Матрична факторизація великих даних у промислових системах

dc.citation.epage73
dc.citation.issue2
dc.citation.journalTitleУкраїнський журнал інформаційних технологій
dc.citation.spage68
dc.citation.volume4
dc.contributor.affiliationНаціональний університет “Львівська політехніка”
dc.contributor.affiliationLviv Polytechnic National University
dc.contributor.authorГордійчук-Бублівська, О. В.
dc.contributor.authorФабрі, Л. П.
dc.contributor.authorHordiichuk-Bublivska, O. V.
dc.contributor.authorFabri, L. P.
dc.coverage.placenameЛьвів
dc.coverage.placenameLviv
dc.date.accessioned2024-03-27T08:56:58Z
dc.date.available2024-03-27T08:56:58Z
dc.date.created2022-02-28
dc.date.issued2022-02-28
dc.description.abstractСтворення нових технологій та їх впровадження в різні сфери зумовило потребу оброблення та зберігання великих обсягів даних. В промислових системах модернізація означає використання великої кількості розумних пристроїв, що виконують спеціалізовані функції, а зібрані дані використовують для управління системою та автоматизації виробничих процесів. В роботі визначено основні характеристики розумних промислових систем. Проаналізовано концепцію Промислового Інтернету речей (англ. Industrial Internet of Things, IIoT) та актуальність проблеми модернізації висобництва. Досліджено проблеми оброблення великих даних в системах Промислового Інтернету речей. Розглянуто використання рекомендаційних систем для швидкого знаходження взаємозв'язків між користувачами та послугами виробництва. Проаналізовано використання алгоритмів матричної факторизації SVD (англ. Singular-Value Decomposition) та FunkSVD для оброблення розріджених матриць даних. Проведено моделювання роботи запропонованих алгоритмів і визначено переваги FunkSVD для роботи з розрідженими даними. Встановлено, що алгоритм FunkSVD опрацьовує дані за меншу тривалість часу, ніж SVD, але це не впливає на точність результату. З'ясовано, що SVD також є складнішим у реалізації та вимагає більше обчислювальних ресурсів. Удосконалено алгоритм FunkSVD для покращення ефективності оброблення великих масивів інформації так, що використовують менше даних для формування рекомендацій. Встановлено, що модифікований метод працює швидше за звичайний, проте зберігає високу точність обчислень, що є важливим для роботи в рекомендаційних системах. Виявлено можливість надавати рекомендації користувачам промислових систем за коротший поміжок часу, в такий спосіб покращуючи їх актуальність. Запропоновано продовжувати досліження для знаходження оптимальних параметрів алгоритму FunkSVD.
dc.description.abstractThe creation of new technologies and their implementation in various fields necessitated Big Data processing and storage. In industrial systems, modernization means the use of a large number of smart devices that perform specialized functions. Data from such devices are used to control the system and automate production processes. A change in the parameters of individual components of the manufacturing system may indicate the need to adjust the global management strategy. The intelligent industrial systems main characteristics were defined in the paper. The Industrial Internet of Things concept and the relevance of the modernization problem for manufacturing were analyzed. The problems of processing Big Data in Industrial Internet of Things systems were examined in the paper. The use of recommendation systems for quickly finding relationships between users and production services was considered. The advantages of Big Data analysis by recommendation systems, which have a favourable effect on industrial enterprise efficiency were given. The use of SVD and FunkSVD matrix factorization algorithms for processing sparse data matrices was analyzed. The possibility of optimizing arrays of information, choosing the most important, and rejecting redundancy with the help of the above algorithms was determined. The proposed algorithms were simulated. The advantages of FunkSVD for working with sparse data were assigned. It was found that the FunkSVD algorithm processes the data in a shorter time than SVD, but this does not affect the accuracy of the result. The SVD is also more difficult to implement and it requires more computing resources was established. It has been shown that FunkSVD uses a lot of data to determine the relationships between it and make recommendations about the products most likely to be of interest to users. To increase the efficiency of processing large sets of information the FunkSVD algorithm was improved in such a way that it uses fewer data to generate recommendations. Based on the results of the research, the modified method works faster than the non-modified one but retains high calculation accuracy, which is important for work in recommender systems. The possibility of providing recommendations to users of industrial systems in a shorter period, thus improving their relevance, was revealed. It was proposed to continue research for finding the optimal parameters of the FunkSVD algorithm for Big Data processing
dc.format.extent68-73
dc.format.pages6
dc.identifier.citationГордійчук-Бублівська О. В. Матрична факторизація великих даних у промислових системах / О. В. Гордійчук-Бублівська, Л. П. Фабрі // Український журнал інформаційних технологій. — Львів : Видавництво Львівської політехніки, 2022. — Том 4. — № 2. — С. 68–73.
