• Journal of the Korea Society of Computer and Information
• /
• v.24 no.10
• /
• pp.79-89
• /
• 2019

While most research focuses on the k-nearest neighbors (kNN) queries in the database community, an important type of proximity queries called k-farthest neighbors (kFN) queries has not received much attention. This paper addresses the problem of finding the k-farthest neighbors in road networks. Given a positive integer k, a query object q, and a set of data points P, a kFN query returns k data objects farthest from the query object q. Little attention has been paid to processing kFN queries in road networks. The challenge of processing kFN queries in road networks is reducing the number of network distance computations, which is the most prominent difference between a road network and a Euclidean space. In this study, we propose an efficient algorithm called FANS for k-FArthest Neighbor Search in road networks. We present a shared computation strategy to avoid redundant computation of the distances between a query object and data objects. We also present effective pruning techniques based on the maximum distance from a query object to data segments. Finally, we demonstrate the efficiency and scalability of our proposed solution with extensive experiments using real-world roadmaps.

• Journal of Broadcast Engineering
• /
• v.21 no.4
• /
• pp.569-577
• /
• 2016

Place recognition for LBS (Location Based Service) has been one of the important techniques for user-oriented service. FLANN (Fast Library for performing Approximate Nearest Neighbor) of place recognition with image features is fast, but it is affected much by environmental condition such as occlusions. This paper presents a place recognition method using quad vocabulary tree with SURF (Speeded Up Robust Features). In learning stage, an image is represented with spatial pyramid of three levels and vocabulary trees of their sub-regions are constructed. Query image is matched with the learned vocabulary trees in each level. The proposed method measures homography error of the matched features. By considering the number of inliers in sub-region, we can improve place recognition performance.

• Proceedings of the Korea Contents Association Conference
• /
• 2018.05a
• /
• pp.9-10
• /
• 2018

모바일 기기의 대중화 및 위치 인식 기술의 발달로 다양한 위치 기반 서비스가 제공되고 있다. 많은 위치 기반 서비스에서는 현재 위치에서 가장 가까운 k개의 아이템을 찾는 k-최근접 질의가 빈번하게 활용되고 있다. 본 논문에서는 효율적인 k-최근접 분산 질의 처리를 질의 할당 기법을 제안한다. 질의 처리 할당을 위해 질의 통계 값을 활용한 질의 모형을 정의하고 규칙 기반의 질의 할당을 수행한다. 성능 평가를 통해 제안하는 기법의 우수성을 보인다.

• Spatial Information Research
• /
• v.20 no.3
• /
• pp.67-81
• /
• 2012

Due to the recent advancement of cloud computing, the research on database outsourcing has been actively done. Moreover, the number of users who utilize Location-based Services(LBS) has been increasing with the development in w ireless communication technology and mobile devices. Therefore, LBS providers attempt to outsource their spatial database to service provider, in order to reduce costs for data storage and management. However, because unauthorized access to sensitive data is possible in spatial database outsourcing, it is necessary to study on the preservation of a user's privacy. Thus, we, in this paper, propose a spatial data encryption scheme to produce outsourced database from an original database. We also propose a k-Nearest Neighbor(k-NN) query processing algorithm that efficiently performs k-NN by using the outsourced database. Finally, we show from performance analysis that our algorithm outperforms the existing one.

• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06a
• /
• pp.65-68
• /
• 2011

최근 무선 통신 기술의 발달 및 모바일 기기의 발달로 인하여 위치 기반 서비스가 주목을 받고 있다. 그러나 사용자의 정확한 위치정보를 통해 LBS 서버에 질의를 요청하는 것은 심각한 개인 정보 누출의 위협이 될 수 있기 때문에, 사용자 정보 보호를 위해 도로 네트워크를 고려하여 질의영역을 생성하는 연구가 활발히 진행되어 왔다. 따라서 질의영역에 대한 효율적인 질의 처리 방법이 요구된다. 이를 위해, 본 논문에서는 도로 네트워크에서 사용자 정보 보호를 지원하는 질의영역에 대한 k최근접점 질의 처리 알고리즘을 제안한다. 제안하는 기법은 POI를 효율적으로 검색하기 위하여 Island 인덱스를 사용한다. 또한, 본 논문은 질의 처리 성능을 향상시키기 위해 적응적 Island 인덱스를 생성하는 방법을 제안한다. 마지막으로, 성능평가를 통해 제안하는 기법이 기존 기법들에 비해 네트워크 확장 비용 및 서비스 시간 측면에서 우수함을 보인다.

