Three-Category Classification of Magnetic Resonance Hearing Loss Images Based on Deep Autoencoder

Abstract

Hearing loss, a partial or total inability to hear, is known as hearing impairment. Untreated hearing loss can have a bad effect on normal social communication, and it can cause psychological problems in patients. Therefore, we design a three-category classification system to detect the specific category of hearing loss, which is beneficial to be treated in time for patients. Before the training and test stages, we use the technology of data augmentation to produce a balanced dataset. Then we use deep autoencoder neural network to classify the magnetic resonance brain images. In the stage of deep autoencoder, we use stacked sparse autoencoder to generate visual features, and softmax layer to classify the different brain images into three categories of hearing loss. Our method can obtain good experimental results. The overall accuracy of our method is 99.5%, and the time consuming is 0.078 s per brain image. Our proposed method based on stacked sparse autoencoder works well in classification of hearing loss images. The overall accuracy of our method is 4% higher than the best of state-of-the-art approaches.

Predict Physics Achievement in Middle School Education by Big Five Model and Artificial Neural Network

“…The convolutional neural network [30][31][32] and auto encoders [33][34][35] are two common models in deep learning.…”

Teeth Classification Based on Haar Wavelet Transform and Support Vector Machine

“…Finally, the proposed SVM method could yield the greatest accuracy of 81.83± 1.79%. Although SVM obtained good results, we shall try to collect more data than used in this study, and tested the effect of deep learning, such as convolutional neural network [34][35][36], deep belief network [37], and autoencoder [38,39].…”

Ridge–based curvilinear structure detection for identifying road in remote sensing image and backbone in neuron dendrite image

“…It is obvious that the result of proposed RCSD is closer to the ground truth result. Although this RCSD was developed for curvilinear structure detection, it may be used in other academic and industrial fields, such as traffic sign detection [32], pathological brain detection [33,34], path planning [35,36], hearing loss detection [37], tea category identification [38][39][40], breast cancer detection [41], multiple sclerosis detection [42], cerebral microbleeding identification [43], etc.…”