[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125587-en":3,"doc-seo-125587-105":29,"detail-sidebar-cat-0-en-105":90},{"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":11,"language":21,"language_code":22,"site_id":23,"html_lang":22,"table_of_contents":24,"faqs":25,"seo_title":26,"seo_description":14,"update_tm":27,"read_time":28},125587,687197100911,"Himbo","https://ap-avatar.wpscdn.com/avatar/a000239b6f1da00475?x-image-process=image/resize,m_fixed,w_180,h_180&k=1785132997149421697",8,"Research & Report","Machine Learning and Kalman Filtering for Nanomechanical Mass Spectrometry","Nanomechanical resonant sensors enable mass spectrometry by detecting resonance frequency jumps, but a core speed–accuracy trade-off limits temporal and size resolution due to resonator characteristics and noise. An adaptive Kalman filtering approach augmented with maximum-likelihood estimation has been proposed as a Pareto-optimal solution. This work introduces confidence-boosted thresholding and machine-learning event detection using neural networks and boosted decision trees for event timing and size estimation, including a pure learning variant and a Kalman-augmented likelihood classifier.","Machine Learning and Kalman Filtering for Nanomechanical Mass Spectrometry  \nMete Erdogan, Nuri Berke Baytekin, Serhat Emre Coban, Alper Demir  \narXiv :2306 .00563v1 [physics .ins-det] 1 Jun 2023  \nAbstract—Nanomechanical resonant sensors are used in mass spectrometry via detection of resonance frequency jumps. Thereis a fundamental trade-off between detection speed and accuracy. Temporal and size resolution are limited by the resonator characteristics and noise. A Kalman filtering technique, augmented with maximum-likelihood estimation, was recently proposed asa Pareto optimal solution. We present enhancements and robust realizations for this technique, including a confidence boosted thresholding approach as well as machine learning for event detection. We describe learning techniques that are based on neural networks and boosted decision trees for temporal location and event size estimation. In the pure learning based approach that discards the Kalman filter, the raw data from the sensor are used in training a model for both location and size prediction. In the alternative approach that augments a Kalman filter, the event likelihood history is used in a binary classifier for event occurrence. Locations and sizes are predicted using maximumlikelihood, followed by a Kalman filter that continually improves the size estimate. We present detailed comparisons of the learning based schemes and the confidence boosted thresholding approach, and demonstrate robust performance for a practical realization.  \nIndex Terms—nanomechanical resonant sensor, mass spectrometry, Kalman filter, adaptive filtering, machine learning, maximum-likelihood estimation, classification.  \nI. INTRODUCTION  \nNANOMECHANICAL resonant sensors are used for the  \ndetection of nano-scale particles and atomic forces, with many applications in experimental physics, nano-engineering and molecular medicine [1] . Nano-scale mass additions cause deviations in the resonance frequency, which can be detected and tracked using several schemes, such as the feedback-free (FF), the frequency-locked loop (FLL) and the self-sustaining oscillator (SSO) configurations [1] .  \nA. Trade-off between speed and accuracy  \nIn the simplest FF tracking scheme, the response to a sudden change in the resonance frequency is limited by the mechanical time constant of the resonator, and can be modeled as the step response of a one-pole low pass filter with the transfer function HR (s) = 1+~~1~~sτr . Here, τr is the time constant of the resonator, and is inversely proportional to its quality factor. The step response, ignoring noise, is simply given by  \n∆ωr (t) = ∆ωe (1 − e−t/τr ) , (1)  \nfor a sudden change ∆ωe in the resonance frequency. With modified FF, FLL and SSO schemes, one can speed up  \nAuthors are with the Department of Electrical Engineering, Koç University, Istanbul 34450, Turkey.  \nthis response considerably but at the expense of degraded accuracy [2] . The degradation or improvement in the accuracy or speed stem from a change in the effective bandwidth of the system, which also determines its noise filtering characteristics. The noise sources in a nanomechanical sensor include the fundamental thermomechanical noise of the resonator, and noise generated in the transduction of the mechanical motion into an electrical signal and in the subsequent processing in the electrical domain [3] . There is a fundamental trade-off between speed and accuracy that can not be circumvented.  \nB. Kalman filtering and likelihood based event detection  \nA Kalman filtering based technique was recently proposed to detect and track resonance frequency changes [4] . This technique uses the raw output of the standard FF scheme operating in a slow speed but high accuracy point on the trade-off characteristics. Extremely fast predictions for both the temporal locations and also the sizes of events can be made using models for the system and streaming measured sensor data. Event size predictions, that are ","cbCailMcjfa69DEh","https://ap.wps.com/l/cbCailMcjfa69DEh","pdf",1204997,1,"English","en",105,"# Introduction\n## Trade-off between speed and accuracy\n## Kalman filtering and likelihood based event detection","[{\"question\":\"为什么纳米机械共振传感器在质谱中会面临速度与精度的权衡？\",\"answer\":\"共振响应的建立速度受机械时间常数等因素限制，而系统有效带宽同时决定噪声抑制能力，因此速度提升往往会导致精度下降，噪声来源也会影响可实现的分辨率。\"},{\"question\":\"文中提出的 Kalman 过滤在事件检测中如何工作？\",\"answer\":\"Kalman 过滤利用设备的流式测量与系统模型进行状态估计，但无法直接预测突变。通过结合最大似然的事件检测算法，计算滑动窗口内突变事件发生的似然并在超过阈值后判定事件发生，再用最大似然估计事件发生时刻与频率跳变大小。\"},{\"question\":\"机器学习方案与“Kalman 增强”方案有何不同？\",\"answer\":\"纯学习方案丢弃 Kalman 过滤，直接用传感器原始数据训练模型以同时预测事件位置与大小；Kalman 增强方案则使用事件似然历史进行二分类确定事件出现，并在随后通过最大似然与更新后的 Kalman 过滤持续改进大小估计。\"}]","Machine Learning and Kalman Filtering for Nanomechanical Mass Spectrometry | PDF",1785900089,20,{"code":4,"msg":30,"data":31},"ok",{"site_id":23,"language":22,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":27},"machine-learning-and-kalman-filtering-for-nanomechanical-mass-spectrometry","",{"@graph":35,"@context":84},[36,53,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/machine-learning-and-kalman-filtering-for-nanomechanical-mass-spectrometry/125587/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":22,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"为什么纳米机械共振传感器在质谱中会面临速度与精度的权衡？","Question",{"text":74,"@type":75},"共振响应的建立速度受机械时间常数等因素限制，而系统有效带宽同时决定噪声抑制能力，因此速度提升往往会导致精度下降，噪声来源也会影响可实现的分辨率。","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"文中提出的 Kalman 过滤在事件检测中如何工作？",{"text":79,"@type":75},"Kalman 过滤利用设备的流式测量与系统模型进行状态估计，但无法直接预测突变。通过结合最大似然的事件检测算法，计算滑动窗口内突变事件发生的似然并在超过阈值后判定事件发生，再用最大似然估计事件发生时刻与频率跳变大小。",{"name":81,"@type":72,"acceptedAnswer":82},"机器学习方案与“Kalman 增强”方案有何不同？",{"text":83,"@type":75},"纯学习方案丢弃 Kalman 过滤，直接用传感器原始数据训练模型以同时预测事件位置与大小；Kalman 增强方案则使用事件似然历史进行二分类确定事件出现，并在随后通过最大似然与更新后的 Kalman 过滤持续改进大小估计。","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":23},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,126,129,133],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":28,"slug":125},9,"Religion & Spirituality","religion-spirituality",{"id":28,"doc_module":4,"doc_module_name":45,"category_name":127,"show_sort_weight":28,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":45,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":45,"category_name":135,"show_sort_weight":105,"slug":136},19,"General","general"]