Relational Query Research Articles

Remembrance of inferences past: Amortization in human hypothesis generation

Bayesian models of cognition assume that people compute probability distributions over hypotheses. However, the required computations are frequently intractable or prohibitively expensive. Since people often encounter many closely related distributions, selective reuse of computations (amortized inference) is a computationally efficient use of the brain’s limited resources. We present three experiments that provide evidence for amortization in human probabilistic reasoning. When sequentially answering two related queries about natural scenes, participants’ responses to the second query systematically depend on the structure of the first query. This influence is sensitive to the content of the queries, only appearing when the queries are related. Using a cognitive load manipulation, we find evidence that people amortize summary statistics of previous inferences, rather than storing the entire distribution. These findings support the view that the brain trades off accuracy and computational cost, to make efficient use of its limited cognitive resources to approximate probabilistic inference.

The North American Forest Database: going beyond national-level forest resource assessment statistics.

Forests cannot be managed sustainably without reliable data to inform decisions. National Forest Inventories (NFI) tend to report national statistics, with sub-national stratification based on domestic ecological classification systems. It is becoming increasingly important to be able to report statistics on ecosystems that span international borders, as global change and globalization expand stakeholders' spheres of concern. The state of a transnational ecosystem can only be properly assessed by examining the entire ecosystem. In global forest resource assessments, it may be useful to break national statistics down by ecosystem, especially for large countries. The Inventory and Monitoring Working Group (IMWG) of the North American Forest Commission (NAFC) has begun developing a harmonized North American Forest Database (NAFD) for managing forest inventory data, enabling consistent, continental-scale forest assessment supporting ecosystem-level reporting and relational queries. The first iteration of the database contains data describing 1.9 billion ha, including 677.5 million ha of forest. Data harmonization is made challenging by the existence of definitions and methodologies tailored to suit national circumstances, emerging from each country's professional forestry development. This paper reports the methods used to synchronize three national forest inventories, starting with a small suite of variables and attributes.

Finding the optimal location and keywords in obstructed and unobstructed space

The problem of optimal location selection based on reverse k nearest neighbor (R $$k$$ NN) queries has been extensively studied in spatial databases. In this work, we present a related query, denoted as a Maximized Bichromatic Reverse Spatial Textual k Nearest Neighbor (MaxST) query, that finds an optimal location and a set of keywords for an object so that the object is a $$k$$ NN object for as many users as possible. Such a query has many practical applications including advertisements, where the query is to find the location and the text contents to include in an advertisement so that it is relevant to the maximum number of users. The visibility of the advertisements also has an important role in the users’ interests. In this work, we address two instances of the spatial relevance when ranking items: (1) the Euclidean distance and (2) the visibility. We carefully design a series of index structures and approaches to answer the MaxST for both instances. Specifically, we present (1) the Grp-topk approach that requires the computation of the top-k objects for all of the users first and then applies various pruning techniques to find the optimal location and keywords; (2) the Indiv-U approach, where we use similarity estimations to avoid computing the top-k objects of the users that cannot be a final result; and (3) the Index-U approach where we propose a hierarchical index structure over the users to improve pruning. We show that the keyword selection component in MaxST queries is NP-hard and present both approximate and exact solutions for the problem.

TriAL

Navigational queries over RDF data are viewed as one of the main applications of graph query languages, and yet the standard model of graph databases—essentially labeled graphs—is different from the triples-based model of RDF. While encodings of RDF databases into graph data exist, we show that even the most natural ones are bound to lose some functionality when used in conjunction with graph query languages. The solution is to work directly with triples, but then many properties taken for granted in the graph database context (e.g., reachability) lose their natural meaning. Our goal is to introduce languages that work directly over triples and are closed, i.e., they produce sets of triples, rather than graphs. Our basic language is called TriAL, or Triple Algebra: it guarantees closure properties by replacing the product with a family of join operations. We extend TriAL with recursion and explain why such an extension is more intricate for triples than for graphs. We present a declarative language, namely a fragment of datalog, capturing the recursive algebra. For both languages, the combined complexity of query evaluation is given by low-degree polynomials. We compare our language with previously studied graph query languages such as adaptations of XPath, regular path queries, and nested regular expressions; many of these languages are subsumed by the recursive triple algebra. We also provide an implementation of recursive TriAL on top of a relational query engine, and we show its usefulness by running a wide array of navigational queries over real-world RDF data, while at the same time testing how our implementation compares to existing RDF systems.

