Computing Reviews
Today's Issue Hot Topics Search Browse Recommended My Account Log In
Review Help
AI-based computer vision using deep learning in 6G wireless networks
Kamruzzaman M., Alruwaili O. Computers and Electrical Engineering102 (1):1-14,2022.Type:Article
Date Reviewed: Mar 22 2023

The development of sixth-generation (6G) wireless networks is expected to revolutionize the way we use the Internet and handle data. This new network will offer faster speeds, better security, and more reliable connections. Along with these advancements, the use of artificial intelligence (AI)-based computer vision is expected to have a major impact on this technology. Deep learning algorithms offer the potential to process vast amounts of data quickly and accurately. With the combination of 6G wireless networks and AI-based computer vision, the possibilities are endless. From facial recognition to autonomous vehicles, AI-based computer vision has the potential to drastically change the way we interact with technology. In this paper, readers will explore the possibilities of using deep learning algorithms within 6G wireless networks and how this technology could be used in a variety of applications.

In this study, the authors provide answers to the most important questions related to AI, computer vision, and deep learning for 6G wireless networks. Their answers are aligned with many aspects that are very useful for making a strong connection to Society 5.0 and what will come next. They also give a very important perspective in terms of opening new challenges for future research directions.

The authors’ idea takes into consideration 6G wireless networks together with deep learning, with the goal to solve important challenges using a new methodology called optimizing computer vision with AI-enabled technology (OCV-AI). Their contribution in this direction is efficient algorithms for computer vision that address the issues mentioned and improve the expected outcomes of such systems. The proposed DL-6G framework “recognize[s] pattern recognition and intelligent management systems and provide[s] driven methodology planned to be provisioned automatically.”

By taking a close look at AI-based computer vision, which refers to a variety of different technologies, deep learning algorithms are one of the most influential AI techniques used in computer vision; in this work, they are significantly emphasized. It is important to identify some differences between the goal of deep learning algorithms in this paper and deep learning algorithms in general, to understand the definition of deep learning as a type of artificial neural network (ANN) that is inspired by the human brain. Networks of interconnected “neurons” process information using a series of mathematical equations. Unlike traditional computer techniques, deep learning is capable of unsupervised learning and adaptation. The algorithms can identify patterns within data and adjust as new information is collected. Deep learning algorithms have been used in applications like image recognition and machine translation, and many of these algorithms have been adapted for use in 6G wireless networks.

The benefits of AI-based computer vision within 6G networks, as described by the authors through their methodology, can be applied across several industries. They can improve automated visual inspection, image recognition, video processing, and data analysis. AI-based computer vision can be used in manufacturing to improve quality control, monitoring, and the management of supply chains. It can also be used in healthcare to improve diagnosis and treatment, such as in the detection of breast cancer and disease onset. AI-based computer vision can be used in security to detect bombs, weapons, and other threats. It can be applied to augmented reality to improve virtual experiences in the real world. AI-based computer vision can also be used to filter and censor inappropriate content, protect privacy, and ensure cybersecurity. Overall, AI-based computer vision can improve decision-making, increase efficiency, and improve safety and security.

The authors’ work contributes to potential applications and research challenges that are ongoing at the moment:

  • Facial recognition technology can be used to authenticate identities and verify users. It can be used to improve the safety and security of wireless networks by ensuring only authorized users are granted access. Facial recognition can be applied in many different industries, including travel, healthcare, and education. It can also be used to improve safety and security within airports, hotels, and other public spaces. In 6G networks, facial recognition technology can be used to authenticate users, improve network safety, and provide more accurate information.
  • Object recognition technology can be used to identify objects within visual content. This can be applied to everything from identifying types of plants in a greenhouse to counting the number of cars at a traffic light. Object recognition can be used in many different industries, including manufacturing, retail, and healthcare. In 6G, object recognition can be used to identify devices within the network, such as smartphones, computers, and more. This information can be used to provide more accurate visual analytics, identify trends in visual data, and improve security.
  • Location identification technology can be used to identify the current location of an image or video. This can be applied to a variety of industries, including retail, travel, and marketing. Location identification can be used in 6G wireless networks to improve visual analytics, identify trends, and provide more accurate information. It can also be used to authenticate users and to protect the network from unauthorized users.

The paper also exposes (new) challenges and concerns related to AI-based computer vision in 6G wireless networks. The main concern is the potential for AI systems to exhibit bias or error. AI-based computer vision systems can make mistakes like any other technology. To prevent biases from affecting AI systems, companies must ensure that their training data is representative of all users and demographics. Another concern is cyberattacks: hackers could potentially target AI systems and attempt to disrupt their operations. To prevent this, organizations must ensure that their systems are secure and protected. Privacy is yet another concern. Although AI-based computer vision can be used to protect privacy, it may still be necessary to implement privacy-friendly measures. Companies should be transparent about the information they are collecting and the use of AI-based computer vision systems.

This paper has been cited by many other works that address significant issues in machine learning for safety digitization, Internet of Things (IoT) for energy-efficient 6G wireless communication, and wireless communication and channel modeling using machine learning. Thus, it has already made an important impact on the field.

In conclusion, 6G wireless networks will provide a range of new benefits, including faster speeds, improved security, and more reliable connections. As this technology grows in popularity and usage, AI-based computer vision will have a major impact on how we use and interact with it. This technology can be applied to a variety of industries and be used for a variety of purposes. Although there are some challenges and concerns that come along with using AI-based computer vision, the technology can drastically improve 6G and the way people use it.

Reviewer:  Mihailescu Marius Iulian Review #: CR147565 (2305-0063)
Bookmark and Share
  Featured Reviewer  
Wireless Communication (C.2.1 ... )
General (I.2.0 )
Would you recommend this review?
Other reviews under "Wireless Communication": Date
Mobile power management for wireless communication networks
Rulnick J., Bambos N. Wireless Networks 3(1): 3-14, 1997. Type: Article
Aug 1 1998
New call blocking versus handoff blocking in cellular networks
Sidi M., Starobinski D. Wireless Networks 3(1): 15-27, 1997. Type: Article
Sep 1 1998
The wireless Net
Fowler D. netWorker: The Craft of Network Computing 1(2): 24-34, 1997. Type: Article
Sep 1 1998

E-Mail This Printer-Friendly
Send Your Comments
Contact Us
Reproduction in whole or in part without permission is prohibited.   Copyright 1999-2023 ThinkLoud®
Terms of Use
| Privacy Policy