Application scenario analysis based on CNN algorithm
DOI:
https://doi.org/10.54097/gszk8e52Keywords:
Deep learning, Convolution neural network, Price prediction, Traffic prediction, Sentiment text analysis.Abstract
The swift advancement of artificial intelligence technology, facilitated by the rapid progress in science and technology, has significantly enhanced the convenience of our daily lives. As a pivotal model in the realm of deep learning, convolution neural network (CNN) has achieved remarkable feats in various domains such as image recognition, speech recognition, natural language processing, and more. The purpose of this paper is to explore the application of CNN algorithm in different fields, including price prediction, traffic prediction and sentiment text analysis, and summarize its application status, and look forward to the future development trend. While CNN algorithm demonstrates strong performance in these areas, its limitations hinder significant contributions in certain fields. Nevertheless, it is anticipated that with continued advancements in science and technology, CNN algorithm will exhibit commendable performance across diverse domains. This study projects CNN's future development trends and gives an overview of the technology's current application status in a number of sectors, making it a useful resource for relevant applications and research.
Downloads
References
Chen Y, Jiang H, Li C, et al. Deep feature extraction and classification of hyperspectral images based on convolutional neural networks. IEEE transactions on geoscience and remote sensing, 2016, 54(10): 6232-6251.
Ayeni J. Convolutional neural network (CNN): the architecture and applications. Applied Journal of Physical Science, 2022, 4(4): 42-50.
Cao Yugui, Xie Mengxing. Model based on WD - CNN - LSTM's share price forecast analysis. Journal of north China water conservancy and hydropower university (social science edition), 2023, 33 (05) 6:15-22.
Yang Xueqian. Gold Futures price prediction based on CNN-BiGRU model. Henan university, 2023.
He S M. Research on carbon emission trading price prediction based on CNN-LSTM model. Henan university, 2023.
Bao Wenhua, Liu Hairui, Yuan Yuan, et al. Short-cycle traffic flow prediction method for traffic intersections based on CNN-ARIMA. Car practical technology, 2023 (22): 13. 178-182.
Shi Junqing, Chen Linwu, Li Sulan, et al. Urban road Traffic incident detection algorithm based on CNN. Journal of Highway Traffic Science and Technology, 2022, 39(03): 176-182.
Tian Sheng, Song Lin. Traffic sign recognition based on integration of CNN and Bagging. Journal of guangxi normal university (natural science edition), 2022, 40 (04): 35-46.
Xu Yuanyin, Wen Xiaoshuang, Ma Lulu, et al. Application research of sentiment classification in commentary text based on BERT and CNN. Information Technology and Informatization, 2023(12): 81-84.
Jin Ning, Jiang Hongwei. Emotion Analysis of logistics comment based on BiLSTM-CNN-MultiHeadAttention-Dropout. Logistics science and technology, 2023, 46-48 (23): 48-52.
Downloads
Published
Issue
Section
License
Copyright (c) 2024 Highlights in Science, Engineering and Technology

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.







