Nippon Telegraph and Telephone Corporation

Nec Corporation

Mitsubishi Jidosha Kogyo Kabushiki Kaisha

Ntt Corporation

Toho Tenax Co., Ltd.

Toho Tenax Europe Gmbh

Ntt Docomo, Inc.

Shuhei Yoshida

Koyo Nitta

Yuta Ukon

Shoko Oteru

Namiko Ikeda

Makoto Terao

Hiroshi Fukuda

Naoki Kobayashi

Daisuke Kobayashi

Hiroyuki Uzawa

Wataru Hattori

Ken Nakamura

Masahiro Tanomura

Saki Hatta

Kaoru Shizuno

Tomoaki Kawamura

Koji Yamazaki

Makoto Kamachi

Yuichi Kamei

Masayoshi Tsuji

Naoki Hashida

Yoshinori Hama

Yosuke Nakamura

Yuya Omori

Hirofumi Yagura

Ronny Wockatz

Hidekazu Yoshikawa

Kantaro Suzuki

Hiromitsu Tahara

Hirotaka Sugimoto

Dirk Ortmanns

Yasuo Kamimura

Yusuke Sekihara

A recognition loss calculation unit of a learning device calculates a recognition loss using: a recognition result with respect to recognition object data in a learning data set that is a set of a pair of the recognition object data and a weak label; a mixing matrix calculated based on the learning data set; and the weak label attached to the recognition object data. The recognition loss calculation unit includes: a difference calculation unit that calculates a difference between a mixing matrix and the recognition result; and a sum of squares calculation unit that calculates the recognition loss by calculating a sum of a square of the difference.

Learning device, learning method, and storage medium for learning device

An image processing device includes a division circuit that divides an input image and outputs a plurality of divided images, a first processor that performs computation of an object detection model and acquires attribute information including an attribute value of an object included in each of the divided images and a first quadrangular frame surrounding the object as first metadata, a scaling circuit that output an overall image obtained by shrinking the input image, a second processor that performs computation of the object detection model and acquires attribute information including an attribute value of an object included in the overall image and a second quadrangular frame as second metadata, and a third processor that generates third metadata of the input image by combining pieces of the attribute information of the second metadata and pieces of attribute information that are not held in common by the first and second metadata.

Device and method for dividing, scaling, and combining similar attributes for object detection

A packet capture device a packet analysis unit that analyzes an input packet; a flow identification unit that identifies a flow as a capture target; an output adjustment unit that adjusts a packet amount of the flow as the capture target to be output to a storage unit; a buffer unit that temporarily accumulates a packet of the flow as the capture target; and the storage unit that stores the packet of the flow as the capture target, in which the output adjustment unit is configured to decide whether to output the packet of the flow as the capture target to the storage unit for each predetermined measurement interval on the basis of a measurement result of the packet amount of the capture target in a predetermined measurement interval, and discard the packet not to be output to the storage unit.

Packet capture device and packet capture method

A traffic monitoring device includes an identification unit that identifies a flow of a packet received from a monitoring target network into a flow of a first flow group and a second flow group other than the first flow group on the basis of a rule table in which a predetermined rule is registered, a traffic aggregation unit that aggregates a traffic amount of the first flow group for each flow, an occurrence probability calculation unit that calculates an occurrence probability of each flow on the basis of a result of sampling at least some of the flow of the packet received, and a traffic estimation unit that estimates a traffic amount of each flow of the second flow group by multiplying the occurrence probability of each flow by the total value of the traffic amount of the second flow group.

Traffic monitoring device and traffic monitoring method

A packet capture system for capturing packets flowing in a capture target network, and a plurality of stages of packet distribution devices for capturing packet of a specific flow are cascade-connected, packet distribution devices identify a capture target flow by analyzing inputted packets, packet distribution devices other than a last-stage packet distribution device are configured to distribute packets to capture packets of a flow to be captured and output packets of a flow not to be captured to a next-stage packet distribution device, and the last-stage packet distribution device is configured to filter the packets of the flow to be captured and to discard the packets of the flow not to be captured.

Packet capture system, method and program

A burst traffic detection device includes a packet receiver configured to receive packets from a network, a flow specification device configured to specify, in accordance with header information of the packets, flow rules, a flow information storage device configured to store flow information of the specified flow rules, a statistical information storage device configured to store statistical information including the total number of packets for each flow rule and/or the total number of bytes for each flow rule, a burst detection device configured to detect the occurrence of burst traffic in accordance with the statistical information, and a detection count storage device configured to store the number of times of the occurrence of burst traffic.

