A Deep Web Query Interfaces Classification Method Based on RBF Neural Network

This paper proposes a new approach for classification for query interfaces of Deep Web, which extracts features from the form＇s text data on the query interfaces, assisted with the synonym library, and uses radial basic function neural network （RBFNN） algorithm to classify the query interfaces. The applied RBFNN is a kind of effective feed-forward artificial neural network, which has a simple networking structure but features with strength of excellent nonlinear approximation, fast convergence and global convergence. A TEL_8 query interfaces＇ data set from UIUC on-line database is used in our experiments, which consists of 477 query interfaces in 8 typical domains. Experimental results proved that the proposed approach can efficiently classify the query interfaces with an accuracy of 95.67%.

Deep Q-Learning Based Optimal Query Routing Approach for Unstructured P2P Network

Deep Reinforcement Learning(DRL)is a class of Machine Learning(ML)that combines Deep Learning with Reinforcement Learning and provides a framework by which a system can learn from its previous actions in an environment to select its efforts in the future efficiently.DRL has been used in many application fields,including games,robots,networks,etc.for creating autonomous systems that improve themselves with experience.It is well acknowledged that DRL is well suited to solve optimization problems in distributed systems in general and network routing especially.Therefore,a novel query routing approach called Deep Reinforcement Learning based Route Selection(DRLRS)is proposed for unstructured P2P networks based on a Deep Q-Learning algorithm.The main objective of this approach is to achieve better retrieval effectiveness with reduced searching cost by less number of connected peers,exchangedmessages,and reduced time.The simulation results shows a significantly improve searching a resource with compression to k-Random Walker and Directed BFS.Here,retrieval effectiveness,search cost in terms of connected peers,and average overhead are 1.28,106,149,respectively.

SNS model for providing social network channels through queries

Users can obtain the information through a basic web searching and find the answer to the questions directly,but maybe the expected answer does not exist.Besides,we do not know the update of new information in time.The online social networking services spread quickly and store many user data,but these data are worth less and may be unreliable answer to users’ questions.Users can obtain the simple answer but can not expect more additional information in knowledge question-answering(QA)system.In this paper,we design the system with the advantages of knowledge QA system,web searching and characteristics of social networking service for providing social network channel based on the query and answer without users’ contact network.The user can obtain real-time answers by the user network interested in users’ querires through the network channel of this system,get the additional information effectively and share it with others in the social network channel in this system.

Deep Neural Network and Pseudo Relevance Feedback Based Query Expansion

The neural network has attracted researchers immensely in the last couple of years due to its wide applications in various areas such as Data mining,Natural language processing,Image processing,and Information retrieval etc.Word embedding has been applied by many researchers for Information retrieval tasks.In this paper word embedding-based skip-gram model has been developed for the query expansion task.Vocabulary terms are obtained from the top“k”initially retrieved documents using the Pseudo relevance feedback model and then they are trained using the skip-gram model to find the expansion terms for the user query.The performance of the model based on mean average precision is 0.3176.The proposed model compares with other existing models.An improvement of 6.61%,6.93%,and 9.07%on MAP value is observed compare to the Original query,BM25 model,and query expansion with the Chi-Square model respectively.The proposed model also retrieves 84,25,and 81 additional relevant documents compare to the original query,query expansion with Chi-Square model,and BM25 model respectively and thus improves the recall value also.The per query analysis reveals that the proposed model performs well in 30,36,and 30 queries compare to the original query,query expansion with Chi-square model,and BM25 model respectively.

Efficient Pr-Skyline Query Processing and Optimization in Wireless Sensor Networks

As one of the commonly used queries in modern databases, skyline query has received extensive attention from database research community. The uncertainty of the data in wireless sensor networks makes the corresponding skyline uncertain and not unique. This paper investigates the Pr-Skyline problem, i.e., how to compute the skyline with the highest existence probability in a computational and energy-efficient way. We formulate the problem and prove that it is NP-Complete and cannot be approximated in a given expression. However, the proposed algorithm SKY-SEARCH with pruning techniques can guarantee the computational efficiency given relatively large input size, while the filter-based distributed optimization strategy significantly reduces the transmission cost and the required storage space of the sensor nodes. Extensive experiments verify the efficiency and scalability of SKY-SEARCH and the distributed optimizing strategy.

