[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121912-en":3,"doc-seo-121912-105":30,"detail-sidebar-cat-0-en-105":83},{"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":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},121912,549758252649,"Ivy","https://ap-avatar.wpscdn.com/avatar/8000253669c5317157?_k=1778319167496531819",7,"Healthcare","Sign Language Conversation Interpretation Using Wearable Sensors and Machine Learning","Hearing loss affects communication access and participation in personal and professional life, creating a widening gap between people with hearing impairments and those around them. This paper proposes a proof of concept for an automatic American Sign Language (ASL) dynamic word interpretation system using data from a wearable device with three flex sensors. Sign sequences are collected and classified with machine learning models, reaching up to 99% accuracy with Random Forest and SVM, and 98% with KNN. Results support paths toward full-scale deployment.","arXiv :2312 . 11903v1 [ ee ss . SP] 19 Dec 2023  \nSign Language Conversation Interpretation Using Wearable Sensors and Machine Learning  \nBasma Kalandar and Ziemowit Dworakowski  \nAGH University of Science and Technology, Department of Robotics and  \nMechatronics  \nDecember 20, 2023  \nAbstract  \nThe count of people suffering from various levels of hearing loss reached 1.57 billion in  \n2019. This huge number tends to suffer on many personal and professional levels and strictly needs to be included with the rest of society healthily. This paper presents a proof of concept of an automatic sign language recognition system based on data obtained using a wearable device of 3 flex sensors. The system is designed to interpret a selected set of American Sign Language (ASL) dynamic words by collecting data in sequences of the performed signs and using machine learning methods. The built models achieved high-quality performances, such as Random Forest with 99% accuracy, Support Vector Machine (SVM) with 99%, and two K-Nearest Neighbor (KNN) models with 98% . This indicates many possible paths toward the development of a full-scale system.  \nKeywords American Sign Language; Random Forest; SVM; KNN; Logistic Regression; Flex sensors; gesture recognition; dynamic signs.  \n1 Introduction  \n1.1 Addressing the problem  \nPeople who suffer from different levels of hearing loss (impaired) and the disabled; all end up being partially, if not almost completely, excluded in their societies due to losing the possibility of communication through words. In 2019, 1.57 Billion people globally suffered from different levels of hearing loss [1] . Figure 1 shows the proportion of hearing loss levels among people between the prevalence of hearing loss and the number of Years Lived with the Disability (YLD) .  \nFigure 1: Proportion of individuals with moderate-to-complete hearing loss by measure and severity  \nAccording to Fernandes et al. [2] quoting the World Health Organization (WHO) in 2020,”a total of 466 million individuals globally have a hearing impairment, and this number is predicted to rise to 900 million individuals in another 30 years, by the year 2050 . Furthermore, current estimates suggest an 83 percent gap in the available aid, i.e., only 17 percent of those who require aid can use it.”. This means that 747 million individuals worldwide won’t be provided with the necessary means to compensate for their disabilities. The fact that these people are being held back affects them, their families, their community, and society.  \nThe communication quality for the impaired suffers mostly due to the lack of knowledge of sign language among common people. These negatively affect their employment chances, cognitive development, and emotional and mental well-being.  \nCommunication for the impaired is based on sign language, which mainly depends on the hand (or both hands) shape, the hand position relative to the signer’s body, and the motion done by the signer. Facial expression is an additional factor used to convey complementary meanings or intentions, such as emotions, agreeing and disagreeing, and indicating a question rather than a statement.  \n1.2 Related Work  \nThe need for a practical, reliable system to close the communication gap between the impaired and those around them is crucial on both individual and community levels. Automatic recognition of sign language is thus an important area of research. Modern approaches to address the problem focus mainly on the hands gestures previously mentioned, either the hand shape and position (known as static signs) or the hand shape, position, and movement (known as dynamic signs) . As a result, they tend to omit the facial expression factor as it is not essential for the initial interpretation of the signs as much as giving them and the conversation more context, which is mostly intuitively understood by the addressed person. Those approaches are divided into two main categories:  \n1. Vision-based Soluti","cbCaimlkktvx7JLa","https://ap.wps.com/l/cbCaimlkktvx7JLa","pdf",4545659,1,12,"English","en",105,"# Introduction\n## Addressing the problem\n## Related work\n# Sign language conversation interpretation system\n## Data collection with wearable sensors\n## Machine learning approaches and results","[{\"question\":\"Which models and accuracies are reported?\",\"answer\":\"The paper reports high-quality performance including Random Forest at 99% accuracy, SVM at 99%, and two KNN models at 98%, indicating strong recognition capability for selected dynamic words.\"}]","Sign Language Conversation Interpretation Using Wearable Sensors and Machine Learning | PDF",1785807702,30,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":78,"head_meta":80,"extra_data":82,"updated_unix":28},"sign-language-conversation-interpretation-using-wearable-sensors-and-machine-learning","",{"@graph":36,"@context":77},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/healthcare/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/sign-language-conversation-interpretation-using-wearable-sensors-and-machine-learning/121912/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71],{"name":72,"@type":73,"acceptedAnswer":74},"Which models and accuracies are reported?","Question",{"text":75,"@type":76},"The paper reports high-quality performance including Random Forest at 99% accuracy, SVM at 99%, and two KNN models at 98%, indicating strong recognition capability for selected dynamic words.","Answer","https://schema.org",{"og:url":52,"og:type":79,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":81,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":84},[85,89,93,97,102,107,110,114,119,122,126],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":86,"show_sort_weight":87,"slug":88},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":90,"show_sort_weight":91,"slug":92},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Exam",70,"exam",{"id":98,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},5,"Comic",60,"comic",{"id":103,"doc_module":4,"doc_module_name":46,"category_name":104,"show_sort_weight":105,"slug":106},6,"Technology",50,"technology",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":108,"slug":109},40,"healthcare",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":29,"slug":113},8,"Research & Report","research-report",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},9,"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":123,"slug":125},10,"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":98,"slug":129},19,"General","general"]