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. 发明申请

WO2020193382A1 ENHANCING DEEP SLEEP BASED ON INFORMATION FROM FRONTAL BRAIN ACTIVITY MONITORING SENSORS 审中-公开
公开(公告)号：WO2020193382A1
公开(公告)日：2020-10-01
申请号：PCT/EP2020/057711
申请日：2020-03-20
申请人： KONINKLIJKE PHILIPS N.V.
发明人： GARCIA MOLINA, Gary Nelson , GROSSEKATHOEFER, Ulf , TRAJANOVSKI, Stojan , SALAZAR, Jesse , TSONEVA, Tsvetomira Kirova , PASTOOR, Sander Theodoor , AQUINO, Antonio , HEINRICH, Adrienne , SACHDEV, Birpal Singh
IPC分类号： A61B5/0478 , A61B5/048 , A61B5/0482 , A61B5/00
摘要： Typically, high NREM stage N3 sleep detection accuracy is achieved using a frontal electrode referenced to an electrode at a distant location on the head (e.g., the mastoid, or the earlobe). For comfort and design considerations it is more convenient to have active and reference electrodes closely positioned on the frontal region of the head. This configuration, however, significantly attenuates the signal, which degrades sleep stage detection (e.g., N3) performance. The present disclosure describes a deep neural network (DNN) based solution developed to detect sleep using frontal electrodes only. N3 detection is enhanced through post-processing of the soft DNN outputs. Detection of slow-waves and sleep micro-arousals is accomplished using frequency domain thresholds. Volume modulation uses a high-frequency /low-frequency spectral ratio extracted from the frontal signal.

2. 发明申请

WO2021160539A1 EXPLAINING A MODEL OUTPUT OF A TRAINED MODEL 审中-公开
公开(公告)号：WO2021160539A1
公开(公告)日：2021-08-19
申请号：PCT/EP2021/052895
申请日：2021-02-07
申请人： KONINKLIJKE PHILIPS N.V.
发明人： BAKKER, Bart Jacob , MAVROEIDIS, Dimitrios , TRAJANOVSKI, Stojan
IPC分类号： G06K9/46 , G06K9/62 , G06K9/32
摘要： The invention relates a computer-implemented method (500) of generating explainability information for explaining a model output of a trained model. The method uses one or more aspect recognition models configured to indicate a presence of respective characteristics in the input instance. A saliency method is applied to obtain a masked source representation of the input instance at a source layer of the trained model (e.g., the input layer or an internal layer), comprising those elements at the source layer relevant to the model output. The masked source representation is mapped to a target layer (e.g., input or internal layer) of an aspect recognition model, and the aspect recognition model is then applied to obtain a model output indicating a presence of the given characteristic relevant to the model output of the trained model. As explainability information, the characteristics indicated by the aspect recognition models are output.

3. 发明申请

WO2019106136A1 TRAINING A NEURAL NETWORK MODEL 审中-公开
公开(公告)号：WO2019106136A1
公开(公告)日：2019-06-06
申请号：PCT/EP2018/083102
申请日：2018-11-30
申请人： KONINKLIJKE PHILIPS N.V.
发明人： MAVRIEUDUS, Dimitros , GEBRE, Binyam, Gebrekidan , TRAJANOVSKI, Stojan
IPC分类号： G06N3/08
CPC分类号： G06N3/082
摘要： A concept for training a neural network model. The concept comprises receiving training data and test data, each comprising a set of annotated images. A neural network model is trained using the training data with an initial regularization parameter. Loss functions of the neural network for both the training data and the test data are used to modify the regularization parameter, and the neural network model is retrained using the modified regularization parameter. This process is iteratively repeated until the loss functions both converge. A system, method and a computer program product embodying this concept are disclosed.

4. 发明申请

WO2020244941A1 DEEP NEURAL NETWORK VISUALISATION 审中-公开
公开(公告)号：WO2020244941A1
公开(公告)日：2020-12-10
申请号：PCT/EP2020/064355
申请日：2020-05-25
申请人： KONINKLIJKE PHILIPS N.V.
发明人： BAKKER, Bart, Jacob , MAVROEIDIS, Dimitrios , TRAJANOVSKI, Stojan
IPC分类号： G06K9/62
摘要： Aspects and embodiments relate to a method of providing a representation of a feature identified by a deep neural network as being relevant to an outcome, a computer program product and apparatus configured to perform that method. The method comprises: providing the deep neural network with a training library comprising: a plurality of samples associated with the outcome; using the deep neural network to recognise a feature in the plurality of samples associated with the outcome; creating a feature recognition library from an input library by identifying one or more elements in each of a plurality of samples in the input library which trigger recognition of the feature by the deep neural network; using the feature recognition library to synthesise a plurality of one or more elements of a sample which have characteristics which trigger recognition of the feature by the deep neural network; and using the synthesised plurality of one or more elements to provide a representation of the feature identified by the deep neural network in the plurality of samples associated with the outcome. Accordingly, rather than visualising a single instance of one or more elements in a sample which trigger a feature associated with an outcome, it is possible to visualise a range of samples including elements which would trigger a feature associated with an outcome, thus enabling a more comprehensive view of operation of a deep neural network in relation to a particular feature.

