Search

Unimodal biometric systems are susceptible to a variety of problems such as noisy data, intra-class variations, limited degrees of freedom, non-universality, spoof attacks and unacceptable error rates. Some of these limitations can be addressed by deploy multimodal biometric systems that integrates the evidence presented by multiple sources of information The proposed system provides effective fusion scheme that combines information presented by the multiple domain experts based on the Rank level fusion integration method, thereby increasing the efficiency of the system which is not possible by the unimodal biometric system. The proposed multimodal biometric system has a number of unique qualities, including principal component analysis and fisher's linear discriminate methods for individual matchers authentication. The novel rank level fusion method is used in order to consolidate the results obtained from different biometric matchers. [ABSTRACT FROM AUTHOR]

Missing Data is of concern in smart manufacturing. There are various reasons why data may be missing. Buffering issues, sensor failure, or protocol issues can cause missing entries or skipped captures. This missing data leads to distorted datasets, failure to train models, and either to disregard, deletion of records or typically to vast manual re-work efforts. This paper shows types of missing data and various approaches to detect them. Replacement or fill-in approaches are presented and their limitations are highlighted. A more precise imputation method beyond the state of the art is explained in detail. The implementation of this physics-informed imputation method was performed and experiments were carried out. The results of the experiments are presented in this paper and the results discussed. [ABSTRACT FROM AUTHOR]

Within the scope of this paper we examine incident detection on inner-city roads using floating car data (FCD) under different traffic conditions and data qualities. We used synthetic FCD to analyze incidents under variable conditions, such as different traffic volumes. They are generated from microscopic traffic flow simulations with the software tool PTV Vissim. Automated processing of the synthetic FCD gained from the microsimulation models also makes it possible to analyze different data qualities resulting from the choice of penetration rate and transmission frequency. We investigated the recognizability of the incidents using five laboratory examples, which depict different traffic incidents, and a real inner-city road in Karlsruhe, Germany. Graphical and quantitative evaluations are used for incident detection, whereby violin plots and the proposed incident indicator have the most reliable detection rate. Incident detection decreases significantly if several incidents overlap, the severity of the incidents or the traffic volume is reduced, the data quality decreases, or if there is no current speed information in the data. For additional insights, we recommend considering the different figures created in the graphical analysis alongside the incident indicator used in the quantitative analysis. [ABSTRACT FROM AUTHOR]

Low quality of data is one of the most critical issues for consumers of data distributed by autonomous sources. The outcomes of non-quality of data, or of poor quality, on decision-making are considerable and have disastrous effects. In this paper, we deal with this problem in the context of biometric applications, specifically those based on the iris modality. In fact, the iris image can be affected by different types of distortion which greatly affect its quality and generate different imperfection forms. Thus, the deterioration of the quality of these images increases the false rejection rate and therefore decreases significantly the performances of iris identification systems. In order to reduce the impact of bad quality of iris image, we add an Image Quality Assessment (IQA) phase to the identification system to reject poor quality images and thus improves system performances. In this paper, a new method based on the possibilistic modeling of imperfect information extracted from the iris images is proposed to assess the iris image quality. The aim of the proposed approach, noted Poss-IIQA, is to handles the different imperfection forms resulting from any type of distortions. As a result, the suggested method key advantage over the baseline system and other earlier approaches, which focuses more on distortions than on imperfections. [ABSTRACT FROM AUTHOR]

Big Data wave has led to a rapid increase in the amount of data being collected by organizations. While the accuracy and reliability of prediction models are often prioritized, the quality of the collected data is frequently overlooked. Poor data quality can result in the common problem of 'garbage in, garbage out'. Traditional measures of data quality, such as accuracy, consistency, completeness, and timeliness, are no longer adequate in the era of Big Data. Therefore, this paper proposes a taxonomy of data quality dimensions specifically for Big Data, addressing emerging challenges by formulating 20 dimensions and categorizing them into four distinct categories. [ABSTRACT FROM AUTHOR]

The Internet of Things (IoT) has emerged as a transformative technology with applications spanning diverse domains, from healthcare to smart cities. Efficient utilization of IoT data is essential for extracting meaningful insights and supporting decision-making processes. This research paper focuses on the critical task of feature extraction from IoT data, with a particular emphasis on the IoT 2023 dataset—a comprehensive and widely-used benchmark dataset in the IoT domain. In this study, exploration and comparison of various feature extraction methods are undertaken to enhance understanding of IoT 2023 dataset characteristics and its potential applications. Traditional statistical techniques, as well as machine learning-based approaches for feature extraction, are investigated. Evaluation of these methods is based on their ability to capture relevant information, reduce dimensionality, and enhance the performance of downstream IoT analytics tasks. Extensive experiments are conducted, and a comprehensive performance analysis is presented to guide the selection of the most suitable feature extraction approach for specific IoT applications. The outcomes of this research contribute to ongoing efforts to harness the potential of IoT data by offering a comprehensive understanding of the impact of feature extraction methods on data quality and predictive accuracy. This aids in paving the way for more informed and effective IoT solutions in 2023 and beyond. [ABSTRACT FROM AUTHOR]

