Pre-trained Deep Convolutional Neural Network Research Articles

An improved deep hashing model for image retrieval with binary code similarities

The exponential growth of data raises an unprecedented challenge in data analysis: how to retrieve interesting information from such large-scale data. Hash learning is a promising solution to address this challenge, because it may bring many potential advantages, such as extremely high efficiency and low storage cost, after projecting high-dimensional data to compact binary codes. However, traditional hash learning algorithms often suffer from the problem of semantic inconsistency, where images with similar semantic features may have different binary codes. In this paper, we propose a novel end-to-end deep hashing method based on the similarities of binary codes, dubbed CSDH (Code Similarity-based Deep Hashing), for image retrieval. Specifically, it extracts deep features from images to capture semantic information using a pre-trained deep convolutional neural network. Additionally, a hidden and fully connected layer is attached at the end of the deep network to derive hash bits by virtue of an activation function. To preserve the semantic consistency of images, a loss function has been introduced. It takes the label similarities, as well as the Hamming embedding distances, into consideration. By doing so, CSDH can learn more compact and powerful hash codes, which not only can preserve semantic similarity but also have small Hamming distances between similar images. To verify the effectiveness of CSDH, we evaluate CSDH on two public benchmark image collections, i.e., CIFAR-10 and NUS-WIDE, with five classic shallow hashing models and six popular deep hashing ones. The experimental results show that CSDH can achieve competitive performance to the popular deep hashing algorithms.

Enhanced PRIM recognition using PRI sound and deep learning techniques.

Pulse repetition interval modulation (PRIM) is integral to radar identification in modern electronic support measure (ESM) and electronic intelligence (ELINT) systems. Various distortions, including missing pulses, spurious pulses, unintended jitters, and noise from radar antenna scans, often hinder the accurate recognition of PRIM. This research introduces a novel three-stage approach for PRIM recognition, emphasizing the innovative use of PRI sound. A transfer learning-aided deep convolutional neural network (DCNN) is initially used for feature extraction. This is followed by an extreme learning machine (ELM) for real-time PRIM classification. Finally, a gray wolf optimizer (GWO) refines the network's robustness. To evaluate the proposed method, we develop a real experimental dataset consisting of sound of six common PRI patterns. We utilized eight pre-trained DCNN architectures for evaluation, with VGG16 and ResNet50V2 notably achieving recognition accuracies of 97.53% and 96.92%. Integrating ELM and GWO further optimized the accuracy rates to 98.80% and 97.58. This research advances radar identification by offering an enhanced method for PRIM recognition, emphasizing the potential of PRI sound to address real-world distortions in ESM and ELINT systems.

Automated algorithm selection using meta-learning and pre-trained deep convolution neural networks

Automated machine learning (AutoML), which explores the automation of various machine learning tasks, has seen significant progress in recent years. One of the fundamental tasks in this field is the selection of effective algorithms for a given dataset. This task is particularly challenging for tabular datasets where, unlike images or text, one cannot use pre-trained embeddings from other datasets. In this study, we present AutoIRAD, a novel meta-learning and vision-based approach for automatic classification algorithm selection for tabular datasets. Our approach is the first to generate image-based representations of entire tabular datasets, enabling us to model the features and interactions of all the dataset samples. Our image-based representation has two significant advantages. First, training our model across multiple datasets enables it to simultaneously learn from diverse domains and create more generalized and effective dataset representations. This representation can also be effectively applied to previously unseen datasets. Secondly, using images enables us to leverage large pre-trained networks (e.g., VGG). By tuning existing networks rather than training new ones, we can both speed up the training of our model and reduce the needed amounts of training data. An extensive evaluation of 150 datasets shows that AutoIRAD achieves results comparable to the leading state-of-the-art AutoML solution but at a fraction of their computation time.

