Training Capsule Networks with Various Parameters

This research paper presents an advanced deep learning framework for tomato ripeness and maturity detection, employing Convolutional Neural Networks (CNNs) as the primary tool for automated classification. In particular, the study emphasizes the utilization of the ResNet-152 architecture, a sophisticated deep neural network known for its exceptional performance in image classification tasks. ResNet-152 addresses the challenges of fine-grained categorization by enabling the extraction of intricate visual features such as color nuances, textures, and shapes inherent to tomatoes. This eliminates the necessity for manual feature engineering, enhancing the model's ability to discern between "RIPE," "UNRIPE," and "ROTTEN" tomato classes with unprecedented accuracy. The ResNet-152 architecture's effectiveness lies in its unique design, featuring residual blocks that facilitate the training of very deep networks. This architecture mitigates the vanishing gradient problem and enables the model to learn complex hierarchical features, contributing to its state-of-the-art performance in image classification. In the context of tomato ripeness detection, ResNet-152 acts as a powerful tool for capturing and understanding the intricate visual cues that define different ripeness states, laying the foundation for an efficient and accurate automated sorting system in the agricultural and food processing industries.

Convolutional neural networks have demonstrated state-of-the-art performance in image classification and various other computer vision tasks. Plant disease detection is an important area of deep learning which has been addressed by many recent methods. However, there is a dire need to optimize these solutions for resource-constrained portable devices such as smartphones. This is a challenging problem because deep learning models are resource extensive in nature. This paper proposes an efficient method to systematically classify plant disease symptoms using convolutional neural networks. These networks are memory efficient and when coupled with the proposed training configuration it enables rapid development of industrial applications by reducing the training times. Another critical problem arises with the improper distribution of samples among classes known as the class imbalance problem, which is addressed by employing a simple statistical methodology. Transfer learning is a known technique for training small datasets which transfers pre-trained weights learned on a large dataset. However, during transfer learning, negative transfer learning is a common problem. Therefore, a stepwise transfer learning approach is proposed which can help in fast convergence, while reducing overfitting and preventing negative transfer learning during knowledge transfer across domains. The system is trained and evaluated on two plant disease datasets i.e., PlantVillage (a publicly available dataset) and pepper disease dataset provided by the National Institute of Horticultural and Herbal Science, Republic of Korea. The pepper dataset is particularly challenging as it contains images from different parts of the plant such as the leaf, pulp, and stem. The proposed system has dominated the previous works on the PlantVillage dataset and achieved 99% and 99.69% accuracy on the Pepper dataset and PlantVillage datasets, respectively.

Medical image analysis using deep neural networks (DNN) has demonstrated state-of-the-art performance in image classification and segmentation tasks, aiding disease diagnosis. The accuracy of the DNN is largely governed by the quality and quantity of the data used to train the model. However, for the medical images, the critical security and privacy concerns regarding sharing of local medical data across medical establishments precludes exploiting the full DNN potential for clinical diagnosis. The federated learning (FL) approach enables the use of local model's parameters to train a global model, while ensuring data privacy and security. In this paper, we review the federated learning applications in medical image analysis with DNNs, highlight the security concerns, cover some efforts to improve FL model performance, and describe the challenges and future research directions.

Deep learning techniques have boosted the performance of hyperspectral image (HSI) classification. In particular, convolutional neural networks (CNNs) have shown superior performance to that of the conventional machine learning algorithms. Recently, a novel type of neural networks called capsule networks (CapsNets) was presented to improve the most advanced CNNs. In this paper, we present a modified two-layer CapsNet with limited training samples for HSI classification, which is inspired by the comparability and simplicity of the shallower deep learning models. The presented CapsNet is trained using two real HSI datasets, i.e., the PaviaU (PU) and SalinasA datasets, representing complex and simple datasets, respectively, and which are used to investigate the robustness or representation of every model or classifier. In addition, a comparable paradigm of network architecture design has been proposed for the comparison of CNN and CapsNet. Experiments demonstrate that CapsNet shows better accuracy and convergence behavior for the complex data than the state-of-the-art CNN. For CapsNet using the PU dataset, the Kappa coefficient, overall accuracy, and average accuracy are 0.9456, 95.90%, and 96.27%, respectively, compared to the corresponding values yielded by CNN of 0.9345, 95.11%, and 95.63%. Moreover, we observed that CapsNet has much higher confidence for the predicted probabilities. Subsequently, this finding was analyzed and discussed with probability maps and uncertainty analysis. In terms of the existing literature, CapsNet provides promising results and explicit merits in comparison with CNN and two baseline classifiers, i.e., random forests (RFs) and support vector machines (SVMs).

