专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明公开

EP4414959A1 COMPUTER-IMPLEMENTED METHOD FOR TRAINING OF A MACHINE LEARNING MODEL IN ACCIDENT EVENT ASSESSMENT 审中-公开
公开(公告)号：EP4414959A1
公开(公告)日：2024-08-14
申请号：EP23155609.3
申请日：2023-02-08
申请人： Autoliv Development AB
发明人： Alkhoury, Ziad , Ahmed, Jawwad
IPC分类号： G08B21/04 , A61B5/11 , G16H50/30
CPC分类号： G08B21/0446 , A61B5/1117 , G16H50/30 , G16H50/70 , G16H50/20 , G16H40/63 , G16H40/67 , G08B29/186
摘要： The present disclosure relates to a computer-implemented method for training of machine learning models in person accident event assessment. The method comprises preparing (S200) training data, by obtaining and automatically acquiring (S210) sensor data generated from sensors (2, 3; 6, 7) at an initial group (200) of subjects (201a-201c), and dividing (S220) the group (200) of subjects (201a-201c) into sub-groups (200a-200h) associated with certain corresponding features that are unique for the subjects (201a-201c) in that sub-group (200a-200h). The method further comprises training (S400) an initial machine learning model for the subjects in the initial group (200) and training (S500) a plurality of machine learning sub-models for the subjects (201a-201c) in the corresponding sub-group (200a-200h), such that one machine learning sub-model for each sub-group (200a-200h) is obtained.

2. 发明公开

EP4379692A2 DETECTING TIRE OR WHEEL THEFT ACTIVITY 审中-公开
公开(公告)号：EP4379692A2
公开(公告)日：2024-06-05
申请号：EP23212116.0
申请日：2023-11-24
申请人： The Goodyear Tire & Rubber Company
发明人： MORRIS, Brian Richard , MILLIREN, Mark Robert
IPC分类号： G08B13/16 , B60R25/10 , G08B29/18
CPC分类号： G08B13/1654 , G08B29/186 , G08B29/188 , B60R25/1004
摘要： A vehicle trailer system is disclosed comprising: a computing device attached to a trailer, the computing device comprising an accelerometer, a processor, and memory; a tire sensor attached to a wheel of the trailer and in data communication with the computing device; machine-readable instructions stored in the memory that, when executed by the processor, cause the computing device to at least: detect an occurrence of an event, the event comprising at least one of a change in height to a portion of the trailer from an accelerometer of the computing device or a pressure loss event; identify a vibration measurement from the accelerometer; and transmit an indication of a theft event to a remote computing device. Also, a method of indicating a theft event is disclosed. The method comprises detecting, by a trailer computing device that is attached to a trailer apparatus, an occurrence of an event, the event comprising at least one of a change in height to a portion of the trailer apparatus from an accelerometer of the trailer computing device or a pressure loss event; identifying, by the accelerometer of the trailer computing device, a vibration measurement from the accelerometer; and transmitting, by the trailer computing device, an indication of a theft event to a remote computing device.

3. 发明公开

EP3220367A1 SYSTEM AND METHOD FOR SOUND BASED SURVEILLANCE 审中-公开
标题翻译：用于基于声音监视的系统和方法
公开(公告)号：EP3220367A1
公开(公告)日：2017-09-20
申请号：EP17160362.4
申请日：2017-03-10
申请人： Tata Consultancy Services Limited
发明人： SUBRAMANIAN, Shivakumar , KOPPARAPU, Sunilkumar
IPC分类号： G08B13/16 , G08B29/18 , G06N5/02 , G08B21/04 , G08B25/00 , G08B21/02
CPC分类号： G08B13/1672 , G06N5/022 , G08B21/02 , G08B21/0415 , G08B21/0423 , G08B21/0438 , G08B21/0469 , G08B25/001 , G08B29/186
摘要： A system and method to identify abnormal events by collecting sound input received from a plurality of sensors in a monitored area, wherein the sensors can be fixed or mobile. Context metadata (time and location) is associated to the collected sound data. A sensor map is created by associating sensor data to location information.
Adjacent sound frames are analysed in the detector for deviations in sound attributes representing a potential abnormal event at the monitored area. Rules from a rule builder are applied to the context metadata or sound data collected by nearby sensors to determine the plausibility that the candidate event represents indeed an abnormality. Alerts are in this case issued to the authorities.
Sound data as well as contextual data associated with the event are stored in a central server to be used for continuous learning.
Can be applied to public places such as schools, bus stops, stations, airports.
摘要翻译：一种通过收集从监测区域中的多个传感器接收到的声音输入来识别异常事件的系统和方法，其中传感器可以是固定的或移动的。上下文元数据（时间和位置）与收集的声音数据相关联。通过将传感器数据与位置信息相关联来创建传感器图。在检测器中分析相邻声音帧的声音属性偏差，这些声音属性表示监测区域的潜在异常事件。来自规则构建器的规则被应用于由附近传感器收集的上下文元数据或声音数据，以确定候选事件实际上表示异常的合理性。在这种情况下警报是向当局发出的。声音数据以及与事件相关的上下文数据存储在中央服务器中以用于持续学习。可以应用于公共场所，如学校，巴士站，车站，机场。

