https://doi.org/10.31449/inf.v46i3.3866 Informatica 46 (2022) 383-392 383 Big Data Intelligent Collection and Network Failure Analysis Based on Artificial Intelligence Jun Ding 1 , Roobaea Alroobaea 2 , Abdullah M. Baqasah 3 , Anas Althobaiti 4 , Rajan Miglani 5* , Harsimranjit Singh Gill 6 1 Anhui Technical College of Industry and Economy, Hefei, Anhui, 230051, China 2 Department Computer Science, College of Computers and Information Technology, Taif University, P. O. Box 11099, Taif 21944, Saudi Arabia 3 Department of Information Technology, College of Computers and Information Technology, Taif University, P. O. Box 11099, Taif 21944, Saudi Arabia 4 College of Environment and Technology, Bristol University, Bristol Bs1, United Kingdom 5 Lovely Professional University, Punjab, India 6 Guru Nanak Dev Engineering College, Ludhiana, India Emails: 1 dingjun82@163.com, 2 r.robai@tu.edu.sa, 3 a.baqasah@tu.edu.sa, 4 anasuk.tu@gmail.com, 5 rajan.16957@lpu.co.in *corresponding author Keywords: Artificial intelligence; big data; intelligent collection; network failure; BP neural network Received: February 2, 2022 To study smart data collection and network error analysis, this paper proposes intelligent data collection and network error analysis based on artificial intelligence. It examines the establishment of an enterprise-level information security situation awareness system and proposes specific information security models, architectures, and implementation methods. By designing and deploying the system, businesses can effectively detect information security threats, receive threats, filter risks, control threats, and comprehensively improve businesses' ability to detect security threats and security attacks. Test results: Through this platform, it is possible to manually intervene in the unknown threat of large data analysis in the system, and professionals can perform a detailed analysis to determine the means, goals and objectives of the attack and restore the complete picture. Intruder through artificial intelligence combined with big data knowledge and intrusion. Dimensional human characteristics. Including similar Trojans and malicious servers with different application forms, encodings, and attack principles, they "track" intruders by their general characteristics, constantly detect unknown threats, and ultimately ensure the accuracy of unknown threat detection, creating a local threat intelligence analytics platform. Practice has shown that the intelligent acquisition of large data by artificial intelligence can effectively analyze network failures. Povzetek: S pomočjo umetne inteligence je narejena analiza napak v omrežjih in zbiranje podatkov. 1 I ntr o duct i o n Artificial intelligence belongs to a key branch of computer science. Relying on the essence of intelligence, in order to generate intelligent machines similar to human intelligence, its key research objects are the application systems and technologies that simulate, expand and expand human intelligence. Artificial intelligence technology highly simulates many thinking processes and intelligent behaviors of human beings, providing great convenience for people's daily life, so it has received high attention from all fields of society [1- 2]. As shown in Figure 1, the system will investigation and analysis of the whole security device logs and network traffic after discovering offensive behavior, so as to determine the specific degree of behavior, and solve these problems as far as possible. In the enterprise passive cycle of information security defense system, the vast majority of enterprises will put more energy on the defense process, but ignore the determination and analysis of the attack cause. There is relatively little investment and research in system repair, which is usually passive repair based on patches from the original manufacturer's products. At the same time, enterprises constantly optimize and improve defense policies to improve system defense capabilities and effectively resist external attacks. The defense means of information security has been effectively optimized. Many enterprises have established a network anti-virus, terminal management, security audit, access restrictions, and integrated security systems, such as the leak was found to be able to ensure the safety of the enterprise business reliably, reduce the information security risk to the enterprise, achieve the unity