Beyond Univariate Statistics: Harnessing Neuroinformatics and Data Mining for Comprehensive Brain Understanding
محل انتشار: پنجمین کنفرانس بین المللی محاسبات نرم
سال انتشار: 1402
نوع سند: مقاله کنفرانسی
زبان: انگلیسی
مشاهده: 94
فایل این مقاله در 10 صفحه با فرمت PDF قابل دریافت می باشد
- صدور گواهی نمایه سازی
- من نویسنده این مقاله هستم
استخراج به نرم افزارهای پژوهشی:
شناسه ملی سند علمی:
CSCG05_077
تاریخ نمایه سازی: 9 اردیبهشت 1403
چکیده مقاله:
The brain's intricate coordination requires integrating massive amounts of information from numerous disciplines. Modern methods include multielectrode arrays, calcium imaging, and optogenetics offer neuron-level data. In systems and circuit neuroscience, investigating huge populations of neurons is difficult. Experimental neurotechnology, optimal control, signal processing, network analysis, and dimensionality reduction may solve these problems. Univariate statistical technique in neuroscience research fails to show component interactions and their effects. This study uses support vector machines, principal component and factor analysis, cluster analysis, multiple linear regression, and random forest regression. The discipline of "connectomics" studies brain connections at big and small scales. This shows how neuroinformatics accelerates progress. NIF integrates neurological data, making database integration easy. Data mining across many neuroscience data layers is also examined for pros and cons.
کلیدواژه ها:
نویسندگان
Elyas Hadizadeh Tasbiti
Master Student of Computer Engineering Department, Imam Khomeini International University, Qazvin, Iran
Morteza Mohammadi Zanjireh
Assistant Professor of Computer Engineering Department, Imam Khomeini International University, Qazvin, Iran.