Explore the vast range of titles available.

To improve the issue of low-frequency and high-frequency components from feature maps being treated equally in existing image super-resolution reconstruction methods, the paper proposed an image super-resolution reconstruction method using attention mechanism with feature map to facilitate reconstruction from original low-resolution images to multi-scale super-resolution images. The proposed model consists of a feature extraction block, an information extraction block, and a reconstruction module. Firstly, the extraction block is used to extract useful features from low-resolution images, with multiple information extraction blocks being combined with the feature map attention mechanism and passed between feature channels. Secondly, the interdependence is used to adaptively adjust the channel characteristics to restore more details. Finally, the reconstruction module reforms different scales high-resolution images. The experimental results can demonstrate that the proposed method can effectively improve not only the visual effect of images but also the results on the Set5, Set14, Urban100, and Manga109. The results can demonstrate the proposed method has structurally similarity to the image reconstruction methods. Furthermore, the evaluating indicator of Peak Signal to Noise Ratio (PSNR) and Structural Similarity Index (SSIM) has been improved to a certain degree, while the effectiveness of using feature map attention mechanism in image super-resolution reconstruction applications is useful and effective.

This article studies the Gram random matrix model G = 1 T Σ ⊺ Σ , Σ = σ ( W X ) , classically found in the analysis of random feature maps and random neural networks, where X = [x₁,...,xT ] ∈ ℝp×T is a (data) matrix of bounded norm, W ∈ ℝn×p is a matrix of independent zero-mean unit variance entries and σ : ℝ → ℝ is a Lipschitz continuous (activation) function—σ(WX) being understood entry-wise. By means of a key concentration of measure lemma arising from nonasymptotic random matrix arguments, we prove that, as n, p, T grow large at the same rate, the resolvent Q = (G + γIT )−1, for γ > 0, has a similar behavior as that met in sample covariance matrix models, involving notably the moment Φ = T n E[ G ] , which provides in passing a deterministic equivalent for the empirical spectral measure of G. Application-wise, this result enables the estimation of the asymptotic performance of single-layer random neural networks. This in turn provides practical insights into the underlying mechanisms into play in random neural networks, entailing several unexpected consequences, as well as a fast practical means to tune the network hyperparameters.

In the remote sensing field, synthetic aperture radar (SAR) is a type of active microwave imaging sensor working in all-weather and all-day conditions, providing high-resolution SAR images of objects such as marine ships. Detection and instance segmentation of marine ships in SAR images has become an important question in remote sensing, but current deep learning models cannot accurately quantify marine ships because of the multi-scale property of marine ships in SAR images. In this paper, we propose a multi-scale feature pyramid network (MS-FPN) to achieve the simultaneous detection and instance segmentation of marine ships in SAR images. The proposed MS-FPN model uses a pyramid structure, and it is mainly composed of two proposed modules, namely the atrous convolutional pyramid (ACP) module and the multi-scale attention mechanism (MSAM) module. The ACP module is designed to extract both the shallow and deep feature maps, and these multi-scale feature maps are crucial for the description of multi-scale marine ships, especially the small ones. The MSAM module is designed to adaptively learn and select important feature maps obtained from different scales, leading to improved detection and segmentation accuracy. Quantitative comparison of the proposed MS-FPN model with several classical and recently developed deep learning models, using the high-resolution SAR images dataset (HRSID) that contains multi-scale marine ship SAR images, demonstrated the superior performance of MS-FPN over other models.

We introduce a new embedding technique based on a nested barycentric coordinate system. We show that our embedding can be used to transform the problems of polyhedron approximation, piecewise linear classification and convex regression into one of finding a linear classifier or regressor in a higher dimensional (but nevertheless quite sparse) representation. Our embedding maps a piecewise linear function into an everywhere-linear function, and allows us to invoke well-known algorithms for the latter problem to solve the former. We explain the applications of our embedding to the problems of approximating separating polyhedra—in fact, it can approximate any convex body and unions of convex bodies—as well as to classification by separating polyhedra, and to piecewise linear regression.

Schizophrenia is a serious chronic mental disorder that significantly affects daily life. Electroencephalography (EEG), a method used to measure mental activities in the brain, is among the techniques employed in the diagnosis of schizophrenia. The symptoms of the disease typically begin in childhood and become more pronounced as one grows older. However, it can be managed with specific treatments. Computer-aided methods can be used to achieve an early diagnosis of this illness. In this study, various machine learning algorithms and the emerging technology of quantum-based machine learning algorithm were used to detect schizophrenia using EEG signals. The principal component analysis (PCA) method was applied to process the obtained data in quantum systems. The data, which were reduced in dimensionality, were transformed into qubit form using various feature maps and provided as input to the Quantum Support Vector Machine (QSVM) algorithm. Thus, the QSVM algorithm was applied using different qubit numbers and different circuits in addition to classical machine learning algorithms. All analyses were conducted in the simulator environment of the IBM Quantum Platform. In the classification of this EEG dataset, it is evident that the QSVM algorithm demonstrated superior performance with a 100% success rate when using Pauli X and Pauli Z feature maps. This study serves as proof that quantum machine learning algorithms can be effectively utilized in the field of healthcare.

In some complex circumstances, the detection of conflagration mostly depends on smog detectors, which have lots of limitations in precision, efficiency and safety. If we make full use of object detection algorithms to detect the flame in industries, it will benefit people’s safety obviously. Among all kinds of object detection algorithms, YOLO series play a very significant role. In this paper, we propose an improving strategy on YOLOv4 to enhance its precision based on multi-scale feature maps. Firstly, we create flame datasets including almost 4000 high-resolution flame pictures. Secondly, some improvements on feature extraction network are made to detect smaller objects. Finally, the total algorithm are trained and tested on our datasets for about 400 epochs. The result show that the method can generate high quality on flame detection in a great number of situations.