of the enterprise early 384 Informatica 46 (2022) 383–392 J. Ding et al. be able to ensure the safety of the enterprise business reliably, reduce the information security risk to the enterprise, achieve the unity of the enterprise early warning, unified management and traceability, reduce information risk's influence on the enterprise normal business activities [4] . Intelligent fault diagnosis technology includes fuzzy technology, grey theory, pattern recognition, fault tree analysis, diagnosis expert system and so on. The first four technologies only use logical reasoning knowledge to some extent and partly solve the problems such as fuzzy information, incomplete information, fault classification and location in the diagnosis process, while the diagnosis expert system can take itself as a platform and integrate other diagnosis technologies to form a hybrid intelligent fault diagnosis system. The narrow sense of intelligent diagnosis technology generally refers to expert system. Due to its inherent super adaptability and learning ability, artificial intelligence has been widely used in many fields and solved many problems that are difficult to be solved by traditional methods. The unique nonlinear adaptive information processing ability of neural network overcomes the defects of traditional artificial intelligence methods in intuition, such as pattern recognition, speech recognition and unstructured information processing, and makes it successfully applied in neural expert system, pattern recognition, intelligent control, combinational optimization, prediction and other fields. The combination of neural network and other traditional methods will promote the continuous development of artificial intelligence and information processing technology. Figure 1 Intelligent collection of big data with artificial intelligence 2 Literature review Fault diagnosis technology has developed greatly from methods to means, and the emergence, development and penetration of a large number of relevant scientific and technological achievements have also promoted its development. At the same time, because of the rapid development of computer technology, the fault diagnosis technology has unprecedented application value and popularization. However, the penetration of various disciplines only changes its methods and means, and its fundamental purpose is still to obtain and interpret the information of equipment operation state, so as to ensure the normal operation of equipment and maintenance according to the situation, reduce or eliminate accidents. In all walks of life, due to the application of fault diagnosis technology, not only effectively prevent the occurrence of many serious accidents, but also achieve great economic and social benefits. Cheng, L. proposed a cloud computing based on big data, information preprocessing optimized clustering algorithm and Chinese NLP (natural language processing) sentiment tendency analysis algorithm artificial intelligence network public opinion analysis platform. Speed up the Big Data Intelligent Collection and Network Failure… Informatica 46 (2022) 383-392 385 screening speed of effective information and the speed of public sentiment-oriented analysis; ensure that under the environment of massive network data, timeliness and effectiveness of public opinion monitoring. Finally through the experiment, compared with the traditional statistical big data information analysis system, this method has fast information convergence speed, information analysis is efficient and reliable, especially after doing a good job of classification training in key areas of focus, as the amount of collected data grows, the results of public opinion-oriented analysis are also more accurate [5]. Wang, J. restored the data in combination with the technology of the system, made precise analysis of the data, and then published the specific data so that other enterprises could store and use the data through the enterprise platform [6]. Zhan, J. believes that with the continuous application of new technologies, the means and methods of attack are increasingly hidden and difficult to detect. Covert attack means that can bypass various traditional security detection and defense measures and achieve targeted attacks through careful camouflage, long-term latency and continuous penetration [7]. Mengyuan, H. Constructed artificial intelligence detection technology of malicious