It is a challenging task to recognize smoke from visual scenes due to large variations in the feature of color, texture, shapes, etc. The current detection algorithms are mainly based on single ...feature or fusion of multiple static features of smoke, which leads to low detection accuracy. To solve this problem, this paper proposes a smoke detection algorithm based on the motion characteristics of smoke and the convolutional neural networks (CNN). Firstly, a moving object detection algorithm based on background dynamic update and dark channel priori is proposed to detect the suspected smoke regions. Then, the features of suspected region is extracted automatically by CNN, on that the smoke identification is performed. Compared to previous work, our algorithm improves the detection accuracy, which can reach 99% in the testing sets. For the problem that the region of smoke is relatively small in the early stage of smoke generation, the strategy of implicit enlarging the suspected regions is proposed, which improves the timeliness of smoke detection. In addition a fine-tuning method is proposed to solve the problem of scarce of data in the training network. Also, the algorithm has good smoke detection performance by testing under various video scenes.
•The Local Binary Pattern (LBP)-based feature has drawback in capturing the color information of an image.•This paper overcomes this problem by incorporating CHF on the LBP-based image retrieval and ...classification.•The hybrid CHF and LBP-based feature yield a promising result and outperform the former existing methods.
The Local Binary Pattern (LBP) operator and its variants play an important role as the image feature extractor in the textural image retrieval and classification. The LBP-based operator extracts the textural information of an image by considering the neighboring pixel values. A single or join histogram can be derived from the LBP code which can be used as an image feature descriptor in some applications. However, the LBP-based feature is not a good candidate in capturing the color information of an image, making it is less suitable for measuring the similarity of color images with rich color information. This work overcomes this problem by adding an additional color feature, namely Color Information Feature (CIF), along with the LBP-based feature in the image retrieval and classification systems. The CIF and LBP-based feature adequately represent the color and texture features. As documented in the experimental result, the hybrid CIF and LBP-based feature presents a promising result and outperforms the existing methods over several image databases. Thus, it can be a very competitive candidate in retrieval and classification application.
The analysis of 3D meshes with deep learning has become prevalent in computer graphics. As an essential structure, hierarchical representation is critical for mesh pooling in multiscale analysis. ...Existing clustering-based mesh hierarchy construction methods involve nonlinear discretization optimization operations, making them nondifferential and challenging to embed in other trainable networks for learning. Inspired by deep superpixel learning methods in image processing, we extend them from 2D images to 3D meshes by proposing a novel differentiable chart-based segmentation method named geodesic differential supervertex (GDSV). The key to the GDSV method is to ensure that the geodesic position updates are differentiable while satisfying the constraint that the renewed supervertices lie on the manifold surface. To this end, in addition to using the differential SLIC clustering algorithm to update the nonpositional features of the supervertices, a reparameterization trick, the Gumbel-Softmax trick, is employed to renew the geodesic positions of the supervertices. Therefore, the geodesic position update problem is converted into a linear matrix multiplication issue. The GDSV method can be an independent module for chart-based segmentation tasks. Meanwhile, it can be combined with the front-end feature learning network and the back-end task-specific network as a plug-in-plug-out module for training; and be applied to tasks such as shape classification, part segmentation, and 3D scene understanding. Experimental results show the excellent performance of our proposed algorithm on a range of datasets.
In many real-world multi-label applications, the content of multi-label data is usually characterized by high dimensional features, which contains complex correlation information, i.e., label ...correlations and redundant features. To alleviate the problem, we present a novel scheme, called learning correlation information for multi-label feature selection (LCIFS) method, by jointly digging up label correlations and controlling feature redundancy. To be specific, the regression model via manifold framework is presented to fit the relationship between feature space and label distribution, during which adaptive spectral graph is leveraged to learn more precise structural correlations of labels simultaneously. Besides, we utilize the relevance of features to constrain the redundancy of the generated feature subset, and a general ℓ2,p-norm regularized model is employed to fulfill more robust feature selection. The proposed method is transformed into an explicit optimization function, which is conquered by an efficient iterative optimization algorithm. Finally, we conduct comprehensive experiments on twelve realistic multi-label datasets, including text domain, image domain, and audio domain. The statistic results demonstrate the effectiveness and superiority of the proposed method among nine competition methods.