Convolutional Neural Networks (CNNs) use convolutional kernels to extract important low-level to high-level features from data. The performance of CNNs improves as they grow deep thereby learning better representations of the data. However, such deep CNNs are compute and memory-intensive, making deployment on resource-constrained devices challenging. To address this, the CNNs are compressed by adopting pruning strategies that remove redundant convolutional kernels from each layer while maintaining accuracy. Existing pruning methods that are based on feature map importance, only prune the convolutional layers uniformly and do not consider fully connected layers. Also, current techniques do not take into account class labels while pruning the less important feature maps and do not explore the need for retraining after pruning. This paper presents pruning techniques to prune convolutional and fully connected layers. This paper proposes a novel class-specific pruning strategy based on finding feature map importance in terms of entropy for convolutional layers and the number of incoming zeros to neurons for fully connected layers. The class-specific approach helps to have a different pruning threshold for every convolutional layer and ensures that the pruning threshold is not influenced by any particular class. A study on the need for retraining the entire network or a part of the network after pruning is also carried out. For Intel image, CIFAR10 and CIFAR100 datasets the proposed pruning method has compressed AlexNet by 83.2%, 87.19%, and 79.7%, VGG-16 by 83.7%, 85.11%, and 84.06% and ResNet-50 by 62.99%, 62.3% and 58.34% respectively.

Facial expression recognition poses a significant challenge in computer vision with numerous applications. However, existing FER methods need more generalization ability and better robustness when dealing with complex datasets with noisy labels. We propose a label distribution learning model, RA-ARNet, with novel reliability-aware (RA) and attention-rectified (AR) modules to handle noisy labels. Specifically, the RA module evaluates the reliability of the image’ neighboring instances in the valence-arousal space and constructs corresponding label distribution based on the evaluation as auxiliary supervision information to enhance the model’s robustness and generalization on various FER datasets with noisy labels. The AR module can gradually improve the model’s ability to extract attention features of facial landmarks by introducing consistency detection of attention feature maps of images and landmarks in training, thereby improving the model’s FER accuracy. The competitive experimental results on public datasets validate the effectiveness of the proposed method and compare it with the current state-of-the-art methods. The experimental results indicate that the classification performance of RA-ARNet reaches 91.36% on RAF-DB and 61.47% on AffectNet (8 cls) and shows potential to deal with images with occlusion.

Network pruning is an essential technique for compressing and accelerating convolutional neural networks (CNNs). Existing pruning algorithms primarily evaluate filter importance or similarity, and then remove unimportant filters or keep only one similar filter at each convolutional layer based on a global pruning ratio. These methods, ignoring the sensitivity of pruning among different convolutional layers, rely on a lot of manual experience and multiple experiments to obtain the optimal convolutional neural network structure. To this end, we propose an automatic filter pruning algorithm via feature map average similarity and reverse search genetic algorithm(RSGA), dubbed as AFPruner, which automatically searches for the optimal combination of pruning ratio for all convolutional layers, evaluates filter similarity by feature map average similarity and then prunes similarity filter. Our method is evaluated against several state-of-the-art CNNs on three different classification datasets, and the experimental results show that our algorithm outperforms most current network pruning algorithms.

Ecological function zoning is an essential means of scientific management of ecosystems. According to the characteristics of ecological function zoning, implementing zoning control is conducive to the governance and protection of the ecological environment and the maintenance of ecological sustainability. This study was conducted with the Nansi Lake Basin as the cross-section for 2018. The Integrated Valuation of Ecosystem Services and Trade-offs model was adopted to assess and measure five ecosystem services, including water yield, crop production, soil conservation, carbon storage and carbon sequestration, and habitat quality. The Self-Organizing Feature Maps neural network was applied to obtain the ecosystem service bundles, and then, the ecological function zones were divided. The results indicated that the overall spatial pattern of ecosystem services in the study zone showed a decreasing schema from east to west; There was a trade-off between supply services and support services and a synergy between supply services and regulatory services; according to the bundling results, the Nansi Lake Basin was divided into four ecological functional zones: the eastern ecological surplus zone, the central crop supply zone, the western ecological balance zone, and the lake habitat protection zone. The results showed that (1) the spatial distribution of various ecosystem services in the Nansi Lake Basin showed spatial heterogeneity and specific regional laws, showing a decreasing pattern from the east to the west as a whole, especially in soil conservation, carbon sequestration, and habitat quality. (2) According to the supply and spatial distribution of each ecosystem service, the Nansi Lake Basin was divided into four ecological functional zones: the eastern ecological surplus zone, the central crop supply zone, the western ecological balance zone, and the lake habitat protection zone. (3) For zone I, provisioning services and regulation services were in synergy. For zone II and zone III, the provisioning service had a trade-off relationship with the regulation service and the supporting service. For zone IV, supporting services were trade-offs not only with provisioning services but also with regulating services. In general, the trade-offs between ecosystem service in the Nansi Lake Basin were stronger than the synergies, and the overall benefits of ecosystem services were smaller. Relying on the perspective of the ecosystem service bundles, at the county level, this study provided an analysis of the trade-offs and synergies among ecosystem services in the Nansi Lake Basin, which helped formulate the management plan for the corresponding region and provided the appropriate recommendations for regional habitat conservation and restoration. Graphical Abstract