Deep neural networks achieve state-of-the-art performance for image classification and other tasks but are easily fooled by forgeries which slightly modify a legitimate image in a specific direction and are visually indistinguishable from the original. This presents a security risk for applications such as driverless transportation systems. We formulate detection of such forgeries as a watermark detection problem and derive locally optimal statistical tests for identifying them. Motivated by this optimal structure, we present a procedure for learning a forgery detector from a training set. The reliability of our forgery detector is assessed for several image classification tasks.

Convolutional Neural Networks have demonstrated state-of-the-art performance in various image classification and computer vision-related tasks. Plant disease detection is one of the essential areas of image classification. Though many models have been proposed for the efficient classification of plant disease images, there is a dire need to develop an image classification mechanism based on deep learning, which has fewer parameters to implement the algorithm on mobile devices. In this manuscript, we propose a ConvPlant-Net, a Convolutional Neural Network based Plant disease detection system that uses a combination of Depth-Wise Separable Convolutional, 2-Dimensional transpose Layer, and a Convolutional layer for efficient learning of the high and low-level features. The proposed model contains only 31,998 trainable parameters. With fewer parameters, the model has achieved an accuracy of 98.62%, 99.36%, and 99.60% on Tomato, Pepper Bell, and Potato crops from the publicly available PlantVillage dataset.

Object classification has been one of the main tasks in computer vision. With the fast development of deep learning, its performance in image classification and object recognition has presented dramatic improvements. In this paper, we propose a new deep convolutional neural network (CNN) architecture for robust object classification. The proposed model is fused with three traditional CNN approaches, Densenet201, Resnet50, and our proposed residual CNN. The fused network architecture allows parallel processing of the multiple networks for keeping the system sped up. A single shot deep convolution network is trained as an object detector to generate all possible candidates of different object classes. The output of each neural network is representing a single vote that is used in the classification process. 3-to-1 voting criteria are applied in the final classification decision between the candidate object classes. Several experiments were conducted to evaluate the performance of the proposed network. The experimental results show that the proposed approach has better performance than the networks used in the fusion process when they act individually. It also has lower miss rates when compared to several states of art methodologies.

The purpose of this study is to offer a basic Convolutional Neural Network (CNN) software for classifying epileptic seizures. The recognition of the Electroencephalography (EEG) signal and its distinctive features are required for the diagnosis of epileptic seizures. As a result, it requires a mechanism for recognising and categorising epileptic seizures. As part of a neural network, deep learning is used .CNN has shown excellent performance in image classification and pattern identification. This study utilizes the Hanning window FFT analyser and CNN ConvNet to categorize epileptic seizures. To transform the time-frequency domain of the EEG signal data, this transform produces an image that may be classified into five properties.

Image classification is an important task that has a wide range of applications. Convolutional neural networks (CNNs) are a common approach that can achieve promising performance in image classification. However, using CNNs to address a problem requires in-depth knowledge about CNN architectures and how it relates to the problem domain. Genetic programming (GP) as an evolutionary computation method can used to reduce the amount of knowledge required to design a CNN for a given problem domain by automatically searching for the optimal architecture. This paper proposes a new algorithm named, GPCNN, which encodes graph-based CNN architectures as trees and uses genetic operators, i.e. mutation, crossover and selection, to find better architectures. A more flexible crossover, partial subtree crossover, is also proposed to improve the search performance. As an preliminary work, GPCNN did not manage to achieve better performance than the state-of-the-art methods due to the limit on computational resource, but it is able to achieve better results than the baseline methods. More importantly, the proposed tree-based graph representation of CNN allows CNN architecture of various shapes, which has a great potential for future work in evolutionary automatic neural architecture search.

