CAN3D: Fast 3D Medical Image Segmentation via Compact Context Aggregation

Direct automatic segmentation of objects from 3D medical imaging, such as magnetic resonance (MR) imaging, is challenging as it often involves accurately identifying a number of individual objects with complex geometries within a large volume under investigation. To address these challenges, most deep learning approaches typically enhance their learning capability by substantially increasing the complexity or the number of trainable parameters within their models. Consequently, these models generally require long inference time on standard workstations operating clinical MR systems and are restricted to high-performance computing hardware due to their large memory requirement. Further, to fit 3D dataset through these large models using limited computer memory, trade-off techniques such as patch-wise training are often used which sacrifice the fine-scale geometric information from input images which could be clinically significant for diagnostic purposes. To address these challenges, we present a compact convolutional neural network with a shallow memory footprint to efficiently reduce the number of model parameters required for state-of-art performance. This is critical for practical employment as most clinical environments only have low-end hardware with limited computing power and memory. The proposed network can maintain data integrity by directly processing large full-size 3D input volumes with no patches required and significantly reduces the computational time required for both training and inference. We also propose a novel loss function with extra shape constraint to improve the accuracy for imbalanced classes in 3D MR images.

Conflict-Free Four-Dimensional Path Planning for Urban Air Mobility Considering Airspace Occupations

Urban air mobility (UAM) has attracted the attention of aircraft manufacturers, air navigation service providers and governments in recent years. Preventing the conflict among urban aircraft is crucial to UAM traffic safety, which is a key in enabling large scale UAM operation. Pre-flight conflict-free path planning can provide a strategic layer in the maintenance of safety performance, thus becomes an important element in UAM. This paper aims at tackling conflict-free path planning problem for UAM operation with a consideration of four-dimensional airspace management. In the first place, we introduced and extended a four-dimensional airspace management concept, AirMatrix. On the basis of AirMatrix, we formulated the shortest flight time path planning problem considering resolution of conflicts with both static and dynamic obstacles. A Conflict-Free A-Star algorithm was developed for planning four-dimensional paths based on first-come-first-served scheme. The algorithm contains a novel design of heuristic function as well as a conflict detection and resolution strategy. Numerical experiment was carried out in Jurong East area in Singapore, and the results show that the algorithm can generate paths resolving a significant number of potential conflicts in airspace utilization, with acceptable computational time and flight delay. The contributions of this study provide references for stakeholders to support the development of UAM.

BrainNNExplainer: An Interpretable Graph Neural Network Framework for Brain Network based Disease Analysis

Interpretable brain network models for disease prediction are of great value for the advancement of neuroscience. GNNs are promising to model complicated network data, but they are prone to overfitting and suffer from poor interpretability, which prevents their usage in decision-critical scenarios like healthcare. To bridge this gap, we propose BrainNNExplainer, an interpretable GNN framework for brain network analysis. It is mainly composed of two jointly learned modules: a backbone prediction model that is specifically designed for brain networks and an explanation generator that highlights disease-specific prominent brain network connections. Extensive experimental results with visualizations on two challenging disease prediction datasets demonstrate the unique interpretability and outstanding performance of BrainNNExplainer.

Third Party Risk Modelling and Assessment for Safe UAV Path Planning in Metropolitan Environments

Various applications of advanced air mobility (AAM) in urban environments facilitate our daily life and public services. As one of the key issues of realizing these applications autonomously, path planning problem has been studied with main objectives on minimizing travel distance, flight time and energy cost. However, AAM operations in metropolitan areas bring safety and society issues. Because most of AAM aircraft are unmanned aerial vehicles (UAVs) and they may fail to operate resulting in fatality risk, property damage risk and societal impacts (noise and privacy) to the public. To quantitatively assess these risks and mitigate them in planning phase, this paper proposes an integrated risk assessment model and develops a hybrid algorithm to solve the risk-based 3D path planning problem. The integrated risk assessment method considers probability and severity models of UAV impact ground people and vehicle. By introducing gravity model, the population density and traffic density are estimated in a finer scale, which enables more accurate risk assessment. The 3D risk-based path planning problem is first formulated as a special minimum cost flow problem. Then, a hybrid estimation of distribution algorithm (EDA) and risk-based A* (named as EDA-RA*) algorithm is proposed to solve the problem. To improve computational efficiency, k-means clustering method is incorporated into EDA-RA* to provide both global and local search heuristic information, which formed the EDA and fast risk-based A* algorithm we call EDA-FRA*. Case study results show that the risk assessment model can capture high risk areas and the generated risk map enables safe UAV path planning in urban complex environments.

