Hongbo Xiao
ABSTRACT
In response to the current difficulty in identifying and predicting cocaine addicted individuals based on brain MRI images, this paper designs a deep learning recognition and prediction model based on convolutional neural networks. 29 cocaine addicted individuals and 24 healthy controls were selected from brain MRI images. After per-forming a series of data preprocessing operations such as skull dissection and data augmentation on brain MRI images, a deep learning model based on convolutional neural networks is constructed to process the processed brain MRI images of cocaine addicted individuals and healthy controls to identify and predict cocaine addicted individuals. The experimental results show that the recognition and prediction accuracy of deep learning models based on convolutional neural networks is 89%. Compared with machine learning models such as SVM and support vector machines, it greatly improves the accuracy of model prediction and can accurately, quickly, and effectively identify and predict cocaine addicted individuals.
- Zhao Wei. 2023. Epilepsy EEG signal recognition method based on CNN-LSTM model. Journal of Putian University, 30 (05): 69-74Google Scholar
- Wei Wanshu; Li Yuxin; Liu Tuo. 2021. Exploration of Psychological Risk Factors for Drug Addiction: Based on Machine Learning Models. Chinese Psychological Society Summary of the 23rd National Conference on Psychology (Part 1) Tianjin Normal University Institute of Psychology and Behavior, Key Research Base of Humanities and Social Sciences of the Ministry of Education; Department of Psychology, Tianjin Normal University; Student Psychological Development and Learning Tianjin University Social Science Laboratory; 2021: 2 DOI: 10.26914/c.cnkihy. 042412Google ScholarCross Ref
- Wang Congzhi; Wang Jiazhi; Wan Rui; Zhang Lin; Willow; Che Hengying; Liu Huan; Wang Min; Li Yuanzhen. 2023. Analysis Of Influencing Factors And Construction And Validation Of Predictive Models For Smartphone Addiction In Nursing Students. Journal of Changzhi Medical College, 37 (03): 177-183Google Scholar
- Wang Zili; Zhang Weidong; Zhang Jiajun. 2008. Network Addiction Prediction Based on Fuzzy Neural Networks. Control Engineering, (05): 556-559Google Scholar
- Gan Xing. 2022. Research On Drug Addiction Imaging Labeling Based On Multimodal Magnetic Resonance Imaging. Guizhou University, DOI: 10.27047/dcnki. ggudu.2022.001730Google ScholarCross Ref
- Kim,KS,KH. 2010. A Prediction Model for Internet Game Addiction in Adolescents: Using a Decision Tree Analysis. J KOREAN ACAD NURSGoogle Scholar
- Kauchak D, Mouradi O, Pentoney C, 2014. Text Simplification Tools: Using Machine Learning to Discover Features that Identify Difficult Text. 2014 47th Hawaii International Conference on System Sciences. IEEE, 2014.DOI:10.1109/HICSS. 330.Google ScholarDigital Library
- Chandankar H, Chaubal T, Bhat R. 2013. Machine Learning And Data Mining Approach To Identify Disease Treatment Relations.Google Scholar
- Nestler E G, Osqui M M, Bernstein J G. 2023. Convolutional Neural Network: US201615379114. US2017169327A1DOI:10.1007/978-3-319-67534-3_5.Google ScholarCross Ref
- Bambharolia P. 2017. Overview Of Convolutional Neural Networks. International Conference on Academic Research in Engineering and Management.Google Scholar
- Xiong C, Zhao X, Tang D, 2015. Conditional Convolutional Neural Network for Modality-Aware Face Recognition. 2015 IEEE International Conference on Computer Vision (ICCV). IEEE. DOI:10.1109. 418.Google Scholar
- Back M, Kim K K. 2022. GAN-based Image Data Augmentation for Improving Object Detection Performance in Industrial Environments. Journal of Software Assessment and Valuation. DOI:10.29056 12. 25.Google Scholar
Recommendations
Research on improved wavelet convolutional wavelet neural networks
AbstractConvolutional neural network (CNN) is recognized as state of the art of deep learning algorithm, which has a good ability on the image classification and recognition. The problems of CNN are as follows: the precision, accuracy and efficiency of ...
Pedestrian trajectory prediction with convolutional neural networks
Highlights- New convolutional model achieves state-of-the-art results on ETH and TrajNet datasets.
AbstractPredicting the future trajectories of pedestrians is a challenging problem that has a range of application, from crowd surveillance to autonomous driving. In literature, methods to approach pedestrian trajectory prediction have evolved,...
Comments