通讯机构:
[Jiang, XT ] C;Cent South Univ Forestry & Technol, Coll Comp & Informat Engn, Changsha 410018, Peoples R China.
关键词:
pine wilt disease;disaster assessment;UAV-based RGB imagery;instance segmentation
摘要:
Pine wilt disease (PWD) is one of the most concerning diseases in forestry and poses a considerable threat to forests. Since the deep learning approach can interpret the raw images acquired by UAVs, it provides an effective means for forest health detection. However, the fact that only PWD can be detected but not the degree of infection can be evaluated hinders forest management, so it is necessary to establish an effective method to accurately detect PWD and extract regions infected by PWD. Therefore, a Mask R-CNN-based PWD detection and extraction algorithm is proposed in this paper. Firstly, the extraction of image features is improved by using the advanced ConvNeXt network. Then, it is proposed to change the original multi-scale structure to PA-FPN and normalize it by using GN and WS methods, which effectively enhances the data exchange between the bottom and top layers under low Batch-size training. Finally, a branch is added to the Mask module to improve the ability to extract objects using fusion. In addition, a PWD region extraction module is proposed in this paper for evaluating the damage caused by PWD. The experimental results show that the improved method proposed in this paper can achieve 91.9% recognition precision, 90.2% mapping precision, and 89.3% recognition rate of the affected regions on the PWD dataset. It can effectively identify the distribution of diseased pine trees and calculate the damage proportion in a relatively accurate way to facilitate the management of forests.
摘要:
Rice is a crucial food crop, but it is frequently affected by diseases during its growth process. Some of the most common diseases include rice blast, flax leaf spot, and bacterial blight. These diseases are widespread, highly infectious, and cause significant damage, posing a major challenge to agricultural development. The main problems in rice disease classification are as follows: (1) The images of rice diseases that were collected contain noise and blurred edges, which can hinder the network's ability to accurately extract features of the diseases. (2) The classification of disease images is a challenging task due to the high intra-class diversity and inter-class similarity of rice leaf diseases. This paper proposes the Candy algorithm, an image enhancement technique that utilizes improved Canny operator filtering (the gravitational edge detection algorithm) to emphasize the edge features of rice images and minimize the noise present in the images. Additionally, a new neural network (ICAI-V4) is designed based on the Inception-V4 backbone structure, with a coordinate attention mechanism added to enhance feature capture and overall model performance. The INCV backbone structure incorporates Inception-iv and Reduction-iv structures, with the addition of involution to enhance the network's feature extraction capabilities from a channel perspective. This enables the network to better classify similar images of rice diseases. To address the issue of neuron death caused by the ReLU activation function and improve model robustness, Leaky ReLU is utilized. Our experiments, conducted using the 10-fold cross-validation method and 10,241 images, show that ICAI-V4 has an average classification accuracy of 95.57%. These results indicate the method's strong performance and feasibility for rice disease classification in real-life scenarios.
摘要:
This paper analyzes the performance of a unidimensional continuous‐variable quantum key distribution protocol using Gaussian‐modulated coherent states under a fast‐fading channel. It uses only one modulator for encoding and demonstrates its ability to tolerate a certain level of excessive channel noise while simplifying operations. This protocol has been proven to reduce costs within an acceptable range of performance losses. Abstract In this paper, the performance of a unidimensional continuous variable quantum key distribution protocol is analyzed using Gaussian modulated coherent state under fast fading channel. In the fast fading channel, both parties are connected in free space, resulting in a harsh propagation environment and pollution caused by atmospheric turbulence. This pollution makes it difficult for the communicators to determine the channel transmittance, which can only be estimated based on a probability distribution. To address this, only one modulator is used to code, which demonstrates performance equivalent to that of the symmetric modulated Gaussian coherent state protocol. The security of the protocol in the face of collective attacks is analyzed and it is proved that it can accept a certain amount of excessive channel noise while simplifying operations. Simultaneously, the impact of finite‐key length effects on the protocol is analyzed. It is also demonstrated that this protocol can reduce costs within an acceptable range of performance losses, making it more practical.