A neural network (NN) is known to be an efficient and learnable tool supporting decision-making processes particularly in Industry 4.0. The majority of NNs are data-driven and, therefore, depend on training data quantity and quality. The current trend in enhancing data-driven models with knowledge-based models promises to enable effective NNs with less data. So-called physics-informed NNs use additional knowledge from computational science to improve NN training. Quite much of the knowledge is available as logical constraints from domain ontologies, and NNs may benefit from using it. In this paper, we study the concept of Taxonomy-Informed NN (TINN), which combines data-driven training of NNs with ontological knowledge. We study different patterns of NN training with additional knowledge on class-subclass hierarchies and instance-class relationships with potential for federated learning. Our experiments show that additional knowledge, which influences TINNs' training process through the loss function at backpropagation, improves the quality of trained models. [ABSTRACT FROM AUTHOR]

In the realm of smart manufacturing, predictive maintenance plays a pivotal role in ensuring equipment reliability, minimizing downtime, optimizing costs, and reducing product failure rate by detecting faulty products in the early stage. However, the efficacy of predictive maintenance hinges on the quality of training data employed for predictive modeling. Inadequate data quality can lead to erroneous predictions and, consequently, ineffective maintenance strategies. This research paper introduces a solution that leverages deep learning and data quality management to enhance predictive maintenance in smart manufacturing. Our proposed methodology encompasses two major components such as data quality management and faulty product detection. Data quality management includes data preprocessing, feature reduction, and data balancing, whereas faulty product detection is done using deep learning techniques. By combining these elements, a predictive model capable of accurately forecasting faulty products in early stages to reduce economic losses is developed. The proposed approach effectively addresses data quality issues and is tested on the SECOM dataset which indicates that it surpasses traditional models with an accuracy of 96.4% and perfect recall. Ultimately, this research contributes to the advancement of predictive maintenance and deep learning in the context of smart manufacturing, benefiting both industrial practitioners and researchers alike. [ABSTRACT FROM AUTHOR]

Pricing and assessing sensory captured data is an essential part of the data economy. In current approaches data are assessed based on individual data quality dimensions describing structured properties of data for downstream analyses. From the domain-specific perspective, an assessment regarding the suitability of data for manufacturing process goals is missing. For this reason, this paper presents a methodology for assessing datasets from the manufacturing perspective using an adapted balanced scorecard. This enables the mapping of manufacturing goals in a single score. The assessment is based on a process model that defines the measurable signals of specific manufacturing processes and represents their interactions. To evaluate the importance of process signals, the number of interactions with quality characteristics is examined. Alternatively, the change in affecting quality characteristics with variation of process signals is determined with a sensitivity analysis. On the application of the methodology, a fictitious dataset of a grinding process is analysed. [ABSTRACT FROM AUTHOR]

In this paper we aim to analyse the adoption of Current Research Information Systems (CRIS) for Research Data Management (RDM). We show how CRISs hold a key role in facilitating the management and reporting of an institution's research activities and outputs – not only do they offer extensive functionality for researchers and research administrators to effectively manage all aspects of their research information, but are also integrating more and more with specialized RDM tools, Institutional Repositories (IR), and other external systems. This paper provides an overview of how CRISs have evolved and integrated to become a crucial part of the RDM chain, including the interoperability, registration, linking, and archiving of data. [ABSTRACT FROM AUTHOR]

The paper focuses on the implementation of new concepts and business models to increase data quality by defining clear rules for real-time error detection in an experimental decision support system (DSS), which helps financial decision-makers to analyse and process useful and business information from raw data, documents, personal knowledge and/or business models in order to identify and solve complex financial problems and to choose the best decisions. [ABSTRACT FROM AUTHOR]

Despite widespread growth in the use and complexity of web portals, insufficient attention is paid to their quality. Thus, this paper aims to describe the validation process of the Brazilian Network of Rare Diseases Portal and identify a set of data quality attributes required for psychometric evaluations that will support the portal implementation. This protocol describes a cross- sectional study of mixed nature divided into three steps: A usability evaluation, a Delphi consensus, and an electronic service quality assessment. Also, the RE-AIM model will be applied at various stages of evaluative research. We hope the improvement carried out during the validation of RARAS can contribute to the dissemination of knowledge in the area and include, based on scientific knowledge and clinical experts, offering clear, attractive, and accessible information for the population. A research gap exists in determining components of integrated e-service quality, usability, and user experience evaluation model in general, and for rare disease web portals, in particular. Users of the RARAS Portal need to get validated content and the required reliable online services without doing exhaustive searches or visiting multiple sources, with the main focus on e-service quality. [ABSTRACT FROM AUTHOR]

