Search

Abstract Although case retrieval of Bayesian network has greatly promoted the application of CBR technique in engineering fields, it is facing huge challenges with the arrival of the era of big data. First, huge computation task of BN learning caused by big data seriously hampers the efficiency of case retrieval; Second, with the increasing data size, the accuracy of case retrieval becomes poorer and poorer because existing methods of improving probability learning become unfit for new situation. Aiming at the first problem, this paper proposes Within-Cross algorithm to assign computation task to improve the result of parallel data processing and gain better efficiency of case retrieval. For the second problem, this paper proposes a new method called Weighted Index Coefficient of Dirichlet Distribution (WICDD) algorithm, which first measures the influence of different factors on probability learning and then gives a weight to each super parameter of Dirichlet Distribution to adjust the result of probability learning. Thus with WICDD algorithm, the effect of probability learning is greatly improved, which then further enhances the accuracy of case retrieval. Finally, lots of experiments are executed to validate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Highlights • There is a growing demand for easily deployable big data platform supporting the execution of map-reduce applications. • Apache Hadoop cluster powered by the Occopus cloud orchestrator tool implements an open-source, cloud-agnostic solution. • Combining with service discovery and monitoring tools auto-scaling has been also realised to dynamise resource capacity. • Based on cost analysis, the solution leads to cost reduction in certain use cases compared to commercial solutions. • Short-term and long-term deployments as well as fine-tuning configuration are supported. Abstract Nowadays a significant part of the cloud applications processes a large amount of data to provide the desired analytics, simulation and other results. Cloud computing is becoming a widely used IT model to address the needs of many scientific and commercial Big Data applications. In this paper, we present a Hadoop platform deployment method for various cloud infrastructures with the Occopus cloud orchestrator tool. Our automated solution provides an easy-to-use, portable and scalable way to deploy the popular Hadoop platform with the main goal to avoid vendor locking issues, i.e. there is no dependency on any cloud provider prepared and offered virtual machine image or "black-box" Platform-as-a-Service mechanism. The paper presents promising performance measurements results and cost analysis. [ABSTRACT FROM AUTHOR]

Abstract Severe weather events pose a significant threat to transportation networks. This research analyzes and discusses the impact of precipitation, temperature, visibility and wind speed on hourly weekday traffic flow volume in Atlanta, Georgia. The study involves the following: determine weather variables that affect traffic volume, develop a machine learning technique to derive decision rules based on weather and traffic volume, and create a web-based decision support visualization tool using the analyzed results. The relationship between extreme weather events and traffic volume was investigated by comparing traffic volume between a base case scenario and an extreme weather scenario. Data from 48 Automatic Traffic Recorder (ATR) sites around Atlanta, GA, USA and hourly precipitation data from 4 climate measurement stations were used to conduct this study. The spatiotemporal relationships between traffic volume and weather variables were analyzed individually and evaluated using a non-parametric statistical test. A machine learning technique is applied to derive decision rules that result in reduction in traffic volume. Results show significant impacts on traffic volume from visibility, precipitation and temperature and helps in isolating hours in a typical weekday when such impacts are felt. A decision support tool was also developed to visualize traffic volume and weather interactions. The data-driven insights from this analysis is applicable to transportation planners, centralized traffic control rooms and urban infrastructure decision makers. Highlights • Paper analyzes correlations between 4 weather hazards and traffic volume by combining Big Data repositories from climate science and transportation. • The paper using extensive statistical analysis to derive hours in a typical day where traffic at a particular location is impacted due to a weather hazard. • Machine learning models were also applied to derive decision rules for traffic planners and transportation personnel to optimize and plan for weather hazards. • A decision support tool was also derived to help display the data analysis, derive insights and optimize transportation decision making. [ABSTRACT FROM AUTHOR]

Abstract New sensing and wireless technologies generate massive data. This paper proposes an efficient Bayesian network to evaluate the slope safety using large-quantity field monitoring information with underlying physical mechanisms. A Bayesian network for a slope involving correlated material properties and dozens of observational points is constructed. Graphical abstract Image 1 Highlights • New sensing and wireless technologies generate massive monitoring data. • This paper proposes an efficient Bayesian network to evaluate the slope safety. • Large-quantity field monitoring information is integrated in the evaluation. • A Bayesian network for a slope involving correlated properties is constructed. • The value of information has also been evaluated in the Bayesian network. [ABSTRACT FROM AUTHOR]

Big data industry development and carbon dioxide emissions reduction are the crucial driver and objective functions of economic growth, respectively. Whether the two types of corresponding policies can achieve the "win-win" effect is the key to green development transformation in the future. However, little attention has been paid to the influence of big data industry development on carbon dioxide emissions. Based on the quasi-natural experiment in China's national big data comprehensive experimental area, the paper identifies the causal effect between big data industry development and carbon dioxide emissions. Specifically, the panel data of 282 cities in China spanning from 2010 to 2019 are used in regression analysis. The study reveals that the big data industry development has a substantial impact in reducing carbon dioxide emissions. Meanwhile, the findings are confirmed by a set of rigorous robustness checks. The heterogeneity analyses suggest that the effect of inhibiting carbon dioxide emissions due to the big data industry development is more significant in eastern & central China, and large-sized cities. In addition, the big data industry reduces carbon dioxide emissions through the effects of industrial structure optimization, technological innovation, and resource allocation. Our findings contribute to the nexus between big data industry development and carbon dioxide emissions. In light of these findings, the paper recommends that governments integrate economic growth and environmental protection policies by promoting big data industry development. • The paper provides a novel insight into the CO 2 emission from the perspective of big data industry. • Based on quasi-natural experiment, the paper has identified the causal effect between the big data industry development and CO 2 emissions with the Difference-in-Difference (DID) methodology. • Big data industry development effectively stimulate the reduction of CO 2 emissions. [ABSTRACT FROM AUTHOR]