code through artificial search engine, based on a large number of samples of malicious software and normal software, searched for information data features existing in different samples, and constructed an effective machine learning model for security scanning of unknown programs [8]. Zhang, Z. Intelligent operation and maintenance mode of transmission network based on artificial intelligence and big data analysis ，can save labor costs, save equipment investment and improve network performance, effectively support the company's Internet-based operation transformation, effectively support the market, improve customer perception, it has good application promotion value. With the emergence and development of new technologies such as artificial intelligence, big data, cloud computing and SDN/NFV, traditional operation and maintenance technology of communication operators based on manual methods, it has been unable to meet the needs of cost and efficiency, automation and intelligent operation and maintenance technology has become an inevitable choice [9]. Karim, A. H. Research results in data analysis and visualization technology, it is possible to build an epidemic prevention and control platform based on big data and artificial intelligence technology, the platform can provide timely and accurate epidemic information for government agencies at all levels, and decision-making support for epidemic prevention and control, provide technical support for the implementation of the major policy of "highlighting key points, overall planning, classification guidance, and district implementation of policies" [10]. Hussein, H. A. T. outlines the basic meaning of network information retrieval, from FTP (File Transfer Protocol) search tools, menu-based search tools, three aspects of keyword-based search tools, analyze the classification of network information retrieval tools, and use this as a basis, put forward the application countermeasures of artificial intelligence in network information retrieval in the era of big data [11]. Raisan, A. Through barcode technology, radio frequency technology, internet of things, global positioning system technology, geographic information system technology, ERP, CRM, wide application of technology such as industrial control system, can quickly collect, process, and analyze data, promote industrial enterprises to realize the interconnection of all links in the production process. Regarding the current status of big data acquisition methods, the main problems in data acquisition methods, analyze the changes and strategies of future acquisition methods, and expounds the trend of change in the way of big data acquisition [12]. Lei, Y. will first introduce big data and artificial intelligence, after analyzing the application of artificial intelligence in computer networks in the current era of big data, in this way, it can be used as a reference for relevant people to communicate [13]. Xia, M. Can use the effective application of artificial intelligence virus detection and killing technology in enterprise information security situation awareness system can realize the effective identification and timely detection and killing of virus, and reduce the damage caused by virus to computer system [14-18].Because these studies have large loopholes, or the detection is not comprehensive enough, this paper proposes a method based on artificial intelligence on the basis of existing studies [19-27]. The design and deployment of the system, effective detection, threat perception, determination and threat risk tracking of information security threats can realize the comprehensive improvement of enterprises and their ability to detect security threats and security attacks [28-35]. 3 Introduction to theory and computer network failures The fault diagnosis of computer network is studied. Trained neural networks can store knowledge about processes and learn directly from historical fault information. The main work is as follows: 386 Informatica 46 (2022) 383–392 J. Ding et al. ①In the computer network management for computer network failure to select the appropriate data. ②Self-organizing feature mapping (SOM) neural network is used to cluster computer network faults. ③Set appropriate weights for the clustering results and add the sample data to establish the BP neural network model. ④ Computer numerical simulation, and the simulation results are compared. 