Industrial Big Data Analytics for Cognitive Internet of Things: Wireless Sensor Networks, Smart Computing Algorithms, and Machine Learning Techniques.
Cognitive Industrial Internet of Things supplies first-rate performance of interacting, computing, supervising, and cutting-edge machine intelligence (Gutu, 2018; Klierova and Kutik, 2017; Meila, 2018; Nica et al., 2018; Popescu Ljungholm, 2018) for advancing smart Industrial Internet of Things applications, e.g. Industry 4.0 and cognitive manufacturing. (Hu et al., 2018) Connected Cognitive Internet of Things devices and sensors generate large volumes of information. Cognitive systems collect data from their encounters and thus enhance their operation when carrying out recurrent assignments. (Gad et al., 2018)
2. Conceptual Framework and Literature Review
The advancement of coherent space and terrestrial interaction and networking technologies offers significant technical backing for the promotion of the Internet of Things. (Jia and Guo, 2019) Industrial Internet of Things constitutes a direct catalyst for manufacturing upgrading. (Zhang et al., 2018) Network devices in the Internet of Things are typically equipped with incongruous sensors and actuators making up lossy and low-powered infrastructure, and through access networks with multifarious technologies (Bratu, 2018; Hoffman and Friedman, 2018; Krizanova et al., 2019; Nelson, 2018; Nica, 2018; Popescu et al., 2017) being connected to the Internet for the purpose of transferring data and sharing resources. (Gheisari and Tahavori, 2019) Big data technology can supply swift computing and vast stowage via parallel computing and distributed storage systems. (Wu et al., 2019) Cognitive Internet of Things improves the effectiveness of intelligence in smart objects that can take autonomous decisions in any setting. (Makkar and Kumar, 2019) For Cognitive Internet of Things, inadequacies in sensing data coverage lead to fatality and social turmoil. (Liu et al., 2019)
3. Methodology and Empirical Analysis
We inspected, used, and replicated survey data from BCG, CIO, EY, Gartner, PwC, and Statista, performing analyses and making estimates regarding how Industry 4.0 is delivering revenue, cost and efficiency gains (%) and top technologies being considered in-line with organizations' strategic plan (%). Structural equation modeling was used to analyze the data and test the proposed conceptual model.
4. Results and Discussion
In Internet of Things, intelligent decisions are taken in conformity with the data extracted from unprocessed information through smart devices. (Zafar et al., 2019) Most devices in the Internet of Things have insufficient processing power, determinate storage capacity and energy limitations. (Gheisari and Tahavori, 2019) Internet of Things carries out the service-oriented design that facilitates the interaction among smart objects. (Makkar and Kumar, 2019) Relying on cognitive computing in putting into operation smart manufacturing, Industrial Internet of Things is considerably becoming more efficient. (Zhang et al., 2018) Cloud-assisted Cognitive Internet of Things encompasses relevant data analytics potentiality derived from the computing and information storage performance of cloud virtual machines. (Zhan et al., 2018) (Tables 1-4)
5. Conclusions and Implications
The standard Internet of Things cannot adequately conform to the growing application performance guidelines (Devine, 2017; Kanovska, 2018; Lazaroiu, 2018; Nica et al., 2014; Pilkington, 2018; Popescu et al., 2018) by being chiefly concerned with how to enable and connect objects to sense the physical realm and subsequently to distribute the gathered information online. (Gheisari and Tahavori, 2019) The services of an incisive Industrial Internet of Things assimilation with cognitive computing can be suggestive, prescriptive, or instructive, being more inspiring and robust by design options to make a new category of issues computable. (Zhang et al., 2018) Cognitive Internet of Things can obtain important data from a range of Internet of Things devices. By carrying out truth identification, factual sensory information can be collected, significantly advancing the validness of Cognitive Internet of Things applications. (Zhang et al., 2019)
The interviews were conducted online and data were weighted by five variables (age, race/ethnicity, gender, education, and geographic region) using the Census Bureau's American Community Survey to reflect reliably and accurately the demographic composition of the United States. The precision of the online polls was measured using a Bayesian credibility interval.
This paper was supported by Grant GE-1473862 from the Center for Big Data-driven Algorithmic Decision-Making, Portland, OR.
All authors listed have made a substantial, direct and intellectual contribution to the work, and approved it for publication.
Conflict of Interest Statement
The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.
Bratu, S. (2018). "The Ethics of Algorithmic Sociality, Big Data Analytics, and Data-Driven Research Patterns," Review of Contemporary Philosophy 17: 100-106.
Devine, N. (2017). "Aims of Education in a Post-Neoliberal Context," Knowledge Cultures 5(6): 96-107.
Gad, R., M. Talha, A. A. Abd El-Latif, M. Zorkany, A. El-Sayed, N. El-Fishawy, et al. (2018). "Iris Recognition Using Multi-Algorithmic Approaches for Cognitive Internet of Things (CIoT) Framework," Future Generation Computer Systems 89: 178-191.
