公开(公告)号：US20240232477A1

公开(公告)日：2024-07-11

申请号：US18616181

申请日：2024-03-26

Applicant: Xiamen University ,  TAN KAH KEE INNOVATION LABORATORY

Inventor： Kai Huang ,  Ying Jiang ,  Zhuoying Jiang ,  Lin Li ,  Cheng Li ,  Jinchai Li ,  Rong Zhang ,  Junyong Kang

IPC: G06F30/27

CPC classification number: G06F30/27

Abstract: A method for predicting performance of LED structure is provided. The prediction method mainly includes: collecting and extracting input feature parameters and output feature parameters of LED structures, and constructing corresponding datasets; preprocessing data in the datasets; constructing a model using a machine learning algorithm, setting structural parameters of the model, and performing initialization training on the model to obtain an initial model; using preprocessed datasets to train and optimize the initial model, thereby obtaining a prediction model; inputting input feature parameters of an LED structure to be predicted into the prediction model, thereby obtaining prediction values of output feature parameters of the LED structure to be predicted. The prediction method can predict the performance of LED structure, has short prediction time, and has high prediction accuracy.

公开(公告)号：US20240211760A1

公开(公告)日：2024-06-27

申请号：US18597920

申请日：2024-03-07

Applicant: Xiamen University ,  TAN KAH KEE INNOVATION LABORATORY

Inventor： Kai Huang ,  Ying Jiang ,  Zhuoying Jiang ,  Lin Li ,  Cheng Li ,  Jinchai Li ,  Rong Zhang ,  Junyong Kang

IPC: G06N3/08 ,  G06N5/022 ,  H02S50/10

CPC classification number: G06N3/08 ,  G06N5/022 ,  H02S50/10

Abstract: A method for predicting performance of solar cell structure includes: collecting and extracting input feature parameters of solar cell structures and corresponding output feature parameters; establishing corresponding data sets, and preprocessing the data sets according to a known criterion; constructing a model by utilizing a machine learning algorithm, and setting structural parameters and performing initialization training on the model; performing training optimization on the model subjected to setting the structural parameters and performing the initialization training by using a preprocessed training data set to obtain a prediction model; and inputting a preprocessed test data set of a to-be-predicted solar cell structure into the prediction model to obtain predicted values of output feature parameters of the to-be-predicted solar cell structure. The performance of solar cell structure can be rapidly predicted, which is convenient to operate and has a high accuracy.

公开(公告)号：US11217225B2

公开(公告)日：2022-01-04

申请号：US17154801

申请日：2021-01-21

Applicant: XIAMEN UNIVERSITY

Inventor： Lin Li ,  Zheng Li ,  Qingyang Hong

IPC: G10L15/02 ,  G06N3/04 ,  G06N3/08 ,  G10L15/01 ,  G10L15/06 ,  G10L15/16 ,  G10L15/22

Abstract: The application discloses a multi-type acoustic feature integration method and system based on deep neural networks. The method and system include using labeled speech data set to train and build a multi-type acoustic feature integration model based on deep neural networks, to determine or update the network parameters of the multi-type acoustic feature integration model; the method and system includes inputting the multiple types of acoustic features extracted from the testing speech into the trained multi-type acoustic feature integration model, and extracting the deep integrated feature vectors in frame level or segment level. The solution supports the integrated feature extraction for multiple types of acoustic features in different kinds of speech tasks, such as speech recognition, speech wake-up, spoken language recognition, speaker recognition, and anti-spoofing etc. It encourages the deep neural networks to explore internal correlation between multiple types of acoustic features according to practical speech tasks, to improve the recognition accuracy and stability of speech applications.