Machine Learning Meets Industrial Big Data
DOI:
https://doi.org/10.5281/zenodo.21455153Keywords:
Predictive Intelligence,Big Data Analytics,Machine Learning Models,Industry 4.0 Applications,Data-Driven Decision Making,Predictive Modeling,Artificial Intelligence Frameworks,Real-Time Data Processing,Industrial Automation,Advanced Analytics Systems.Abstract
A concept of predictive intelligence, based on industry-scale big data and supervised machine learning models, is put forth, establishing the foundations of a Predictive Intelligence Framework designed to enable trusted predictions in specific application domains. Such predictions encompass various forecasting, anomaly detection, and binary/multi-class classification tasks. An objective, evidence-based analysis of how data, models, and governance serve to enable specific applications provides a framework for the architectural, engineering, and deployment choices required for trusted predictions in the context of real-world industry use cases.
Like general artificial intelligence, industry-scale predictive intelligence encompasses multiple paradigms and tasks. These include not only the mini–brain models that perform high-level cognition on limited training data but also the predictive tasks for which data availability has reached industrial scale, enabling the use of Deep Learning on Data-Demanding Tasks. These data-driven systems are of particular interest to industry due to their inherent focus on prediction, given that prediction is often the key component of any task that requires the application of intelligence. Predictive Intelligence focuses on such tasks, whose execution in real-world scenarios has thus far remained limited owing to the need for substantial engineering effort.
References
[1]Al-Sharif M, Jones A, Nikolopoulos K (2020) Forecasting customer demand in the restaurant industry: case study of a UK casual dining chain. International Journal of Production Research 58(12):3584–3599. [Link]
[2]Alyousef W, Abou Elazm A, Zahrani A, Abou Moustafa M, Waddah H (2021) A novel big data framework for IoT based anti-fraud detection in e-business. J King Saud University - Computer and Information Sciences. [Link]
[3]Ayub A, Wong NK, Catherwood A (2018) Building intelligence and integrity in the cyber-physical systems: a framework. Computers, Materials, & Continua 59(3):867–884. doi:10.32604/cmc.2018.03393
[4]Choudhary A, Shinde K, Mukherjee S (2018) Enhancing social media sentiment prediction using hybrid machine learning model. Journal of Engineering Research and Application 5(5):89–99
[5]Colak T, Kahvecioglu E (2019) Customer and product actions clustering in big data. International Conference on Big Data and Smart City, IEEE, 62–65
[6]Dürr M, Oreopoulos A, Szumilo-Madej J, Jägerhorn J (2022) A Plant Condition Monitoring Framework that Superimposes with an Asset Integrity Management System. In O. F. A. M. De Vries, D. D. A. R. F. A. H. Willemen (Ed.), Proceedings of the SNAME 2022 Annual Meeting & Expo, 2022. The Society of Naval Architects and Marine Engineers
[7]García M, Muñoz B, Porras C, Fernández J (2023) Anomaly detection in neutron data acquired during Dismantling projects. In H. W. F. Claudio F. Macri, M. Donadeo (Ed.), Proceedings of the 11th International Nuclear Plant Life Management Conference, 2023. American Nuclear Society
[8]García M, Núñez M, de Santiago-José S (2021) Evaluation of time series and deep learning models for neutron detectors applied to dismantling projects. Proceedings of the 27th SYMPOSIUM ON NEUTRON SOURCES
[9]García A, Dreiling A, Manhart C, Miles R, Wong G (2020) Producing complex products in a low-wage environment by integrating one-piece flow in a supply chain. Journal of the Society of Manufacturing Process Engineers 2(2):207–218
[10]Güner S, Keleş A, Sönmezoglu A (2021) A survey of big data processing in manufacturing. Big Data and Cognitive Computing 5(4):52
[11]Higgins J, Schooley S (2019) Predicting spike activity in paired neuron models with extreme value theory. Heron 72(1)
[12]Hoi P, Zhang H, Zhao P, Lijwan M, Xu Y, Wang X, Hatzilygeroudis I, Yang B (2023) Data modeling framework for wheat quality detection. 2023 IEEE 11th International Conference on Cloud Computing and Big Data Analysis, 251–254. doi:10.1109/CCBDA59284.2023.001135
[13]Huang P, Pan F, Jiang H, Guofei Z (2020) A novel artificial intelligence-based model for hydrogen consumption prediction during hydrogen blistering in pure titanium. Scripta Materialia 181:78–82. [Link]
[14]Iqbal J, Muneer S, Tanveer M, Akram A, Aijaz D, Jeeva K, Frikha B (2021) Information Technolgy4life: an Affective Cold Data Warehouse Based on Big Data for World to Come. International Journal of Information Technology 13(4):1323–1340
[15]Jacovitti M, Di Giacinto F, Amici A, Di Fenzo M, Pippa L (2022) Towards remote fault localization in industrial control systems. In 2022 IEEE International Symposium on Networks, Computers and Communications (ISNCC), 1–6. doi:10.1109/ISNCC55288.2022.9820166
[16]Jiang T, Li M, Sun J, Liu H (2021) An ND-ARC intelligence model paradigm for the big data analytics based green management model in manufacturing. Journal of Cleaner Production 312:127876
[17]Kasi A, Mehta P, Kumari P, Gupta B, Van Gupta R (2021) A survey of the role of big data in software maintenance process and the development of a big-data-based intelligent maintenance framework. Journal of Software: Evolution and Process 33(7):e2333
