Simulation of an Artificial Intelligence Behavior Analysis Model Based on Neural Network Algorithm

被引:0
作者
Lin, Shanshan [1 ]
Jia, Fengqi [1 ]
机构
[1] Weifang Engn Vocat Coll, Qingzhou 262500, Shandong, Peoples R China
来源
2024 INTERNATIONAL CONFERENCE ON POWER, ELECTRICAL ENGINEERING, ELECTRONICS AND CONTROL, PEEEC | 2024年
关键词
Neural Network; Artificial Intelligence; Convolutional Neural Network; Behavior analysis model; PREDICTION;
D O I
10.1109/PEEEC63877.2024.00066
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
AI (Artificial Intelligence) behavior analysis is a powerful tool, which can help us better understand and predict human behavior and provide support for decision-making in various fields. This paper aims to design an efficient and accurate user behavior analysis model by combining NN (Neural Network) algorithm module and behavior analysis module. In order to achieve this goal, this paper adopts CNN (Convolutional Neural Network) as the core algorithm, and combines with specific business needs and scenarios to formulate behavior analysis strategies. After a series of experiments, the proposed algorithm can quickly identify and classify different user behaviors, and has high accuracy in identifying user behaviors. Its MAPE value is only 0.251, which is significantly better than other comparison algorithms. At the same time, the algorithm shows high efficiency in different scale data sets. In addition, sensitivity analysis and scene test are carried out to verify the adaptability and stability of the model under various conditions and scenarios. By studying the application of NN algorithm in the field of user behavior analysis, we can further enrich and perfect the theoretical system in the field of AI, and promote the improvement and innovation of related algorithms.
引用
收藏
页码:328 / 333
页数:6
相关论文
共 12 条
[1]  
Cai YiFeng Cai YiFeng, 2017, International Agricultural Engineering Journal, V26, P349
[2]   Predicting the intent of sponsored search users: An exploratory user session-level analysis [J].
Im, Il ;
Dunn, Brian Kimball ;
Lee, Dong Il ;
Galletta, Dennis F. ;
Jeong, Seok-Oh .
DECISION SUPPORT SYSTEMS, 2019, 121 :25-36
[3]   Machine-Learning-Based User Position Prediction and Behavior Analysis for Location Services [J].
Jiang, Haiyang ;
He, Mingshu ;
Xi, Yuanyuan ;
Zeng, Jianqiu .
INFORMATION, 2021, 12 (05)
[4]   Crowd Behavior Recognition Using Hybrid Tracking Model and Genetic algorithm Enabled Neural Network [J].
Kumar, Manoj ;
Bhatnagar, Charul .
INTERNATIONAL JOURNAL OF COMPUTATIONAL INTELLIGENCE SYSTEMS, 2017, 10 (01) :234-246
[5]   A Study of Consumer Repurchase Behaviors of Smartphones Using Artificial Neural Network [J].
Lee, Hong Joo .
INFORMATION, 2020, 11 (09)
[6]   The Effects of Non-Directional Online Behavior on Students' Learning Performance: A User Profile Based Analysis Method [J].
Liang, Kun ;
Liu, Jingjing ;
Zhang, Yiying .
FUTURE INTERNET, 2021, 13 (08)
[7]  
Lu W, 2017, Acta Technica CSAV (Ceskoslovensk Akademie Ved), V62, P53
[8]   Fatigue behavior prediction and analysis of shot peened mild carbon steels [J].
Maleki, Erfan ;
Unal, Okan ;
Kashyzadeh, Kazem Reza .
INTERNATIONAL JOURNAL OF FATIGUE, 2018, 116 :48-67
[9]   Privacy-Preserving Selective Aggregation of Online User Behavior Data [J].
Qian, Jianwei ;
Qiu, Fudong ;
Wu, Fan ;
Ruan, Na ;
Chen, Guihai ;
Tang, Shaojie .
IEEE TRANSACTIONS ON COMPUTERS, 2017, 66 (02) :326-338
[10]   Game Analysis of Access Control Based on User Behavior Trust [J].
Wang, Yan ;
Tian, Liqin ;
Chen, Zhenguo .
INFORMATION, 2019, 10 (04)