Effectively utilizing extensive unlabeled high-density EEG data to improve performance in scenarios with limited labeled low-density EEG data presents a significant challenge. In this paper, we address this challenge by formulating it as a graph transfer learning and knowledge distillation problem. We propose a Unified Pre-trained Graph Contrastive Masked Autoencoder Distiller, named EEG-DisGCMAE, to bridge the gap between unlabeled and labeled as well as high- and low-density EEG data. Our approach introduces a novel unified graph self-supervised pre-training paradigm, which seamlessly integrates the graph contrastive pre-training with the graph masked autoencoder pre-training. Furthermore, we propose a graph topology distillation loss function, allowing a lightweight student model trained on low-density data to learn from a teacher model trained on high-density data during pre-training and fine-tuning. This method effectively handles missing electrodes through contrastive distillation. We validate the effectiveness of EEG-DisGCMAE across four classification tasks using two clinical EEG datasets with abundant data.

ABSTRACT In this paper, we present an Augmented Reality (AR)‐based application combined with a robotic system for percutaneous renal puncture navigation interaction and demonstrate its technical feasibility. Our system provides an intuitive interaction scheme between the surgeon and the robot without the need for traditional external input devices, and applies an image‐target‐based 3D registration scheme to transform the coordinate system between Hololens2 and the robot without using additional tracking devices. Users can visualize the abdominal puncture phantom and obtain 3D depth information of the lesion site by wearing Hololens2 and control the robot directly using buttons or gestures. To investigate the accuracy and feasibility of the proposed interaction scheme, six subjects were recruited to complete 3D registration alignment accuracy experiments, and puncture positioning accuracy experiments using ultrasound unaided navigation, AR unaided navigation and AR robotic navigation. The results showed that the average alignment error of 3D registration was 3.61 ± 1.05 mm. The average positioning errors of ultrasound freehand navigation, AR freehand navigation and AR robotic navigation were 7.67 ± 2.00 mm, 6.13 ± 1.07 mm and 5.52 ± 0.37 mm, respectively; the average puncture times were 34.86 ± 1.67 s, 22.40 ± 2.07 s, and 29.41 ± 1.37 s.

Accurate electroencephalogram (EEG) pattern decoding for specific mental tasks is one of the key steps for the development of brain-computer interface (BCI), which is quite challenging due to the considerably low signal-to-noise ratio of EEG collected at the brain scalp. Machine learning provides a promising technique to optimize EEG patterns toward better decoding accuracy. However, existing algorithms do not effectively explore the underlying data structure capturing the true EEG sample distribution and, hence, can only yield a suboptimal decoding accuracy. To uncover the intrinsic distribution structure of EEG data, we propose a clustering-based multitask feature learning algorithm for improved EEG pattern decoding. Specifically, we perform affinity propagation-based clustering to explore the subclasses (i.e., clusters) in each of the original classes and then assign each subclass a unique label based on a one-versus-all encoding strategy. With the encoded label matrix, we devise a novel multitask learning algorithm by exploiting the subclass relationship to jointly optimize the EEG pattern features from the uncovered subclasses. We then train a linear support vector machine with the optimized features for EEG pattern decoding. Extensive experimental studies are conducted on three EEG data sets to validate the effectiveness of our algorithm in comparison with other state-of-the-art approaches. The improved experimental results demonstrate the outstanding superiority of our algorithm, suggesting its prominent performance for EEG pattern decoding in BCI applications.

In micro-grids, energy storage systems (ESSs) have provided a feasible option in mitigating load mismatch as well as facilitating integration of renewable distributed generations. However, due to the high construction cost of ESSs, proper mechanisms are needed for the optimization of their sizing. In this paper, owing to the temporal and spatial disparities of different types of loads, a mathematical model for the annual profit of micro-grid was developed in consideration of economic factors, and a game theory based method was proposed to reduce the energy and power rating of ESS in interconnected micro-grids. It was proved with a test case that the centralized ESS allocated in interconnected micro-grids was effective and feasible.

