Deep Convolutional Neural Network Features Research Articles

An Instrument Indication Acquisition Algorithm Based on Lightweight Deep Convolutional Neural Network and Hybrid Attention Fine-Grained Features

An Instrument Indication Acquisition Algorithm Based on Lightweight Deep Convolutional Neural Network and Hybrid Attention Fine-Grained Features

Classification of deep learning convolutional neural network feature extraction for student graduation prediction

<span>One indicator of a university’s educational quality is the proportion of enrolled students who actually graduate within four years. This proportion is typically fewer than the number of students that enroll in a given year. A low graduation rate can have a negative impact on both the university’s reputation and its accreditation because it indicates that fewer students are completing their degrees. Student activity, economic, and other issues all play a role in why some students are unable to complete their degrees on time. As a result, stakeholders need a model that can predict whether or not students will graduate on time as a means of evaluating and giving a basis for policy actions. This research proposes a model for converting textual data into an image format using a deep learning convolutional neural network (CNN), and then classifying the extracted features using a variety of machine learning classification algorithms like the decision tree, random forest, Naive Bayes, support vector machine (SVM), and k-nearest neighbor (K-NN). The classification model trained on feature extraction data had a 96.1% accuracy rate, while the classification model trained on the original data achieved a 71.2% accuracy rate.</span>

Effects of Aging on Successful Object Encoding: Enhanced Semantic Representations Compensate for Impaired Visual Representations.

Whereas episodic memory and visual processing decline substantially with healthy aging, semantic knowledge is generally spared. There is evidence that older adults' spared semantic knowledge can support episodic memory. Here, we used fMRI combined with representational similarity analyses (RSA) to examine how novel visual and pre-existing semantic representations at encoding predict subjective memory vividness at retrieval. Eighteen young and seventeen older adults (female and male participants) encoded images of objects during fMRI scanning and recalled these images while rating the vividness of their memories. After scanning, participants discriminated between studied images and similar lures. RSA based on a deep convolutional neural network and normative concept feature data was used to link patterns of neural activity during encoding to visual and semantic representations. Relative to young adults, the specificity of activation patterns for visual features was reduced in older adults, consistent with dedifferentiation. However, the specificity of activation patterns for semantic features was enhanced in older adults, consistent with hyperdifferentiation. Despite dedifferentiation, visual representations in early visual cortex predicted high memory vividness in both age groups. In contrast, semantic representations in lingual and fusiform gyrus were associated with high memory vividness only in the older adults. Intriguingly, data suggests that older adults with lower specificity of visual representations in combination with higher specificity of semantic representations tended to rate their memories as more vivid. Our findings suggest that memory vividness in aging relies more on semantic representations over anterior regions, potentially compensating for age-related dedifferentiation of visual information in posterior regions.Significance StatementNormal aging is associated with impaired memory for events while semantic knowledge might even improve. We investigated the effects of aging on the specificity of visual and semantic information in the brain when viewing common objects and how this information enables subsequent memory vividness for these objects. Using fMRI combined with modeling of the stimuli, we found that visual information was represented with less specificity in older than young adults, while still supporting memory vividness. In contrast, semantic information supported memory vividness only in older adults, and especially in those individuals that had the lowest specificity of visual information. These findings provide evidence for a spared semantic memory system increasingly recruited to compensate for degraded visual representations in older age.

A UNIFIED PARADIGM OF CLASSIFYING GI TRACT DISEASES IN ENDOSCOPY IMAGES USING MULTIPLE FEATURES FUSION

The automatic identification of Gastrointestinal (GI) tract diseases in endoscopy images has been associated with the domain of medical imaging and computer vision. Its classification has various challenges, including color, low contrast, lesion shape, and complex background. A Deep features-based method for the classification of gastrointestinal disease is implemented in this article. The method suggested involves four significant steps: preprocessing, extraction of handcrafted, and deep Convolutional neural network features (Deep CNN), selection of solid features, fusion, and classification. 3D-Median filtering in the preprocessing stage increases the lesion contrast. The second stage extracts the features centered on the shape. The extracted features are of three types: HOG features, ResNet50, and Xception. Principal Component Analysis (PCA) is chosen to select extracted features, combined by concatenating them in a single array. A support vector system eventually categorizes fused features into multiple classes. The Kvasir dataset is used for the proposed model. The SVM has outstanding efficiency reached 96.6 percent, showing the proposed system's robustness

