Hyperparameter Tuning in Deep Learning-Based Image Classification to Improve Accuracy using Adam Optimization

doi:10.23940/ijpe.23.09.p3.579586

Abstract

Abstract: Deep learning (DL) is a cutting-edge image-processing technology that includes various satellite image sources being processed to analyze, enhance, and classify. This article covers a multilayer DL framework that classifies different types of vegetation and land cover using IRS p6 satellite images from many time scales and sources. The core of the design is an ensemble of supervised NNs and unsupervised neural networks (NNs) for optical imaging categorization and incomplete data restitution due to mists, reflections, and other natural effects that affect images. In this article, we contrast the traditional densely integrated multilayer perceptron (MLP) with the most popular method in remote sensing field random forest as the basic supervised NN architecture with convolutional NNs (CNNs). In general, utilizing the aforementioned procedure reduced accuracy and required longer computation times to train the model which produced 94.3%. The hyperparameters to adjust are the number of neurons, input layer, optimizer, number of epochs, filter size, and iterations. The second stage involves adjusting the number of layers. Some other conventional algorithms are lacking in this. The accuracy might be impacted by many layers. To overcome that, applying the Adam optimizer will produce a higher accuracy level of 96.72% with faster computation time and less memory management.

Key words: accuracy assessment, classification, CNNs, deep learning, image classification, remote sensing

Janarthanan Sekar and Ganesh Kumar T. Hyperparameter Tuning in Deep Learning-Based Image Classification to Improve Accuracy using Adam Optimization [J]. Int J Performability Eng, 2023, 19(9): 579-586.