The Algorithm Scientific Software Integration and System Transition Team (ASSISTT) at NESDIS STAR (National Environmental Satellite Data and Information Service, Center for Satellite Applications and Research) has designed, developed and implemented a Near Real-Time (NRT) processing system to process algorithms for scientists and other stakeholders. The system generates products using the STAR Algorithm Processing Framework (SAPF). The SAPF was originally developed by ASSISTT as a testbed for GOES-R project products and have expanded to the other projects such as VIIRS Polar Winds, GOES Winds, AHI Winds and JPSS Risk Reduction Project. The NRT processing system specific to AHI Winds and JPSS Risk Reduction Project products will be introduced here.

As a close proxy of the GOES-R Advanced Baseline Imager (ABI) instrument, the on-board 16-band Advanced Himawari Imager (AHI) brings an unprecedented opportunity to exercise the ABI algorithms developed for GOES-R in the STAR Algorithm Processing Framework (SAPF). STAR has been collaborating with JMA and NASA since AHI's post launch checkout and has been acquiring the full resolution AHI data form JMA's Cloud Service. Because AHI has almost identical channels as ABI, most of the ABI algorithms can be easily adapted to run with AHI data. This presentation describes the process to update the GOES-R ABI baseline algorithms for AHI data, including the update of SAPF system and the ABI algorithm software. The benefits and lessons learned from the AHI data exercise will also be discussed.

An unprotected scan-chain makes a perfect back-door in a secure chip. Therefore, many secure chips disable the access to the scan-chains once the testing is completed. In this paper, we consider an attack that is carried out on a blank chip. The scan-chain is still accessible, yet there is no key to be attacked. We show that the attacker can use the scan chain to reveal information that can be used to improve other physical attacks, such side-channel analysis, fault analysis and probing analysis.

This paper summarizes work investigating the zenith angular dependence of residual cloud and/or aerosol contamination on “clear-sky” infrared observations, which include cloud-cleared radiances and cloud-masked data, along with the implication for achieving agreement with forward calculations over the scanning range of the sensor.

The spatial variability of both meteorological and geographic features has a great influence on rainfall runoff process. When making flood forecasting, the influence of this variability on runoff should be considered. In this paper, the distributed hydrological modeling technique was adopted to simulate flood discharge with consideration of spatial variability using DEMs and remotely sensed data. In our approach, the grid based digital elevation data was used for the presentation of watershed discretization and deriving flow path system and parameters. The infiltration and rainfall excess on each hillslope grid cell were calculated using the Green-Ampt infiltration equation. Soil lateral flow was estimated based on Darcy's law and continuity equation, overland and channel flows were calculated by using one-dimensional kinematic wave equations on hillslope and channel grid cells respectively. The land use and land cover data derived from remotely sensed images was used for the determination of Manning's roughness coefficients. The soil type data was used for deriving soil hydraulic parameters needed for calculation. The approach was applied in Jiaokou Watershed with area of 259 km2, a sub-basin of Yongjiang River in Zhejiang Province, China. The data collected for this study included land cover processed from Landsat TM images, soil type distribution from the soil maps, and 100-m spatial resolution DEMs produced from digital topographic maps. Spatial distribution of rainfall for each flood event was calculated by using distance inverse interpolation methods. Nine flood events were simulated, two of which were used for calibration, and the others for validation. The simulated hydrographs at basin outlet showed good agreement with observed ones for both calibrated and validated flood events, and average coefficients of efficiency were 94% for calibrated flood events and 92% for validated flood events.

In this paper, we propose a new rotation-invariant image retrieval system based on steerable pyramids and the concept of angular alignment across scales. First, we define energy-based texture features which are steerable under rotation, i.e., such that features corresponding to the rotated version of an image can be easily obtained from the features of the original (non-rotated) image. We also propose an approach to measure similarity between images that is robust to rotation; images are compared after being aligned in angle. The retrieval process is performed by means of a decision tree classifier where the angular alignment is performed at each node in the tree. To demonstrate the effectiveness of our system we consider a distributed image classification system, where the feature encoder and the classifier are physically apart and thus features are compressed before being transmitted. Our results of retrieval performance versus rate show a clear gain with respect to a wavelet transform (as an example, for the same rate, the retrieval precision is increased from 40% to 65%).