Transfer Learning-based Drowsiness Detection System for Driver Assistance and Classification of Traffic Signs Employing a Deep Convolutional Neural Network

In this research paper, a comparative analysis of various image enhancements in the spatial domain techniques was performed based on three-dimensional image quality statistics such as mean squared error (MSE), peak signal-to-noise ratio (PSNR), and structural similarity for measuring the image quality (SSIM). The conditions for choosing the best method are low mean square error (MSE) and high peak signal-to-noise ratio as well as the structural similarity for measuring the image quality. The pre-processed image was subjected to a classification task using a stepwise version of pre-trained deep convolutional neural networks. The problem of driver drowsiness caused by fatigue, lack of sleep, medication, etc. will have to be solved by improving the efficiency of driver drowsiness detection. Many traffic accidents are largely caused by drowsy drivers. Driver fatigue and distraction can cause a lack of alertness, which can lead to driver inattention. In this paper, we proposed a new deep-learning technique for driver drowsiness detection. Two methods using convolutional deep neural network and GoogleNet transfer learning are compared to achieve a better accuracy of 99%.

A fine-tuning deep residual convolutional neural network for emotion recognition based on frequency-channel matrices representation of one-dimensional electroencephalography

Emotion recognition (ER) plays a crucial role in enabling machines to perceive human emotional and psychological states, thus enhancing human-machine interaction. Recently, there has been a growing interest in ER based on electroencephalogram (EEG) signals. However, due to the noisy, nonlinear, and nonstationary properties of electroencephalography signals, developing an automatic and high-accuracy ER system is still a challenging task. In this study, a pretrained deep residual convolutional neural network model, including 17 convolutional layers and one fully connected layer with transfer learning technique in combination frequency-channel matrices (FCM) of two-dimensional data based on Welch power spectral density estimate from the one-dimensional EEG data has been proposed for improving the ER by automatically learning the underlying intrinsic features of multi-channel EEG data. The experiment result shows a mean accuracy of 93.61 ± 0.84%, a mean precision of 94.70 ± 0.60%, a mean sensitivity of 95.13 ± 1.02%, a mean specificity of 91.04 ± 1.02%, and a mean F1-score of 94.91 ± 0.68%, respectively using 5-fold cross-validation on the DEAP dataset. Meanwhile, to better explore and understand how the proposed model works, we noted that the ranking of clustering effect of FCM for the same category by employing the t-distributed stochastic neighbor embedding strategy is: softmax layer activation is the best, the middle convolutional layer activation is the second, and the early max pooling layer activation is the worst. These findings confirm the promising potential of combining deep learning approaches with transfer learning techniques and FCM for effective ER tasks.

Cervical Cancer Classification From Pap Smear Images Using Deep Convolutional Neural Network Models

As one of the most common female cancers, cervical cancer often develops years after a prolonged and reversible pre-cancerous stage. Traditional classification algorithms used for detection of cervical cancer often require cell segmentation and feature extraction techniques, while convolutional neural network (CNN) models demand a large dataset to mitigate over-fitting and poor generalization problems. To this end, this study aims to develop deep learning models for automated cervical cancer detection that do not rely on segmentation methods or custom features. Due to limited data availability, transfer learning was employed with pre-trained CNN models to directly operate on Pap smear images for a seven-class classification task. Thorough evaluation and comparison of 13 pre-trained deep CNN models were performed using the publicly available Herlev dataset and the Keras package in Google Collaboratory. In terms of accuracy and performance, DenseNet-201 is the best-performing model. The pre-trained CNN models studied in this paper produced good experimental results and required little computing time.Graphical

Diagnostic usefulness of deep learning methods for Helicobacter pylori infection using esophagogastroduodenoscopy images.

We aimed to assess the diagnostic potential of deep convolutional neural networks (DCNNs) for detecting Helicobacter pylori infection in patients who underwent esophagogastroduodenoscopy and Campylobacter-like organism tests. We categorized a total of 13,071 images of various gastric sub-areas and employed five pretrained DCNN architectures: ResNet-101, Xception, Inception-v3, InceptionResnet-v2, and DenseNet-201. Additionally, we created an ensemble model by combining the output probabilities of the best models. We used images of different sub-areas of the stomach for training and evaluated the performance of our models. The diagnostic metrics assessed included area under the curve (AUC), specificity, accuracy, positive predictive value, and negative predictive value. When training included images from all sub-areas of the stomach, our ensemble model demonstrated the highest AUC (0.867), with specificity at 78.44%, accuracy at 80.28%, positive predictive value at 82.66%, and negative predictive value at 77.37%. Significant differences were observed in AUC between the ensemble model and the individual DCNN models. When training utilized images from each sub-area separately, the AUC values for the antrum, cardia and fundus, lower body greater curvature and lesser curvature, and upper body greater curvature and lesser curvature regions were 0.842, 0.826, 0.718, and 0.858, respectively, when the ensemble model was used. Our study demonstrates that the DCNN model, designed for automated image analysis, holds promise for the evaluation and diagnosis of Helicobacter pylori infection.