Add to citation manager EndNote|Reference Manager|ProCite|BibTeX|RefWorks

References

1. Kussul N., Lavreniuk M., Skakun S., andShelestov A.Deep Learning Classification of Land Cover and Crop Types using Remote Sensing Data. IEEE Geoscience and Remote Sensing Letters, vol. 14, no. 5, pp. 778-782, 2017.
2. Khatami R., Mountrakis G., andStehman S.V.A Meta-Analysis of Remote Sensing Research on Supervised Pixel-Based Land-Cover Image Classification Processes: General Guidelines for Practitioners and Future Research. Remote sensing of environment, vol. 177, pp. 89-100, 2016.
3. Gislason P.O., Benediktsson J.A., andSveinsson J.R.Random Forests for Land Cover Classification. Pattern recognition letters, vol. 27, no. 4, pp. 294-300, 2006.
4. Zhang Z., Liu Q., andWang Y.Road Extraction by Deep Residual U-Net. IEEE Geoscience and Remote Sensing Letters, vol. 15, no. 5, pp. 749-753, 2018.
5. Roy S.K., Krishna G., Dubey S.R., andChaudhuri B.B.HybridSN: Exploring 3-D-2-D CNN Feature Hierarchy for Hyperspectral Image Classification. IEEE Geoscience and Remote Sensing Letters, vol. 17, no. 2, pp. 277-281, 2019.
6. Sun S., Mu L., Wang L., andLiu P. L-UNet: An LSTM Network for Remote Sensing Image Change Detection, IEEE Geoscience and Remote Sensing Letters, vol. 19, pp. 1-5, 2022.
7. Celik T.Unsupervised Change Detection in Satellite Images using Principal Component Analysis and $k$-Means Clustering. IEEE geoscience and remote sensing letters, vol. 6, no. 4, pp.772-776, 2009.
8. He, X. and Chen, Y.Optimized Input for CNN-Based Hyperspectral Image Classification using Spatial Transformer Network. IEEE Geoscience and Remote Sensing Letters, vol. 16, no. 12, pp. 1884-1888, 2019.
9. Chatterjee A., Saha J., Mukherjee J., Aikat S., andMisra A.Unsupervised Land Cover Classification of Hybrid and Dual-Polarized Images using Deep Convolutional Neural Network. IEEE Geoscience and Remote Sensing Letters, vol. 18, no. 6, pp.969-973, 2020.
10. Romero A., Gatta C., andCamps-Valls, G. Unsupervised Deep Feature Extraction for Remote Sensing Image Classification. IEEE Transactions on Geoscience and Remote Sensing, vol. 54, no. 3, pp. 1349-1362, 2015.
11. Glorot, X. and Bengio, Y.Understanding the Difficulty of Training Deep Feedforward Neural Networks. InProceedings of the thirteenth international conference on artificial intelligence and statistics, pp. 249-256, 2010.
12. Brownlee J.Code Adam Optimization Algorithm from Scratch.Machine Learning Mastery, 2021.
13. Ghorbanian, A. and Mohammadzadeh, A.An Unsupervised Feature Extraction Method based on Band Correlation Clustering for Hyperspectral Image Classification using Limited Training Samples. Remote Sensing Letters, vol. 9, no. 10, pp. 982-991, 2018.
14. Song J., Gao S., Zhu Y., andMa C.A Survey of Remote Sensing Image Classification based on CNNs. Big earth data, vol. 3, no. 3, pp. 232-254, 2019.
15. Wei Y., Luo X., Hu L., Peng Y., andFeng J.An Improved Unsupervised Representation Learning Generative Adversarial Network for Remote Sensing Image Scene Classification. Remote Sensing Letters, vol. 11, no. 6, pp. 598-607, 2020.
16. Cong M., Wang Z., Tao Y., Xi J., Ren C., andXu M.Unsupervised Self-Adaptive Deep Learning Classification Network based on the Optic Nerve Microsaccade Mechanism for Unmanned Aerial Vehicle Remote Sensing Image Classification. Geocarto International, vol. 36, no. 18, pp. 2065-2084, 2021.
17. Adepoju, K.A. and Adelabu, S.A.Improving Accuracy of Landsat-8 OLI Classification using Image Composite and Multisource Data with Google Earth Engine. Remote Sensing Letters, vol. 11, no. 2, pp. 107-116, 2020.
18. Chatterjee A., Saha J., Mukherjee J., Aikat S., andMisra A.Unsupervised Land Cover Classification of Hybrid and Dual-Polarized Images using Deep Convolutional Neural Network. IEEE Geoscience and Remote Sensing Letters, vol. 18, no. 6, pp. 969-973, 2020.
19. Wu Y., Zhang P., Wu J., andLi C.Object-Oriented and Deep-Learning-Based High-Resolution Mapping from Large Remote Sensing Imagery. Canadian Journal of Remote Sensing, vol. 47, no. 3, pp. 396-412, 2021.
20. Zhang X., Tan X., Chen G., Zhu K., Liao P., andWang T.Object-Based Classification Framework of Remote Sensing Images with Graph Convolutional Networks. IEEE Geoscience and Remote Sensing Letters, vol. 19, pp. 1-5, 2021.
21. Zhang X., Wang Q., Chen G., Dai F., Zhu K., Gong Y., andXie Y.An Object-Based Supervised Classification Framework for Very-High-Resolution Remote Sensing Images using Convolutional Neural Networks. Remote sensing letters, vol. 9, no. 4, pp. 373-382, 2018.