摘要:
Wrinkles, crucial for age estimation and skin quality assessment, present challenges due to their uneven distribution, varying scale, and sensitivity to factors like lighting. To overcome these challenges, this study presents facial wrinkle detection with multiscale spatial feature fusion based on image enhancement and an adaptively spatial feature fusion squeeze-and-excitation Unet network (ASFF-SEUnet) model. Firstly, in order to improve wrinkle features and address the issue of uneven illumination in wrinkle images, an innovative image enhancement algorithm named Coiflet wavelet transform Donoho threshold and improved Retinex (CT-DIR) is proposed. Secondly, the ASFF-SEUnet model is designed to enhance the accuracy of full-face wrinkle detection across all age groups under the influence of lighting factors. It replaces the encoder part of the Unet network with EfficientNet, enabling the simultaneous adjustment of depth, width, and resolution for improved wrinkle feature extraction. The squeeze-and-excitation (SE) attention mechanism is introduced to grasp the correlation and importance among features, thereby enhancing the extraction of local wrinkle details. Finally, the adaptively spatial feature fusion (ASFF) module is incorporated to adaptively fuse multiscale features, capturing facial wrinkle information comprehensively. Experimentally, the method excels in detecting facial wrinkles amid complex backgrounds, robustly supporting facial skin quality diagnosis and age assessment.
期刊:
JOURNAL OF INTELLIGENT & FUZZY SYSTEMS,2023年45(1):1743-1756 ISSN:1064-1246
通讯作者:
Wu, CT
作者机构:
[Jiang, Feng; Lin, Chunhua; Chen, Jing] Cent South Univ Forestry & Technol, Sch Comp & Informat Engn, Changsha, Peoples R China.;[Wu, Chutian] Louisiana State Univ, Dept Elect & Comp Engn, Baton Rouge, LA USA.;[Wu, CT] Louisiana State Univ, Dept Elect & Comp Engn, Baton Rouge, LA 70803 USA.
通讯机构:
[Wu, CT ] ;Louisiana State Univ, Dept Elect & Comp Engn, Baton Rouge, LA 70803 USA.
关键词:
I-LEACH;cluster head node;OMP
摘要:
New energy integration is thought to be one of the most potential solutions to support the power system with a sustainable energy infrastructure. However, new energy is an uncertain power generation resource, and the electricity generated by it has the characteristics of randomness, intermittency and reverse peak regulation. Its large-scale integration into the power grid makes the operation and reliability scheduling of the power system more challenging. It was important to build a wireless sensing and monitoring network to monitor the power and change trend of the new energy field (station) in real time. The energy consumption of wireless sensing monitoring network is an important factor to improve the reliability of new energy scheduling. Based on the energy consumption of the wireless sensing monitoring network built by the new energy scheduling, the compression sensing technology was integrated and the network routing protocol (I-LEACH protocol) was optimized. The sampling data was transmitted by the cluster head node at the compression rate of 0.6, the improved OMP (Orthogonal Matching Pursuit) algorithm was reconstructed to achieve reliable data transmission, and the network energy consumption was further reduced. Compared with the I-LEACH routing protocol network, the experiments show that the network residual energy of the proposed method increased by 22% and the life cycle increased by about 30%. This method is helpful to improve the reliability of new energy power dispatching system and it can provide reference for realizing the reliability scheduling of new energy power system.
摘要:
The model-based polarimetric decomposition is extensively studied due to its simplicity and clear physical interpretation of Polarimetric Synthetic Aperture Radar (PolSAR) data. Though there are many fine basic scattering models and well-designed decomposition methods, the overestimation of volume scattering (OVS) may still occur in highly oriented buildings, resulting in severe scattering mechanism ambiguity. It is well known that not only vegetation areas but also oriented buildings may cause intense cross-pol power. To improve the scattering mechanism ambiguity, an appropriate scattering model for oriented buildings and a feasible strategy to assign the cross-pol power between vegetation and oriented buildings are of equal importance. From this point of view, we propose a five-component decomposition method with a general rotated dihedral scattering model and an assignment strategy of cross-pol power. The general rotated dihedral scattering model is established to characterize the integral and internal cross-pol scattering from oriented buildings, while the assignment of cross-pol power between volume and rotated dihedral scattering is achieved by using an eigenvalue-based descriptor DOOB. In addition, a simple branch condition with explicit physical meaning is proposed for model parameters inversion. Experiments on spaceborne Radarsat−2 C band and airborne UAVSAR L band PolSAR datasets demonstrate the effectiveness and advantages of the proposed method in the quantitative characterization of scattering mechanisms, especially for highly oriented buildings.
