Research on algorithm composition and emotion recognition based on adaptive networks

Author:

Hou Shuxin1,Wang Ning2,Su Baoming1

Affiliation:

1. 1 School of Music , Linyi University , Linyi , Shandong , , China .

2. 2 Theory Teaching and Research Department , School of Music, Linyi University , Linyi , Shandong , , China .

Abstract

Abstract Adaptive linear neural networks lay the foundation for the development of the uniqueness of algorithmic composition and emotion recognition. In this paper, we first analyze the process of emotion recognition and the development of algorithmic compositions to establish the emotion recognition dataset. Secondly, the algorithm of the adaptive linear neural network is selected, including the analysis of the adaptive linear neuron model and gradient and most rapid descent method and LMS algorithm. The analysis focuses on the LMS algorithm flow, convergence conditions and performance parameters of the LMS algorithm. Finally, the sentiment recognition results of four models, SVM, CNN, LSTM and Adaline neural network, based on different dimensional self-encoder features, are analyzed. To verify whether the classification method of self-encoder + Adaline neural network can find the information connection between various emotions and improve the efficiency of emotion recognition. The classification method of self-encoder + Adaline neural network can improve the recognition rate by up to 85% for noise-reducing self-encoder features in 500 dimensions.

Publisher

Walter de Gruyter GmbH

Subject

Applied Mathematics,Engineering (miscellaneous),Modeling and Simulation,General Computer Science

Reference20 articles.

1. Herremans, D., Chuan, C. H., & Chew, E. (2017). A functional taxonomy of music generation systems. ACM Computing Surveys (CSUR), 50(5), 69.1-69.30.

2. Kirke, A. J. (2019). Applying quantum hardware to non-scientific problems: grover’s algorithm and rule-based algorithmic music composition. International journal of unconventional computing, 14(3/4), 349-374.

3. Nw, A., Hui, X. B., Feng, X. C., & Lei, C. D. (2021). The algorithmic composition for music copyright protection under deep learning and blockchain. Applied Soft Computing.

4. Jenke, R., Peer, A., & Buss, M. (2017). Feature extraction and selection for emotion recognition from eeg. IEEE Transactions on Affective Computing, 5(3), 327-339.

5. Berggren, S., Fletcher-Watson, S., Milenkovic, N., Marschik, P. B., B? Lte, S., & Jonsson, U. (2017). Emotion recognition training in autism spectrum disorder: a systematic review of challenges related to generalizability. Developmental Neurorehabilitation, 1-14.

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3