Abstract:One of the main challenges of employing deep learning models in the field of medicine is a lack of training data due to difficulty in collecting and labeling data, which needs to be performed by experts. To overcome this drawback, transfer learning (TL) has been utilized to solve several medical imaging tasks using pre-trained state-of-the-art models from the ImageNet dataset. However, there are primary divergences in data features, sizes, and task characteristics between the natural image classificati… Show more
“…In most cases, the available data are sufficient to obtain a good performance model. However, sometimes there is a shortage of data for using DL directly [ 87 ]. To properly address this issue, three suggested methods are available.…”
Section: Challenges (Limitations) Of Deep Learning and Alternate Solumentioning
confidence: 99%
“…For example, using X-ray images of different chest diseases to train the model, then fine-tuning and training it on chest X-ray images for COVID-19 diagnosis. More details about same-domain TL and how to implement the fine-tuning process can be found in [ 87 ]. Fig.…”
Section: Challenges (Limitations) Of Deep Learning and Alternate Solumentioning
In the last few years, the deep learning (DL) computing paradigm has been deemed the Gold Standard in the machine learning (ML) community. Moreover, it has gradually become the most widely used computational approach in the field of ML, thus achieving outstanding results on several complex cognitive tasks, matching or even beating those provided by human performance. One of the benefits of DL is the ability to learn massive amounts of data. The DL field has grown fast in the last few years and it has been extensively used to successfully address a wide range of traditional applications. More importantly, DL has outperformed well-known ML techniques in many domains, e.g., cybersecurity, natural language processing, bioinformatics, robotics and control, and medical information processing, among many others. Despite it has been contributed several works reviewing the State-of-the-Art on DL, all of them only tackled one aspect of the DL, which leads to an overall lack of knowledge about it. Therefore, in this contribution, we propose using a more holistic approach in order to provide a more suitable starting point from which to develop a full understanding of DL. Specifically, this review attempts to provide a more comprehensive survey of the most important aspects of DL and including those enhancements recently added to the field. In particular, this paper outlines the importance of DL, presents the types of DL techniques and networks. It then presents convolutional neural networks (CNNs) which the most utilized DL network type and describes the development of CNNs architectures together with their main features, e.g., starting with the AlexNet network and closing with the High-Resolution network (HR.Net). Finally, we further present the challenges and suggested solutions to help researchers understand the existing research gaps. It is followed by a list of the major DL applications. Computational tools including FPGA, GPU, and CPU are summarized along with a description of their influence on DL. The paper ends with the evolution matrix, benchmark datasets, and summary and conclusion.
“…In most cases, the available data are sufficient to obtain a good performance model. However, sometimes there is a shortage of data for using DL directly [ 87 ]. To properly address this issue, three suggested methods are available.…”
Section: Challenges (Limitations) Of Deep Learning and Alternate Solumentioning
confidence: 99%
“…For example, using X-ray images of different chest diseases to train the model, then fine-tuning and training it on chest X-ray images for COVID-19 diagnosis. More details about same-domain TL and how to implement the fine-tuning process can be found in [ 87 ]. Fig.…”
Section: Challenges (Limitations) Of Deep Learning and Alternate Solumentioning
In the last few years, the deep learning (DL) computing paradigm has been deemed the Gold Standard in the machine learning (ML) community. Moreover, it has gradually become the most widely used computational approach in the field of ML, thus achieving outstanding results on several complex cognitive tasks, matching or even beating those provided by human performance. One of the benefits of DL is the ability to learn massive amounts of data. The DL field has grown fast in the last few years and it has been extensively used to successfully address a wide range of traditional applications. More importantly, DL has outperformed well-known ML techniques in many domains, e.g., cybersecurity, natural language processing, bioinformatics, robotics and control, and medical information processing, among many others. Despite it has been contributed several works reviewing the State-of-the-Art on DL, all of them only tackled one aspect of the DL, which leads to an overall lack of knowledge about it. Therefore, in this contribution, we propose using a more holistic approach in order to provide a more suitable starting point from which to develop a full understanding of DL. Specifically, this review attempts to provide a more comprehensive survey of the most important aspects of DL and including those enhancements recently added to the field. In particular, this paper outlines the importance of DL, presents the types of DL techniques and networks. It then presents convolutional neural networks (CNNs) which the most utilized DL network type and describes the development of CNNs architectures together with their main features, e.g., starting with the AlexNet network and closing with the High-Resolution network (HR.Net). Finally, we further present the challenges and suggested solutions to help researchers understand the existing research gaps. It is followed by a list of the major DL applications. Computational tools including FPGA, GPU, and CPU are summarized along with a description of their influence on DL. The paper ends with the evolution matrix, benchmark datasets, and summary and conclusion.
“…The accuracy obtained by the trained model was 93.67%. In [ 84 , 85 ], the researchers suggested a first round of training using transfer learning from the original and augmented samples of a large-scale dataset which is in the same domain of the targeted dataset, followed by re-training the model using the original and augmented samples of the target dataset. The highest accuracy achieved was 97.40%.…”
Section: Feature Representation In Deep Classifiersmentioning
Deep learning (DL) represents the golden era in the machine learning (ML) domain, and it has gradually become the leading approach in many fields. It is currently playing a vital role in the early detection and classification of plant diseases. The use of ML techniques in this field is viewed as having brought considerable improvement in cultivation productivity sectors, particularly with the recent emergence of DL, which seems to have increased accuracy levels. Recently, many DL architectures have been implemented accompanying visualisation techniques that are essential for determining symptoms and classifying plant diseases. This review investigates and analyses the most recent methods, developed over three years leading up to 2020, for training, augmentation, feature fusion and extraction, recognising and counting crops, and detecting plant diseases, including how these methods can be harnessed to feed deep classifiers and their effects on classifier accuracy.
“…We also perform transfer learning to fine-tune the models to enhance their performances. Transfer learning (TL) is a solution for the lack of training data in deep learning [33]. TL means using the knowledge from a specific task to solve another correlated task.…”
Plant disease, especially crop plants, is a major threat to global food security since many diseases directly affect the quality of the fruits, grains, and so on, leading to a decrease in agricultural productivity. Farmers have to observe and determine whether a leaf was infected by naked eyes. This process is unreliable, inconsistent, and error prone. Several works on deep learning techniques for detecting leaf diseases had been proposed. Most of them built their models based on limited resolution images using convolutional neural networks (CNNs). In this research, we aim at detecting early disease on plant leaves with small disease blobs, which can only be detected with higher resolution images, by an artificial neural network (ANN) approach. After a pre-processing step using a contrast enhancement method, all the infested blobs are segmented for the whole dataset. A list of several measurement-based features that represents the blobs are chosen and then selected based on their influences on the model's performance using a wrapperbased feature selection algorithm, which is built based on a hybrid metaheuristic. The chosen features are used as inputs for an ANN. We compare the results obtained using our methods with another approach using popular CNN models (AlexNet, VGG16, ResNet-50) enhanced with transfer learning. The ANN's results are better than those of CNNs using a simpler network structure (89.41% vs 78.64%, 79.92%, and 84.88%, respectively). This shows that our approach can be implemented on low-end devices such as smartphones, which will be of great assistance to farmers on the field. INDEX TERMS Neural network, image classification, plant disease, feature selection, precision agriculture.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
