Feature map quantification: An efficient approach for active trachoma image classification.

In recent electroencephalograph (EEG)-based emotion recognition, the differential entropy (DE) features extracted from multiple electrodes are organized as a 2D feature map for convolutional neural network (CNN) in order to utilize the information hidden in the electrodes. In this study, we attempt to investigate the influence of different feature maps on the recognition performance. Six different 2D feature maps (M1-M4: baseline feature maps without sparsity and location relationship, M5-M6: pre-defined feature maps with sparsity and location relationship) are used to organize the DE features for the traditional CNN model. Evaluation study on the DEAP dataset finds that the 2D feature map configuration exhibits statistically significant effect on the classification performance of the traditional CNN model in classifying the high/low arousal and high/low valence, respectively. However, the differences are rather limited, e.g., only 1% improvement can be resulted from selecting the optimal 2D feature map among 6 feature maps. This implies that the feature map may not be a critical issue when applying the DE features to classifying the emotion states in a CNN.

Facial expression recognition is one of the research hotspots in the field of computer vision. Aiming at the problems that the current machine learning method extracts facial features are less robust and the traditional convolutional neural network can not fully extract the expression features, a residual network model integrating CBAM attention mechanism is proposed. Given an intermediate feature map, a attention map is generated on the channel domain and the spatial domain of the feature map respectively by our module, and multiplied by the original feature map to obtain a recalibrated feature map. In the training process, the improved loss function A-Softmax is used to generate the angular interval by manipulating the feature surface, so that the different class features learned have angular intervals in the angular space, and the similar features are more closely clustered. Experiments on FER2013 and JAFFE dataset show that the proposed method effectively improves the feature expression ability of the network, enhances the ability to distinguish different facial expression features, and achieves good recognition performance.

Convolutional Neural Networks (CNNs) are frequently used algorithms because of their propensity to learn relevant and hierarchical features through their feature extraction technique. However, the availability of enormous volumes of data in various variations is crucial for their performance. Capsule networks (CapsNets) perform well on a small amount of data but perform poorly on complex images. To address this, we proposed a new Capsule Network architecture called Tri Texton-Dense CapsNet (TTDCapsNet) for better complex and medical image classification. The TTDCapsNet is made up of three hierarchic blocks of Texton-Dense CapsNet (TDCapsNet) models. A single TDCapsNet is a CapsNet architecture composed of a texton detection layer to extract essential features, which are passed onto an eight-layered block of dense convolution that further extracts features, and then the output feature map is given as input to a Primary Capsule (PC), and then to a Class Capsule (CC) layer for classification. The resulting feature map from the first PC serves as input into the second-level TDCapsNet, and that from the second PC serves as input into the third-level TDCapsNet. The routing algorithm receives feature maps from each PC for the various CCs. Routing the concatenation of the three PCs creates an additional CC layer. All these four feature maps combined, help to achieve better classification. On fashion-MNIST, CIFAR-10, Breast Cancer, and Brain Tumor datasets, the proposed model is evaluated and achieved validation accuracies of 94.90%, 89.09%, 95.01%, and 97.71% respectively. Findings from this work indicate that TTDCapsNet outperforms the baseline and performs comparatively well with the state-of-the-art CapsNet models using different performance metrics. This work clarifies the viability of using Capsule Network on complex tasks in the real world. Thus, the proposed model can be used as an intelligent system, to help oncologists in diagnosing cancerous diseases and administering treatment required.

With the rapid development of Convolutional Neural Networks (CNNs), higher accuracy is often accompanied by a large number of parameters and computations. In embedded devices with limited computing resources, it is often difficult to implement large network models. Therefore, the lightweight network came into being. Recent studies have shown that there are a large number of redundant feature maps in convolutional neural networks, which is an important reason for the success of convolutional neural networks. GhostNet which proposes that redundant feature maps can be obtained by linear variation. Compared with standard convolution, the Ghost module uses linear variation to replace the partial convolution operation that outputs the same number of feature maps, saving a lot of parameters and computation, resulting in a lightweight network. In CondenseNet, a convolutional neural network, a method is proposed to drop unimportant convolution kernel channels in stages during the training process, making the network a lightweight network in the inference stage. Based on the above ideas, we propose the SeLective module to discard unimportant convolution kernels and use linear changes to replace the missing feature maps, thereby improving the neural network.