Multimodal Gait Abnormality Recognition Using a Convolutional Neural Network-Bidirectional Long Short-Term Memory (CNN-BiLSTM) Network Based on Multi-Sensor Data Fusion.

Global aging leads to a surge in neurological diseases. Quantitative gait analysis for the early detection of neurological diseases can effectively reduce the impact of the diseases. Recently, extensive research has focused on gait-abnormality-recognition algorithms using a single type of portable sensor. However, these studies are limited by the sensor's type and the task specificity, constraining the widespread application of quantitative gait recognition. In this study, we propose a multimodal gait-abnormality-recognition framework based on a Convolutional Neural Network-Bidirectional Long Short-Term Memory (CNN-BiLSTM) network. The as-established framework effectively addresses the challenges arising from smooth data interference and lengthy time series by employing an adaptive sliding window technique. Then, we convert the time series into time-frequency plots to capture the characteristic variations in different abnormality gaits and achieve a unified representation of the multiple data types. This makes our signal processing method adaptable to several types of sensors. Additionally, we use a pre-trained Deep Convolutional Neural Network (DCNN) for feature extraction, and the consequently established CNN-BiLSTM network can achieve high-accuracy recognition by fusing and classifying the multi-sensor input data. To validate the proposed method, we conducted diversified experiments to recognize the gait abnormalities caused by different neuropathic diseases, such as amyotrophic lateral sclerosis (ALS), Parkinson's disease (PD), and Huntington's disease (HD). In the PDgait dataset, the framework achieved an accuracy of 98.89% in the classification of Parkinson's disease severity, surpassing DCLSTM's 96.71%. Moreover, the recognition accuracy of ALS, PD, and HD on the PDgait dataset was 100%, 96.97%, and 95.43% respectively, surpassing the majority of previously reported methods. These experimental results strongly demonstrate the potential of the proposed multimodal framework for gait abnormality identification. Due to the advantages of the framework, such as its suitability for different types of sensors and fewer training parameters, it is more suitable for gait monitoring in daily life and the customization of medical rehabilitation schedules, which will help more patients alleviate the harm caused by their diseases.

Object detection and classification of butterflies using efficient CNN and pre-trained deep convolutional neural networks

Object detection and classification of butterflies using efficient CNN and pre-trained deep convolutional neural networks

Standard fetal ultrasound plane classification based on stacked ensemble of deep learning models

Identifying standard fetal ultrasound (US) planes with key anatomical structures during mid-pregnancy prenatal screening is crucial for measuring fetal growth parameters and early detection of abnormalities. However, obtaining these standard planes is laborious and time-consuming and depends on the clinical experience of sonographers. Automatic detection of these planes can aid sonographers in identifying the correct standard planes. In recent times, various deep learning techniques have developed to automate the detection of standard fetal US planes. However, a common limitation among these approaches is their dependence on a single model prediction to make the final decision, which introduces the possibility of inaccuracies. Therefore, we propose an automated identification of commonly used standard fetal US planes based on the stacking ensemble of deep convolutional neural networks (CNN). The stacking ensemble method employs three pre-trained deep CNNs: AlexNet, VGG-19, and DarkNet-19. Softmax and random forest classifiers are used to get predictions from deep CNNs. The final prediction is made using the absolute majority voting technique. A publicly available fetal US dataset is employed to evaluate the performance of the stacking ensemble approach. The proposed ensemble model classifies fetal US planes into six distinct classes: abdomen, brain, femur, thorax, maternal cervix, and other (less commonly employed planes, such as kidney, and limbs) fetal planes. Experimental findings demonstrate that the stacking ensemble approach achieved high performance with an accuracy of 95.69%, precision of 94.02%, recall of 96.28%, F1-score of 95.08%, specificity of 99.12%, and Matthews correlation coefficient of 94.19% compared to individual deep CNN models and other competing methods.

