Deep Learning-Based Domain Adaptation Healthcare Method for Predicting Mortality Risk of ICU Patient
Keywords:
Deep Learning, Unsupervised, Domain Adaptation, Softmax, Cosine Margin Loss, BI-LSTM, MedicalAbstract
Deep learning models often encounter issues such as insufficient labelled training data, shifts in overall data distribution, and shifts in data distribution between categories, leading to a drop in model prediction accuracywhen employed in prediction tasks in the medical area. A deep learning-based domain adaptation marginal softmax aware additive cosine margin loss prediction (DDSCM) model is presented to address such issues. The presented approachutilizes a bidirectional memory network along with an attention modulein order to retrieve the crucial features. The approach offers the concept of generative adversarial networks to reduce data distribution shifts between comprehensive data in the form of domain adversarial. The idea of metric learning is then included in the method to reduce the data distribution shift between categories even further by optimizing the decision boundary which thereby increase the domain adaptation effect and prediction accuracy of the model. At last, real-world medical data collection is used to conduct the mortality risk prediction job. The experimental findings were compared to the baseline models of the other five. The proposed method solves the problem of data distribution shift better than existing baseline models and obtains a better classification result.
Downloads
References
S. Hussein, P. Kandel, C. W. Bolan, M. B. Wallace and U. Bagci, "Lung and Pancreatic Tumor Characterization in the Deep Learning Era: Novel Supervised and Unsupervised Learning Approaches," in IEEE Transactions on Medical Imaging, vol. 38, no. 8, pp. 1777-1787, Aug. 2019, doi: 10.1109/TMI.2019.2894349.
N. Abid et al., "Burnt Forest Estimation from Sentinel-2 Imagery of Australia using Unsupervised Deep Learning," 2021 Digital Image Computing: Techniques and Applications (DICTA), 2021, pp. 01-08, doi: 10.1109/DICTA52665.2021.9647174.
N. Rajpurohit, A. Agarwalla and J. S. Bhatt, "A Sure-Based Unsupervised Deep Learning Method for SarDespeckling," 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS, 2021, pp. 5119-5122, doi: 10.1109/IGARSS47720.2021.9553918.
Y. Hui, L. Du, S. Lin, Y. Qu and D. Cao, "Extraction and Classification of TCM Medical Records Based on BERT and Bi-LSTM With Attention Mechanism," 2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2020, pp. 1626-1631, doi: 10.1109/BIBM49941.2020.9313359.
T. Jain, R. Sharma and R. Malhotra, "Handwriting Recognition for Medical Prescriptions using a CNN-Bi-LSTM Model," 2021 6th International Conference for Convergence in Technology (I2CT), 2021, pp. 1-4, doi: 10.1109/I2CT51068.2021.9418153.
Q. -J. Lv et al., "A Multi-Task Group Bi-LSTM Networks Application on Electrocardiogram Classification," in IEEE Journal of Translational Engineering in Health and Medicine, vol. 8, pp. 1-11, 2020, Art no. 1900111, doi: 10.1109/JTEHM.2019.2952610.
Y. Ren, T. Zhang, X. Liu and H. Lin, "End-to-end Answer Selection via Attention-Based Bi-LSTM Network," 2018 1st IEEE International Conference on Hot Information-Centric Networking (HotICN), 2018, pp. 264-265, doi: 10.1109/HOTICN.2018.8606015.
H. Zhao, L. Deng and Y. Xie, "A Training Strategy for Enhancing the Accuracy of Real-Time Tumor Tracking Based on Deep Bi-LSTM Learning," 2019 International Conference on Medical Imaging Physics and Engineering (ICMIPE), 2019, pp. 1-4, doi: 10.1109/ICMIPE47306.2019.9098226.
E. Dong, Y. Qiao and Z. Zhang, "Application of Difficult Sample Mining based on Cosine Loss in Face Recognition," 2020 IEEE International Conference on Mechatronics and Automation (ICMA), 2020, pp. 1052-1057, doi: 10.1109/ICMA49215.2020.9233852.
R. Li, N. Li, D. Tuo, M. Yu, D. Su and D. Yu, "Boundary Discriminative Large Margin Cosine Loss for Text-independent Speaker Verification," ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019, pp. 6321-6325, doi: 10.1109/ICASSP.2019.8682749.
R. Ji, J. Cao, X. Cai and B. Xu, "Max Margin Cosine Loss for Speaker Identification on Short Utterances," 2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP), 2018, pp. 304-308, doi: 10.1109/ISCSLP.2018.8706654.
D. Zhong and J. Zhu, "Centralized Large Margin Cosine Loss for Open-Set Deep Palmprint Recognition," in IEEE Transactions on Circuits and Systems for Video Technology, vol. 30, no. 6, pp. 1559-1568, June 2020, doi: 10.1109/TCSVT.2019.2904283.
H. Wang et al., "CosFace: Large Margin Cosine Loss for Deep Face Recognition," 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018, pp. 5265-5274, doi: 10.1109/CVPR.2018.00552.
C. Gui and J. Hu, "Unsupervised Domain Adaptation by regularizing Softmax Activation," 2018 24th International Conference on Pattern Recognition (ICPR), 2018, pp. 397-402, doi: 10.1109/ICPR.2018.8545224.
