Autism spectrum disorder (ASD) is a mental disorder that severely affects social interaction and communication skills. A timely and accurate diagnosis is crucial for effective intervention. However, as an objective diagnostic tool, the existence of spurious connections and noise within the functional connectivity (FC) matrix in the brain contribute to the complexity of ASD diagnosis. In this study, we propose an unsupervised sparse graph structure learning framework, called NeuroSparse, for reasoning regarding the topological connectivity relationships between brain regions. First, the framework fuses spatiotemporal information from static and dynamic FC to provide a comprehensive representation of complex brain networks. Next, the context and neighborhood information of nodes are captured as their local and global embeddings, and the latent representations of node embeddings are learned, which are then decoded to infer the connectivity relationships among the regions of interest. Finally, we introduce three innovative loss functions to regularize and optimize the sparse representation generation process. The experimental results showed that, after learning using NeuroSparse, the FC matrix achieved state-of-the-art performance in ASD diagnosis using only a simple multilayer perceptron, indicating its wide-ranging application potential. The code is available at https://github.com/yangshuqigit/NeuroSparse.

Data migration from legacy systems to modern environments, such as migrating DB2 from z/OS to the cloud, often requires significant effort and time. Customers often encounter confusion when determining the appropriate migration route, use case, and efficient movement of source data to the target data repository. This paper explores various migration patterns and provides recommendations on target technology and platform selection. We propose a core Data Elements Migration (cDEM) strategy, focusing on schema, objects, and data volume, rather than a complete data warehouse. By enabling users to quickly assess workload, extract core data elements, map components from the source data pool to the target repository, and evaluate data volume and migration complexity, this approach reduces workload and accelerates the overall process. The model presented in this paper illustrates the migration of end-to-end data objects from legacy DB2 on z/OS to the public cloud, specifically Azure SQL Server as a demonstration case, while remaining applicable to other cloud providers and popular data repositories like MySQL.

Unsupervised change detection (CD) in Synthetic Aperture Radar (SAR) imagery is pivotal for terrestrial observations, more so for disaster-related applications. However, most existing deep learning methods primarily emphasize the construction of diverse networks, often overlooking the critical aspect of refining pseudo labels. This letter proposes a two-stage pseudo labels refining (TSPLR) framework for SAR image unsupervised CD. During the first stage, Fuzzy-C-Means (FCM) clustering is employed on the bi-temporal SAR images to yield initial pseudo labels, categorizing high-confidence data as changed or unchanged and the rest as uncertain. A straightforward network is then trained first with confident data, with the training subsequently extended to the uncertain data. In the second stage, we start by comparing the predictions from the model trained during the first phase with the initial pseudo labels. Data with inconsistencies is added to the uncertain dataset, and some pixels filtered according to connectivity areas are selected as hard samples. Subsequently, the model is trained further using the updated dataset. This two-stage refinement process bolsters the credibility of pseudo labels and creates a more robust network training against speckle noise. The experimental results show that even with a simple network, the performance of the proposed TSPLR exceeds the current performance of SOTA. We will be making the source codes publicly accessible at https://github.com/sdust-mmlab.

In recent years, semantic change detection (SCD) has emerged as a pivotal field within the remote sensing (RS) research community, underscored by its essential contribution to various Earth observation undertakings. Conventional SCD methodologies typically adopt a multitask network architecture, fusing a binary change detection (BCD) sub-task with dual semantic segmentation (SS) sub-tasks. These strategies frequently rely on the encoder’s low-resolution yet semantically dense features, derived from multiple down-sampling stages, as the inputs for the decoding heads. Departing from this traditional path and targeting the nuanced characteristics of the multisubtasks, this study pioneers a novel methodology that harnesses the potential of the encoding phase’s high-resolution features. By integrating HRNet as the encoder structure, we introduce the BT-HRSCD framework, featuring two simple and effective modules. The first, bidirectional shallow and deep features aggregation module (BiFAM), seeks to imbue features with richer semantic insights through bidirectional feature fusion that spans from shallow-to-deep as well as deep-to-shallow layers. The second module, high-resolution difference extraction (HRDE), utilizes the encoder’s highest spatial resolution features, evaluating their differences to enhance the precision in identifying change areas. BiFAM is devised to boost the SS sub-tasks’ effectiveness, whereas HRDE aims to elevate the accuracy of the BCD sub-task. Experimental results reveal that our method outperforms state-of-the-art performances relative to previous SCD efforts. Our source code is released athttps://github.com/iridescent524/BT-HRSCD.

Recently, Semantic Change Detection (SCD) has gained growing attention from the Remote Sensing (RS) research community due to its critical role in Earth observation applications. Typical approaches tackle the task using a multi-task network, comprising one Change Detection (CD) sub-task and two Semantic Segmentation (SS) sub-tasks. Although these approaches have achieved good performance, one crucial question persists: What is the effective way to handle the feature interactions across SCD sub-tasks? To address this issue, this paper first offers an overview of existing SCD networks and compares them from a perspective view of Multi-Task Learning (MTL). Following that, we select an architecture combining a two-branch encoder and a three-branch decoder as the baseline due to its compatibility with MTL. Then, one simple yet very effective module, decoder feature interaction across sub-tasks (DFIT), is introduced. DFIT seeks to enhance the CD decoding feature by leveraging the feature differences between two SS decoding branches on a layer-wise basis. Additionally, the feature aggregation module (FAM) is designed further to enhance the network performance in cooperation with DFIT. FAM aims to produce more representative shared information across the SS and CD sub-tasks by merging the outputs from the final three encoder layers. Combining DFIT and FAM, the proposed network exploiting Decoder-Focused MTL (DEFO-MTLSCD) presents more representative information by capitalizing on both CD and SS losses back-propagations across all coding paths and achieves better performance. Experimental results reveal that our method outperforms state-of-the-art performances relative to previous SCD efforts. Our source code is released at https://github.com/byyztgxz/Decoder_Fusion.