Patient Identification Based on Deep Metric Learning for Preventing Human Errors in Follow-up X-Ray Examinations

Biological fingerprints extracted from clinical images can be used for patient identity verification to determine misfiled clinical images in picture archiving and communication systems. However, such methods have not been incorporated into clinical use, and their performance can degrade with variability in the clinical images. Deep learning can be used to improve the performance of these methods. A novel method is proposed to automatically identify individuals among examined patients using posteroanterior (PA) and anteroposterior (AP) chest X-ray images. The proposed method uses deep metric learning based on a deep convolutional neural network (DCNN) to overcome the extreme classification requirements for patient validation and identification. It was trained on the NIH chest X-ray dataset (ChestX-ray8) in three steps: preprocessing, DCNN feature extraction with an EfficientNetV2-S backbone, and classification with deep metric learning. The proposed method was evaluated using two public datasets and two clinical chest X-ray image datasets containing data from patients undergoing screening and hospital care. A 1280-dimensional feature extractor pretrained for 300 epochs performed the best with an area under the receiver operating characteristic curve of 0.9894, an equal error rate of 0.0269, and a top-1 accuracy of 0.839 on the PadChest dataset containing both PA and AP view positions. The findings of this study provide considerable insights into the development of automated patient identification to reduce the possibility of medical malpractice due to human errors.

An efficient and robust Phonocardiography (PCG)-based Valvular Heart Diseases (VHD) detection framework using Vision Transformer (ViT)

Background and objectives:Valvular heart diseases (VHDs) are one of the dominant causes of cardiovascular abnormalities that have been associated with high mortality rates globally. Rapid and accurate diagnosis of the early stage of VHD based on cardiac phonocardiogram (PCG) signal is critical that allows for optimum medication and reduction of mortality rate. Methods:To this end, the current study proposes novel deep learning (DL)-based high-performance VHD detection frameworks that are relatively simpler in terms of network structures, yet effective for accurately detecting multiple VHDs. We present three different frameworks considering both 1D and 2D PCG raw signals. For 1D PCG, Mel frequency cepstral coefficients (MFCC) and linear prediction cepstral coefficients (LPCC) features, whereas, for 2D PCG, various deep convolutional neural networks (D-CNNs) features are extracted. Additionally, nature/bio-inspired algorithms (NIA/BIA) including particle swarm optimization (PSO) and genetic algorithm (GA) have been utilized for automatic and efficient feature selection directly from the raw PCG signal. To further improve the performance of the classifier, vision transformer (ViT) has been implemented levering the self-attention mechanism on the time frequency representation (TFR) of 2D PCG signal. Our extensive study presents a comparative performance analysis and the scope of enhancement for the combination of different descriptors, classifiers, and feature selection algorithms. Main Results:Among all classifiers, ViT provides the best performance by achieving mean average accuracy Acc of 99.90 % and F1-score of 99.95 % outperforming current state-of-the-art VHD classification models. Conclusions:The present research provides a robust and efficient DL-based end-to-end PCG signal classification framework for designing a automated high-performance VHD diagnosis system.

An efficient method using the fusion of deep convolutional neural network features for cloud detection using Landsat-8 OLI spectral bands

An efficient method using the fusion of deep convolutional neural network features for cloud detection using Landsat-8 OLI spectral bands

Breast Tumor Classification in Ultrasound Images by Fusion of Deep Convolutional Neural Network and Shallow LBP Feature.