dc.identifier.citationenHordiichuk-Bublivska O. V. Matrix factorization of big data in the industrial systems / O. V. Hordiichuk-Bublivska, L. P. Fabri // Ukrainian Journal of Information Technology. — Lviv : Lviv Politechnic Publishing House, 2022. — Vol 4. — No 2. — P. 68–73.
dc.identifier.issn2707-1898
dc.identifier.urihttps://ena.lpnu.ua/handle/ntb/61558
dc.language.isouk
dc.publisherВидавництво Львівської політехніки
dc.publisherLviv Politechnic Publishing House
dc.relation.ispartofУкраїнський журнал інформаційних технологій, 2 (4), 2022
dc.relation.ispartofUkrainian Journal of Information Technology, 2 (4), 2022
dc.relation.references[1] Birul, K. (2016). A novel latent factor model for recommender system," in JISTEM – Journal of Information Systems and Technology Management, 13(3), 497–514. https://doi.org/10.4301/S1807-17752016000300008
dc.relation.references[2] Christou, I. T., Kefalakis, N., Zalonis, A., & Soldatos, J. (2020). Predictive and Explainable Machine Learning for Industrial Internet of Things Applications, 16th International Conference on Distributed Computing in Sensor Systems (DCOSS), 213–218. https://doi.org/10.1109/DCOSS49796.2020.00043
dc.relation.references[3] El Handri, K., & Idrissi, A. (2021). Parallelization of Topk Algorithm Through a New Hybrid Recommendation System for Big Data in Spark Cloud Computing Framework, IEEE Systems Journal, 5(4), 4876–4886. https://doi.org/10.1109/JSYST.2020.3019368
dc.relation.references[4] Gao, H., Qin, X., Barroso, R. J. D., Hussain, W., Xu, Y., & Yin, Y. (2022). Collaborative Learning-Based Industrial IoT API Recommendation for Software-Defined Devices: The Implicit Knowledge Discovery Perspective, IEEE Transactions on Emerging Topics in Computational Intelligence, 6(1), 66–76. https://doi.org/10.1109/TETCI.2020.3023155
dc.relation.references[5] Guo, S., & Li, C. (2020). Hybrid Recommendation Algorithm based on User Behavior, IEEE 9th Joint International Information Technology and Artificial Intelligence Conference (ITAIC), 2242–2246. https://doi.org/10.1109/ITAIC49862.2020.9339083
dc.relation.references[6] Han, X. (2022). Design and Implementation of Intelligent Logistics Equipment Scheduling Platform based on Internet of Things and Cloud Computing, IEEE 2nd International Conference on Electronic Technology, Communication and Information (ICETCI), 979–986. https://doi.org/10.1109/ICETCI55101.2022.9832062
dc.relation.references[7] Jadala, V. C., Pasupuletti, S. K., Raju, S. H., Kavitha, S., Sai Bhaba, Ch. M H, & Sreedhar, B. (2021). Need of Intenet of Things, Industrial IoT, Industry 4.0 and Integration of Cloud for Industrial Revolution, Innovations in Power and Advanced Computing Technologies (IPACT), 1–5. https://doi.org/10.1109/i-PACT52855.2021.9696696
dc.relation.references[8] Kasongo, S. M. (2021). An Advanced Intrusion Detection System for IIoT Based on GA and Tree Based Algorithms, IEEE Access, 9, 113199–113212. https://doi.org/10.1109/ACCESS.2021.3104113
dc.relation.references[9] Lin, N., Shi, Y., Zhang, T., & Wang, X. (2019). An Effective Order-Aware Hybrid Genetic Algorithm for Capacitated Vehicle Routing Problems in Internet of Things, IEEE Access, 7, 86102–86114. https://doi.org/10.1109/ACCESS.2019.2925831
dc.relation.references[10] Mantravadi, S., Schnyder, R., Møller, C., & Brunoe, T. D. (2020). Securing IT/OT Links for Low Power IIoT Devices: Design Considerations for Industry 4.0, IEEE Access, 8, 200305–200321. https://doi.org/10.1109/ACCESS.2020.3035963
dc.relation.references[11] Petrik, D., Schönhofen, F., & Herzwurm, G. (2022). Understanding the Design of App Stores in the IIoT, IEEE/ACM International Workshop on Software-Intensive Business (IWSiB), 43–50.