•The proposed method is based on the embedding and filter approaches.•The label correlations are explored by an adaptive spectral graph.•The feature redundancy is analyzed by a general characteristic between features.•An efficient algorithm is designed to solve the optimization problem.
Incidents of thyroid cancer have dramatically increased in recent years; however, early ultrasound diagnosis can reduce morbidity and mortality. The work in clinical situations relies heavily on the ...subjective experience of the sonographer. Numerous computer-aided diagnostic techniques exist, but most consider how good the results are, ignoring the pre-image collecting and its usefulness in post-clinical practise. To address these issues, this study proposes a computer-aided diagnosis method based on an attentional mechanism. Due to its lightweight properties, the model can rapidly identify nodules and distinguish between benign and malignant ones without using much hardware. The model uses a bounding box to locate the thyroid nodule and determines whether it is benign or cancerous, and outputs the diagnostic result of the thyroid nodule ultrasound images. The latest attention mechanisms are used to get better results at a fraction of the cost. Additionally, ultrasound images with different features of benign and malignant thyroid nodules were collected following the Thyroid Imaging Reporting and Data System standards. The experimental results showed that the approach identifies and classifies thyroid nodules rapidly and effectively; the mAP value of the results reached 0.89, and the mAP value of malignant nodules reached 0.94, with detection rate of single image reached 7 ms. Young physicians and small hospitals with limited resources can benefit from using this method to assist with thyroid ultrasound examination diagnosis.
•A deep learning model based on the attention mechanism is proposed, which can distinguish between benign and malignant thyroid nodules with high accuracy, especially for malignant nodules.•A light-weight thyroid nodule recognition network is proposed, which can accurately identify and frame thyroid nodules at a fast speed and has practical effects in clinical applications.•A data set based on the TI-RADS standard was constructed, and all the data were consistent with the characteristics of benign and malignant thyroid nodules, which can better guide the model to distinguish between benign and malignant nodules.
Abstract
This paper introduces a moderated‐mediation model to investigate the relationship between green innovation, as measured by green patent stocks, and firms' stock market value, as measured by ...Tobin's Q. Using longitudinal data drawn from 351 heavily polluting firms in China's A‐share market from 2007 to 2018, we find that green innovation is likely to affect firms' stock market value positively. A 1% increase in the green innovation over assets index will enhance by 0.18% the Tobin's Q at the firm level. Environmental compliance costs significantly mediate the green innovation‐firms' stock market value association by 8.5%. We also emphasize the positive moderating role of technological collaboration with public research organizations on green innovation‐environmental compliance costs linkage. Our results emphasize that the recurrent question in the extant literature “does it pay to be green?” should be substituted by “how and under what conditions does it pay to be green for firms?” and further stress how firms obtain sustainable development in the environment and economy through green innovation. Implications for firms and investors are also proposed.
Objectives
Ultrasound screening during early pregnancy is vital in preventing congenital disabilities. For example, nuchal translucency (NT) thickening is associated with fetal chromosomal ...abnormalities, particularly trisomy 21 and fetal heart malformations. Obtaining accurate ultrasound standard planes of a fetal face during early pregnancy is the key to subsequent biometry and disease diagnosis. Therefore, we propose a lightweight target detection network for early pregnancy fetal facial ultrasound standard plane recognition and quality assessment.
Methods
First, a clinical control protocol was developed by ultrasound experts. Second, we constructed a YOLOv4 target detection algorithm based on the backbone network as GhostNet and added attention mechanisms CBAM and CA to the backbone and neck structure. Finally, key anatomical structures in the image were automatically scored according to a clinical control protocol to determine whether they were standard planes.
Results
We reviewed other detection techniques and found that the proposed method performed well. The average recognition accuracy for six structures was 94.16%, the detection speed was 51 FPS, and the model size was 43.2 MB, and a reduction of 83% compared with the original YOLOv4 model was obtained. The precision for the standard median sagittal plane was 97.20%, and the accuracy for the standard retro‐nasal triangle view was 99.07%.