Available evidence suggests that dynamic functional connectivity can capture time-varying abnormalities in brain activity in resting-state cerebral functional magnetic resonance imaging (rs-fMRI) data and has a natural advantage in uncovering mechanisms of abnormal brain activity in schizophrenia (SZ) patients. Hence, an advanced dynamic brain network analysis model called the temporal brain category graph convolutional network (Temporal-BCGCN) was employed. Firstly, a unique dynamic brain network analysis module, DSF-BrainNet, was designed to construct dynamic synchronization features. Subsequently, a revolutionary graph convolution method, TemporalConv, was proposed based on the synchronous temporal properties of features. Finally, the first modular test tool for abnormal hemispherical lateralization in deep learning based on rs-fMRI data, named CategoryPool, was proposed. This study was validated on COBRE and UCLA datasets and achieved 83.62% and 89.71% average accuracies, respectively, outperforming the baseline model and other state-of-the-art methods. The ablation results also demonstrate the advantages of TemporalConv over the traditional edge feature graph convolution approach and the improvement of CategoryPool over the classical graph pooling approach. Interestingly, this study showed that the lower-order perceptual system and higher-order network regions in the left hemisphere are more severely dysfunctional than in the right hemisphere in SZ, reaffirmings the importance of the left medial superior frontal gyrus in SZ. Our code was available at: https://github.com/swfen/Temporal-BCGCN.

Abstract Graph partitioning is an NP-hard combinatorial optimization problem, and is a fundamental step in distributing workloads on parallel compute systems, circuit placement, and sparse matrix reordering. The proposed heuristic algorithms such as streaming graph partitioning provide solutions to large-scale graph in a reasonable amount of time. However, the ability of breaking out of local minima in existing these methods is very limited as they are simple in reflecting the connectivity between vertices in real graphs with power-law distribution characteristic. As hill climbing algorithm is a local search method, it can be adopted to improve the result of graph partitioning. However, directly adopting the existing hill climbing algorithm to graph partitioning will result in local minima and poor convergence speed during the iterative process. In this paper, we propose an improved hill climbing graph partitioning algorithm based on clustering. Instead of taking a single vertex as a basic unit, the proposed method considers a cluster consisting of a series of vertices as a hill to move during each iteration. The method uses a new metric that considers both balance and edgecuts to look for the most beneficial cluster as the hill. With these improvements, the method provides a strong power to break out of local minima and achieve an adaptive tradeoff between balance and edgecuts. Experimental results on real-world graphs show that the proposed algorithm substantially reduces edgecuts within a controlled imbalance range.

We propose a new incompressible Navier-Stokes solver based on the impulse gauge transformation. The mathematical model of our approach draws from the impulse-velocity formulation of Navier-Stokes equations, which evolves the fluid impulse as an auxiliary variable of the system that can be projected to obtain the incompressible flow velocities at the end of each time step. We solve the impulse-form equations numerically on a Cartesian grid. At the heart of our simulation algorithm is a novel model to treat the impulse stretching and a harmonic boundary treatment to incorporate the surface tension effects accurately. We also build an impulse PIC/FLIP solver to support free-surface fluid simulation. Our impulse solver can naturally produce rich vortical flow details without artificial enhancements. We showcase this feature by using our solver to facilitate a wide range of fluid simulation tasks including smoke, liquid, and surface-tension flow. In addition, we discuss a convenient mechanism in our framework to control the scale and strength of the turbulent effects of fluid.

We propose a novel gauge fluid solver based on Clebsch wave functions to solve incompressible fluid equations. Our method combines the expressive power of Clebsch wave functions to represent coherent vortical structures and the generality of gauge methods to accommodate a broad array of fluid phenomena. By evolving a transformed wave function as the system's gauge variable enhanced by an additional projection step to enforce pressure jumps on the free boundaries, our method can significantly improve the vorticity generation and preservation ability for a broad range of gaseous and liquid phenomena. Our approach can be easily implemented by modifying a standard grid-based fluid simulator. It can be used to solve various fluid dynamics, including complex vortex filament dynamics, fluids with different obstacles, and surface-tension flow.

We propose a new family of neural networks to predict the behaviors of physical systems by learning their underpinning constraints. A neural projection operator lies at the heart of our approach, composed of a lightweight network with an embedded recursive architecture that interactively enforces learned underpinning constraints and predicts the various governed behaviors of different physical systems. Our neural projection operator is motivated by the position-based dynamics model that has been used widely in game and visual effects industries to unify the various fast physics simulators. Our method can automatically and effectively uncover a broad range of constraints from observation point data, such as length, angle, bending, collision, boundary effects, and their arbitrary combinations, without any connectivity priors. We provide a multi-group point representation in conjunction with a configurable network connection mechanism to incorporate prior inputs for processing complex physical systems. We demonstrated the efficacy of our approach by learning a set of challenging physical systems all in a unified and simple fashion including: rigid bodies with complex geometries, ropes with varying length and bending, articulated soft and rigid bodies, and multi-object collisions with complex boundaries.