22. Shi S., Zhong Y., Zhao J., Lv P., Liu Y., andZhang L.Land-Use/Land-Cover Change Detection based on Class-Prior Object-Oriented Conditional Random Field Framework for High Spatial Resolution Remote Sensing Imagery. IEEE Transactions on Geoscience and Remote Sensing, vol. 60, pp. 1-16, 2020.
23. Yu X., Fan J., Chen J., Zhang P., Zhou Y., andHan L.NestNet: A Multiscale Convolutional Neural Network for Remote Sensing Image Change Detection. International Journal of Remote Sensing, vol. 42, no. 13, pp. 4898-4921, 2021.
24. Alem, A. and Kumar, S.Deep Learning Models Performance Evaluations for Remote Sensed Image Classification. IEEE Access, vol. 10, pp. 111784-111793, 2022.
25. Zahid U., Ashraf I., Khan M.A., Alhaisoni M., Yahya K.M., Hussein H.S., andAlshazly H.BrainNet: Optimal Deep Learning Feature Fusion for Brain Tumor Classification. Computational Intelligence and Neuroscience, vol. 2022, 2022.
26. Yang B., Hu S., Guo Q., andHong D.Multisource Domain Transfer Learning based on Spectral Projections for Hyperspectral Image Classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 15, pp. 3730-3739, 2022.
27. Mahdianpari M., Salehi B., Rezaee M., Mohammadimanesh F., andZhang Y.Very Deep Convolutional Neural Networks for Complex Land Cover Mapping using Multispectral Remote Sensing Imagery. Remote Sensing, vol. 10, no. 7, pp. 1119, 2018.
28. Maggiori E., Tarabalka Y., Charpiat G., andAlliez P.Convolutional Neural Networks for Large-Scale Remote-Sensing Image Classification. IEEE Transactions on geoscience and remote sensing, vol. 55, no. 2, pp. 645-657, 2016.
29. Zhu Q., Deng W., Zheng Z., Zhong Y., Guan Q., Lin W., Zhang L., andLi D.A Spectral-Spatial-Dependent Global Learning Framework for Insufficient and Imbalanced Hyperspectral Image Classification. IEEE Transactions on Cybernetics, vol. 52, no. 11, pp. 11709-11723, 2021.
30. Feng Y., Song R., Ni W., Zhu J., andWang X.A Novel Semi-Supervised Long-Tailed Learning Framework with Spatial Neighborhood Information for Hyperspectral Image Classification. IEEE Geoscience and Remote Sensing Letters, vol. 20, pp.1-5, 2023.
31. Gao K., Liu B., Yu X., andYu A.Unsupervised Meta Learning with Multiview Constraints for Hyperspectral Image Small Sample Set Classification. IEEE Transactions on Image Processing, vol. 31, pp. 3449-3462, 2022.
32. Chugh R.S., Bhatia V., Khanna K., andBhatia V.A Comparative Analysis of Classifiers for Image Classification. In2020 10th International Conference on Cloud Computing, Data Science & Engineering (Confluence), IEEE, pp. 248-253, 2020.
33. Chen K., Li W., Chen J., Zou Z., andShi Z.Resolution-Agnostic Remote Sensing Scene Classification with Implicit Neural Representations. IEEE Geoscience and Remote Sensing Letters, vol. 20, pp. 1-5, 2022.
34. Zhao Z., Li J., Luo Z., Li J., andChen C.Remote Sensing Image Scene Classification based on an Enhanced Attention Module. IEEE Geoscience and Remote Sensing Letters, vol. 18, no. 11, pp. 1926-1930, 2020.
35. Wei J., Mi L., Hu Y., Ling J., Li Y., andChen Z.Effects of Lossy Compression on Remote Sensing Image Classification based on Convolutional Sparse Coding. IEEE Geoscience and Remote Sensing Letters, vol. 19, pp. 1-5, 2021.
36. Huang X., Sun Y., Feng S., Ye Y., andLi X.Better Visual Interpretation for Remote Sensing Scene Classification. IEEE Geoscience and Remote Sensing Letters, vol. 19, pp. 1-5, 2021.
37. Liu S.J., Luo H., andShi Q.Active Ensemble Deep Learning for Polarimetric Synthetic Aperture Radar Image Classification. IEEE Geoscience and Remote Sensing Letters, vol. 18, no. 9, pp. 1580-1584, 2020.
38. Shi J., Liu W., Shan H., Li E., Li X., andZhang L.Remote Sensing Scene Classification based on Multibranch Fusion Attention Network. IEEE Geoscience and Remote Sensing Letters, vol. 20, pp. 1-5, 2023.
39. Maxwell A.E., Warner T.A., andFang F.Implementation of Machine-Learning Classification in Remote Sensing: An Applied Review. International journal of remote sensing, vol. 39, no. 9, pp. 2784-2817, 2018.
40. Dou, P. and Chen, Y.Remote Sensing Imagery Classification using AdaBoost with a Weight Vector (WV AdaBoost). Remote Sensing Letters, vol. 8, no. 8, pp. 733-742, 2017.
41. Bera, S. and Shrivastava, V.K.Analysis of Various Optimizers on Deep Convolutional Neural Network Model in the Application of Hyperspectral Remote Sensing Image Classification. International Journal of Remote Sensing, vol. 41, no. 7, pp. 2664-2683, 2020.

