Search

Visible-infrared person re-identification aims to solve the matching problem between cross-camera and cross-modal person images. Existing methods strive to perform better cross-modal alignment, but often neglect the critical importance of feature enhancement for achieving better performance. Therefore, we proposed an effective method that combines both modal alignment and feature enhancement. Specifically, we introduced Visible-Infrared Modal Data Augmentation (VIMDA) for visible images to improve modal alignment. Margin MMD-ID Loss was also used to further enhance modal alignment and optimize model convergence. Then, we proposed Multi-Grain Feature Extraction (MGFE) Structure for feature enhancement to further improve recognition performance. Extensive experiments have been carried out on SYSY-MM01 and RegDB. The result indicates that our method outperforms the current state-of-the-art method for visible-infrared person re-identification. Ablation experiments verified the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

The mounting behaviour of dairy cows is driven by oestrus and is also related to their welfare. To improve the accuracy and speed of the detection of mounting of dairy cows in dense scenes, a detection model for the mounting behaviour of dairy cows was developed in this study based on the feature enhancement module. Firstly, an improved attention module (C3GC-3) based on global context information and convolution was proposed to capture long-distance dependence. Then, a feature enhancement module based on atrous spatial pyramid pooling and the C3GC-3 was designed to realise the multiscale fusion of high-level semantic information and improve the feature extraction ability of the model for dense dairy cows images. Finally, the K-means clustering algorithm was used to obtain new anchors for the mounting behaviour of dairy cows, and CIoU was used to optimise the loss function. A camera was installed on a farm containing 200 dairy cows for data collection. The mosaic method was used to expand the 2668 images of the mounting behaviour of dairy cows to train the model, and the remaining 675 images were used to test the model. The experimental results showed that the proposed model had a high inference speed of 61 fps, and the detection time for each image was 16.3 ms, which met the real-time performance requirements for detecting mounting in dairy cows. The mean average precision of the model was 94.3%, which was 5.9% higher than that of YOLOv5l. The proposed model showed promising results regarding the mounting of dairy cows and might be used in any weather. • A mounting behaviour dataset of group-raised dairy cows in dense scenes was proposed.. • ASPP can improve the accuracy of multi-scale object detection. • Attention mechanism can improve the feature extraction ability of the model. • Mean average precision model was 94.3%, which is 5.9% higher than that of YOLOv5l. [ABSTRACT FROM AUTHOR]

Feature selection is one of the most important techniques to deal with the high-dimensional data for a variety of machine learning and data mining tasks, such clustering, classification, and retrieval, etc. Fuzziness is a widespread nature of data in nature human society. However, most existing feature selection methods ignore the existence of fuzziness in the data, resulting in sub-optimal feature subsets. To address the problem, we propose a novel unsupervised feature selection method, called Unsupervised Discriminative Projection for Feature Selection (UDPFS) to select discriminative features by conducting fuzziness learning and sparse learning, simultaneously. Specifically, we use projection matrix transform data as its low-dimensional representation, which are partitioned into clusters by using membership matrix with sparse constraint. In addition, $\ell _{2, 1}$ ℓ 2 , 1 -norm regularization is applied to the projection matrix. Then, a discriminative projection matrix with row sparse is obtained by perform fuzziness learning and sparse learning, simultaneously. An effective alternative optimization algorithm is proposed to solve the objective function. Evaluate experimental results on several real-world datasets show the effectiveness and superiority of the proposed unsupervised feature selection method. [ABSTRACT FROM AUTHOR]

