• ETRI Journal
• /
• v.44 no.2
• /
• pp.244-259
• /
• 2022

Bicycle- or bike-sharing systems (BSSs) have received increasing attention as a secondary transportation mode due to their advantages, for example, accessibility, prevention of air pollution, and health promotion. However, in BSSs, due to bias in bike demands, the bike rebalancing problem should be solved. Various methods have been proposed to solve this problem; however, it is difficult to apply such methods to small cities because bike demand is sparse, and there are many practical issues to solve. Thus, we propose a demand prediction model using multiple classifiers, time grouping, categorization, weather analysis, and station correlation information. In addition, we analyze real-world relocation data by relocation managers and propose a relocation algorithm based on the analytical results to solve the bike rebalancing problem. The proposed system is compared experimentally with the results obtained by the real relocation managers.

• Journal of Institute of Control, Robotics and Systems
• /
• v.17 no.8
• /
• pp.739-746
• /
• 2011

Recently, recommender systems have been widely applied in E-commerce websites to help their customers find the items what they want. A recommender system should be able to provide users with useful information regarding their interests. The ability to immediately respond to the changes in user's preference is a valuable asset of recommender systems. This paper proposes a novel recommender system which aims to effectively adapt and respond to the immediate changes in user's preference. The proposed system combines IEC (Interactive Evolutionary Computation) with a content-based filtering method and also employs data grouping in order to improve time efficiency. Experiments show that the proposed system makes acceptable recommendations while ensuring quality and speed. From a comparative experimental study with an existing recommender system which uses the content-based filtering, it is revealed that the proposed system produces more reliable recommendations and adaptively responds to the changes in any given condition. It denotes that the proposed approach can be an alternative to resolve limitations (e.g., over-specialization and sparse problems) of the existing methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.3
• /
• pp.792-812
• /
• 2022

Multi-agent systems often need to achieve the goal of learning more effectively for a task through coordination. Although the introduction of deep learning has addressed the state space problems, multi-agent learning remains infeasible because of the joint action spaces. Large-scale joint action spaces can be sparse according to implicit or explicit coordination structure, which can ensure reasonable coordination action through the coordination structure. In general, the multi-agent system is dynamic, which makes the relations among agents and the coordination structure are dynamic. Therefore, the explicit coordination structure can better represent the coordinative relationship among agents and achieve better coordination between agents. Inspired by the maximization of social group utility, we dynamically construct a factor graph as an explicit coordination structure to express the coordinative relationship according to the utility among agents and estimate the joint action values based on the local utility transfer among factor graphs. We present the application of such techniques in the scenario of multiple intelligent vehicle systems, where state space and action space are a problem and have too many interactions among agents. The results on the multiple intelligent vehicle systems demonstrate the efficiency and effectiveness of our proposed methods.

• Proceedings of the Korean Society for Bioinformatics Conference
• /
• 2003.10a
• /
• pp.164-169
• /
• 2003

In this paper, we propose the integrated Bayesian network framework to reconstruct genetic regulatory networks from genome expression data. The proposed model overcomes the dimensionality problem of multivariate analysis by building coherent sub-networks from confined gene clusters and combining these networks via intermediary points. Gene Shaving algorithm is used to cluster genes that share a common function or co-regulation. Retrieved clusters incorporate prior biological knowledge such as Gene Ontology, pathway, and protein protein interaction information for extracting other related genes. With these extended gene list, system builds genetic sub-networks using Bayesian network with MDL score and Sparse Candidate algorithm. Identifying functional modules of genes is done by not only microarray data itself but also well-proved biological knowledge. This integrated approach can improve there liability of a network in that false relations due to the lack of data can be reduced. Another advantage is the decreased computational complexity by constrained gene sets. To evaluate the proposed system, S. Cerevisiae cell cycle data [1] is applied. The result analysis presents new hypotheses about novel genetic interactions as well as typical relationships known by previous researches [2].

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.7
• /
• pp.3338-3355
• /
• 2018

Images acquired by Large Aperture Static Imaging Spectrometer (LASIS) exhibit obvious interference stripes, which are vertical and stationary due to the special imaging principle of interference hyperspectral image (IHI) data. As the special characteristics above will seriously affect the intrinsic structure and sparsity of IHI, decomposition of IHI has drawn considerable attentions of many scientists and lots of efforts have been made. Although some decomposition methods for interference hyperspectral data have been proposed to solve the above problem of interference stripes, too many times of iteration are necessary to get an optimal solution, which will severely affect the efficiency of application. A novel algorithm for decomposition of interference hyperspectral images based on split Bregman iteration is proposed in this paper, compared with other decomposition methods, numerical experiments have proved that the proposed method will be much more efficient and can reduce the times of iteration significantly.