5. 发明申请

WO2020043545A1 ADAPTABLE NEURAL NETWORK 审中-公开
公开(公告)号：WO2020043545A1
公开(公告)日：2020-03-05
申请号：PCT/EP2019/072211
申请日：2019-08-20
申请人： KONINKLIJKE PHILIPS N.V.
发明人： GEBRE, Binyam, Gebrekidan , TRAJANOVSKI, Stojan
IPC分类号： G06N3/04 , G06N3/08
摘要： An adaptable neural network system (1) formed of two neural networks (4, 5). One of the neural networks (5) adjusts a structure of the other neural network (4) based on information about a specific task each time that new second input data (12) indicative of a desired task is received by the one neural network (5), so that the other neural network (4) is adapted to perform that specific task. Thus, an adaptable neural network system (1) capable of performing different tasks on input data (11) can be realized.

6. 发明申请

WO2020201516A1 IDENTIFYING BOUNDARIES OF LESIONS WITHIN IMAGE DATA 审中-公开
公开(公告)号：WO2020201516A1
公开(公告)日：2020-10-08
申请号：PCT/EP2020/059583
申请日：2020-04-03
申请人： KONINKLIJKE PHILIPS N.V.
发明人： MAVROEIDIS, Dimitrios , TRAJANOVSKI, Stojan , BAKKER, Bart, Jacob
IPC分类号： G06T7/187
摘要： The present invention provides a method, computer program and processing system for identifies boundaries of lesions within image data. The image data is processed using a machine learning algorithm to generate probability data and uncertainty data. The probability data provides, for each image data point of the image data, a probability data points indicating a probability that said image data point is part of a lesion. The uncertainty data provides, for each probability data point, an uncertainty data point indicating an uncertainty of the said probability data point. The uncertainty data is processed to identify or correct boundaries of the lesions.

7. 发明申请

WO2020043530A1 GENERATING METADATA FOR TRAINED MODEL 审中-公开
公开(公告)号：WO2020043530A1
公开(公告)日：2020-03-05
申请号：PCT/EP2019/072157
申请日：2019-08-19
申请人： KONINKLIJKE PHILIPS N.V.
发明人： BAKKER, Bart, Jacob , MAVROEIDIS, Dimitros , TRAJANOVSKI, Stojan
IPC分类号： G16H30/40
摘要： The invention relates to a trained model, such as a trained neural network, which is trained on training data. System and computer-implemented methods are provided for generating metadata which encodes a numerical characteristic of the training data of the trained model, and for using the metadata to determine conformance of input data of the trained model to the numerical characteristics of the training data. If the input data does not conform to the numerical characteristics, the use of the trained model on the input data may be considered out-of-specification ('out-of-spec'). Accordingly, a system applying the trained model to the input data may, for example, warn a user of the non-conformance, or may decline to apply the trained model to the input data, etc.

9. 发明公开

EP3980939A1 DEEP NEURAL NETWORK VISUALISATION 审中-实审
公开(公告)号：EP3980939A1
公开(公告)日：2022-04-13
申请号：EP20728463.9
申请日：2020-05-25
申请人： Koninklijke Philips N.V.
发明人： BAKKER, Bart, Jacob , MAVROEIDIS, Dimitrios , TRAJANOVSKI, Stojan
IPC分类号： G06K9/62

10. 发明公开

EP3862922A1 EXPLAINING THE OUTPUT OF A TRAINED MODEL 审中-公开
公开(公告)号：EP3862922A1
公开(公告)日：2021-08-11
申请号：EP20156426.7
申请日：2020-02-10
申请人： Koninklijke Philips N.V.
发明人： BAKKER, Bart , MAVROEIDIS, Dimitrios , TRAJANOVSKI, Stojan
IPC分类号： G06K9/46 , G06K9/62 , G06K9/32
摘要： The invention relates a computer-implemented method (500) of generating explainability information for explaining a model output of a trained model. The method uses one or more aspect recognition models configured to indicate a presence of respective characteristics in the input instance. A saliency method is applied to obtain a masked source representation of the input instance at a source layer of the trained model (e.g., the input layer or an internal layer), comprising those elements at the source layer relevant to the model output. The masked source representation is mapped to a target layer (e.g., input or internal layer) of an aspect recognition model, and the aspect recognition model is then applied to obtain a model output indicating a presence of the given characteristic relevant to the model output of the trained model. As explainability information, the characteristics indicated by the aspect recognition models are output.

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