期刊:
Mathematical Methods in the Applied Sciences,2024年47(6):- ISSN:0170-4214
通讯作者:
Fan, LL
作者机构:
[Bai, Yinsong; Zhao, Huijiang] Wuhan Univ, Sch Math & Stat, Wuhan, Peoples R China.;[Bai, Yinsong] Xinjiang Univ, Coll Math & Syst Sci, Urumqi, Peoples R China.;[Fan, Lili] Wuhan Polytech Univ, Sch Math & Comp Sci, Wuhan, Peoples R China.;[Fan, Lili; Fan, LL] Wuhan Polytech Univ, Sch Math & Comp Sci, Wuhan 430023, Peoples R China.
通讯机构:
[Fan, LL ] W;Wuhan Polytech Univ, Sch Math & Comp Sci, Wuhan 430023, Peoples R China.
关键词:
a hyperbolic system with Cattaneo's law;asymptotic nonlinear stability;boundary effect;initial-boundary value problem;small initial perturbation;viscous shock profiles;weighted energy method
摘要:
We consider the asymptotic nonlinear stability of viscous shock profiles for an initial-boundary value problem of the scalar conservation laws with an artificial heat flux satisfying Cattaneo's law in the negative half line Double-struck capital R-=(-infinity,0)$$ {\mathrm{\mathbb{R}}}_{-} equal to \left(-\infty, 0\right) $$ with Dirichlet boundary condition. When the nonlinear flux function is assumed to be strictly convex and the unique global entropy solution of the corresponding Riemann problem of the resulting scalar conservation laws consists of shock wave with negative speed, it is shown in this paper that the large time behavior of its global smooth solutions can be precisely described by the suitably shifted viscous shock profiles, where the time-dependent shift function is uniquely determined by both the boundary value and the initial data. We also show that the shift function converge to a constant time asymptotically. Our analysis is based on weighted L2-$$ {L} circumflex 2- $$energy method.
摘要:
This article proposes a novel soft multiprototype clustering algorithm (SMP) for high-dimensional data clustering with noisy and complex structural patterns. SMP integrates dimensionality reduction, multiprototype clustering, and multiprototype merge clustering under a two-layer seminonnegative matrix factorization (semi-NMF) architecture. Specifically, the first semi-NMF layer performs multiprototype clustering, which solves the problem that a single prototype cannot represent complex data structures. Meanwhile, the multiprototype fuzzy clustering constraints ensure that the multiprototypes better characterize the original data structure. The second semi-NMF layer performs multiprototype merge clustering to mitigate the issues of heavy computation burden and poor antinoise performance of the spectral clustering algorithm. The introduction of the Laplace graph matrix regularization constraint in this layer assists SMP in completing the merging of multiprototypes with complex data structures. Comprehensive experiments demonstrate that the proposed method outperforms the state-of-the-art algorithms.
摘要:
Weeds are a significant threat to agricultural productivity and the environment. The increasing demand for sustainable weed control practices has driven innovative developments in alternative weed control technologies aimed at reducing the reliance on herbicides. The barrier to adoption of these technologies for selective in-crop use is availability of suitably effective weed recognition. With the great success of deep learning in various vision tasks, many promising image-based weed detection algorithms have been developed. This paper reviews recent developments of deep learning techniques in the field of image-based weed detection. The review begins with an introduction to the fundamentals of deep learning related to weed detection. Next, recent advancements in deep weed detection are reviewed with the discussion of the research materials including public weed datasets. Finally, the challenges of developing practically deployable weed detection methods are summarized, together with the discussions of the opportunities for future research. We hope that this review will provide a timely survey of the field and attract more researchers to address this inter-disciplinary research problem.
