{"id":4787,"date":"2022-06-26T18:04:18","date_gmt":"2022-06-26T10:04:18","guid":{"rendered":"https:\/\/ascendas-asia.com\/?page_id=4787"},"modified":"2024-01-10T17:26:42","modified_gmt":"2024-01-10T09:26:42","slug":"ai-for-wireless-communications","status":"publish","type":"page","link":"https:\/\/ascendas-asia.com\/th\/ai-for-wireless-communications\/","title":{"rendered":"AI for Wireless"},"content":{"rendered":"\n\n\n
\n

Whether you use machine learning, deep learning, or reinforcement learning workflows, you can reduce development time with ready-to-use algorithms and data generated with MATLAB ®<\/span> and wireless communications products. You can easily leverage existing deep learning networks outside MATLAB; streamline training, testing, and verification of your designs; and simplify deployment of your AI networks on embedded devices, enterprise systems, and the cloud. With MATLAB, you can:<\/p>\n

    \n
  • Generate training data in the form of synthetic and over-the-air signals using the Wireless Waveform Generator app<\/li>\n
  • Augment signal space by adding RF impairments and channel models to your generated signals<\/li>\n
  • Label signals collected from wireless systems using the Signal Labeler app<\/li>\n
  • Apply reusable and streamlined training, simulation, and testing workflows to various wireless applications using the Deep Network Designer and Experiment Manager apps<\/li>\n
  • Add custom layers to your deep learning designs<\/li>\n<\/ul>\n<\/td>\n
<\/td>\n\"AI<\/a><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

<\/h1>\n

Why Use AI for Wireless?<\/strong><\/span><\/h2>\n

<\/strong><\/p>\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n
\n

\"Using<\/h1>\n<\/td>\n

<\/td>\n\n

\"Design<\/h3>\n

<\/a><\/td>\n<\/tr>\n

<\/td>\n<\/td>\n<\/td>\n<\/tr>\n
\n

Spectrum Sensing and Signal Classification<\/span><\/h3>\n<\/td>\n

<\/td>\n\n

Device Identification<\/span><\/h3>\n<\/td>\n<\/tr>\n

\n
\n
Identify signals in a wideband spectrum using deep learning techniques. Perform waveform modulation classification using deep learning networks.<\/div>\n<\/div>\n
    \n
  • Spectrum Sensing with Deep Learning to Identify 5G and LTE Signals<\/li>\n
  • Modulation Classification with Deep Learning<\/li>\n<\/ul>\n<\/td>\n
<\/td>\n\n
\n
Develop radio frequency (RF) fingerprinting methods to identify various devices and detect device impersonators.<\/div>\n<\/div>\n
    \n
  • Design a Deep Neural Network with Simulated Data to Detect WLAN Router Impersonation<\/li>\n
  • Test a Deep Neural Network with Captured Data to Detect WLAN Router Impersonation<\/li>\n<\/ul>\n<\/td>\n<\/tr>\n
\n

<\/h1>\n<\/td>\n

\n

<\/h1>\n<\/td>\n

\n

<\/h1>\n<\/td>\n<\/tr>\n

\n
\n
\"A<\/div>\n<\/div>\n<\/td>\n
<\/td>\n\n
\n
\"Comparing<\/div>\n<\/div>\n<\/td>\n<\/tr>\n
\n

<\/h1>\n<\/td>\n

<\/td>\n\n

<\/h1>\n<\/td>\n<\/tr>\n

\n

Digital Pre-Distortion<\/span><\/h3>\n
\n
Apply neural network-based digital predistortion (DPD) to offset the effects of nonlinearities in a power amplifier (PA).<\/div>\n<\/div>\n
    \n
  • Neural Network for Digital Predistortion Design – Offline Training<\/li>\n<\/ul>\n<\/td>\n

<\/td>\n\n

Beam Management and Channel Estimation<\/span><\/h2>\n
\n
Use a neural network to reduce the computational complexity in the 5G NR beam selection task. Train a CNN for 5G NR channel estimation.<\/div>\n<\/div>\n
    \n
  •  Neural Network for Beam Selection<\/li>\n
  • Deep Learning Data Synthesis for 5G Channel Estimation<\/li>\n<\/ul>\n<\/td>\n<\/tr>\n

\n

<\/h1>\n<\/td>\n

<\/td>\n\n

<\/h1>\n<\/td>\n<\/tr>\n

\n

\"Comparing<\/h2>\n<\/td>\n

<\/td>\n\n

\"Visualizing<\/h2>\n<\/td>\n<\/tr>\n

\n

<\/h1>\n<\/td>\n

<\/td>\n\n

<\/h1>\n<\/td>\n<\/tr>\n

\n

Localization and Positioning<\/span><\/h3>\n
\n
Use generated IEEE ®<\/sup> 802.11az™ data to train a CNN for localization and positioning.<\/div>\n<\/div>\n
    \n
  •  Three-Dimensional Indoor Positioning with 802.11az Fingerprinting and Deep Learning<\/li>\n<\/ul>\n<\/td>\n

<\/td>\n\n

Transceiver Design<\/span><\/h3>\n
\n
Use an unsupervised neural network that learns how to efficiently compress and decompress data, forming an autoencoder. Train and test a neural network to estimate likelihood ratios (LLR).<\/div>\n<\/div>\n