The essence of an information system lies in the data; if it is not of good quality or not sufficiently protected, the consequences will undoubtedly be harmful. Quality and Security are two essential aspects that add value to data and their implementation has become a real need and must be adopted before any data exploitation. Due to the high volume of data, their diversity and their rapid generation, effective implementation of such systems requires well thought out mechanisms and strategies. This paper provides an overview of Data Quality and Data Security in a Big Data context. We want through this paper to highlight the conflicts that may exist during the implementation of data security and data quality management systems. Such a conflict makes the complexity greater and requires new adapted solutions. [ABSTRACT FROM AUTHOR]

Consolidation of the research information improves the quality of data integration, reducing duplicates between systems and enabling the required flexibility and scalability when processing various data sources. We assume that the combination of a data lake as a data repository and a data wrangling process should allow low-quality or "bad" data to be identified and eliminated, leaving only high-quality data, referred to as "research information" in the Research Information System (RIS) domain, allowing for the most accurate insights gained on their basis. This, however, would lead to increased value of both the data themselves and data-driven actions contributing to more accurate and aware decision-making. This cleansed research information is then entered into the appropriate target Current Research Information System (CRIS) so that it can be used for further data processing steps. In order to minimize the effort for the analysis, the proliferation and enrichment of large amounts of data and metadata, as well as to achieve far-reaching added value in information retrieval for CRIS employees, developers and end users, this paper outlines the concept of a curated data lake with the data wrangling process, showing how it can be used in CRIS to clean up data from heterogeneous data sources during their collection and integration. [ABSTRACT FROM AUTHOR]

The essence of an information system lies in the data; if it is not of good quality or not sufficiently protected, the consequences will undoubtedly be harmful. Quality and Security are two essential aspects that add value to data and their implementation has become a real need and must be adopted before any data exploitation. Due to the high volume of data, their diversity and their rapid generation, effective implementation of such systems requires well thought out mechanisms and strategies. This paper provides an overview of Data Quality and Data Security in a Big Data context. We want through this paper to highlight the conflicts that may exist during the implementation of data security and data quality management systems. Such a conflict makes the complexity greater and requires new adapted solutions. [ABSTRACT FROM AUTHOR]

Near-real-time monitoring and classification of business process event streams is becoming more and more prominent. This also includes ensuring data quality for the application of downstream online process mining activities and therefore identify and classify incorrect process behavior of incoming event streams in an online setting, what is considered too little in existing approaches. In this paper, we present an online classification approach that supports monitoring and anomaly detection in event streams at the event level. Possible process drifts can be handled by an online learning workflow. By integrating two explanatory components, the results of the online classification are made transparent and comprehensible. Through a technical experiment, the performance of the classification approach is evaluated based on different data sets. Thereby, the classification model achieves an average F1 score of 0.877 with an average processing time of ∼15 ms per event. [ABSTRACT FROM AUTHOR]

AI becomes a key enabler for Industry 4.0. Data / information quality become a real cornerstone on the overall process from user expectation to products / systems / solutions in a consistent perspective in order to ensure quality of the manufacturing production. This paper highlights some key characteristics in terms of information quality required to implement an effective AI based monitoring framework, in order to achieve operational excellence in Industry. [ABSTRACT FROM AUTHOR]

Recently, Big Data analytics has been one of the most emerging topics in the business field. Data is collected, processed and analyzed to gain useful insight for their organization. Big Data analytics has the potential to improve the quality of life and help to achieve Sustainable Development Goals (SDG). To ensure that SDG goals are achieved, we must utilize existing data to meet those targets and ensure accountability. However, data quality is often left out when dealing with data. Any types of errors presented in the dataset should be properly addressed to ensure the analysis provided is accurate and truthful. In this paper, we have addressed the concept of data quality diagnosis to identify the outlier presented in the dataset. The cause of the outlier is further discussed to identify potential improvements that can be done to the dataset. In addition, recommendations to improve the quality of data and data collection systems are provided. [ABSTRACT FROM AUTHOR]

The implementation of Electronic Health Records (EHRs) in developing countries is considered a means for improving data quality and high quality care. However, existing research, indicate that EHRs have recorded greater quantity of bad data instead of improving the quality of data. The reasons for this is not exactly clear. Accordingly, this paper takes a broader socio-technical approach to explore the issues in more detail. The paper explores the relationship between EHRs and quality at the Pentecost Hospital Madina-Ghana by using an interpretative research approach. The result of our study indicates that the EHRs introduced at the hospital have so far had limited effect on data quality and that context-related challenges are the major pitfalls identified in the study. Based on a socio- technical approach the paper discusses the need to; consider users and technology as intertwined, how technology changes practice and how it formalizes roles and responsibilities in the process, why it requires collaborative work and why realistic goals as opposed to exaggerated expectation. [ABSTRACT FROM AUTHOR]