Breast cancer is one of the most dangerous and common cancers in women which leads to a major research topic in medical science. To assist physicians in pre-screening for breast cancer to reduce unnecessary biopsies, breast ultrasound and computer-aided diagnosis (CAD) have been used to distinguish between benign and malignant tumors. In this study, we proposed a CAD system for tumor diagnosis using a multi-channel fusion method and feature extraction structure based on multi-feature fusion on breast ultrasound (BUS) images. In the pre-processing stage, the multi-channel fusion method completed the color conversion of the BUS image to make it contain richer information. In the feature extraction stage, the pre-trained ResNet50 network was selected as the basic network, and three levels of features were combined based on adaptive spatial feature fusion (ASFF), and finally, the shallow local binary pattern (LBP) texture features were fused. Support vector machine (SVM) was used for comparative analysis. A retrospective analysis was carried out, and 1615 breast tumor images (572 benign and 1043 malignant) confirmed by pathological examinations were collected. After data processing and augmentation, for an independent test set consisting of 874 breast ultrasound images (457 benign and 417 malignant), the accuracy, precision, recall, specificity, F1 score, and AUC of our method were 96.91%, 98.75%, 94.72%, 98.91%, 0.97, and 0.991, respectively. The results show that the integration of shallow LBP texture features and multi-level depth features can more effectively improve the comprehensive performance of breast tumor diagnosis, and has strong clinical application value. Compared with the past methods, our proposed method is expected to realize the automatic diagnosis of breast tumors and provide an auxiliary tool for radiologists to accurately diagnose breast diseases.

Enhanced Face Presentation Attack Prevention Employing Feature Fusion of Pre-trained Deep Convolutional Neural Network Model and Thepade's Sorted Block Truncation Coding

The evolution and improvements of deep learning are being used to tackle any research obstacles that could be converted into classification problems in all spheres of life. Each Deep convolutional neural network (DCNN) design's output is determined by the depth and value of the hyperparameters, which explains why so many of them have been proposed. These DCNN architectures must be created entirely from scratch, and they can only be used for the applications for which they were intended. Transfer learning may be used to modify these pre-trained networks so they are more appropriate for particular purposes. This article aims to evaluate the empirical performance of the applicability of pre-trained DCNN models to identify human face presentation threats (FPAD). Human FPAD is one of the most significant and crucial areas of research right now because of the introduction of ambient computing, which necessitates contact-free identification of persons with the help of their biometric traits. Six pre-trained DCNN models are taken into account for an experimental evaluation in human FPAD alias VGG19, VGG16, DensNet121, MobileNet, Xception, and InceptionV3. The investigation makes use of the NUAA and Replay-Attack benchmark FPAD datasets. Thepade's sorted block truncation coding (SBTC) 10-ary features are merged with deep learning features produced from the finest performing finetuned DCNNs to enhance the FPAD capabilities of analyzed machine learning (ML) classifiers. The integration of features of Thepade's SBTC 10-ary and DCNN has considerably increased the FPAD accuracy of ML classifiers with slightly more computations of feature extraction.

Automated classification of protein expression levels in immunohistochemistry images to improve the detection of cancer biomarkers

BackgroundThe expression changes of some proteins are associated with cancer progression, and can be used as biomarkers in cancer diagnosis. Automated systems have been frequently applied in the large-scale detection of protein biomarkers and have provided a valuable complement for wet-laboratory experiments. For example, our previous work used an immunohistochemical image-based machine learning classifier of protein subcellular locations to screen biomarker proteins that change locations in colon cancer tissues. The tool could recognize the location of biomarkers but did not consider the effect of protein expression level changes on the screening process.ResultsIn this study, we built an automated classification model that recognizes protein expression levels in immunohistochemical images, and used the protein expression levels in combination with subcellular locations to screen cancer biomarkers. To minimize the effect of non-informative sections on the immunohistochemical images, we employed the representative image patches as input and applied a Wasserstein distance method to determine the number of patches. For the patches and the whole images, we compared the ability of color features, characteristic curve features, and deep convolutional neural network features to distinguish different levels of protein expression and employed deep learning and conventional classification models. Experimental results showed that the best classifier can achieve an accuracy of 73.72% and an F1-score of 0.6343. In the screening of protein biomarkers, the detection accuracy improved from 63.64 to 95.45% upon the incorporation of the protein expression changes.ConclusionsMachine learning can distinguish different protein expression levels and speed up their annotation in the future. Combining information on the expression patterns and subcellular locations of protein can improve the accuracy of automatic cancer biomarker screening. This work could be useful in discovering new cancer biomarkers for clinical diagnosis and research.

Robust thermal infrared tracking via an adaptively multi-feature fusion model.

