Neural Network and Prior Knowledge Ensemble for Whistle Recognition

被引：0

作者：

Kleingarn, Diana ^{[1
]}

Braemer, Dominik ^{[1
]}

机构：

[1] TU Dortmund Univ, Sect Informat Technol, Robot Res Inst, D-44227 Dortmund, Germany

来源：

ROBOCUP 2023: ROBOT WORLD CUP XXVI | 2024年 / 14140卷

关键词：

Whistle recognition; Convolutional neural network; Classical audio processing;

D O I：

10.1007/978-3-031-55015-7_2

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Whistle recognition is becoming an increasingly crucial aspect of RoboCup. Therefore neural networks are being utilized in this field more frequently. They are typically more effective than straightforward conventional approaches but still have flaws in fields that require prior knowledge, as conventional approaches do. In this work, we present an approach that can outperform standalone variants of both methods by fusing prior knowledge of traditional methods with a neural network. Additionally, we were able to keep the composite system runtime efficient on the integrated hardware of the NAO Robot.

引用

页码：17 / 28

页数：12

共 50 条

[1] An ensemble unsupervised spiking neural network for objective recognition
Fu, Qiang
Dong, Hongbin
NEUROCOMPUTING, 2021, 419 : 47 - 58
[2] Locomotion Recognition Using XGBoost and Neural Network Ensemble
Lu, Hong
Pinaroc, Maximilian
Lv, Mengchun
Sun, Shouwei
Han, Hemin
Shah, Rahul C.
UBICOMP/ISWC'19 ADJUNCT: PROCEEDINGS OF THE 2019 ACM INTERNATIONAL JOINT CONFERENCE ON PERVASIVE AND UBIQUITOUS COMPUTING AND PROCEEDINGS OF THE 2019 ACM INTERNATIONAL SYMPOSIUM ON WEARABLE COMPUTERS, 2019, : 757 - 760
[3] Number image recognition based on neural network ensemble
Wang, Jian
Yang, Jingfeng
Li, Shaofa
Dai, Qiufang
Xie, Jiaxing
ICNC 2007: THIRD INTERNATIONAL CONFERENCE ON NATURAL COMPUTATION, VOL 1, PROCEEDINGS, 2007, : 237 - +
[4] Stress affects the neural ensemble for integrating new information and prior knowledge
Vogel, Susanne
Kluen, Lisa Marieke
Fernandez, Guillen
Schwabe, Lars
NEUROIMAGE, 2018, 173 : 176 - 187
[5] Distribution Network Connectivity Recognition Based on Ensemble Deep Neural Network
Jiang W.
Tang H.
Qi H.
Chen H.
Chen J.
Jiao H.
Dianli Xitong Zidonghua/Automation of Electric Power Systems, 2020, 44 (01): : 101 - 108
[6] Representing and incorporating prior knowledge in neural network training
NEURAL NETWORKS: TRICKS OF THE TRADE, 1998, 1524 : 235 - 237
[7] The use of prior knowledge in neural network configuration and training
Hilario, M
Rida, A
BIOLOGICAL AND ARTIFICIAL COMPUTATION: FROM NEUROSCIENCE TO TECHNOLOGY, 1997, 1240 : 227 - 236
[8] A Prior-Knowledge-Guided Neural Network Based on Supervised Contrastive Learning for Radar HRRP Recognition
Liu, Qi
Zhang, Xinyu
Liu, Yongxiang
IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS, 2024, 60 (03) : 2854 - 2873
[9] Convolutional Neural Network Based Ensemble Approach for Homoglyph Recognition
Majumder, Md Taksir Hasan
Rahman, Md Mahabur
Iqbal, Anindya
Rahman, M. Sohel
MATHEMATICAL AND COMPUTATIONAL APPLICATIONS, 2020, 25 (04)
[10] Usage of convolutional neural network ensemble for traffic sign recognition
Kharchenko, Igor I.
Borovskoy, Igor G.
Shelmina, Elena A.
VESTNIK TOMSKOGO GOSUDARSTVENNOGO UNIVERSITETA-UPRAVLENIE VYCHISLITELNAJA TEHNIKA I INFORMATIKA-TOMSK STATE UNIVERSITY JOURNAL OF CONTROL AND COMPUTER SCIENCE, 2022, (61): : 88 - 96

← 1 2 3 4 5 →