Organizations are increasingly looking to trusted data to drive their decision making process. Trusted data has a clear, defined and consistent quality which meets the expectations of the user. Data infrastructures which produce trusted data and provide organizations with the capability to make the right decisions at the right time are socio-technical networks, consisting of technical infrastructures and actor networks, and as such they are often complex and adaptive. Critical issues, challenges, and dilemmas can be identified while looking at data infrastructures as a socio-technical systems. This paper explores conditions and factors for effective and sustainable development of data infrastructures in organizations and suggests that the inherent complexity of data infrastructures requires a multi-faceted way of data governance. Several predefined components of data infrastructures which contain the behavior of agents through various coordination mechanisms have been developed to model the effect of data governance on data infrastructures. These components can be further customized to model an empirical situation more closely. Finally, the paper suggests institutionalization of data governance within an organization as a unifying concept towards the effectiveness and sustainability of data infrastructures, recognizing their inherent complexities. The approach is illustrated with a case study in the asset management domain. [ABSTRACT FROM AUTHOR]

Time-series modeling is a well-studied topic of classical analysis and machine learning. However, large datasets are required to obtain the model with a better prediction quality with the increasing model complexity. Therefore, some applications demand synthetic datasets that are preserving modeling-sensitive properties. Another application of synthetic data is data anonymization. The synthetic data generation algorithm may be split into two parts: the time-series modeling and the synthetic data generation parts. The model must be interpretable to obtain the synthetic data with good quality. The model parameter interpretation allows controlling generation by adding noise to different groups of parameters. In the paper, the evolutionary multi-objective closed-form algebraic expressions discovery approach that allows obtaining the model in the form that may be analyzed using the mathematics is proposed. The analysis allows the interpretation of the model parameters for the controllable generation of the synthetic data. The notion of synthetic data quality is discussed. The examples of the synthetic time-series generation based on two datasets with different properties are shown. [ABSTRACT FROM AUTHOR]

This paper presents a passive hydrostatic stabilization system design for a box-shaped autonomous underwater vehicle. In order to ensure the quality of data collected, underwater inspection mission require a high stability AUV, especially in roll and pitch direction. However, conventional AUV adopt torpedo-shaped body, which has limited passive restoring moment in roll and pitch direction. Therefore, this paper presents design of a box-shaped autonomous underwater vehicle which is highly stable in roll and pitch direction. The passive stability of the designed autonomous underwater vehicle is improved by putting the heavy components at the bottom part of the vehicle whereas light component at the top part of the vehicle. The designed vehicle weights 68.8 kilogram in air with 0.6 kilogram positive buoyant. It has centre of buoyancy exactly above the centre of gravity with 7.39 centimeter metacentric height. By calculation, the vehicle will have 35.68 newton meter restoring moment at 45 degree. By pool test, result shows that the vehicle is able to retain its original vertical axis as vertical without steady state error. [ABSTRACT FROM AUTHOR]

Materialized views evolve in order to meet the user's requirement in the dynamically changing data warehouse environment. Therefore, materialized view evolution approach focuses on choosing materialized views in the design process of data warehouses or maintaining a materialized view in response to data changes or to data sources changes and sometimes to monitor the DW quality under schema evolution. Although few researchers have addressed materialized view evolution problem for evolving an appropriate set of views. But, none of the surveys provides a classification of materialized view evolution approaches in order to identify their advantages and disadvantages. This survey tries to fill this gap. The present paper provides a review of model based materialized view evolution methods by identifying the three main dimensions namely; (i) Framework, (ii) Architecture and (iii) Model/Design Model, that are the basis in the classification of materialized view evolution methods. The goal of this paper is to provide a comparative study on model based materialized view evolution methods, by identifying respective potentials and limits. [ABSTRACT FROM AUTHOR]

For production of sheet metal parts for car bodies, an adjustment of process parameters is required to maintain the desired part quality in presence of scattering blank properties. The digital transformation enables the application of data-driven methods for finding process parameters instead of a time-consuming experience-driven trial-and-error approach. However, due to cost and technical limitations, it is still hard to measure quality for every part. Removing data points of low-quality parts helps recommending proper process parameters. In this paper, we propose classification-based solution for recommending process parameters. In data preprocessing, the solution utilizes anomaly detection and knowledge-based methods to remove potential data points of low-quality parts without quality measures. On the processed data, a classification model is trained to predict process parameters according to blank properties. Our solution detects 30% low-quality parts and gives competitive performance (92.26% prediction accuracy) compared to a model trained on data comprising quality measures. [ABSTRACT FROM AUTHOR]

In order to make good decisions, the data used for decision-making needs to be of high quality. As the volume of data continually increases, ensuring high data quality is a big challenge nowadays and needs to be automated with tools. The goal of the Data Quality Library (DaQL) is to provide a tool to continuously ensure and measure data quality as proposed in [5]. In this paper, we present the current status of the development of the new DaQL version 2.0. The main contribution of DaQL 2.0 is the possibility to define data quality rules for complex data objects (called entities), which represent business objects. In contrast to existing tools, a user does not require detailed knowledge about the database schema that is observed. [ABSTRACT FROM AUTHOR]