When dealing with complex thermal infrared (TIR) tracking scenarios, the single category feature is not sufficient to portray the appearance of the target, which drastically affects the accuracy of the TIR target tracking method. In order to address these problems, we propose an adaptively multi-feature fusion model (AMFT) for the TIR tracking task. Specifically, our AMFT tracking method adaptively integrates hand-crafted features and deep convolutional neural network (CNN) features. In order to accurately locate the target position, it takes advantage of the complementarity between different features. Additionally, the model is updated using a simple but effective model update strategy to adapt to changes in the target during tracking. In addition, a simple but effective model update strategy is adopted to adapt the model to the changes of the target during the tracking process. We have shown through ablation studies that the adaptively multi-feature fusion model in our AMFT tracking method is very effective. Our AMFT tracker performs favorably on PTB-TIR and LSOTB-TIR benchmarks compared with state-of-the-art trackers.

Unifying Deep ConvNet and Semantic Edge Features for Loop Closure Detection

Loop closure detection is an important component of Simultaneous Localization and Mapping (SLAM). In this paper, a novel two-branch loop closure detection algorithm unifying deep Convolutional Neural Network (ConvNet) features and semantic edge features is proposed. In detail, we use one feature extraction module to extract both ConvNet and semantic edge features simultaneously. The deep ConvNet features are subjected to a Context Feature Enhancement (CFE) module in the global feature ranking branch to generate a representative global feature descriptor. Concurrently, to reduce the interference of dynamic features, the extracted semantic edge information of landmarks is encoded through the Vector of Locally Aggregated Descriptors (VLAD) framework in the semantic edge feature ranking branch to form semantic edge descriptors. Finally, semantic, visual, and geometric information is integrated by the similarity score fusion calculation. Extensive experiments on six public datasets show that the proposed approach can achieve competitive recall rates at 100% precision compared to other state-of-the-art methods.

Unsound wheat kernel recognition based on deep convolutional neural network transfer learning and feature fusion

 Unsound wheat kernel recognition is an important part of wheat quality inspection, and it is also a key indicator to measure wheat quality. Research on unsound wheat kernel recognition is of great significance to the correct evaluation of wheat quality. The existing researches on unsound wheat kernel recognition are mainly to directly optimize the classical classification networks, and the recognition effect is often unsatisfactory due to insufficient training data. Aiming at the problem that the recognition rate of unsound wheat kernels is not ideal due to the lack of training data, we propose a Transfer Learning Feature Fusion (TLFF) model. The model uses transfer learning and feature fusion to identify unsound wheat kernels. First, feature extraction is performed by deep Convolutional Neural Networks (CNNs) VGG-16 and VGG-19 pre-trained on the large public dataset ImageNet. Then, the features extracted by the pre-trained neural networks are fused and classified through the flattening layer, fully connected layer, Dropout layer, and Softmax layer. We conduct experiments on single model, two-model fusion, three-model fusion, and four-model fusion, and select the three-model fusion scheme to perform this task. Finally, we vote on the output results of the three best fusion models to further improve the recognition rate. The pre-trained models we use are trained on a large public dataset ImageNet. Since the scale of the dataset is very large, these pre-trained models also have good generalization performance for images other than ImageNet dataset. Therefore, although our dataset is small, we can still achieve good recognition results. Experimental results show that the recognition performance of the TLFF model is significantly better than the existing unsound wheat kernel recognition models.

A comprehensive analysis of dermoscopy images for melanoma detection via deep CNN features

Melanoma is the fastest growing and most lethal cancer among all forms of skin cancer. Deep learning methods, mainly convolutional neural networks (CNNs) have recently brought considerable attention in detecting skin cancers from dermoscopy images. However, learning valuable features by these methods has been challenging due to the inadequate training data, inter-class similarity, and intra-class variation in the skin lesions. In addition, most of these methods demand a considerable amount of parameters to tune. To address these issues, we present an automated framework that extracts visual features from dermoscopy images using a pre-trained deep CNN model and then employs a set of classifiers to detect melanoma. Recently, few pre-trained CNN architectures have been employed to extract deep features from skin lesions. However, a comprehensive analysis of such features derived from a variety of CNN architectures has not yet been performed for melanoma classification. Therefore, in this paper, we investigate the effectiveness of deep features extracted from eight contemporary CNN models. Also, we explore the impact of boundary localization and normalization techniques on melanoma detection. The suggested approach is evaluated using four benchmark datasets: PH2, ISIC 2016, ISIC 2017 and HAM10000. Experimental outcomes indicate that the DenseNet-121 with multi-layer perceptron (MLP) achieves a higher performance in terms of accuracy of 98.33%, 80.47%, 81.16% and 81% on PH2, ISIC 2016, ISIC 2017 and HAM10000 datasets compared to other CNN models and state-of-the-art methods.