摘要:
Hail, a highly destructive weather phenomenon, necessitates critical identification and forecasting for the protection of human lives and properties. The identification and forecasting of hail are vital for ensuring human safety and safeguarding assets. This research proposes a deep learning algorithm named Dual Attention Module EfficientNet (DAM-EfficientNet), based on EfficientNet, for detecting hail weather conditions. DAM-EfficientNet was evaluated using FY-4A satellite imagery and real hail fall records, achieving an accuracy of 98.53% in hail detection, a 97.92% probability of detection, a false alarm rate of 2.08%, and a critical success index of 95.92%. DAM-EfficientNet outperforms existing deep learning models in terms of accuracy and detection capability, with fewer parameters and computational needs. The results validate DAM-EfficientNet's effectiveness and superior performance in hail weather detection. Case studies indicate that the model can accurately forecast potential hail-affected areas and times. Overall, the DAM-EfficientNet model proves to be effective in identifying hail weather, offering robust support for weather disaster alerts and prevention. It holds promise for further enhancements and broader application across more data sources and meteorological parameters, thereby increasing the precision and timeliness of hail forecasting to combat hail disasters and boost public safety.
期刊:
Journal of Functional Analysis,2024年286(7):110316 ISSN:0022-1236
通讯作者:
Liu, CT
作者机构:
[Liu, Chuntai; Liu, CT] Wuhan Polytech Univ, Sch Math & Comp Sci, Wuhan 430023, Peoples R China.;[Liu, Chuntai; Liu, CT] Guangxi Normal Univ, Sch Math & Stat, Guilin 541004, Peoples R China.
通讯机构:
[Liu, CT ] W;Wuhan Polytech Univ, Sch Math & Comp Sci, Wuhan 430023, Peoples R China.;Guangxi Normal Univ, Sch Math & Stat, Guilin 541004, Peoples R China.
关键词:
Self-affine tile;Homeomorphism;Brouwer's invariance of domain;theorem
摘要:
The author of this paper and coauthors in 2022 studied a family of self-affine tiles in Rd with noncollinear digit sets, and gave a sufficient and necessary condition for such tiles to be tame balls. We in this paper mainly present a simpler proof of such equivalent condition. We replace quadric surfaces by some zigzag planes, and redefine the quasi-invariant plane which plays a key role in the construction of the desired homeomorphism. This adjustment greatly simplifies the proof. (c) 2024 Elsevier Inc. All rights reserved.
摘要:
Melanoma is a malignant skin tumor that threatens human life and health. Early detection is essential for effective treatment. However, the low contrast between melanoma lesions and normal skin and the irregularity in size and shape make skin lesions difficult to detect with the naked eye in the early stages, making the task of skin lesion segmentation challenging. Traditional encoder-decoder built with U-shaped networks using convolutional neural network (CNN) networks have limitations in establishing long-term dependencies and global contextual connections, while the Transformer architecture is limited in its application to small medical datasets. To address these issues, we propose a new skin lesion segmentation network, SUTransNET, which combines CNN and Transformer in a parallel fashion to form a dual encoder, where both CNN and Transformer branches perform dynamic interactive fusion of image information in each layer. At the same time, we introduce our designed multi-grouping module SpatialGroupAttention (SGA) to complement the spatial and texture information of the Transformer branch, and utilize the Focus idea of YOLOV5 to construct the Patch Embedding module in the Transformer to prevent the loss of pixel accuracy. In addition, we design a decoder with full-scale information fusion capability to fully fuse shallow and deep features at different stages of the encoder. The effectiveness of our method is demonstrated on the ISIC 2016, ISIC 2017, ISIC 2018 and PH2 datasets and its advantages over existing methods are verified.
摘要:
The immense representation power of deep learning frameworks has kept them in the spotlight in hyperspectral image (HSI) classification. Graph Convolutional Neural Networks (GCNs) can be used to compensate for the lack of spatial information in Convolutional Neural Networks (CNNs). However, most GCNs construct graph data structures based on pixel points, which requires the construction of neighborhood matrices on all data. Meanwhile, the setting of GCNs to construct similarity relations based on spatial structure is not fully applicable to HSIs. To make the network more compatible with HSIs, we propose a staged feature fusion model called SFFNet, a neural network framework connecting CNN and GCN models. The CNN performs the first stage of feature extraction, assisted by adding neighboring features and overcoming the defects of local convolution; then, the GCN performs the second stage for classification, and the graph data structure is constructed based on spectral similarity, optimizing the original connectivity relationships. In addition, the framework enables the batch training of the GCN by using the extracted spectral features as nodes, which greatly reduces the hardware requirements. The experimental results on three publicly available benchmark hyperspectral datasets show that our proposed framework outperforms other relevant deep learning models, with an overall classification accuracy of over 97%.