Big Data will revolutionize modern industry by improving process optimization, facilitating insight discovery, and improving decision-making. This big data revolution presents a multitude of possibilities and challenges in evolving from traditional batch processes to smart batch processes. This tremendous potential requires the ability to extract value from vast amounts of industrial process data. Using a new three-dimensional (3D) perspective of time, batch, and operational context, this paper explores smart batch processes with higher efficiency, greater profitability, and longer sustainability. First, we review the traditional one-dimensional (1D) perspective on batch processes and summarize the existing two-dimensional (2D) perspectives on batch processes, i.e., modeling, monitoring, control, and optimization methods. Based on those results, the spotlight will focus on how big data can be used to achieve smart batch processes using the 3D perspective. This will include detailed discussions of definitions and concepts, operational mechanisms, and the benefits and advantages of smart batch processes. For further implementation of the 3D perspective, we present several monitoring and control methodologies. Next, we analyze several challenges and issues in implementing smart batch processes in the era of Big Data. In conclusion, we provide both a novel viewpoint and encouragement for future research into batch process automation from the 3D perspective. [ABSTRACT FROM AUTHOR]

Big data and time series are typical features of modern industrial process data. Effective time series modeling methods are required for ensuring the normal and stable operation of industrial processes. However, the existing time series prediction methods usually cannot take important historical data features long ago into consideration. In this paper, we proposed a new attention-mechanism based dynamic-inner partial least squares long short-term memory (ADiPLS-LSTM) method to predict the time series data. First, the DiPLS method is applied to extract the dynamic features in the selected data group, and the attention-mechanism is used then to define the importance of the responded features. The product of the extracted dynamic features and the attention-mechanism results is regarded as the input of LSTM to predict the future time information. The proposed method uses both the recent data information and important data information in a long run, which helps to obtain more accurate prediction results. The effectiveness of the ADiPLS-LSTM method is verified by the data of a 660MW coal-fired boiler. Compared with BPNN, LSTM, and DiPLS-LSTM, the proposed method also advances in time series data prediction and interpretability. • The receive field of LSTM is usually very limited, and the interpretability is weak • DiPLS can extract dynamic features between input and output • The existing prediction methods cannot take important historical data features. • A new novel ADiPLS-LSTM method is proposed in this paper. • Application results confirm the effectiveness and reliability of the proposed method. [ABSTRACT FROM AUTHOR]

Security issues are the most critical challenges facing new technologies associated with the internet of things (IoT), big data, and cloud computing. A secure and efficient intrusion detection system (IDS) is crucial to detect security threats. Existing IDSs are known to suffer from many problems, most notably the high rate of false positive alerts, the long time required to detect attacks, and the inability to detect zero-day attacks, which can ruin companies. The weakness of IDS backend engines costs companies time in the investigation process. This paper proposes and enhances IDS detection mechanisms via two processes: using a deep neural network (DNN) model with new features for threat detection based on two assumptions related to handling zero-day attacks, with low computing power and resources, and a comprehensive solution for detection by merging the DNN model and principle component analysis (PCA) to increase security and performance. The proposed detection mechanism combines DNN, PCA, statistical, and knowledge-based approaches to offer significantly greater efficiency than existing IDS, as indicated by analytical and software results. A simulation model is used with up-to-date web attacks, distributed denial of service (DDoS), denial of service (DoS), brute force, insider infiltration, Botnet, and Heartbleed attacks. The proposed detection techniques for large networks are analyzed and complexity in the design is avoided by reducing the number of DNN model layers, thus minimizing detection time delay and false positives, while increasing security against network attacks. Integrating the proposed DNN with PCA, an innovative contribution, introduces robust IDS to significantly improve the detection time delay and security performance. The proposed model showed a 98% accuracy rate. To best of our knowledge, the highest accuracy rate stated based on a large number of attacks is 97%, which makes our model state of art. [ABSTRACT FROM AUTHOR]

Big data analytics is difficult for people since there are so many factors that can influence the ways stock market change. Big data analytics is different from weather forecasting, which can be made by applying the laws of atmospheric change and mass experience and other comprehensive research. However, stock markets do not have a fixed law that allows people to do analysis. They are influenced by governments decision, information on the website, citizens' behaviors, etc. Hence, this paper helps people learn how to do big data analytics and stock market prediction by three steps, such as sentiment analysis, information extraction and cleaning, and three models for stock market prediction. The implementation process of big data analytics generally includes several stages, such as data acquisition and recording, information extraction and cleaning, data integration and presentation, selection of modeling and analysis methods, interpretation of results, effectiveness of evaluation results and monitoring. [1] , [2] The result of the prediction is that LSTM model is the best model in prediction of the trend of stock market. [ABSTRACT FROM AUTHOR]

Information technology has promoted the development of globalization, and cross-border e-commerce business has also ushered in rapid development. In recent years, the scale of cross-border e-commerce in our country has grown rapidly, and this industry has gradually become an important component of the import and export trading. Since the cross-border e-commerce business happens between two different countries or regions, there are certain differences in logistics laws, logistics service facilities and human culture in each country or region, so there are many potential risk factors, thus the risks in cross-border e-commerce export trading are also increasingly prominent. Based on the analysis of the market environment risks, customs clearance risks and logistics risks faced by our country's cross-border e-commerce exports, this paper formulates targeted countermeasures combined with the application of big data technology in risk identification, and proposes practical and feasible solutions with preventive advice towards the- cross-border e-commerce export risks in China. [ABSTRACT FROM AUTHOR]

Association rules are popular form for knowledge discovery domain. They are used for finding interesting relationships and patterns hidden in large data sets and in the area of associative classification, where usually rules with one item in the right-hand side are considered. There are many different approaches and algorithms for mining association rules. One of the most popular group are methods which are based on mining frequent itemsets, usually applied for data in transaction format. Such data can be transformed to binary information system which corresponds to matrix data format. Technological development means that we are dealing with an increasing amount of data that can be heterogeneous, taking into account their format and location. In this paper, we assume that dispersed data is represented by a finite set S of information systems with equal sets of attributes. We discuss one of the possible ways to the study association rules common to all information systems from the set S : building a joint information system for which the set of true association rules that are realizable for a given row r and have given attribute f on the right-hand side coincides with the set of association rules that are true for all information systems from S , are realizable for the row r , and have the attribute f on the right-hand side. We show how to build a joint information system in a polynomial time. When we build such an information system, we can apply to it various association rule learning algorithms. [ABSTRACT FROM AUTHOR]

