基于HBase的路网移动对象时空索引方法

在处理路网移动对象时,由于HBase只能采用key查询,不适用于移动对象的多维查询,导致HBase存在存储索引与查询效率不高的问题。针对此问题,在HBase存储结构的基础上设计并实现了一种高效的路网移动对象HBase索引框架（RM-HBase）。首先,对原生HBase索引框架的上层HMaster和下层HRegionServer进行改进,解决分布式集群数据的热点分布问题,提高空间数据的查询效率;其次,提出路网移动索引——RN-tree,解决空间划分中的"死空间"问题,同时提高空间中路段的查询效率;然后,基于上述对HBase的索引改进,分别设计了时空范围查询、时空K最近邻（KNN）查询和移动对象轨迹查询的查询算法;最后,实验选用了同样是基于HBase分布式数据库而提出的时空HBase索引（STEHIX）框架作为对比对象,分别从索引框架的性能和算法的查询效率两个方面对RM-HBase的性能进行分析。实验结果表明,所提的RM-HBase在数据的均衡分布性能和时空查询算法的查询性能方面都优于STEHIX框架,有助于提升海量路网移动对象数据的时空索引效率。     

An efficient location update mechanism for continuous queries over moving objects

In a moving-object database system that supports continuous queries (CQ), an important problem is to keep the location data consistent with the actual locations of the entities being monitored, in order to produce correct query results. This goal is often difficult to achieve due to limited network resources. However, if an object is not required by any query, its value need not be refreshed. Based on this observation, we redefine the notion of temporal consistency of data items with respect to the query result, where only data items that are relevant to the CQs need to be fresh. To exploit this correctness definition, we develop an adaptive time-based update technique called query-result update (QRU). The advantage of this technique is that it identifies objects with different levels of significance to the correctness of query results. Locations of objects that have more impact to the query result are acquired more frequently than the ones that do not.     

An approach to process continuous location-dependent queries on moving objects with support for location granules

Location-based services have attracted the attention of important research in the field of mobile computing. Specifically, different mechanisms have been proposed to process location-dependent queries. In the above mentioned context, it is usually assumed that the location data are expressed at a fine geographic precision. However, a different granularity may be more appropriate in certain situations. Thus, a location resolution higher than required may even be inconvenient or not understandable by the user (for example, if the user expects a city name as an answer and instead the system provides the latitude/longitude coordinates). Moreover, if the locations presented to the user need to be refreshed automatically as the objects move, it is obvious that maintaining up-to-date GPS-like geographic coordinates would be more expensive in terms of processing and communication. Unfortunately, the existing approaches assume queries whose locations are always given with maximum precision (i.e., GPS locations).In this paper, a distributed query processing approach that adapts itself to the level of the location resolution required is presented. Thus, it supports continuous location-dependent queries based on the required terminology for the locations, depending on the granularity used (e.g., GPS, cities, states, provinces, or any other predefined geographic area). For the above mentioned purpose, location granules can be defined to specify the semantics appropriate for the queries and/or the way the results should be presented. A prototype showing the functionality and benefits of the approach has been implemented and used in an extensive experimental evaluation. The proposal not only increases the flexibility and expressive power of the queries considerably but also performs efficiently.     

An efficient location reporting and indexing framework for urban road moving objects

The tracking of moving objects consists of two critical operations: location reporting, in which moving objects (or clients) send their locations to centralized servers, and index maintenance, through which centralized servers update the locations of moving objects. In existing location reporting techniques, each moving object reports its locations to servers by utilizing long-distance links such as 3G/4G. Corresponding to this location reporting strategy, servers need to respond to all the location updating requests from individual moving objects. Such techniques suffer from very high communication cost (due to the individual reporting using long-distance links) and high index update I/Os (due to the massive amount of location updating requests). In this paper, we present a novel Group-movement based location Reporting and Indexing (GRI) framework for location reporting (at moving object side) and index maintenance (at server side). In the GRI framework, we introduce a novel location reporting strategy which allows moving objects to report their locations to servers in a group (instead of individually) by aggregating the moving objects that share similar movement patterns through wireless local links (such as WiFi). At the server side, we present a dual-index, Hash-GTPR-tree (H-GTPR), to index objects sharing similar movement patterns. Our experimental results on synthetic and real data sets demonstrate the effectiveness and efficiency of our new GRI framework, as well as the location reporting strategy and the H-GTPR tree index technique.     