摘要:
With the lack of sufficient prior information, unsupervised hyperspectral unmixing (HU) has been a preprocessing step in the hyperspectral image (HSI) processing pipeline, which can provide the types of material and corresponding abundance information of HSI, to further provide assistance for downstream higher level semantic tasks to overcome the limitation caused by mixed pixels. However, the unmixing results obtained by current unsupervised HU methods are unstable and unprecise under the guidance of the least reconstruction error (RE), which have no consistency with the performance of high-level tasks. To solve this problem, this article takes the hyperspectral anomaly detection (HAD) as an entry point and proposes a novel algorithm based on deep clustering which can jointly perform HU and HAD in an end-to-end manner. A mutual feedback mechanism is formed between the upstream HU process and the downstream HAD process, and through joint optimization, both two tasks can achieve relatively good performances. However, the low dimensional abundance has a limited representation, which may lead to the increase of false alarm rate. To overcome this limitation, the principal components (PCs) of HSI are fused with the abundance to enhance the representation ability. Moreover, we use the reweighted reconstruction loss strategy to enhance the role of anomalies in the HU process. Experiments performed on several real datasets verify the rationality and superiority of the proposed UADNet algorithm.
摘要:
In the realm of practical problem-solving, multi-objective optimisation problems with redundant variables and indefinite objective functions (MOPRVIF) are becoming increasingly prevalent. MOPRVIF involve determining the optimal decision variables that optimise multiple objectives, leveraging the relational data of a set of variables and multiple objectives. For these problems, this paper focuses on the following two issues: one is the demand for a unified computational model to solve this problem; the other is how to improve the algorithm's deep intelligent search capability. In this regard, this paper designs a dual data-driven multi-objective optimisation method. The method used consisted of four parts: elimination of redundant variables (ERV), objective function construction (OFC), selection evolution operator (SEO), and multi-objective evolutionary algorithm (MOEA). MOEA was the main focus of the method. ERV is data preparation and variable selection according to multiple objectives. OFC involves constructing the relationship model between variables and objectives, and a high-accuracy model is important for guaranteeing reliable results. Furthermore, SEO can adjust the evolution operator during a deep search. This is an important guarantee for deep, intelligent search. MOEA combined OFC and SEO to form the final solution algorithm-Dual Data Driven Multi-Objective Evolutionary Algorithm (DDMOEA). DDMOEA was explored using two different disciplinary problems of drug compound optimisation and wild blueberry cultivation and benchmarks were selected. The first two problem domains are distinct. The first problem is more complex than the second; however, both encompass redundant variables and indefinite objective functions. Benchmarks are utilised independently to gauge the profound intelligent search capability. The experiments affirm that the dual data -driven optimization approach proposed in this paper is effective, practical, and scalable.
摘要:
Images captured in low-light or underwater environments are often accompanied by significant degradation, which can negatively impact the quality and performance of downstream tasks. While convolutional neural networks (CNNs) and Transformer architectures have made significant progress in computer vision tasks, there are few efforts to harmonize them into a more concise framework for enhancing such images. To this end, this study proposes to aggregate the individual capability of self-attention (SA) and CNNs for accurate perturbation removal while preserving background contents. Based on this, we carry forward a Retinex-based framework, dubbed as Mutual Retinex, where a two-branch structure is designed to characterize the specific knowledge of reflectance and illumination components while removing the perturbation. To maximize its potential, Mutual Retinex is equipped with a new mutual learning mechanism, involving an elaborately designed mutual representation module (MRM). In MRM, the complementary information between reflectance and illumination components are encoded and used to refine each other. Through the complementary learning via the mutual representation, the enhanced results generated by our model exhibit superior color consistency and naturalness. Extensive experiments have shown the significant superiority of our mutual learning based method over thirteen competitors on the low-light task and ten methods on the underwater image enhancement task. In particular, our proposed Mutual Retinex respectively surpasses the state-of-the-art method MIRNet-v2 by 0.90 dB and 2.46 dB in PSNR on the LOL 1000 and FIVEK datasets, while with only 19.8% model parameters.