Z. -H. Liu, B. -L. Lu, H. -L. Wei, L. Chen, X. -H. Li and M. Rätsch, "Deep Adversarial Domain Adaptation Model for Bearing Fault Diagnosis," in IEEE Transactions on Systems, Man, and Cybernetics: Systems, vol. 51, no. 7, pp. 4217-4226, July 2021, doi: 10.1109/TSMC.2019.2932000.
B. Gholami, O. Rudovic and V. Pavlovic, "PUnDA: Probabilistic Unsupervised Domain Adaptation for Knowledge Transfer Across Visual Categories," 2017 IEEE International Conference on Computer Vision (ICCV), 2017, pp. 3601-3610, doi: 10.1109/ICCV.2017.387.
J. Wu, S. Liao, Z. lei, X. Wang, Y. Yang and S. Z. Li, "Clustering and Dynamic Sampling Based Unsupervised Domain Adaptation for Person Re-Identification," 2019 IEEE International Conference on Multimedia and Expo (ICME), 2019, pp. 886-891, doi: 10.1109/ICME.2019.00157.
M. A. Kabir and X. Luo, "Unsupervised Learning for Network Flow Based Anomaly Detection in the Era of Deep Learning," 2020 IEEE Sixth International Conference on Big Data Computing Service and Applications (BigDataService), 2020, pp. 165-168, doi: 10.1109/BigDataService49289.2020.00032.
H. Yan, P. Yu and D. Long, "Study on Deep Unsupervised Learning Optimization Algorithm Based on Cloud Computing," 2019 International Conference on Intelligent Transportation, Big Data & Smart City (ICITBS), 2019, pp. 679-681, doi: 10.1109/ICITBS.2019.00168.
H. -X. Yu, A. Wu and W. -S. Zheng, "Unsupervised Person Re-Identification by Deep Asymmetric Metric Embedding," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 42, no. 4, pp. 956-973, 1 April 2020, doi: 10.1109/TPAMI.2018.2886878.
B. Zhou, D. Su and Z. Qu, "Medical Text Classification System Based on Deep Learning," 2021 International Conference on Intelligent Computing, Automation and Applications (ICAA), 2021, pp. 388-392, doi: 10.1109/ICAA53760.2021.00077.
X. Hu and Q. Yuan, "Epileptic EEG Identification Based on Deep Bi-LSTM Network," 2019 IEEE 11th International Conference on Advanced Infocomm Technology (ICAIT), 2019, pp. 63-66, doi: 10.1109/ICAIT.2019.8935899.
B. Liu et al., "Fair Loss: Margin-Aware Reinforcement Learning for Deep Face Recognition," 2019 IEEE/CVF International Conference on Computer Vision (ICCV), 2019, pp. 10051-10060, doi: 10.1109/ICCV.2019.01015.
N. I. Kajla, M. M. S. Missen, M. M. Luqman, M. Coustaty, A. Mehmood and G. S. Choi, "Additive Angular Margin Loss in Deep Graph Neural Network Classifier for Learning Graph Edit Distance," in IEEE Access, vol. 8, pp. 201752-201761, 2020, doi: 10.1109/ACCESS.2020.3035886.
H. Ren, M. El-Khamy and J. Lee, "Stereo Disparity Estimation via Joint Supervised, Unsupervised, and Weakly Supervised Learning," 2020 IEEE International Conference on Image Processing (ICIP), 2020, pp. 2760-2764, doi: 10.1109/ICIP40778.2020.9191126.
P. Du, X. lin, X. Pi and X. wang, "An Unsupervised Learning Algorithm for Deep Recurrent Spiking Neural Networks," 2020 11th IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON), 2020, pp. 0603-0607, doi: 10.1109/UEMCON51285.2020.9298074.
K. Yu, "Deep Learning for Unsupervised Neural Machine Translation," 2021 2nd International Conference on Big Data & Artificial Intelligence & Software Engineering (ICBASE), 2021, pp. 614-617, doi: 10.1109/ICBASE53849.2021.00121.
Y. Xu, B. Liu, Y. Quan and H. Ji, "Unsupervised Deep Background Matting Using Deep Matte Prior," in IEEE Transactions on Circuits and Systems for Video Technology, vol. 32, no. 7, pp. 4324-4337, July 2022, doi: 10.1109/TCSVT.2021.3132461.
Q. Liu, G. Luan, F. Wang, B. Peng and D. Hu, "Multi-focus Image Fusion Algorithm Based on Unsupervised Deep Learning," 2021 International Conference on Computer Information Science and Artificial Intelligence (CISAI), 2021, pp. 362-366, doi: 10.1109/CISAI54367.2021.00076.
Jaruwatcharaset, C. . (2023). Effects of Using a Temperature Control System in Bandicota indica Stalls with Internet of Things Technology. International Journal on Recent and Innovation Trends in Computing and Communication, 11(4s), 166–170. https://doi.org/10.17762/ijritcc.v11i4s.6324
Yathiraju, D. . (2022). Blockchain Based 5g Heterogeneous Networks Using Privacy Federated Learning with Internet of Things. Research Journal of Computer Systems and Engineering, 3(1), 21–28. Retrieved from https://technicaljournals.org/RJCSE/index.php/journal/article/view/37
Sai Pandraju, T.K., Samal, S., Saravanakumar, R., Yaseen, S.M., Nandal, R., Dhabliya, D. Advanced metering infrastructure for low voltage distribution system in smart grid based monitoring applications (2022) Sustainable Computing: Informatics and Systems, 35, art. no. 100691, .
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.