专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

51. 发明授权

US10902743B2 Gesture recognition and communication 有权
公开(公告)号：US10902743B2
公开(公告)日：2021-01-26
申请号：US15952784
申请日：2018-04-13
申请人： Prajwal Paudyal , Ayan Banerjee , Sandeep Gupta
发明人： Prajwal Paudyal , Ayan Banerjee , Sandeep Gupta
IPC分类号： G09B21/00 , G06F3/01 , G06K9/00 , G06K9/62 , G10L15/18 , G10L15/25 , G10L15/22 , G06F3/0346 , G06F40/10 , G06F40/56 , G06F40/58 , G10L15/26 , H04B1/3827
摘要： Systems and methods are described for facilitating non-verbal communication. An electronic processor receives data from the hand-gesture sensor indicative of one or more gestures performed by a user, determines at least one word or phrase corresponding to the data from the hand-gestures sensor, and outputs a text representation of the at least one word or phrase on the display screen. Some systems output the text representation as a natural language sentence based on the data from the hand-gesture sensor and linguistic prosody information determined based, at least in part, on image data of the user captured while performing the one or more gesture. Some systems also includes at least one brain sensor and generate an alternative natural language text sentence in response to detecting a signal from the brain sensor indicative of a contradiction response after displaying the natural language text sentence on the display screen.

52. 发明授权

US10796246B2 Brain-mobile interface optimization using internet-of-things 有权
公开(公告)号：US10796246B2
公开(公告)日：2020-10-06
申请号：US15857794
申请日：2017-12-29
申请人： Sandeep Gupta , Ayan Banerjee , Mohammad Javad Sohankar Esfahani , Seyed Koosha Sadeghi Oskooyee
发明人： Sandeep Gupta , Ayan Banerjee , Mohammad Javad Sohankar Esfahani , Seyed Koosha Sadeghi Oskooyee
IPC分类号： G06F16/00 , G06N20/00 , G05D1/00 , H04L29/08 , H04W40/24
摘要： A Brain-Mobile Interface (BMoI) system is provided. A control circuit is configured to execute a predictive model to generate a defined number of predicted signal features in future time based on a number of signal features extracted from a first type sensory data (e.g., electroencephalogram (EEG) data). A predicted future mental state(s) can thus be generated based on the number of predicted signal features and used to trigger a corresponding action(s) in a BMoI application(s). In a non-limiting example, a second type sensory data (e.g., electrocardiogram (ECG) data) can be used to improve accuracy of the predictive model. By using the predicted signal features to generate the predicted future mental state(s) to control the BMoI application(s), it is possible to duty-cycle the BMoI system to help reduce power consumption and processing latency, thus allowing the BMoI application(s) to operate in real-time with improved accuracy and power consumption.

53. 发明授权

US10575788B2 Compressive sensing of quasi-periodic signals using generative models 有权
公开(公告)号：US10575788B2
公开(公告)日：2020-03-03
申请号：US15787534
申请日：2017-10-18
申请人： Sandeep Gupta , Ayan Banerjee
发明人： Sandeep Gupta , Ayan Banerjee
IPC分类号： A61B5/00 , A61B5/0404 , A61B5/0456 , A61B5/0432 , A61B5/0452 , A61B5/04 , G16H50/20 , G16H40/63
摘要： Methods and systems are described for sensing and recovery of a biological signal using generative-model-based compressive sensing. A transformation is applied to sparsify the quasi-periodic signal removing morphology parameters and leaving temporal parameters. The sparsified signal is sampled and the sampled signal data is transmitted to a base station. A homotopy recovery algorithm is applied to the received sampled signal data by the base station to recover the temporal parameters of the biological signal. Generative modelling is applied using previously captured morphology parameters to generate a reconstructed signal. Finally, the reconstructed signal is adjusted and scaled based on the recovered temporal parameters to provide a reconstructed signal that is diagnostically equivalent to the original biological signal.

54. 发明申请

US20180301061A1 GESTURE RECOGNITION AND COMMUNICATION 审中-公开
公开(公告)号：US20180301061A1
公开(公告)日：2018-10-18
申请号：US15952784
申请日：2018-04-13
申请人： Prajwal Paudyal , Ayan Banerjee , Sandeep Gupta
发明人： Prajwal Paudyal , Ayan Banerjee , Sandeep Gupta
IPC分类号： G09B21/00 , G06F3/01 , G06K9/00 , G06K9/62 , G10L15/22 , G06F17/21 , G10L15/18 , G10L15/26 , G10L15/25
摘要： Systems and methods are described for facilitating non-verbal communication. An electronic processor receives data from the hand-gesture sensor indicative of one or more gestures performed by a user, determines at least one word or phrase corresponding to the data from the hand-gestures sensor, and outputs a text representation of the at least one word or phrase on the display screen. Some systems output the text representation as a natural language sentence based on the data from the hand-gesture sensor and linguistic prosody information determined based, at least in part, on image data of the user captured while performing the one or more gesture. Some systems also includes at least one brain sensor and generate an alternative natural language text sentence in response to detecting a signal from the brain sensor indicative of a contradiction response after displaying the natural language text sentence on the display screen.

