Nowadays more and more elderly people are suffering from Alzheimer’s disease (AD). Finely recognizing mild cognitive impairment (MCI) in early stage of the symptom is vital for AD therapy. However, brain image samples are relatively scarce, meanwhile have multiple modalities, which makes finely classifying brain images by computers extremely difficult. This paper proposes a fine-grained brain image classification approach for diagnosing Alzheimer’s disease, with re-transfer learning and multi-modal learning. First of all, an end-to-end deep neural network classifier CNN4AD is designed to finely classify diffusion tensor image (DTI) into four categories. And according to the characteristics of multi-modal brain image dataset, the re-transfer learning method is proposed based on transfer learning and multi-modal learning theories. Experimental results show that the proposed approach obtain higher accuracy with less labeled training samples. This could help doctors diagnose Alzheimer’s disease more timely and accurately.
相似文献Alzheimer’s disease (AD) is an irreversible and progressive brain disease causing brain degenerative disorder and dementia. An early diagnosis of AD provides the individual an opportunity to participate in clinical trials. Computer Aided Diagnosis (CAD) system in the health care sector has been widely used and plays an important role in detecting such diseases. However, the main challenge of such systems is through identifying the region of interest obtained through precise segmentation. This paper attempts to solve the segmentation issue by developing a precise image segmentation model. The proposed model used a derivation of a hybrid cross entropy thresholding technique for the precise extraction of infected regions. In other words, a novel segmentation methodology has been proposed using the output derivation of both Gamma and Gaussian distributions. Moreover, to tackle the performance and time-consuming problems in digital image segmentation, a parallel boosting methodology has been developed and implemented. Through using the ADNI, OASIS, and MIRIAD benchmark datasets, the experimentation results validate the effectiveness of the proposed model through achieving more than 90% accuracy with 2x times speed improvement compared to other benchmark segmentation methods.
相似文献This paper proposes a neural approximation based model predictive control approach for tracking control of a nonholonomic wheel-legged robot in complex environments, which features mechanical model uncertainty and unknown disturbances. In order to guarantee the tracking performance of wheel-legged robots in an uncertain environment, effective approaches for reliable tracking control should be investigated with the consideration of the disturbances, including internal-robot friction and external physical interactions in the robot’s dynamical system. In this paper, a radial basis function neural network (RBFNN) approximation based model predictive controller (NMPC) is designed and employed to improve the tracking performance for nonholonomic wheel-legged robots. Some demonstrations using a BIT-NAZA robot are performed to illustrate the performance of the proposed hybrid control strategy. The results indicate that the proposed methodology can achieve promising tracking performance in terms of accuracy and stability.
相似文献
Alzheimer is an advanced nervous brain disease. In old aged people, Alzheimer is also causing the death. The earlier prediction of Alzheimer’s disease (AD) helps to proper treatment and protects from brain tissue damages. In earlier works, different machine learning techniques are presented and the techniques are lacks in the detection performance. This work presented an innovative methodology for the Alzheimer detection in brain image. Initially, an input image is pre-processed by the skull stripping, and normalized linear smoothing and median joint (NLSMJ) filtering. In the next stage, grey matter (GM), white matter (WM) and cerebrospinal fluid (CSF) brain regions are segmented from the filtered images using adaptive fuzzy based atom search optimizer which is the high convergence rate optimizer for enhancing the segmentation performance. After the image segmentation, GM is registered with the filtered images using the improved affine transformation. Subsequently, features are extracted utilizing improved Zernike features and hybrid wavelet walsh features. Afterwards, features are selected utilizing adaptive rain optimization. Finally, hybrid equilibrium optimizer with capsule auto encoder (HEOCAE) framework is utilized for the detection of Alzheimer, normal and mild cognitive impairment images. The implementation platform used in this work is MATLAB. The presented technique is tested with the ADNI dataset images. The experimental results of the presented technique provide improved performance than the existing techniques in regards of accuracy (98.21%), sensitivity (97.31%), specificity (98.64%), precision (97.45%), NPV (0.098), F1 measure (97.37%) and AUC score (98.29%).