3.1 Learning algorithm of BP neural network The jth neuron in the k layer of the BP neural network has the following input and output relationship:   ) , , 2 , 1 ; , 2 , 1 ( 1 1 - i ) ( ) 1 ( ) 1 ( k N k j k i k ij k j k j N j M k y W f y k                    （1 ） Among them, the connection weight of the ith node the 1  k -th layer to this node is   1  k ij W ;   k j  is the function of the node; k N is the number of nodes in layer k ; M is the total number of layers.   k j f is taken as the Sigmoid function     x e x f    1 1 . BP neural network uses error back propagation algorithm for learning, and the adjustment of weights is as follows:             1 1 1 1 1         k hj I h k hj k ij k ij y t W t W   （2 ） Among them, I is the total number of samples, 1 0    is the learning step size, and   k hj  is the error transmission term. For the output layer:             M hj j M hj M hj M hj y f y y   ˆ  （3 ） For other layers:             t W y f k hj N i k hj k hj j k hj k      1 1 1   （4 ） The output error 1  of the network is calculated as follows:       2 1 1 1 ˆ       I h N j M hj M hj M y y  （5 ） If    1 (  is the error of the preselection setting), then continue to the next round of learning to adjust the weights, otherwise, the network stops learning. The network formed by the weight of ij W after learning can achieve the desired output within the error range set by  [36-38] . 3.2 SOM network implementation process The algorithm process of SOM network learning is ① Initialization. For N input neuron bands, the connection weights are small. Select the set j S of output neurons j "adjacent neurons". Among them,   0 j S represents the "adjacent neuron" set of neuron j at time t=0,   t S j represents the set of "adjacent neurons" at time t. Area   t S j keeps shrinking with time [16] . ② Provide a new input mode X. ③ j is distance from the input and the output:             N i ij i j j t w t x W X d 1 2 （6 ） And find a neuron * j with the smallest distance, that is, a certain unit k is determined, so that for any j, there is   j k d d min  . ④ Give a surrounding neighborhood   t S k . ⑤ Correct the weight of output neuron * j "adjacent neuron":             t w t x t t w r w ij i ij ij      1 （7 ）  Gain item, gradually reduced to 0              10000 1 2 . 0 1 t t or t t   （8 ） ⑥Calculation output k o :         j j k W X f o min （9 ） Among them,   . f is generally a 0-1 function or other non-linear function. 3.3 LM and fuzzy theory There are also some different strategies, such as BP algorithm combined with other techniques such as fuzzy theory or genetic algorithm [39-43] . Big Data Intelligent Collection and Network Failure… Informatica 46 (2022) 383-392 387 Let k x be the approximate value of the k-th iteration, and F be the objective function         s v r w r w s H R M t i    1 2 （10）           T N x v x v x v x v ,..., , 2 1  in the above formula. Then the LM algorithm is:         k k T k k k k k s v s J I s H s s s 1 1          （11） J is the Jacobi matrix of F:                                                            n N N N n n x x v x x v x x v x x v x x v x x v x x v x x v x x v x J ... ... ... ... ... ... ... 2 1 2 2 2 1 2 1 2 1 1 1 (12） H is the approximate matrix of the Hesse matrix of F, which is taken as:       k k T k x J x J x H  （13） k  is greater than 0, it will be gradually used in LM algorithm. When equal to 0, it approaches Gaussian Newton algorithm. At maximum, LM drops linearly [44-51] . 4 Results and Discussion Figure 2 shows the BP neural network training process without any improvement. After adjusting the sample weight, the sampling training process using the improved LM algorithm is shown in Figure 3. From Figure 4, when the unimproved neural network is trained 100 times, there is still a big gap from the error of 10 -2 , and the neural network combined by the SOM method and the LM method, convergence is reached after 20 trainings [52- 58] . Using the above combination of SOM method and LM method, the training process is shown in Figures 4, 5 and Figures 6, 7. It can be seen from Figures 4, 5 and Figures 6, 7 and the continuous era development and the rapid progress of computer technology, in recent years, the infection types of computer virus emerge in endlessly, which seriously threatens the normal work of computer system. Through the application of artificial intelligence virus detection technology in the big data technology can improve the perception ability of enterprises to the virus, using a variety of virus location methods can improve the efficiency of the existing virus search, improve the accuracy and scientific nature of virus detection. 