Reverse kNN Research Articles

PHRkNN: Efficient and Privacy-Preserving Reverse kNN Query Over High-Dimensional Data in Cloud

PHRkNN: Efficient and Privacy-Preserving Reverse kNN Query Over High-Dimensional Data in Cloud

Efficient and Privacy-Preserving Spatial-Feature-Based Reverse kNN Query

Reverse k nearest neighbor (RkNN) query has been widely applied in the targeted push of information. Many schemes for the RkNN query on encrypted data have been proposed for coordinating the emerging trend of outsourcing data to the cloud. However, none of them supports the spatial data with many features, a prevalent data type in location-based services, e.g., each user in online dating apps usually has a spatial location and many personality trait features. Meanwhile, incorporating features with the spatial data endows the spatial-feature-based RkNN query to provide more precise services than the spatial-based RkNN query. Therefore, as a steppingstone, we propose an efficient and privacy-preserving spatial-feature-based RkNN scheme in this work for the first time. Specifically, we first design a modified intersection and union R tree (MIUR-tree) to index the spatial and feature data. Then, we introduce an MIUR-tree based RkNN query algorithm in the filter and refinement framework to efficiently process RkNN queries. After that, based on a symmetric homomorphic encryption (SHE) scheme, we design a private filter protocol and a private refinement protocol, and leverage them to propose our RkNN query scheme. Rigorous security analysis demonstrates that our scheme is privacy-preserving, and extensive experiments indicate that our scheme is computationally efficient.

Extended natural neighborhood for SMOTE and its variants in imbalanced classification

Imbalanced data classification is a challenging issue encountered in many practical applications. Synthetic minority oversampling technique (SMOTE) and its variants are popular resampling methods. However, in most of these methods, the neighborhood determined by k-nearest neighbor (kNN) cannot reflect the local distribution precisely, leading to the generation of noisy examples. To solve this problem, we propose a neighborhood concept without parameter k called extended natural neighbor (ENaN), which is derived from natural neighbor (NaN). ENaN unites kNN and reverse kNN to determine neighbors adaptively according to the sample distribution. Compared to NaN, ENaN explores broad neighborhoods, which facilitates to improve the quality of generated examples. ENaN-based SMOTE (ENaNSMOTE) can improve the sample distribution obtained by SMOTE and NaNSMOTE. Extensive experiments using 30 synthetic and 20 real-world datasets prove the effectiveness of ENaN in SMOTE and its variants.

SetRkNN: Efficient and Privacy-Preserving Set Reverse kNN Query in Cloud

The advance of cloud computing has driven a new paradigm of outsourcing large-scale data and data-driven services to public clouds. Due to the increased awareness of privacy protection, many studies have focused on addressing security and privacy issues in outsourced query services. Although many privacy-preserving schemes have been proposed for various query types, the set reverse k nearest neighbors (RkNN) query is still an unexplored area. Even if some existing schemes can be adapted to achieve privacy-preserving set RkNN queries, they will suffer from linear search efficiency. As a steppingstone, in this paper, we propose an efficient and privacy-preserving set RkNN query scheme over encrypted data with sublinear query efficiency. Specifically, we first design an inverted prefix index to organize the set dataset and propose an algorithm to traverse the index with sublinear search efficiency. Then, we propose two oblivious data comparison protocols based on a symmetric homomorphic encryption (SHE) scheme and design the private filter/refinement protocols to preserve the privacy of index searching. After that, we propose an access pattern privacy-preserving set RkNN query scheme by using private filter/refinement protocols. Rigorous security analysis demonstrates that our scheme can protect data privacy and access pattern privacy. Experimental results indicate that our scheme is more efficient than the available naive solution in terms of computational costs and communication overheads.

