KEYWORDS: Deep learning, Education and training, Process modeling, Simulation of CCA and DLA aggregates, Polishing, Performance modeling, Motion analysis, Machine learning, Image segmentation, Image processing
Stomata play a crucial role in the photosynthetic process of plants by regulating the water and carbon dioxide levels in their leaves. The effective identification of stomata in plant leaves has become a hot topic in related research fields. With the development of deep learning, some automatic stomatal identification methods have been proposed in the past. However, these methods are based on horizontal anchor network, which can be challenging when collecting stomatal images on plant leaves since most stomata are rotated. As a result, the proposed methods cannot completely identify rotated stomata, leading to reduced efficiency in subsequent stomatal trait analysis. To address this issue, we propose an improved method for the automatic identification of rotating stomata in maize leaves based on the CenterNet (Objects as Points) detection model. The network structure of CenterNet is enhanced by adding an angle prediction branch, which enables the detection of rotating stomata. Experimental results show that the improved CenterNet deep learning model achieves a recognition precision of 94.3% on the maize leaf stomata dataset. This method can automate the identification of maize leaf stomata, assisting researchers in conducting large-scale studies on stomatal morphology and structure.
Proteins secreted by various cells and tissues into different body fluids can signal several physiological disorders. However, the degree of complexity in different body fluids and the presence of a large number of proteins in fluids can make studying them with existing proteomics techniques complex and result in large discrepancies between experimental studies. To address this, we developed a deep learning framework called SecBert that identifies secreted proteins in two human body fluids. SecBert uses a sequence-based approach with end-to-end automatic feature extraction for protein classification. Our results show that SecBert performs well, achieving an average area under the ROC curve of 0.94-0.95 on each fluid test dataset.
Protein-protein interaction (PPI) is the process by which two or more protein molecules form a protein complex through non-covalent bonds. The interactions between protein and the protein complexes formed by these interactions are the primary complements of various essential cellular functions and carry out almost all vital life activities. Most PPI research today focuses on the use of machine learning methods, of which the use of graph neural networks (GNN) for prediction is a current hot direction. This paper highlights the main advances in the application of GNN to proteinprotein interactions. The first part reviews protein sequence-based methods for PPI prediction. And the second part focuses on structure-based graph neural network PPI prediction methods. Finally, we discuss the shortcomings of GNNs in this area and future directions in PPI prediction.
Images form the basis of human vision and are an important source of information for both human perception and machine pattern recognition. Since the development of the image quality evaluation field, a large number of image quality evaluation algorithms have emerged. In recent years, deep learning has become a hot area and has also been applied to the image domain. This paper focuses on reference-free image quality evaluation and reviews the no-reference image quality assessment based on deep learning. Firstly, the classification of IQA, technical indexes for IQA algorithm evaluation, and several public IQA databases available online are introduced. Then, several deep learning models applied to NR-IQA are discussed, compared, and evaluated in detail. Finally, an outlook on future research is provided.
Medical imaging has been widely used in clinical practice. It is an important basis for medical experts to diagnose the disease. However, medical images have many unstable factors such as complex imaging mechanism, the target displacement will cause constructed defect and the partial volume effect will lead to error and equipment wear, which increases the complexity of subsequent image processing greatly. The segmentation algorithm which based on SLIC (Simple Linear Iterative Clustering, SLIC) superpixels is used to eliminate the influence of constructed defect and noise by means of the feature similarity in the preprocessing stage. At the same time, excellent clustering effect can reduce the complexity of the algorithm extremely, which provides an effective basis for the rapid diagnosis of experts.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.