Cow recognition forms the foundation of smart livestock management. Current closed-set cow recognition models can exclusively identify cows within their training set and are ill-equipped to recognize other subjects in the open world. Additionally, there is a dearth of comprehensive research on open-set cow recognition. Existing open-set recognition models not only exhibit suboptimal accuracy but also impose a substantial burden on hardware resources due to their extensive parameterization. These challenges hinder the practical deployment of cow recognition models. This study introduces an innovative open-set metric learning-based recognition framework for cow-back patterns, aiming to rectify a significant limitation of individual cow recognition models, which is their inability to identify cows not included in the training set. The proposed framework combines various loss functions, metric methods, and backbone networks. This integration enables the open-set recognition of cow back pattern images, thereby facilitating the identification of cows previously unrecognized by the model. To mitigate hardware resource consumption, we have devised a novel ultra-lightweight backbone network known as LightCowsNet. This network draws inspiration from existing lightweight backbone networks such as MobileFaceNet, MobileViT, and EfficientNetV2. Its purpose is to extract features from cow back pattern images efficiently. LightCowsNet employs attention mechanisms, inverted residual structures, and depthwise separable convolutions. LightCowsNet first uses attention mechanisms, inverted residual structures, and depthwise separable convolutions to design multiple new feature extraction modules. These modules, which have different structures, are subsequently placed to extract different levels of image information, which enables complete extraction of the textural information of the cows' back patterns. The present study reorganized the Cows2021 dataset to render it suitable for open-set recognition of cow-back patterns, with the test set comprising image pairs. The results revealed that using A-SoftMax as the loss function and Euclidean distance as the metric method enabled LightCowsNet to achieve the highest accuracy of 94.26 %, with a model weight space occupation of only 4.06 MB. Compared to MobileFaceNet, MobileViT, and EfficientNetV2, LightCowsNet achieved 6.24 %, 8.82 %, and 2.3 % greater accuracy on the test set, respectively. Its weight also decreased by 0.71 MB, 0.24 MB, and 4.3 MB, respectively. These results demonstrate that the proposed model achieved both accuracy improvement and model lightweightness, and these findings could serve as reference solutions for intelligent farming on cow farms. [ABSTRACT FROM AUTHOR]

The Internet of Things (IoT), cloud, and fog computing paradigms provide a powerful large-scale computing infrastructure for a variety of data and computation-intensive applications. These cutting-edge computing infrastructures, however, are nevertheless vulnerable to serious security and privacy risks. One of the most important countermeasures against cybersecurity threats is intrusion detection and prevention systems, which monitor devices, networks, and systems for malicious activity and policy violations. The detection and prevention systems range from antivirus software to hierarchical systems that monitor the traffic of whole backbone networks. At the moment, the primary defensive solutions are based on malware feature extraction. Most known feature extraction algorithms use byte N-gram patterns or binary strings to represent log files or other static information. The information taken from program files is expressed using word embedding (GloVe) and a new feature extraction method proposed in this article. As a result, the relevant vector space model (VSM) will incorporate more information about unknown programs. We utilize convolutional neural network (CNN) to analyze the feature maps represented by word embedding and apply Softmax to fit the probability of a malicious program. Eventually, we consider a program to be malicious if the probability is greater than 0.5; otherwise, it is a benign program. Experimental result shows that our approach achieves a level of accuracy higher than 98%. [ABSTRACT FROM AUTHOR]

Hyperspectral anomaly detection (HAD) has drawn a significant attention of late due to its importance in many military and civilian applications. In this article, a fast hyperspectral anomaly detector that combines multiple features and isolation forest is proposed. This approach, which is based on the assumption that the anomalous pixels are more susceptible to isolation than the background pixels, consists of two main parts. First, the spectral, Gabor, extended morphological profile (EMP) and extended multiattribute profile (EMAP) features are extracted from the hyperspectral image (HSI). Next, the isolation forest of each feature is constructed using the subsampling strategy. This combination of multiple features can exploit both the spectral and spatial information of the HSI, thereby improving the anomaly detection performance significantly. Compared with eight state-of-the-art HAD methods, the experimental results on four real hyperspectral data sets demonstrate that the performance of our proposed approach is quite competitive in terms of detection accuracy and running time. [ABSTRACT FROM AUTHOR]