摘要:
This paper aims to solve large-scale and complex isogeometric topology optimization problems that consume significant computational resources. A novel isogeometric topology optimization method with a hybrid parallel strategy of CPU/GPU is proposed, while the hybrid parallel strategies for stiffness matrix assembly, equation solving, sensitivity analysis, and design variable update are discussed in detail. To ensure the high efficiency of CPU/GPU computing, a workload balancing strategy is presented for optimally distributing the workload between CPU and GPU. To illustrate the advantages of the proposed method, three benchmark examples are tested to verify the hybrid parallel strategy in this paper. The results show that the efficiency of the hybrid method is faster than serial CPU and parallel GPU, while the speedups can be up to two orders of magnitude.
作者:
Du, Fan;Hua, Qiaoqiao;Wang, Chunhua;Wang, Qingfang
期刊:
Journal of Differential Equations,2024年393:102-138 ISSN:0022-0396
通讯作者:
Wang, CH
作者机构:
[Hua, Qiaoqiao; Wang, Chunhua; Du, Fan; Wang, CH] Cent China Normal Univ, Sch Math & Stat, Wuhan 430079, Peoples R China.;[Wang, Chunhua; Wang, CH] Cent China Normal Univ, Key Lab Nonlinear Anal & Applicat, Minist Educ, Wuhan 430079, Peoples R China.;[Wang, Qingfang] Wuhan Polytech Univ, Sch Math & Comp Sci, Wuhan 430023, Peoples R China.
通讯机构:
[Wang, CH ] C;Cent China Normal Univ, Sch Math & Stat, Wuhan 430079, Peoples R China.;Cent China Normal Univ, Key Lab Nonlinear Anal & Applicat, Minist Educ, Wuhan 430079, Peoples R China.
摘要:
We revisit the following nonlinear critical elliptic equation -Delta u +V (vertical bar y'vertical bar,y '')u =u(N+2 /N-2), u > 0, u is an element of H-1(R-N), where (y', y '') is an element of R-3 x RN-3, V (vertical bar y vertical bar, y '') is a bounded non-negative function in R+ x RN-3. Assuming that r(2)V (r, y '')has a stable critical point (r(0), y(0)'') with r(0) > 0 and V (r(0), y(0)'') > 0, by using a modified finitedimensional reduction method and various local Pohozaev identities, we prove that the problem above has multi-piece of bubble solutions, whose energy can be made arbitrarily large. Since there involves a new variable (h) over bar in the concentrated points {x(j)(+/-)}(j=1)(m) during the reduction process, we have obtain a more precise estimate for the error term. And the bubble solutions are centered at points lying on the top and the bottom circles of a cylinder. Particularly, in one of these cases, the bubble solutions can concentrate at a pair of symmetric points relative to the origin. Our results present a new clustering type of blow-up phenomenon and we think the reason why this phenomenon can occur is mainly because that the function (r)2V (r, y '') has non-isolated critical points. (c) 2024 Elsevier Inc. All rights reserved.
摘要:
In this paper, we propose a underwater target detection method that optimizes YOLOv8s to make it more suitable for real-time and underwater environments. First, a lightweight FasterNet module replaces the original backbone of YOLOv8s to reduce the computation and improve the performance of the network. Second, we modify current bi-directional feature pyramid network into a fast one by reducing unnecessary feature layers and changing the fusion method. Finally, we propose a lightweight-C2f structure by replacing the last standard convolution, bottleneck module of C2f with a GSConv and a partial convolution, respectively, to obtain a lighter and faster block. Experiments on three underwater datasets, RUOD, UTDAC2020 and URPC2022 show that the proposed method has mAP50\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$_{50}$$\end{document} of 86.8%, 84.3% and 84.7% for the three datasets, respectively, with a speed of 156 FPS on NVIDIA A30 GPUs, which meets the requirement of real-time detection. Compared to the YOLOv8s model, the model volume is reduced on average by 24%, and the mAP accuracy is enhanced on all three datasets.
期刊:
International Journal of Remote Sensing,2023年44(22):6954-6980 ISSN:0143-1161
通讯作者:
Liu, CX
作者机构:
[Liu, Chaoxian; Zeng, Shan] Wuhan Polytech Univ, Sch Math & Comp Sci, Wuhan, Peoples R China.;[Sui, Haigang] Wuhan Univ, State Key Lab Informat Engn Surveying, Mapping & Remote Sensing, Wuhan, Peoples R China.