Gheisari, S., and E. Tahavori (2019). "CCCLA: A Cognitive Approach for Congestion Control in Internet of Things Using a Game of Learning Automata," Computer Communications 147: 40-49.
Gutu, G. (2018). "Interferential Creativity: The Case of Paul Celan," Creativity 1(2): 113-135.
Hoffman, S. F., and H. H. Friedman (2018). "Machine Learning and Meaningful Careers: Increasing the Number of Women in STEM," Journal of Research in Gender Studies 8(2): 11-27.
Hu, L., D. Tian, and K. Lin (2018). "Cognitive Industrial Internet of Things," Mobile Networks and Applications 23: 1607-1609.
Jia, M., and Q. Guo (2019). "Intelligent Cognitive Internet of Integrated Space and Terrestrial Things," Mobile Networks and Applications 24: 1924-1925.
anovska, L. (2018). "Smart Services and Their Benefits for Manufacturers from a Global Perspective," Ekonomicko-manazerske spektrum 12(2): 46-56.
Klierova, M., and J. Kutik (2017). "One Stop Government--Strategy of Public Services for Citizens and Businesses in Slovakia," Administratie si Management Public 28: 66-80.
Krizanova, A., G. Lazaroiu, L. Gajanova, J. Kliestikova, M. Nadanyiova, and D. Moravcikova (2019). "The Effectiveness of Marketing Communication and Importance of Its Evaluation in an Online Environment," Sustainability 11: 7016.
Lazaroiu, G. (2018). "Participation Environments, Collective Identities, and Online Political Behavior: The Role of Media Technologies for Social Protest Campaigns," Geopolitics, History, and International Relations 10(2): 58-63.
Liu, Y., A. Liu, T. Wang, X. Liu, and N. N. Xiong (2019). "An Intelligent Incentive Mechanism for Coverage of Data Collection in Cognitive Internet of Things," Future Generation Computer Systems 100: 701-714.
Makkar, A., and N. Kumar (2019). "Cognitive Spammer: A Framework for PageRank Analysis with Split by Over-sampling and Train by Under-Fitting," Future Generation Computer Systems 90: 381-404.
Meila, A. D. (2018). "Sustainable Urban Mobility in the Sharing Economy: Digital Platforms, Collaborative Governance, and Innovative Transportation," Contemporary Readings in Law and Social Justice 10(1): 130-136.
Nelson, C. (2018). "Beyond Prometheus: Creativity, Discourse, Ideology, and the Anthropocene," Knowledge Cultures 6(2): 111-131.
Nica, E., G. H. Popescu, E. Nicolaescu, and V. D. Constantin (2014). "The Effectiveness of Social Media Implementation at Local Government Levels," Transylvanian Review of Administrative Sciences 10(SI): 152-166.
Nica, E., C. Manole, and C. I. Stan (2018). "A Laborless Society? How Highly Automated Environments and Breakthroughs in Artificial Intelligence Bring About Innovative Kinds of Skills and Employment Disruptions, Altering the Nature of Business Process and Affecting the Path of Economic Growth," Journal of Self-Governance and Management Economics 6(4): 25-30.
Nica, E. (2018). "Will Robots Take the Jobs of Human Workers? Disruptive Technologies that May Bring About Jobless Growth and Enduring Mass Unemployment," Psychosociological Issues in Human Resource Management 6(2): 56-61.
Pilkington, O. A. (2018). "Presented Discourse in Popular Science Narratives of Discovery: Communicative Side of Thought Presentation," Linguistic and Philosophical Investigations 17: 7-28.
Popescu Ljungholm, D. (2018). "Regulation of Automated Individual Decision-Making and Artificially Intelligent Algorithmic Systems: Is the GDPR a Powerful Enough Mechanism to Protect Data Subjects?," Analysis and Metaphysics 17: 116-121.
Popescu, G. H., V. Sima, E. Nica, and I. G. Gheorghe (2017). "Measuring Sustainable Competitiveness in Contemporary Economies--Insights from European Economy," Sustainability 9(7): 1230.
Popescu, G. H., I. E. Petrescu, and O. M. Sabie (2018). "Algorithmic Labor in the Platform Economy: Digital Infrastructures, Job Quality, and Workplace Surveillance," Economics, Management, and Financial Markets 13(3): 74-79.
Wu, P., Z. Lu, Q. Zhou, Z. Lei, X. Li, M. Qiu, et al. (2019). "Big Data Logs Analysis Based on seq2seq Networks for Cognitive Internet of Things," Future Generation Computer Systems 90: 477-488.
Zafar, S., R. Hussain, F. Hussain, and S. Jangsher (2019). "Interplay between Big Spectrum Data and Mobile Internet of Things: Current Solutions and Future Challenges," Computer Networks 163: 106879.
Zhan, D., L. Ye, H. Zhang, B. Fang, H. Li, Y. Liu, et al. (2018). "A High-Performance Virtual Machine Filesystem Monitor in Cloud-assisted Cognitive IoT," Future Generation Computer Systems 88: 209-219.