dc.relation.references[12] Qiu, Y., Zhu, X., & Lu, J. (2021). Fitness Monitoring System Based on Internet of Things and Big Data Analysis, IEEE Access, 9, 8054–8068. https://doi.org/10.1109/ACCESS.2021.3049522
dc.relation.references[13] Simeone, A., Zeng, Y., & Caggiano, A. (2021). Intelligent decision-making support system for manufacturing solution recommendation in a cloud framework, International Journal of Advanced Manufacturing Technology, 112. https://doi.org/10.1007/s00170-020-06389-1
dc.relation.references[14] Sun, F., & Li, X. (2021). Star Chart Recognition Algorithm Based on Singular Value Decomposition, IEEE 5th Advanced Information Technology, Electronic and Automation Control Conference (IAEAC), 124–129. https://doi.org/10.1109/IAEAC50856.2021.9391032
dc.relation.references[15] Wang, J., Wang, K., Jia, R., & Chen, X. (2020). Research on Load Clustering Based on Singular Value Decomposition and K-means Clustering Algorithm, Asia Energy and Electrical Engineering Symposium (AEEES), 831–835. https://doi.org/10.1109/AEEES48850.2020.9121555
dc.relation.references[16] Zhang, P., Wang, C., Jiang, C., & Han, Z. (2021). Deep Reinforcement Learning Assisted Federated Learning Algorithm for Data Management of IIoT, IEEE Transactions on Industrial Informatics, 17(12), 8475–8484. https://doi.org/10.1109/TII.2021.306435
dc.relation.referencesen[1] Birul, K. (2016). A novel latent factor model for recommender system," in JISTEM – Journal of Information Systems and Technology Management, 13(3), 497–514. https://doi.org/10.4301/S1807-17752016000300008
dc.relation.referencesen[2] Christou, I. T., Kefalakis, N., Zalonis, A., & Soldatos, J. (2020). Predictive and Explainable Machine Learning for Industrial Internet of Things Applications, 16th International Conference on Distributed Computing in Sensor Systems (DCOSS), 213–218. https://doi.org/10.1109/DCOSS49796.2020.00043
dc.relation.referencesen[3] El Handri, K., & Idrissi, A. (2021). Parallelization of Topk Algorithm Through a New Hybrid Recommendation System for Big Data in Spark Cloud Computing Framework, IEEE Systems Journal, 5(4), 4876–4886. https://doi.org/10.1109/JSYST.2020.3019368
dc.relation.referencesen[4] Gao, H., Qin, X., Barroso, R. J. D., Hussain, W., Xu, Y., & Yin, Y. (2022). Collaborative Learning-Based Industrial IoT API Recommendation for Software-Defined Devices: The Implicit Knowledge Discovery Perspective, IEEE Transactions on Emerging Topics in Computational Intelligence, 6(1), 66–76. https://doi.org/10.1109/TETCI.2020.3023155
dc.relation.referencesen[5] Guo, S., & Li, C. (2020). Hybrid Recommendation Algorithm based on User Behavior, IEEE 9th Joint International Information Technology and Artificial Intelligence Conference (ITAIC), 2242–2246. https://doi.org/10.1109/ITAIC49862.2020.9339083
dc.relation.referencesen[6] Han, X. (2022). Design and Implementation of Intelligent Logistics Equipment Scheduling Platform based on Internet of Things and Cloud Computing, IEEE 2nd International Conference on Electronic Technology, Communication and Information (ICETCI), 979–986. https://doi.org/10.1109/ICETCI55101.2022.9832062
dc.relation.referencesen[7] Jadala, V. C., Pasupuletti, S. K., Raju, S. H., Kavitha, S., Sai Bhaba, Ch. M H, & Sreedhar, B. (2021). Need of Intenet of Things, Industrial IoT, Industry 4.0 and Integration of Cloud for Industrial Revolution, Innovations in Power and Advanced Computing Technologies (IPACT), 1–5. https://doi.org/10.1109/i-PACT52855.2021.9696696
dc.relation.referencesen[8] Kasongo, S. M. (2021). An Advanced Intrusion Detection System for IIoT Based on GA and Tree Based Algorithms, IEEE Access, 9, 113199–113212. https://doi.org/10.1109/ACCESS.2021.3104113
dc.relation.referencesen[9] Lin, N., Shi, Y., Zhang, T., & Wang, X. (2019). An Effective Order-Aware Hybrid Genetic Algorithm for Capacitated Vehicle Routing Problems in Internet of Things, IEEE Access, 7, 86102–86114. https://doi.org/10.1109/ACCESS.2019.2925831
dc.relation.referencesen[10] Mantravadi, S., Schnyder, R., Møller, C., & Brunoe, T. D. (2020). Securing IT/OT Links for Low Power IIoT Devices: Design Considerations for Industry 4.0, IEEE Access, 8, 200305–200321. https://doi.org/10.1109/ACCESS.2020.3035963
dc.relation.referencesen[11] Petrik, D., Schönhofen, F., & Herzwurm, G. (2022). Understanding the Design of App Stores in the IIoT, IEEE/ACM International Workshop on Software-Intensive Business (IWSiB), 43–50.