相似文献In a conventional steering system for a multi-axle crane, the steering angle of each axle is determined according to Ackermann’s steering principle, which minimizes the slip angles of the tires. The role of optimal steering control in improving a driver’s steering efficiency is hardly considered in Ackermann’s principle. To address this problem, this paper proposes a control strategy for determining the optimal steering angles for a multi-axle crane and thereby improving a driver’s steering efficiency by applying the model predictive control (MPC) algorithm and defining a driver’s intentions. A simplified crane model for the steering system was developed using a bicycle model, and a comparative study was carried out via simulation to analyze steering performance for the conventional (Ackermann) and proposed steering control systems for the cases of all-wheel steering and road steering modes. The simulation results show that both the minimum turning radius and the driver’s steering effort are decreased more by the proposed steering control system than by conventional system and that the proposed control strategy therefore yields better steering performance.
相似文献In machine learning, image classification accuracy generally depends on image segmentation and feature extraction methods with the extracted features and its qualities. The main focus of this paper is to determine the defected area of mangoes using image segmentation algorithm for improving the classification accuracy. The Enhanced Fuzzy based K-means clustering algorithm is designed for increasing the efficiency of segmentation. Proposed segmentation method is compared with K-means and Fuzzy C-means clustering methods. The geometric, texture and colour based features are used in the feature extraction. Process of feature selection is done by Maximally Correlated Principal Component Analysis (MCPCA). Finally, in the classification step, severe portions of the affected area are analyzed by Backpropagation Based Discriminant Classifier (BBDC). Proposed classifier is compared with BPNN and Naive Bayes classifiers. The images are classified into three classes in final output like Class A –good quality mango, Class B-average quality mango, and Class C-poor quality mango. Finally, the evaluated results of the proposed model examine various defected and healthy mango images and prove that the proposed method has the highest accuracy when compared with existing methods.
相似文献This study presents an alternative global localization scheme that uses dual laser scanners and the pure rotational motion of a mobile robot. The proposed method extracts the initial state of the robot’s surroundings to select robot pose candidates, and determines the sample distribution based on the given area map. Localization success is determined by calculating the similarity of the robot’s sensor state compared to that which would be expected at the estimated pose on the given map. In both simulations and experiments, the proposed method shows sufficient efficiency and speed to be considered robust to real-world conditions and applications.
相似文献Prevention and treatment of diseases are critical to improve grape yield and quality. Automatic identification of grape diseases is important to prevent insect pests timely and effectively. This study proposed an automatic detection method for grape leaf diseases based on image analysis and back–propagation neural network (BPNN). The Wiener filtering method based on wavelet transform was applied to denoise the disease images. The grape leaf disease regions were segmented by Otsu method, and morphological algorithms were used to improve the lesion shape. Prewitt operator was utilized to extract the complete edge of lesion region. Five effective characteristic parameters, namely, perimeter, area, circularity, rectangularity, and shape complexity, were extracted. The proposed recognition model for grape leaf diseases based on BPNN could efficiently inspect and recognize five grape leaf diseases: leaf spot, Sphaceloma ampelinum de Bary, anthracnose, round spot, and downy mildew. Results indicated that the proposed detection system for grape leaf diseases could be used to inspect grape diseases with high classification accuracy.
相似文献The electrocardiogram (ECG) has been proven to be the most common and effective approach to investigate cardiovascular diseases because that it is simple, noninvasive and inexpensive. However, the differences among ECG signals are difficult to be distinguished. In this paper, hand-engineered ECG features and automatic ECG features extracted with deep neural networks are combined to generate high dimensional features. First, rich hand-engineered features were extracted using some extraction methods for common ECG features. Second, a convolutional neural network model was designed to extract the ECG features automatically. High dimensional feature set is obtained through combing hand-engineered features and automatic features. To get the most informative ECG feature combination, a feature selection method based on mutual information was proposed. An ensemble learning method was then used to build the classification model for abnormal ECG types. Six atrial arrhythmia subtypes’ ECG signals from the Chinese cardiovascular disease database dataset were analyzed through the proposed method. The precision of the classification results reaches 98.41%, which is higher than the results based on other current methods.
相似文献