Domain content querying using ontology-based context-awareness in information systems

Ubiquitous computing technologies have been applied in several areas. However, it still presents a number of challenges, both for the full implementation of technologies and for the integration with existing information systems. One of the main mismatches evidenced by recent works is how context-awareness, a widely used capability in ubiquitous computing and actual information systems with relational databases may be integrated to allow ubiquitous and traditional systems to query relational data sources without the necessity to modify the schema of the database. This paper presents an integration model relating context and domain information allowing relational data to be retrieved in context without the necessity to change the originally used relational queries. A set of linking rules and algorithms are formalized in a model and this model is implemented in a prototype. The evaluation of the model is performed by applying it in a case study in a Massive Open Online Course (MOOC) platform. The evaluation of the model by the application of it in a case study in a MOOC platform demonstrated the possibility to use an ontology frequently used in ubiquitous middleware as an extra filtering layer for information systems without the necessity to recreate queries or make a re-engineering in the relational database schema. The results of the queries after the application of the model showed an average decrease of 21% in returned tuples, which was evaluated as a significant reduce in tuple results.

LAILAPS-QSM: A RESTful API and JAVA library for semantic query suggestions.

In order to access and filter content of life-science databases, full text search is a widely applied query interface. But its high flexibility and intuitiveness is paid for with potentially imprecise and incomplete query results. To reduce this drawback, query assistance systems suggest those combinations of keywords with the highest potential to match most of the relevant data records. Widespread approaches are syntactic query corrections that avoid misspelling and support expansion of words by suffixes and prefixes. Synonym expansion approaches apply thesauri, ontologies, and query logs. All need laborious curation and maintenance. Furthermore, access to query logs is in general restricted. Approaches that infer related queries by their query profile like research field, geographic location, co-authorship, affiliation etc. require user’s registration and its public accessibility that contradict privacy concerns. To overcome these drawbacks, we implemented LAILAPS-QSM, a machine learning approach that reconstruct possible linguistic contexts of a given keyword query. The context is referred from the text records that are stored in the databases that are going to be queried or extracted for a general purpose query suggestion from PubMed abstracts and UniProt data. The supplied tool suite enables the pre-processing of these text records and the further computation of customized distributed word vectors. The latter are used to suggest alternative keyword queries. An evaluated of the query suggestion quality was done for plant science use cases. Locally present experts enable a cost-efficient quality assessment in the categories trait, biological entity, taxonomy, affiliation, and metabolic function which has been performed using ontology term similarities. LAILAPS-QSM mean information content similarity for 15 representative queries is 0.70, whereas 34% have a score above 0.80. In comparison, the information content similarity for human expert made query suggestions is 0.90. The software is either available as tool set to build and train dedicated query suggestion services or as already trained general purpose RESTful web service. The service uses open interfaces to be seamless embeddable into database frontends. The JAVA implementation uses highly optimized data structures and streamlined code to provide fast and scalable response for web service calls. The source code of LAILAPS-QSM is available under GNU General Public License version 2 in Bitbucket GIT repository: https://bitbucket.org/ipk_bit_team/bioescorte-suggestion

An infodemiological study using search engine query data to explore the temporal variations of depression in Finland

A majority of healthcare is undertaken by individuals without the involvement or knowledge of healthcare professionals. People often try to treat health problems themselves, often first consulting the Internet, with search engines as natural starting points. Health information seeking conducted in search engines generate big data, data that can provide valuable insights into patterns of symptoms and disease, especially for stigmatizing or sensitive health topics, like mental health problems. The aim of this article is to utilize search engine query data for trends and temporal variations of depression in Finland. The key findings of this study show that depression related Internet search query volumes are slightly increasing during the time periods studied. The results also show that search query volumes follow seasonal patterns with peaks during autumn and spring and troughs during the summer months and mid-winter. Of all weekdays, Sundays have the highest search volume for depression related queries. These results present new meaningful insights into the epidemiology of depression, as it can give insights into the part of the population that does not present for treatment or professional help. It can also help health professionals and other officials to understand broader patterns of mental illness when planning services and campaigns.