Conclusions
The proposed method can better identify standard or non‐standard planes from ultrasound image data, providing a theoretical basis for automatic acquisition of standard planes in the prenatal diagnosis of early pregnancy fetuses.
Since a human face can be represented by a few feature points (FPs) with less redundant information, and calculated by a linear combination of a small number of prototypical faces, we propose a ...two-step 3D face reconstruction approach including FP depth estimation and shape deformation. The proposed approach can reconstruct a realistic 3D face from a 2D frontal face image. In the first step, a coupled dictionary learning method based on sparse representation is employed to explore the underlying mappings between 2D and 3D training FPs, and then the depth of the FPs is estimated. In the second step, a novel shape deformation method is proposed to reconstruct the 3D face by combining a small number of most relevant deformed faces by the estimated FPs. The proposed approach can explore the distributions of 2D and 3D faces and the underlying mappings between them well, because human faces are represented by low-dimensional FPs, and their distributions are described by sparse representations. Moreover, it is much more flexible since we can make any change in any step. Extensive experiments are conducted on BJUT_3D database, and the results validate the effectiveness of the proposed approach.
Purpose
Uterine fibroids (UF) are the most frequent tumors in ladies and can pose an enormous threat to complications, such as miscarriage. The accuracy of prognosis may also be affected by way of ...doctor inexperience and fatigue, underscoring the want for automatic classification fashions that can analyze UF from a giant wide variety of images.
Methods
A hybrid model has been proposed that combines the MobileNetV2 community and deep convolutional generative adversarial networks (DCGAN) into useful resources for medical practitioners in figuring out UF and evaluating its characteristics. Real‐time automated classification of UF can aid in diagnosing the circumstance and minimizing subjective errors. The DCGAN science is utilized for superior statistics augmentation to create first‐rate UF images, which are labeled into UF and non‐uterine‐fibroid (NUF) classes. The MobileNetV2 model then precisely classifies the photos based totally on this data.
Results
The overall performance of the hybrid model contrasts with different models. The hybrid model achieves a real‐time classification velocity of 40 frames per second (FPS), an accuracy of 97.45%, and an F1 rating of 0.9741.
Conclusion
By using this deep learning hybrid approach, we address the shortcomings of the current classification methods of uterine fibroid.
We propose a novel hybrid model combining the MobileNetV2 network and deep convolutional generative adversarial networks (DCGAN) to support physicians in identifying uterine fibroid (UF) and assessing its characteristics. Real‐time automatic classification of the UF can assist doctors in diagnosis and reduce subjective randomness.
•A hybrid evolutionary multitask (HEMT) framework is presented for MOVRPTWs.•An exploration stage (ESKT) is suggested to promote the transfer of useful knowledge.•An exploitation stage (ESKR) is ...introduced to reuse the problem-specific knowledge.•A tradeoff mechanism (TOM) is employed for the collaboration between ESKT and ESKR.•Four suites of multitasking instances are generated to verify the validity of HEMT.
The vehicle routing problem with time windows (VRPTW), as an important logistic problem, has been widely investigated in recent decades. However, it is still a great challenge for most existing approaches to solve multiobjective VRPTWs (MOVRPTWs) with many conflicting objectives. In this study, a hybrid evolutionary multitask algorithm, termed HEMT, is proposed to address MOVRPTWs under the framework of evolutionary multitasking, where multiple MOVRPTWs are optimized simultaneously by leveraging the similarity between them. In particular, HEMT is characterized by three aspects: (1) an exploration stage with knowledge transfer (ESKT) is designed to globally explore the search space by transferring knowledge across different MOVRPTWs; (2) an exploitation stage with knowledge reuse (ESKR) is employed to further promote the quality of solutions by conducting local searches and reusing problem-specific knowledge; and (3) a tradeoff mechanism (TOM) is suggested to adaptively switch the search between ESKT and ESKR. Furthermore, to verify the efficacy of the proposed HEMT, four suites of new multitasking instances are generated based on 45 real-world MOVRPTW benchmarks under different multitask environments. The experimental results show that HEMT not only effectively solves multiple MOVRPTWs simultaneously but also achieves better performances than the traditional single-task counterparts.