In recent years, with the continuous exploration of NNs and the upgrading of mobile phone hardware, more and more researches focus on how to design effective models to suort terminal task reasoning. IC is a classic task in many studies. It can be used in many fields such as image search, face recognition, and medical imaging. It has great practical significance in reality. The main purpose of this paper is to carry out optimization research on the classification algorithm of multiple image formats based on the suort of complex NN models (NNM). This paper proposes improved methods for problem transformation and model adaptation, and studies the problems of blurred scenes and difficult method selection in multi-format image classification (IC). In the direction of problem transformation, a basic classification model and a classification model combined with advanced strategies are designed., in the direction of model adaptation, transform multi-format output and use transfer learning for training. Finally, it is found that the problem transformation method can obtain better classification results in small data sets, but the classification time is several times as long as the model adaptation method. The model adaptation method can save a lot of time and is easier to promote.

Romany Jalali. Classification Algorithm for Multiple Image Formats Suorting Complex Neural Network Models. International Journal of Neural Network (2021), Vol. 2, Issue 3: 53-61. https://doi.org/10.38007/NN.2021.020307.

[1] Puthongkham P, Wirojsaengthong S, Sueangam A. Machine Learning and Chemometrics for Electrochemical Sensors: Moving Forward To the Future of Analytical Chemistry. The Analyst. (2021) 146(21):6351-6364. https://doi.org/10.1039/D1AN01148K

[2] Hanif A M, Beqiri S, Keane P A, et al. Alications of Interpretability in Deep Learning Models for Ophthalmology. Current Opinion in Ophthalmology. (2021) 32(5):452-458. https://doi.org/10.1097/ICU.0000000000000780

[3] Ansari A S, Mohammadi M S, Parvez M T. A Multiple-Format Steganography Algorithm for Color Images. IEEE Access. (2020) (99):1-1. https://doi.org/10.1109/ACCESS.2020.2991130

[4] Devi T, Darwin P. Hyper Spectral Fruit IC for Deep Learning Aroaches and NN Techniques. International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems. (2021) 30(03):357-383. https://doi.org/10.1142/S0218488522400116

[5] Suguna G, Lavanya R. Performance Assessment of EyeNet Model in Glaucoma Diagnosis. Pattern Recognition and Image Analysis. (2021) 31(2):334-344. https://doi.org/10.1134/S1054661821020164

[6] Oliveira J, Silva E G, Neto P. A Hybrid System Based on Dynamic Selection for Time Series Forecasting. IEEE Transactions on NNs and Learning Systems. (2021) (99):1-13.

[7] Himanshu Aneja Deepanshu Jindal and Ajay Tiwari Utkarsh Pandey. Comparative study of IC Algorithms. International Journal for Modern Trends in Science and Technology. (2021) 7(1):88-92. https://doi.org/10.46501/IJMTST070120

[8] Kobayashi M. Synthesis of Complex- and Hyperbolic-Valued Hopfield NNs. Neurocomputing. (2021) 423(4):80-88. https://doi.org/10.1016/j.neucom.2020.10.002

[9] Yosefvand F, Rajabi A, Shabanlou S. Predicting Non-deposition Sediment Transport in Clean Pipes: Assessing Heuristic Models. Iranian Journal of Science and Technology, Transactions of Civil Engineering. (2021) 46(1):615-629. https://doi.org/10.1007/s40996-021-00766-w

[10] Yasin Q, M Majdański, Sohail G M, et al. Fault and Fracture Network Characterization Using Seismic Data: a Study Based on NNMS Assessment. Geomechanics and Geophysics for Geo-Energy and Geo-Resources. (2021) 8(2):1-26. https://doi.org/10.1007/s40948-022-00352-y

[11] Poloziuk K, Yaremenko V. NNs and Monte-Carlo Method Usage in Multi-Agent Systems for Sudoku Problem Solving. Technology Audit and Production Reserves. (2020) 6(2(56)):38-41. https://doi.org/10.15587/2706-5448.2020.218427

[12] Jassim M S, Coskuner G, Zontul M. Comparative Performance Analysis of Suort Vector Regression and Artificial NN for Prediction of Municipal Solid Waste Generation:. Waste Management & Research. (2021) 40(2):195-204. https://doi.org/10.1177/0734242X211008526

[13] Chatterjee O, Chakrabartty S. Resonant Machine Learning Based on Complex Growth Transform Dynamical Systems. IEEE Transactions on NNs and Learning Systems. (2020) (99):1-15.

[14] Hewage P, Trovati M, Pereira E, et al. Deep Learning-Based Effective Fine-Grained Weather Forecasting Model. Pattern Analysis and Alications. (2021) 24(1):343-366. https://doi.org/10.1007/s10044-020-00898-1

[15] Huynh P H, Nguyen V H, Do T N. Improvements in the Large p, Small n Classification Issue. SN Computer Science. (2020) 1(4):1-19. https://doi.org/10.1007/s42979-020-00210-2

[16] Raziani S, Ahmadian S, Jalali S, et al. An Efficient Hybrid Model Based on Modified Whale Optimization Algorithm and Multilayer Perceptron NN for Medical Classification Problems. Journal of Bionic Engineering. (2021) 19(5):1504-1521. https://doi.org/10.1007/s42235-022-00216-x

[17] Ekici B, Kazanasmaz Z T, Turrin M, et al. Multi-zone Optimisation of High-Rise Buildings Using Artificial Intelligence for Sustainable Metropolises. Part 1: Background, Methodology, Setup, and Machine Learning Results. Solar Energy. (2021) 224(2):373-389. https://doi.org/10.1016/j.solener.2021.05.083

[18] Vadiati M, Yami Z R, Eskandari E, et al. Alication of Artificial Intelligence Models for Prediction of Groundwater Level Fluctuations: Case Study (Tehran-Karaj alluvial aquifer). Environmental Monitoring and Assessment. (2021) 194(9):1-21. https://doi.org/10.1007/s10661-022-10277-4