National Cheng-Kung University

Gwo-Giun Lee

He-Yuan Lin

Ming-Jiun Wang

Yu-Min Kuo

Wei-Chiao Yang

Min-Shan Wu

Yi-Ru Xie

A system and a method for Alzheimer's disease prediction using a neural network, a computer-readable recording medium with a stored program, and a computer program product are provided. The processor obtains a first brain MRI data, a second brain MRI data, a first neuropsychological assessment score, and a second neuropsychological assessment score. The processor obtains a plurality of image feature data according to the first brain MRI data and the second brain MRI data. Each image feature data is selected from a group consisting of a plurality of hippocampal subfield geometric change data. The processor obtains a neuropsychological change data according to the first neuropsychological assessment score and the second neuropsychological assessment score. The processor obtains an Alzheimer's disease prediction result according to the neural network module, the image feature data, and the neuropsychological change data.

System and method for Alzheimer's disease prediction using neural network, computer-readable recording medium with stored program, and computer program product

A design space exploration method of a reconfigurable motion compensation architecture is disclosed. The method comprises: defining a predetermined application specification; extracting the community among plural motion compensation algorithms corresponding to plural video compression standards; analyzing the computation of the plural motion compensation algorithms basing on the community, thereby determining the computation elements included in a processing element; analyzing the data flow of the reconfigurable motion compensation architecture basing on the predetermined application specification, both in the cases of peak computation and worst data configuration, while executing the plural motion compensation algorithms with different data granularities and different number of the processing elements, thereby obtaining plural hardware parameters corresponding to the plural motion compensation algorithms; and selecting a predetermined data granularity and a predetermined number of the processing elements of the reconfigurable motion compensation architecture, basing on a predetermined design target and the plural hardware parameters previously obtained.

Space exploration method of reconfigurable motion compensation architecture

A method of determining a design framework is implemented by an algorithm analyzer. The method includes configuring the algorithm analyzer to perform intrinsic complexity analysis of an algorithm for a predetermined application to obtain a set of parameters representing intrinsic characteristics of the algorithm. The method also includes configuring the algorithm analyzer to establish candidate design frameworks based on the parameters. Each candidate design framework includes a set of design constraints corresponding to the algorithm and which are used when designing a hardware and/or software configuration for implementing the predetermined application. The method also includes configuring the algorithm analyzer to analyze the suitability of the set of design constraints of each candidate design framework based on given specification restrictions of the predetermined application to determine which candidate design framework(s) is suited for the predetermined application.

Method and algorithm analyzer for determining a design framework

A method of analyzing intrinsic parallelism of an algorithm, comprising: generating a dataflow graph which is composed of vertexes representing computation and directed edges denoting the dependency and flow of data from the algorithm; building a matrix representing the dataflow graph; and quantifying the intrinsic parallelism based on rank and dimension of the matrix representing the generated dataflow graph.

Method of analyzing intrinsic parallelism of algorithm

A motion estimation method includes: (A) defining one pixel in a reference image as a center of search (CS) corresponding to a target pixel set in a current image; (B) determining a center error (CE) signal; (C) defining another pixel in the reference image as a target of search (TS) with reference to the CS, one candidate search vector available for selection from a vector set, and a step size; (D) determining a target error (TE) signal; (E) determining whether to update the CS and the CE signal; (F) if determined, updating the CS, the CE signal and the vector set; (G) repeating steps (C)&#x2dc;(F) using a candidate search vector selected from the vector set and the same step size until there is no candidate search vector available for selection in the vector set; (H) repeating steps (C)&#x2dc;(G) using a smaller step size until a predetermined value is reached; and (I) computing a motion vector based on the target pixel set and one pixel set that includes the CS.

Growing community of inventors

Taipei, Taiwan

Gwo-Giun Lee