Abstract Locality preserving projection (LPP) is a classical tool for dimensionality reduction and feature extraction. It usually makes use of the ℓ 2 -norm criterion for optimization, and is thus sensitive to outliers. In order to achieve robustness, LPP-L1 is proposed by employing the ℓ 1 -norm as distance criterion. However, the edge weights of LPP-L1 measure only the dissimilarity of pairs of vertices and ignore the preservation of the similarity. In this paper, we develop a novel algorithm, termed as ILPP-L1, in which the ℓ 1 -norm is utilized to obtain robustness and the similarities of pairs of vertices are effectively preserved, simultaneously. ILPP-L1 is robust to outliers because of the use of the ℓ 1 -norm. The ℓ 1 -norm minimization problem is directly solved, which ensures the preservation of the similarity of pairs of vertices. The solution is justified to converge to local minimum. In addition, ILPP-L1 avoids small sample size problem. Experiment results on benchmark databases confirm the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Liquid chromatography coupled with mass spectrometry (LC-MS) has shown great potential in analysis complex samples. However, informative feature extraction is still challenge since the electrospray ionization in LC-MS tends to produce ninety percent or more ions not originated from compounds of interest. The concept of pure ion chromatogram (PIC) is effective to extract informative ions, but tradition PIC methods are time-consuming because of their theories and programming languages. In this study, we present a novel method, called Fast Pure Ions Chromatograms (FPIC), for extracting PICs from raw LC-MS dataset effectively and quickly. This method can search ion of PIC from its maximum bi-directionally and adaptively, which can improve the stability and reduce the computation time drastically. A further speedup has been achieved by exploiting modern software engineering techniques. FPIC was validated by analyzing four LC-MS datasets: MM14 and MM48, simulated MM48 and quantification (MTBLS234) datasets. Results show that FPIC outperformed traditional methods in the recall, precision and F-score, and it has good reliability of quantification. Furthermore, the method is very fast with few adjustable parameters, which leads to an approximately 125-fold speedup over PITracer and 18-fold speedup over XCMS. An open source implementation of the FPIC method is available at https://github.com/zmzhang/pymass . [ABSTRACT FROM AUTHOR]

• This article propose a dual-branch, efficient, channel attention (DECA) module which uses a dual-branch 1D convolution operation to filter effective feature information. • It also introduces an adaptive convolution kernel parameter k and an adaptive parameter α to participate in the reverse training of the model. • The DECA_ResNet model is proposed to realize crop disease recognition. • We verified the DECA_ResNet model on the AI Challenger 2018 dataset, PlantVillage dataset, and self-collected cucumber disease dataset; the disease recognition accuracies are 86.35%, 99.74% and 98.54%, respectively. Efficient and accurate recognition of crop diseases plays an important role in disease prevention. Aiming at the low accuracy of existing crop disease recognition methods, we improve the attention mechanism and residual neural network (ResNet) to propose a dual-branch, efficient, channel attention (DECA)-based crop disease recognition model. The DECA module uses a dual-branch 1D convolution operation to filter effective feature information. It also introduces an adaptive convolution kernel parameter k and an adaptive parameter α to participate in the reverse training of the model so that the model can independently select effective features and establish dependencies between channels. Then, the DECA module is added to the residual module to recalibrate the channel characteristics and improve the characteristic representability of the residual module. Finally, a DECA_ResNet model is proposed to realize crop disease recognition. The crop disease model based on improved attention is verified on the AI Challenger 2018 dataset, PlantVillage dataset, and self-collected cucumber disease dataset; the disease recognition accuracies are 86.35%, 99.74% and 98.54%, respectively, which are higher than those of the ResNet and squeeze-and-excitation network (SENet) before improvement. The recognition accuracy of the proposed model in the PlantVillage dataset is higher than that of existing models. The experimental results show that the proposed plant recognition model with 18 layers (DECA_ResNet18) can achieve a high recognition accuracy. The DECA module can independently select each branch feature without causing a significant increase in the number of parameters, which improves the plant disease recognition accuracy and reduces the extraction of redundant features. [ABSTRACT FROM AUTHOR]

