iosr-JCE   Volume-25 ~ Issue-3 ~ May - June 2023

Abstract: In developing world, virtual network plays an important role where A virtual network connects devices and virtual machines, irrespective of the location of the user is, using software. Virtual networks form their connections through internet. Virtual network has grown massively in recent years and it involves researchers from different fields. This chapter classifies these methods into two categories. The first category concerns strategies used for the network data collection, while the second category deals with strategies used for network data visualization

[1]. Article about Virtual Network Computing which was published on February 1998, Source: IEEE Xplore
[2]. By the reference of Virtual networks Isolations, Performances, and Trends project.
[3]. By the reference of Network functions virtualization on laptop installation and survey by Alireza PiranKashani,
[4]. By the reference of Computer Networks Textbook.
[5]. Technikum-wien UAS; Telecommunication and Internet Technology-vienna, Austria.

Abstract:Smart home automation leveraging Internet of Things (IoT) technologies has gained significant attention in recent years due to its potential to enhance convenience, comfort, and energy efficiency in residential environments. This paper aims to explore the challenges associated with IoT device connectivity in smart home systems and propose effective solutions to mitigate such issues. The implementation of smart home automation relies on interconnected IoT devices, which enable seamless communication and control within the ecosystem. However, the connectivity of these devices can be hindered by various factors, including wireless interference, device compatibility, network congestion, and inadequate network coverage......

[1]. Jayawardana Gubbi, Rajkumar Buyya, Slaven Mantsic, Marimuthu Palaniswami, "Internet of Things (IOT): A vision, architectural elements, and future directions", Future Generation Computer Systems (Elsevier), 2013, pp. 1645-1660.
[2]. Boban Davidovic, Aleksandm Labus, "A SMART HOME SYSTEM BASED ON SENSOR TECHNOLOGY", Electronics and Energetics vol. 29, No 3, September 2016, pp. 451 —460.
[3]. Jayashri Bangali, Arvind Shaligmm, "Energy efficient Smart home based on Wireless Sensor Network using LabVIEW', IJER, vol. 2, Issue 12, 2013, pp. 409-413.
https://iot-analytics.com/number-connected-iot-devices/
[4]. Ahamed, S., Rehman, S. U., & Xhafa, F. (2020). Smart Homes: Architectures, Technologies, and Applications. John Wiley & Sons.
[5]. Al-Fuqaha, A., Guizani, M., Mohammadi, M., Aledhari, M., & Ayyash, M. (2015). Internet of Things: A Survey on Enabling Technologies, Protocols, and Applications. IEEE Communications Surveys & Tutorials, 17(4), 2347-2376.

Abstract: Smart Transportation Systems Have Emerged As A Promising Solution For Managing Urban Traffic Congestion And Improving Overall Transportation Efficiency. One Critical Aspect Of Such Systems Is Accurate Traffic Prediction, Which Enables Proactive Traffic Management Strategies And Enhances User Experience. This Paper Proposes An Approach To Unleash The Power Of Machine Learning Techniques For Enhancing Traffic Prediction In Smart Transportation Systems. This Involves Making Predictions Based On Data From The Previous Year And Data From The Most Recent Year, Which Eventually Yields Accuracy And Mean Square Error. This Involves Making Predictions Based On Data From The Previous Year And Data From The Most Recent Year, Which Eventually Yields Accuracy And Mean Square Error......

Keywords: Intelligent Transport System (ITS), Regression, Traffic, Machine Learning, And Prediction

[1]. Vlahogianni, E. I., M. G. Karlaftis, and J. C. Golias. Optimized and Meta-Optimized Neural Networks for Short Term Traffic Flow Prediction: A Genetic Approach. Transportation Research Part C: Emerging Technologies, Vol. 13, No. 3, 2005, pp. 211–234.
[2]. Machine Learning Approach to Short-Term Traffic Congestion Prediction in a Connected Environment AmrElfar1, Alireza Talebpour2, and Hani S. Mahmassani1, National Academy of Sciences: Transportation Research Board 2018.
[3]. Big data-driven machine learning-enabled traffic flow prediction Fanhui Kong1 Jian Li1 Bin Jiang2 Tianyuan Zhang3 Houbing Song3, 2018.
[4]. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC2845248/
[5]. Hong, J. S., and Kim, Y. J. (2015). Using a multi factor pattern recognition paradigm, the urban TFP system. 16(5),2744–2755, IEEE Transactions on ITS.

