公开(公告)号：US20220277231A1

公开(公告)日：2022-09-01

申请号：US17187432

申请日：2021-02-26

Applicant: Hitachi, Ltd.

Inventor： Jeremy OSTERGAARD ,  Joydeep ACHARYA

IPC: G06N20/20 ,  G06F11/34 ,  G06F8/65

Abstract: Example implementations described herein involve systems and methods to substantially simultaneously orchestrate machine learning models over multiple resource constrained control edge devices, so that the overall system is more agile to changes in events and environmental conditions where the models have been deployed. The example implementations described herein involve multiple processes that when executed, determine a list of edge devices to be updated along with the corresponding models based on correlation.

公开(公告)号：US20130137442A1

公开(公告)日：2013-05-30

申请号：US13718484

申请日：2012-12-18

Applicant: Hitachi, Ltd.

Inventor： Joydeep ACHARYA

IPC: H04W84/04

CPC classification number: H04W84/042 ,  H04J11/0053 ,  H04W72/02

Abstract: In the embodiments of the present invention, proposed is a method in which a CoMP enabled UE chooses the BSs to be in its cooperating set and a BS partitions its bandwidth to serve its own UEs and UEs from other cells that have requested it to be in its cooperating set.

Abstract translation: 在本发明的实施例中，提出了一种方法，其中启用CoMP的UE选择在协作集合中的BS，并且BS分配其带宽以服务于其自己的UE和来自已请求它进入的其他小区的UE 其合作组合。

公开(公告)号：US20240046650A1

公开(公告)日：2024-02-08

申请号：US17883590

申请日：2022-08-08

Applicant: Hitachi, Ltd.

Inventor： Joydeep ACHARYA

IPC: G06V20/52 ,  G06V10/72 ,  H04N5/232 ,  H04N7/18 ,  H04W4/20

CPC classification number: G06V20/52 ,  G06V10/72 ,  H04N5/23206 ,  H04N7/181 ,  H04W4/20 ,  H04W88/16

Abstract: Example implementations described herein involve systems and methods that involve recognizing, from sensor data, an area from the plurality of areas and a candidate task from the one or more candidate tasks associated with the area; estimating a probability of each of the plurality of candidate tasks for the each of the plurality of areas for a specific future period of time, based on referencing historical data of task sequences previously executed; accepting the ones of the plurality of candidate tasks for the each of the plurality of areas having the probability being higher than a threshold; and scheduling one or more sensors to activate and transmit in the specific future period of time in associated areas for the plurality of areas associated with other ones of the plurality of candidate tasks for the each of the plurality of areas not having the probability being higher than the threshold.

公开(公告)号：US20210034031A1

公开(公告)日：2021-02-04

申请号：US16530448

申请日：2019-08-02

Applicant: Hitachi, Ltd.

Inventor： Joydeep ACHARYA ,  Sudhanshu GAUR

IPC: G05B19/05

Abstract: In example implementations described herein, the power of time series machine learning is used to extract the statistics of Programmable Logic Controller (PLC) data and external sensor data. The accuracy of time series machine learning is improved by manufacturing context-dependent segmentation of the time series into states which is factory may be in. The invention can capture subtle trends in these time series data and be able to classify them into several outcomes from ICS security attacks to normal anomalies and machine/sensor failures.

公开(公告)号：US20240028949A1

公开(公告)日：2024-01-25

申请号：US17869528

申请日：2022-07-20

Applicant: Hitachi, Ltd.

Inventor： Andrew James WALKER ,  Joydeep ACHARYA

IPC: G06N20/00

CPC classification number: G06N20/00

Abstract: Example implementations described herein involve systems and methods for providing a reward to a machine learning algorithm, which can include receiving an image, and a task description defined in text; slicing the image into a plurality of sub-images; executing an embedding model to embed the text of the task description and the sub-images to generate a distribution for the sub-images based on relevance to the task description; and generating the reward from the distribution for the sub-images.

公开(公告)号：US20210375492A1

公开(公告)日：2021-12-02

申请号：US16886428

申请日：2020-05-28

Applicant: Hitachi, Ltd.

Inventor： Andrew WALKER ,  Joydeep ACHARYA

IPC: G16Y40/35 ,  G16Y40/10 ,  G16Y40/20 ,  H04L29/08 ,  G06F17/14

Abstract: Example implementations described herein can dynamically adapt to changing nature of sensor data traffic and through artificial intelligence (AI, strike a good tradeoff between reducing volume of sensed data, and retain enough data fidelity so that subsequent analytics applications perform well. The example implementations eliminate heuristic methods of setting sensing parameters (such as DAQ sampling rate, resolution etc.) and replaces them with an automated, AI driven edge solution core that can be readily ported on any Internet of Things (IoT) edge gateway that is connected to the DAQ.

公开(公告)号：US20140146689A1

公开(公告)日：2014-05-29

申请号：US13684327

申请日：2012-11-23

Applicant: HITACHI, LTD.