Two concepts currently at the leading edge of todays information technology revolution are Analytics and Big Data. The public transportation industry has been at the forefront in utilizing and implementing Analytics and Big Data, from ridership forecasting to transit operations Rail transit systems have been especially involved with these IT concepts, and tend to be especially amenable to the advantages of Analytics and Big Data because they are generally closed systems that involve sophisticated processing of large volumes of data. The more that public transportation professionals and decision makers understand the role of Analytics and Big Data in their industry in perspective, the more effectively they will be able to utilize its promise. This paper gives an overview of Big Data technologies in context of transportation with specific to Railways. This paper also gives an insight on how the existing data modules from the transport authority combines Big Data and how can be incorporated in providing maintenance decision making. [ABSTRACT FROM AUTHOR]

This paper looks at graphical models and discusses the quality of tree approximations by ex- amining information measures and formulating the problem as a detection problem. One of the widely used algorithms for tree-structured approximation and modeling is the Chow-Liu algo- rithm. While this algorithm is optimal for Gaussian distributions in the sense of the Kullback- Leibler (KL) divergence, it is not optimal when compared with other information divergences and criteria such as Area Under the detection Curve (AUC) and reverse KL divergence. In this paper, we discuss the optimality of tree approximation methods. We show that different information theory divergences and criteria such as the KL divergence, the Jeffreys divergence and the AUC are all related of the correlation approximation matrix (CAM), Δ . We also show some explicit relations between these different information divergences and criteria and investigate the relation between quality of the tree approximation by formulating a detection problem and considering the AUC and the Jefferys divergence which is a distance between two conditional means, as alternative approaches for the tree approximation. The tree structure approximation algorithms have interesting applications. In general, the tree structured enables us to do distributed algorithms such as belief propagation and also to do inference. Because of computational complexity, it is important to consider simpler graphical models such as trees when modeling systems for many applications. We previously discuss the problem of convergence of the distributed state estimation algorithm for electric distribution grids, “mi- crogrids,” with distributed renewable energy generation. The correlations between distributed renewable energy generators was approximated by a simpler tree-structured graphical model. This paper carries the research further by looking at real spatial solar irradiation data and approximating correlation matrices by a tree structured graph. We also conduct simulations on synthetic data with larger number of nodes. [ABSTRACT FROM AUTHOR]

Nowadays, the development of data sharing technologies allows to involve more people to collaboratively contribute knowledge on the Web. The shared knowledge is usually represented as Collaborative Open Data (COD), for example, Wikipedia is one of the well-known sources for COD. The Wikipedia articles can be written in different languages, updated in real time, and originated from a vast variety of editors. However, COD also bring different data quality problems such as data inconsistency and low data objectiveness due to the crowd-based and dynamic nature. These data quality problems such as biased information may lead to sentimental changes or social impacts. This paper therefore proposes a new measurement model to assess the quality of COD. In order to evaluate the proposed model, A preliminary experiment is conducted with a large scale of Wikipedia articles to validate the applicability and efficiency of this proposed quality model in the real-world scenario. [ABSTRACT FROM AUTHOR]

Data quality has become an important issue. This issue becomes more and more important in medicine area, where the need for effective decision making is high. In this context, the need for data cleaning to improve data quality is becoming crucial. Duplicate records elimination is a challenging data cleansing task. In this paper, we present a duplicate records elimination approach to improve the quality of data. We propose a deep learning-based approach for duplicate records detection using a sentence embeddings model. Also, we propose an algorithm for duplicated records correction. Then, we apply the proposed duplicate records elimination approach to analyse the effect of data cleaning on the quality of decisions. We evaluate our proposal on heart disease problem using Cleveland heart disease dataset. Experiments show that the classification performance improves upon the application of the duplicate records elimination approach on datasets compared to that of datasets with duplicate records. [ABSTRACT FROM AUTHOR]

Massive amounts of data are available for the organization which will influence their business decision. Data collected from the various resources are dirty and this will affect the accuracy of prediction result. Data cleansing offers a better data quality which will be a great help for the organization to make sure their data is ready for the analyzing phase. However, the amount of data collected by the organizations has been increasing every year, which is making most of the existing methods no longer suitable for big data. Data cleansing process mainly consists of identifying the errors, detecting the errors and corrects them. Despite the data need to be analyzed quickly, the data cleansing process is complex and time-consuming in order to make sure the cleansed data have a better quality of data. The importance of domain expert in data cleansing process is undeniable as verification and validation are the main concerns on the cleansed data. This paper reviews the data cleansing process, the challenge of data cleansing for big data and the available data cleansing methods. [ABSTRACT FROM AUTHOR]

Today, as technologies mature and people are encouraged to contribute data to organizations' databases, more transactions are being captured than ever before. Meanwhile, improvements in data storage technologies have made the cost of evaluating, selecting, and destroying legacy data considerably greater than simply letting it accumulate. On the one hand, the excess of stored data has considerably increased the opportunities to interrelate and analyze them, while the moderate enthusiasm generated by data warehousing and data mining in the 1990s has been replaced by a rampant euphoria about big data and data analytics. But, is this as wonderful as seems? This paper presents a risk analysis of Big Data and Big Data Analytics based on a review of quality factors. [ABSTRACT FROM AUTHOR]