dc.relation.referencesen[12] Qiu, Y., Zhu, X., & Lu, J. (2021). Fitness Monitoring System Based on Internet of Things and Big Data Analysis, IEEE Access, 9, 8054–8068. https://doi.org/10.1109/ACCESS.2021.3049522
dc.relation.referencesen[13] Simeone, A., Zeng, Y., & Caggiano, A. (2021). Intelligent decision-making support system for manufacturing solution recommendation in a cloud framework, International Journal of Advanced Manufacturing Technology, 112. https://doi.org/10.1007/s00170-020-06389-1
dc.relation.referencesen[14] Sun, F., & Li, X. (2021). Star Chart Recognition Algorithm Based on Singular Value Decomposition, IEEE 5th Advanced Information Technology, Electronic and Automation Control Conference (IAEAC), 124–129. https://doi.org/10.1109/IAEAC50856.2021.9391032
dc.relation.referencesen[15] Wang, J., Wang, K., Jia, R., & Chen, X. (2020). Research on Load Clustering Based on Singular Value Decomposition and K-means Clustering Algorithm, Asia Energy and Electrical Engineering Symposium (AEEES), 831–835. https://doi.org/10.1109/AEEES48850.2020.9121555
dc.relation.referencesen[16] Zhang, P., Wang, C., Jiang, C., & Han, Z. (2021). Deep Reinforcement Learning Assisted Federated Learning Algorithm for Data Management of IIoT, IEEE Transactions on Industrial Informatics, 17(12), 8475–8484. https://doi.org/10.1109/TII.2021.306435
dc.relation.urihttps://doi.org/10.4301/S1807-17752016000300008
dc.relation.urihttps://doi.org/10.1109/DCOSS49796.2020.00043
dc.relation.urihttps://doi.org/10.1109/JSYST.2020.3019368
dc.relation.urihttps://doi.org/10.1109/TETCI.2020.3023155
dc.relation.urihttps://doi.org/10.1109/ITAIC49862.2020.9339083
dc.relation.urihttps://doi.org/10.1109/ICETCI55101.2022.9832062
dc.relation.urihttps://doi.org/10.1109/i-PACT52855.2021.9696696
dc.relation.urihttps://doi.org/10.1109/ACCESS.2021.3104113
dc.relation.urihttps://doi.org/10.1109/ACCESS.2019.2925831
dc.relation.urihttps://doi.org/10.1109/ACCESS.2020.3035963
dc.relation.urihttps://doi.org/10.1109/ACCESS.2021.3049522
dc.relation.urihttps://doi.org/10.1007/s00170-020-06389-1
dc.relation.urihttps://doi.org/10.1109/IAEAC50856.2021.9391032
dc.relation.urihttps://doi.org/10.1109/AEEES48850.2020.9121555
dc.relation.urihttps://doi.org/10.1109/TII.2021.306435
dc.rights.holder© Національний університет “Львівська політехніка”, 2022
dc.subjectПромисловий Інтернет речей
dc.subjectсингулярне подання матриці
dc.subjectрозріджені дані
dc.subjectрекомендаційні системи
dc.subjectIndustrial Internet of Things
dc.subjectSingular-Value Decomposition (SVD)
dc.subjectsparse data
dc.subjectrecommendation systems
dc.titleМатрична факторизація великих даних у промислових системах
dc.title.alternativeMatrix factorization of big data in the industrial systems
dc.typeArticle

Files

Original bundle

Now showing 1 - 2 of 2
Thumbnail Image
Name:
2022v4n2_Hordiichuk-Bublivska_O_V-Matrix_factorization_68-73.pdf
Size:
1.64 MB
Format:
Adobe Portable Document Format
Thumbnail Image
Name:
2022v4n2_Hordiichuk-Bublivska_O_V-Matrix_factorization_68-73__COVER.png
Size:
1.84 MB
Format:
Portable Network Graphics

License bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.83 KB
Format:
Plain Text
Description: