Explore the vast range of titles available.

Sparse representation has been widely applied to multi-focus image fusion in recent years. As a key step, the construction of an informative dictionary directly decides the performance of sparsity-based image fusion. To obtain sufficient bases for dictionary learning, different geometric information of source images is extracted and analysed. The classified image bases are used to build corresponding subdictionaries by principle component analysis. All built subdictionaries are merged into one informative dictionary. Based on constructed dictionary, compressive sampling matched pursuit algorithm is used to extract corresponding sparse coefficients for the representation of source images. The obtained sparse coefficients are fused by Max-L1 fusion rule first, and then inverted to form the final fused image. Multiple comparative experiments demonstrate that the proposed method is competitive with other the state-of-the-art fusion methods.

Federated learning is a new learning paradigm that decouples data collection and model training via multi-party computation and model aggregation. As a flexible learning setting, federated learning has the potential to integrate with other learning frameworks. We conduct a focused survey of federated learning in conjunction with other learning algorithms. Specifically, we explore various learning algorithms to improve the vanilla federated averaging algorithm and review model fusion methods such as adaptive aggregation, regularization, clustered methods, and Bayesian methods. Following the emerging trends, we also discuss federated learning in the intersection with other learning paradigms, termed federated X learning, where X includes multitask learning, meta-learning, transfer learning, unsupervised learning, and reinforcement learning. In addition to reviewing state-of-the-art studies, this paper also identifies key challenges and applications in this field, while also highlighting promising future directions.

The Semliki Forest Virus (SFV) is an RNA virus with a positive-strand that belongs to the Togaviridae family’s Alphavirus genus. An epidemic was observed among French troops stationed in the Central African Republic, most likely caused by the SFV virus. The two transmembrane proteins El and E2 and the peripheral protein E3 make up the viral spike protein. The virus binds to the host cell and is internalized via endocytosis; endosome acidification causes the E1/E2 heterodimer to dissociate and the E1 subunits to trimerize. Lupenone was evaluated against the E1 spike protein of SFV in this study based on state-of-the-art cheminformatics approaches, including molecular docking, molecular dynamics simulation, and binding free energy calculation. The molecular docking study envisaged major interactions of Lupenone with binding cavity residues involved non-bonded van der Waal’s and Pi-alkyl interactions. Molecular dynamic simulation of a time scale 200 ns corroborated interaction pattern with molecular docking studies between Lupenone and E1 spike protein. Nevertheless, Lupenone intearcation with the E1 spike protein conforming into a stable complex substantiated by free energy landscape (FEL), PCA analysis. Free energy decomposition of the binding cavity resdiues of E1 spike protein also ensured the efficient non-bonded van der Waal’s interaction contributing most energy to interact with the Lupenone. Therefore, Lupenone interacted strongly at the active site conforming into higher structural stability throughout the dynamic evolution of the complex. Thus, this study perhaps comprehend the efficiency of Lupenone as lead molecule against SFV E1 spike protein for future therapeutic purpose.

Conventional action recognition algorithms adopt a single type of feature or a simple concatenation of multiple features. In this paper, we propose to better fuse and embed different feature representations for action recognition using a novel spectral coding algorithm called Kernelized Multiview Projection (KMP). Computing the kernel matrices from different features/views via time-sequential distance learning, KMP can encode different features with different weights to achieve a low-dimensional and semantically meaningful subspace where the distribution of each view is sufficiently smooth and discriminative. More crucially, KMP is linear for the reproducing kernel Hilbert space, which allows it to be competent for various practical applications. We demonstrate KMP’s performance for action recognition on five popular action datasets and the results are consistently superior to state-of-the-art techniques.