Human beings share their good or bad opinions about subjects, products, and services through internet and social networks. The ability to effectively analyze this kind of information is now seen as a key competitive advantage to better inform decisions. In order to do so, organizations employ Sentiment Analysis (SA) techniques on these data. However, the usage of social media around the world is ever-increasing, which considerably accelerates massive data generation and makes traditional SA systems unable to deliver useful insights. Such volume of data can be efficiently analyzed using the combination of SA techniques and Big Data technologies. In fact, big data is not a luxury but an essential necessary to make valuable predictions. However, there are some challenges associated with big data such as quality that could highly affect the SA systems' accuracy that use huge volume of data. Thus, the quality aspect should be addressed in order to build reliable and credible systems. For this, the goal of our research work is to consider Big Data Quality Metrics (BDQM) in SA that rely of big data. In this paper, we first highlight the most eloquent BDQM that should be considered throughout the Big Data Value Chain (BDVC) in any big data project. Then, we measure the impact of BDQM on a novel SA method accuracy in a real case study by giving simulation results. [ABSTRACT FROM AUTHOR]

High data quality is a prerequisite for accurate data analysis. However, data inconsistencies often arise in real data, leading to untrusted decision making downstream in the data analysis pipeline. In this paper, we study the problem of inconsistency detection and repair of the Ontology Multi-dimensional Data Model (OMD). We propose a framework of data quality assessment, and repair for the OMD. We formally define a weight-based repair-by-deletion semantics, and present an automatic weight generation mechanism that considers multiple input criteria. Our methods are rooted in multi-criteria decision making that consider the correlation, contrast, and conflict that may exist among multiple criteria, and is often needed in the data cleaning domain. [ABSTRACT FROM AUTHOR]

The accuracy and relevance of Business Intelligence & Analytics (BI&A) rely on the ability to bring high data quality to the data warehouse from both internal and external sources using the ETL process. The latter is complex and time-consuming as it manages data with heterogeneous content and diverse quality problems. Ensuring data quality requires tracking quality defects along the ETL process. In this paper, we present the main ETL quality characteristics. We provide an overview of the existing ETL process data quality approaches. We also present a comparative study of some commercial ETL tools to show how much these tools consider data quality dimensions. To illustrate our study, we carry out experiments using an ETL dedicated solution (Talend Data Integration) and a data quality dedicated solution (Talend Data Quality). Based on our study, we identify and discuss quality challenges to be addressed in our future research. [ABSTRACT FROM AUTHOR]

Due to the small amount of sample data and poor quality in cotton mills, this leads to large errors in the prediction of yarn quality to make the model difficult to train. This paper uses the appropriate data stretching algorithm after data preprocessing. Then, based on the features extracted by the main factors, the mapping relationship model of cotton blending is established. Finally, the evaluation and the correction of model are established. Actual tests have shown that the cost of cotton mills is decreased about 15% by the system and is increased about 25% for the profit by the system. [ABSTRACT FROM AUTHOR]

In the recent years, a growing popularity of knowledge management and knowledge conceptualization in the form of ontology is observed. However, one of the most important and up-to-date challenges infolds the quality evaluation of knowledge conceptualization. The prospective mistakes and omissions in ontologies have an influence on the exploitation of the full potential of exchanging data. For this reason, the process of ontology evaluation has a great impact on the higher degree of reuse and a better cooperation over the boundaries of applications and domains. However, this process is quite complex and it requires the specified knowledge about available methods and tools supporting the ontology evaluation process. This paper discusses existing evaluation metrics supporting the ontology evaluation process. Based on this, the author’s proposal of ontology-based approach for evaluation metrics is provided, offering a useful guidance to knowledge handling, conceptualization and representation, and using knowledge engineering. [ABSTRACT FROM AUTHOR]

Sports results prediction is increasingly important than many years ago, many factors can impact the results. Other than prediction accuracy, easy to predict is also significant. This research paper explores three easy to grab factors and uses DOE (Design of Experiment) method to determine the effects on sports result prediction. Another goal is to explore the three factors’ importance. This research data modeling is based on the NBA (National Basketball Association) game data. All the data is extracted from an official and public data source of 2015 to 2016 regular season. [ABSTRACT FROM AUTHOR]

We analyze the problem of data availability and how this situation (which is very common in practice) is a limiting factor for doing quality control and data restoration of MetOcean fields. In order to support our claim, we analyzed the case of data availability in the Arctic Region, since it is true that climate historical archives have always been scarce in this area, due to the harsh climate conditions and logistic difficulties that involve the deployment of in-situ weather systems in the region. In addition to the problem of data scarcity, we also have the problem of inconsistent and missing observations. In this paper, we highlight this problem by the analysis of 125 hourly temperature and hourly wind speed time series, which have been all in common their spatial distribution and present an evaluation of those data in terms of quality and availability. We also discuss the way the presence of gaps in time series can condition the ability of estimating synthetic data and discuss possible solutions to overcome this problem in areas where no neighboring stations are available. [ABSTRACT FROM AUTHOR]