Due to the weak structural features of pipelines and underwater light attenuation, the complex and harsh environment of the seabed greatly increases the possibility of an underwater autonomous remotely operated vehicle losing a detected seabed-contacting segment during pipe-laying operations. To address this problem, we propose a cascade attention module and a prefusion module with a convolutional neural network. The cascade attention module samples the feature maps in a non-convolutional form to realize the interaction between structure and channels, and the attention map is generated by cascading attention. The prefusion module pre-fuses the three layers of feature maps from different stages in the backbone, and the delicate features of the shallow feature maps are fused with the deeper feature maps to generate richer feature maps with space location and semantic classification information. We conduct experiments to verify our modules, both on the underwater pipeline dataset and in a tank test. The results show that our modules can improve the performance of different neural network models for seabed-contacting segment detection. The target detection and instance segmentation performance of the best model is improved through a 6.3% increase in AP and a 3.8% increase in mean intersection over union compared with the baseline model.

Due to the simple design pipeline, end-to-end (E2E) neural models for speech enhancement (SE) have attracted great interest. In order to improve the performance of the E2E model, the local and sequential properties of speech should be efficiently taken into account when modelling. However, in most current E2E models for SE, these properties are either not fully considered or are too complex to be realized. In this letter, we propose an efficient E2E SE model, termed WaveCRN. Compared with models based on convolutional neural networks (CNN) or long short-term memory (LSTM), WaveCRN uses a CNN module to capture the speech locality features and a stacked simple recurrent units (SRU) module to model the sequential property of the locality features. Different from conventional recurrent neural networks and LSTM, SRU can be efficiently parallelized in calculation, with even fewer model parameters. In order to more effectively suppress noise components in the noisy speech, we derive a novel restricted feature masking approach, which performs enhancement on the feature maps in the hidden layers; this is different from the approaches that apply the estimated ratio mask to the noisy spectral features, which is commonly used in speech separation methods. Experimental results on speech denoising and compressed speech restoration tasks confirm that with the SRU and the restricted feature map, WaveCRN performs comparably to other state-of-the-art approaches with notably reduced model complexity and inference time.

.Significance: Automatic and accurate classification of three-dimensional (3-D) retinal optical coherence tomography (OCT) images is essential for assisting ophthalmologist in the diagnosis and grading of macular diseases. Therefore, more effective OCT volume classification for automatic recognition of macular diseases is needed.Aim: For OCT volumes in which only OCT volume-level labels are known, OCT volume classifiers based on its global feature and deep learning are designed, validated, and compared with other methods.Approach: We present a general framework to classify OCT volume for automatic recognizing macular diseases. The architecture of the framework consists of three modules: B-scan feature extractor, two-dimensional (2-D) feature map generation, and volume-level classifier. Our architecture could address OCT volume classification using two 2-D image machine learning classification algorithms. Specifically, a convolutional neural network (CNN) model is trained and used as a B-scan feature extractor to construct a 2-D feature map of an OCT volume and volume-level classifiers such as support vector machine and CNN with/without attention mechanism for 2-D feature maps are described.Results: Our proposed methods are validated on the publicly available Duke dataset, which consists of 269 intermediate age-related macular degeneration (AMD) volumes and 115 normal volumes. Fivefold cross-validation was done, and average accuracy, sensitivity, and specificity of 98.17%, 99.26%, and 95.65%, respectively, are achieved. The experiments show that our methods outperform the state-of-the-art methods. Our methods are also validated on our private clinical OCT volume dataset, consisting of 448 AMD volumes and 462 diabetic macular edema volumes.Conclusions: We present a general framework of OCT volume classification based on its 2-D feature map and CNN with attention mechanism and describe its implementation schemes. Our proposed methods could classify OCT volumes automatically and effectively with high accuracy, and they are a potential practical tool for screening of ophthalmic diseases from OCT volume.

