High-dimensional MR imaging often requires long data acquisition time, thereby limiting its practical applications. This paper presents a low-rank tensor based method for accelerated high-dimensional MR imaging using sparse sampling. This method represents high-dimensional images as low-rank tensors (or partially separable functions) and uses this mathematical structure for sparse sampling of the data space and for image reconstruction from highly undersampled data. More specifically, the proposed method acquires two datasets with complementary sampling patterns, one for subspace estimation and the other for image reconstruction; image reconstruction from highly undersampled data is accomplished by fitting the measured data with a sparsity constraint on the core tensor and a group sparsity constraint on the spatial coefficients jointly using the alternating direction method of multipliers. The usefulness of the proposed method is demonstrated in MRI applications; it may also have applications beyond MRI.
9 July 2024 in IEEE Transactions on Circuits and Systems for Video Technology
Cross-view geo-localization seeks to match geographic locations using images from varied sources, including drones and satellites. Interpreting images captured by drones poses significant challenges due to the varying positions and scales resulting from the camera’s aerial perspective. Traditional approaches have primarily focused on harnessing contextual cues, which may lead to overfitting. Therefore, it is crucial to find an optimal balance between leveraging contextual details and identifying relevant features. To address this, we introduce a novel method for cross-view geo-localization that employs counterfactual causal reasoning (CCR). This method aims to refine the model’s focus, ensuring a balanced emphasis on both the intricate details of the target structure and its broader contextual environment. Our method incorporates an Adaptive Dimension Interaction Block (ADIB), which effectively discerns feature interactions across multiple dimensions, enhanced by counterfactual causal reasoning to improve recognition of target structures and their contexts. In tasks of image-based drone-view target localization and drone navigation, our method achieves superior performance on the University-1652 and SUES-200 benchmark datasets. The code and model files will be made available at https://github.com/Cyberpunk1998/CCR.
In wireless sensor networks (WSNs), data recovery is an indispensable operation for data loss or energy constrained WSNs using sparse sampling. However, the recovery accuracy is not satisfying for WSNs with various sensor types due to the neglect of the correlation among multi-attribute data. In this paper, we propose a novel data recovery method with joint sparsity and low-rank constraints based on tensor completion for multi-attribute data in WSNs. The proposed method represents the high-dimensional data as low-rank tensors to effectively exploit the correlation that exists in the multi-attribute data. The utilization of the spatiotemporal sparsity in the signal is emphasized by sparsity constraints. Furthermore, an algorithm based on the alternating direction method of multipliers is developed to solve the resultant optimization problem efficiently. Experimental results demonstrate that the proposed method significantly outperforms existing solutions in terms of recovery accuracy in WSNs.
A surface plasmon resonance sensor based on double-sided polished microstructured optical fiber with hollow core is put forward for refractive index sensing. Two gold films parallel to each other attached to the polished surface act as microfluidic sensing channels for the analyte. The artificially introduced air hole can facilitate the phase matching between the core mode and the plasmon mode. The sensitivities of the proposed sensor are investigated by the wavelength, amplitude and phase interrogation methods when the analyte refractive index increases from 1.33 to 1.34. In contrast to the D-shaped design, the double-sided polished structure demonstrates narrower resonance spectral width and greater phase sensitivity. Moreover, the numerical results indicate that the proposed sensor shows a good stability in the fabrication tolerances of ±5% of the thickness of gold film and the depth of polishing, respectively.
Background: Intrinsically disordered proteins possess flexible 3-D structures, which makes them play an important role in a variety of biological functions. Molecular recognition features (MoRFs) act as an important type of functional regions, which are located within longer intrinsically disordered regions and undergo disorder-to-order transitions upon binding their interaction partners. Results: We develop a method, MoRFCNN, to predict MoRFs based on sequence properties and convolutional neural networks (CNNs). The sequence properties contain structural and physicochemical properties which are used to describe the differences between MoRFs and non-MoRFs. Especially, to highlight the correlation between the target residue and adjacent residues, three windows are selected to preprocess the selected properties. After that, these calculated properties are combined into the feature matrix to predict MoRFs through the constructed CNN. Comparing with other existing methods, MoRFCNN obtains better performance. Conclusions: MoRFCNN is a new individual MoRFs prediction method which just uses protein sequence properties without evolutionary information. The simulation results show that MoRFCNN is effective and competitive.
Sparse sensing schemes based on matrix completion for data collection have been proposed to reduce the power consumption of data-sensing and transmission in wireless sensor networks (WSNs). While extensive efforts have been made to improve the recovery accuracy from the sparse samples, it is usually at the cost of running time. Moreover, most data-collection methods are difficult to implement with low sampling ratio because of the communication limit. In this paper, we design a novel data-collection method including a Rotating Random Sparse Sampling method and a Fast Singular Value Thresholding algorithm. With the proposed method, nodes are in the sleep mode most of the time, and the sampling ratio varies over time slots during the sampling process. From the samples, a corresponding algorithm with Nesterov technique is given to recover the original data accurately and fast. With two real-world data sets in WSNs, simulations verify that our scheme outperforms other schemes in terms of energy consumption, reconstruction accuracy, and rate. Moreover, the proposed sampling method enhances the recovery algorithm and prolongs the lifetime of WSNs.