The Medical Internet of Things (MIoT) has applications beyond clinical settings including in outpatient and care environments where monitoring is occurring over public networks and may involve non-dedicated devices. This poses a number of security and privacy challenges exacerbated by a heterogeneous and dynamic environment, but still requires standards for handling personally identifiable and medical information of patients and in some cases caregivers to be maintained. Whilst risk and threat assessments generally assume a stable and well-defined environment, this cannot be done in MIoT environments where devices may be added, removed, or changed in their configuration including connectivity to server back ends. Conducting a complete threat assessment for each such configuration changes is infeasible. In this paper, we seek to define a mechanism for prioritising MIoT threats and aspects of the analysis that are likely to be affected by composition and related alterations. We propose a mechanism based on the UK HMG IS1 1 approach and provide a case study in the form of the Technology Integrated Health Management (TIHM) 2 test bed. [ABSTRACT FROM AUTHOR]

Abstract: Volunteered geographic information (VGI) phenomenon offers an alternative mechanism for the acquisition of geospatial information. It has shown its effectiveness in various applications such as disaster management. However VGI suffers from a general lack of metadata quality assurance. This paper proposes an approach that aims to enhance VGI process by evaluating geospatial metadata quality. We introduce a set of indicators for geospatial metadata quality and we propose a method to evaluate them with respect to the context of VGI. [ABSTRACT FROM AUTHOR]

The paper discusses an external solution for data quality management in information systems. In contradiction to traditional data quality assurance methods, the proposed approach provides the usage of a domain specific language (DSL) for description data quality models. Data quality models consists of graphical diagrams, which elements contain requirements for data object's values and procedures for data object's analysis. The DSL interpreter makes the data quality model executable therefore ensuring measurement and improving of data quality. The described approach can be applied: (1) to check the completeness, accuracy and consistency of accumulated data; (2) to support data migration in cases when software architecture and/or data models are changed; (3) to gather data from different data sources and to transfer them to data warehouse. [ABSTRACT FROM AUTHOR]

The availability of new Sentinel-1A/B (S1A/B) satellites provides geohazards community with a large amount of Synthetic Aperture Radar (SAR) acquisitions over critical areas around the world. The current S1A mission has a minimum re-visit time of 12 days, but with the recent launch of S1B, this temporal gap will be reduced to only 6 days. This high acquisition frequency, jointly with the large coverage and high quality of S1 data, allows the rapid generation of interferograms 1,2 for sudden events, such as earthquakes. This rapid response is crucial for the damage evaluation and fault model refinement. This paper presents results obtained for the latest earthquakes occurred in Japan in April 2016. Two S1A interferograms in ascending and descending orbits have been generated, and after phase unwrapping 3,4 processing the Line Of Sight (LOS) motion maps are obtained. This LOS 1,2 component corresponds to the range distance between the satellite and ground, and it does not provide real horizontal and vertical information of the displacement. The usage of two different view directions, in ascending and descending orbits, allows the decomposition of LOS motion into horizontal (West-East) and vertical (Up-Down) directions. These new motion maps are essential to better understand the dynamics of the earthquake and to perform further analysis and modelling by seismic experts. [ABSTRACT FROM AUTHOR]

Quality of data is one of the key issues in the domain of Volunteered geographic information (VGI). To this purpose, in literature VGI data has been sometime compared with authoritative geospatial data. Evaluation of single contributions to VGI databases is more relevant for some applications and typically relies on evaluating reputation of contributors and using it as proxy measures for data quality. In this paper, we present a novel approach for reputation evaluation that is based on the well known PageRank algorithm for Web pages. We use a simple model for describing different versions of a geospatial entity in terms of corrections and completions. Authors, VGI contributions and their mutual relationships are modeled as nodes of a graph. In order to evaluate reputation of authors and contributions in the graph we propose an algorithm that is based on the personalized version of PageRank. [ABSTRACT FROM AUTHOR]

Mobile phone-based sensing is a new paradigm that aims at using smartpohnes to answer sensing requests and collect useful data. Nowadays, a wide variety of domains ranging from health-care applications to pollution monitoring are benefiting from such collected data. However, despite its increasing popularity and the huge amount of data provided by users, there is no platform where mobile phone owners can effectively sell their data. In this paper, we propose the idea of a data monetization platform using two-sided market theory. In this platform, the data is viewed as an economic good and the data sharing activity is considered as an economic transaction. The proposed platform considers the case of abundant data. An experimental analysis is conducted to compare our approach against the peer-to-peer model using a real case study from the health care domain. We show that our proposed platform has the potential to generate higher profit for both data providers and data consumers. [ABSTRACT FROM AUTHOR]