Linear discriminant analysis (LDA) has been proven to be effective in dimensionality reduction. However, the performance of LDA depends on the consistency assumption of the global structure and the local structure. Some work extended LDA along this line of research and proposed local formulations of LDA. Unfortunately, the learning scheme of these algorithms is suboptimal in that the intrinsic relationship between data points is pre-learned in the original space, which is usually affected by the noise and redundant features. Besides, the time cost is relatively high. To alleviate these drawbacks, we propose a Fast Locality Discriminant Analysis framework (FLDA), which has three advantages: (1) It can divide a non-Gaussian distribution class into many sub-blocks that obey Gaussian distributions by using the anchor-based strategy. (2) It captures the manifold structure of data by learning the fuzzy membership relationship between data points and the corresponding anchor points, which can reduce computation time. (3) The weights between data points and anchor points are adaptively updated in the subspace where the irrelevant information and the noise in high-dimensional space have been effectively suppressed. Extensive experiments on toy data sets, UCI benchmark data sets and imbalanced data sets demonstrate the efficiency and effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Linear discriminant analysis (LDA) has been proven to be effective in dimensionality reduction. However, the performance of LDA depends on the consistency assumption of the global structure and the local structure. Some work extended LDA along this line of research and proposed local formulations of LDA. Unfortunately, the learning scheme of these algorithms is suboptimal in that the intrinsic relationship between data points is pre-learned in the original space, which is usually affected by the noise and redundant features. Besides, the time cost is relatively high. To alleviate these drawbacks, we propose a Fast Locality Discriminant Analysis framework (FLDA), which has three advantages: (1) It can divide a non-Gaussian distribution class into many sub-blocks that obey Gaussian distributions by using the anchor-based strategy. (2) It captures the manifold structure of data by learning the fuzzy membership relationship between data points and the corresponding anchor points, which can reduce computation time. (3) The weights between data points and anchor points are adaptively updated in the subspace where the irrelevant information and the noise in high-dimensional space have been effectively suppressed. Extensive experiments on toy data sets, UCI benchmark data sets and imbalanced data sets demonstrate the efficiency and effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Within the current process of large-scale dairy-cattle breeding, to address the problems of low recognition-accuracy and significant recognition-error associated with existing visual methods, we propose a method for recognizing the feeding behavior of dairy cows, one based on an improved RefineMask instance-segmentation model, and using high-quality detection and segmentation results to realize the recognition of the feeding behavior of dairy cows. Firstly, the input features are better extracted by incorporating the convolutional block attention module into the residual module of the feature extraction network. Secondly, an efficient channel attention module is incorporated into the neck design to achieve efficient integration of feature extraction while avoiding the surge of parameter volume computation. Subsequently, the GIoU loss function is used to increase the area of the prediction frame to optimize the convergence speed of the loss function, thus improving the regression accuracy. Finally, the logic of using mask information to recognize foraging behavior was designed, and the accurate recognition of foraging behavior was achieved according to the segmentation results of the model. We constructed, trained, and tested a cow dataset consisting of 1000 images from 50 different individual cows at peak feeding times. The method's effectiveness, robustness, and accuracy were verified by comparing it with example segmentation algorithms such as MSRCNN, Point_Rend, Cascade_Mask, and ConvNet_V2. The experimental results show that the accuracy of the improved RefineMask algorithm in recognizing the bounding box and accurately determining the segmentation mask is 98.3%, which is higher than that of the benchmark model by 0.7 percentage points; for this, the model parameter count size was 49.96 M, which meets the practical needs of local deployment. In addition, the technologies under study performed well in a variety of scenarios and adapted to various light environments; this research can provide technical support for the analysis of the relationship between cow feeding behavior and feed intake during peak feeding periods. [ABSTRACT FROM AUTHOR]

Semisupervised band selection (BS) technique plays an important role in processing hyperspectral images (HSIs) because of its superiority of using the limited labeled data and plentiful unlabeled data to select the discriminative and informative feature, which copes with the problem of high-dimensional and scare labeled samples of HSIs. Among semisupervised BS models, graph-based methods are superior to others in many situations and have received more and more attention. However, traditional graph-based models construct a similarity matrix and select valuable bands independently. The similarity matrix remains constant, which will damage the local manifold structure and lead to a suboptimal result. To solve this problem, we propose a semisupervised band selection with an optimal graph (BSOG) approach, which performs BS and local structure learning simultaneously. Instead of fixing the input similarity matrix, the similarity matrix is updated constantly to learn a better local structure. Besides, the learned similarity matrix is adaptive. Then, the optimal band subset can be selected by analyzing the obtained projection matrix $\boldsymbol W$. An efficient and simple optimization algorithm is proposed to solve this model. Experiments on four real HSIs data validate the effectiveness of the proposed model. [ABSTRACT FROM AUTHOR]

