توجه: محتویات این صفحه به صورت خودکار پردازش شده و مقاله‌های نویسندگانی با تشابه اسمی، همگی در بخش یکسان نمایش داده می‌شوند.
۱Evaluation of Separability Measures in GA–based Feature Subset Selection for Myoelectric Classification
نویسنده(ها): ،
اطلاعات انتشار: سیزدهمین کنفرانس مهندسی پزشکی ایران، سال
تعداد صفحات: ۶
This paper evaluates the separability measures applied on feature subset selection for myoelectric signal (MES). The separability measures which are considered to evaluation are Davies–Bouldin index (DBI), Fishers linear discriminant index (FLDI), Dunn’s index (DI) and generalized Dunn’s index (GDI). Four channel of myoelectric signal from upper limb muscles are used in this paper to classify six distinctive activities. Cascaded genetic algorithm (GA) has been adopted as the search strategy in feature subset selection. Results prove more accurate and reliable classification for the elite subset of features selected based on Davies–Bouldin index (DBI).<\div>

۲ارائه یک واسط انسان–کامپیوتر بمنظور کنترل صندلی چرخدار مجازی بر اساس سیگنالهای چند کاناله ثبت شده از پیشانی
اطلاعات انتشار: چهاردهمین کنفرانس مهندسی پزشکی ایران، سال
تعداد صفحات: ۶
The goal of Human–Computer Interface (HCI)) (Human–Robot interface HRI) research is to provide humans with a new communication channel that allows translating Human's will states via a computer into application specific actions. This paper presents a novel hands–free control system for controlling a virtual wheelchair, which is based on Forehead Multi–channels Bio–signals as EMG (Electromyogram) signals. In this method, new locations for three Bi–polar electrodes are selected. The Bioelectric signals are picked up from lateral sides and centre of Forehead then the Bio–signals are passed through a band pass filters. Motion control commands (forward, left, right, backward and stop) are classified by SVM method. These commands are used for controlling the virtual wheelchair by interface software in a Personal Computer.

۳ارزیابی عملکرد SVM درطبقه بندی حرکت اندام فوقانی با استفاده از سیگنال الکترومایوگرام
نویسنده(ها): ،
اطلاعات انتشار: چهاردهمین کنفرانس مهندسی پزشکی ایران، سال
تعداد صفحات: ۶
This paper evaluates the Support Vector Machine (SVM) applied to upper limb motion classification using myoelectric signals. The main purpose of this paper is to compare SVM–based classifiers with LDA and MLP. SVM demonstrates exceptional classification accuracy and results in a
robust way of limb motion classification with low computational cost. The validity of entropy, as an index to measure correctness of classification, is also examined. Experimental results show that entropy is a reliable measure for online training in myoelectric control systems.
نمایش نتایج ۱ تا ۳ از میان ۳ نتیجه