[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128185-en":3,"doc-seo-128185-105":31,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},128185,2336475104042,"Skyler","https://ap-avatar.wpscdn.com/avatar/22000c4c32af1715be0?x-image-process=image/resize,m_fixed,w_180,h_180&k=1786537525561427321",8,"Research & Report","Controlling a Prosthetic Limb via Interpreting Arbitrary Signals Through Machine Learning - Thesis","Machine learning is used to enable more natural and intuitive control of prosthetic limbs than current systems that rely on non-intuitive patient motions. The thesis develops a human-machine interface using six non-invasive surface EMG sensors connected to an Arduino-based microprocessor for signal interpretation. Multiple models are evaluated, including a Multilayer Perceptron and Gradient Boosted Trees, with analysis of sensor count effects, real-time live-data classification, error sources, and expansion to additional gestures.","CALIFORNIA STATE UNIVERSITY, NORTHRIDGE  \nControlling a Prosthetic Limb via Interpreting Arbitrary Signals Through  \nMachine Learning  \nA thesis in partial fulfillment of the requirements For the degree of Master of Science in Software Engineering  \nBy  \nNicholas Clayton  \nThe thesis of Nicholas Clayton is approved:  \nAni Nahapetian, Ph.D. Date  \nKyle Dewey, Ph.D.  \nDate  \n____________________________________ __________  \nGeorge Wang, Ph.D., Chair Date  \nCalifornia State University, Northridge  \nACKNOWLEDGMENTS  \nThis project utilizes a modified C++ library entitled fix_fft authored by Dimitrios P. Bouras and maintained by Enrique Condes to perform a fixedpoint in-place fast Fourier Transform to process incoming EMG data .  \nTable of Contents  \nSIGNATURE PAGE................................................................................ ii  \nACKNOWLEDGMENTS.......................................................................... iii  \n[LIST OF TABLES................................................................................. vi](LIST OF TABLES................................................................................. vi)  \n[LIST OF FIGURES..............................................................................](LIST OF FIGURES..............................................................................). vii  \nABSTRACT ....................................................................................... viii  \n1. INTRODUCTION ............................................................................... 1  \n1.1 Problem Statement..................................................................... 1  \n1.2 Objective...................................................................................3  \n2. SURVEYS AND RELATED WORKS........................................................ 5  \n3. TECHNICAL APPROACH.....................................................................8  \n3.1 Hardware Configuration ...............................................................8  \n3.2 Data Handling and Pre-processing.................................................9  \n4. MODELS ....................................................................................... 12  \n4.1 Multilayer Perceptron (MLP) ........................................................ 12  \n4.2 Gradient Boosted Trees (GBT) ..................................................... 14  \n5. RESULTS ...................................................................................... 15  \n5.1 Multilayer Perceptron Statistics ................................................... 16  \n5.2 Multilayer Perceptron Performance Comparisons ............................20  \n5.3 Effects of Number of Sensors on Performance ...............................21  \n5.4 Gradient Boosted Tree Comparison ..............................................24  \n5.5 Real-time Classification of Live Data ............................................24  \n5.6 Potential Sources of Error ...........................................................27  \n5.7 Training Additional Gestures .......................................................28  \n6. CONCLUSIONS..............................................................................31  \n6.1 Overall System Performance .......................................................31  \n6.2 Future Work.............................................................................32  \n6.3 Final Thoughts ..........................................................................34  \n7. BIBLIOGRAPHY..............................................................................35  \nLIST OF TABLES  \nTable 1: Average MLP Model Performance Statistics ................................23  \nTable 2: Classification Scores for Each MLP Model...................................23  \nTable 3: Extended Gesture MLP Model Performance Statistics ...................29  \nTable 4: Average Classification Scores for Extended Gesture MLP Models...30  \nLIST OF FIGURES  \nFigure 1: ","cbCaig9PTWP3hrYB","https://ap.wps.com/l/cbCaig9PTWP3hrYB","pdf",1131843,4,1,44,"English","en",105,"# 1. Introduction\n## 1.1 Problem Statement\n## 1.2 Objective\n# 2. Surveys and Related Works\n# 3. Technical Approach\n## 3.1 Hardware Configuration\n## 3.2 Data Handling and Pre-processing\n# 4. Models\n## 4.1 Multilayer Perceptron (MLP)\n## 4.2 Gradient Boosted Trees (GBT)\n# 5. Results\n## 5.1 Multilayer Perceptron Statistics\n## 5.2 Multilayer Perceptron Performance Comparisons\n## 5.3 Effects of Number of Sensors on Performance\n## 5.4 Gradient Boosted Tree Comparison\n## 5.5 Real-time Classification of Live Data\n## 5.6 Potential Sources of Error\n## 5.7 Training Additional Gestures\n# 6. Conclusions\n## 6.1 Overall System Performance\n## 6.2 Future Work\n## 6.3 Final Thoughts\n# 7. Bibliography","[{\"question\":\"What problem does the thesis address in prosthetic limb control?\",\"answer\":\"Current prosthesis control often requires awkward, non-intuitive motions. The thesis targets improving usability by enabling more natural and intuitive control through machine learning.\"},{\"question\":\"How does the system collect input signals for the prosthetic controller?\",\"answer\":\"It uses six non-invasive surface EMG sensors placed on an elastic band to capture muscle activity. An Arduino-based microprocessor interprets the sensor signals for subsequent processing.\"},{\"question\":\"Which machine learning models are evaluated and what aspects are analyzed?\",\"answer\":\"A Multilayer Perceptron and Gradient Boosted Trees are compared. Results include model statistics, performance comparisons, the effect of sensor number, real-time classification on live data, potential error sources, and retraining for additional gestures.\"}]","Controlling a Prosthetic Limb via Interpreting Arbitrary Signals Through Machine Learning - Thesis | PDF",1785945342,111,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":29},"controlling-a-prosthetic-limb-via-interpreting-arbitrary-signals-through-machine-learning-thesis","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,52],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":51},"https://docshare.wps.com/document/research-report/",3,{"item":53,"name":13,"@type":44,"position":20},"https://docshare.wps.com/document/controlling-a-prosthetic-limb-via-interpreting-arbitrary-signals-through-machine-learning-thesis/128185/",{"url":53,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-29","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What problem does the thesis address in prosthetic limb control?","Question",{"text":76,"@type":77},"Current prosthesis control often requires awkward, non-intuitive motions. The thesis targets improving usability by enabling more natural and intuitive control through machine learning.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does the system collect input signals for the prosthetic controller?",{"text":81,"@type":77},"It uses six non-invasive surface EMG sensors placed on an elastic band to capture muscle activity. An Arduino-based microprocessor interprets the sensor signals for subsequent processing.",{"name":83,"@type":74,"acceptedAnswer":84},"Which machine learning models are evaluated and what aspects are analyzed?",{"text":85,"@type":77},"A Multilayer Perceptron and Gradient Boosted Trees are compared. Results include model statistics, performance comparisons, the effect of sensor number, real-time classification on live data, potential error sources, and retraining for additional gestures.","https://schema.org",{"og:url":53,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]