Efficient and power-awareness query over sensor networks

Sensor networks consisted of low-cost, low-power, multifunctional miniature sensor devices have played an important role in our daily life. Light and humidity monitoring, seismic and animal activity detection, environment and habitat monitoring are the most common applications. However, due to the limited power supply, ordinary query methods and algorithms can not be applied on sensor networks. Queries over sensor networks should be power-aware to guarantee the maximum power savings. The minimal power consumption by avoiding the expensive communication of the redundant sensor nodes is concentrated on. A lot of work have been done to reduce the participated nodes, but none of them have considered the overlapping minimum bounded rectangle (MBR) of sensors which make them impossible to reach the optimization solution. The proposed OMSI-tree and OMR algorithm can efficiently solve this problem by executing a given query only on the sensors involved. Experiments show that there is an obvious improvement compared with TinyDB and other spatial index, adopting the proposed schema and algorithm.

Hash-area-based data dissemination protocol in wireless sensor networks

HashQuery,a Hash-area-based data dissemination protocol,was designed in wireless sensor networks. Using a Hash function which uses time as the key,both mobile sinks and sensors can determine the same Hash area. The sensors can send the information about the events that they monitor to the Hash area and the mobile sinks need only to query that area instead of flooding among the whole network,and thus much energy can be saved. In addition,the location of the Hash area changes over time so as to balance the energy consumption in the whole network. Theoretical analysis shows that the proposed protocol can be energy-efficient and simulation studies further show that when there are 5 sources and 5 sinks in the network,it can save at least 50% energy compared with the existing two-tier data dissemination(TTDD) protocol,especially in large-scale wireless sensor networks.

A Fast Method for Shortest-Path Cover Identification in Large Complex Networks

Fast identifying the amount of information that can be gained by measuring a network via shortest-paths is one of the fundamental problem for networks exploration and monitoring.However,the existing methods are time-consuming for even moderate-scale networks.In this paper,we present a method for fast shortest-path cover identification in both exact and approximate scenarios based on the relationship between the identification and the shortest distance queries.The effectiveness of the proposed method is validated through synthetic and real-world networks.The experimental results show that our method is 105 times faster than the existing methods and can solve the shortest-path cover identification in a few seconds for large-scale networks with millions of nodes and edges.

An Energy-Efficient Query Based on Variable Region for Large-Scale Smart Grid

The state-of-the-art query techniques in power grid monitoring systems focus on querying history data, which typically introduces an unwanted lag when the systems try to discover emergency situations. The monitoring data of large-scale smart grids are massive, dynamic and highly dimensional, so global query, the method widely adopted in continuous queries in Wireless Sensor Networks(WSN), is rendered not suitable for its high energy consumption. The situation is even worse with increasing application complexity. We propose an energy-efficient query technique for large-scale smart grids based on variable regions. This method can query an arbitrary region based on variable physical windows, and optimizes data retrieve paths by a key nodes selection strategy. According to the characteristics of sensing data, we introduce an efficient filter into the each query subtree to keep non-skyline data from being retrieved. Experimental results show that our method can efficiently return the overview situation of any query region. Compared to TAG and ESA, the average query efficiency of our approach is improved by 79% and 46%, respectively; the total energy consumption of regional query is decreased by 82% and 50%, respectively.

A Method for Calculating the Association Degrees between Concepts of Concept Networks

Depicting the associating degrees between two concepts and their relationships are major works for constructing a multi-relationship fuzzy concept network. This paper indicates some drawbacks of the existing methods of calculating associating degrees between concepts, and proposes a new method for overcoming these drawbacks. We also use some examples to compare the proposed method with the existing methods for calculating the associating degrees between two concepts in a multi-relationship fuzzy concept networks.

Bitmap lattice index in road networks

A novel technique called the bitmap lattice index(BLI) is proposed, which combines the advantages of a wireless broadcasting environment with a road network. Existing road networks are based on the on-demand method: a server's workload increases as the query request increases when a server sends a client information. To solve this problem, we propose the BLI. The BLI denotes an object and a node as 0 and 1 in the Hilbert curve(HC) map. The BLI can identify the position of a node and an object through bit information; it can also reduce the broadcasting frequency of a server by reducing the size of the index, thereby decreasing the access latency and query processing times. Moreover, the BLI is highly effective for data filtering, as it can identify the positions of both an object and a node. In a road network, if filtering is done via the Euclidean distance, it may result in an error. To prevent this, we add another validation procedure. The experiment is conducted by applying the BLI to kNN query, and the technique is assessed by a performance evaluation experiment.

