, relation, and multimedia. The checklists from above 5 categories are tested in 3-stage, and in this paper, 11 checklists from shape, color, and relation factor of the second stage are verified by online survey. The purpose of this survey is to find out the difference between user groups(designer, computer related, etc) and more important factors in the checklists that affect the total results of similarity. In the results of survey, the checklists have no relation with the user groups and among the checklists, external shape, composition element, and design methods have impact factors on the evaluation of similarity.

• Journal of Internet Computing and Services
• /
• v.12 no.5
• /
• pp.113-125
• /
• 2011

As information resources have become more various and the number of the resources has increased, knowledge customization on the social web has been becoming more difficult. To reduce the burden, we offer a framework for context-based similarity calculation for knowledge customization using ontology on the CBR. Thereby, we newly developed context- and intensity-based similarity calculation methods which are applied to extraction of the most similar case considered semantic similarity and syntactic, and effective creation of the user-tailored knowledge using the selected case. The process is comprised of conversion of unstructured web information into cases, extraction of an appropriate case according to the user requirements, and customization of the knowledge using the selected case. In the experimental section, the effectiveness of the developed similarity methods are compared with other edge-counting similarity methods using two classes which are compared with each other. It shows that our framework leads higher similarity values for conceptually close classes compared with other methods.