The smart city has become a persistent need and is no longer just a concept. The concept of smart cities heavily relies on collecting enormous amounts of data. This paper proposes a data-management-based solution for smart city, which is labeled Smart Systems Oriented Big Data Architecture. Big data technologies have become essential to the functioning of cities. The architecture includes complex components to be implemented based on the architectural requirements. A data migration strategy was proposed to handle the various data sources such as IoT devices, video cameras, and drones. The proposed approach also takes into account data processing and data storage. The technical constraints related to data processing in a big-data environment are also studied. We also consider data modeling from a business intelligence point of view and a data science perspective. Our main goal is to favor the facilitation of the daily life practices in the context of a smart city by providing the city administrators with a solution that helps them maintain their city smartly and effectively. [ABSTRACT FROM AUTHOR]

Examining logical satisfiability, as a decision problem or a preference-based choice situation, is a fully natural human activity. The aim of this paper is to present a set of algorithms using the maximum satisfiability method (MaxSAT) with weights, where the object of analysis can be big data sets, coming from large databases or social media, processed using some NLP (Natural Language Processing) procedures. The process of creating and matching weights is driven by the pairwise comparison method (PwC), which is an effective evaluation and ranking procedure. The algorithms are productive and have already been implemented, combining MaxSAT and PwC results in a synergy effect. [ABSTRACT FROM AUTHOR]

Advancement in the fields of electronic communication, data processing, and internet technologies enable easy access to and interaction with a variety of physical devices throughout the globe. Our whole world is enveloped by a blanket of innumerable smart devices equipped with the sensors and actuators. Extensive research on the Internet of things (IoT) with cloud technologies, make it possible to accumulate tremendous data created from this heterogeneous environment and transform it into precious knowledge by utilizing data mining technologies. Furthermore, this generated knowledge will play a key role in intelligent decision making, system performance boosting, and optimum management of resources and services. With this background, this paper presents a systematic and detailed review of various data mining techniques employed in the large and small scale IoT applications to formulate an intelligent environment. It also presents an overview of cloud-assisted IoT Big data mining system to better understand the importance of data mining for an IoT environment. [ABSTRACT FROM AUTHOR]

In the recent past, cloud infrastructure has considerably increased its applicability. This has resulted in effective Big Data processing. Hadoop schedulers are critical components to deliver required levels of efficiency, where MapReduce tasks are assigned to Hadoop nodes by the scheduler. There is a significant challenge in planning the increasing amount of functions and resources in a scalable way. Also, this challenge is further compounded by the potential heterogeneity of the deployed Hadoop. This paper proposes a scheduler that makes scheduling a choice by assessing the entire task group in the job queue. Further, the proposed scheduler uses a new scheduling method based on Real Coded Genetic Algorithm (RCGA). RCGA with MapReduce enables users to create more scalable applications. A higher abstraction is provided in less time. The experimental results indicate that the proposed RCGA scheduler achieves better performance than the existing systems for the following metrics: Execution Time, Total Cost, Resource Utilization, Speedup, Throughput, Scheduling Efficiency, Fairness Relaxation, Scheduling Time, Turnaround Time, CPU Time, Data Locality and Average Node-Locality Ratio. [ABSTRACT FROM AUTHOR]

Sensitive Health Information (SHI) is a developing patient-centric model of medical data exchange, which is frequently outsourced to be stored at third party servers. Though, there have been various privacy issues as SHI could be disclosed to the unauthorised and third parties. This is a promising method to encrypt the SHI before outsourcing to assure the patients' control over access to their own SHI. However, challenges like scalability in key management and flexible access have remained the most significant issues toward achieving fine-grained, cryptographically data access control. In this paper, the authors proposed a novel patient-centric system model for access control to SHIs stored in semi-honest servers. For fine-grained and scalable access control for SHIs, authors have proposed an encryption technique which is an improvement over RSA techniques to encrypt every patient's SHI file. To different from previous works in secure data transmission, the authors focus on the data owner and divide users into several domains in SHI, which greatly decrease the key management complexity for data owners and users. Comprehensive analytical and experimental results are presented which reflect the efficiency of the proposed approach. [ABSTRACT FROM AUTHOR]

Autonomous driving is assisted by different sensors, each providing information about certain parameters. What we are looking for is an integrated perspective of all these parameters to drive us into better decisions. To achieve this goal, a system that can handle these Big Data issues regarding volume, velocity and variety is needed. This paper aims to design and develop a real-time Big Data Warehouse repository, integrating the data generated by the multiple sensors developed in the context of IVS (In-Vehicle Sensing) systems; the data to be stored in this repository should be merged, which will imply its processing, consolidation and preparation for the analytical mechanisms that will be required. This multisensory fusion is important because it allows the integration of different perspectives in terms of sensor data, since they complement each other. Therefore, it can enrich the entire analysis process at the decision-making level, for instance, understanding what is going on inside the cockpit. [ABSTRACT FROM AUTHOR]

Internet of Medical Things (IoMT) facilitate revolutionary development in healthcare services, recognized as smart healthcare. By collecting big healthcare data and utilizing artificial intelligence algorithms, P4-medicine can be realized in intelligent diagnosis, risk analysis, and health management. As more data is collected, privacy and security become imperatives in healthcare research, and split learning is ideal for big data predictions, but relative research is at an early stage without systematically designing and considering data characteristics. In this paper, a Heterogeneous Transfer learning for spliT Prediction System (HTTPS) is proposed. HTTPS converts the dataset into both sparse and dense feature matrices, subsequently directing them into the sparse and dense embedding networks. For privacy considerations, embedding networks are designed as split learning to embed local features, and can further transfer experience from heterogeneous data. Experimental findings demonstrate that HTTPS outperforms the benchmark systems and has strong transferability. Furthermore, the designed mechanism motivates users to share some personal information to obtain precise predictions, and still provides a general model for privacy-conscious users. • Both time-series and feature-information are extracted by the designed mechanism. • Embedding networks embed features and enhance regularization, simultaneously. • Heterogeneous transfer learning is able to transfer knowledge from distinct domains. • The split learning mechanism enhances the privacy level of the proposed HTTPS. • HTTPS provides generic and customized models for privacy-conscious users. [ABSTRACT FROM AUTHOR]