• Journal of Computational Design and Engineering
• /
• v.1 no.1
• /
• pp.48-54
• /
• 2014

In this paper, the authors propose a system for assisting mold designers of plastic parts. With a CAD model of a part, the system automatically determines the optimal ejecting direction of the part with minimum undercuts. Since plastic parts are generally very thin, many rib features are placed on the inner side of the part to give sufficient structural strength. Our system extracts the rib features from the CAD model of the part, and determines the possible ejecting directions based on the geometric properties of the features. The system then selects the optimal direction with minimum undercuts. Possible ejecting directions are represented as discrete points on a Gauss map. Our new point distribution method for the Gauss map is based on the concept of the architectural geodesic dome. A hierarchical structure is also introduced in the point distribution, with a higher level "rough" Gauss map with rather sparse point distribution and another lower level "fine" Gauss map with much denser point distribution. A system is implemented and computational experiments are performed. Our system requires less than 10 seconds to determine the optimal ejecting direction of a CAD model with more than 1 million polygons.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.5
• /
• pp.2082-2102
• /
• 2018

In recent years, social network related applications such as WeChat, Facebook, Twitter and so on, have attracted hundreds of millions of people to share their experience, plan or organize, and attend social events with friends. In these operations, plenty of valuable information is accumulated, which makes an innovative approach to explore users' preference and overcome challenges in traditional recommender systems. Based on the study of the existing social network recommendation methods, we find there is an abundant information that can be incorporated into probability matrix factorization (PMF) model to handle challenges such as data sparsity in many recommender systems. Therefore, the research put forward a unified social network recommendation framework that combine tags, trust between users, ratings with PMF. The uniformed method is based on three existing recommendation models (SoRecUser, SoRecItem and SoRec), and the complexity analysis indicates that our approach has good effectiveness and can be applied to large-scale datasets. Furthermore, experimental results on publicly available Last.fm dataset show that our method outperforms the existing state-of-art social network recommendation approaches, measured by MAE and MRSE in different data sparse conditions.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.8
• /
• pp.2879-2899
• /
• 2021

The tone reservation (TR) scheme is an attractive method to reduce peak-to-average power ratio (PAPR) in the filter bank multicarrier with offset quadrature amplitude modulation (FBMC-OQAM) systems. However, the high PAPR of FBMC signal will severely degrades system performance. To address this issue, a cyclic shift based TR (CS-TR) scheme with embedding side information (SI) is proposed to reduce the PAPR of FBMC signals. At the transmitter, four candidate signals are first generated based on cyclic shift of the output of inverse discrete Fourier transform (IDFT), and the SI of the selected signal with minimum peak power among the four candidate signals is embedded in sparse symbols with quadrature phase-shift keying constellation. Then, the TR weighted by optimal scaling factor is employed to further reduce PAPR of the selected signal. At the receiver, a reliable SI detector is presented by determining the phase rotation of SI embedding symbols, and the transmitted data blocks can be correctly demodulated according to the detected SI. Simulation results show that the proposed scheme significantly outperforms the existing TR schemes in both PAPR reduction and bit error rate (BER) performances. In addition, the proposed scheme with detected SI can achieve the same BER performance compared to the one with perfect SI.

• Journal of Information Processing Systems
• /
• v.17 no.3
• /
• pp.462-472
• /
• 2021

With an increase in the scale of recommender systems, users' rating data tend to be extremely sparse. Some methods have been utilized to alleviate this problem; nevertheless, it has not been satisfactorily solved yet. Therefore, we propose an effective pre-rating method based on users' dichotomous preferences and average ratings fusion. First, based on a user-item ratings matrix, a new user-item preference matrix was constructed to analyze and model user preferences. The items were then divided into two categories based on a parameterized dynamic threshold. The missing ratings for items that the user was not interested in were directly filled with the lowest user rating; otherwise, fusion ratings were utilized to fill the missing ratings. Further, an optimized parameter λ was introduced to adjust their weights. Finally, we verified our method on a standard dataset. The experimental results show that our method can effectively reduce the prediction error and improve the recommendation quality. As for its application, our method is effective, but not complicated.

• Journal of KIISE:Computer Systems and Theory
• /
• v.30 no.3_4
• /
• pp.205-212
• /
• 2003

In this paper, we propose a simple and efficient hardware-supported antialiasing algorithm and its rendering scheme. The proposed method can efficiently reduce the required memory bandwidth as well as memory size compared to a conventional supersampling when rendering 3D models. In addition, it can provide almost the same high quality scenes as supersampling does. In this paper, we have introduced the RUF (Recently Used Fragment) buffer that stores some or whole parts of a fragment or two more the merged results of fragments that recently used in color calculation. We have also proposed a color calculation algorithm to deteriorate the image quality as referencing the RUF buffer. Because of the efficiency presented in the proposed algorithm, the more number of sampling points increases the more memory saving ratio we can gain relative to the conventional supersampling. In our simulation, the proposed method can reduce the amount of memory size by 31% and the memory bandwidth by 11% with a moderate pixel color difference of 1.3% compared to supersampling for 8 sparse sampling points.