关键词:
classification;attention module;infection severity;color space
摘要:
In this paper, a lightweight convolutional neural network model is proposed to diagnose the disease severity of tomato infection. Different regions of tomato leaf image had obvious threshold differences in Lab color space, and the grading label of disease infection degree of each tomato leaf image was obtained. At the same time, in order to solve the problems of low efficiency and general recognition accuracy of artificial recognition of tomato leaf diseases, and unable to accurately judge the tomato disease grade, this paper proposed a new method based on lightweight convolutional neural network, which selected ShuffleNet V2 as the backbone and applied Attention mechanisms that coordinate channel and spatial bidirectional perception. The results of a large number of cross-validation experiments showed that the accuracy of the network structure in classifying the severity of four common tomato leaf diseases and one healthy leaf infection was 91.817%, and the average accuracy was 85.496%.
通讯机构:
[Li, JJ ] C;Cent South Univ Forestry & Technol, Coll Comp Sci & Informat Technol, Changsha, Peoples R China.
摘要:
The health of the trees in the forest affects the ecological environment, so timely detection of Standing Dead Trees (SDTs) plays an important role in forest management. However, due to the large spatial scope of forests, it is difficult to find SDTs through conventional approaches such as field inventories. In recent years, the development of deep learning and Unmanned Aerial Vehicle (UAV) has provided technical support for low-cost real-time monitoring of SDTs, but the inability to fully utilize global features and the difficulty of small-scale SDTs detection have brought challenges to the detection of SDTs in visible light images. Therefore, this paper proposes a multi-scale attention mechanism detection method for identifying SDTs in UAV RGB images. This method takes Faster-RCNN as the basic framework and uses Swin-Transformer as the backbone network for feature extraction, which can effectively obtain global information. Then, features of different scales are extracted through the feature pyramid structure and feature balance enhancement module. Finally, dynamic training is used to improve the quality of the model. The experimental results show that the algorithm proposed in this paper can effectively identify the SDTs in the visible light image of the UAV with an accuracy of 95.9%. This method of SDTs identification can not only improve the efficiency of SDTs exploration, but also help relevant departments to explore other forest species in the future.
摘要:
Simple SummaryCurrently, more and more people keep dogs, and the gastrointestinal diseases of pet dogs have brought great losses to families. However, the condition of the dog's feces is closely related to the health of its stomach and intestines. We can know the intestinal condition of dogs in advance by scoring dog feces, and implement measures such as food adjustments. The PURINA FECAL SCORING CHART and the WALTHAM (TM) Faeces Scoring System are good at scoring dog feces visually, but some scoring experience is required. Therefore, this paper proposes an artificial intelligence method to automatically classify the condition of dog feces by combining their classification criteria with the assistance of animal experts. This method can achieve an accuracy of 88.27%, improving the diagnostic efficiency of veterinarians.In a natural environment, factors such as weathering and sun exposure will degrade the characteristics of dog feces; disturbances such as decaying wood and dirt are likely to make false detections; the recognition distinctions between different kinds of feces are slight. To address these issues, this paper proposes a fine-grained image classification approach for dog feces using MC-SCMNet under complex backgrounds. First, a multi-scale attention down-sampling module (MADM) is proposed. It carefully retrieves tiny feces feature information. Second, a coordinate location attention mechanism (CLAM) is proposed. It inhibits the entry of disturbance information into the network's feature layer. Then, an SCM-Block containing MADM and CLAM is proposed. We utilized the block to construct a new backbone network to increase the efficiency of fecal feature fusion in dogs. Throughout the network, we decrease the number of parameters using depthwise separable convolution (DSC). In conclusion, MC-SCMNet outperforms all other models in terms of accuracy. On our self-built DFML dataset, it achieves an average identification accuracy of 88.27% and an F1 value of 88.91%. The results of the experiments demonstrate that it is more appropriate for dog fecal identification and maintains stable results even in complex backgrounds, which may be applied to dog gastrointestinal health checks.