The recommender systems are one of the most effective big data tools for solving the information overload problem, but data sparsity greatly affects its performance. However, most of the existing graph-based contrastive learning methods perturb the original graph structure for data augmentation, which may lead to semantic loss and subsequently degrade the recommendation performance. Meanwhile, studies have shown that improving the uniformity of data distribution is more effective than data augmentation using graph perturbation. In this paper, to enhance the uniformity of data distribution, we propose D istribution- A ware H ybrid N oise augmentation in graph contrastive learning for Rec ommendation (DAHNRec). Specifically, we design distribution-aware hybrid noise augmentation (DAHN) method to generate noise suitable for the users and items, instead of simply utilizing random noise following uniform distributions. By applying DAHN, the model can learn the appropriate noise distribution during the training process to enhance the uniformity of the embedding space. Additionally, we propose Balanced Bayesian Personalized Ranking (BBPR) as the loss function for recommendation tasks to improve difference characterizing between positive and negative samples. This improves the ranking tasks' performance. Furthermore, we conduct extensive experiments based on public benchmark datasets. The results indicate that DAHNRec outperforms several existing methods. Furthermore, DAHNRec is a general recommendation model based on user–item interactions, which can be used to improve the recommendation performance in various real-world scenarios, such as e-commerce platforms and social media. • A distribution-aware hybrid noise augmentation boosts contrastive tasks. • New loss function enhances recommendation performance. • Ensuring data distribution uniformity is beneficial for graph-based contrastive recommendation. [ABSTRACT FROM AUTHOR]

In the context of the explosive growth of manufacturing data, a manufacturing big data consortium is a collaborative organization aimed at promoting efficient decision-making and technological innovation. It is of vital significance to study how to effectively promote the data sharing among the members of manufacturing big data consortium. In this paper, we propose an evolutionary game model to investigate how to facilitate data sharing in the manufacturing big data consortium. Then, we analyze the synergistic revenue allocation method based on the indirect data sharing mode, and calculate the probability of the ideal event. We explore the influencing factors of data sharing in the manufacturing big data consortium by simulating Evolutionary Stable Strategies. Our findings reveal that the initial willingness of participants has a profound impact on their sharing behavior. Furthermore, the optimal interval revenue allocation coefficient can improve the probability of the manufacturing big data consortium to share data. Factors such as incentive revenue and social penalties positively influence the evolution towards active sharing strategies. In contrast, factors such as speculative revenue and data sharing costs inhibit the evolution towards active sharing strategies. • Indirect data sharing scheme is proposed for manufacturing industry collaboration. • Evolutionary game theory is introduced to study data sharing in manufacturing big data consortium. • A revenue allocation method is proposed for indirect data sharing in manufacturing big data consortium. • The incentive revenue coefficient and social penalty coefficient promote the evolution of active sharing strategy. • The data sharing cost coefficient and speculative revenue coefficient inhibit the evolution of positive sharing strategy. [ABSTRACT FROM AUTHOR]

Abstract In recent years, with the rapid expansion of urban power grids, the automatic voltage control (AVC) system develops some new characteristics. Based on the technology of big data analysis and mining, this paper expounds an AVC system for urban power network with high load density based on the integrated dispatch and operation mode. This paper introduces several different application modes, and shows the operation characteristics of the multi-point distribution mode and the integrated control mode. The big data mining technology is used to discovering the hidden troubles and defects in AVC system. This paper also presents some other AVC key technologies such as security check of remote control, self-adaption analysis method and so on. [ABSTRACT FROM AUTHOR]

Abstract Customers' Segmentation is an important concept for designing marketing campaigns to improve businesses and increase revenue. Clustering algorithms can help marketing experts to achieve this goal. The rapid growth of high dimensional databases and data warehouses, such as Customer Relationship Management (CRM), stressed the need for advanced data analytics techniques. In this paper we investigate different data analytics algorithms, specifically K-Means and SOM, using the TIC CRM dataset. While K-Means has shown promising clustering results, SOM has outperformed in the sense of: speed, quality of clustering, and visualization. Also we discuss how both techniques segmentation analysis can be useful in studying customer's interest. The purpose of this paper is to provide a proof of concept (based on a small publicity of data) of how big data analytics can be used in customer segmentation. [ABSTRACT FROM AUTHOR]

Abstract The amount of data created by people, machines and corporations around the world is growing every year. Thanks to innovations such as the Internet of Things, this trend will continue, giving rise to the creation of Big Data. Data visualization leverages principles of visual psychology to help stakeholders identify patterns, trends and correlations that might go undetected in text-based or spreadsheet data. The return on investment (ROI) of big data visualization is well-documented in numerous studies and use cases. However, to achieve ROI from analytics investments, key insights must be uncovered, understood and communicated. Synthesizing huge quantities of data into key insights grows more challenging as data volumes and varieties increase. To address visualization challenges posed by big and high-dimensional data, this paper explores algorithms and techniques that compress the amount of data and/or reduce the number of attributes to be analyzed and visualized. Specifically, this paper examines applying dimensionality reduction and data compression algorithms to reduce attributes, tuples and data points returned to the visualization. By reducing data returned to the visualization, trends, patterns and correlations are easier to view and visualization tool performance is optimized. [ABSTRACT FROM AUTHOR]

The present paper measures external effects in a specific type of common-pool resource, an information commons. Employing a novel dataset related to more than 700,000 transactions in distinct libraries during a 10-year period (2006–2015), we estimate the external effects of actions of library users who were subject to a non-monetary sanction (professors and university employees) on users who were subject to a monetary sanction (students). Additionally, we estimate peer effects among users, considering the number of items they borrow from the library. When investigating externalities, we uncover a “crowding-out” effect: for an additional unity in professors and employees' counts, there is an approximate one-to-one decrease in students' counts. In the case of peer effects, we find a positive influence of group behavior on individuals: for every 100 books borrowed by a user's peer group, there is a rise of three books per user, on average. The results reported in this paper have important implications for theories based on common-pool resource management, as well as public goods provision. [ABSTRACT FROM AUTHOR]