55. 发明授权

US10074028B2 Real-time diet assessment and food identification using thermal imaging 有权
公开(公告)号：US10074028B2
公开(公告)日：2018-09-11
申请号：US15298581
申请日：2016-10-20
申请人： Sandeep Gupta , Ayan Banerjee
发明人： Sandeep Gupta , Ayan Banerjee
IPC分类号： G06K9/00 , G06K9/46 , G06T7/90 , G09B19/00
CPC分类号： G06K9/4652 , G01N25/72 , G01N33/02 , G06K9/00 , G06K9/6289 , G06K9/629 , G06K2209/17 , G06T7/11 , G06T7/12 , G06T7/136 , G06T7/162 , G06T7/174 , G06T7/90 , G06T2207/10024 , G06T2207/10048 , G06T2207/20061 , G06T2207/20152
摘要： Systems and methods are described for automatically identifying a food item. A color image and a thermal image are received by an electronic processor with a first food item in the field of view of both the color image and the thermal image. The electronic processor identifies a region of pixels in the color image that corresponds to the first food item based at least in part on a temperature intensity of the pixels in the identified region of pixels relative to other pixels in the thermal image. At least one feature is extracted from the identified region of pixels in the color image corresponding to the first food item and the electronic processor automatically identifies a type of food corresponding to the first food item based at least in part on the at least extracted feature.

56. 发明申请

US20180189678A1 BRAIN-MOBILE INTERFACE OPTIMIZATION USING INTERNET-OF-THINGS 审中-公开
公开(公告)号：US20180189678A1
公开(公告)日：2018-07-05
申请号：US15857794
申请日：2017-12-29
申请人： Sandeep Gupta , Ayan Banerjee , Mohammad Javad Sohankar Esfahani , Seyed Koosha Sadeghi Oskooyee
发明人： Sandeep Gupta , Ayan Banerjee , Mohammad Javad Sohankar Esfahani , Seyed Koosha Sadeghi Oskooyee
IPC分类号： G06N99/00 , H04L29/08 , G05D1/00
CPC分类号： G06N20/00 , G05D1/0088 , H04L67/12 , H04W40/24 , Y02D30/40
摘要： A Brain-Mobile Interface (BMoI) system is provided. A control circuit is configured to execute a predictive model to generate a defined number of predicted signal features in future time based on a number of signal features extracted from a first type sensory data (e.g., electroencephalogram (EEG) data). A predicted future mental state(s) can thus be generated based on the number of predicted signal features and used to trigger a corresponding action(s) in a BMoI application(s). In a non-limiting example, a second type sensory data (e.g., electrocardiogram (ECG) data) can be used to improve accuracy of the predictive model. By using the predicted signal features to generate the predicted future mental state(s) to control the BMoI application(s), it is possible to duty-cycle the BMoI system to help reduce power consumption and processing latency, thus allowing the BMoI application(s) to operate in real-time with improved accuracy and power consumption.

57. 发明申请

US20180103911A1 COMPRESSIVE SENSING OF QUASI-PERIODIC SIGNALS USING GENERATIVE MODELS 审中-公开
公开(公告)号：US20180103911A1
公开(公告)日：2018-04-19
申请号：US15787534
申请日：2017-10-18
申请人： Sandeep Gupta , Ayan Banerjee
发明人： Sandeep Gupta , Ayan Banerjee
IPC分类号： A61B5/00 , A61B5/0404 , A61B5/0456 , A61B5/0432
CPC分类号： A61B5/7232 , A61B5/0006 , A61B5/04011 , A61B5/04014 , A61B5/0404 , A61B5/0432 , A61B5/04525 , A61B5/0456 , A61B5/681 , A61B5/6823 , A61B5/7264 , A61B5/7275 , A61B5/7278 , A61B2560/0209 , A61B2562/04 , G16H40/63 , G16H50/20
摘要： Methods and systems are described for sensing and recovery of a biological signal using generative-model-based compressive sensing. A transformation is applied to sparsify the quasi-periodic signal removing morphology parameters and leaving temporal parameters. The sparsified signal is sampled and the sampled signal data is transmitted to a base station. A homotopy recovery algorithm is applied to the received sampled signal data by the base station to recover the temporal parameters of the biological signal. Generative modelling is applied using previously captured morphology parameters to generate a reconstructed signal. Finally, the reconstructed signal is adjusted and scaled based on the recovered temporal parameters to provide a reconstructed signal that is diagnostically equivalent to the original biological signal.