通讯机构:
[Zhou, GX ] C;Cent South Univ Forestry & Technol, Coll Comp & Informat Engn, Changsha, Hunan, Peoples R China.
关键词:
Apple disease detection;AMCFNet;Particle swarm optimization;K-means;GrabCut
摘要:
Traditional image processing technology has some difficulties in detecting apple diseases. For example, fruit trees, leaves, and branches can interfere with the detection of apple diseases; different diseases of apples are similar and difficult to distinguish. In order to solve these problems, a convolutional neural network based on adaptive multi-channel feature fusion (AMCFNet) is proposed to detect apple diseases. Firstly, we used K-means algorithm for particle swarm optimization to roughly segment the apple disease image to obtain candidate frames, and then used GrabCut to finely segment the candidate frames to remove the background interference of fruit trees, leaves, and branches. Finally, the segmented apple disease image is input to the AMCFNet for detection. Experiments show that our method has better performance than other algorithms, and can reach an accuracy of 99.25% during testing, and it takes only 2.6 s to detect 100 apples.
摘要:
A growing number of studies have confirmed the important role of microRNAs (miRNAs) in human diseases and the aberrant expression of miRNAs affects the onset and progression of human diseases. The discovery of disease-associated miRNAs as new biomarkers promote the progress of disease pathology and clinical medicine. However, only a small proportion of miRNA-disease correlations have been validated by biological experiments. And identifying miRNA-disease associations through biological experiments is both expensive and inefficient. Therefore, it is important to develop efficient and highly accurate computational methods to predict miRNA-disease associations. A miRNA-disease associations prediction algorithm based on Graph Convolutional neural Networks and Principal Component Analysis (GCNPCA) is proposed in this paper. Specifically, the deep topological structure information is extracted from the heterogeneous network composed of miRNA and disease nodes by a Graph Convolutional neural Network (GCN) with an additional attention mechanism. The internal attribute information of the nodes is obtained by the Principal Component Analysis (PCA). Then, the topological structure information and the node attribute information are combined to construct comprehensive feature descriptors. Finally, the Random Forest (RF) is used to train and classify these feature descriptors. In the five-fold cross-validation experiment, the AUC and AUPR for the GCNPCA algorithm are 0.983 and 0.988 respectively.
摘要:
Recent shadow detectors excel on simple datasets but encounter difficulties with facial shadow images under complex lighting due to the lack of annotated shadow masks, varying shadow sizes, and imbalances between the target and background. This leads to training difficulties, reduced accuracy, and slower processing, posing a significant challenge for precise and fast detection framework development. We collected images and created Extended Yale Shadow Detection Dataset (EYSDD). In comparison to other datasets, this dataset includes additional manually annotated shadow masks, making it suitable for training convolutional neural networks. To address this problem, we propose incorporating Channel Spatial Direction-aware Spatial Context (CSDSC) module into Fast Shadow Detection Network (FSDNet). Additionally, we introduce Selective Attention Inverted Residual Bottleneck (SAIRB) with Selective Attention Mechanism (SAM). Furthermore, we integrate Detail Enhancement Module (DEM), which refines low-level features, into Fast Face Shadow Detection Framework (FFSDF). Finally, compared to other methods, our model surpasses the baseline method FSDNet and the advanced method EVP by 3.5% and 1.9% in terms of IoU, and 1.8% and 4.3% in terms of Dice score, respectively. Our model has only 4.31 M parameters and achieves a computing speed of 0.022 sec/image, demonstrating superior efficiency compared to other methods. (c) 2023 The Author(s). Published by Elsevier B.V. on behalf of King Saud University. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).