Highlights • Intelligent Hybrid Context-Aware Model for Patients Under-Supervision in Home (IHCAM-PUSH) is proposed to monitor patients with chronic diseases in real-time remotely. • A Hybrid Classification Module (HCM) is proposed to classify patient's health status on dual-mode, on the cloud side (online) or on local side (offline). • The proposed HCM handles the problem of imbalanced datasets in big data. • This paper presents a case study for monitoring elderly patients suffering from blood pressure disorders using (IHCAM-PUSH). Abstract This paper proposes an intelligent hybrid context-aware model for patients under supervision at home that adopts a hybrid architecture with both local and cloud-based components. The cloud-based portion of the model facilitates storing and processing the big data generated by ambient assisted living systems that are used to monitor patients suffering from chronic diseases in their homes, particularly the elderly. The local portion of the model monitors patients in the event of internet disconnections or any other failure in the cloud system. The proposed model utilises context-aware techniques by monitoring physiological signals, ambient conditions, and patient activities simultaneously to derive the real-time health status of the patient. Experimental results demonstrate the effectiveness of our proposed model for monitoring patients and accurately detecting emergencies in imbalanced datasets through a case study on patients suffering from blood-pressure disorders. [ABSTRACT FROM AUTHOR]

Abstract This paper introduces the integration of two data processing platforms, RHhadoop and SparkR, to carry out rapid big data retrieval and analytics using R programming, which can serve as part of business intelligence. Besides, it has developed the job scheduling optimization called Memory-Sensitive Heterogeneous Earliest Finish Time algorithm to enhance system throughput. However, the bottleneck of system throughput is definitely relevant to data traffic problem over network, especially a large amount of data exchange between distributed computing nodes within a cluster. The objective of this paper is to propose an intelligence approach to tackle the crucial problems of inefficient data traffic flow. Adaptive network-based fuzzy inference system along with particle swarm optimization has employed to tune the network-related parameters at computing nodes for improving network QoS and speed up data transportation significantly. In order to examine the computing efficiency, performance index has been evaluated for all of treatments in the experiment. [ABSTRACT FROM AUTHOR]

Abstract In the era of Big Data, data assets have become a strategic resource which cannot be overlooked by both society and enterprises. However, data is not equal to the assets. This paper first introduces the necessary conditions of data assetization and discriminates the concepts of data governance, data management and data asset management. Then it focuses on the unique connotation and characteristics of grid data assets. With reference to the mainstream theory of data management, the framework for the grid data asset management is set up in the combination of the characteristics of data assets, business needs and the actual situation in the power supply enterprises. Finally, this paper puts forward higher system requirements and technical requirements for China's power supply enterprises to conduct data asset management. [ABSTRACT FROM AUTHOR]

Abstract Cloud computing (CC) though has a great potential in providing on-demand, scalable provisioning of services with reduce management efforts and flexible pricing models has significant constraints. Firstly, CC pose a challenge in connectivity between the cloud and the end devices thereby unable to provide delay-sensitive services. Secondly, CC provider face limitations due to the imposition from the regulatory bodies to process the data at certain locations where they do not have any data centres. Thirdly, quality of CC service is compromised due to added mobility dimensions. Finally, CC is considered not a viable solution for most of the Internet of Things (IoT) solutions. In this paper, author proposes a new discipline – Fogology , as a novel branch of a discipline CABology. The paper attempt to present and discuss elements of Fogology. [ABSTRACT FROM AUTHOR]

Abstract Data mining has been an active research area for a couple of decades, yet the complicated nature of data mining is still not fully understood. One common misunderstanding of data mining is: Give me the data set, and data mining tools will show me the hidden knowledge. However, this thinking is quite naive, and is not realistic in many real world applications. In this paper, we explore extended data mining, which has the ultimate goal of automatically collecting additional data when needed for effective data mining. Existing web crawling and scraping techniques can be incorporated, but additional steps are still needed. In this paper, we examine important technical aspects for extended data mining via web crawling and scraping. [ABSTRACT FROM AUTHOR]

Abstract Knowledge management plays a significant role in organizations; supporting organizations to deal effectively with changes, increasing their productivity and paving the way to development and innovation. Several scientific studies have addressed the relevance of applying knowledge management initiatives to improve projects as well as organizations that conduct projects. This paper will look at the interaction between knowledge management and big data within the context of projects. In this regard, this paper will discuss, among other things, (1) how big data can contribute to enhance knowledge management in projects and project-based organizations (2) what kind of pitfalls, challenges and opportunities that are associated with the interplay between knowledge management and big data (3) how this interplay can improve projects so that the projects can be carried out effectively and efficiently. These three questions are addressed by taking into consideration some of the important, underlying issues that are essential for ensuring improved decision making and performance in projects and project-based organizations. [ABSTRACT FROM AUTHOR]

Abstract In recent years the concept of shared leadership has begun to receive notable attention. Prior research has proven that teams with a shared leadership structure tend to outperform those with a traditional vertical leadership structure. However, there is a dearth of research on the factors which may influence the relationship between shared leadership and team performance. This paper expands this debate by providing insight into moderating factors and aspects to be considered on assembling teams for shared leadership in order to facilitate team effectiveness. An analysis based on a systematic literature review was undertaken, addressing what potential moderating factors affect the relationship between shared leadership and team performance. The search strategy identified 15,000 studies, of which 9 papers were selected for further inquiry. We found that when there are multiple team members collaborating and working towards shared goals the team's overall performance improves. Shared leadership typology, personality composition and complexity of work are moderator factors that positively affect the relationship between shared leadership and team performance. On the other hand, the team type and the method used were found to not have a significant effect on project results. [ABSTRACT FROM AUTHOR]

Abstract In the last decade, Enterprise Architecture (EA) has been proposed to have the potential to improve and support strategic alignment between business and IT. This paper reviews the literature on cross-domain strategic alignment, as well as on Enterprise Architecture, and presents a new model to depict strategic alignment between business and IT by augmenting the widely cited Strategic Alignment Model (SAM) with an Enterprise Architecture framework, The Open Group Architecture Framework (TOGAF). The contribution of this paper is that it intends to present a holistic, generic model by synthesizing the SAM with the constructs of TOGAF to present a more comprehensive technique of modelling strategic alignment of business and IT. Also, the model illustrates this using Enterprise Systems as the chosen IT platform. Subsequently, the proposed model will be tested using empirical data from case studies and the results will be presented in another paper. [ABSTRACT FROM AUTHOR]