The traditional convolutional neural network (CNN) only focuses on the features of the last layer of the network, ignoring those of other layers. The detailed information of the shallow network can improve the accuracy of classification to some extent. With the deepening of the network, the problems such as gradient disappearance and explosion are obvious. In order to alleviate this problem, a method for residual network image classification with multi-scale feature fusion is proposed in the paper. First of all, the Random Image Cropping and Patching (RICAP), a data augmentation method, is adopted to cut and splice the new training samples from the training set, based on which feature maps of different sizes are obtained by residual modules. Secondly, after reducing the dimension of high-level feature maps, all the feature maps with the same dimension are processed by the multi-scale fusion. Finally, these feature vectors are input into the Softmax classifier for training and classification, and the method of learning rate decay is used in the training process. The experiment results indicate that this method has a good performance on image classification based on the public datasets of MNIST and CIFAR-10.KeywordsMulti-scale feature fusionResidual networkData augmentationImage classification

Convolutional Neural Network (CNN) is a powerful and successful deep learning technique for a variety of computer vision and image analysis applications. Interpreting and explaining the decisions of CNNs is one of the most challengeable tasks despite its significant success in various image analysis tasks. Topological Data Analysis (TDA) is an approach that exploits algebraic invariants from topology to analyse high dimensional and noisy datasets as well as growing challenges of big data applications. Persistent homology (PH) is an algebraic topology method for measuring topological features of shapes and/or functions at different distance or similarity resolutions. This work is an attempt to investigate the algebraic properties of pretrained CNN convolutional layer filters based on random Gaussian/Uniform distribution. We shall investigate the stability and sensitivity of the condition number of CNN filters during and post the model training with focus on class discriminability of the PH features of the convolved images. We shall demonstrate a strong link between the condition number of the CNN filters and their discriminating power of the PH representation. In particular, we shall establish that if small perturbation added to the original images then feature maps with well-conditioned filters will produce similar topological features to the original image. Our investigation and findings are based on training CNN's with Digits, MNIST and CIFAR-10 datasets. Our ultimate interest in applying the results of these findings in designing appropriate CNN models for classifications of ultrasound tumor scan images. Preliminary results for these applications are encouraging.

