January 2025
·
9 Reads
Artificial Intelligence in Agriculture
This page lists works of an author who doesn't have a ResearchGate profile or hasn't added the works to their profile yet. It is automatically generated from public (personal) data to further our legitimate goal of comprehensive and accurate scientific recordkeeping. If you are this author and want this page removed, please let us know.
January 2025
·
9 Reads
Artificial Intelligence in Agriculture
December 2024
Expert Systems with Applications
August 2024
·
11 Reads
·
2 Citations
Biosystems Engineering
July 2024
·
60 Reads
·
2 Citations
Animals
Using computer vision technology to estimate pig live weight is an important method to realize pig welfare. But there are two key issues that affect pigs’ weight estimation: one is the uneven illumination, which leads to unclear contour extraction of pigs, and the other is the bending of the pig body, which leads to incorrect pig body information. For the first one, Mask R-CNN was used to extract the contour of the pig, and the obtained mask image was converted into a binary image from which we were able to obtain a more accurate contour image. For the second one, the body length, hip width and the distance from the camera to the pig back were corrected by XGBoost and actual measured information. Then we analyzed the rationality of the extracted features. Three feature combination strategies were used to predict pig weight. In total, 1505 back images of 39 pigs obtained using Azure kinect DK were used in the numerical experiments. The highest prediction accuracy is XGBoost, with an MAE of 0.389, RMSE of 0.576, MAPE of 0.318% and R2 of 0.995. We also recommend using the Mask R-CNN + RFR method because it has fairly high precision in each strategy. The experimental results show that our proposed method has excellent performance in live weight estimation of pigs.
July 2024
·
21 Reads
Applied Intelligence
Vehicle density estimation plays a crucial role in traffic monitoring, providing the traffic management department with the traffic volume and traffic flow to monitor traffic safety. Currently, all vehicle density estimation methods based on Convolutional Neural Network (CNN) fall short in extracting global information due to the limited receptive field of the convolution kernel, resulting in the loss of vehicle information. Vision Transformer can capture long-distance dependencies and establish global context information through the self-attention mechanism, and is expected to be applied to vehicle density estimation. However, directly using Vision Transformer will result in the discontinuity of vehicle information between patches. In addition, the completion of vehicle density estimation also faces challenges, such as vehicle multi-scale changes, occlusion, and background noise. To solve the above challenges, a novel Overlapping Splitting Transformer Network (OSTNet) tailored for vehicle density estimation is designed. Overlapping splitting is proposed so that each patch shares half of its area, ensuring the continuity of vehicle information between patches. Dilation convolution is introduced to remove fixed-size position codes in order to provide accurate vehicle localization information. Meanwhile, Feature Pyramid Aggregation (FPA) module is utilized to obtain different scale information, which can tackle the issue of multi-scale changes. Moreover, a novel loss function called integrated density loss is designed to address the existing vehicle occlusion and background noise problems. The extensive experimental results on four open source datasets have shown that OSTNet outperforms the SOTA methods and can help traffic management department to better estimate vehicle density. The source code and pre-trained models are available at: https://github.com/quyang-hub/vehicle-density-estimation.
May 2024
·
4 Reads
·
1 Citation
Neural Networks
April 2024
·
16 Reads
·
1 Citation
Neural Computing and Applications
Heterogeneous domain adaptation (HDA) aims at facilitating the target model training by leveraging knowledge from the heterogeneous source domain. HDA is a challenging problem since the domains are not consistent in not only data distribution but also feature space. Most HDA methods attend to search for a subspace, where the features and the distributions across domains can be aligned. However, these methods barely consider the shared semantic label space of two domains and do not align the decision boundaries of the two domains, which may cause misclassification. To address the above issue, we propose a novel HDA method called Class centroid Matching and local Discriminative structure Preservation (CMDP), which can transfer discriminative semantic source knowledge to the target domain. Specifically, we project cross-domain samples to regress the label matrix to align the discriminative directions of two domains. Then, we introduce the inner product strategy to align the distance and angle of the class centroids across domains, such that the discriminative source knowledge can more sufficiently transfer to the target domain. Besides, to further improve the quality of the class centroids in each domain, we propose a novel cross-domain graph embedding strategy to exploit the structure information of data more thoroughly. A simple and efficient optimization algorithm is designed to solve the CMDP model. Extensive experiments on heterogeneous datasets validate the superiority of our proposal over several advanced methods.