Advanced metering technologies coupled with informatics creates an opportunity to form digital multi-utility service providers. These providers will be able to concurrently collect a customers’ medium-high resolution water, electricity and gas demand data and provide user-friendly platforms to feed this information back to customers and supply/distribution utility organisations. Providers that can install low-cost integrative systems will reap the benefits of derived operational synergies and access to mass markets not bounded by historical city, state or country limits. This paper provides a vision of the required transformative process and features of an integrated multi-utility service provider covering the system architecture, opportunities and benefits, impediments and strategies, and business opportunities. The heart of the paper is focused on demonstrating data modelling processes and informatics opportunities for contemporaneously collected demand data, through illustrative examples and four informative water-energy nexus case studies. Finally, the paper provides an overview of the transformative R&D priorities to realise the vision. [ABSTRACT FROM AUTHOR]

Due to increasingly customised manufacturing, unpredictable ambient working conditions in shop floors and stricter requirements on sustainability, it is challenging to achieve energy efficient optimisation for machining processes. This paper presents a novel Cyber Physical System (CPS) and Big Data enabled machining optimisation system to address the above challenge. The innovations and characteristics of the system include the following four aspects: (1) a novel process of “scheduling, monitoring/learning, rescheduling” is designed to enhance system adaptability during manufacturing lifecycles; (2) an innovative energy model to support energy efficient optimisation over manufacturing lifecycles is developed. The energy model, which is enabled by CPS, Big Data analytics and intelligent learning algorithms, considers dynamic and aging conditions of machine tool systems during manufacturing lifecycles; (3) an effective evolutional algorithm based on Fruit Fly Optimisation (FFO), is applied to generate an adaptive energy efficient schedule, and improve schedule when there are significantly varying working conditions and adjustments on the schedule are necessary (that is rescheduling); (4) the system has been successfully deployed into European machining companies to verify capabilities. According to the results, around 40% energy saving and 30% productivity improvement have been achieved in the companies. A practical case study presented in this paper demonstrates the effectiveness and great potential of applicability of the system in practice. [ABSTRACT FROM AUTHOR]

Large amount of data from social networks needs to be shared, distributed and indexed in a parallel structure to be able to make best use of the data. Neo4j High Availability (Neo4jHA) is a popular open-source graph database used for query handling on large social data. This paper analyses how storing and indexing of social data across machines can be carried out by placing all the related information on the same or adjacent machines, with replication. The social graph data allocation problem referred to as Neo4jHA allocation has proved to be NP-Hard in this paper. An integration of Best Fit Decreasing algorithm with Ant Colony Optimization based metaheuristics is proposed for data allocation in a distributed architecture of Neo4jHA. The evaluation of the algorithm is carried out by simulation. The query processing efficiency is compared with other heuristic algorithms like First Fit, Best Fit, First Fit Decreasing and Best Fit Decreasing found in literature. A Skip List index was constructed on Neo4jHA of every machine after the implementation of the proposed allocation strategy for enhancing the query processing efficiency. The results illustrate how the proposed algorithm outperforms other data allocation approaches in query execution with and without an index. [ABSTRACT FROM AUTHOR]

Most recently, the large scale graphs with billions of edges and nodes have become quite prevalent and significant. These graphs are intensely being used in complex networks associated with the package of big data like social networks etc. some of common challenges associated with these graphs that hinder the performance of complex systems and needs to be addressed are the huge number of nodes and edges present in the data, diverse types of edges and nodes, significant amount of important information is not available and many clustering problems are NP-hard. As a matter of demand, analyzing and processing graphs has came up as a challenging issue faced by the big data researchers across the globe. In the light of the similar context, this research paper addresses and investigates validation techniques and methodology for various existing algorithms like edge betweenness, walktrap, leading eigen vector, and infomap for the datasets like Zachary karate club network and Immunograph. This research paper also proposed an algorithm namely random walk fast greedy and compared it with existing algorithms. The implementation has been carried out on R version 3.3.2. The authors have reported and analyzed the comparative performance characteristics of these algorithms promising to contribute towards the large scale graph community for complex systems and higher analytical inferences. The results achieved while implementation depicts markable improvement as compared with the current state of art techniques. [ABSTRACT FROM AUTHOR]

Chinese urbanization has generated great impacts on the world since the reform and opening up. However, urban problems, e.g., environmental pollution, resources shortage, and traffic jam, have been more and more serious for urban management and development. Smart city has been put forward as an effective approach to achieve better urban management recently. Smart city aims to realize the integration of municipal service, business, transportation, water, energy source and other urban sub-systems through close combination of human wisdom and information communication techniques (ICTs). As a result, the link and synergy of information could be ultimately established with ICTs, e.g., internet, internet of things, cloud computing. Yet, few studies have been conducted to systematically link smart city with big data in China. This paper aims to put forward a development framework of smart city with Chinese characteristics against the background of big data. Key actions, including rational planning of city infrastructures, the establishment and improvement of long-acting mechanism, the effective performance of city managerial function, are proposed to realize the development idea. Meanwhile, this paper also investigates the risks embedded in development of smart city with Chinese characteristics, e.g., information safety, weak emergency responding capacity and poor independent research and development capacity of core technology. This study can facilitate Chinese local governments to systematically plan smart city before clinging the hot concept in a rush. [ABSTRACT FROM AUTHOR]

Big Data has become very useful in many fields since it provides answers to many important questions that can significantly enhance decision making and process optimization. One of the most interesting domains in big data is the prediction of human features, facts and behaviors. In this paper a new and effective algorithm to predict the nationality of Twitter users is proposed. The proposed algorithm tries to prognosticate the Twitter user's location from their friend's location information only without needing GPS information. Although only approximately 30% of Twitter users write their location information in meaningful form, this paper proves that this percentage is enough to determine the nationality of any Twitter user correctly. The proposed algorithm is applied to estimate the thresholds that will be used to determine the nationality of Twitter users. The results show that our algorithm can correctly classify an average of 90% of the Twitter users. [ABSTRACT FROM AUTHOR]