58. 发明授权

US09424084B2 Systems, methods, and media for online server workload management 有权
标题翻译：用于在线服务器工作负载管理的系统，方法和介质
公开(公告)号：US09424084B2
公开(公告)日：2016-08-23
申请号：US14717908
申请日：2015-05-20
申请人： Sandeep Gupta , Zahra Abbasi
发明人： Sandeep Gupta , Zahra Abbasi
IPC分类号： G06F9/46 , G06F9/48 , G06F9/50
CPC分类号： G06F9/4881 , G06F1/3228 , G06F9/48 , G06F9/4893 , G06F9/50 , G06F9/5027 , G06F9/5094 , Y02D10/22
摘要： Methods, using a hardware processor, for online server workload management are provided, comprising: receiving information regarding client device requests; determining, using a hardware processor, a workload distribution for the requests based on electricity cost and carbon footprint of one or more data centers using Lyapunov optimization; sending the workload distribution to the one or more data centers; and causing servers in the one or more data center to be active or inactive based on the workload distribution. Systems are provided, comprising at least one hardware processor configured to: receive information regarding client device requests; determine a workload distribution for the requests based on electricity cost and carbon footprint of one or more data centers using Lyapunov optimization; send the workload distribution to the one or more data centers; and cause servers in the one or more data center to be active or inactive based on the workload distribution.
摘要翻译：提供了使用硬件处理器的用于在线服务器工作负载管理的方法，包括：接收关于客户端设备请求的信息; 基于使用Lyapunov优化的一个或多个数据中心的电费和碳足迹来确定使用硬件处理器的请求的工作负载分布; 将工作负载分配发送到一个或多个数据中心; 并且使得一个或多个数据中心中的服务器基于工作负载分布而被激活或不活动。提供了系统，包括至少一个硬件处理器，其被配置为：接收关于客户端设备请求的信息; 根据使用Lyapunov优化的一个或多个数据中心的电费和碳足迹确定请求的工作量分布; 将工作负载分配发送到一个或多个数据中心; 并使一个或多个数据中心中的服务器基于工作负载分布而处于活动状态或非活动状态。

59. 发明授权

US09317285B2 Instruction set architecture mode dependent sub-size access of register with associated status indication 有权
标题翻译：指令集体系结构模式相关的子大小访问寄存器与相关状态指示
公开(公告)号：US09317285B2
公开(公告)日：2016-04-19
申请号：US13460178
申请日：2012-04-30
申请人： Sandeep Gupta , Conrado Blasco-Allue , John H. Mylius , Gerard R. Williams, III , James B. Keller
发明人： Sandeep Gupta , Conrado Blasco-Allue , John H. Mylius , Gerard R. Williams, III , James B. Keller
IPC分类号： G06F9/34 , G06F9/30 , G06F9/38 , G06F1/32
CPC分类号： G06F9/30141 , G06F1/3234 , G06F9/30112 , G06F9/384
摘要： A system and method for efficiently reducing the power consumption of register file accesses. A processor is operable to execute instructions with two or more data types, each with an associated size and alignment. Data operands for a first data type use operand sizes equal to an entire width of a physical register within a physical register file. Data operands for a second data type use operand sizes less than an entire width of a physical register. Accesses of the physical register file for operands associated with a non-full-width data type do not access a full width of the physical registers. A given numerical value may be bypassed for the portion of the physical register that is not accessed.
摘要翻译：一种有效降低寄存器文件访问功耗的系统和方法。处理器可操作以执行具有两个或多个数据类型的指令，每个数据类型具有相关联的大小和对齐。第一种数据类型的数据操作数使用等于物理寄存器文件中物理寄存器的整个宽度的操作数大小。第二种数据类型的数据操作数使用小于物理寄存器整个宽度的操作数大小。访问与非全宽数据类型相关的操作数的物理寄存器文件不能访问物理寄存器的全部宽度。对于未访问的物理寄存器的部分，可以忽略给定的数值。

60. 发明申请

US20120004310A1 NON-PEPTIDE BDNF NEUROTROPHIN MIMETICS 审中-公开
标题翻译：非肽BDNF神经营养因子
公开(公告)号：US20120004310A1
公开(公告)日：2012-01-05
申请号：US13117537
申请日：2011-05-27
申请人： Frank M. LONGO , Stephen M. Massa , Sandeep Gupta
发明人： Frank M. LONGO , Stephen M. Massa , Sandeep Gupta
IPC分类号： A61K31/166 , C07C33/26 , C07C33/30 , C07C43/23 , C07C237/34 , C07C233/78 , C07C215/68 , C07D211/42 , C07D295/135 , C07D215/20 , A61K31/047 , A61K31/09 , A61P25/28 , A61P25/00 , A61P25/08 , A61P25/16 , A61P9/10 , A61P25/24 , A61P3/00 , A61P3/04 , A61P29/00 , A61P35/00 , C12N5/071 , C12N5/0793 , C07C327/48
CPC分类号： C07C33/30 , A61K31/136 , C07C33/26 , C07C33/46 , C07C43/2055 , C07C43/23 , C07C211/53 , C07C215/16 , C07C215/68 , C07C215/70 , C07C215/74 , C07C233/78 , C07C237/34 , C07C237/42 , C07C327/48 , C07C2601/14 , C07D211/42 , C07D215/14 , C07D215/20 , C07D295/135 , C07D401/10
摘要： Methods and compounds for treating neurological and other disorders are provided. Included is the administering to a subject in need thereof an effective amount of a compound having binding and/or modulation specificity for a TrkB receptor molecule.
摘要翻译：提供了治疗神经系统疾病和其他疾病的方法和化合物。包括向有需要的受试者施用有效量的对TrkB受体分子具有结合和/或调节特异性的化合物。

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