[1]	Pancham Singh, Updesh Kumar Jaiswal, Eshank Jain, Nikhil Kumar, and Vimlesh Mishra. A Novel Methodology Utilizing Modern CCTV Cameras and Software as a Service Model for Crime Detection and Prediction [J]. Int J Performability Eng, 2025, 21(2): 112-121.
[2]	Seema Kalonia and Amrita Upadhyay. Comparative Analysis of Machine Learning Model and PSO Optimized CNN-RNN for Software Fault Prediction [J]. Int J Performability Eng, 2025, 21(1): 48-55.
[3]	Manu Banga. Enhancing Software Fault Prediction using Machine Learning [J]. Int J Performability Eng, 2024, 20(9): 529-540.
[4]	Aditya Dayal Tyagi, and Krishna Asawa. Influence Maximization in Social Network using Community Detection and Node Modularity [J]. Int J Performability Eng, 2024, 20(9): 552-562.
[5]	Ekta Singh, and Parma Nand. Efficient Multi-Class Facial Emotion Recognition using YOLOv9: A Deep Learning Approach for Real-Time Applications [J]. Int J Performability Eng, 2024, 20(9): 581-590.
[6]	Manpreet Singh, Gauri Jindal, Akshita Oberoi, and Rohan Dhangar. Improving Crime Detection Through Geo-MDA: A Hybrid Linear Regression Approach in Data Mining [J]. Int J Performability Eng, 2024, 20(8): 469-477.
[7]	Nilesh Shelke, Deepali Sale, Sagar Shinde, Atul Kathole, and Rachna Somkunwar. A Comprehensive Framework for Facial Emotion Detection using Deep Learning [J]. Int J Performability Eng, 2024, 20(8): 487-497.
[8]	Kalyani H. Deshmukh, Gajendra R. Bamnote, and Pratik K Agrawal. A Novel Approach for Drought Monitoring and Evaluation using Time Series Analysis and Deep Learning [J]. Int J Performability Eng, 2024, 20(8): 498-509.
[9]	Lakshya Vaswani, Sai Sri Harsha, Subham Jaiswal, and Aju D. Unravelling Complexity: Investigating the Effectiveness of SHAP Algorithm for Improving Explainability in Network Intrusion System Across Machine and Deep Learning Models [J]. Int J Performability Eng, 2024, 20(7): 421-431.
[10]	Rohit Kumar Verma and Sukhvir Singh. A Hybrid Framework of Resource Allocation using Firefly and Deep Learning in Big Data Scheduling [J]. Int J Performability Eng, 2024, 20(6): 333-343.
[11]	Vikas Verma, Arun Malik, and Isha Batra. Analyzing and Classifying Malware Types on Windows Platform using an Ensemble Machine Learning Approach [J]. Int J Performability Eng, 2024, 20(5): 312-318.
[12]	Priya Singh and Rajalakshmi Krishnamurthi. AgriGuard: IoT-Powered Real-Time Object Detection and Alert System for Intelligent Surveillance [J]. Int J Performability Eng, 2024, 20(4): 232-241.
[13]	Ujjwal Deep, Sushant Kumar, and Kanika Singla. Integrating Deep Learning Architectures for Enhanced Human Action Recognition: An Ensemble Approach [J]. Int J Performability Eng, 2024, 20(4): 253-262.
[14]	Manu Jyoti Gupta and Parveen Sehgal. Optimizing Credit Card Fraud Detection: Classifier Performance and Feature Selection Empowered by Grasshopper Algorithm [J]. Int J Performability Eng, 2024, 20(3): 177-185.
[15]	Atul Kumar and Gurpreet Singh Lehal. Layout Detection of Punjabi Newspapers using the YOLOv8 Model [J]. Int J Performability Eng, 2024, 20(3): 186-193.