Efficient and Privacy-Preserving Aggregated Reverse kNN Query Over Crowd-Sensed Data

Efficient and Privacy-Preserving Aggregated Reverse kNN Query Over Crowd-Sensed Data

Answering range-based reverse kNN and why-not reverse kNN queries

Answering range-based reverse kNN and why-not reverse kNN queries

Pre-computed Region Guardian Sets Based Reverse kNN Queries

Given a set of objects and a query q, a point p is q’s Reverse k Nearest Neighbour (RkNN) if q is one of p’s k-closest objects. RkNN queries have received significant research attention in the past few years. However, we realize that the state-of-the-art algorithm, SLICE, accesses many objects that do not contribute to its RkNN results when running the filtering phase, which deteriorates the query performance. In this paper, we propose a novel RkNN algorithm with pre-computation by partitioning the data space into disjoint rectangular regions and constructing the guardian set for each region R. We guarantee that, for each q that lies in R, its RkNN results are only affected by the objects in R’s guardian set. The advantage of this approach is that the results of a query $$q\in R$$ can be computed by using SLICE on only the objects in its guardian set instead of using the whole dataset. Besides, we raise two new useful variants of RkNN and propose algorithms. Our comprehensive experimental study on synthetic and real the proposed approaches are the most efficient algorithms for RkNN and its variants.

Monitoring continuous all [formula omitted]-nearest neighbor query in mobile network environments

This paper investigates the continuous all k-nearest neighbor (CAkNN) problem in a pervasive and mobile computing environment, which is a spatial query that continuously monitors kNN results for all mobile users in the network for a specified period of time. This problem is characterized by the fact that a single movement of a node may result in that several users have to re-compute their kNN results. The affected nodes are the moving node itself and its Reverse-kNN (RkNN) nodes at both the previous and the new locations. This paper proposes the use of a bucket point-region quadtree to index mobile users. This structure is unique in that it can be readily reorganized for maintenance purpose when nodes move. In addition, it helps to quickly determine an appropriate search radius for each of these nodes. In this paper, we have proposed two novel RkNN techniques that are tailored for the structure with only small maintenance overhead. These techniques enable us to integrate kNN and RkNN searching operations together so as to facilitate continuous monitoring of the query result. Based on the notion of maximum prune distance, we present two algorithms to offer true continuity for a CAkNN query. Simulation results show that our algorithms outperform existing solutions by a significant margin.

Group Reverse kNN Query optimisation

Spatial queries have been used to assist human mobility. One of them is the Reverse Nearest Neighbour (RNN) Queries, which its concept is to have a set of objects that considers a query object as the nearest neighbour. One solution to the RNN queries is through region approach, which in this case every single object in the space has a certain region where all objects inside this region will think of the query object as their nearest neighbour. This approach is very efficient, especially when it is implemented in mobile environment. However, current RNN queries with region approach can only be applicable to a single query object. In real life, there are some cases where we want to find a region for several objects altogether, not only for a single object. Hence, we propose a solution to this problem through the Group Reverse kNN. We will find a specific region based on multiple query objects, where any objects located inside this region will always consider all of the query objects as the nearest compared to the non-query objects. The development of the algorithm is achieved through the application of computational geometry. Our experiments demonstrate the performance efficiency and accuracy of the proposed algorithms.

On efficient mutual nearest neighbor query processing in spatial databases

This paper studies a new form of nearest neighbor queries in spatial databases, namely, mutual nearest neighbor (MNN) search. Given a set D of objects and a query object q, an MNN query returns from D, the set of objects that are among the k 1 (⩾1) nearest neighbors (NNs) of q; meanwhile, have q as one of their k 2 (⩾1) NNs. Although MNN queries are useful in many applications involving decision making, data mining, and pattern recognition, it cannot be efficiently handled by existing spatial query processing approaches. In this paper, we present the first piece of work for tackling MNN queries efficiently. Our methods utilize a conventional data-partitioning index (e.g., R-tree, etc.) on the dataset, employ the state-of-the-art database techniques including best-first based k nearest neighbor ( kNN) retrieval and reverse kNN search with TPL pruning, and make use of the advantages of batch processing and reusing technique. An extensive empirical study, based on experiments performed using both real and synthetic datasets, has been conducted to demonstrate the efficiency and effectiveness of our proposed algorithms under various experimental settings.