0 20 40 60 80 100 45 50 55 60 65 70 75 80 Training-Blue Goal-Black 100 Epochs Figure 2 Training process of the combined algorithm -2 0 2 4 6 8 10 12 14 16 18 20 -10 0 10 20 30 40 50 60 70 80 17 Epochs Training-Blue Goal-Black Figure 3 Training of the original algorithm 0 20 40 60 80 -10 0 10 20 30 40 50 60 70 80 100 Epochs Training-Blue Goal-Black Figure 4 Combined algorithm training process 388 Informatica 46 (2022) 383–392 J. Ding et al. 0 2 4 6 8 10 12 -10 0 10 20 30 40 50 60 70 12 Epochs Training-Blue Goal-Black Figure 5 Training process of the original algorithm 0 20 40 60 80 100 10 20 30 40 50 60 70 80 100 Epochs Training-Blue Goal-Black Figure 6 Combine the training process of the algorithm -2 0 2 4 6 8 10 12 14 0 10 20 30 40 50 60 70 80 14 Epochs Training-Blue Goal-Black Figure 7 Training process of the original algorithm 5 Conclusions Although neural network has achieved good results in the field of fault diagnosis, the structure and training times of neural network have great influence on the fault diagnosis ability of neural network. An insufficiently designed neural network may have poor performance in fault diagnosis. Based on large data and information security situational awareness of artificial intelligent technology for enterprise digital information security and the normal operation of the enterprise has the vital role, because the quantity of a security threat facing the enterprises growth trends, so enterprises must adopt more effective measures and means to show complete these threats, and take corresponding measures to solve it. The effective application of big data and artificial intelligence technology can improve the accuracy and accuracy of information processing, comprehensively assess the security risk status of information system, and realize the safe and orderly operation of enterprises. The main research direction in the future probably has two aspects: (1) better, fast design of the optimal neural network structure, in the fault diagnosis to achieve the best effect. If the neural network can be designed more scientifically and objectively, and can be carved scientifically with mathematical language, the neural network model can be established better and faster, laying a foundation for further research. (2) Further application of artificial intelligence. With the further development of computer science, it is believed that there will be more and better artificial intelligence models. If these intelligent algorithms are applied to the field, it is believed that in the near future there will be better results applied in the field of fault diagnosis, and further improve the scientific and intelligent fault diagnosis. Acknowledgement Anhui provincial demonstration experiment training center, “Cloud computing technology and application craftsman workshop model demonstration practice training center”, Fund number ：2020sxzx04. References: [1] Guo, A. , & Yuan, C. . (2021). Network intelligent control and traffic optimization based on sdn and artificial intelligence. Electronics, 10(6), 700. https://doi.org/10.3390/electronics10060700 [2] Hu, H. , Bo, T. , Gong, X. , Wei, W. , & Wang, H. . (2017). Intelligent fault diagnosis of the high-speed train with big data based on deep neural networks. IEEE Transactions on Industrial Informatics, 13(4), 2106-2116. https://doi.org/10.1109/tii.2017.2683528 [3] Hu, J. , Zhang, L. , Cai, Z. , & Wang, Y. . (2015). An intelligent fault diagnosis system for process plant Big Data Intelligent Collection and Network Failure… Informatica 46 (2022) 383-392 389 using a functional hazop and dbn integrated methodology. Engineering Applications of Artificial Intelligence, 45(OCT.), 119-135. https://doi.org/10.1016/j.engappai.2015.06.010 [4] Juying, Dai, Jian, Tang, Shuzhan, & Huang, et al. (2019). Signal-based intelligent hydraulic fault diagnosis methods: review and prospects. Chinese Journal of Mechanical Engineering, v.32(05), 11-32. https://doi.org/10.1186/s10033-019-0388-9 [5] Cheng, L. , & Yu, T. . (2018). Dissolved gas analysis principle-based intelligent approaches to fault diagnosis and decision making for large oil-immersed power transformers: a survey. Energies, 11(4), 