Abstract: An object of the present invention is to provide an image recognition system, an image recognition server, and an image recognition method having a new high security framework that can achieve utilization of multi-device diversity. The image recognition system according to the present disclosure includes a computationally non-intensive encryption algorithm based on random unitary transformation and achieves a high level of security. In addition, the image recognition system achieves high recognition performance by using ensemble learning to integrate recognition results based on the dictionaries of different devices.

Abstract: Provided is a concealment signal generation unit that acquires learning constellation data and identification constellation data output from a signal processing circuit for optical communication, reduces and conceals the number of pieces of data from each of the pieces of constellation data through random projection, and generates a learning concealment signal and an identification concealment signal based on each piece of constellation data after the reduction and concealment of the number of pieces of data. Provided are a sparse dictionary learning unit that learns a concealment sparse dictionary using a sparse dictionary learning algorithm based on the learning concealment signal; and an identification unit that estimates a state of the optical communication using the concealment sparse dictionary based on the identification concealment signal.

Abstract: A data accumulation unit that acquires traffic data of a network obtained in time series and creates a plurality of data sets having different time intervals, a training unit that evaluates a correlation between the plurality of data sets by a plurality of latent functions and calculates a weight coefficient, and a prediction unit that calculates a predicted average using the latent functions calculated by the training unit and predicts network traffic of a future time scale are included.

Abstract: The present disclosure has been made in view of such a problem, and an object of the present disclosure is to make it possible to predict fluctuation of unsteady traffic with a small amount of calculation.

Abstract: The present disclosure has an object of proposing a method and a device for estimating the state of a transmission path or an optical transmitter capable of mechanically estimating a factor causing an error with a small amount of constellation data and a low computing amount.

Abstract: The present disclosure is to perform beamforming corresponding to the influence of a dynamic environment in which a user moves. The present disclosure relates to a beamforming prediction device that includes: a storage unit that stores a dictionary D obtained by learning fingerprints based on trajectories, and a fingerprint database based on trajectories; a trajectory prediction unit that calculates a trajectory of a mobile terminal, using location information about the mobile terminal; a fingerprint estimation unit that applies the trajectory of the mobile terminal to an input of the dictionary D, and calculates the sparse coefficient X corresponding to the trajectory of the mobile terminal; and a beamforming calculation unit that calculates beamforming of the mobile terminal, using the sparse coefficient X calculated by the fingerprint estimation unit and the fingerprint database.

Abstract: The present disclosure has been made in view of such a problem, and an object of the present disclosure is to make it possible to predict fluctuation of unsteady traffic with a small amount of calculation.

Abstract: One aspect of the present invention is a secure computation method including, acquiring a plurality of pieces of encrypted analysis target information being a plurality of pieces of encrypted information about an event to be analyzed, and analyzing, based on the plurality of pieces of the encrypted analysis target information, the event without decrypting the plurality of pieces of the encrypted analysis target information. In the secure computation method, encryption keys for the plurality of pieces of the encrypted analysis target information are unitary matrices, and at least one of the encryption keys for the plurality of pieces of the encrypted analysis target information is different from another of the encryption keys.

Abstract: The present disclosure has an object of proposing a method and a device for estimating the state of a transmission path or an optical transmitter capable of mechanically estimating a factor causing an error with a small amount of constellation data and a low computing amount.

Abstract: An object of the invention is to provide a photographed target matching method and the like which allows video image data including a plurality of photographed targets and sensor data from terminals worn by the targets to be automatically associated with one another, so that a data set for analysis can be produced.

Abstract: An object of the present invention is to provide an image recognition system, an image recognition server, and an image recognition method having a new high security framework that can achieve utilization of multi-device diversity. The image recognition system according to the present disclosure includes a computationally non-intensive encryption algorithm based on random unitary transformation and achieves a high level of security. In addition, the image recognition system achieves high recognition performance by using ensemble learning to integrate recognition results based on the dictionaries of 4 different devices.

Abstract: An objective of the present disclosure is to enable estimation of an attention target of communication parties even if there are a plurality of objects having the same appearance in a space. An attention target estimation device 10 according to the present disclosure acquires a first-person point-of-view video IMi captured from a perspective of a person and a line-of-sight position gi of a person when the first-person point-of-view video IMi is captured, identifies positions in a 3D space of objects 31, 32, and 33 extracted from the first-person point-of-view video IMi, and determines an object close to the line-of-sight position gi of the person among the objects 31, 32, and 33 included in the first-person point-of-view video IMi as the attention target of the person.

Abstract: A selective PEG algorithm, creating a sparse matrix while maintaining row weight/column weight at arbitrary multi-levels, and in the process, inactivating an arbitrary edge so that a minimum loop formed between arbitrary nodes is enlarged or performing constrained interleaving, so that encoding efficiency in the case where a matrix space is narrow is improved.

Abstract: An objective of the present disclosure is to enable estimation of an attention target of communication parties even if there are a plurality of objects having the same appearance in a space. An attention target estimation device 10 according to the present disclosure acquires a first-person point-of-view video IMi captured from a perspective of a person and a line-of-sight position gi of a person when the first-person point-of-view video IMi is captured, identifies positions in a 3D space of objects 31, 32, and 33 extracted from the first-person point-of-view video IMi, and determines an object close to the line-of-sight position gi of the person among the objects 31, 32, and 33 included in the first-person point-of-view video IMi as the attention target of the person.

Abstract: This method and device makes it possible to implement maximum likelihood decoding of a sparse graph code at low computational complexity in the maximum likelihood decoding of the sparse graph code. This is, in the maximum likelihood of decoding of the sparse graph code, a lost data decoding process by a trivial decoding method and a lost data decoding process by a Gauss elimination method are performed repeatedly and alternately.

Abstract: A selective PEG algorithm, creating a sparse matrix while maintaining row weight/column weight at arbitrary multi-levels, and in the process, inactivating an arbitrary edge so that a minimum loop formed between arbitrary nodes is enlarged or performing constrained interleaving, so that encoding efficiency in the case where a matrix space is narrow is improved.

Abstract: This method and device makes it possible to implement maximum likelihood decoding of a sparse graph code at low computational complexity in the maximum likelihood decoding of the sparse graph code. This is, in the maximum likelihood of decoding of the sparse graph code, a lost data decoding process by a trivial decoding method and a lost data decoding process by a Gauss elimination method are performed repeatedly and alternately.

Abstract: A encoding apparatus decomposes an original image into M (M is an integer and M>2) uniform subbands, and encodes the decomposed signals by using an embedded type entropy encoding method. A decoding apparatus receives the coded data encoded by the encoding apparatus, extracts N signals from the coded data from a low frequency component side in decomposed signals, decodes the N signals by using an entropy decoding method, and synthesizes the N decoded signals to obtain a decoded image of a resolution of N/M times (M and N are integers, and 1?N?M and M>2) that of an original image.

Abstract: A encoding apparatus decomposes an original image into M (M is an integer and M>2) uniform subbands, and encodes the decomposed signals by using an embedded type entropy encoding method. A decoding apparatus receives the coded data encoded by the encoding apparatus, extracts N signals from the coded data from a low frequency component side in decomposed signals, decodes the N signals by using an entropy decoding method, and synthesizes the N decoded signals to obtain a decoded image of a resolution of N/M times (M and N are integers, and 1?N?M and M>2) that of an original image.