Breast cancer remains one of the most common cancers amongst women globally. Early detection is crucial for improving survival rates. While mammography is widely used and an effective imaging technique, it can sometimes yield false positive or false negatives. Mammogram interpretation is highly operator-dependent, introducing variability and the potential for diagnostic errors. Additionally, mammographic images have limitations, such as low contrast in breast tissue and overlapping structures that can obscure lesions or mimic abnormalities. These limitations can lead to unnecessary biopsies or delayed diagnosis. These challenges highlight the needs for advanced and data driven diagnostic tools to support and enhance current screening practices.</p> <p>In recent years, machine learning has emerged as a transformative force in the health care industry offering innovative solution to complex medical challenges. One of the most promising applications of this technology is in the early and accurate detection of breast cancer particularly through the mammography image analysis. Machine learning algorithms, especially deep learning models, have shown significant potential in identifying patterns in mammography that may indicate abnormal cases. This study utilizes the power of deep learning particularly Convolutional Neural Networks (CNNs) to enhance the classification of breast ultrasound images.</p> <p>This research proposes a novel two-level classification approach. At the first level classification, the system distinguishes normal from abnormal cases. Next, the second level classification, it further classifies abnormal cases into benign or malignant tumors. To address challenges such as limited and imbalanced datasets, the study incorporates comprehensive preprocessing techniques including contrast enhancement via Contrast Limited Adaptive Histogram Equalization (CLAHE) and region of interest (ROI). The preprocessing step were evaluated separately and in combination to assess their individual contributions. Additionally, data augmentation is utilized to improve model generalization. To further enhance performance and robustness, multiple CNN architectures are combined using an ensemble mechanism. Soft voting and hard voting leverage the strengths of diverse CNNs reducing individual model biases and improving overall accuracy.</p> <p>The main contributions of this research are: (1) the design of a two-level classification system (2) the utilization of multiple preprocessing techniques to improve image quality, (3) the application of voting ensemble learning to improve predictive stability and accuracy, and (4) an extensive evaluation on the BUSI dataset. This breaks down the complex diagnostic task into smaller, manageable steps to allow for more accurate comparisons, analysis, and improvements at each stage.</p> <p>The first preprocessing step involved the application of CLAHE. In the first level classification (normal vs abnormal), performance of various models has been evaluated. The models achieved an 82.05% accuracy for AlexNet, 84.62% for DenseNet, 85.26% for Inception, 82.69% for MobileNet, 82.05% for ResNet and 82.69% for VGG16. The accuracy of soft voting is 96.20% and accuracy of hard voting 92.09%. In the second level classification (benign vs malignant), the models achieved an 75.00% accuracy for AlexNet, 80.47% for DenseNet, 35.94% for Inception, 41.41% for MobileNet, 35.94% for ResNet and 82.81% for VGG16. The accuracy of soft voting is 90.84% and hard voting is 85.76%.</p> <p>The second preprocessing step involved the ROI was implemented. This step helped isolate the regions containing potential abnormalities, such as tumors, while filtering out irrelevant areas. After the application of ROI (normal vs abnormal), the system evaluated the performance of various models. In the first level classification (normal vs abnormal), the models achieved an 82.69% accuracy for AlexNet, 82.69% for DenseNet, 83.97% for Inception, 87.18% for MobileNet, 82.69% for ResNet and 82.05% for VGG16. The accuracy of soft voting is 100.00% and hard voting is 98.08%. In the second level classification (benign vs malignant), the system evaluated the performance of various models. The models achieved an 75.00% accuracy for AlexNet, 80.47% for DenseNet, 35.94% for Inception, 41.41% for MobileNet, 35.94% for ResNet and 82.81% for VGG16. Soft voting achieved 89.15% and hard voting achieved 80.95%.</p> <p>The final step in the preprocessing stage combines both CLAHE and ROI. The combination led to an improvement in classification performance. In the first level classification (normal vs abnormal), the models achieved an 91.77% accuracy for AlexNet, 92.72% for DenseNet, 95.57% for Inception, 96.52% for MobileNet, 76.90% for ResNet and 91.14% for VGG16. The accuracy of soft voting is 90.88% and hard voting is 93.99%. In the second level classification (benign vs malignant), the system evaluated the performance of various models. The models achieved an 87.69% accuracy for AlexNet, 99.23% for DenseNet, 96.92% for Inception, 93.08% for MobileNet, 94.62% for ResNet and 97.69% for VGG16. Soft voting achieved 96.92% and hard voting achieved 97.69%.</p> <p>These results indicate that every preprocessing step contributed to an improvement in classification accuracy across all models. This study demonstrates that a two-level, ensemble-based deep learning system can significantly improve the diagnostic accuracy of breast ultrasound images, offering a promising tool to assist radiologists and support early detection efforts, particularly in resource-constrained healthcare environments.

Building compact convolutional neural networks (CNNs) with reliable performance is a critical but challenging task, especially when deploying them in real-world applications. As a common approach to reduce the size of CNNs, pruning methods delete part of the CNN filters according to some metrics such as l1-norm. However, previous methods hardly leverage the information variance in a single feature map and the similarity characteristics among feature maps. In this paper, we propose a novel filter pruning method, which incorporates two kinds of feature map selections: diversity-aware selection (DFS) and similarity-aware selection (SFS). DFS aims to discover features with low information diversity while SFS removes features that have high similarities with others. We conduct extensive empirical experiments with various CNN architectures on publicly available datasets. The experimental results demonstrate that our model obtains up to 91.6% parameter decrease and 83.7% FLOPs reduction with almost no accuracy loss.

Convolutional neural network (CNN) has developed such a large network size in last few years, so reducing the storage requirement without hurting its accuracy becomes necessary. In this paper, in order to reduce the number of high dimensional feature maps in shallow layers, we propose a feature map selection method, which cuts the feature map number by correlation coefficient between kernels and finishes detection by HOG+SVM method. Firstly, we extract feature maps of shallow layers from trained CNN. Then, we merge strongly relevant feature maps and choose all maps among weakly relevant feature maps by analyzing correlation coefficient of kernels. Finally, we extract HOG features of the chosen feature maps and use SVM to complete the training and classification. The experimental results show that the proposed method can effectively prune high dimensional feature maps and stabilize or even advance the performance in pedestrian detection.