Deep Learning Based Obstacle Awareness from Airborne Optical Sensors

Aviation statistics identify collision with terrain and obstacles as a leading cause of helicopter accidents. Assisting helicopter pilots in detecting the presence of obstacles can greatly mitigate the risk of collisions. However, only a limited number of helicopters in operation have an installed helicopter terrain awareness and warning system (HTAWS), while the cost of active obstacle warning systems remains prohibitive for many civil operators. In this work, we apply machine learning to automate obstacle detection and classification in combination with commercially available airborne optical sensors. While numerous techniques for learning-based object detection have been published in the literature, many of them are data and computation intensive. Our approach seeks to balance the detection and classification accuracy of the method with the size of the training data required and the runtime. Specifically, our approach combines the invariant feature extraction ability of pretrained deep convolutional neural networks (CNNs) and the high-speed training and classification ability of a novel, proprietary frequency-domain support vector machine (SVM) method. We describe our experimental setup comprising the CNN + SVM model and datasets of predefined classes of obstacles—pylons, chimneys, antennas, TV towers, wind turbines, helicopters—synthesized from prerecorded airborne video sequences of low-altitude helicopter flight. We analyze the detection performance using average precision, average recall, and runtime performance metrics on representative test data. Finally, we present a simple architecture for real-time, onboard implementation and discuss the obstacle detection performance of recently concluded flight tests.

Efficient pollen grain classification using pre-trained Convolutional Neural Networks: a comprehensive study

Pollen identification is necessary for several subfields of geology, ecology, and evolutionary biology. However, the existing methods for pollen identification are laborious, time-consuming, and require highly skilled scientists. Therefore, there is a pressing need for an automated and accurate system for pollen identification, which can be beneficial for both basic research and applied issues such as identifying airborne allergens. In this study, we propose a deep learning (DL) approach to classify pollen grains in the Great Basin Desert, Nevada, USA. Our dataset consisted of 10,000 images of 40 pollen species. To mitigate the limitations imposed by the small volume of our training dataset, we conducted an in-depth comparative analysis of numerous pre-trained Convolutional Neural Network (CNN) architectures utilizing transfer learning methodologies. Simultaneously, we developed and incorporated an innovative CNN model, serving to augment our exploration and optimization of data modeling strategies. We applied different architectures of well-known pre-trained deep CNN models, including AlexNet, VGG-16, MobileNet-V2, ResNet (18, 34, and 50, 101), ResNeSt (50, 101), SE-ResNeXt, and Vision Transformer (ViT), to uncover the most promising modeling approach for the classification of pollen grains in the Great Basin. To evaluate the performance of the pre-trained deep CNN models, we measured accuracy, precision, F1-Score, and recall. Our results showed that the ResNeSt-110 model achieved the best performance, with an accuracy of 97.24%, precision of 97.89%, F1-Score of 96.86%, and recall of 97.13%. Our results also revealed that transfer learning models can deliver better and faster image classification results compared to traditional CNN models built from scratch. The proposed method can potentially benefit various fields that rely on efficient pollen identification. This study demonstrates that DL approaches can improve the accuracy and efficiency of pollen identification, and it provides a foundation for further research in the field.

