公开(公告)号：US20120130645A1

公开(公告)日：2012-05-24

申请号：US13110066

申请日：2011-05-18

申请人： Harinath Garudadri ,  Pawan K. Baheti ,  Somdeb Majumdar

发明人： Harinath Garudadri ,  Pawan K. Baheti ,  Somdeb Majumdar

IPC分类号： G01N27/02

CPC分类号： A61B5/0531 ,  A61B5/0022 ,  A61B5/0024 ,  A61B5/02416 ,  A61B5/0402 ,  A61B5/0536 ,  A61B5/0816 ,  A61B5/14551 ,  A61B5/7232 ,  G16H40/67 ,  H03M7/30

摘要： Certain aspects of the present disclosure relate to techniques for measuring body impedance based on baseband signal detection in analog domain. Proposed methods and apparatus are able to measure an impedance of human body based on sub-Nyquist sampling of signals. The proposed techniques can be particularly beneficial for reducing overall sensor power when an actuation signal generates electrical signals corresponding to vital signs in humans.

摘要翻译： 本公开的某些方面涉及基于模拟域中的基带信号检测来测量身体阻抗的技术。 提出的方法和装置能够基于子奈奎斯特信号采样来测量人体的阻抗。 当致动信号产生对应于人类生命体征的电信号时，所提出的技术可以特别有利于降低总传感器功率。

公开(公告)号：US20120011119A1

公开(公告)日：2012-01-12

申请号：US12832796

申请日：2010-07-08

申请人： Pawan K. Baheti ,  Ashwin Swaminathan ,  Serafin Diaz Spindola ,  Xia Ning

发明人： Pawan K. Baheti ,  Ashwin Swaminathan ,  Serafin Diaz Spindola ,  Xia Ning

IPC分类号： G06F17/30

CPC分类号： G06K9/6228 ,  G06F16/583 ,  G06K9/4676 ,  G06K9/6226

摘要： A database for object recognition is generated by performing at least one of intra-object pruning and inter-object pruning, as well as keypoint clustering and selection. Intra-object pruning removes similar and redundant keypoints within an object and different views of the same object, and may be used to generate and associate a significance value, such as a weight, with respect to remaining keypoint descriptors. Inter-object pruning retains the most informative set of descriptors across different objects, by characterizing the discriminability of the keypoint descriptors for all of the objects and removing keypoint descriptors with a discriminability that is less than a threshold. Additionally, a mobile platform may download a geographically relevant portion of the database and perform object recognition by extracting features from the query image and using determined confidence levels for each query feature during outlier removal.

摘要翻译： 通过执行对象内修剪和对象间修剪以及关键点聚类和选择中的至少一个来生成用于对象识别的数据库。 对象内修剪删除对象内的相似和冗余的关键点以及相同对象的不同视图，并且可以用于生成关联剩余关键点描述符的重要值（例如权重）并将其相关联。 对象间修剪通过表征所有对象的关键点描述符的可区分性并且以小于阈值的区分性去除关键点描述符来保留跨越不同对象的最有用的描述符集合。 此外，移动平台可以下载数据库的地理上相关的部分并且通过从查询图像中提取特征并且在异常值去除期间使用确定的每个查询特征的置信水平来执行对象识别。

公开(公告)号：US20120005248A1

公开(公告)日：2012-01-05

申请号：US12972005

申请日：2010-12-17

申请人： Harinath Garudadri ,  Pawan K. Baheti ,  Somdeb Majumdar

发明人： Harinath Garudadri ,  Pawan K. Baheti ,  Somdeb Majumdar

IPC分类号： G06F7/02

CPC分类号： G06F7/02 ,  G06F2207/02 ,  H03M7/30 ,  H03M7/3059 ,  H03M7/3062

摘要： Certain aspects of the present disclosure relate to a method for quantizing signals and reconstructing signals, and/or encoding or decoding data for storage or transmission. Points of a signal may be determined as local extrema or points where an absolute rise of the signal is greater than a threshold. The tread and value of the points may be quantized, and certain of the quantizations may be discarded before the quantizations are transmitted. After being received, the signal may be reconstructed from the quantizations using an iterative process.

摘要翻译： 本公开的某些方面涉及用于量化信号和重构信号的方法，和/或用于存储或传输的数据的编码或解码的方法。 可以将信号的点确定为局部极值或信号的绝对上升大于阈值的点。 可以对点的胎面和值进行量化，并且在量化被发送之前某些量化可能被丢弃。 在接收之后，可以使用迭代过程从量化重构信号。

公开(公告)号：US20100081946A1

公开(公告)日：2010-04-01

申请号：US12547982

申请日：2009-08-26

申请人： Harinath Garudadri ,  Federico S. Cattivelli ,  Pawan K. Baheti

发明人： Harinath Garudadri ,  Federico S. Cattivelli ,  Pawan K. Baheti

IPC分类号： A61B5/021

CPC分类号： A61B5/0002 ,  A61B5/0024 ,  A61B5/0028 ,  A61B5/021 ,  A61B5/02125 ,  A61B5/02416 ,  A61B5/0245 ,  A61B5/0285 ,  A61B5/0456 ,  A61B5/681 ,  A61B5/7221

摘要： Certain aspects of the present disclosure relate to a method for estimating a blood pressure using both a pulse arrival time (PAT) and an instantaneous heart rate (HR). The PAT can be measured as the delay between QRS peaks in an electrocardiogram (ECG) signal and corresponding points in a photoplethysmogram (PPG) waveform. Parameters of the estimation model can be determined through an initial training. Then, the model parameters can be recalibrated in constant intervals using the recursive least square (RLS) approach combined with a smooth bias fixing. The proposed estimation algorithm is applied on a multi-parameter intelligent monitoring for intensive care (MIMIC) database, and the results are compared with estimation methods that use PAT only or HR only. The proposed estimation algorithm meets, on average, the Association for the Advancement of Medical Instrumentation (AAMI) requirements and outperforms other methods from the prior art. It is also shown in the present disclosure that the proposed estimation algorithm is robust to unknown skew between the ECG and PPG signals.

摘要翻译： 本公开的某些方面涉及使用脉冲到达时间（PAT）和瞬时心率（HR）两者来估计血压的方法。 可以测量PAT作为心电图（ECG）信号中的QRS峰值与光谱体积描记图（PPG）波形中对应点之间的延迟。 估计模型的参数可以通过初始训练来确定。 然后，模型参数可以使用递归最小二乘法（RLS）方法与平滑偏置固定相结合，以恒定间隔进行重新校准。 提出的估计算法应用于重度护理（MIMIC）数据库的多参数智能监测，并将结果与​​仅使用PAT或HR的估计方法进行比较。 所提出的估计算法平均符合医疗器械进步协会（AAMI）要求，并优于现有技术的其他方法。 在本公开中还示出了所提出的估计算法对ECG和PPG信号之间的未知偏差是鲁棒的。