Analysis of the changes in the distinguishing features in electroencephalogram signal processing for heroin addicts

  • سال انتشار: 1404
  • محل انتشار: مجله مهندسی برق مجلسی، دوره: 19، شماره: 1
  • کد COI اختصاصی: JR_MJEE-19-1_014
  • زبان مقاله: انگلیسی
  • تعداد مشاهده: 69
دانلود فایل این مقاله

نویسندگان

Atefeh Tobieha

Department of Electrical Engineering, Najafabad Branch, Islamic Azad University, Najafabad, Iran.

Neda Behzadfar

Department of Electrical Engineering, Najafabad Branch, Islamic Azad University, Najafabad, Iran.

Mohammad Reza Yousefi

Department of Electrical Engineering, Najafabad Branch, Islamic Azad University, Najafabad, Iran.

Homayoun Mahdavi-Nasab

Department of Electrical Engineering, Najafabad Branch, Islamic Azad University, Najafabad, Iran.

Ghazanfar Shahgholian

Department of Electrical Engineering, Najafabad Branch, Islamic Azad University, Najafabad, Iran.

چکیده

Heroin is a highly addictive drug with devastating effects on various parts of the body, including the digestive system, nervous system, and mental health, and it can lead to premature death. One of the most destructive impacts of heroin use is on the brain. Electroencephalograms (EEG) indicate the brain’s activity in the physiological and psychological states of heroin addicts. Identifying distinguishing features is crucial for processing these signals and determining the differences between the EEGs of healthy individuals and addicts. The frequency and time domain features extracted from different channels of EEG vary, but identifying distinguishing features can aid in better analysis of these signals. This article uses the Davies-Bouldin criterion to determine distinguishing frequency and time domain features. EEGs of heroin addicts (۱۵ individuals) and healthy individuals (۱۵ individuals) were extracted from ۱۶ different channels. The distinguishing feature with the lowest Davies-Bouldin index value was selected. The results of this study show that inpeople addicted to heroin, the frequency power spectrum in the upper alpha subband of the O۱ channel has decreased. Additionally, approximate entropy is increased in the Cz channel of heroin addicts. To evaluate the distinguishing features, support vector machine classification has been used to distinguish addicts from healthy individuals. The sensitivity and accuracy of distinguishing an addicted person from a healthy person in the approximate entropy feature are ۹۱.۵۰% and ۹۱.۸۱%, respectively, and in the power spectrum feature in the upper alpha subband of the O۱ channel, they are ۹۵.۹۲% and ۹۲.۴۰%, respectively. Compared to other studies, the obtained results confirm the distinction and superiority of these features in terms of precision and accuracy. According to the results, the analysis of frequency and time domain features of brain signals can help to better understand the effects of heroin consumption on brain activity. This study may help provide solutions to improve the treatment and prevention of heroin addiction.

کلیدواژه ها

Power Spectrum, Distinctive features, Electroencephalogram signal, Heroin, Brain signal processing

اطلاعات بیشتر در مورد COI

COI مخفف عبارت CIVILICA Object Identifier به معنی شناسه سیویلیکا برای اسناد است. COI کدی است که مطابق محل انتشار، به مقالات کنفرانسها و ژورنالهای داخل کشور به هنگام نمایه سازی بر روی پایگاه استنادی سیویلیکا اختصاص می یابد.

کد COI به مفهوم کد ملی اسناد نمایه شده در سیویلیکا است و کدی یکتا و ثابت است و به همین دلیل همواره قابلیت استناد و پیگیری دارد.