Burst traffic detection device and method

An embodiment is a packet capture device including a first local timer synchronized with an external global timer, a second local timer, a time stamp assign unit for assigning a time stamp to a inputted packet signal based on the second local timer, a filter unit for selecting the packet signal to which the time stamp is assigned, a capture file generation unit for receiving the selected packet signal, and a storage unit for storing a capture file generated in the capture file generation unit, wherein the capture file generation unit calculate a difference between a timer value of the first local timer and a timer value of the second local timer to correct the time stamp value on the basis of the difference.

Packet capture device, time stamp amendment method, packet capture method and packet capture program

The dataset supply unit supplies a learning dataset. The recognition unit outputs the recognition result for the recognition object data in the supplied learning dataset. Further, the intersection matrix computation unit computes the intersection matrix based on the learning dataset. The recognition loss computation unit computes the recognition loss using the recognition result, the intersection matrix, and the correct answer data given to the recognition object data. Then, the updating unit updates the parameters of the recognition unit based on the recognition loss.

Learning device, learning method and recording medium

An embodiment is a data sequence correction method. The data sequence correction method including temporarily saving data with sequence information imparted thereto in a ring buffer, the ring buffer having a predetermined number of storage regions corresponding to the sequence information, and being provided with a monitoring section made up of one, or two or more consecutive sequence numbers, and an acceptance section in which a start or a second sequence number of the monitoring section is a start sequence number, and the sequence number ahead by a count of storage regions of the ring buffer including the start of the monitoring section is an end sequence number.

Data sequence amendment method, packet monitoring apparatus, data sequence amendment device, and data sequence amendment program

A packet processing apparatus includes a packet processor that performs processing on a packet received from a communication line and outputs data that is a result of the processing, a data combiner that concatenates a plurality of pieces of data output from the packet processor to generate a data block, and a combination data transferor that DMA-transfers the data block generated by the data combiner to a data memory. The combination data transferor writes information on an address in the data memory of a beginning of an individual piece of data in the data block to a descriptor that is a data area on a predetermined memory.

Packet processing device and packet processing method

The packet processing apparatus includes a packet memory, a transmission processing unit that writes a plurality of packets to be transmitted to the packet memory to generate a combination packet into which the plurality of packets have been concatenated, a line handling unit that sends packets to a communication line, and a combination packet transfer unit that DMA-transfers the combination packet from the packet memory to the line handling unit. The transmission processing unit writes information on an address in the packet memory of beginning data of an individual packet in the combination packet to a descriptor. The line handling unit separates the DMA-transferred combination packet into a plurality of packets and sends the plurality of packets to the communication line.

A traffic monitoring apparatus that monitors traffic of a monitoring target network and includes a statistical information processor that acquires statistical information per specific flow of the traffic, and a packet capture unit that captures a packet of the specific flow, in which the statistical information processor includes a statistical information aggregation unit that aggregates the pieces of statistical information, and a statistical information file generation unit that generates a statistical information file based on the pieces of aggregated statistical information.

Traffic monitoring device, traffic monitoring method, and traffic monitoring program

A traffic monitoring apparatus includes: a header analysis circuit configured to acquire one or more identifiers from a header of a received packet; a rule registration circuit configured to convert a rule table including rules in which one or more rule elements are registered for each of the rules into a predetermined format and register the rule table in a rule matching circuit; and the rule matching circuit configured to search for rules to be matched with the acquired identifiers.

Traffic monitoring device, and traffic monitoring method

The learning deviceD is learned to extract moving image feature amount Fm which is feature amount relating to the moving image data Dm when the moving image data Dm is inputted thereto, and is learned to extract still image feature amount Fs which is feature amount relating to the still image data Ds when the still image data Ds is inputted thereto. The first inference unitD performs a first inference regarding the moving image data Dm based on the moving image feature amount Fm. The second inference unitD performs a second inference regarding the still image data Ds based on the still image feature amount Fs. The learning unitD performs learning of the feature extraction unitD based on the results of the first inference and the second inference.

Updated learning of feature extraction model that extracts moving image feature amount from moving image data and still image feature amount from still image data

A data sequence correction method for temporarily saving data with sequence information in a ring buffer and performing sequence correction is provided. The ring buffer includes a number of storage regions, a monitoring section having one or more continuous sequence numbers, and an acceptance section having a first or second sequence number of the monitoring section as a start sequence number and a sequence number immediately preceding the start sequence number of the monitoring section as an end sequence number. The method includes, when a value determined based on a remainder obtained by dividing a sequence number of received data by the number of storage regions is inside the acceptance section, writing the received data in a position of the storage region corresponding to the determined value, and when data are written in the entire monitoring section, reading out all the data in the monitoring section.

Growing community of inventors

Tokyo, Japan

Shuhei Yoshida