Semi-supervised learning models for multiview data are important in image classification tasks, since heterogeneous features are easy to obtain and semi-supervised schemes are economical and effective. To model the view importance, conventional graph-based multiview learning models learn a linear combination of views while assuming a priori weights distribution. In this paper, we present a novel structural regularized semi-supervised model for multiview data, termed Adaptive MUltiview SEmi-supervised model (AMUSE). Our new model learns weights from a priori graph structure, which is more reasonable than weight regularization. Theoretical analysis reveals the significant difference between AMUSE and the prior arts. An efficient optimization algorithm is provided to solve the new model. Experimental results on six real-world data sets demonstrate the effectiveness of the structural regularized weights learning scheme. [ABSTRACT FROM AUTHOR]

A Concurrent-wavelength Reconstruction Algorithm (CRA) based on multi-wavelength information fusion is proposed in this paper that aims to further improve the accuracy of Fluorescence Molecular Tomography (FMT) reconstruction. Combining multi-spectral data with FMT technology, the information of 650 and 750 nm wavelengths near-infrared was used to increase the feature information of the dominant 850 nm wavelength near-infrared effectively. Principal component analysis, which can remove redundant information and achieve data dimensionality reduction, was then utilized to extract the feature information. Finally, tomographic reconstruction of the anomalies was performed based on the stacked auto-encoder neural network model. The comparison results of numerical experiments showed that the reconstruction effect of CRA was superior to the performance of the single wavelength model. The correlation coefficient between CRA reconstructed anomalies' fluorescence yield values and the real fluorescence yield values remained at 0.95 or more under the noise of different levels of signal-to-noise ratios. Therefore, the CRA proposed in this paper could effectively improve on the ill-posedness of the inverse problem, which could further enhance the accuracy of FMT reconstruction. [ABSTRACT FROM AUTHOR]

Linear discriminant analysis (LDA) is one of commonly used supervised subspace learning methods. However, LDA will be powerless faced with the no-label situation. In this paper, the unsupervised LDA (Un-LDA) is proposed and first formulated as a seamlessly unified objective optimization which guarantees convergence during the iteratively alternative solving process. The objective optimization is in both the ratio trace and the trace ratio forms, forming a complete framework of a new approach to jointly clustering and unsupervised subspace learning. The extension of LDA into Un-LDA enables to not only complete unsupervised subspace learning via the explicitly presented subspace projection matrix but also simultaneously finish clustering and even clustering out-of-sample data via the explicitly presented transformation matrix. To overcome the difficulty in solving the non-convex objective optimization, we mathematically prove that the Un-LDA optimization in both forms can be transformed into the simple K-means clustering optimization when the subspace is determined. The Un-LDA optimization is eventually completed by alternatively optimizing the clusters using K-means and the subspace using the supervised LDA methods and iterating this whole process until convergence or stopping criterion. The experiments demonstrate that our proposed Un-LDA algorithms are comparable or even much superior to the counterparts. [ABSTRACT FROM AUTHOR]

Since technologies in image fusion, image splicing, and target recognition have developed rapidly, as the basis of many image applications, the performance of image registration directly affects subsequent work. In this work, for rich features of satellite-borne optical imagery such as panchromatic and multispectral images, the Harris corner algorithm is combined with the scale invariant feature transform (SIFT) operator for feature point extraction. Our rough matching strategy uses the K-D (K-Dimensional) tree combined with the BBF (Best Bin First) method, and the similarity measure is the nearest neighbor/the second-nearest neighbor ratio. Finally, a triangle-area representation (TAR) algorithm is utilized to eliminate false matches in order to ensure registration accuracy. The performance of the proposed algorithm is compared with existing popular algorithms. The experimental results indicate that for visible light and multi-spectral satellite remote sensing images of different sizes and different sources, the proposed algorithm in this work is excellent in accuracy and efficiency. [ABSTRACT FROM AUTHOR]