Multi-modality MRI for Alzheimer's disease detection using deep learning.

Diffusion tensor imaging (DTI) is a new technology in magnetic resonance imaging, which allows us to observe the insightful structure of the human body in vivo and non-invasively. It identifies the microstructure of white matter (WM) connectivity by estimating the movement of water molecules at each voxel. This makes possible the identification of the damage to WM integrity caused by Alzheimer's disease (AD) at its early stage, called mild cognitive impairment (MCI). Furthermore, the brain's gray matter (GM) atrophy characterizes the main structural changes in AD, which can be sensitively detected by structural MRI (sMRI) modality. In this research, we aimed to classify the Alzheimer's diseases stages by developing a novel multi-modality MRI (DTI and sMRI) fusion strategy to detect WM alterations and GM atrophy in AD patients. The latter is based on a 2-dimensional deep convolutional neural network (CNN) features extractor and a support vector machine (SVM) classifier. The fusion framework consists of merging features extracted from DTI scalar metrics [(fractional anisotropy (FA) and mean diffusivity (MD)], and GM using 2D-CNN and feeding them to SVM to classify AD versus cognitively normal (CN), AD versus MCI, and MCI versus CN. Our novel multimodal AD method demonstrates a superior performance with an accuracy of 99.79%, 99.6%, and 97.00% for AD/CN, AD/MCI, and MCI/CN respectively.

Reliable Scene Recognition Approach for Mobile Robots with Limited Resources Based on Deep Learning and Neuro-Fuzzy Inference

Indoor scene recognition is complex due to the commonality shared between different spaces. Still, when it comes to robotics applications, the uncertainty increases due to illumination change, motion blur, interruption due to external light sources, and cluttered environments. Most existing fusion approaches do not consider the uncertainty, and others have a high computational cost that may not suit robots with limited resources. To mitigate these issues, this paper proposes a reliable indoor scene recognition approach for mobile robots with limited resources based on robust deep convolutional neural networks (CNNs) feature extractors and neuro-fuzzy inference to consider the uncertainty of the data. All CNN feature extractors are pre-trained on the Imagenet dataset and used in the manner of transfer learning. The performance of our fusion method has been assessed on a customized MIT-67 dataset and for real-time processing on a Locobot robot. We also compare the proposed method with two standard fusion methods---Early Feature Fusion (EFF) and Weighted Average Late Fusion (WALF). The experimental results demonstrate that our method achieves competitive results with a precision of 94%, and it performs well on the Locobot robot with a speed of 3.1 frames per second.

An efficient model of residual based convolutional neural network with Bayesian optimization for the classification of malarial cell images

BackgroundMalaria is a disease caused by the Plasmodium parasite, which results in millions of deaths in the human population worldwide each year. It is therefore considered a major global health issue with a massive disease burden. Accurate and rapid diagnosis of malaria is important for treatment. Rapid diagnosis of this disease will be very valuable for patients, as traditional methods require tedious work for its detection. The aim of the study is to classify malaria cell images using machine learning and deep learning methods. Material & methodsThe National Institutes of Health (NIH) database was used for malaria cell images classification as infected and uninfected, with a total of 27,558 malaria cell images used in the experimental study. Additionally, the training option parameters (initial learning rate, L2 regularization, and momentum values) of the Residual Convolutional Neural Network (CNN) were optimized using the Bayesian method. In the study, Residual CNN, k-Nearest Neighbors (k-NN), and Support Vector Machine (SVM) classifiers were used to classify the malaria cell images. Neighborhood Components Analysis (NCA) were observed to increase the performance of classifiers used in the classification of malaria cell images. Results and conclusionThe Accuracy (Acc), Sensitivity (Se), Specificity (Spe), and F-score were used as the performance metrics for the classifier performances. The best classification results were achieved with SVM (Acc 99.90%, Se 99.98%, Spe 87.50%, and F-Score 99.90%). As a result, a high level of classification performance was achieved from creating a hybrid model with Bayesian optimization and Deep Residual CNN features.