• Proceedings of the Korea Contents Association Conference
• /
• 2019.05a
• /
• pp.443-444
• /
• 2019

효율적인 이미지 검색을 위해 고차원 데이터 색인에 대한 연구가 진행되고 있다. 거리 기반 색인 구조는 다차원 데이터를 색인하는데 자주 활용되는데, k-최근접 질의 처리에서 초기 탐색 범위를 전체 영역의 1%만으로 결정한다. 본 논문에서는 거리 기반 색인구조에서 k-최근접 질의를 효율적으로 처리하기 위해 데이터 분포 기반의 최적화 및 질의 처리 비용 기반 최적화 기법을 제안한다.

• The Journal of the Korea Contents Association
• /
• v.20 no.10
• /
• pp.715-725
• /
• 2020

In this paper, we propose an optimization scheme for a k-Nearest Neighbor(k-NN) query, which finds k objects closest to the query in the high dimensional feature vectors. The k-NN query is converted and processed into a range query based on the range that is likely to contain k data. In this paper, we propose an optimization scheme using DNN model to derive an optimal range that can reduce processing cost and accelerate search speed. The entire system of the proposed scheme is composed of online and offline modules. In the online module, a query is actually processed when it is issued from a client. In the offline module, an optimal range is derived for the query by using the DNN model and is delivered to the online module. It is shown through various performance evaluations that the proposed scheme outperforms the existing schemes.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.7
• /
• pp.1518-1524
• /
• 2014

In this paper, a new method of spatial query, which is called Surround Search (SuSe) is suggested. This method makes it possible to search for the closest spatial object of interest to the user from a query point. SuSe is differentiated from the existing spatial object query schemes, because it locates the closest spatial object of interest around the query point. While SuSe searches the surroundings, the spatial object is saved on an R-tree, and MINDIST, the distance between the query location and objects, is measured by considering an angle that the existing spatial object query methods have not previously considered. The angle between targeted-search objects is found from a query point that is hidden behind another object in order to distinguish hidden objects from them. The distinct feature of this proposed scheme is that it can search the faraway or hidden objects, in contrast to the existing method. SuSe is able to search for spatial objects more precisely, and users can be confident that this scheme will have superior performance to its predecessor.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.1
• /
• pp.368-391
• /
• 2018

Face recognition (FR) with a single sample per person (SSPP) is common in real-world face recognition applications. In this scenario, it is hard to predict intra-class variations of query samples by gallery samples due to the lack of sufficient training samples. Inspired by the fact that similar faces have similar intra-class variations, we propose a virtual sample generating algorithm called k nearest neighbors based virtual sample generating (kNNVSG) to enrich intra-class variation information for training samples. Furthermore, in order to use the intra-class variation information of the virtual samples generated by kNNVSG algorithm, we propose image set based multimanifold discriminant learning (ISMMDL) algorithm. For ISMMDL algorithm, it learns a projection matrix for each manifold modeled by the local patches of the images of each class, which aims to minimize the margins of intra-manifold and maximize the margins of inter-manifold simultaneously in low-dimensional feature space. Finally, by comprehensively using kNNVSG and ISMMDL algorithms, we propose k nearest neighbor virtual image set based multimanifold discriminant learning (kNNMMDL) approach for single sample face recognition (SSFR) tasks. Experimental results on AR, Multi-PIE and LFW face datasets demonstrate that our approach has promising abilities for SSFR with expression, illumination and disguise variations.

• Journal of KIISE:Databases
• /
• v.35 no.2
• /
• pp.169-181
• /
• 2008

Because moving objects usually move on spatial networks, efficient trajectory index structures are required to achieve good retrieval performance on their trajectories. However, there has been little research on trajectory index structures for spatial networks such as FNR-tree and MON-tree. But, because FNR-tree and MON-tree are stored by the unit of the moving object's segment, they can't support the whole moving objects' trajectory. In this paper, we propose an efficient trajectory index structure, named Trajectory of Moving objects on Network Tree(TMN Tree), for moving objects. For this, we divide moving object data into spatial and temporal attribute, and preserve moving objects' trajectory. Then, we design index structure which supports not only range query but trajectory query. In addition, we divide user queries into spatio-temporal area based trajectory query, similar-trajectory query, and k-nearest neighbor query. We propose query processing algorithms to support them. Finally, we show that our trajectory index structure outperforms existing tree structures like FNR-Tree and MON-Tree.