استفاده از تركيب الگوريتم ژنتيك و شبكه هاي عصبي مصنوعي براي پيش بيني نيروي گاز گرفتن از روي سيگنال الكترومايوگرام

Application of an ANN-GA Method for Predicting the Biting Force Using Electromyogram Signals

امروزه بررسي ارتباط بين سيگنال­‌هاي نيرو و فعاليت الكتريكي عضله‌­ها بسيار حائز اهميت بوده و در مسائل مهمي مانند تحليل حركت، علوم ارتوپدي، توانبخشي، طراحي ارگونوميك و تعامل انسان- ماشين و كاربردهاي پزشكي مانند كنترل پروتزهاي مصنوعي كاربرد فراواني دارد. از مزيت­‌هاي استفاده از الكترودهاي سطحي، ارزان­تر و قابل­‌حمل‌بودن آن­ها در مقايسه با حس‌گرهاي نيرو است كه به‌طورمعمول گران هستند و ساختار حجيمي دارند. از آنجايي كه اندازه­‌گيري نيروي گاز‌گرفتن بسيار سخت و پيچيده است، در اين مقاله مي‌­خواهيم توانايي شبكه‌هاي عصبي چند لايه پرسپترون (MLPANN) و توابع با پايه شعايي (RBFANN) را در پيش ­بيني نيروي گاز‌گرفتن توسط دندان پيشين از روي سيگنال­‌هاي اكترومايوگرام صورت بررسي كنيم. بدين منظور سيگنال الكترومايوگرام عضلات گيجگاهي و ماضغه و نيروي گاز‌گرفتن به‌ترتيب به‌عنوان ورودي و خروجي شبكه‌­هاي عصبي در نظر گرفته شده­‌اند. براي پيدا‌كردن بهترين ساختار شبكه و تأخير زماني مناسب سيگنال­‌هاي الكترومايوگرام، از الگوريتم ژنتيك (GA) استفاده شده است. نتايج نشان مي‌­دهند كه سيگنال الكترومايوگرام عضلات يادشده شامل اطلاعات مفيدي از نيروي گازگرفتن هستند. روش‌­هاي MLPANN و RBFANN ديناميك مورد نظر را با دقت مناسبي شناسايي مي­‌كنند. درصد ميانگين مربع خطا در مرحله آموزش و آزمون به‌ ترتيب 2/3%و 19/4% براي MLPANN و 8/3% و 22/7% براي RBFANN است. همچنين روش تحليل واريانس نشان مي‌­دهد كه تفاوت معناداري بين نتايج حاصله از MLPANN و RBFANN وجود ندارد.

Human mastication is a common rhythmic behavior and a complex biomechanical process which is hard to reproduce. Today, investigating the relation between electrical activity of muscles and force signals is of high importance in many applications including gait analysis, orthopedics, rehabilitation, ergonomic design, haptic technology, tele-presence surgery and human-machine interaction. Surface electrodes have many advantages over force sensors which are often expensive and of massive structure, two of which are less expensive and portable. Since the biting force is too difficult to be measured, in this paper, we aim to investigate the ability of a Multi-Layer Perceptron artificial neural network (MLPANN) and Radial Basis Function artificial neural network (RBFANN) to predict the biting force of incisor teeth based on surface electromyography (EMG) signals. RBFANN and MLPANN are two of the most widely used neural network architecture. These two methods are both known as universal approximates for nonlinear input-output mapping. To do this, biting force and EMG signals from the masticatory muscles were recorded and used as output and input of neural networks, respectively. Genetic algorithm was applied to find the best structure for ANNs and the appropriate total time-delay of EMGs. Results show that the EMG signals recorded from aforementioned muscles contain useful information about the biting force. Furthermore, they indicate that MLPANN and RBFANN can detect the dynamics of the system with good precision. The mean percentage error in the training and validation phase is %2.3 and %19.4 for MLPANN and %8.3 and %22.7 for RBFANN, sequentially. Also the variance analysis technique shows that there is no significant difference between results achieved through MLPANN and RBFANN. The provided analysis will aid researchers in characterizing and investigating the mastication process, through the specification of SEMG signal patterns and the observation of the resulting biting force. Such models can provide clinical insight into the development of more effective rehabilitation therapies, and can aid in assessing the effects of an intervention. This methodology can be applied to any tele-operated robot or orthotic device (exoskeleton), either for rehabilitation or extension of human ability.