A survey of real-time approximate nearest neighbor query over streaming data for fog computing

Real-time approximate nearest neighbor (ANN) query over streaming data in fog computing environment is the fundamental problem of real-time analysis of big data. As the fog computing paradigm needs to provide real-time and low latency services, and traditional streaming data ANN query technology cannot be directly applied. Exploring the basic theory, querying framework and technology of real-time ANN query over streaming data for fog computing becomes one of the current research hotspots. This paper summarizes the related ANN query technology based on random hash, learning-to-hash and synopses, analyzes the problems and challenges of real-time ANN query in resource-limited fog computing environment, and finally discusses in detail the basic theory and method of the query, the dimension reduction and encoding method based on learning-to-hash, the generating synopses method for ANN query over streaming data from Internet of Thing, and the future related research directions of ANN query framework and others. Additionally, we propose a Dynamic Adaptive Quantization (DAQ) method for learning-to-hash. Experiments show that DAQ outperformed other quantization methods.

UPCaD: A Methodology of Integration Between Ontology-Based Context-Awareness Modeling and Relational Domain Data

Context-awareness is a key feature for ubiquitous computing scenarios applications. Currently, technologies and methodologies have been proposed for the integration of context-awareness concepts in intelligent information systems to adapt them to the execution of services, user interfaces and data retrieval. Recent research proposed conceptual modeling alternatives to the integration of the domain modeling in RDBMS and context-awareness modeling. The research described using highly expressiveness ontologies. The present work describes the UPCaD (Unified Process for Integration between Context-Awareness and Domain) methodology, which is composed of formalisms and processes to guide the data integration considering RDBMS and context modeling. The methodology was evaluated in a virtual learning environment application. The evaluation shows the possibility to use a highly expressive context ontology to filter the relational data query and discusses the main contributions of the methodology compared with recent approaches.

Global trends in the awareness of sepsis: insights from search engine data between 2012 and 2017

BackgroundSepsis is an established global health priority with high mortality that can be curtailed through early recognition and intervention; as such, efforts to raise awareness are potentially impactful and increasingly common. We sought to characterize trends in the awareness of sepsis by examining temporal, geographic, and other changes in search engine utilization for sepsis information-seeking online.MethodsUsing time series analyses and mixed descriptive methods, we retrospectively analyzed publicly available global usage data reported by Google Trends (Google, Palo Alto, CA, USA) concerning web searches for the topic of sepsis between 24 June 2012 and 24 June 2017. Google Trends reports aggregated and de-identified usage data for its search products, including interest over time, interest by region, and details concerning the popularity of related queries where applicable. Outlying epochs of search activity were identified using autoregressive integrated moving average modeling with transfer functions. We then identified awareness campaigns and news media coverage that correlated with epochs of significantly heightened search activity.ResultsA second-order autoregressive model with transfer functions was specified following preliminary outlier analysis. Nineteen significant outlying epochs above the modeled baseline were identified in the final analysis that correlated with 14 awareness and news media events. Our model demonstrated that the baseline level of search activity increased in a nonlinear fashion. A recurrent cyclic increase in search volume beginning in 2012 was observed that correlates with World Sepsis Day. Numerous other awareness and media events were correlated with outlying epochs. The average worldwide search volume for sepsis was less than that of influenza, myocardial infarction, and stroke.ConclusionsAnalyzing aggregate search engine utilization data has promise as a mechanism to measure the impact of awareness efforts. Heightened information-seeking about sepsis occurs in close proximity to awareness events and relevant news media coverage. Future work should focus on validating this approach in other contexts and comparing its results to traditional methods of awareness campaign evaluation.

In Search of a Job: Forecasting Employment Growth in the US Using Google Trends

We show that Google search activity on relevant terms is a strong out-of-sample predictor of future employment growth in the US and that it greatly outperforms benchmark predictive models based on macroeconomic, financial, and sentiment variables. Using a subset of ten keywords, we construct a panel with 211 variables using Google’s own algorithms to find related search queries. We use Elastic Net variable selection in combination with Partial Least Squares to extract the most important information from a large set of search terms. Our forecasting model, which can be constructed in real time and is free from revisions, delivers an out-of-sample R^2 statistic of 65% to 88% for horizons between one month and one year ahead over the period 2008-2017, which compares to between roughly 30% and 60% for the benchmark models.