Deep Seasonal Network for Remote Sensing Imagery Classification of Multi-Temporal Sentinel-2 Data

As a medium-resolution multi-temporal data source, Sentinel-2 data has the potential to match the performance of using very-high-resolution (VHR) images in deep learning applications. To fully leverage the multi-temporal nature of Sentinel-2 data, we introduce the Deep Seasonal Network (DeepSN). This composite architecture combines a pre-trained deep convolutional neural network (DCNN) for visual feature extraction with a long short-term memory (LSTM) model to capture temporal information and make classification predictions. We evaluate the effectiveness of DeepSN on a Maasai Boma classification task in the Tanzania region. The DeepSN takes a sequence of four seasonal data, each spanning three months, for Boma prediction. Through cross-season validation experiments, we compare various advanced DCNNs and select EfficientNet as the backbone for DeepSN, as it performs the best. DeepSN with an EfficientNet backbone achieves a significant 19% improvement in the F1 score compared to plain EfficientNet for the Boma classification task. This work introduces a versatile composite architecture capable of handling multi-temporal data efficiently, providing flexibility in choosing the most suitable feature extraction backbone. The performance of DeepSN demonstrates the viability of utilizing medium-resolution multi-temporal data instead of high-resolution images for diverse tasks.

Three-Dimensional-Slice-Super-Resolution-Net: A Fast Few Shooting Learning Model for 3D Super-Resolution Using Slice-Up and Slice-Reconstruction

Abstract 3D modeling accurately depicts the physical world but typically requires substantial data acquisition resources and significant storage space. We introduce a novel three-dimensional slice-reconstruction model (3DSR) to address these challenges. This 3D data super-resolution model leverages low-resolution 3D data as input to generate high-resolution results promptly and accurately, reducing the time and storage required to create detailed 3D models. To enhance the computational efficiency and accuracy of deep learning models, the 3D data are partitioned into multiple slices. The 3DSR processes each slice into a high-resolution 2D image, which is then reassembled into high-resolution 3D data. Our slice-up method and slice-reconstruction technique are specifically designed to preserve the primary characteristics of the 3D data. We employ a pre-trained deep 2D convolutional neural network to expand the resolution of the 2D image, resulting in excellent performance. This approach reduces the time required for training deep learning models and enhances computational efficiency during the resolution improvement process. Importantly, our model can deliver superior performance even when trained on fewer data.

Prediction of Treatment Outcome in Major Depressive Disorder Using Ensemble of Hybrid Transfer Learning and Long Short-Term Memory Based on EEG Signal

Major Depressive Disorder (MDD) is a widespread global mental disease. The Effectiveness of Selective Serotonin Reuptake Inhibitors (SSRIs) antidepressants prescribed for MDD patients is limited and pre-treatment assessment of treatment outcome is a vital task. In this study, a hybrid model based on Transfer Learning (TL) of powerful pre-trained deep Convolutional Neural Networks (CNNs) empowered with bidirectional Long Short-term Memory (BLSTM) cells and attention mechanism were developed to classify Responders (R) and Non-Responders (NR) to SSRI antidepressants, using raw data images of pre-treatment EEG signal obtained from 30 MDD patients. TL-LSTM-Attention models based on VGG16, Xception, and Densenet121 models were created for the classification of R/NR. Results show that the highest performance of hybrid TL-LSTM-Attention models was achieved by VGG16-LSTM-Attention with an accuracy of 98.21%, sensitivity of 96.22%, and specificity of 99.67%. An Ensemble model based on weighted majority voting among hybrid models is constructed to surpass the performance of each single hybrid model. Our proposed ensemble model gained accuracy, sensitivity, and specificity of 98.84%, 97.80%, and 99.60%, respectively. Hence, the proposed model which is an ensemble of TL-LSTM-Attention models fed by raw data images of EEG signal leads to high confidence in the prediction of antidepressants treatment outcome.

TRANSFER LEARNING BASED CNN FOR COVID 19

TRANSFER LEARNING BASED CNN FOR COVID 19

Heart sounds classification: Application of a new CyTex inspired method and deep convolutional neural network with transfer learning

