Advances in Cognitive Sciences
تازه های علوم شناختی
Advances in Cognitive Sciences
Literature & Humanities
http://icssjournal.ir
1
admin
1561-4174
2783-073x
10.30514/icss
fa
jalali
1399
12
1
gregorian
2021
3
1
23
1
online
1
fulltext
fa
طبقهبندی پتانسیلهای وابسته به رویداد شنیداری در یک تکلیف افتراق زمانی مبتنی بر پارادایم ادبال
Classification of auditory event-related potentials in a time discrimination task based on the oddball paradigm
علوم اعصاب شناختی
پژوهشي اصیل
Research
<strong><span style="font-family:B Titr;"><span style="font-size:12.0pt;">مقدمه:</span></span></strong> <span style="font-family:B Nazanin;"><span style="font-size:12.0pt;">با وجود بیش از یک سده مطالعات در زمینه چگونگی ادراک زمان توسط مغز انسان، پژوهش در مورد تشخیص الگوهای مربوط به ادراک زمان در سیگنال الکتروآنسفالوگرافی افراد نادر بوده است.</span></span> <span style="font-family:B Nazanin;"><span style="font-size:12.0pt;">هدف از این مطالعه تشخیص کوتاه یا بلند بودن بازه <span style="background:white;">مورد قضاوت</span> توسط یک فرد، بر اساس سیگنال الکتروآنسفالوگرافی وی بود. </span></span><br>
<strong><span style="font-family:B Titr;"><span style="font-size:12.0pt;">روش کار:</span></span></strong> <span style="font-family:B Nazanin;"><span style="font-size:12.0pt;">در یک تکلیف ادبال شنیداری، از آزمودنی</span></span><strong><span style="font-family:B Mitra;">­</span></strong><span style="font-family:B Nazanin;"><span style="font-size:12.0pt;">ها خواسته شد که مدت زمانی محرک ادبال کوتاه (</span></span><span dir="LTR"><span style="font-family:Times New Roman,serif;">ms</span></span><span style="font-family:B Nazanin;"><span style="font-size:12.0pt;">400) یا بلند (</span></span><span dir="LTR"><span style="font-family:Times New Roman,serif;">ms</span></span><span style="font-family:B Nazanin;"><span style="font-size:12.0pt;">600) را با مدت ارائه محرک</span></span><strong><span style="font-family:B Mitra;">­</span></strong><span style="font-family:B Nazanin;"><span style="font-size:12.0pt;">های استاندارد (</span></span><span dir="LTR"><span style="font-family:Times New Roman,serif;">ms</span></span><span style="font-family:B Nazanin;"><span style="font-size:12.0pt;">500) پیش از آن مقایسه کنند. همزمان با ارائه تکلیف، الکتروآنسفالوگرافی افراد ثبت می</span></span><strong><span style="font-family:B Mitra;">­</span></strong><span style="font-family:B Nazanin;"><span style="font-size:12.0pt;">شد. سپس نمونه</span></span><strong><span style="font-family:B Mitra;">­</span></strong><span style="font-family:B Nazanin;"><span style="font-size:12.0pt;">های هدف (پتانسیل</span></span><strong><span style="font-family:B Mitra;">­</span></strong><span style="font-family:B Nazanin;"><span style="font-size:12.0pt;">های مغزی برانگیخته شده توسط محرک ادبال </span></span><span dir="LTR"><span style="font-family:Times New Roman,serif;">ms</span></span><span style="font-family:B Nazanin;"><span style="font-size:12.0pt;">400 یا </span></span><span dir="LTR"><span style="font-family:Times New Roman,serif;">ms</span></span><span style="font-family:B Nazanin;"><span style="font-size:12.0pt;">600) و نمونه</span></span><strong><span style="font-family:B Mitra;">­</span></strong><span style="font-family:B Nazanin;"><span style="font-size:12.0pt;">های غیر هدف (پتانسیل</span></span><strong><span style="font-family:B Mitra;">­</span></strong><span style="font-family:B Nazanin;"><span style="font-size:12.0pt;">های مغزی برانگیخته شده توسط محرک استاندارد) به الگوریتم</span></span><strong><span style="font-family:B Mitra;">­</span></strong><span style="font-family:B Nazanin;"><span style="font-size:12.0pt;">های طبقه</span></span><strong><span style="font-family:B Mitra;">­</span></strong><span style="font-family:B Nazanin;"><span style="font-size:12.0pt;">بندی داده شد. </span></span><strong><span style="font-family:B Titr;"><span style="font-size:12.0pt;"></span></span></strong><br>
<strong><span style="font-family:B Titr;"><span style="font-size:12.0pt;">یافته­ها:</span></span></strong> <span style="font-family:B Nazanin;"><span style="font-size:12.0pt;">طبقه</span></span><strong><span style="font-family:B Mitra;">­</span></strong><span style="font-family:B Nazanin;"><span style="font-size:12.0pt;">بند </span></span><span dir="LTR"><span style="font-family:Times New Roman,serif;">SVM</span></span><span style="font-family:B Nazanin;"><span style="font-size:12.0pt;"> با کرنل </span></span><span dir="LTR"><span style="font-family:Times New Roman,serif;">RBF</span></span><span style="font-family:B Nazanin;"><span style="font-size:12.0pt;"> توانست با بالاترین صحت طبقه بندی 25/94 درصد از میان طبقه</span></span><strong><span style="font-family:B Mitra;">­</span></strong><span style="font-family:B Nazanin;"><span