Node Differential Privacy in Social Graph Degree Publishing

Effective analysis of social network dataset has gained attention in various fields. The published dataset is often limited by the privacy of individual user whose data is included in it. Existing anonymization methods to publish the entire dataset or the approaches to release specific results may not provide user privacy. But, the differential privacy (DP) technique provides strong guarantees about the privacy of the participants in a released database. For the social graph data, differential privacy is divided into two parts: edge and node differential privacy. Edge-DP protects the relationship between two nodes represented as an edge whereas node-DP provide privacy to all edges connected to a node. For node-DP, we have proposed projection approach to restrict degree of a node below a certain value, to reduce the sensitivity of user related queries. The existing graph projection techniques lose much useful information. Our proposed projection approach retains more information by accessing node according to their increasing degree value. The degree distribution of social dataset under node-DP is generated to release the information regarding user’s degree.

Синтаксический анализ графов с использованием конъюнктивных грамматик

Graphs are used as a data structure to represent large volumes of information in a compact and convenient for analysis form in many areas: bioinformatics, graph databases, static code analysis, etc. In these areas, it is necessary to evaluate a queries for large graphs in order to determine the dependencies between the nodes. The answer to such queries is usually a set of all triples (A, m, n) for which there is a path in the graph from the vertex m to the vertex n, such that the labels on the edges of this path form a string derivable from the nonterminal A in some context-free grammar. This type of query is calculated using relational query semantics and context-free grammars but there are conjunctive grammars, which form a broader class of grammars than traditional context-free grammars. The use of conjunctive grammars in the path querying allows us to formulate more complex queries to the graph and solve a wider class of problems. It is known that the path querying using relational query semantics and conjunctive grammars is undecidable problem. In this paper, we propose a path querying algorithm which uses relational query semantics and conjunctive grammars, and approximates the exact solution. The proposed algorithm is based on matrix operations, and our evaluation shows that it is possible to significantly improve the performance of the algorithm by using a graphics processing unit.

Relational calculi in a deductive system

This work describes the addition of relational calculus languages in the deductive database system DES. Based on first-order logic, such languages admit a clean logical reading of queries, providing truly declarativeness, in contrast to other languages based on logic such as Prolog (a classical language used to build expert systems). Interesting properties as termination (for finite relations) and recursion are ensured because the DES deductive engine is used for solving relational calculus queries. Recursion in particular opens a brand new ream of applications (social networks, data warehouses, ...) for relational calculus languages which were unmanageable up to now. Since the DES system was targeted at teaching, we have also make a special emphasis on providing a practical system for students by providing appropriate syntax error feedback in a system supporting different languages (including relational algebra, SQL and Datalog).

Automating Characterization Deployment in Distributed Data Stream Management Systems

Distributed data stream management systems (DDSMS) are usually composed of upper layer relational query systems (RQS) and lower layer stream processing systems (SPS). When users submit new queries to RQS, a query planner needs to be converted into a directed acyclic graph (DAG) consisting of tasks which are running on SPS. Based on different query requests and data stream properties, SPS need to configure different deployments strategies. However, how to dynamically predict deployment configurations of SPS to ensure the processing throughput and low resource usage is a great challenge. This article presents OrientStream, a framework for automating characterization deployment in DDSMS using incremental machine learning techniques. By introducing the data-level, query plan-level, operator-level, and cluster-level’s four-level feature extraction mechanism, we first use the different query workloads as training sets to predict the resource usage by DDSMS, and select the optimal resource configuration from candidate settings based on the current query requests and stream properties, then migrate the operator state by introducing dynamic reconfiguration. Finally, we validate our approach on the open source SPS–Storm. In view of the application scenarios with long monitoring cycle and non-frequent data fluctuation, experiments show that OrientStream can reduce CPU usage of 8-15 percent and memory usage of 38-48 percent, respectively.