通讯机构:
[Liu, CX ] W;Wuhan Polytech Univ, Sch Math & Comp Sci, Wuhan, Peoples R China.
关键词:
Building damage assessment;aerial video;lightweight deep learning;ShuffleNet;damage levels
摘要:
A challenging problem for post-disaster emergency services is how to quickly and precisely acquire building damage with limited time and computation resources. With the development of unmanned aerial vehicle (UAV) technology and convolutional neural networks (CNN), using drone video and CNNs to determine the building damage has become one effective solution. In this research, we propose a stacked lightweight damage assessment model to overcome the current challenge in getting fast and precise post-disaster information based on aerial video datasets and artificial intelligence. Specifically, we developed an instance-level recognition building damage dataset based on aerial video. Then, we proposed a stacked lightweight ShuffleNet architecture that includes location and classification models to assess the building damage state. With regards to the location model, the lightweight network achieves a reduction in the model training time by approximately 37% and in the detection time by 44%, achieving similar location accuracy. As for the classification model, the trained model can achieve classification accuracy of approximately 83% for different damage levels by optimizing ShuffleNet. For post-disaster emergencies with limited time and computation resources, the proposed framework provides a valuable solution to better balance fast and precise building damage assessment.
摘要:
Building heterojunctions is a promising strategy for the achievement of highly efficient photocatalysis. Herein, a novel SnIn4S8@ZnO Z-scheme heterostructure with a tight contact interface was successfully constructed using a convenient two-step hydrothermal approach. The phase composition, morphology, specific surface area, as well as photophysical characteristics of SnIn4S8@ZnO were investigated through a series of characterization methods, respectively. Methylene blue (MB) was chosen as the target contaminant for photocatalytic degradation. In addition, the degradation process was fitted with pseudo-first-order kinetics. The as-prepared SnIn4S8@ZnO heterojunctions displayed excellent photocatalytic activities toward MB degradation. The optimized sample (ZS800), in which the molar ratio of ZnO to SnIn4S8 was 800, displayed the highest photodegradation efficiency toward MB (91%) after 20 min. Furthermore, the apparent rate constant of MB photodegradation using ZS800 (0.121 min-1) was 2.2 times that using ZnO (0.054 min-1). The improvement in photocatalytic activity could be ascribed to the efficient spatial separation of photoinduced charge carriers through a Z-scheme heterojunction with an intimate contact interface. The results in this paper bring a novel insight into constructing excellent ZnO-based photocatalytic systems for wastewater purification.
关键词:
Evolution of cooperation;Reinforcement learning;Differential privacy;Social network
摘要:
Cooperation is an essential behavior in multi-agent systems. Existing mechanisms have two common drawbacks. The first drawback is that malicious agents are not taken into account. Due to the diverse roles in the evolution of cooperation, malicious agents can exist in multi-agent systems, and they can easily degrade the level of cooperation by interfering with agent's actions. The second drawback is that most existing mechanisms have a limited ability to fit in different environments, such as different types of social networks. The performance of existing mechanisms heavily depends on some factors, such as network structures and the initial proportion of cooperators. To solve these two drawbacks, we propose a novel mechanism which adopts differential privacy mechanisms and reinforcement learning. Differential privacy mechanisms can be used to relieve the impact of malicious agents by exploiting the property of randomization. Reinforcement learning enables agents to learn how to make decisions in various social networks. In this way, the proposed mechanism can promote the evolution of cooperation in malicious social networks.
