The Image Classification Method with CNN-XGBoost Model Based on Adaptive Particle Swarm Optimization

Abstract

CNN is particularly effective in extracting spatial features. However, the single-layer classifier constructed by activation function in CNN is easily interfered by image noise, resulting in reduced classification accuracy. To solve the problem, the advanced ensemble model XGBoost is used to overcome the deficiency of a single classifier to classify image features. To further distinguish the extracted image features, a CNN-XGBoost image classification model optimized by APSO is proposed, where APSO optimizes the hyper-parameters on the overall architecture to promote the fusion of the two-stage model. The model is mainly composed of two parts: feature extractor CNN, which is used to automatically extract spatial features from images; feature classifier XGBoost is applied to classify features extracted after convolution. In the process of parameter optimization, to overcome the shortcoming that traditional PSO algorithm easily falls into a local optimal, the improved APSO guide the particles to search for optimization in space by two different strategies, which improves the diversity of particle population and prevents the algorithm from becoming trapped in local optima. The results on the image set show that the proposed model gets better results in image classification. Moreover, the APSO-XGBoost model performs well on the credit data, which indicates that the model has a good ability of credit scoring.

A Hybrid Deep Learning-Based (HYDRA) Framework for Multifault Diagnosis Using Sparse MDT Reports

“…Then we pass the extracted features to XGBoost which is computationally efficient as compared to the classification layer of CNN [38] and provides better accuracy when used as a hybrid [39], [40]. XGBoost takes the extracted features and performs fault diagnosis.…”

“…The tree-based nature and gradient boosting makes XGBoost yield superior results using fewer computing resources in the shortest amount of time. Time and computation efficiency is the reason we use XGBoost as a classification model of HYDRA instead of other ML models like artificial neural networks (ANN) [38], RNN, MLP, or extreme learning machines (ELM) [39], [40]. Furthermore, it gives more accurate results as compared to SVM and random forest.…”

DNS Request Log Analysis of Universities in Shanghai: A CDN Service Provider’s Perspective

“…XGBoost is an integrated decision tree algorithm in which new trees can correct the results of existing trees in the model so that the model can be made satisfactory by continuously adding decision trees. XGBoost is widely applicable and has been used by researchers for different prediction scenarios, such as image classification [36], intrusion detection [37], malicious account detection [38], and cross-site influential user identification [39]. LightGBM optimizes the temporal and spatial performance based on the traditional GBDT algorithm to speed up the training of GBDT models without compromising the accuracy and has been applied in movie box office prediction [40], credit scoring [41], and network traffic classification [42].…”

Emerging Trends in Deep Learning for Credit Scoring: A Review

“…The proposed algorithm achieved an AUC value of 0.803 for the German (numerical) dataset (see Table 9). Jiao et al [64] used the CNN-XGBoost model with adaptive particle swarm optimization (APSO) [68] to develop a credit scoring model and investigate classification performance. First, to eliminate the errors caused by data with self-variations or large differences in values, they preprocessed the original credit data.…”

“…Figure 14 shows that two DL-based classifiers are amongst the top five models with the highest accuracy for the German (numerical) dataset. Notably, the sixth-highest classifier is a hybrid of CNN and XGBoost [64]. The German (numerical) dataset is composed of 24 numerical attributes.…”