Accurate and reliable localization is crucial for Unmanned Surface Vehicles (USVs) in complex urban waterways. The capability typically relies on the fusion of Global Navigation Satellite System (GNSS) and Inertial Navigation System (INS). However, the signals are frequently compromised by obstructions, e.g., bridges and riverside buildings. The resulting multipath effects and non-line-of-sight (NLOS) reception create non-stationary error patterns. Traditional multi-sensor fusion methods often fail to maintain accuracy under the aforementioned degraded signal conditions. The performance degradation stems from the reliance on static noise assumptions. The static assumptions are insufficient for addressing the temporal correlations inherent in signal distortions. The study presents an uncertainty-aware fusion framework integrated with a Spatio-Temporal GNSS Covariance (ST-GNSSCov) learning model. By combining a Set Transformer with seqauential networks, the model incorporates spatial satellite geometry and temporal dependencies. The architecture enables dynamic uncertainty prediction for GNSS observations. The predicted uncertainty is expressed as a time-varying covariance. The results are subsequently implemented in a factor graph back-end to adaptively reweight GNSS factors for state estimation. The proposed method outperforms conventional DOP-based uncertainty modeling in positioning accuracy. Specifically, during short-term GNSS degradation, the mean absolute positioning error (MAE) decreases from 0.673 m to 0.190 m. Under long-term signal fluctuations, the system achieves a stable positioning RMSE of 0.183 m. The performance exceeds the accuracy of DOP-based modeling, as well as spatial-only and temporal-only GNSS uncertainty modeling approaches.

Integrated circuits are increasingly sensitive to radiation-induced multi-node upset in advanced CMOS technology. This paper proposes a novel low-power quadruple-node-upset recovery latch (QNU-CPN), which is based on the feedback interconnection of twenty-two input-split C-elements with P-input and N-input (CPNs) to achieve high reliability. Post-layout simulation results for 45nm CMOS by HSPICE technology show that the proposed QNU-CPN latch exhibits a reduction in power consumption by an average of 56.45%, a reduction in power-delay product (PDP) by an average of 56.92%, a reduction in area-power-delay product (APDP) by an average of 58.59%, and a reduction in setup time by an average of 11.11%, in comparison to four other existing quadruple-node upset recovery latch (LDAVPM, QRHIL, QRHIL-LC, MURLAV). Furthermore, this paper proposes the recovery rate calculation algorithm method that can calculate the recovery rate based on the configuration of multiple fault-tolerant components.

Few-shot fine-grained image classification aims to use only few labelled samples to successfully recognize subtle sub-classes within the same parent class. This task is extremely challenging, due to the co-occurrence of large inter-class similarity, low intra-class similarity, and only few labelled samples. In this paper, to address these challenges, we propose a new Channel-Spatial Cross-Attention Module (CSCAM), which can effectively drive a model to extract discriminative fine-grained feature representations with only few shots. CSCAM collaboratively integrates a channel cross-attention module and a spatial cross-attention module, for the attentions across support and query samples. In addition, to fit for the characteristics of fine-grained images, a support averaging method is proposed in CSCAM to reduce the intra-class distance and increase the inter-class distance. Extensive experiments on four few-shot fine-grained classification datasets validate the effectiveness of CSCAM. Furthermore, CSCAM is a plug-and-play module, conveniently enabling effective improvement of state-of-the-art methods for few-shot fine-grained image classification.

Attributed graphs are widely used to represent network data where the attribute information of nodes is available. To address the problem of identifying clusters in attributed graphs, most of existing solutions are developed simply based on certain particular assumptions related to the characteristics of clusters of interest. However, it is yet unknown whether such assumed characteristics are consistent with attributed graphs. To overcome this issue, we innovatively introduce an inductive clustering algorithm that tends to address the clustering problem for attributed graphs without any assumption made on the clusters. To do so, we first process the attribute information to obtain pairwise attribute values that significantly frequently co-occur in adjacent nodes as we believe that they have potential ability to represent the characteristics of a given attributed graph. For two adjacent nodes, their likelihood of being grouped in the same cluster can be weighted by their ability to characterize the graph. Then based on these verifed characteristics instead of assumed ones, a depth-first search strategy is applied to perform the clustering task. Moreover, we are able to classify clusters such that their significance can be indicated. The experimental results demonstrate the performance and usefulness of our algorithm.

Protein-protein interactions are of great significance for us to understand the functional mechanisms of proteins. With the rapid development of high-throughput genomic technology, the amount of protein-protein interaction data has become so big that most of existing prediction algorithms are no longer applicable. To address this problem, we develop a distributed framework by reimplementing one of state-of-the-art algorithms, i.e., CoFex, by using MapReduce. In particular, we adopt a novel tree-based data structure to reduce the heavy memory consumption cased by the huge sequence information of proteins. After that, the procedure of CoFex is modified by following the paradigm of MapReduce such that the prediction task can be completed in a distributed manner, thus fulfilling the demanding requirements of large-scale protein-protein interaction prediction. A series of experiments have been conducted to evaluate the performance of the proposed distributed framework in terms of both efficiency and effectiveness. Experimental results demonstrate that the proposed framework can considerably improve the efficiency of CoFex by achieving more than two-orders-of-magnitude improvement in computational efficiency while retaining a comparable level of accuracy.

This work investigates the problem of undersampled face recognition (i.e., insufficient training data) encountered in practical Internet-of-Things (IoT) applications. Insufficient and uncertain samples captured by IoT devices may include background and facial disguise that makes face recognition more challenging than that with sufficient and reliable images. Many models work well in face recognition on a big data set, but when training data are insufficient, they achieve unsatisfactory performance. This work proposes a novel method named sparse common feature-based representation (SCFR) that provides a unique and stable result and completely avoids very time-consuming training required by a deep learning model. Specially, it constructs a common feature dictionary using both training and test images. Thereinto, a common feature is based on a discriminative common vector and learned by a Gaussian mixture model for both training and test images in a semisupervised learninig manner, which would reduce the difference among samples in each class. In the optimization, the latent indicator of test data is initialized by the estimated label. This can avoid learning invalid information and lead to good prototype images. A new variation dictionary characterizes variables that can be shared by different classes. Finally, this work adopts minimum reconstruction residuals to recognize test images, thus bringing about a substantial improvement in SCFR's performance. Extensive results on benchmark face databases demonstrate that the proposed method is better than the state-of-the-art methods handling undersampled face recognition.

The performance of face recognition has been greatly improved by deep neural network algorithms when a dataset is large. However, when face data are insufficient as in practical Internet of Things (IoT) applications and captured by IoT devices under the same intrasubject variation, both data quantity and quality bring big challenges to construct a model or representation, and most of the time it becomes infeasible to build a deep neural network model. This work proposes a sparse individual low-rank component-based representation (SILR) such that the representation of testing images can be based on individual subjects’ low-rank component. Theoretically, we put the$l_{2}$-norm constraint on intrasubject coefficients to represent testing images, thus making intrasubject coefficients dense. Hence, we alleviate the impact of an undersampled training dataset and its same intersubject variation on classification performance. We solve a convex minimization problem in polynomial time via an augmented lagrange multiplier scheme to get the solution of SILR. The scheme can reduce the influences from the same intersubject variation and contribute to an accurate recognition of the undersampled training dataset. We adopt sparse individual low-rank component representation and minimum reconstruction residual to recognize testing images. Extensive results on various databases show that SILR outperforms the other state-of-the-art methods for face recognition.

Knowing how proteins interact with each other are crucial to for us to understand the functional mechanisms of proteins. It is for this reason that the CoFex has been developed in attempts to predict protein-protein interactions (PPIs) computationally. However, the procedure of obtaining coevolutionary patterns adopted by CoFex is inefficient especially for large-scale prediction of PPIs, as it needs to traverse the entire protein sequence dataset once when computing the number of co-occurrences for each candidate of coevolutionary patterns. Hence, to improve the efficiency of CoFex, we propose a novel tree-based data structure, namely CF-Tree, to integrate with CoFex so that the running time of CoFex can be reduced by only traversing the sequence dataset once. The experiment results show that CF-Tree is a promising tree-based data structure to identify the coevolutionary patterns more efficiently from the sequence information of proteins in different species.

Sparse-representation-based classification (SRC) has been showing a good performance for face recognition in recent years. But SRC is not good at face recognition with low quality images (e.g., disguised, corrupted, occluded, and so on) which often appear in practical applications. To solve the problem, in this paper, we propose a novel SRC-based method for face recognition with low quality images named sparse low-rank component-based representation (SLCR). In SLCR, we utilize low-rank matrix recovery on the training data set to obtain low-rank components and non-low-rank components, which are used to construct the dictionary. The new dictionary is capable of describing facial features better, especially for low quality face samples. Furthermore, the minimum class-wise reconstruction residual is used as the recognition rule, leading to a substantial improvement on the proposed SLCR's performance. Extensive experiments on benchmark face databases demonstrate that the proposed method is consistently superior to other sparse-representation-based approaches for face recognition with low quality images.

Sparse representation-based classification shows a good performance for face recognition in recent years, but it can not be suitable for face recognition with illumination and corruption, which are often presented in the practical applications. To solve the problem, in this paper, we propose a novel SRC based method for face recognition named sparse low-rank component coding (SLC). In SLC, we utilize the low-rank component from training dataset to construct dictionary. The dictionary composed of low-rank component is able to describe the face feature better, especially for training samples with illumination and corruption. Our recognition rule is based on the minimum class-wise reconstruction residual which leads to a substantial improvement on the performance of SLC. Extensive experiments on benchmark face databases demonstrate that the proposed method consistently outperforms the other sparse representation based approaches for face recognition with illumination and corruption.

Sparse representation-based classification (SRC) shows a good performance for face recognition in recent years, but SRC can not be suitable for low quality data with disguise or noise, which are often presented in the practical applications. To solve the problem, in this paper, we propose a novel SRC based method for face recognition with low quality images named sparse low-rank component based representation (SLCR). In SLCR, we utilize the low-rank component from training dataset to construct dictionary. The dictionary composed of low-rank component and non-low-rank component is able to describe the face feature better, especially for low quality training samples. Our recognition rule is based on the minimum class-wise reconstruction residual which leads to a substantial improvement on the proposed SLCR's performance. Extensive experiments on benchmark face databases demonstrate that the proposed method consistently outperforms the other sparse representation based approaches for disguised and corrupted face recognition.

In this paper, we present a new and effective dimensionality reduction method called locality sparsity preserving projections (LSPP). Locality preserving projections (LPP) and sparsity preserving projections (SPP) only focus on an aspect of local structure and sparse reconstructive information of the dataset, respectively. The proposed method integrates the sparse reconstructive information and local structure of data. The projection of LSPP is sought such that the sparse reconstructive weights and local preserving weights can be best preserved and integrated. Extensive experiments on ORL, Yale, Yale B, AR and CMU PIE face databases show the effectiveness of the proposed LSPP.