Domain- and task-specific transfer learning for medical segmentation tasks

Deep neural network (DNN) models, particularly convolutional neural networks (CNNs), have demonstrated remarkable performance in biomedical image classification due to their ability to automatically learn features from large datasets. One common challenge in the preparation of large, microscopic datasets for DNN tasks is sample defocusing, potentially impairing the model performance. To handle defocusing, computational imaging, or specifically quantitative phase imaging (QPI), performs digital refocusing by using both the phase and the amplitude of the complex optical field. This leads us to investigate whether feeding the complex field into DNN would potentially address the defocusing problem as in-focus information is implicitly encoded in the complex field. In this paper, we assess the feasibility of employing neural networks to directly process full amplitude and phase data from a defocus plane without digital refocusing. Our specific focus lies in understanding the tolerance for defocus in image classification neural networks when amplitude and phase are taken as inputs. To accomplish this, we used Fourier ptychography microscopy (FPM) to acquire in-focus phase and amplitude images of two distinct object types - normal red blood cells and echinocytes. We then digitally propagate the complex field to generate progressively defocused images of the samples to serve as training and testing datasets for image classification neural networks. While the digitally defocused images contain sufficient information to recover the original in-focus images, we observed that current standard implementations of deep learning models are unable to effectively utilize the defocused field to distinguish between the two cell types. We conclude that the physical-model-based digital refocusing capability of QPI remains indispensable for overcoming defocusing issues in current standard DNN models.

The COVID-19 pandemic in the world has given rise to a lot of research done in the field of medical imaging using deep learning and artificial intelligence methods for the detection and prognosis of the disease. Capsule Networks (CapsNet) perform image classification by identifying the spatial location and orientation of features within the images. In this paper, a Multi-lane Capsule Neural Networks (MLCN) model is introduced that performs dynamic routing networks with dimensionally distinct parallel lanes, replacing the traditional pooling operations in Convolutional Neural Networks (CNN). With the use of parallel capsules, feature orientation identification at any given part of the image is improved. The MLCN model has been studied in this paper using the X-ray images collected from patients tested for COVID-19 and its performance is evaluated using a number of metrics. It has been observed that the performance of the constructed CapsNet model achieved a testing accuracy of 96.8% with the F-1 score 97.19% performing better than the existing state-of-the-art models.

This paper explores the application of deep learning architectures in retinal image analysis, with a particular focus on the early detection of diabetic retinopathy (DR). Leveraging large-scale retinal imaging datasets, the study examines the diagnostic capacity of advanced neural models in identifying subtle pathological markers such as microaneurysms, hemorrhages, and exudates at the earliest clinical stages. Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and hybrid deep learning frameworks are evaluated for their performance in image classification and lesion localization. Results demonstrate that CNN-based architectures achieve an accuracy of 94.2%, with sensitivity and specificity values exceeding 93%, underscoring their robustness in medical image interpretation. Hybrid models integrating CNN and attention mechanisms further enhance feature discrimination, achieving 95.1% accuracy and improved area under the curve (AUC) metrics. RNN-driven architectures exhibit competitive performance, particularly in sequential image feature learning, with overall accuracy surpassing 92%. The findings highlight the transformative role of deep learning in automating ophthalmic diagnostics, enabling scalable, precise, and timely detection of diabetic retinopathy to mitigate preventable vision loss.

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.

Convolutional neural network (CNN) is a state-of-art deep learning (DL) method with superior performance in image classification. Here, a CNN-based workflow is proposed to discriminate hominid teeth. Our hope is that this method could help confirm otherwise questionable records of Homo from Pleistocene deposits where there is a standing risk of mis-attributing molars of Pongo to Homo. A two-step workflow was designed. The first step is converting the enamel-dentine junction (EDJ) into EDJ card, that is, a two-dimensional image conversion of the three-dimensional EDJ surface. In this step, researchers must carefully orient the teeth according to the cervical plane. The second step is training the CNN learner with labeled EDJ cards. A sample consisting of 53 fossil Pongo and 53 Homo (modern human and Neanderthal) was adopted to generate EDJ cards, which were then separated into training set (n = 84) and validation set (n = 22). To assess the feasibility of this workflow, a Pongo-Homo classifier was trained from the aforementioned EDJ card set, and then the classifier was used to predict the taxonomic affinities of six samples (test set) from von Koenigswald's Chinese Apothecary collection. Results show that EDJ cards in validation set are classified accurately by the CNN learner. More importantly, taxonomic predictions for six specimens in test set match well with the diagnosis results deduced from multiple lines of evidence, implying the great potential of CNN method. This workflow paves a way for future studies using CNN to address taxonomic complexity (e.g., distinguishing Pongo and Homo teeth from the Pleistocene of Asia). Further improvements include visual interpretation and extending the applicability to moderately worn teeth.