Analysis of heart sounds is an effective means for the early diagnosis of cardiac pathologies. Heart sound classification is a challenging multi-disciplinary field that attracts many machine learning researchers. This paper proposes a new CyTex-inspired transform to convert heart sound signals to textured images. In our proposed method, the neighboring pixels have meaningful relationships that result in semi-periodic patterns in the output image. This method has two significant benefits. Firstly, this makes it possible to apply deep convolutional neural networks (DCNN) to heart sound classification. Consequently, correlative moving masks of the convolutional layers can extract short-term and long-term information from these images in vertical and horizontal directions. Secondly, by converting the heart sound signal to images as a compatible input for DCNNs, we can employ a transfer learning scheme to reduce the risk of overfitting. The performance of four popular pre-trained DCNNs – AlexNet, VGG16, InceptionV3, and ResNet50 – has been tested. Furthermore, data augmentation, hyper-parameter optimization, and drop-out techniques are employed. The performance of the proposed system is verified on the heart sounds dataset PhysioNet. Results were obtained using cross-validation techniques. Our experiments demonstrate the potential of our proposed method for achieving excellent performance compared to previous methods on the same dataset with a score of over 0.9200 at a sensitivity of 0.8775 and specificity of 0.9637 using the ResNet with data augmentation, hyperparameter optimization, and dropout techniques.

Analyzing performance of deep learning models under the presence of distortions in identifying plant leaf disease

<p>Convolutional neural networks (CNN) trained using deep learning (DL) have advanced dramatically in recent years. Researchers from a variety of fields have been motivated by the success of CNNs in computer vision to develop better CNN models for use in other visually-rich settings. Successes in image classification and research have been achieved in a wide variety of domains throughout the past year. Among the many popularized image classification techniques, the detection of plant leaf diseases has received extensive research. As a result of the nature of the procedure, image quality is often degraded and distortions are introduced during the capturing of the image. In this study, we look into how various CNN models are affected by distortions. Corn-maze leaf photos from the 4,188-image corn or maize leaf Dataset (split into four categories) are under consideration. To evaluate how well they handle noise and blur, researchers have deployed pre-trained deep CNN models like visual geometry group (VGG), InceptionV3, ResNet50, and EfficientNetB0. Classification accuracy and metrics like as recall and f1-score are used to evaluate CNN performance.</p>

Feature extraction and fusion using deep convolutional neural networks for Covid-19 detection using CT and X-RAY images

COVID-19 represents a novel variant of the coronavirus disease, having rapidly disseminated across the globe. In recent studies pertaining to computer vision, image processing, and classification techniques, numerous methodologies have been introduced employing chest X-ray images and computerized tomography (CT) images. This investigation introduces novel fused deep features founded on CT and X-ray image classification, with the aim of detecting COVID-19 disease. The proposed approach encompasses three key phases: deep feature generation, iterative feature selection, and classification. During the feature generation phase, well-known pre-trained deep convolutional neural networks, namely DenseNet201, MobileNetV2, ResNet18, ResNet50, ResNet101, VGG16, and VGG19, were leveraged. Each network model generated 1000 features, which were subsequently fused, culminating in the acquisition of a final feature vector comprising 7000 dimensions. In order to distill the most pertinent information, the ReliefF and iterative maximum relevance minimum redundancy (RFImRMR) feature selection techniques were employed in the generation of the ultimate feature vector. To evaluate the performance of the proposed method, publicly available datasets of CT images and X-ray images were employed. Notably, the suggested deep learning approach attained accuracy rates of 99.33% and 93.10% for COVID-19 detection using CT and X-ray images, respectively. These achieved results serve as compelling evidence substantiating the efficacy of the proposed fused deep features and RFImRMR-based COVID-19 detection.

Deep learning image-based automated application on classification of tomato leaf disease by pre-trained deep convolutional neural networks

The agriculture sector is one of the major sectors in India. India is well known for the production of various varieties of spices, fruits, vegetables, herbs, etc. Along with the pollution, the diseases that are affecting plants are increasing and there are various reasons for this. Tomato is one of the high-demand crops in the market and is produced in large quantities. There are many diseases that tomatoes get affected by because of the virus, fungus, bacteria, etc. In this project, we proposed a model to identify the diseases of tomato plants using images of tomato plant leaves. Our main goal is to develop a good model with decent accuracy and a mobile application that works with or without the internet for users, especially farmers. The Convolution Neural Network-based approach is used to create the model for this project. This proposed system model gives 98 % accuracy and that model is converted to the TF Lite model which is used in the application. This application can precisely predict the disease of the tomato leaf and suggest the treatment for it.