March 2024
·
73 Reads
·
2 Citations
Object detection adopting deep-learning has strongly promoted the development of intensive aquaculture. However, shrimp larvae, as an important aquatic organism, are more difficult to be detected than others. On the one hand, they have indeed small sizes, which will cause them to be easily ignored due to the background noise pollution. On the other hand, affected by environmental factors and the fact that shrimp larvae like to move fast as jumping, the images of shrimp larvae often appear blurry. In order to obtain better shrimp larvae detection performance, we propose an improved anchor-free method called CAGNet in this paper. Compared with YOLOX_s, three structures including backbone, neck, and head have been improved in the proposed method. Firstly, we ameliorate the backbone by adding a coordinate attention module to extract more location information and semantic information of shrimp larvae at different levels. Secondly, an adaptively spatial feature fusion module is introduced to the neck. It can adaptively integrate effective shrimp larvae features from different levels and suppress the interference of conflicting information arising from the background. Moreover, in the head, we use GIoU module instead of conventional IoU for more accurate bounding box regression. We conducted experiments by collecting shrimp larvae data from a real aquaculture farm. Compared with the general object detection methods and previous related research, CAGNet has achieved better performance in Precision, Recall, F1 Score, and AP@0.5:0.95. Hence, the proposed method can be effectively applied to shrimp larvae detection in intensive aquaculture.
March 2024
·
24 Reads
·
1 Citation
IEEE Transactions on Neural Networks and Learning Systems
Heterogeneous domain adaptation (HDA) aims to address the transfer learning problems where the source domain and target domain are represented by heterogeneous features. The existing HDA methods based on matrix factorization have been proven to learn transferable features effectively. However, these methods only preserve the original neighbor structure of samples in each domain and do not use the label information to explore the similarity and separability between samples. This would not eliminate the cross-domain bias of samples and may mix cross-domain samples of different classes in the common subspace, misleading the discriminative feature learning of target samples. To tackle the aforementioned problems, we propose a novel matrix factorization-based HDA method called HDA with generalized similarity and dissimilarity regularization (HGSDR). Specifically, we propose a similarity regularizer by establishing the cross-domain Laplacian graph with label information to explore the similarity between cross-domain samples from the identical class. And we propose a dissimilarity regularizer based on the inner product strategy to expand the separability of cross-domain labeled samples from different classes. For unlabeled target samples, we keep their neighbor relationship to preserve the similarity and separability between them in the original space. Hence, the generalized similarity and dissimilarity regularization is built by integrating the above regularizers to facilitate cross-domain samples to form discriminative class distributions. HGSDR can more efficiently match the distributions of the two domains both from the global and sample viewpoints, thereby learning discriminative features for target samples. Extensive experiments on the benchmark datasets demonstrate the superiority of the proposed method against several state-of-the-art methods.
January 2024
·
37 Reads
Environmental Science and Pollution Research
The detection and prediction of pathogenic microorganisms play a crucial role in the sustainable development of the aquaculture industry. Currently, researchers mainly focus on the prediction of water quality parameters such as dissolved oxygen for early warning. To provide early warning directly from the pathogenic source, this study proposes an innovative approach for the detection and prediction of pathogenic microorganisms based on yellow croaker aquaculture. Specifically, a method based on quantitative polymerase chain reaction (qPCR) is designed to detect the Cryptocaryon irritans (Cri) pathogenic microorganisms. Furthermore, we design a predictive combination model for small samples and high noise data to achieve early warning. After performing wavelet analysis to denoise the data, two data augmentation strategies are used to expand the dataset and then combined with the BP neural network (BPNN) to build the fusion prediction model. To ensure the stability of the detection method, we conduct repeatability and sensitivity tests on the designed qPCR detection technique. To verify the validity of the model, we compare the combined BPNN to long short-term memory (LSTM). The experimental results show that the qPCR method provides accurate quantitative measurement of Cri pathogenic microorganisms, and the combined model achieves a good level. The prediction model demonstrates higher accuracy in predicting Cri pathogenic microorganisms compared to the LSTM method, with evaluation indicators including mean absolute error (MAE), recall rate, and accuracy rate. Especially, the accuracy of early warning is increased by 54.02%.