Interpolation artifacts caused by the discrete nature of digital images and interpolation kernels have been previously reported in the literature for mutual information based image registration. Unfortunately they become pronounced in the case of SAR (synthetic aperture radar) image registration, exacerbated by speckle noise. We analyzed the two widely used interpolation algorithms in image registration, namely bilinear interpolation and partial volume interpolation. According to simulation results, we found that the former algorithm produces an extremely non-smooth metric function, whereas the latter method introduces a spurious global optimum at some position of misalignment, instead of the position of perfect registration, under certain circumstances. To make the mutual information criterion useful for the application of SAR image registration, we proposed two pre-processing steps including speckle reduction and an appropriate selection of the number of bins for histogram construction. Simulation results indicate that, by this effort, interpolation artifacts in the mutual information function can be significantly suppressed, and as a consequence, accurate registration is allowed. In conjunction with the two proposed pre-processing steps, we implemented a multiscale elastic registration algorithm. An example of registering a pair of JERS-1 (L-band, HH-polarization) and RADARSAT (C-band, HH-polarization) images verified the potential of this algorithm.

Most existing wavelet denoising techniques are developed for additive white Gaussian noise. In their applications to speckle reduction in SAR imagery, the traditional approach is to first perform a logarithmic transformation to convert the multiplicative noise model to an additive model, and then after wavelet denoising is performed on the log-transformed image, an exponential operation has to be implemented for radiometric preservation. In this paper, we introduce a low-complexity wavelet-based SAR speckle reduction algorithm which omits both the log-transform and the exponential transform operations. We decompose the multiplicative speckle model into an additive model with signal-dependent noise. Then, in the wavelet domain, we derive the shrinkage factor for each wavelet coefficient by applying the Minimum Mean Square Error (MMSE) estimation procedure. Simulated SAR images are used to evaluate the denoising performance of our proposed algorithm along with another wavelet-based denoising algorithm that involves the log-transform and exponential operation, as well as the refined Lee speckle filter. Experimental results show that the proposed filter outperforms the other filters in most cases.

In synthetic aperture radar (SAR) image processing and analysis, the logarithmic transform is often employed to convert the multiplicative speckle model to an additive noise model. However, this nonlinear operation totally changes the statistics of SAR images. In this communication, we first review the statistical properties of speckle noise in both the intensity and the amplitude formats. Then, we derive the probability density functions, the mean values, and the variances to characterize the log-transformed speckle. Finally we discuss the problems introduced by the logarithmic transform on statistical analysis of SAR images. The statistical models developed in this communication will facilitate subsequent SAR image processing tasks based on the additive noise model.

The granular appearance of speckle noise in synthetic aperture radar (SAR) imagery makes it very difficult to visually and automatically interpret SAR data. Therefore, speckle reduction is a prerequisite for many SAR image processing tasks. In this paper, we develop a speckle reduction algorithm by fusing the wavelet Bayesian denoising technique with Markov-random-field-based image regularization. Wavelet coefficients are modeled independently and identically by a two-state Gaussian mixture model, while their spatial dependence is characterized by a Markov random field imposed on the hidden state of Gaussian mixtures. The Expectation-Maximization algorithm is used to estimate hyperparameters and specify the mixture model, and the iterated-conditional-modes method is implemented to optimize the state configuration. The noise-free wavelet coefficients are finally estimated by a shrinkage function based on local weighted averaging of the Bayesian estimator. Experimental results show that the proposed method outperforms standard wavelet denoising techniques in terms of the signal-to-noise ratio and the equivalent-number-of-looks measures in most cases. It also achieves better performance than the refined Lee filter.