4. 发明公开

EP0834845A1 Verfahren zur Frequenzanalyse eines Signals 失效
标题翻译： Verfahren zur Frequenzanalyse eines信号
公开(公告)号：EP0834845A1
公开(公告)日：1998-04-08
申请号：EP96115952.2
申请日：1996-10-04
申请人： CERBERUS AG
发明人： Thuillard, Marc Pierre, Dr.
IPC分类号： G08B17/02
CPC分类号： G08B29/186
摘要： In einem Verfahren zur Frequenzanalyse eines Signals wird eine Wavelet-Transformation mit Fuzzy-Logik vereinigt. In der Transformation mittels einem orthonormalen oder semi-orthonormalen Wavelet wird das ursprüngliche Signal einer mehrstufigen Filterkaskade von Hoch-/Tiefpassfilterpaaren zugeführt. Bei jeder Filterstufe wird aus Resultaten des Hochpassfilters, Wavelet-Koeffizienten und Werten des ursprünglichen Signals eine Zugehörigkeitsfunktion erzeugt. Diese Funktionen sind normalisiert und werden in dieser Form für die weitere Auswertung nach Fuzzy-Logik-Regeln verwendet. Das Verfahren eignet sich insbesondere für die Auswertung der Ausgangssignale von Sicherheitsmeldern wie Flammenmeldern, Geräuschmeldern und dergleichen. Die Wavelet-Transformation und Fuzzy-Logik-Auswertung erfolgt durch eine kleine Anzahl Zeilen von Prozessorcode, wodurch die Auswertung mit einem kostengünstigen Prozessor realisierbar ist und sie bei gleicher oder erhöhter Genauigkeit beschleunigt wird.
摘要翻译：该方法涉及快速小波变换和模糊逻辑。在小波变换期间，原始信号通过高/低通滤波器对的级联。快速小波变换与模糊逻辑评估相结合，从而得到一个对应关系。从每个滤波器级的高通滤波器的结果产生功能。对应功能用于使用模糊逻辑规则进一步分析频率信号。

5. 发明公开

EP0630208A1 WRIST-HELD MONITORING DEVICE FOR PHYSICAL CONDITION 失效
标题翻译：腕戴式监测装置的物理。
公开(公告)号：EP0630208A1
公开(公告)日：1994-12-28
申请号：EP93904063.0
申请日：1993-02-26
申请人： MYLLYMÄKI, Matti
发明人： MYLLYMÄKI, Matti
IPC分类号： A61B5 , G08B21
CPC分类号： G08B29/186 , A61B5/0022 , A61B5/02055 , A61B5/02455 , A61B5/0533 , A61B5/11 , A61B5/681 , A61B5/7264 , G06F19/00 , G08B21/0453 , G08B21/0492 , G16H40/67
摘要： PCT No. PCT/FI93/00067 Sec. 371 Date Aug. 24, 1994 Sec. 102(e) Date Aug. 24, 1994 PCT Filed Feb. 26, 1993 PCT Pub. No. WO93/16636 PCT Pub. Date Sep. 2, 1993.The present invention relates to a wrist-held monitoring device for independently observing the physical condition of a person by means of motoric activity or movement and physiological conditions, e.g., temperature and/or electric conductivity of the skin. The anomalous condition data is transmitted by conventional techniques on a radio frequency message to one or more receivers, which either set off a local alarm or further transfer the data by conventional techniques to a centralized receiving point for alarm generation there.

6. 发明公开

EP4423735A1 COMPUTER-IMPLEMENTED METHOD FOR USER FALL ASSESSMENT IMPLEMENTING A TRAINED MACHINE LEARNING MODEL COMPRISING AN ACTION PLAN 审中-公开
公开(公告)号：EP4423735A1
公开(公告)日：2024-09-04
申请号：EP22813140.5
申请日：2022-10-28
申请人： Autoliv Development AB
发明人： AHMED, Jawwad
IPC分类号： G08B21/04 , G08B31/00
CPC分类号： G06N20/00 , G08B31/00 , G08B29/186 , G08B21/0446 , G08B21/043

7. 发明公开

EP4374355A1 VERFAHREN UND VORRICHTUNG ZUR DETEKTION VON WALDRÄNDEN 审中-实审
公开(公告)号：EP4374355A1
公开(公告)日：2024-05-29
申请号：EP22751351.2
申请日：2022-07-13
申请人： Dryad Networks GmbH
发明人： BRINKSCHULTE, Carsten , HOLLOS, Daniel
IPC分类号： G08B29/18 , G08B17/00
CPC分类号： G08B17/005 , G08B29/186