基于道路网络的移动对象聚类

现有的基于道路网络对象聚类算法eb-cls采用网络距离描述移动对象间的相似性,没有充分利用对象的时间和空间属性,造成算法不能体现移动对象动态演化的移动模式,频繁更新聚类结果并且聚类精度不理想,执行效率低等问题。针对这些不足,提出基于道路网络的移动对象聚类算法MOBORN（Moving Objects Based on Road Network）,该算法引入时空相似系数,考虑了移动对象速度、方向和位置。当移动对象间的时空相似系数达到给定阈值,将其分到同一聚类,并动态维护聚类结果,减少聚类次数。实验结果证明,与eb-cls算法相比,该算法聚类精度保持在97%以上,运行效率提高了40%。     

A method of real-time recognition of moving objects and its application

A simple method of real-time recognition of moving objects, as well as its theoretical basis are described. This method utilizes a TV camera to pick up image signals from an object moving in the horizontal scan direction. The shape and position of the object are detected at every vertical scanning period by using the information from a few window-like image portions each consisting of four sub-areas. This method is succesfully applied as an electronic eye to a bolting robot used for concrete pile/pole manufacture.     

基于HBase的支持频繁更新与多用户并发的R树

基于位置服务的应用已经进入大数据时代,传统基于位置服务的技术面临系统扩展性、性能等方面的挑战。云计算技术是大数据处理的基础,索引是优化查询的重要手段。尽管目前已存在大量的研究成果,但尚未有HBase上的支持频繁更新与多用户并发的R树索引。针对移动对象索引的频繁更新与多用户并发的需求,文中提出了基于HBase的支持频繁更新与多用户并发的R树索引,它只索引包含移动对象的网格,避免了频繁更新问题;进一步基于HBase的数据行与数据分区的组织与读写特性,对R树的节点进行重组,并对网格Z-order编码,从而减少了对HBase的读写操作,提高了查询效率;最后提出了基于ZooKeeper分布式读写锁的优化策略,提高了索引的吞吐量。实验结果表明,与网格索引相比,在数据非均匀的情况下,所提策略的查询吞吐量提高了25%～50%,更新吞吐量约在同一数量级;与分布式共享锁索引相比,分布式读写锁索引的吞吐量提高了近40%。     

An efficient data processing framework for mining the massive trajectory of moving objects

Recently, there has been increasing development of positioning technology, which enables us to collect large scale trajectory data for moving objects. Efficient processing and analysis of massive trajectory data has thus become an emerging and challenging task for both researchers and practitioners. Therefore, in this paper, we propose an efficient data processing framework for mining massive trajectory data. This framework includes three modules: (1) a data distribution module, (2) a data transformation module, and (3) a high performance I/O module. Specifically, we first design a two-step consistent hashing algorithm, which takes into account load balancing, data locality, and scalability, for a data distribution module. In the data transformation module, we present a parallel strategy of a linear referencing algorithm with reduced subtask coupling, easy-implemented parallelization, and low communication cost. Moreover, we propose a compression-aware I/O module to improve the processing efficiency. Finally, we conduct a comprehensive performance evaluation on a synthetic dataset (1.114 TB) and a real world taxi GPS dataset (578 GB). The experimental results demonstrate the advantages of our proposed framework.     

An efficient method for privacy preserving location queries

Recently, the issue of privacy preserving location queries has attracted much research. However, there are few works focusing on the tradeoff between location privacy preservation and location query information collection. To tackle this kind of tradeoff, we propose the privacy persevering location query (PLQ), an efficient privacy preserving location query processing framework. This framework can enable the location-based query without revealing user location information. The framework can also facilitate location-based service providers to collect some information about the location based query, which is useful in practice. PLQ consists of three key components, namely, the location anonymizer at the client side, the privacy query processor at the server side, and an additional trusted third party connecting the client and server. The location anonymizer blurs the user location into a cloaked area based on a map-hierarchy. The map-hierarchy contains accurate regions that are partitioned according to real landforms. The privacy query processor deals with the requested nearest-neighbor (NN) location based query. A new convex hull of polygon (CHP) algorithm is proposed for nearest-neighbor queries using a polygon cloaked area. The experimental results show that our algorithms can efficiently process location based queries.     

Location-based measurement and visualization for interdependence network on construction sites

Appropriately assigning workers to tasks is vitally important in project management. To do this, project managers need to objectively and effectively measure and visualize the spatiotemporal orders of real construction process as well as coordination structure of the workforce. However, currently there is no method/tool available to project managers to represent spatiotemporal orders of construction processes. To address this issue, this paper presents a novel approach to measuring the real spatiotemporal order of onsite tasks as well as the task interdependence by an interdependence network. This approach extracts the distance of workspace distributions as a key interdependence indicator from historical location tracks across different construction stages according to the area-restricted nature of construction activities. It then integrates generated interdependence into a network over time, to imply the cooperation patterns in stages and a task delivery across stages with a holistic view. To validate the approach, location data were collected from 31 workers working in a high-rise housing construction project for one week to construct the interdependence network of this project, which was used to quantitatively evaluate the performance of construction schedule, assignments and cooperation. Results show that the interdependence network is able to provide insightful information on how workers perform individual tasks onsite and it is also an effective tool to identify and display the interactions among site workers.     