Web Page Recommendation Using Distributional Recurrent Neural Network

In the data retrieval process of the Data recommendation system,the matching prediction and similarity identification take place a major role in the ontology.In that,there are several methods to improve the retrieving process with improved accuracy and to reduce the searching time.Since,in the data recommendation system,this type of data searching becomes complex to search for the best matching for given query data and fails in the accuracy of the query recommendation process.To improve the performance of data validation,this paper proposed a novel model of data similarity estimation and clustering method to retrieve the relevant data with the best matching in the big data processing.In this paper advanced model of the Logarithmic Directionality Texture Pattern(LDTP)method with a Metaheuristic Pattern Searching(MPS)system was used to estimate the similarity between the query data in the entire database.The overall work was implemented for the application of the data recommendation process.These are all indexed and grouped as a cluster to form a paged format of database structure which can reduce the computation time while at the searching period.Also,with the help of a neural network,the relevancies of feature attributes in the database are predicted,and the matching index was sorted to provide the recommended data for given query data.This was achieved by using the Distributional Recurrent Neural Network(DRNN).This is an enhanced model of Neural Network technology to find the relevancy based on the correlation factor of the feature set.The training process of the DRNN classifier was carried out by estimating the correlation factor of the attributes of the dataset.These are formed as clusters and paged with proper indexing based on the MPS parameter of similarity metric.The overall performance of the proposed work can be evaluated by varying the size of the training database by 60%,70%,and 80%.The parameters that are considered for performance analysis are Precision,Recall,F1-score and the accuracy of data retrieval,the query recommendation output,and comparison with other state-of-art methods.

Causal Analysis of User Search Query Intent

We investigated the application of Causal Bayesian Networks (CBNs) to large data sets in order to predict user intent via internet search prediction. Here, sample data are taken from search engine logs (Excite, Altavista, and Alltheweb). These logs are parsed and sorted in order to create a data structure that was used to build a CBN. This network is used to predict the next term or terms that the user may be about to search (type). We looked at the application of CBNs, compared with Naive Bays and Bays Net classifiers on very large datasets. To simulate our proposed results, we took a small sample of search data logs to predict intentional query typing. Additionally, problems that arise with the use of such a data structure are addressed individually along with the solutions used and their prediction accuracy and sensitivity.

A Location-Based Content Search Approach in Hybrid Delay Tolerant Networks

In Delay Tolerant Networks （DTNs）, the offiine users can, through the encountering nodes, use the specific peer-to-peer message routing approach to deliver messages to the destination. Thus, it solves the problem that users have the demands to deliver messages while they are temporarily not able to connect to the Internet. Therefore, by the characteristics of DTNs, people who are not online can still query some location based information, with the help of users using the same service in the nearby area. In this paper, we proposed a location-based content search approach. Based on the concept of three-tier area and hybrid node types, we presented four strategies to solve the query problem, namely, Data Replication, Query Replication, Data Reply, and Data Synchronization strategies. Especially we proposed a Message Queue Selection algorithm for message transferring. The priority concept is set associated with every message such that the most ＂important＂ one could be sent first. In this way, it can increase the query success ratio and reduce the query delay time. Finally, we evaluated our approach, and compared with other routing schemes. The simulation results showed that our proposed approach had better query efficiency and shorter delay.

基于差分隐私的路网环境skyline查询

路网中的skyline查询在智慧交通、兴趣点发现和位置服务等领域具有重要的应用价值,但存在查询效率较低、未考虑查询结果的隐私性等问题。有鉴于此,文中提出了一种基于差分隐私的路网环境下skyline查询方法。首先,针对路网环境下的初始数据集数据量大和数据复杂的特点,对数据集进行预处理,利用基于距离属性划分的skyline层和路网Voronoi图的性质提出了3个剪枝规则,基于剪枝规则给出了路网环境下的数据集剪枝算法,从而有效地过滤掉大量冗余数据;其次,针对过滤后的数据集,利用网格索引的存储方式来节省存储空间,并设计了基于网格索引的skyline扩展树,基于扩展树和相应的剪枝规则提出了查询全局候选skyline点集的算法;最后,针对查询结果集,利用差分隐私预算分配模型来分配隐私预算,并基于信息散度进行结果集发布,有效提高了数据信息的隐私性。实验结果表明:所提出的查询方法的准确率在99%以上;其在数据集规模较大情况下的查询效率相较于传统skyline查询方法提升10%以上;在总差分隐私预算为0.01、0.10、0.50和1.00时,所提出的隐私预算分配方法的相对误差均低于等差分配和等比分配方法。