This paper focuses on techniques for dealing with imperfect data in a frame of early warning system (EWS). Despite the fact that data may be technically damaged by presenting noise, outliers or missing values, met-ocean simulation systems have to deal with them to provide data transaction between models, real time data assimilation, calibration, etc. In this context data quality-control becomes one of the most important parts of EWS. St. Petersburg FWS was considered as an example of EWS. Quality control in St. Petersburg FWS contains blocks of technical control, human mistakes control, statistical control of simulated fields, statistical control and restoration of measurements and control using alternative models. Domain specific quality control was presented as two types of procedures based on theoretically proved methods were applied. The first procedure is based on probabilistic model of dynamical system, where processes are spatially interrelated and could be implemented in a form of multivariate regression (MRM). The second procedure is based on principal component analysis extended for taking into account temporal relations in data set (ePCA). [ABSTRACT FROM AUTHOR]

This paper describes techniques to manage the quality-of-data (QoD), particularly in telemedicine systems. Hence, clinical data users, such as clinical decision support systems that support ‘real-time’ guidance of ambulatory patients, can process the data together with QoD in order to make the ‘best’ treatment decisions. Current information and communication technology (ICT) applied in telemedicine systems enables remote clinical data collection and delivery to the point of decision, thereby giving opportunities to develop new, pervasive, healthcare applications. However, the QoD in such distributed and decentralized environments is not always guaranteed. We propose QoD management techniques that take into account the multidimensionality of QoD and its ‘fitness for use’. Additionally, we present a technique that handles the quality of ‘real-time’ streaming data. We developed a telemedicine system prototype to investigate the applicability and the usefulness of the proposed techniques. [ABSTRACT FROM AUTHOR]

With the evolution of technology, the ways to acquire data and the applications of data are more diverse. As data volume con- tinuously grows, the data quality may not be high as usual. The data can be defected, imprecise or inaccurate due to the process of data acquiring. Recently, the skyline query is widely used in data analysis to derive the results that meets more than one spe- cific condition simultaneously. For example, the forest monitoring system, which collects the temperature and humidity of the surrounding environment with sensors, to monitor the disasters. Using the skyline query, the zones of potential fire hazards can be found in time, where the temperature is high and the humidity is low. In the mentioned application, the derived data change with time. We refer to such data as data streams. The constant change and uncertainty of data make the query process difficult and need more computations. Thus, how to have an effective skyline query process in terms of time and space over uncertain data streams becomes crucial. In this paper, we discuss this problem and propose an effective approach, Efficient Probabilistic Skyline Update (EPSU), using a new data structure by augmenting the R-tree structure. The relevant algorithms are analyzed and discussed. Last, we perform the simulated experiments extensively with synthetic data to validate the EPSU approach. The results show that EPSU can effectively compute the probabilistic skyline query in terms of the time and space and outperforms the existing ones. [ABSTRACT FROM AUTHOR]

This research paper reports on a study focusing on a franchise relationship that utilizes an enterprise system (ES) to optimize its supply chain. The ES is in its post-implementation phase; however, the franchisee has challenges with inventory management due to poor data quality, which causes problems with vendor analysis and revenue control. An action case study was carried out to identify and diagnose the source of the problem, and interventions were implemented and evaluated. The findings demonstrate that several of the challenges related to poor data quality in the supply chain were influenced by problems of a socio-technical character. These included a lack of understanding of the system, a shortage of training, workarounds, opportunistic behaviors and a lack of effective control mechanisms for the franchisor. Implications for the franchisor include the need for greater emphasis on good communication routines with franchisees, so problems in the system can be identified early and resolved. Franchisees must try to establish a good relationship with the franchisor and to be aware that knowledge and training can be the keys to realizing the benefits of the ES. [ABSTRACT FROM AUTHOR]

More and more asset management organizations are relying on trusted data to drive their decision making process. Yet little systematic research has been performed regarding the generation of trusted data. Trusted data has a clear, defined and consistent quality which meets the expectations of the user. The aim of the research presented in this paper is to develop a conceptual model to support asset management organizations with regards to their development of data infrastructures which produce trusted data and provide organizations with the capability to make the right decisions at the right time. The autonomous characteristics of agent-based systems and process orientation of discrete-event simulation are combined in our conceptual model. In this way both the autonomous social behavior of organizations and their business processes can be modelled. Several predefined components containing the behavior of agents through various coordination mechanisms have been developed. These components can be further customized to model an empirical situation more closely. The approach is illustrated with a case study in the asset management domain. [ABSTRACT FROM AUTHOR]

The KDD data set is a well known benchmark in the research of Intrusion Detection techniques. A lot of work is going on for the improvement of intrusion detection strategies while the research on the data used for training and testing the detection model is equally of prime concern because better data quality can improve offline intrusion detection. This paper presents the analysis of KDD data set with respect to four classes which are Basic, Content, Traffic and Host in which all data attributes can be categorized. The analysis is done with respect to two prominent evaluation metrics, Detection Rate (DR) and False Alarm Rate (FAR) for an Intrusion Detection System (IDS). As a result of this empirical analysis on the data set, the contribution of each of four classes of attributes on DR and FAR is shown which can help enhance the suitability of data set to achieve maximum DR with minimum FAR. [ABSTRACT FROM AUTHOR]