Brain programming is immune to adversarial attacks: Towards accurate and robust image classification using symbolic learning

In recent years, the security concerns about the vulnerability of Deep Convolutional Neural Networks (DCNN) to Adversarial Attacks (AA) in the form of small modifications to the input image almost invisible to human vision make their predictions untrustworthy. Therefore, it is necessary to provide robustness to adversarial examples in addition to an accurate score when developing a new classifier. In this work, we perform a comparative study of the effects of AA on the complex problem of art media categorization, which involves a sophisticated analysis of features to classify a fine collection of artworks. We tested a prevailing bag of visual words approach from computer vision, four state-of-the-art DCNN models (AlexNet, VGG, ResNet, ResNet101), and the Brain Programming (BP) algorithm. In this study, we analyze the algorithms' performance using accuracy. Besides, we use the accuracy ratio between adversarial examples and clean images to measure robustness. Moreover, we propose a statistical analysis of each classifier's predictions' confidence to corroborate the results. We confirm that BP predictions' change was below 2\% using adversarial examples computed with the fast gradient sign method. Also, considering the multiple pixel attack, BP obtained four out of seven classes without changes and the rest with a maximum error of 4\% in the predictions. Finally, BP also gets four categories using adversarial patches without changes and for the remaining three classes with a variation of 1\%. Additionally, the statistical analysis showed that the predictions' confidence of BP were not significantly different for each pair of clean and perturbed images in every experiment. These results prove BP's robustness against adversarial examples compared to DCNN and handcrafted features methods, whose performance on the art media classification was compromised with the proposed perturbations.

Real-time Vehicle Detection implementing Deep Convolutional Neural Network features Data Augmentation Technique

Background/Objectives: In this progressive Hi-Tech ecosystem, the cuttingedge technologies in the Deep Learning techniques for Vehicle Detection and Classification engendered swift paradigm shifts in diverse operations through the deployment of convolutional neural models in the Traffic Surveillance System. The fundamental element of the Traffic management system constitutes a real-time dynamic image, which forms the base input for vehicle recognition systems. The deep model functionalities on these base static images are highly pragmatic, and a radical approach leads to its successful applicability. Methods: This study proposes Faster Region-based Convolutional Neural Network (R-CNN) technique for image-based vehicle detection with significant performance benefits. Essentially, the base network of a pre-trained deep model, fine-tuned VGG-16 is transformed into Faster R-CNN. At this stage, the framework is constructed for a customized finitecapacity vehicle dataset. Subsequently, it is applied to train and test the system. From the performance lens, for further system enhancement, the speedup Bottleneck, and Data Augmentation implementation improve training speed and accuracy. Findings: The Experiments demonstrate that the sensitivity factor is 93.5% which provides acceptable results of 87.6% with 0.42s in vehicle detection in aspects of accuracy and execution time. Novelty : For our customized dataset, the performance-enhanced detection framework shows an increase of 4% in sensitivity and 3.23s with respect to time as compared to the other existing models. The proposed research is designed for a novel Faster RCNN algorithm that is fine-tuned detection algorithm of vehicles integrating sophisticated approaches for dynamic transformation of the live traffic video stream recording by transposing these real-time traffic videos to image inputs to this optimized detection framework achieving a high sensitivity factor with an efficient computation stack benefiting cost and time. Keywords: Data Augmentation; Deep Learning; Faster RegionConvolutional Neural Network; Traffic Surveillance System; VGG16 pretrained model; Vehicle Detection

Integrating the Reconstructed Scattering Center Feature Maps With Deep CNN Feature Maps for Automatic SAR Target Recognition

Automatic target recognition has been one of the hottest research in synthetic aperture radar (SAR) data processing. Noticing that popular recognition methods cannot utilize multiple features of SAR complex data, a method fused scattering center feature and deep convolutional neural network (CNN) feature is proposed in this letter. This method contains three key parts, namely, scattering center extraction and reconstruction block, CNN feature extraction block, and final feature fusion and classification block. In this process, the scattering center feature and CNN feature are fused at the level of feature maps, which retain the space information of 2-D feature maps. What is more, the proposed half end-to-end strategy realizes the automatic update of weighting parameters in feature extraction network and subnetwork, which promotes a better recognition efficiency. Experimental results on measured SAR data show that the proposed method can achieve better accuracy than other single feature-based methods and feature fusion methods.