In the last decade, we have witnessed an explosion of data volume available on the Web. This is due to the rapid technological advances with the availability of smart devices and social networks such as Twitter, Facebook, Instagram, etc. Hence, the concept of Big Data was created to face this constant increase. In this context, many domains should take in consideration this growth of data, especially, the Business Intelligence (BI) domain. Where, it is full of important knowledge that is crucial for effective decision making. However, new problems and challenges have appeared for the Decision Support System that must be addressed. Accordingly, the purpose of this paper is to adapt Extract-Transform-Load (ETL) processes with Big Data technologies, in order to support decision-making and knowledge discovery. In this paper, we propose a new approach called Big Dimensional ETL (BigDimETL) dealing with ETL development process and taking into account the Multidimensional structure. In addition, in order to accelerate data handling we used the MapReduce paradigm and Hbase as a distributed storage mechanism that provides data warehousing capabilities. Experimental results show that our ETL operation adaptation can perform well especially with Join operation. [ABSTRACT FROM AUTHOR]

Large-scale data clustering is a crucial task in addressing big data challenges. However, existing approaches often struggle to efficiently and effectively identify different types of big data, making it a significant challenge. In this paper, we propose a novel sample-based clustering algorithm, which is very simple but extremely efficient, and runs in about O (n × r) expected time, where n is the size of the dataset and r is the category number. The method is based on two key assumptions: (1) The data of each sufficient sample should have similar data distribution, as well as category distribution, to the entire data set; (2) the representative of each category in all sufficient samples conform to Gaussian distribution. It processes data in two stages, one is to classify data in each local sample independently, and the other is to globally classify data by assigning each point to the category of its nearest representative category center. The experimental results show that the proposed algorithm is effective, which outperforms other current variants of clustering algorithm. [ABSTRACT FROM AUTHOR]

Instance selection is an important preprocessing technology in data mining and machine learning. In this paper, we proposed a novel evolutionary based instance selection algorithm for big data. First, we defined a coarse granularity chromosome structure to reduce the size of search space and costs of chromosome operations(recombination and mutation, etc.). Then a stratified evolution strategy was proposed to remove the hyper parameter in classic fitness function and achieve precise control over the reduction ratio of instances. Finally, a sampling-based fitness function was proposed to reduce the time complexity. Experimental results shown that our new algorithm is efficient to complete the instance selection task on data set with millions of instances in minutes-level. The 10-fold cross-validation also proved that the selection results on many datasets have high nearest neighbor classification accuracy. • We proposed a distributed coarse granularity chromosome structure to reduce search space and ensure load balance. • We proposed a stratified evolution strategy to transform multi-objective to multiple single-objective tasks. • We proposed a sampling-based fitness function with less time complexity [ABSTRACT FROM AUTHOR]

Efficient attribute reduction algorithm capable of handling high dimensional big data is one of the hot topics of rough set theory, and some related researchers have achieved with |C| jobs. In this paper, we present the definition of a marked reduction set and propose a more efficient attribute reduction algorithm (RA-MRS). The RA-MRS includes a batch processing phase and a vibration optimization phase, which reduce the number of jobs from |C| to log 2 |C|. Additionally, we provide an effective judgment strategy based on MapReduce, which supports the exception processing mechanism of Java to interrupt and advance the current job. Finally, the proposed algorithm is implemented in parallel based on Spark computing framework. The experimental results show that the proposed RA-MRS algorithm is over 99% faster than the classical PAAR_PR algorithm and 70% faster than the algorithm in the literature (Yin et al., 2021). [ABSTRACT FROM AUTHOR]

• Integration Design: Maintains anonymity, immutability, and handles large data. • ETL Rules: New rules enable seamless integration between blockchain and big data. • Sustainable Supply Chain: Integrates traceability and carbon tracking. • Data Storage: Managing large data and complex growth in fisheries supply chains. • Anonymity-Preserving Big Data Storage: Ensures anonymity via blockchain metadata. The utilization of blockchain technology in the fishing industry has been extensively studied and implemented to address issues such as illegal fishing and carbon emissions control. However, integrating blockchain with the vast amounts of data in the fishing supply chain poses significant challenges. Challenges include managing extensive data such as photos or videos for product traceability throughout their lifecycle, compounded by the growing complexity of cross-border trade and market expansion. Additionally, blockchain's storage capacity limitations present hurdles in fully accommodating and comprehensively storing detailed supply data from a complex and expanding supply chain. While solutions like the Interplanetary File System (IPFS) have been explored for large data storage on the blockchain, this paper proposes a directly integrated blockchain solution tailored for the challenges of fishing with big data. We introduce a novel big data design that preserves blockchain's anonymity and immutability features, addressing storage limitations while maintaining the architecture's purpose. Furthermore, our proposal integrates product supply chain traceability with carbon footprint tracking, enabling comprehensive assessment based on quality, sustainability, and carbon footprint criteria. Despite the proposed solution needing to be tested in real-life situations, we conducted rigorous testing through simulation, white-box evaluation, and complexity analysis. The results demonstrate the potential of our solution to address challenges faced in fisheries supply chains, providing valuable insights for future practical implementation and validation efforts. [ABSTRACT FROM AUTHOR]

In the Big Data era, context-aware mobile recommender systems are crucial in assisting citizens and tourists in making informed decisions, providing a suitable way for users to find the relevant data. These systems should be proactive, able to detect the ideal time and location to provide recommendations for a specific item or activity. To accomplish this, push-based recommender systems can be employed, utilizing context rules to determine when a recommendation should be initiated. However, there is very limited reported experience in defining and implementing such systems and a complete generic solution that adapts flexibly to the preferences of users and protects their privacy is still missing. In this paper, we present a novel approach where appropriate types of recommendations are provided automatically, without the need for user input. Our proposal allows users to easily activate, deactivate, customize, and create rules for improved personalization. Additionally, the module that, based on the context, decides the types of recommendations required is executed on the user's mobile device, reducing wireless communication and safeguarding the user's privacy, as context data are evaluated locally. To illustrate the approach, we have developed R-Rules, a prototype for Android devices focused on the triggering of recommendation rules, which provides a friendly user interface that facilitates user personalization. We have evaluated various technological options and demonstrated the feasibility, performance, and scalability of the proposal, as well as its suitability to users' needs. • Generic architecture for mobile push-based recommendations. • Decision module executing on the user device: privacy and wireless savings. • Flexible user-defined rules to decide when to fire a specific type of recommendation. • Android prototype and extensive experimental evaluation. [ABSTRACT FROM AUTHOR]