8. 发明公开

EP3167442A4 A SELF LEARNING SYSTEM FOR IDENTIFYING STATUS AND LOCATION OF PET ANIMALS 审中-公开
公开(公告)号：EP3167442A4
公开(公告)日：2018-03-21
申请号：EP15822423
申请日：2015-07-13
申请人： GEOSATIS SA
发明人： YANG YU
IPC分类号： G08B23/00 , A01K27/00 , A61B5/11
CPC分类号： A01K11/008 , A01K27/009 , A01K29/005 , A61B5/1112 , A61B2503/40 , G08B29/186 , G08B29/188 , H04W4/026 , H04W52/0254 , Y02D70/00 , Y02D70/142 , Y02D70/144 , Y02D70/162 , Y02D70/164 , Y02D70/26
摘要： A pet animal-wearable self learning device for has been disclosed. The device determines the status of the pet animal by analyzing wireless signal information gathered by the device over a predetermined period of time. The signal information is analyzed to identify useful patterns for determining the status of a pet animal. The pet animal status typically is a multi-dimensional, qualitative or quantitative indicator such as GPS Latitude/Longitude of the pet animal, safe or unsafe condition of the pet animal The status of the pet animal is determined by various factors/conditions such as identifying whether the pet animal is in an enclosed space or not, identifying if the pet is in extreme temperature not suitable for the pet animal's health, identifying whether the pet animal is moving or stationary, identifying if the pet-wearable device has been removed.

9. 发明公开

EP3139359A1 SYSTEM AND METHOD PROVIDING EARLY PREDICTION AND FORECASTING OF FALSE ALARMS BY APPLYING STATISTICAL INFERENCE MODELS 有权
标题翻译：系统和方法的早期发现和统计推断模型预测误报警USE
公开(公告)号：EP3139359A1
公开(公告)日：2017-03-08
申请号：EP16185790.9
申请日：2016-08-25
申请人： Honeywell International Inc.
发明人： NALUKURTHY, RajeshBabu , SETHI, Aatish , NARAHARISETTI, Kanaka Nagendra Prasad , SINGAM, Kiran Reddy
IPC分类号： G08B21/16 , G08B31/00 , G08B17/10 , G08B25/00 , G08B25/08 , G08B25/14 , G08B26/00 , G08B29/18 , G08B13/196
CPC分类号： G08B29/186 , G06N7/005 , G08B13/19682 , G08B17/10 , G08B21/16 , G08B25/008 , G08B25/009 , G08B25/08 , G08B25/14 , G08B26/008 , G08B29/185 , G08B31/00
摘要： A diagnostics and prediction system including a cloud system that continuously collects operating parameters from each of a number of environmental sensors and provides access to this data by a plurality of processing applications including (1) a predictive modeling system including (a) a health prediction system, (b) a sensor false alarm prediction system, (c) a zone false alarm prediction system and (d) a reporting system, (2) a system that diagnoses and predicts environmental hazardous areas and clusters areas based upon concentrations of CO in the site or building; and (3) a battery prediction system that predicts a battery life for the sensor.
摘要翻译：甲诊断和预测系统，其包括云系统做连续地从每一个数字环境传感器的收集操作参数和通过的处理应用中，包括（1）一个预测建模系统包括（a）一个健康预测系统中的多个提供对该数据的访问（b）一种传感器假警报预测系统，（c）中的区域误报警预测系统和（d）一个报告系统，（2）的系统做了诊断和预测在基于CO的浓度的环境危险区域和簇区域现场或建筑物; 和（3）的电池预测系统做预测用于传感器的电池寿命。

10. 发明公开

EP2885151A1 METHOD FOR DETERMINING THE OPERATIONAL STATE OF A DRIVER 有权
标题翻译：程序对驾驶员的确定所述操作状态
公开(公告)号：EP2885151A1
公开(公告)日：2015-06-24
申请号：EP12889739.4
申请日：2012-08-14
申请人： Volvo Lastvagnar AB
发明人： KRONBERG, Peter , SANDBLOM, Fredrik
IPC分类号： B60K28/06 , A61B5/18 , G08B21/06
CPC分类号： A61B5/18 , A61B3/113 , A61B5/11 , A61B5/1128 , A61B5/4809 , A61B5/6893 , A61B5/7246 , A61B5/7264 , A61B5/7275 , B60K28/06 , B60W40/08 , B60W2040/0818 , B60W2550/10 , B60W2550/30 , G06F17/18 , G06F19/00 , G08B21/06 , G08B29/186 , G08B29/188
摘要： A method for determining an operational state of a driver of a vehicle uses an awareness detection arrangement. The awareness detection arrangement includes at least a first and a second source for generating data relating to the behavior of the driver. The method includes receiving, from the first and the second source, data relating to at least one of physiological data of the driver, the operation of the vehicle, and a model of the driver operating the vehicle, comparing the data from the first and the second source with a driver state model defining a plurality of predefined driver states for each of the first and the second source, respectively, determining based on the comparison, for each of the first and the second source, a state probability for each of the plurality of predefined driver states, and weighing the determined driver states for the first and the second source with each other for determining an overall operational state probability for the driver.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式