913. https://doi.org/10.3390/en11040913 [6] Wang, J. , Wang, D. , Wang, S. , Li, W. , & Song, K. . (2021). Fault diagnosis of bearings based on multi- sensor information fusion and 2d convolutional neural network. IEEE Access, PP(99), 1-1. https://doi.org/10.1109/access.2021.3056767 [7] Zhan, J. , Wang, R. , Yi, L. , Wang, Y. , & Xie, Z. . (2019). Health assessment methods for wind turbines based on power prediction and mahalanobis distance. International Journal of Pattern Recognition & Artificial Intelligence, 33(2), 1951001.1-1951001.17. https://doi.org/10.1142/s0218001419510017 [8] Mengyuan, H. , D Qiaolin, Shutao, Z. , & Yao, W. . (2017). Research of circuit breaker intelligent fault diagnosis method based on double clustering. Ieice Electronics Express, 14(17), 20170463-20170463. https://doi.org/10.1587/elex.14.20170463 [9] Zhang, Z. . (2020). Big data analysis with artificial intelligence technology based on machine learning algorithm. Journal of Intelligent and Fuzzy Systems, 39(5), 1-8. https://doi.org/10.3233/jifs-191265 [10] Karim, A. H. , Hassaan, G. A. , & Hegazy, A. . (2021). Artificial neural network based intelligent fault identification of rotating machinery. International Journal of Web Engineering and Technology, 2(No 6,), 26-39. [11] Hussein, H. A. T. , Ammar, M. E. , & Hassan, M. A. M. . (2017). Three phase induction motors stator turns fault analysis based on artificial intelligence. International Journal of System Dynamics Applications, 6(3), 1-19. https://doi.org/10.4018/ijsda.2017070101 [12] Raisan, A. , Yaacob, M. M. , & Alsaedi, M. A. . (2015). Faults diagnosis and assessment of transformer insulation oil quality: intelligent methods based on dissolved gas analysis a-review. International Journal of Engineering & Technology, 4(1), 54. https://doi.org/10.14419/ijet.v4i1.3941 [13] Lei, Y. , Jia, F. , Lin, J. , Xing, S. , & Ding, S. X. . (2016). An intelligent fault diagnosis method using unsupervised feature learning towards mechanical big data. IEEE Transactions on Industrial Electronics, 63(5), 3137-3147. https://doi.org/10.1109/tie.2016.2519325 [14] Xia, M. , Li, T. , Liu, L. , Xu, L. , & Silva, C. . (2017). An intelligent fault diagnosis approach with unsupervised feature learning by stacked denoising autoencoder. IET Science Measurement ? Technology, 11(6), 687-695. https://doi.org/10.1049/iet- smt.2016.0423 [15] E. -M. Amhoud, M. Chafii, A. Nimr and G. Fettweis, "OFDM with Index Modulation in Orbital Angular Momentum Multiplexed Free Space Optical Links," 2021 IEEE 93rd Vehicular Technology Conference (VTC2021-Spring), 2021, pp. 1-5, doi: 10.1109/VTC2021-Spring51267.2021.9448928. https://doi.org/10.1109/vtc2021- spring51267.2021.9448928 [16] Gill, H. S., Singh, T., Kaur, B., Gaba, G. S., Masud, M., & Baz, M. (2021). A Metaheuristic Approach to Secure Multimedia Big Data for IoT-Based Smart City Applications. Wireless Communications and Mobile Computing, 2021. https://doi.org/10.1155/2021/7147940 [17] Kumar, A., Sehgal, V . K., Dhiman, G., Vimal, S., Sharma, A., & Park, S. (2021). Mobile networks-on-chip mapping algorithms for optimization of latency and energy consumption. Mobile Networks and Applications, 1-15. https://doi.org/10.1007/s11036-021-01827-0 [18] Boguszewicz, C., Boguszewicz, M., Iqbal, Z., Khan, S., Gaba, G., Suresh, A., & Pervaiz, B. The Fourth Industrial Revolution-Cyberspace Mental Wellbeing: Harnessing Science & Technology for Humanity. [19] E. Amhoud, G. R. Othman and Y . Jaouën, "Concatenation of Space-Time Coding and FEC for Few- Mode Fiber Systems," in IEEE Photonics Technology Letters, vol. 29, no. 7, pp. 603-606, 1 April1, 2017, doi: 10.1109/LPT.2017.2675919. https://doi.org/10.1109/lpt.2017.2675919 390 Informatica 46 (2022) 383–392 J. Ding et al. [20] E. -M. Amhoud et al., "Experimental Demonstration of Space-Time Coding for MDL Mitigation in Few-Mode Fiber Transmission Systems," 2017 European Conference on Optical Communication (ECOC), 2017, pp. 1-3, doi: 10.1109/ECOC.2017.8345841. https://doi.org/10.1109/ecoc.2017.8345841 [21] Gaba, G.S. (2021). Privacy-Preserving Authentication and Key Exchange Mechanisms in Internet of Things Applications (Doctoral Dissertation, Lovely Professional University Punjab). [22] Choudhary, K., & Gaba, G. S. (2021). Artificial intelligence and machine learning aided blockchain systems to address security vulnerabilities and threats in the industrial Internet of things. Intelligent Wireless