Abdelhay Ali;Amr N. Abdelrahman;Abdulkadir Celik;Mohammed E. Fouda;Ahmed M. Eltawil
{"title":"基于gan信道建模的鲁棒自编码器HBC收发器","authors":"Abdelhay Ali;Amr N. Abdelrahman;Abdulkadir Celik;Mohammed E. Fouda;Ahmed M. Eltawil","doi":"10.1109/JSEN.2025.3551539","DOIUrl":null,"url":null,"abstract":"Human body communication (HBC) offers a promising alternative for efficient and secure data transmission in wearable healthcare systems by leveraging the body’s conductive properties. Using the conductive properties of the human body, HBC offers significant advantages over conventional radio frequency wireless communication methods, including ultralow power consumption and minimal interference. However, HBC systems face key challenges in energy efficiency, data rate optimization, channel adaptability, and accurate body channel modeling. In this article, we present a novel dual-mode HBC transceiver architecture designed to overcome these challenges by integrating autoencoder-based signal processing with generative adversarial network (GAN)-driven channel modeling framework to enhance communication reliability. Operating in both broadband and narrowband modes, the transceiver dynamically adjusts its data rate and power efficiency based on application-specific demands. The design process involves first developing a conditional GAN (CGAN)-based channel model from real HBC measurements, and then using this model to train an autoencoder-based transceiver architecture. Our CGAN framework generates realistic synthetic channel responses for training, enabling the autoencoder to learn optimal encoding and decoding strategies that are robust to channel variations. Subsequently, we developed a low-power hardware architecture that supports flexible data rates of the proposed design while ensuring robust performance in diverse scenarios. This systematic approach provides key advantages: improved channel modeling accuracy achieving a 0.9 correlation coefficient between generated and real channels and mean squared error (mse) of 0.0071, reduced hardware complexity through elimination of digital-to-analog converter (DAC)/analog-to-digital converter (ADC), and flexible operation with dual-mode support. Operating at a clock speed of 42 MHz in the narrowband mode, the transceiver achieves an energy efficiency of 349 pJ/bit at a data rate of 262.5 kb/s with a sensitivity of −64 dBm, appealing for long-range and low-power applications. In broadband mode, the transceiver achieves an energy efficiency of 16 pJ/bit at a data rate of 5.25 Mb/s, suitable for applications demanding high data rates over shorter distances.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 9","pages":"15935-15949"},"PeriodicalIF":4.3000,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A Robust Autoencoder HBC Transceiver With CGAN-Based Channel Modeling\",\"authors\":\"Abdelhay Ali;Amr N. Abdelrahman;Abdulkadir Celik;Mohammed E. Fouda;Ahmed M. Eltawil\",\"doi\":\"10.1109/JSEN.2025.3551539\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Human body communication (HBC) offers a promising alternative for efficient and secure data transmission in wearable healthcare systems by leveraging the body’s conductive properties. Using the conductive properties of the human body, HBC offers significant advantages over conventional radio frequency wireless communication methods, including ultralow power consumption and minimal interference. However, HBC systems face key challenges in energy efficiency, data rate optimization, channel adaptability, and accurate body channel modeling. In this article, we present a novel dual-mode HBC transceiver architecture designed to overcome these challenges by integrating autoencoder-based signal processing with generative adversarial network (GAN)-driven channel modeling framework to enhance communication reliability. Operating in both broadband and narrowband modes, the transceiver dynamically adjusts its data rate and power efficiency based on application-specific demands. The design process involves first developing a conditional GAN (CGAN)-based channel model from real HBC measurements, and then using this model to train an autoencoder-based transceiver architecture. Our CGAN framework generates realistic synthetic channel responses for training, enabling the autoencoder to learn optimal encoding and decoding strategies that are robust to channel variations. Subsequently, we developed a low-power hardware architecture that supports flexible data rates of the proposed design while ensuring robust performance in diverse scenarios. This systematic approach provides key advantages: improved channel modeling accuracy achieving a 0.9 correlation coefficient between generated and real channels and mean squared error (mse) of 0.0071, reduced hardware complexity through elimination of digital-to-analog converter (DAC)/analog-to-digital converter (ADC), and flexible operation with dual-mode support. Operating at a clock speed of 42 MHz in the narrowband mode, the transceiver achieves an energy efficiency of 349 pJ/bit at a data rate of 262.5 kb/s with a sensitivity of −64 dBm, appealing for long-range and low-power applications. In broadband mode, the transceiver achieves an energy efficiency of 16 pJ/bit at a data rate of 5.25 Mb/s, suitable for applications demanding high data rates over shorter distances.