Abstract: The paper is articulated in the expanded form as per APA criteria. There are fast-changing threats arising in the business world concerning technology; the rapid advancement of generative AI technology is giving birth to threats in the financial sector such as synthetic identifications by means of deep fakes or the use of AI systems to build identities that imitate existing people using very close-to-real facial images, recorded voice profiles, and identification documents to compromise Know Your Customer (KYC) and Anti-Money Laundering (AML) compliances. This backdrop of extremely intensified adversarial threats in this area of finance beginning to turn probability......

Keyword Synthetic Identity Fraud; Deepfakes; Behavioral Biometrics; Fintech Security; KYC Validation; AML Compliance; Generative AI; Anomaly Detection; Keystroke Dynamics; Facial Micro-expressions; Voice Biometrics; Regulatory Technology (RegTech); Authorized Identity; AI-Enabled Fraud Prevention

[1]. Alabdulmohsin, I. M., & Gao, X. (2022). Synthetic identity fraud detection using machine learning: A survey. IEEE Access, 10, 123456–123469.
[2]. Bhatia, A., & Singh, R. (2022). Deep learning approaches for detecting deepfake videos: A review. Journal of Information Security and Applications, 65, 103123.
[3]. Chen, Y., & Liu, Y. (2022). Behavioral biometrics for identity verification: A comprehensive survey. ACM Computing Surveys, 54(5), 1–36.
[4]. Deng, J., & Li, X. (2022). A review of deepfake detection methods: Challenges and future directions. Pattern Recognition Letters, 152, 1–10.
[5]. Feng, Y., & Zhang, H. (2022). Synthetic identity fraud in the financial sector: Detection and prevention strategies. Financial Innovation, 8(1), 1–15

Abstract: The field now has the technology to use Generative Adversarial Networks (GANs) to carry out fantastic feats at data synthesis, simulation, and content generation for artificial intelligence. Nonetheless, doing so leads us face to face with two of the most severe challenges. These are the interpretability and vulnerability to adversarial attacks. Such constraints have most likely been limiting the already compromised integration of GAN techniques in those areas where public safety is paramount, or wherein trust is indispensable. This research aims for an abstract, invoking the actions of......

Keyword Generative Adversarial Networks (GANs), Explainable AI (XAI), Adversarial AI, Interpretability, Robustness, Deep Learning, Model Security, Trustworthy AI, Adversarial Defense, Latent Space Analysis

[1]. Gupta, S. (2021). Agency, Trust, and Interpretability of Generative Adversarial Networks (GANs) (Doctoral dissertation, PhD thesis, North Carolina State University).
[2]. Sauka, K., Shin, G. Y., Kim, D. W., & Han, M. M. (2022). Adversarial robust and explainable network intrusion detection systems based on deep learning. Applied Sciences, 12(13), 6451.
[3]. Wu, C., Zhang, H., Chen, J., Gao, Z., Zhang, P., Muhammad, K., & Del Ser, J. (2022). Vessel-GAN: Angiographic reconstructions from myocardial CT perfusion with explainable generative adversarial networks. Future Generation Computer Systems, 130, 128-139.
[4]. Wang, S., Zhao, C., Huang, L., Li, Y., & Li, R. (2023). Current status, application, and challenges of the interpretability of generative adversarial network models. Computational Intelligence, 39(2), 283-314.
[5]. Carbone, G. (2023). Robustness and interpretability of neural networks' predictions under adversarial attacks