Communications, 329. https://doi.org/10.1049/pbte094e_ch13 [23] Zerhouni, K., Amhoud, E. M., & Chafii, M. (2021). Filtered Multicarrier Waveforms Classification: A Deep Learning-Based Approach. IEEE Access, 9, 69426- 69438. https://doi.org/10.1109/access.2021.3078252 [24] Gaba, G. S., Kumar, G., Monga, H., Kim, T. H., Liyanage, M., & Kumar, P. (2020). Robust and lightweight key exchange (LKE) protocol for industry 4.0. IEEE Access, 8, 132808-132824. https://doi.org/10.1109/access.2020.3010302 [25] Sharma, A., & Kumar, N. (2021). Third eye: an intelligent and secure route planning scheme for critical services provisions in internet of vehicles environment. IEEE Systems Journal. https://doi.org/10.1109/jsyst.2021.3052072 [26] Kumar, P., & Gaba, G. S. (2020). Biometric‐based robust access control model for industrial internet of things applications. IoT Security: Advances in Authentication, 133-142. https://doi.org/10.1002/9781119527978.ch7 [27] M. Hedabou. Cryptography for addressing Cloud Computing Security, Privacy and Trust Issues. Book on Computer and Cyber Security: Principles, Algorithm, Applications and Perspective. CRC Press, Francis and Taylor Publisher. USA, 2018. https://doi.org/10.1201/9780429424878-11 [28] Z. Iggaramen, M. Hedabou. FADETPM: Novel approach of file assured deletion based on trusted platform module. In Lecture Notes in Networks and Systems, vol. 49, pp. 49-59. Springer Verlag, 2017. https://doi.org/10.1007/978-3-319-97719-5_4 [29] Azougaghe, M. Hedabou, M. Belkasmi. An Electronic Voting System Based On Homomorphic Encryption and Prime Numbers. In International Conference On Information Assurance and Security. Marrakech 2015. https://doi.org/10.1109/isias.2015.7492759 [30] Bentajer, M. Hedabou. AN IBE-Based Design For Assured Deletion In Cloud Storage. In Journal of Cryptologia vol 141, pp. 559-564. Springer-Verlag, 20119. https://doi.org/10.1080/01611194.2018.1549123 [31] Gaba, G. S., Kumar, G., Monga, H., Kim, T. H., & Kumar, P. (2020). Robust and lightweight mutual authentication scheme in distributed smart environments. IEEE Access, 8, 69722- 69733. https://doi.org/10.1109/access.2020.2986480 [32] M. Hedabou. Some Ways to secure elliptic curves cryptosystems. In Journal of Advances in Cliford Algebras, Vol 18, pp 677-688, 2008. https://doi.org/10.1007/s00006-008-0093-8 [33] Gaba, G. S., Kumar, G., Kim, T. H., Monga, H., & Kumar, P. (2021). Secure device-to-device communications for 5g enabled internet of things applications. Computer Communications, 169, 114-128. https://doi.org/10.1016/j.comcom.2021.01.010 [34] Sharma, A., Podoplelova, E., Shapovalov, G., Tselykh, A., & Tselykh, A. (2021). Sustainable Smart Cities: Convergence of Artificial Intelligence and Blockchain. Sustainability, 13(23), 13076. https://doi.org/10.3390/su132313076 [35] Bentajer, M. Hedabou,K. Abouelmehdi, S. ELFEZAZI. CS-IBE : A Data Confidentiality System in Public Cloud Storage System. In Procedia Computer Science vol 141, pp. 559-564. Elsevier, 2018. https://doi.org/10.1016/j.procs.2018.10.126 [36] Azougaghe, M. Hedabou, O. Oualhaj, M Belkasmi, A. Kobbane. Many-to -One matching game towards secure virtual machine migrating in cloud computing. International Conference on Advanced Communication System and Information Security. Marrakech, 2016. https://doi.org/10.1109/acosis.2016.7843922 Big Data Intelligent Collection and Network Failure… Informatica 46 (2022) 383-392 391 [37] Masud, M., Gaba, G. S., Choudhary, K., Hossain, M. S., Alhamid, M. F., & Muhammad, G. (2021). Lightweight and anonymity-preserving user authentication scheme for IoT-based healthcare. IEEE Internet of Things Journal. https://doi.org/10.1109/jiot.2021.3080461 [38] Sharma, A., Singh, P. K., Sharma, A., & Kumar, R. (2019). An efficient architecture for the accurate detection and monitoring of an event through the sky. Computer Communications, 148, 115-128. https://doi.org/10.1016/j.comcom.2019.09.009 [39] Masud, M., Gaba, G. S., Choudhary, K., Alroobaea, R., & Hossain, M. S. (2021). A robust and lightweight secure access scheme for cloud based E-healthcare services. Peer-to-peer Networking and Applications, 14(5), 3043-3057. https://doi.org/10.1007/s12083-021-01162-x [40] M. Hedabou. A Frobenius Map Approach for an Efficient and Secure Multiplication on Koblitz curves. International Journal of Network Security, Vol. 3, N. 2, PP.233-237. 