\",\"PeriodicalId\":447,\"journal\":{\"name\":\"IEEE Sensors Journal\",\"volume\":\"25 9\",\"pages\":\"15935-15949\"},\"PeriodicalIF\":4.3000,\"publicationDate\":\"2025-03-24\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE Sensors Journal\",\"FirstCategoryId\":\"103\",\"ListUrlMain\":\"https://ieeexplore.ieee.org/document/10935704/\",\"RegionNum\":2,\"RegionCategory\":\"综合性期刊\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ENGINEERING, ELECTRICAL & ELECTRONIC\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Sensors Journal","FirstCategoryId":"103","ListUrlMain":"https://ieeexplore.ieee.org/document/10935704/","RegionNum":2,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
A Robust Autoencoder HBC Transceiver With CGAN-Based Channel Modeling
Human body communication (HBC) offers a promising alternative for efficient and secure data transmission in wearable healthcare systems by leveraging the body’s conductive properties. Using the conductive properties of the human body, HBC offers significant advantages over conventional radio frequency wireless communication methods, including ultralow power consumption and minimal interference. However, HBC systems face key challenges in energy efficiency, data rate optimization, channel adaptability, and accurate body channel modeling. In this article, we present a novel dual-mode HBC transceiver architecture designed to overcome these challenges by integrating autoencoder-based signal processing with generative adversarial network (GAN)-driven channel modeling framework to enhance communication reliability. Operating in both broadband and narrowband modes, the transceiver dynamically adjusts its data rate and power efficiency based on application-specific demands. The design process involves first developing a conditional GAN (CGAN)-based channel model from real HBC measurements, and then using this model to train an autoencoder-based transceiver architecture. Our CGAN framework generates realistic synthetic channel responses for training, enabling the autoencoder to learn optimal encoding and decoding strategies that are robust to channel variations. Subsequently, we developed a low-power hardware architecture that supports flexible data rates of the proposed design while ensuring robust performance in diverse scenarios. This systematic approach provides key advantages: improved channel modeling accuracy achieving a 0.9 correlation coefficient between generated and real channels and mean squared error (mse) of 0.0071, reduced hardware complexity through elimination of digital-to-analog converter (DAC)/analog-to-digital converter (ADC), and flexible operation with dual-mode support. Operating at a clock speed of 42 MHz in the narrowband mode, the transceiver achieves an energy efficiency of 349 pJ/bit at a data rate of 262.5 kb/s with a sensitivity of −64 dBm, appealing for long-range and low-power applications. In broadband mode, the transceiver achieves an energy efficiency of 16 pJ/bit at a data rate of 5.25 Mb/s, suitable for applications demanding high data rates over shorter distances.
期刊介绍:
The fields of interest of the IEEE Sensors Journal are the theory, design , fabrication, manufacturing and applications of devices for sensing and transducing physical, chemical and biological phenomena, with emphasis on the electronics and physics aspect of sensors and integrated sensors-actuators. IEEE Sensors Journal deals with the following:
-Sensor Phenomenology, Modelling, and Evaluation
-Sensor Materials, Processing, and Fabrication
-Chemical and Gas Sensors
-Microfluidics and Biosensors
-Optical Sensors
-Physical Sensors: Temperature, Mechanical, Magnetic, and others
-Acoustic and Ultrasonic Sensors
-Sensor Packaging
-Sensor Networks
-Sensor Applications
-Sensor Systems: Signals, Processing, and Interfaces
-Actuators and Sensor Power Systems
-Sensor Signal Processing for high precision and stability (amplification, filtering, linearization, modulation/demodulation) and under harsh conditions (EMC, radiation, humidity, temperature); energy consumption/harvesting
-Sensor Data Processing (soft computing with sensor data, e.g., pattern recognition, machine learning, evolutionary computation; sensor data fusion, processing of wave e.g., electromagnetic and acoustic; and non-wave, e.g., chemical, gravity, particle, thermal, radiative and non-radiative sensor data, detection, estimation and classification based on sensor data)
-Sensors in Industrial Practice