style="font-size:12.0pt;">بندهای درخت تصمیم</span></span><strong><span style="font-family:B Mitra;">­</span></strong><span style="font-family:B Nazanin;"><span style="font-size:12.0pt;">گیری و شبکه عصبی پرسپترون چند لایه (</span></span><span dir="LTR"><span style="font-family:Times New Roman,serif;">MLP</span></span><span style="font-family:B Nazanin;"><span style="font-size:12.0pt;">)، نمونه</span></span><strong><span style="font-family:B Mitra;">­</span></strong><span style="font-family:B Nazanin;"><span style="font-size:12.0pt;">های مورد آزمایش هدف (بازه </span></span><span dir="LTR"><span style="font-family:Times New Roman,serif;">ms</span></span><span style="font-family:B Nazanin;"><span style="font-size:12.0pt;">400) را از نمونه</span></span><strong><span style="font-family:B Mitra;">­</span></strong><span style="font-family:B Nazanin;"><span style="font-size:12.0pt;">های غیر هدف (بازه</span></span><strong><span style="font-family:B Mitra;">­</span></strong><span style="font-family:B Nazanin;"><span style="font-size:12.0pt;">های </span></span><span dir="LTR"><span style="font-family:Times New Roman,serif;">ms</span></span><span style="font-family:B Nazanin;"><span style="font-size:12.0pt;">500 و </span></span><span dir="LTR"><span style="font-family:Times New Roman,serif;">ms</span></span><span style="font-family:B Nazanin;"><span style="font-size:12.0pt;">600) تشخیص دهد. همچنین، این الگوریتم با صحت 98/93 </span></span><span style="font-family:B Nazanin;"><span style="font-size:12.0pt;">درصد </span></span><span style="font-family:B Nazanin;"><span style="font-size:12.0pt;">نمونه</span></span><strong><span style="font-family:B Mitra;">­</span></strong><span style="font-family:B Nazanin;"><span style="font-size:12.0pt;">های هدف </span></span><span dir="LTR"><span style="font-family:Times New Roman,serif;">ms</span></span><span style="font-family:B Nazanin;"><span style="font-size:12.0pt;">600 را از نمونه</span></span><strong><span style="font-family:B Mitra;">­</span></strong><span style="font-family:B Nazanin;"><span style="font-size:12.0pt;">های غیر هدف (بازه</span></span><strong><span style="font-family:B Mitra;">­</span></strong><span style="font-family:B Nazanin;"><span style="font-size:12.0pt;">های </span></span><span dir="LTR"><span style="font-family:Times New Roman,serif;">ms</span></span><span style="font-family:B Nazanin;"><span style="font-size:12.0pt;">500 و </span></span><span dir="LTR"><span style="font-family:Times New Roman,serif;">ms</span></span><span style="font-family:B Nazanin;"><span style="font-size:12.0pt;">400) تشخیص داد و در نهایت با صحت 95/87 </span></span><span style="font-family:B Nazanin;"><span style="font-size:12.0pt;">درصد </span></span> <span style="font-family:B Nazanin;"><span style="font-size:12.0pt;">توانست</span></span> <span style="font-family:B Nazanin;"><span style="font-size:12.0pt;">نمونه</span></span><strong><span style="font-family:B Mitra;">­</span></strong><span style="font-family:B Nazanin;"><span style="font-size:12.0pt;">های مربوط به بازه</span></span><strong><span style="font-family:B Mitra;">­</span></strong><span style="font-family:B Nazanin;"><span style="font-size:12.0pt;">های </span></span><span dir="LTR"><span style="font-family:Times New Roman,serif;">ms</span></span><span style="font-family:B Nazanin;"><span style="font-size:12.0pt;">400</span></span> <span style="font-family:B Nazanin;"><span style="font-size:12.0pt;">را از </span></span><span dir="LTR"><span style="font-family:Times New Roman,serif;">ms</span></span><span style="font-family:B Nazanin;"><span style="font-size:12.0pt;">600 و </span></span><span dir="LTR"><span style="font-family:Times New Roman,serif;">ms</span></span><span style="font-family:B Nazanin;"><span style="font-size:12.0pt;">500 تشخیص دهد. </span></span><br>
<strong><span style="font-family:B Titr;"><span style="font-size:12.0pt;">نتیجه­گیری:</span></span></strong> <span style="font-family:B Nazanin;"><span style="font-size:12.0pt;">یافته</span></span><strong><span style="font-family:B Mitra;">­</span></strong><span style="font-family:B Nazanin;"><span style="font-size:12.0pt;">های این مطالعه نشان می</span></span><strong><span style="font-family:B Mitra;">­</span></strong><span style="font-family:B Nazanin;"><span style="font-size:12.0pt;">دهد که یادگیری ماشین می</span></span><strong><span style="font-family:B Mitra;">­</span></strong><span style="font-family:B Nazanin;"><span style="font-size:12.0pt;">تواند الگوهای مربوط به ادراک بازه کوتاه و بلند را بر اساس سیگنال الکتروانسفالوگرافی افراد، با دقت بالایی تشخیص دهد. </span></span><strong><span dir="LTR"><span style="font-family:Times New Roman,serif;"></span></span></strong><br>