2006. [41] Sharma, A., Georgi, M., Tregubenko, M., Tselykh, A., & Tselykh, A. (2022). Enabling Smart Agriculture by Implementing Artificial Intelligence and Embedded Sensing. Computers & Industrial Engineering, 107936. https://doi.org/10.1016/j.cie.2022.107936 [42] H. Boukhriss, M. Hedabou, A. Azougaghe New Technique of Localization a Targeted Virtual. In Proceedings of the 5th International Workshop on Codes, Cryptography and Communication Systems, El Jadida November 27-28, 2014. https://doi.org/10.1109/wcccs.2014.7107907 [43] Liu, Z. , Dai, C. , Hu, K. , & He, S. . (2016). A new search algorithm of mbd based on spider web and its application in power distribution network fault diagnosis. International Journal of Artificial Intelligence Tools, 25(02), 1650002. https://doi.org/10.1142/s0218213016500020 [44] Wang, X. , Su, Y. , Li, Q. , & Han, F. . (2021). Research on intelligent operation and maintenance management method of enterprise it. Journal of Physics: Conference Series, 1732(1), 012059 (7pp). https://doi.org/10.1088/1742-6596/1732/1/012059 [45] Yang, Z. , & Yin, R. . (2017). Design and research of electronic circuit fault diagnosis based on artificial intelligence. Revista de la Facultad de Ingenieria, 32(12), 766-772. [46] Qiang, L. I. , Wenbin, W. , & Xue, L. . (2015). Intelligent recognition of axis orbits with fish-based algorithms and neural networks with mentors. Shuili Fadian Xuebao/Journal of Hydroelectric Engineering, 34(6), 191-196. [47] Stéfano Frizzo Stefenon, Silva, M. C. , Bertol, D. W. , Meyer, L. H. , & Nied, A. . (2019). Fault diagnosis of insulators from ultrasound detection using neural networks. Journal of Intelligent and Fuzzy Systems, 37(5), 6655-6664. https://doi.org/10.3233/jifs-190013 [48] Chen, L. , Lan, S. , & Jiang, S. . (2019). Elevators fault diagnosis based on artificial intelligence. Journal of Physics: Conference Series, 1345(4), 042024 (10pp). https://doi.org/10.1088/1742-6596/1345/4/042024 [49] Bode, G. , Thul, S. , Baranski, M. , & D Müller. (2020). Real-world application of machine-learning- based fault detection trained with experimental data. Energy, 198(May1), 117323.1-117323.8. https://doi.org/10.1016/j.energy.2020.117323 [50] Noureldeen, O. , Hamdan, I. , & Hassanin, B. . (2019). Design of advanced artificial intelligence protection technique based on low voltage ride-through grid code for large-scale wind farm generators: a case study in egypt. SN Applied Sciences, 1(6), 515-. https://doi.org/10.1007/s42452-019-0538-9 [51] Liu, Q. , & Huang, Z. . (2020). Research on intelligent prevention and control of covid-19 in china's urban rail transit based on artificial intelligence and big data. Journal of Intelligent and Fuzzy Systems, 39(21), 1- 6. https://doi.org/10.3233/jifs-189307 [52] Xu, K. , Li, S. , Li, R. , Lu, J. , & Zeng, M. . (2021). Deep domain adversarial method with central moment discrepancy for intelligent transfer fault diagnosis. Measurement Science and Technology, 32(12), 124005 (16pp). https://doi.org/10.1088/1361-6501/ac20f1 [53] Samara, S. , & Natsheh, E. . (2020). Intelligent pv panels fault diagnosis method based on narx network and linguistic fuzzy rule-based systems. Sustainability, 12(5), 2011. https://doi.org/10.3390/su12052011 [54] Lee, K. , Han, S. , Pham, V. H. , Cho, S. , & Lee, S. W. . (2021). Multi-objective instance weighting-based 392 Informatica 46 (2022) 383–392 J. Ding et al. deep transfer learning network for intelligent fault diagnosis. Applied Sciences, 11(5), 2370. https://doi.org/10.3390/app11052370 [55] Li, S. , & Zhou, D. . (2016). Study on a new fault diagnosis method based on combining intelligent technologies. International Journal of Multimedia and Ubiquitous Engineering, 11(6), 61-72. https://doi.org/10.14257/ijmue.2016.11.6.06 [56] P. Ahmad et al., "MH UNet: A Multi-Scale Hierarchical Based Architecture for Medical Image Segmentation," in IEEE Access, vol. 9, pp. 148384- 148408, 2021, doi: 10.1109/ACCESS.2021.3122543. https://doi.org/10.1109/access.2021.3122543 [57] M. A. Razzaq et al., "The 3-Axis Scalable Service- Cloud Resource Modeling for Burst Prediction Under Smart Campus Scenario," in IEEE Access, vol. 9, pp. 116927-116941, 2021, https://doi.org/10.1109/access.2021.3105539 [58] Abbas, A., Alroobaea, R., Krichen, M. et al. Blockchain-assisted secured data management framework for health information analysis based on Internet of Medical Things. Pers Ubiquit Comput (2021). https://doi.org/10.1007/s00779-021-01583-8