[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124111-en":3,"doc-seo-124111-105":30,"detail-sidebar-cat-0-en-105":91},{"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},124111,7971461740886,"Theodore","https://ap-avatar.wpscdn.com/davatar_3d24733baf745e90a7e4bdd5f77d97b2",6,"Technology","Selective Mobile Device Screen Activation Using Sensor Fusion and Machine Learning","Proximity sensing on mobile devices can malfunction in conditions such as direct sunlight or specific hand/ear angles, causing incorrect screen brightness and touch activation and leading to unintended behaviors like inadvertent call hang-ups. This disclosure presents an on-device machine-learning face proximity detector that fuses multi-sensor inputs—accelerometer, gyroscope, ambient light sensor, proximity sensor, and related signals—to estimate phone-to-face distance with high detection accuracy. The approach aims for a low false-alarm rate while keeping operation stable and reliable across varied scenarios.","Technical Disclosure Commons  \nDefensive Publications Series  \n29 Jan 2025  \nSelective Mobile Device Screen Activation Using Sensor Fusion and Machine Learning  \nChris Kuiper Vishal Agarwal Hong Z. Tan Alessio Centazzo  \nKeyu Chen  \nFollow this and additional works at: [https://www.tdcommons.org/dpubs_series](https://www.tdcommons.org/dpubs_series)  \nRecommended Citation  \nKuiper, Chris; Agarwal, Vishal; Tan, Hong Z.; Centazzo, Alessio; and Chen, Keyu, \"Selective Mobile Device Screen Activation Using Sensor Fusion and Machine Learning\", Technical Disclosure Commons,(January 29, 2025)  \n[https://www.tdcommons.org/dpubs_series/7777](https://www.tdcommons.org/dpubs_series/7777)  \nThis work is licensed under a Creative Commons Attribution 4.0 License.  \nThis Article is brought to you for free and open access by Technical Disclosure Commons. It has been accepted for inclusion in Defensive Publications Series by an authorized administrator of Technical Disclosure Commons.  \nSelective Mobile Device Screen Activation Using Sensor Fusion and Machine Learning  \nABSTRACT  \nProximity sensors used by mobile devices such as a smartphone to activate the screen can malfunction under certain situations, e.g., direct sunlight, holding the phone against the ear at certain angles, etc. This disclosure describes a stable and accurate face proximity detector based on an on-device machine-learning (ML) model that fuses multi-sensor inputs, including inputs  \nfrom sensors such as accelerometer, gyroscope, ambient light sensor (ALS), proximity sensor,  \netc., to determine the phone-to-face distance and to correctly activate the screen at a high  \ndetection rate and a low false alarm rate.  \nKEYWORDS  \n● Proximity sensing  \n● Proximity detection  \n● Face proximity  \n● Gesture detection  \n● Gesture duration  \n● Screen activation  \n● Screen malfunction  \n● Screen brightness  \n● Touch sensitivity  \n● Sensor fusion  \n● On-device machine learning  \nPublished by Technical Disclosure Commons, 2025 2  \nBACKGROUND  \nReadings from a proximity sensor on a mobile device such as a smartphone are used to  \ndetermine the distance of the device from the user’s face and to accordingly turn on/off the  \nbrightness and touch sensitivity of the screen. However, proximity sensing can malfunction in  \ncertain situations such as:  \n● Under direct sunlight, the proximity sensor can get deactivated due to high infrared radiation (IR) and can fail to accurately determine the distance of the device from the user’s face. This causes the screen and touch sensitivity to remain on even when the user moves the phone to their face. As a result, hang-up of a voice call may inadvertently occur due to incorrect activation of the device touchscreen when the phone screen brushes against their cheek.  \n● Holding a phone near the ear at a tilt angle greater than the detection range can cause the phone to incorrectly determine that it is away from the face, causing the screen to turn on. In this case (a false negative), hang-up of a voice call may inadvertently occur due to incorrect activation of the device touchscreen when the phone screen brushes against their cheek.  \nSome current techniques to improve the accuracy of proximity detection include:  \n● Using inertial measurement unit (IMU) sensors such as accelerometer and gyroscopes to detect gestures. These are limited to certain gestures and have high false positive rates.  \n● Using touch events and data to classify cheek touches as non-triggers for screen activation. This works when the phone is near the face; in particular, it does not address the issues caused by the device being under sunlight.  \n[https://www.tdcommons.org/dpubs_series/7777](https://www.tdcommons.org/dpubs_series/7777) 3  \n● Using ultrasound waves emitted by the speakers and captured by the microphone to estimate the phone-to-face distance. This has a high false-trigger rate and does not work when the phone is too close to the cheek.  \nExisting techniques use heurist","cbCaik8QOnQIQQth","https://ap.wps.com/l/cbCaik8QOnQIQQth","pdf",302101,1,9,"English","en",105,"# Abstract\n# Background\n## Failure scenarios and false activations\n## Limitations of existing techniques\n# Description\n## Multi-sensor ML-based face proximity detector\n## Processing pipeline (segmentation, normalization, downsampling, feature extraction, ML inference)\n# Figures","[{\"question\":\"Why can a mobile device proximity sensor malfunction during screen activation?\",\"answer\":\"Malfunction can occur under conditions like direct sunlight, which can deactivate the proximity sensor due to high infrared radiation, and when holding the phone near the ear at angles outside the detection range. These situations can lead to incorrect distance determination and unintended screen activation.\"},{\"question\":\"What core method does the disclosure propose to improve accuracy?\",\"answer\":\"It proposes an on-device machine-learning model that fuses inputs from multiple sensors, such as the accelerometer, gyroscope, ambient light sensor (ALS), and proximity sensor. The model predicts phone-to-face distance to trigger screen activation reliably with a low false alarm rate.\"},{\"question\":\"How are sensor signals processed before ML inference?\",\"answer\":\"The disclosure describes segmenting raw sensor data, normalizing and downsampling as needed, extracting features, and feeding those features into the machine-learning model. The model then outputs a prediction such as whether the phone is close to or away from the face/ear.\"}]","Selective Mobile Device Screen Activation Using Sensor Fusion and Machine Learning | PDF",1785820473,23,{"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":86,"head_meta":88,"extra_data":90,"updated_unix":28},"selective-mobile-device-screen-activation-using-sensor-fusion-and-machine-learning","",{"@graph":36,"@context":85},[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/technology/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/selective-mobile-device-screen-activation-using-sensor-fusion-and-machine-learning/124111/",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",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why can a mobile device proximity sensor malfunction during screen activation?","Question",{"text":75,"@type":76},"Malfunction can occur under conditions like direct sunlight, which can deactivate the proximity sensor due to high infrared radiation, and when holding the phone near the ear at angles outside the detection range. These situations can lead to incorrect distance determination and unintended screen activation.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What core method does the disclosure propose to improve accuracy?",{"text":80,"@type":76},"It proposes an on-device machine-learning model that fuses inputs from multiple sensors, such as the accelerometer, gyroscope, ambient light sensor (ALS), and proximity sensor. The model predicts phone-to-face distance to trigger screen activation reliably with a low false alarm rate.",{"name":82,"@type":73,"acceptedAnswer":83},"How are sensor signals processed before ML inference?",{"text":84,"@type":76},"The disclosure describes segmenting raw sensor data, normalizing and downsampling as needed, extracting features, and feeding those features into the machine-learning model. The model then outputs a prediction such as whether the phone is close to or away from the face/ear.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,113,118,123,127,130,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":111,"slug":112},50,"technology",{"id":114,"doc_module":4,"doc_module_name":46,"category_name":115,"show_sort_weight":116,"slug":117},7,"Healthcare",40,"healthcare",{"id":119,"doc_module":4,"doc_module_name":46,"category_name":120,"show_sort_weight":121,"slug":122},8,"Research & Report",30,"research-report",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]