集合空间关键字内聚组查询方法

给定一个道路网络和社交网络,集合空间关键字查询的目的是找到一组兴趣点,该组兴趣点的文本信息包含所有查询关键字,与查询的位置较近且彼此之间的距离较小。内聚组查询的目的是找到在地理位置和社交关系上紧密联系的一组用户;而集合空间关键字内聚组查询的目的是找到满足查询要求的一对最佳匹配的兴趣点集合和用户集合。针对这一问题,提出一种新的集合空间关键字内聚组查询处理模式。首先通过快速贪心查询过程获得候选兴趣点集合,然后使用core-tree结构存储(k,c)-core核心分解的结果,从而提高内聚组查询效率,并且保证查询结果能够同时满足用户之间的社会关系约束和兴趣点之间的空间位置约束。通过在真实数据集上开展实验,结果表明提出的方法比枚举方法的查询效率快1~2个数量级,并且具有较高查询准确性。

基于TreeLSTM的查询基数估计

针对传统的数据库管理系统无法很好地学习谓词之间的交互以及无法准确地估计复杂查询的基数问题,提出了一种树形结构的长短期记忆神经网络(Tree Long Short Term Memory, TreeLSTM)模型建模查询,并使用该模型对新的查询基数进行估计.所提出的模型考虑了查询语句中包含的合取和析取运算,根据谓词之间的操作符类型将子表达式构建为树形结构,根据组合子表达式向量来表示连续向量空间中的任意逻辑表达式.TreeLSTM模型通过捕捉查询谓词之间的顺序依赖关系从而提升基数估计的性能和准确度,将TreeLSTM与基于直方图方法、基于学习的MSCN和TreeRNN方法进行了比较.实验结果表明:TreeLSTM的估算误差比直方图、MSCN、TreeRNN方法的误差分别降低了60.41%,33.33%和11.57%,该方法显著提高了基数估计器的性能.

基于依存关系图注意力网络的SQL生成方法

研究基于自然语言问题的结构化查询语言(SQL)生成问题(Text-to-SQL).提出两阶段框架,旨在解耦模式链接和SQL生成过程,降低SQL生成的难度.第1阶段通过基于关系图注意力网络的模式链接器识别问题中提及的数据库表、列和值,利用问题的语法结构和数据库模式项之间的内部关系,指导模型学习问题与数据库的对齐关系.构建问题图时,针对Text-to-SQL任务的特点,在原始句法依存树的基础上,合并与模式链接无关的关系,添加并列结构中的从属词与句中其他成分间的依存关系,帮助模型捕获长距离依赖关系.第2阶段进行SQL生成,将对齐信息注入T5的编码器,对T5进行微调.在Spider、Spider-DK和Spider-Syn数据集上进行实验,实验结果显示,该方法具有良好的性能,尤其是对中等难度以上的Text-to-SQL问题具有良好的表现.

基于TCN-A模型的高效查询负载预测算法

针对大数据查询领域中出现的由于查询负载随时间动态变化且难以有效预测所导致的数据库管理系统无法及时优化的问题,提出了一种基于新型时间序列预测模型的查询负载预测算法。首先,该算法采用过滤、时域间隔划分以及查询负载构造等技术对原始的历史用户查询进行预处理,得到便于网络模型分析处理的查询负载序列。其次,所提算法以时间卷积神经网络为核心构建时序预测模型,提取查询负载数据的历史变化趋势及自相关性特征,高效地实现时序预测;同时,融入设计的时域注意力机制,对查询负载序列进行重要性加权,保证模型的分析计算效率,提升算法的预测性能。最后,基于上述时序预测模型,充分利用查询间隔时间完成对未来查询负载的精确预测,使得数据库管理系统得以预先实现自身性能调优,以适应工作负载的动态变化。实验结果表明,设计的查询负载预测算法在多个评价指标中均表现出良好的预测性能,并且能够在查询时间间隔内更加精确地预测未来查询负载的变化。