[18]Khan MI, Mohsin S, Driankov D, Ahmad R, Mehmood A (2019) Mining takedown big-data of malicious websites for improvement of classifiers during the classification of malicious website for prevention. Journal of Business & Management 21(10):73-83
[19]Khan NA, Abida N, Ashraf E, Tripathi A (2020) A framework for efficient storage and retrieval of big data for Internet of Things. Future Generation Computer Systems 115:627–636 Magas R Matveev Y, Sudakov S (2021) Sense: a framework for rendering virutal reality application for computational evolutional chemistry. International Journal ofmbot.org
[20]Li Y, Pan H, He J, Yang C (2023) Forecasting short-term PM2.5 concentration with multiple factors based on attention mechanism and long short-term memory networks. Advances in Science, Technology and Engineering Systems Journal 8(2):414–424
[21]Li D, Yang Y, Chen X, Yang D (2023) Research on the correlation of regional economy and environment based on machine learning. Advances in Science, Technology and Engineering Systems Journal 8(2):409–413
[22]Li J, Xu P, Fan J (2019) A simple approach to implementing deep reinforcement learning for high-dimensional control tasks. Advances in Science, Technology and Engineering Systems Journal 4(9):267–275
[23]Lim D, Na YS, Yang JM, Lee O (2022) Data Quality Assessment Based on Metadata in Data Lake. 2022 International Conference on Artificial Intelligence and Computer Applications, 322–326
[24]Liu C, Wang Z, Wu M (2014) Study on intelligent parking space resource prediction based on big data. Journal of Applied Sciences 14(23):3016
[25]Maheshwar K, Almaghrabi D, Shahin M, Shafaghy M (2022) A Review Study of the Implementation of Big Data Techniques into Software Testing. 2022 IEEE International Conference on Software Testing, Verification & Validation Workshops (ICSTW), 446–451
[26]Mishra M, Badkul R, Tyagi P (2021) Prioritizing Critical Service-Delivery Factors. Journal of Services Marketing 31(4):0571–6760
[27]Murray M, Ranjan P (2020) Integrating big data technologies in production and operations management: a framework for facilitating change and innovation. International Journal of Production Economics 219:292–298. [Link]
[28]Nekrasov V, Roshchupkin V, Sokolov N, Tutubalin A (2023) Architectural Approach to Construction of Automated Monitoring Information System for Natural Food Quality in Greenhouses. Cybernetics and Systems Analysis 59(2)299–307
[29]Ome G, Makam M, Kallol S (2021) Customer Lifetime Value Prediction Using Machine Learning. 2021 International Conference on Emerging Trends in Science and Technology, 257–260.
[30]Patel S, Tiwari A (2023) A Novel Approach for Data Integrity in Cloud Using Advanced Encryption Standard. 2023 IEEE 11th International Conference on Cloud Computing and Big Data Analysis, 145–149. doi:10.1109/CCBDA59284.2023.001352
[31]Perera HM, Hossan M, Shyam S, Shubhasmita R, Danfalani J, Infra M, Renuka T (2021) A Predictive Plumbing Management Framework for Smart Cities Using Big Data. 2021 IEEE International Conference on Renewable Energy and Sustainable Energy (IRSEE), 189–194.
[32]Peng G-W, Zhu H-L, Yang S-Y, Lan J-J (2021) Cloud Service Pricing Model Based on Reputation and Cloud Computing Technology. 2021 6th International Conference on Cryptography, Security and Privacy, 160–164.
[33]Perkins S, Srivastava I (2021) Techniques to Enhance Customer Satisfaction: A Study on Improving Web Performance Using Big Data. 2021 International Conference on Emerging Trends in Science and Technology, 348–351.
[34]Philominraj S, Kumar B, Narayanasamy V (2020) A big data architecture design for the smart factory in the Industry 4.0 environment. International Journal of Systems and Service-Oriented Engineering 10(4):1–17
[35]Radovic M, Nikolopoulos K (2020) Retail demand forecasting: Time series versus regression. 2019 18th International Conference on Information Technology Based Higher Education and Training, 1–5
[36]Reddy G, Kumar R, Reddy K (2020) A Quick Survey on Predictive Analytics in Healthcare Domain by Using Big Data. International Journal of Recent Technology and Engineering 9(2):9100–9103
[37]Rohilla S, Gupta D, Gupta S (2020) A STUDY OF CRIME DATA PREDICTION USING MACHINE LEARNING. International Journal of Recent Technology and Engineering 9(2):4308–4311
[38]Safi H, Md Zahir Mohd Rani N, Bahram A (2021) A robust big data and machine learning framework for seizure prediction in patients with epilepsy. Journal of Informatics and Mathematical Sciences 13(1):1-12
[39]Sambyal S, Choudhry R, Sharma R, Wang H, Srivastava S, Kaur M (2022) A critical review of smart agriculture using big data and IoT. Agronomy 12(6):1337
[40]Sasidharan M, Gudi M, Manisha K, Maharshri R, Almutairi H (2022) A Comprehensive Survey on Voice Conversion Using Short-Time Spectro-Temporal Features and Artificial Intelligence. Information 13(10):V-V
Additional Files
Published
Issue
Section
License
Articles published in the European Advanced Journal for Science & Engineering (EAJSE) are made freely available online immediately upon publication under the terms of the Creative Commons Attribution 4.0 International License (CC BY 4.0). This license permits unrestricted use, distribution, and reproduction in any medium or format, provided the original work is properly cited. Authors retain copyright of their work. By submitting to EAJSE, authors grant the journal the right of first publication. For details, visit: https://creativecommons.org/licenses/by/4.0/