... Recently, computer vision technology has been applied in various fields [14], such as target detection, image super-resolution, and population counting [15]. Regarding the counting of shrimp larvae [16][17][18][19], traditional image processing techniques primarily utilize image segmentation and object detection methods to recognize and count target images. Kesvarakul et al. counted shrimp larvae in images by converting them into binary images with a threshold [20]. ...
August 2024
Biosystems Engineering
... Machine learning approaches can be particularly effective in analyzing datasets with varying standards [12]. Currently, models trained on various parameters such as images, body size, and age have been developed to predict the healthy weight of commercial species, including horses, pigs, and dogs [13][14][15]. Machine learning or deep learning algorithms facilitate the analysis of vast and complex datasets, enabling conservationists to monitor wildlife populations more efficiently and accurately [16,17]. However, the establishment of predictive models for body weight across the entire lifetime is challenging due to difficulties in data acquisition, particularly the limited number of artificially bred individuals. ...
July 2024
Animals
... After feature transformation, the mainstream approach is to minimize the difference in data distribution [29,30]. Some researchers focus on optimizing the discriminative ability of the classifier with source domain knowledge [31][32][33]. Although previous methods have been successful and have focused on domain alignment, the inherent geometric structure information has not been taken into consideration. ...
April 2024
Neural Computing and Applications
... Usually, larger models typically have more parameters and deeper network structures, allowing to learn and capture richer and more abstract features. Such models possess enhanced feature extraction capabilities, enabling better adaptation to the complex data distributions (Siripattanadilok and Siriborvornratanakul 2024;Zhang et al. 2024). But, with the rising model size, there is also a corresponding increase in the computational and storage costs. ...
March 2024
... Ensuring stego text is indistinguishable from randomly sampled language model text is not sufficient for real-world applications. In real-world scenarios, sensors can access extensive real-world human data from the domain as cover samples to train stego detectors, a common setup in existing steganalysis tasks [11][12][13]. ...
January 2023
IEEE Transactions on Information Forensics and Security
... While many studies delve deeper into enhancing a model's adaptability [63][64][65][66][67][68], these often involve significant changes such as altered model architectures. Such complex modifications might be beyond the skillset of conservationists, whose primary aims are to census/monitor wildlife. ...
October 2023
Biosystems Engineering
... To select valuable samples from multisource data, the ATL method was constructed to adaptively assign sample weights to improve domainadaptive recognition results [14]. To learn and exploit the intrinsic graph structure of cross-source samples, probabilistic-based graph embedding methods were developed to learn the category-based nearest-neighbor information of the source and target domain samples and thus maintain the original intrinsic graph structure in the domain adaptation results [15]. To reduce the cross-source sample distribution differences and maintain the sample clustering information, the CMMS method was constructed to combine the class matching and the Kmean clustering term, improving the discriminative ability of the domain adaptation results [16]. ...
December 2022
IEEE Transactions on Image Processing
... The matrix ℓ 2,p norm is a nonconvex and nonsmooth function. And it has been applied to image processing [20], machine learning [23,11], feature selection [19,31], multi-view classification [33], etc. To measure the linear structural sparsity of the sparse noise tensor S, we extend the matrix ℓ 2,p norm for group sparsity to its tensor form. ...
November 2022
Engineering Applications of Artificial Intelligence
... The framework's effectiveness is demonstrated through experiments on the ImageNet VID dataset and real-world tasks. Researchers have also utilized image interpolation to detect fish under varying color distortions [242]. For underwater crack detection, Huang et al. [243] employ image-to-image translation, such as CycleGAN, to generate synthetic underwater crack images from above-water counterparts. ...
July 2022
Computers and Electronics in Agriculture
... To improve the sparsity of the model, we add 2,1 -norm regularization term for each view, which can be expressed by ∑ ‖ ‖ , = [24], the norm ‖ ‖ , need to be relaxed by Tr ( ) for additional optimization [16]. Finally, the ultimate objective function can be expressed as: ...
March 2022
Signal Processing