Inventor： Sudhanshu GAUR ,  Long GAO ,  Joydeep ACHARYA

IPC: H04W72/08

CPC classification number: H04W72/082 ,  H04J11/0053 ,  H04J11/0056 ,  H04L1/0069 ,  H04L1/1867 ,  H04L5/0035 ,  H04L5/0044 ,  H04L5/0073 ,  H04L2001/0093

Abstract: A communications system employing CoMP transmission to suppress interference comprises: a CoMP user equipment; and a plurality of base stations, one of the base stations being an associated base station of the CoMP user equipment to transmit data to the CoMP user equipment, the plurality of base stations including multiple CoMP base stations for the CoMP user equipment. The CoMP base stations for the CoMP user equipment transmit CoMP downlink data, including subframes which comprise physical resource blocks having a plurality of resource elements (REs) and cell-specific reference signal (CRS) resource element (RE) locations. PDSCH bit-level muting or puncturing information is determined, based on radio resource management measurement and the subframes sent from the multiple CoMP base stations, to identify PDSCH REs that suffer strong CRS interference transmission from within the multiple CoMP base stations and are to be subjected to one of bit-level muting or bit-level puncturing.

Abstract translation: 采用CoMP传输抑制干扰的通信系统包括：CoMP用户设备; 以及多个基站，所述基站中的一个是所述CoMP用户设备的相关基站，用于向所述CoMP用户设备发送数据，所述多个基站包括用于所述CoMP用户设备的多个CoMP基站。 用于CoMP用户设备的CoMP基站发送CoMP下行链路数据，包括包括具有多个资源元素（RE）和小区特定参考信号（CRS）资源元素（RE））位置的物理资源块的子帧。 基于无线电资源管理测量和从多个CoMP基站发送的子帧来确定PDSCH比特级静音或删截信息，以识别在多个CoMP基站内遭受强CRS干扰传输并且将被承受的PDSCH RE 到位级静音或比特级穿孔之一。

公开(公告)号：US20130243109A1

公开(公告)日：2013-09-19

申请号：US13875619

申请日：2013-05-02

Applicant: HITACHI, LTD.

Inventor： Sudhanshu GAUR ,  Joydeep ACHARYA

IPC: H04B7/04

CPC classification number: H04B7/0456 ,  H04B7/0426 ,  H04B7/0452 ,  H04B7/0465

Abstract: A method for processing user symbols with Tomlinson Harashima precoder (THP) in a base station, of a wireless system having K user terminals (UEs) which communicate with the base station via an uplink channel and a corresponding downlink (DL) channel, comprises estimating DL channel matrix; determining receiver processing matrix; computing effective matrix DL channel Heff; performing QR decomposition of Heff; computing THP matrices; calculating scalar weights for the UEs; processing user symbols by the THP having the THP matrices to produce an output of filtered vector symbols for the UEs; directing output of the THP to a channel represented by the DL channel matrix through which communications occur in the wireless system with the UEs; providing the receiver processing matrix to the UEs for performing additional receiver processing on the transmitted signals; and providing the scalar weights to the UEs to be used on the transmitted signals at the UEs.

Abstract translation: 一种用于在具有通过上行链路信道和相应的下行链路（DL）信道与基站通信的K个用户终端（UE）的无线系统的基站中用Tomlinson Harashima预编码器（THP）处理用户符号的方法，包括估计 DL信道矩阵; 确定接收机处理矩阵; 计算有效矩阵DL信道Heff; 执行Heff的QR分解; 计算THP矩阵; 计算UE的标量权重; 通过具有THP矩阵的THP处理用户符号以产生用于UE的滤波后的矢量符号的输出; 将所述THP的输出引导到由与所述UE在无线系统中发生通信的DL信道矩阵表示的信道; 向所述UE提供所述接收机处理矩阵，以对所发射的信号执行附加的接收机处理; 以及向在UE处发送的信号上要使用的UE提供标量权重。

公开(公告)号：US20250116996A1

公开(公告)日：2025-04-10

申请号：US18376690

申请日：2023-10-04

Applicant: HITACHI, Ltd.

Inventor： Ravneet KAUR ,  Joydeep ACHARYA

IPC: G05B19/418

Abstract: Presented herein are systems and methods for receiving video data associated with at least one task performed by at least one worker and executing, based on the received video data, a human action recognition program to identify at least one action associated with the at least one task and executing an object detection program to identify at least one object associated with the at least one task, identifying, based on a combination of the identified at least one action and the identified at least one object associated with the at least one task, at least one subtask of the at least one task, and generating at least first and second labels for the identified at least one subtask based on at least first and second labels, respectively, associated from a first set of existing labels for identified actions and from a second set of existing labels for identified objects, respectively.

公开(公告)号：US20200044961A1

公开(公告)日：2020-02-06

申请号：US16054930

申请日：2018-08-03

Applicant: Hitachi, Ltd.

Inventor： Yusuke SHOMURA ,  Joydeep ACHARYA ,  Sudhanshu GAUR

IPC: H04L12/721 ,  H04L12/24 ,  H04L29/06 ,  H04L29/08 ,  H04L12/813

Abstract: This invention aim to improves the flexibility of data flows management from sensor to cloud, datalake or other system, which can manage the overall data flows within the system and control them dynamically. As a result, it can reduce transmission cost and storage cost properly.