The aim of this study is to develop new and efficient theories for handling complex and unreliable data in real-world scenarios. The proposed approach integrates two distinct theories: the Bipolar Complex Fuzzy Set (BCFS) and the Soft Set (SS), resulting in a novel and superior method compared to existing solutions. Furthermore, the value of big data analytics cannot be overstated as it provides businesses with the opportunity to use their data to find areas for development and progress. To gain insights from raw data, it must first be collected and organized. Data modeling represents these large, complex data sets in a visual format, such as a chart or diagram. However, the visualization process often results in uncertainties and inaccuracies, highlighting the need for a more robust approach to data analysis. To address this issue, this paper introduces the concept of Bipolar Complex Fuzzy Soft Relations (BCFSRs), a fuzzy decision-making method within a complex bipolar fuzzy environment that can have the advantages of both a Bipolar Complex fuzzy relation and a soft relation at the same time. In BCFSRs, an element can have degrees of membership in both the positive and negative directions, reflecting a more nuanced and versatile representation of uncertainty or ambiguity. These mathematical ideas are explained through the Cartesian product of two Bipolar Complex Fuzzy Soft Sets (BCFSSs) and serve to simplify the decision-making process by presenting the BCFSSs in a clear and concise manner. The inventive notion of the BCFSRs elucidates the combined positive and negative effects of anything with parameterization. To support organizations in making data-driven choices and obtain insights for strategic planning and inventiveness, the analysis of big data is essential in several industries, including financial services, marketing, and medical treatment, among others. To choose the optimal big data analytics for efficient operation, this research presents modeling methodologies based on BCFSRs, including the formulation and analysis of scoring functions. The validity of the proposed work is demonstrated through a comparison study with existing methods, providing valuable insights for effective data analysis. • Bipolar Complex fuzzy and soft sets are presented. • Introduced novel, and effective ideas to manage complex, unreliable data. • Presents modeling methodologies based on Bipolar Complex fuzzy soft information. • Conducted a comparative study of existing techniques. [ABSTRACT FROM AUTHOR]

• A comprehensive and up-to-date review of deep learning-based encryption for digital images is presented. • A detail overview of image encryption using deep learning models along with recent applications are discussed. • Comparative analysis of the reviewed methods and their limitations are discussed to guide future directions. With the innovation of high-throughput big data storage technology and the construction of digital information systems in media applications, images are the common and most popular media carriers and are generated and transmitted in huge quantities. Due to the significant advantages and high value of digital image content, there is an urgent demand to protect their privacy and prevent leakage. In the past few years, deep learning models have brought more options for image encryption algorithm design. This paper offers a comprehensive survey of recent digital image encryption using deep learning models. First, a strong motivation for image encryption using deep learning models along with recent applications is introduced. Next, various state-of-the-art deep learning-based encryption techniques are discussed. The technical summary of different popular techniques is then given in tabular form. Lastly, by deeply investigating existing deep learning-based encryption, we establish some important research challenges and possible solutions, including standard security metrics. [Display omitted] [ABSTRACT FROM AUTHOR]

In knowledge discovery and data mining, removing redundant and irrelevant data attributes is crucial. Traditional algorithms, however, struggle with efficiency in high-dimensional big data contexts. To solve this problem, this paper proposes a novel global search attribute reduction method namely RHC-IGWO (Rough Hypercuboid Structure via Improved Grey Wolf Optimizer) by integrating the rough hypercuboid method and Improved Grey Wolf Optimizer (IGWO) with the pheromone mechanism. The algorithm is embedded into the Apache Spark parallel computing framework (Parallel computing Rough Hypercuboid Structure via Improved Grey Wolf Optimizer, PcRHC-IGWO) to accelerate and simplify the attribute reduction process. The algorithm divides the decision table into several independent blocks, introduces the pheromone mechanism to simulate the wolf pack behavior, and uses the IGWO for global search, which is conducive to efficient local search and global information sharing between individuals. The position of the individual is initialized by calculating the relevance between the attributes, and the pheromone value is dynamically updated according to the reduction quality. This allows automatically giving more search focus to more promising attribute regions. Experiments with public and real datasets demonstrate the RHC-IGWO algorithm's significant speedup and its efficacy in maintaining or enhancing classification accuracy. Particularly noteworthy is its performance on schizophrenia datasets, where the proposed method achieves outstanding classification accuracies of 86.2%, 88.89%, and 92.86% across various classifiers. These results not only demonstrate its effectiveness but also underline its potential in advanced data analysis scenarios. Additionally, on some large-scale datasets, the time required for processing has been reduced by 85.71%, showcasing the algorithm's efficiency in handling complex and voluminous data. • This study presents the unbalanced evaluation indicators of attribute subsets by parallel computing. • The pheromone and mutation mechanisms in BGWA are combined with rough hypercuboid approach. • This study presents a distributed meta-heuristic attribute reduction via Apache Spark. [ABSTRACT FROM AUTHOR]

Data-driven methods have been regarded as desirable methods for fault detection and diagnosis (FDD) of practical chemical processes. However, with the big data era coming, how to effectively extract and present fault features is one of the keys to successful industrial applications of FDD technologies. In this paper, an extensible deep belief network (DBN) based fault diagnosis model is proposed. Individual fault features in both spatial and temporal domains are extracted by DBN sub-networks, aided by the mutual information technology. A global two-layer back-propagation network is trained and used for fault classification. In the final part of this paper, the benchmarked Tennessee Eastman process is utilized to illustrate the performance of the DBN based fault diagnosis model. [ABSTRACT FROM AUTHOR]