ﺳﯿﺴﺘﻢ ﺍﺣﺮﺍﺯﻫﻮیت ﺑﺎ سیگناﻝ ﺿﺮﺑﺎﻥ ﻗﻠﺐ ﺑﺮ پایه یاﺩگیری ﻋﻤﯿﻖ

دﺭ ﺩﻧﯿﺎی ﺑﺮ پایه ﺍﺭﺗﺒﺎﻃﺎﺕ ﺩیجیتاﻝ، ﺍﺣﺮﺍﺯ ﻫﻮیت ﺩﻏﺪﻏﻪ مهمی ﺍﺳﺖ ﻭ ﻧﯿﺎﺯ ﺑﻪ یک ﺳﯿﺴﺘﻢ ﺍﻣﻦ ﻭ ﻣﻄﻤﺌﻦ ﻧﯿﺰ ﺍین ﺩﻏﺪﻏﻪ ﺭﺍ ﺗﺸﺪید می کند که ﺿﺮﻭﺭﺕ ﻃﺮﺍحی ﺳﯿﺴﺘﻢﻫﺎی ﺍﺣﺮﺍﺯ ﻫﻮیت ﺭﺍ ﺑﺎﻻ میﺑﺮﺩ. ﺑﺮﺍی ﺍﻧﺠﺎﻡ ﺍﺣﺮﺍﺯ ﻫﻮیت، ﺭﻭیکرﺩﻫﺎی ﺑﺮ پایه ﺯیستﺳﻨﺠﻪ ﺑﻪ ﺩﻟﯿﻞ ﺩﺍﺷﺘﻦ ﺧﺎﺻﯿﺖ ﺯﻧﺪﻩ ﺑﻮﺩﻥ ﻭ ﻣﻘﺎﻭﻡ ﺑﻮﺩﻥ ﺩﺭ ﺑﺮﺍﺑﺮ ﺟﻌﻞ ﺑﺴﯿﺎﺭ ﻣﻮﺭﺩ ﺗﻮﺟﻪ ﻗﺮﺍﺭ ﺩﺍﺭﻧﺪ. ﺩﺭ ﺍین ﻣﻄﺎﻟﻌﻪ یک ﺳﯿﺴﺘﻢ ﺍﺣﺮﺍﺯ ﻫﻮیت ﺑﺮ پایه سیگنال ﻗﻠﺐ ﻃﺮﺍحی ﺷﺪﻩ ﺍﺳﺖ. ﺑﺎ ﺗﻮﺟﻪ ﺑﻪ ﻓﺮﺁیند ﺩﺭیاﻓﺖ سیگناﻝﻫﺎی ﻗﻠﺐ، ﺩﺍﺩﻩﻫﺎی ﺁﻧﻬﺎ ﻣﻌﻤﻮﻻً  ﻧﻮیز ﺯیاﺩی ﺩﺍﺭﻧﺪ. ﺑﻪ ﻣﻨﻈﻮﺭ ﺁﻣﺎﺩﻩﺳﺎﺯی ﻭ پیش پرﺩﺍﺯﺵ ﺩﺍﺩﻩﻫﺎ، ﺩﺭ ﺳﯿﺴﺘﻢ پیشنهاﺩی ﺍﺑﺘﺪﺍ سیگناﻝﻫﺎی ﻗﻠﺐ ﺗﻤﯿﺰ ﺷﺪﻩ ﻭ سپس ﺑﺮﺍی ﺍﺳﺘﺨﺮﺍﺝ ﻭیژگی، ﺑﻪ ﻓﻀﺎی ﺑﺴﺎﻣﺪ ﺑﺮﺩﻩ میﺷﻮﻧﺪ. همچنین ﺑﻪ ﻣﻨﻈﻮﺭ ﺑﻬﺮﻩﺑﺮﺩﺍﺭی ﺑﯿﺸﯿﻨﻪ ﺍﺯ سیگناﻝﻫﺎ، ﺑﺎ ﺍﻋﻤﺎﻝ ﺗﻮﺯیع ویگنر‑ﻭﺍیل ﺑﻪ یک ﺗﺼﻮیر ﺗﺒﺪیل میﺷﻮﻧﺪ، ﺑﻪ ﻃﻮﺭیکه ﻫﺮ ﺗﺼﻮیر ﺣﺎﻭی ﺍﻃﻼﻋﺎﺕ سیگناﻝ ﻗﻠﺐ ﻫﺮ ﻓﺮﺩ ﺑﻮﺩﻩ ﻭ یکتا ﺍﺳﺖ. ﺩﺭ ﺳﯿﺴﺘﻢ ﺍﺣﺮﺍﺯ ﻫﻮیت پیشنهاﺩی ﺍین ﺗﺼﺎﻭیر ﺑﺮﺍی ﺁﻣﻮﺯﺵ ﻭ ﺍﺭﺯیابی ﺩﺭ یک شبکه عصبی ﻋﻤﯿﻖ کاﻧﻮﻟﻮشنی ﺑﻪ کاﺭ گرﻓﺘﻪ میﺷﻮﻧﺪ. ﺧﺮﻭجی ﺍین ﺳﯿﺴﺘﻢ ﺍمکاﻥ ﺍﺣﺮﺍﺯﻫﻮیت ﺍﻓﺮﺍﺩ ﺭﺍ ﻓﺮﺍﻫﻢ می کند. ﺩﺍﺩﻩﻫﺎی ﺍین پژﻭﻫﺶ ﺑﺮگرﻓﺘﻪ ﺍﺯ پایگاه ﺩﺍﺩﻩﻫﺎی nsrdb و mitdb ﻫﺴﺘﻨﺪ ﻭ ﻧﺘﺎیج چشمگیری ﻧﺴﺒﺖ ﺑﻪ پژﻭﻫﺶﻫﺎی پیشین ﺣﺎﺻﻞ ﺷﺪﻩ ﺍﺳﺖ.

electrocardiogram signal authentication system based on deep learning

in the world of digital communication, authentication is an important concern and the need for a safe and secure system increases the necessity of designing authentication systems. to perform authentication, biometric-based approaches are of great interest due to the property of being alive and resistant to forgery. in this study, an authentication system based on heart signal is designed. due to the process of receiving heart signals, their data usually has a lot of noise. in order to prepare the data, in the proposed system, the heart signals are first cleaned and then transferred to the frequency domain for feature extraction. also, they are converted into an image by applying the wigner-ville distribution, so that each image contains the signal information of each person’s heart and is unique. in the proposed authentication system, these images are used for training and evaluation in a deep convolutional neural network. the output of this system provides the possibility of people’s identification. the data of this study are taken from the nsrdb and mitdb databases, and significant results have been obtained compared to previous studies.