LiDAR-based simultaneous localization and mapping (SLAM) approaches have obtained considerable success in autonomous robotic systems. This is in part owing to the high accuracy of robust SLAM algorithms and the emergence of new and lower-cost LiDAR products. This study benchmarks the current state-of-the-art LiDAR SLAM algorithms with a multi-modal LiDAR sensor setup, showcasing diverse scanning modalities (spinning and solid state) and sensing technologies, and LiDAR cameras, mounted on a mobile sensing and computing platform. We extend our previous multi-modal multi-LiDAR dataset with additional sequences and new sources of ground truth data. Specifically, we propose a new multi-modal multi-LiDAR SLAM-assisted and ICP-based sensor fusion method for generating ground truth maps. With these maps, we then match real-time point cloud data using a normal distributions transform (NDT) method to obtain the ground truth with a full six-degrees-of-freedom (DOF) pose estimation. These novel ground truth data leverage high-resolution spinning and solid-state LiDARs. We also include new open road sequences with GNSS-RTK data and additional indoor sequences with motion capture (MOCAP) ground truth, complementing the previous forest sequences with MOCAP data. We perform an analysis of the positioning accuracy achieved, comprising ten unique configurations generated by pairing five distinct LiDAR sensors with five SLAM algorithms, to critically compare and assess their respective performance characteristics. We also report the resource utilization in four different computational platforms and a total of five settings (Intel and Jetson ARM CPUs). Our experimental results show that the current state-of-the-art LiDAR SLAM algorithms perform very differently for different types of sensors. More results, code, and the dataset can be found at GitHub.

The techniques of hybridisation and ensemble learning are popular model fusion techniques for improving the predictive power of forecasting methods. With limited research that instigates combining these two promising approaches, this paper focuses on the utility of the Exponential Smoothing-Recurrent Neural Network (ES-RNN) in the pool of base learners for different ensembles. We compare against some state-of-the-art ensembling techniques and arithmetic model averaging as a benchmark. We experiment with the M4 forecasting dataset of 100,000 time-series, and the results show that the Feature-Based FORecast Model Averaging (FFORMA), on average, is the best technique for late data fusion with the ES-RNN. However, considering the M4’s Daily subset of data, stacking was the only successful ensemble at dealing with the case where all base learner performances were similar. Our experimental results indicate that we attain state-of-the-art forecasting results compared to Neural Basis Expansion Analysis (N-BEATS) as a benchmark. We conclude that model averaging is a more robust ensembling technique than model selection and stacking strategies. Further, the results show that gradient boosting is superior for implementing ensemble learning strategies.

The detection of cardiovascular diseases through the analysis of phonocardiograms (PCGs), which are digital recordings of heartbeat sounds, is crucial for early diagnosis. Conventional feature extraction methods often face challenges in distinguishing non-stationary signals like healthy and pathological PCG signals. Our research addresses these challenges by adopting a hybrid feature extraction scheme that leverages deep learning and handcrafted techniques. This approach allows for a more effective analysis and classification of PCG signals. This paper presents a novel approach to PCG signal classification, leveraging a fusion of deep learning features and handcrafted features based on mutual information measurements. High-level features are obtained through a pretrained deep network applied to time-frequency representations of PCG signals. Additionally, Mel-Frequency Cepstral Coefficients of empirical wavelet subbands serve as handcrafted features. Canonical correlation analysis is employed for feature fusion, effectively combining crucial information from both feature types. Classification is performed using support vector machines, k-nearest neighbor, and multilayer perceptron (MLP) classifiers with a fivefold cross-validation approach. Evaluation using the Physionet Challenge 2016 database demonstrates the superior performance of our proposed approach compared to existing state-of-the-art studies, showcasing its efficacy in PCG signal classification.

Pan-sharpening is a technique used to generate high-resolution multi-spectral (HRMS) images by merging high-resolution panchromatic (PAN) images with low-resolution multi-spectral (LRMS) images. Many existing methods face challenges in effectively balancing the trade-off between spectral and spatial information, leading to spectral and spatial structural distortion. In order to effectively tackle these issues, we propose a dual-branch and triple attention (DBTA) network. The proposed DBTA network consists of two essential modules: the Channel-spatial Attention (CSA) module and the Spectral Attention (SPA) module. The CSA module effectively captures the spatial structural information of the images by jointly using spatial and channel attention units. Meanwhile, the SPA module improves the expressive capacity of spectral information by dynamically adjusting channel weights. These two modules work in synergy to achieve comprehensive extraction and fusion of spectral and spatial information, thus resulting in more accurate and clearer reconstructed images. Extensive experiments have been conducted on various satellite datasets to evaluate the performance of the proposed DBTA method outperforms the state-of-the-art competitors in both qualitative and quantitative evaluations.

High spatial resolution (HSR) imagery scene classification has recently attracted increased attention. The bag-of-visual-words (BoVW) model is an effective method for scene classification. However, it can only extract handcrafted features, and it disregards the spatial layout information, whereas deep learning can automatically mine the intrinsic features as well as preserve the spatial location, but it may lose the characteristic information of the HSR images. Although previous methods based on the combination of BoVW and deep learning have achieved comparatively high classification accuracies, they have not explored the combination of handcrafted and deep features, and they just used the BoVW model as a feature coding method to encode the deep features. This means that the intrinsic characteristics of these models were not combined in the previous works. In this paper, to discover more discriminative semantics for HSR imagery, the deep-local-global feature fusion (DLGFF) framework is proposed for HSR imagery scene classification. Differing from the conventional scene classification methods, which utilize only handcrafted features or deep features, DLGFF establishes a framework integrating multi-level semantics from the global texture feature–based method, the BoVW model, and a pre-trained convolutional neural network (CNN). In DLGFF, two different approaches are proposed, i.e., the local and global features fused with the pooling-stretched convolutional features (LGCF) and the local and global features fused with the fully connected features (LGFF), to exploit the multi-level semantics for complex scenes. The experimental results obtained with three HSR image classification datasets confirm the effectiveness of the proposed DLGFF framework. Compared with the published results of the previous scene classification methods, the classification accuracies of the DLGFF framework on the 21-class UC Merced dataset and 12-class Google dataset of SIRI-WHU can reach 99.76%, which is superior to the current state-of-the-art methods. The classification accuracy of the DLGFF framework on the 45-class NWPU-RESISC45 dataset, 96.37 ± 0.05%, is an increase of about 6% when compared with the current state-of-the-art methods. This indicates that the fusion of the global low-level feature, the local mid-level feature, and the deep high-level feature can provide a representative description for HSR imagery.

The polyp segmentation technology based on computer-aided can effectively avoid the deterioration of polyps and prevent colorectal cancer. To segment the polyp target precisely, the Multi-Scale Feature Enhancement and Fusion Network (MFEFNet) is proposed. First of all, to balance the network's predictive ability and complexity, ResNet50 is designed as the backbone network, and the Shift Channel Block (SCB) is used to unify the spatial location of feature mappings and emphasize local information. Secondly, to further improve the network's feature-extracting ability, the Feature Enhancement Block (FEB) is added, which decouples features, reinforces features by multiple perspectives and reconstructs features. Meanwhile, to weaken the semantic gap in the feature fusion process, we propose strong associated couplers, the Multi-Scale Feature Fusion Block (MSFFB) and the Reducing Difference Block (RDB), which are mainly composed of multiple cross-complementary information interaction modes and reinforce the long-distance dependence between features. Finally, to further refine local regions, the Polarized Self-Attention (PSA) and the Balancing Attention Module (BAM) are introduced for better exploration of detailed information between foreground and background boundaries. Experiments have been conducted under five benchmark datasets (Kvasir-SEG, CVC-ClinicDB, CVC-ClinicDB, CVC300 and CVC-ColonDB) and compared with state-of-the-art polyp segmentation algorithms. The experimental result shows that the proposed network improves Dice and mean intersection over union (mIoU) by an average score of 3.4% and 4%, respectively. Therefore, extensive experiments demonstrate that the proposed network performs favorably against more than a dozen state-of-the-art methods on five popular polyp segmentation benchmarks. •Proposing a polyp segmentation network MFEFNet based on CNN.•Simplifying parameters and emphasizing local information by unifying the spatial location.•Reinforcing feature engineering by decoupling, enhancing and reconstructing.•Integrating high-order features by cross-complementary information interaction modes to weaken semantic gaps.•Refining local regions by introducing efficient attention mechanisms.