摘要:
With the increasing popularity of online fruit sales, accurately predicting fruit yields has become crucial for optimizing logistics and storage strategies. However, existing manual vision-based systems and sensor methods have proven inadequate for solving the complex problem of fruit yield counting, as they struggle with issues such as crop overlap and variable lighting conditions. Recently CNN-based object detection models have emerged as a promising solution in the field of computer vision, but their effectiveness is limited in agricultural scenarios due to challenges such as occlusion and dissimilarity among the same fruits. To address this issue, we propose a novel variant model that combines the self-attentive mechanism of Vision Transform, a non-CNN network architecture, with Yolov7, a state-of-the-art object detection model. Our model utilizes two attention mechanisms, CBAM and CA, and is trained and tested on a dataset of apple images. In order to enable fruit counting across video frames in complex environments, we incorporate two multi-objective tracking methods based on Kalman filtering and motion trajectory prediction, namely SORT, and Cascade-SORT. Our results show that the Yolov7-CA model achieved a 91.3% mAP and 0.85 F1 score, representing a 4% improvement in mAP and 0.02 improvement in F1 score compared to using Yolov7 alone. Furthermore, three multi-object tracking methods demonstrated a significant improvement in MAE for inter-frame counting across all three test videos, with an 0.642 improvement over using yolov7 alone achieved using our multi-object tracking method. These findings suggest that our proposed model has the potential to improve fruit yield assessment methods and could have implications for decision-making in the fruit industry.
通讯机构:
[Zhang, F ] W;Wuhan Polytech Univ, Sch Math & Comp Sci, Wuhan 430023, Peoples R China.
关键词:
Face anti -spoofing;Presentation attack;Disentangled representation;Deep learning;Face recognition
摘要:
Face recognition systems have been widely applied in security-related areas of our daily life. However, they are vulnerable to face spoofing attacks. Specifically, an attacker can fool a face recognition system into making false decisions, by presenting spoof face information (such as printed photos, replayed videos, etc.), rather than live face, to the face recognition system. Therefore, Face Anti-Spoofing (FAS) is critical for the security operation of a face recognition system.Deep learning-based FAS approaches show the best performance among existing FAS approaches. The basic idea of deep learning-based FAS approaches is to learn statistical representations capable of distin-guishing spoof faces from live ones, and then leverage the learned representations for live and spoof face classifications. Therefore, the learned representations play a key role in the performance of FAS. However, most existing approaches learn representations from representation-entangled spaces, in which critical and irrelevant representations for live and spoof face classifications are entangled with each other, thereby bringing a negative influence on the performance of a FAS system.To address the issue, we introduced a Twin Autoencoder Disentanglement (TAD) framework. Our TAD framework utilizes adversarial learning and a reconstruction strategy to disentangle both critical and irrelevant representations into two mutually independent representation spaces. In addition, to further suppress irrelevant representations that may remain in the critical representation space, we design a multi-branch supervision architecture (MSA) and embed it into TAD. MSA achieves the goal via imposing depth supervision and pattern supervision to the critical representation space. i.e., learning spatial rep-resentation (face depth information) and texture representation (face spoof pattern information).Experimental results on four typical public datasets, OULU-NPU, SiW, Replay-Attack, and CASIA-MFSD, demonstrate that our proposed TAD approach successfully disentangles critical and irrelevant represen-tations, and the two disentangled representations are more interpretable than state-of-the-art FAS meth-ods. The codes are available at https://github.com/TAD-FAS/TAD.& COPY; 2023 Elsevier B.V. All rights reserved.
通讯机构:
[Yang, H ] W;Wuhan Polytech Univ, Sch Math & Comp Sci, Wuhan 430040, Peoples R China.
关键词:
text classification;convolutional neural networks (CNN);attention mechanism;multi-layer feature fusion
摘要:
Text classification is one of the fundamental tasks in natural language processing and is widely applied in various domains. CNN effectively utilizes local features, while the Attention mechanism performs well in capturing content-based global interactions. In this paper, we propose a multi-layer feature fusion text classification model called CAC, based on the Combination of CNN and Attention. The model adopts the idea of first extracting local features and then calculating global attention, while drawing inspiration from the interaction process between membranes in membrane computing to improve the performance of text classification. Specifically, the CAC model utilizes the local feature extraction capability of CNN to transform the original semantics into a multi-dimensional feature space. Then, global attention is computed in each respective feature space to capture global contextual information within the text. Finally, the locally extracted features and globally extracted features are fused for classification. Experimental results on various public datasets demonstrate that the CAC model, which combines CNN and Attention, outperforms models that solely rely on the Attention mechanism. In terms of accuracy and performance, the CAC model also exhibits significant improvements over other models based on CNN, RNN, and Attention.