Welcome to Scholar Publishing Group

International Journal of Neural Network, 2022, 3(4); doi: 10.38007/NN.2022.030401.

Neural Network Classifier Improvements Based on Ant Colony Algorithm


Amar Sadia

Corresponding Author:
Amar Sadia

Jimma University, Ethiopia


Compared with other classifiers, neural network (NN) classifiers are faster and have more advantages. However, the NN classifier is unique, because the number of features often changes when selecting features and the classifier is classified by the number of hidden layer nodes, and a NN with a fixed number of hidden layer nodes is used to evaluate different types of feature subsets obviously inappropriate. Therefore, the NN classifier is optimized, and the ant colony optimization (ACO) algorithm is introduced to obtain a diverse solution, which will be faster than the NN classifier to avoid it falling into the problem of local solutions. As a classic feedforward NN, BP neural network (BPNN) is currently the most widely used NN for classification problems. Therefore, this paper constructs a BPNN classifier. By comparing the traditional BPNN classifier and the improved ACO-BPNN classifier on malicious web page detection and classification effects of different sizes of data sets, the results show that, compared with the traditional BPNN classification model, ACO-BPNN The classification accuracy of the BPNN classification model is higher and the classification effect is better.


nt Colony Algorithm, Neural Network Classifier, Classification Effect, BP Neural Network

Cite This Paper

Amar Sadia. Neural Network Classifier Improvements Based on Ant Colony Algorithm. International Journal of Neural Network (2022), Vol. 3, Issue 4: 1-8. https://doi.org/10.38007/NN.2022.030401.


[1] Alotaibi A, Hamdaoui R. Improvement of Semi-Supervised Document Classification based on Fine Tuning Naive Bayesian Classifier. European Journal of Scientific Research, 2021, 158(3):181-190.

[2] Adams J W, Zhang Z, Noetscher G M, et al. Application of a NN Classifier to Radiofrequency-Based Osteopenia/Osteoporosis Screening. IEEE Journal of Translational Engineering in Health and Medicine, 2021, PP(99):1-1. https://doi.org/10.1109/JTEHM.2021.3108575

[3] Ghazikhani H, Rouhani M. A Deep NN Classifier for P300 BCI Speller Based on Cohen's Class Time-Frequency Distribution. Turkish Journal of Electrical Engineering and Computer Sciences, 2021, 29(2):1226-1240. https://doi.org/10.3906/elk-2005-201

[4] Azzam R, Kong F H, Taha T, et al. Pose-Graph NN Classifier for Global Optimality Prediction in 2D SLAM. IEEE Access, 2021, PP(99):1-1. https://doi.org/10.1109/ACCESS.2021.3084599

[5] Pamela V. An Efficient Intrusion Detection System Using Improved Bias Based Convolutional NN Classifier. Turkish Journal of Computer and Mathematics Education (TURCOMAT), 2021, 12(6):2468-2482. https://doi.org/10.17762/turcomat.v12i6.5689

[6] Sedova N, Sedov V, Bazhenov R, et al. NN Classifier for Automatic Course-Keeping Based on Fuzzy Logic. Journal of Intelligent and Fuzzy Systems, 2021, 40(2):1-12. https://doi.org/10.3233/JIFS-201495

[7] Gautam S, Singhai J. Cosine-similarity watershed algorithm for water-body segmentation applying deep NN classifier. Environmental Earth Sciences, 2021, 81(9):1-16. https://doi.org/10.1007/s12665-022-10376-y

[8] Oluwole A H , Ositola O M , Olufisayo O , et al. Women's Behavioral Patterns in Domestic Tasks in Western Nigeria: Hazards Forecasting with NN Classifier . Journal of International Women's Studies, 2020, 21(1):241-254.

[9] Masuda H , Nakai T , Yoshida K , et al. Black-Box Adversarial Attack against Deep NN Classifier Utilizing Quantized Probability Output. Journal of Signal Processing, 2020, 24(4):145-148. https://doi.org/10.2299/jsp.24.145

[10] Zadkarami M , Safavi A A , Taheri M , et al. Data driven leakage diagnosis for oil pipelines: An integrated approach of factor analysis and deep NN classifier:. Transactions of the Institute of Measurement and Control, 2020, 42(14):2708-2718. https://doi.org/10.1177/0142331220928145

[11] Shahin I, Nassif A B. Novel Cascaded Gaussian Mixture Model-Deep NN Classifier For Speaker Identification in Emotional Talking Environments. Neural Computing and Applications, 2020, 32(7):2575-2587. https://doi.org/10.1007/s00521-018-3760-2

[12] Giveki D, Rastegar H, Karami M. Erratum to: A New NN Classifier Based on Atanassov's Intuitionistic Fuzzy Set Theory. Optical Memory and NNs, 2019, 28(3):237-237. https://doi.org/10.3103/S1060992X19030111

[13] Abdullah S M. A Deep NN Classifier for Android Malwares Detection using Feature Combination. Journal of Engineering and Applied Sciences, 2019, 14(23):8761-8768. https://doi.org/10.36478/jeasci.2019.8761.8768

[14] Daud K, Abidin A F, Ismail A P, et al. Evaluating Windowing-Based Continuous S-Transform with NN Classifier for Detecting and Classifying Power Quality Disturbances. Indonesian Journal of Electrical Engineering and Computer Science, 2019, 13(3):1136-1142. https://doi.org/10.11591/ijeecs.v13.i3.pp1136-1142

[15] Jayanthi S, Vennila C. Advanced Satellite Image Classification of Various Resolution Image Using a Novel Approach of Deep NN Classifier. Wireless Personal Communications, 2019, 104(1):357-372. https://doi.org/10.1007/s11277-018-6024-7

[16] Hidayat A A, Purwandari K, Cenggoro T W, et al. A Convolutional NN-based Ancient Sundanese Character Classifier with Data Augmentation. Procedia Computer Science, 2021, 179(2):195-201. https://doi.org/10.1016/j.procs.2020.12.025

[17] Anjani S, Ch S. An efficient facial emotion recognition system using novel deep learning nn-regression activation classifier. Multimedia Tools and Applications, 2021, 80(6):1-26. https://doi.org/10.1007/s11042-021-10547-2

[18] Satti S K, Devi K S, Dhar P, et al. Detecting Potholes on Indian Roads Using Haar Feature-Based Cascade Classifier, Convolutional NN, And Instance Segmentation. Soft Computing, 2021, 26(18):9141-9153. https://doi.org/10.1007/s00500-022-07265-8

[19] Madhusudhana S K, Symes L B, Klinck H. A Deep Convolutional NN Based Classifier for Passive Acoustic Monitoring Of Neotropical Katydids. The Journal of the Acoustical Society of America, 2019, 146(4):2982-2982. https://doi.org/10.1121/1.5137323