The report presents an algorithm for constructing a convolutional hierarchical neural network classifier, which is a modification of the algorithm for constructing hierarchical neural network classifiers suggested before. The original algorithm was designed to exploit intrinsic class hierarchy to build a class tree with a neural network in each node classifying groups of initial classes (in a non-terminal node) or a subset of original classes (in a terminal node). The convolutional modification utilizes convolutional neural networks instead of regular fully connected networks in order to apply the model to image classification tasks. Use of class hierarchy for image classification should reduce the number of adjusted neural network parameters compared to deep convolutional neural networks, and therefore it should reduce training and inference time. In this context the algorithm may be compared with some pruning techniques. The convolutional hierarchical neural network classifier inherits some hyperparameters of a conventional hierarchical neural network classifier, like the activation threshold and the threshold by the share of voting patterns. The goal of this study was to explore different strategies of choosing these hyperparameters. To test these strategies, we used the CIFAR-10 dataset. Also, for demonstration purposes we apply the convolutional hierarchical neural network classifier to the CIFAR-100 dataset.

Recently Pretrained Convolutional Neural Networks (CNNs) have proven its effectiveness in image extraction and classification. This powerful feature of CNNs in image processing is facilitated by machine learning to train and classify big data. Image capturing and security transformation are considered as a central necessity of remote sensing imagery of unmanned aerial vehicles (UAVs) and drones. This paper presents a novel artificial intelligent drone-based encrypted machine learning of image classification using a pertained CNN and image encryption-decryption by utilizing singular value decomposition (SVD) and XOR-Secret-Key block cipher cryptology. Initially, pretrained convolutional neural networks (CNN) are extensively used to extract and classify image features making advantage of machine learning training tools features. Training of partial set of image data can be performed to test, classify and label the untrained image data. Pretrained CNN can classify images into object categories. Afterward, the CNN the classified image output is transformed into a digital matrix using SVD and identifies its associated eigenvalues. These eigenvalues are then converted into a binary code. The image data encryption is implemented according to suggested keys. The first part applies the exclusive OR (XOR) operation of the eigenvalues with a selected cipher key. Meanwhile, the second part implements the XOR operation of the output of part one with a randomly generated key using Poisson distribution. The last step in the encryption will be obtained by generating a non-real SVD decomposition matrix; according to which a non-readable image will be resulted. The original image-matrix can be constructed by reversing the process using the security key-cipher block (Poisson Distribution Key and Stand-alone Cipher Code). Finally, SVD image processing results are demonstrated to verify the effectiveness and security of the applied approach that can be implemented for different images.

Semantic segmentation is a fundamental task in remote sensing image processing. The large appearance variations of ground objects make this task quite challenging. Recently, deep convolutional neural networks (DCNNs) have shown outstanding performance in this task. A common strategy of these methods (e.g., SegNet) for performance improvement is to combine the feature maps learned at different DCNN layers. However, such a combination is usually implemented via feature map summation or concatenation, indicating that the features are considered indiscriminately. In fact, features at different positions contribute differently to the final performance. It is advantageous to automatically select adaptive features when merging different-layer feature maps. To achieve this goal, we propose a gated convolutional neural network to fulfill this task. Specifically, we explore the relationship between the information entropy of the feature maps and the label-error map, and then a gate mechanism is embedded to integrate the feature maps more effectively. The gate is implemented by the entropy maps, which are generated to assign adaptive weights to different feature maps as their relative importance. Generally, the entropy maps, i.e., the gates, guide the network to focus on the highly-uncertain pixels, where detailed information from lower layers is required to improve the separability of these pixels. The selected features are finally combined to feed into the classifier layer, which predicts the semantic label of each pixel. The proposed method achieves competitive segmentation accuracy on the public ISPRS 2D Semantic Labeling benchmark, which is challenging for segmentation by only using the RGB images.