Zhang, Y., L. Peng, Y. Sun, and H. Lu (2018). "Intelligent Industrial IoT Integration with Cognitive Computing," Mobile Networks and Applications 23: 185-187.
Zhang, C., L. Zhu, C. Xu, K. Sharif, X. Du, and M. Guizani (2019). "LPTD: Achieving Lightweight and Privacy-Preserving Truth Discovery in CIoT," Future Generation Computer Systems 90: 175-184.
The Cognitive Automation Research Unit at CLI, New Haven, CT, USA
The School of Expertness and Valuation, The Institute of Technology and Business in Ceske Budejovice, Czech Republic
Faculty of Operation and Economics of Transport and Communications, Department of Economics, University of Zilina, Zilina, Slovak Republic
Faculty of Operation and Economics of Transport and Communications, Department of Economics, University of Zilina, Zilina, Slovak Republic
Received 29 March 2019 * Received in revised form 26 August 2019
Accepted 28 August 2019 * Available online 15 December 2019
Table 1 How Industry 4.0 is delivering revenue, cost and efficiency gains (%) Additional revenue from: Digitizing products and services within the existing portfolio 21 New digital products, services and solutions 20 Offering big data and analytics as a service 19 Personalized products and mass customization 14 Capturing high-margin business through improved 14 customer insight from data analytics Increasing market share of core products 12 Lower cost and greater efficiency from: Real-time inline quality control based on big data analytics 19 Modular, flexible and customer-tailored production concepts 13 Real-time visibility into process and product variance, 15 augmented reality and optimization by data analytics Predictive maintenance on key assets using predictive algorithms to 13 optimize repair and maintenance schedules and improve asset uptime Vertical integration from sensors through MES to real-time production 10 planning for better machine utilization and faster throughput times Horizontal integration, as well as track-and-trace of products 9 for better inventory performance and reduced logistics Digitization and automation of processes for a smarter use 8 of human resources and higher operations speed System based, real-time end-to-end planning and horizontal collaboration 7 using cloud based planning platforms for execution optimization Increased scale from increased market share of core products 6 Sources: PwC; our survey among 4,700 individuals conducted February 2019. Table 2 Technology developments that enable Service 4.0 (%) Big data and analytics develop deeper insight into customer 18 behavior, preferences, and pathways. Cloud computing manages huge data volume in open 13 systems and provide services on demand. Robotic process replaces humans in work processes that 14 automation are entirely rule based. Bionic computing interacts naturally with virtual agents, 8 digital devices, and services. Cognitive computing simulates human thought processes and 11 provide intelligent, virtual assistance. Virtualization free services from reliance on specific 8 software and hardware and ensure flexibility, adaptability, and robustness. Ubiquitous create an ongoing connection in areas as 12 connectivity and varied as on-the-spot service provision the Internet and remote monitoring. of Things Smart devices develop an ecosystem of apps and cloud 11 services that utilize high-performance devices. Augmented reality provide the necessary information when 5 needed in areas as varied as manuals, pricing, and alerts. Sources: BCG; our survey among 4,700 individuals conducted February 2019. Table 3 To what extent have you implemented, piloted, or planned to implement the following technologies within your company? (%) Digital Digital novice follower Predictive maintenance of assets 36 82 and products Manufacturing execution systems 26 75 Integrated end-to-end 31 74 supply chain planning Connectivity/ 27 71 Industrial Internet of Things Digital twin of products 21 56 and manufacturing line Collaborative robots, smart robots, 21 39 Robotic Process Automation Artificial intelligence 9 16 Virtual reality/Augmented reality 7 19 solutions Digital Digital innovator champion Predictive maintenance of assets 97 98 and products Manufacturing execution systems 94 96 Integrated end-to-end 95 100 supply chain planning Connectivity/ 95 99 Industrial Internet of Things Digital twin of products 86 98 and manufacturing line Collaborative robots, smart robots, 78 95 Robotic Process Automation Artificial intelligence 52 77 Virtual reality/Augmented reality 48 82 solutions Sources: PwC; our survey among 4,700 individuals conducted February 2019. Table 4 Top technologies being considered in-line with organizations' strategic plan (%) Virtual/Augmented/Mixed reality 35 Cognitive analytics and machine learning 68 Robotic process automation 57 Blockchain 31 Digital/Crypto-currencies 6 Conversational systems 37 Analytics on non-conventional data sources 38 3D printing 19 Sources: CIO; EY; our survey among 4,700 individuals conducted February 2019.
|Printer friendly Cite/link Email Feedback|
|Author:||Graessley, Scott; Suler, Petr; Kliestik, Tomas; Kicova, Eva|
|Publication:||Analysis and Metaphysics|
|Date:||Jan 1, 2019|
|Previous Article:||Regulating Government and Private Use of Unmanned Aerial Vehicles: Drone Policymaking, Law Enforcement Deployment, and Privacy Concerns.|
|Next Article:||Semantically Enriched Internet of Things Sensor Data in Smart Networked Environments.|