<strong><span dir="RTL"><span style="font-family:B Titr;"><span style="font-size:12.0pt;">واژه­های کلیدی:</span></span></span></strong>
<div style="text-align: justify;"><strong>Introduction</strong>: Despitemore than a century of research on how the brain perceives time, research on EEG pattern recognition related to time perception has been rare. A deficit in time perception has been demonstrated in many mental and neurological disorders such as Parkinson's, ADHD, depression, autism, and schizophrenia. Classification of event-related potentials in time discrimination tasks could be used as a screening tool for such diseases. This study aims to recognize whether the duration is judged as short or long by a person based on his electroencephalography (EEG) signal.<br>
<strong>Methods</strong>: For this purpose, the oddball paradigm was used. 24 male and female students of Tabriz University took part in the experiment. From which 18 were selected after artifact rejection. Written informed consent was obtained from all the participants. EEG of the participants was recorded simultaneously with the task presentations. In an oddball auditory task, after two or four presentation of a pure tone of frequency 1000Hz, each one lasting for 500ms (standard stimuli) at a constant interstimulus interval of 300ms, a tone of a different frequency (500hz,700hz,1300hz, or 1500hz) and with the duration of 400ms or 600ms was presented (oddball stimulus). Participants were asked to compare the duration of the short (400ms) or long (600ms) oddball stimulus to the duration of its preceding standard stimuli (500ms). After the required preprocessing steps, averaging was performed to obtain the ERP segments at each of the experimental conditions. The Cz electrode was selected to reduce further analysis among the 64 channels used for recording since most of the factors were significant at Cz, and the highest amplitude of ERP components was seen over there. The labeled target samples (ERP segments related to either 400ms or 600ms oddball stimuli) and labeled non-target samples (ERP segments related to the standard stimuli) were fed to the classifiers as the training set. After training the classifiers with a subset of this dataset, the test was executed on the reminder.<br>
<strong>Results</strong>: Behavioral results revealed that in the four repetition conditions, participants significantly perceived the oddball stimulus as more extended than in the two repetition condition, which implies that repetition causes time overestimation. Electroencephalography results indicated that the repetition suppression effect was evident throughout the ERP waveform. Repeating a standard stimulus causes reduction in the amplitude of ERP components elicited by it. Whereas, presentation of a novel stimulus –oddball- leads to an increase in the corresponding ERP components amplitude. Finally, classification results showed that SVM (RBF) classifier could recognize the target samples (400ms intervals) from non-target samples (500ms and 600ms intervals) with the highest accuracy of 94.25% among decision tree and multilayer perceptron (MLP) classifiers. Also, SVM (RBF) yielded the highest accuracy of 93.98% when classifying 600ms related samples (target) versus 500ms and 600ms related samples (non-target). Finally, it achieved the best accuracy of 87.95% when classifying the test samples into multiclass of 400ms, 600ms, and 500ms classes separately.<br>
<strong>Conclusion</strong>: The study results demonstrate that machine learning could accurately detect patterns related to short and long perceived intervals based on the peoples’ electroencephalography (EEG) signal.</div>
ادراک زمان, طبقهبندی, پتانسیل وابسته به رویداد, تکلیف ادبال شنیداری
Time perception, Classification, Event-related potential (ERP), Auditory oddball task
73
84
http://icssjournal.ir/browse.php?a_code=A-10-400-1&slc_lang=fa&sid=1
Hoda
Jalalkamali
هدی
جلال کمالی
Hodajalalkamali@uk.ac.ir
100319475328460013225
100319475328460013225
Yes
Assistant Professor in Cognitive Neuroscience, Computer Engineering Group, Higher Educational Complex of Zarand, Zarand, Iran
استادیار علوم اعصاب شناختی، گروه مهندسی کامپیوتر، مجتمع آموزش عالی زرند، زرند، ایران
Amirhossein
Tajik
امیرحسین
تاجیک
100319475328460013226
100319475328460013226
No
Graduate Student, Electronic Engineering, Shahid Bahonar University of Kerman, Kerman, Iran
دانشجوی کارشناسی ارشد مهندسی الکترونیک، دانشگاه شهید باهنر کرمان، کرمان، ایران
Hossein
Nezamabadi-Pour
حسین
نظام آبادی پور
100319475328460013227
100319475328460013227
No
Professor in Electrical Engineering, Electrical Engineering Department, Shahid Bahonar University of Kerman, Kerman, Iran
استاد مهندسی برق، بخش مهندسی برق، دانشگاه شهید باهنر کرمان، کرمان، ایران