A Novel Auction-Based Query Pricing Schema

As a common processing method, query is widely used in many areas, such as graph processing, machine learning, statistics. However, queries are usually priced according to vendor-specified fixed views (API) or number of transactions, which ignores query heterogeneity(computing resource consumption for query and information that the answer brings) and violates the microeconomic principles. In this work we study the relational query pricing problem and design efficient auctions by taking into account both information (i.e., data) value and query resource consumption. Different from the existing query pricing schemes, query auction determines data prices that reflect the demand–supply of shared computing resources and information value (i.e., price discovery). We target query auction that runs in polynomial time and achieves near-optimal social welfare with a good approximation ratio, while elicits truthful bids from consumers. Towards these goals, we adapt the posted pricing framework in game-theoretic perspective by casting the query auction design into an Integer Linear Programming problem, and design a primal-dual algorithm to approximate the NP-hard optimization problem. Theoretical analysis and empirical studies driven by a real-world data market benchmark verify the efficiency of our query auction schema.

Correctness of SQL Queries on Databases with Nulls

Multiple issues with SQL's handling of nulls have been well documented. Having efficiency as its main goal, SQL disregards the standard notion of correctness on incomplete databases -- certain answers -- due to its high complexity. As a result, the evaluation of SQL queries on databases with nulls may produce answers that are just plain wrong. However, SQL evaluation can be modified, at least for relational algebra queries, to approximate certain answers, i.e., return only correct answers. We examine recently proposed approximation schemes for certain answers and analyze their complexity, both theoretical bounds and real-life behavior

A framework for recommending health-related topics based on topic modeling in conversational data (Twitter)

Social media is an environment where it enables the user’s to create and share content or participate in all social networking activities; it has given rise to information overloading problem and knowledge starvation. Generally, in large conversational dataset like Twitter it is very difficult to identifying public health-related topics. Machine learning is the area which helps us to overcome this situation. By applying probabilistic unsupervised machine learning we have identified latent topics from the text corpora. Topic modeling algorithms are probabilistic generative models which is used to analyze the words of the original texts to identify themes that run through them, how connected to each other by themes, and how the topics change over (Blei in Commun ACM 55(4):77–84, 2012). In this paper we have proposed a framework for recommending health-related topics by applying an enhanced topic model hierarchical latent Dirichlet allocation for identifying public health-related topics and themes in tweets. We have tested our model by exploring tobacco usage across conversational data, as well as tested with the subset of data generated by tobacco related queries. Our test results indicate most of the public health related issues are uncovered in our model. However, this model provides relevant topic across the tobacco subset.

No-but-semantic-match: computing semantically matched xml keyword search results

Users are rarely familiar with the content of a data source they are querying, and therefore cannot avoid using keywords that do not exist in the data source. Traditional systems may respond with an empty result, causing dissatisfaction, while the data source in effect holds semantically related content. In this paper we study this no-but-semantic-match problem on XML keyword search and propose a solution which enables us to present the top-k semantically related results to the user. Our solution involves two steps: (a) extracting semantically related candidate queries from the original query and (b) processing candidate queries and retrieving the top-k semantically related results. Candidate queries are generated by replacement of non-mapped keywords with candidate keywords obtained from an ontological knowledge base. Candidate results are scored using their cohesiveness and their similarity to the original query. Since the number of queries to process can be large, with each result having to be analyzed, we propose pruning techniques to retrieve the top-k results efficiently. We develop two query processing algorithms based on our pruning techniques. Further, we exploit a property of the candidate queries to propose a technique for processing multiple queries in batch, which improves the performance substantially. Extensive experiments on two real datasets verify the effectiveness and efficiency of the proposed approaches.

Improved continuous query plan with cluster weighted dominant querying in synthetic datasets

The arrival of large voluminous continuous queries sets for a given query leads an insignificant insights. The elimination of certain data tuples occurs in order to balance the system load. The streaming query removes the improper data tuples and uses proper data tuples in the form of defined tables or sets. However, major drawback occurs due to unbounded streaming and inadequate access to end data. Due to such constraints, many stream processing methods makes the processed data unavailable for any applications or to the related queries of neighborhood branches. This paper avoids such problems during the process of data tuples at the generation of queries. The study uses a streaming model that executes effective query plans in continuous data. The streaming model aims reduce the communication cost and improves the scalability of continuous aggregation queries. It sub-divides the client query and executes it over data aggregators within the incoherent limit. A weighted dominant query algorithm is formulated to provide the top dominant value in each sub-query clusters. This reduces the cost for computation in synthetic databases. The experimental results proved that the proposed model with weighted dominant query algorithm effectively improves scalability by reducing the computational cost.