A novel directional object detection method for piled objects using a hybrid region-based convolutional neural network

Digital transformation is an information technology (IT) process that integrates digital information with operating processes. Its introduction to the workplace can promote the development of progressively efficient manufacturing processes, accelerating competition in terms of speed and production capacity. Equipment combined with computer vision has begun to replace manpower in certain industries including manufacturing. However, current object detection methods are unable to identify the actual rotation angle of a specific grasped target while objects are piled. Hence this study proposes a framework based on deep learning that integrates two object detection models. Faster R-CNN (region based convolutional neural network) is utilized to search for the direction reference point of the target, and Mask R-CNN is adopted to obtain the segmentation that not only forms the basis of an area filter but also generates a rotated bounding box by minAreaRect function. After integrating the output from two models, the location and actual rotated angle of target can be obtained. The purpose of this research is to provide the robot arm with the position and angle information of the object located on the top for grasping. An empirical dataset of piled footwear insoles was employed to test the proposed method during the assembly process. Results show that the accuracy of the detection reached 96.26%. The implementation of proposed method in the manufacturing process not only can save man power who responsible for sorting out products but also reduce process time to enlarge production capacity. The proposed method can serve as a part of smart manufacturing system to enhance the enterprise’s competitiveness in the future.     

The caging configuration design and optimization for planar moving objects using multi-fingered mechanism

Due to the larger number of fingers, and the relative motion between object and fingers, the moving object caging using multi-fingered mechanism is complicated and difficulty. In this paper, a novel algorithm for planar moving objects caging configuration design and optimization using multi-fingered mechanism is proposed. In the proposed algorithm: (1) the lead finger is chosen and controlled to track the caging point nearby the moving object; (2) possible configurations of following fingers are determined according to interconnections of the multi-fingered mechanism; (3) the caging condition is applied to choose effective caging configurations. Compared to existing methods, advantages of the proposed method lie on the simple task mode – ‘leader-follower mode’ and low calculation burden. In addition, considering caging is a loose closure strategy with a certain margin, the caging margin, which is the space between the multi-fingered mechanism and the moving target, is introduced and quantified. Moreover, the caging configurations are optimized to maximize the caging margin to provide maximum local freedom for the object. For verifying the efficiency of the proposed method, it is applied in the rectangular and regular pentagonal shaped moving objects caging problems, and the simulation results illustrate the validity of the proposed algorithm.     

An efficient algorithm for electromagnetic scattering by a set of perfect conducting cylindrical objects using the artificial neural network

In this article an efficient algorithm based on the wave concept iterative process is formulated and applied in order to investigate the electromagnetic scattering by a set of conducting arbitrarily shaped objects placed in the free space. In this approach, the cylindrical coordinates system is used as a modal base in order to develop the modal coefficients of the diffraction operator. This operator models the reaction of the environment expressing the electromagnetic coupling between each two pixels of the discretized surface. A study of electromagnetic coupling between two pixels positioned and oriented somehow in the free space is highlighted so as to determine the coupling operator for different positions and orientations of the emitted and received waves. Twelve coupling operators are developed. For a complex geometric shape structure, the determination of these characteristics involved the determination of interactions between each pixel and the others that constitute the discretized surface. This interaction involves the wave formulation already highlighted for each couple of pixels which implies a higher calculation time. In order to optimize the calculation time, the artificial neural networks are adopted with the feed‐forward architecture. The supervised learning has been chosen with the use of the resilient backpropagation algorithm.     

An efficient data-centric storage method using time parameter for sensor networks

In wireless sensor networks, various schemes have been proposed to efficiently store and process sensed data. Among them, the data-centric storage (DCS) scheme is one of the most well-known. The DCS scheme distributes data regions and stores the data in the sensor that is responsible for the region. The DCS based scheme was proposed to reduce the communication cost for transmitting data and to efficiently process exact queries and range queries. Recently, a KDDCS scheme was proposed to overcome storage hot-spots by dynamically readjusting the distributed data regions to sensors based on the K-D tree. However, the existing DCS based schemes including KDDCS suffer from query hot-spots that are formed when query regions are not uniformly distributed. As a result, it reduces the lifetime of the sensor network.In this paper, we propose a new DCS based scheme, called Time-Parameterized Data-Centric Storage (TPDCS), that avoids the problems of storage hot-spots and query hot-spots. To decentralize the skewed data and queries, the data regions are assigned by a time dimension as well as data dimensions in our proposed scheme. Therefore, TPDCS extends the lifetime of sensor networks. It is shown through various experiments that our scheme outperforms the existing schemes.     

An optimization model for reverse logistics network under stochastic environment by using genetic algorithm

Recovery of used products has become increasingly important recently due to economic reasons and growing environmental or legislative concern. Product recovery, which comprises reuse, remanufacturing and materials recycling, requires an efficient reverse logistic network. One of the main characteristics of reverse logistics network problem is uncertainty that further amplifies the complexity of the problem. The degree of uncertainty in terms of the capacities, demands and quantity of products exists in reverse logistics parameters. With consideration of the factors noted above, this paper proposes a probabilistic mixed integer linear programming model for the design of a reverse logistics network. This probabilistic model is first converted into an equivalent deterministic model. In this paper we proposed multi-product, multi-stage reverse logistics network problem for the return products to determine not only the subsets of disassembly centers and processing centers to be opened, but also the transportation strategy that will satisfy demand imposed by manufacturing centers and recycling centers with minimum fixed opening cost and total shipping cost. Then, we propose priority based genetic algorithm to find reverse logistics network to satisfy the demand imposed by manufacturing centers and recycling centers with minimum total cost under uncertainty condition. Finally, we apply the proposed model to a numerical example.     

An efficient method for tracking failure detection using parallel correlation filtering and Siamese network

Applied Intelligence - In recent years, object tracking based on Siamese network has attracted the attention by taking advantage of both speed and accuracy. However, when similar object...     

An efficient and robust design optimisation of multi-state flow network for multiple commodities using generalised reliability evaluation algorithm and edge reduction method

The network of delivering commodities has been an important design problem in our daily lives and many transportation applications. The reliability of delivering commodities from a source node to a sink node in the network is maximised to find the optimal routing. However, the design problem is not simple due to randomly distributed attributes in each path, multiple commodities with variable path capacities and the allowable time constraints for delivery. This paper presents the design optimisation of the multi-state flow network (MSFN) for multiple commodities. We propose an efficient and robust approach to evaluate the system reliability in the MSFN with respect to randomly distributed path attributes and to find the optimal routing subject to the allowable time constraints. The delivery rates of the path segments are evaluated and the minimal-speed arcs are eliminated to reduce the complexity of the MSFN. Accordingly, the correct optimal routing is found and the worst-case reliability is evaluated. The reliability of the optimal routing is at least higher than worst-case measure. Three benchmark examples are utilised to demonstrate the proposed method. The comparisons between the original and the reduced networks show that the proposed method is very efficient.     

An intelligent hierarchical residual attention learning-based conjoined twin neural network for Alzheimer's stage detection and prediction

Alzheimer's disorder (AD) causes permanent impairment in the brain's memory of the cellular system, leading to the initiation of dementia. Earlier detection of Alzheimer's disease in the initial stages is challenging for researchers. Deep learning and machine learning-based techniques can help resolve many issues associated with brain imaging exploration. Brain MR Images (Brain-MRI) are used to detect Alzheimer's in computable research work. To correctly categorize the stages of Alzheimer's disease, discriminative features need to be extracted from the MR images. Recently, many studies have used deep learning methods for the early detection of this disorder. However, overfitting degrades the deep learning method's performance because the dataset's selection images are smaller and imbalanced. Some studies could not reach more discriminative and effectual attention-aware features for Alzheimer's stage classification to increase the model performance. In this paper, we develop a novel hierarchical residual attention learning-inspired multistage conjoined twin network (HRAL-CTNN) to classify the stages of Alzheimer's. We used augmentation approaches to scale insufficient and imbalanced data. The HRAL-CTNN is efficiently overcoming the issues of not obtaining efficient attention-aware and generative features for Alzheimer's stage classification. The proposed model solved the problem of redundant features by extracting attentive discriminant features, and scaling imbalance data by data augmentation, after that training and validation using HRAL-CTNN. The execution of this proposed work has been performed on the ADNI MRI dataset. This work achieved outstanding accuracy of 99.97 $\pm$ 0.01% and F1 score of 99.30 $\pm$ 0.02% for Alzheimer's stage classification. This model proposed by our group outperformed the existing related studies in terms of the model's performance score.