Deep Kernel Gaussian Process Based Financial Market Predictions

The Gaussian Process with a deep kernel is an extension of the classic GP regression model and this extended model usually constructs a new kernel function by deploying deep learning techniques like long short-term memory networks. A Gaussian Process with the kernel learned by LSTM, abbreviated as GP-LSTM, has the advantage of capturing the complex dependency of financial sequential data, while retaining the ability of probabilistic inference. However, the deep kernel Gaussian Process has not been applied to forecast the conditional returns and volatility in financial market to the best of our knowledge. In this paper, grid search algorithm, used for performing hyper-parameter optimization, is integrated with GP-LSTM to predict both the conditional mean and volatility of stock returns, which are then combined together to calculate the conditional Sharpe Ratio for constructing a long-short portfolio. The experiments are performed on a dataset covering all constituents of Shenzhen Stock Exchange Component Index. Based on empirical results, we find that the GP-LSTM model can provide more accurate forecasts in stock returns and volatility, which are jointly evaluated by the performance of constructed portfolios. Further sub-period analysis of the experiment results indicates that the superiority of GP-LSTM model over the benchmark models stems from better performance in highly volatile periods.

FedScale: Benchmarking Model and System Performance of Federated Learning

We present FedScale, a diverse set of challenging and realistic benchmark datasets to facilitate scalable, comprehensive, and reproducible federated learning (FL) research. FedScale datasets are large-scale, encompassing a diverse range of important FL tasks, such as image classification, object detection, language modeling, speech recognition, and reinforcement learning. For each dataset, we provide a unified evaluation protocol using realistic data splits and evaluation metrics. To meet the pressing need for reproducing realistic FL at scale, we have also built an efficient evaluation platform to simplify and standardize the process of FL experimental setup and model evaluation. Our evaluation platform provides flexible APIs to implement new FL algorithms and includes new execution backends with minimal developer efforts. Finally, we perform indepth benchmark experiments on these datasets. Our experiments suggest fruitful opportunities in heterogeneity-aware co-optimizations of the system and statistical efficiency under realistic FL characteristics. FedScale is open-source with permissive licenses and actively maintained,1 and we welcome feedback and contributions from the community.

Long time existence for semilinear wave equations with the inverse-square potential

In this paper, we study the semilinear wave equations with the inverse-square potential. By transferring the original equation to a fractional dimensional wave equation and analyzing the properties of its fundamental solution, we establish a long-time existence result, for sufficiently small, spherically symmetric initial data. Together with the previously known blow-up result, we determine the critical exponent which divides the global existence and finite time blow-up. Moreover, the sharp lower bounds of the lifespan are obtained, except for certain borderline case. In addition, our technology allows us to handle an extreme case for the potential, which has hardly been discussed in literature.

Newtonian Binding from Lattice Quantum Gravity

We study scalar fields propagating on Euclidean dynamical triangulations (EDT). In this work we study the interaction of two scalar particles, and we show that in the appropriate limit we recover an interaction compatible with Newtons gravitational potential in four dimensions. Working in the quenched approximation, we calculate the binding energy of a two-particle bound state, and we study its dependence on the constituent particle mass in the non-relativistic limit. We find a binding energy compatible with what one expects for the ground state energy by solving the Schr{o}dinger equation for Newtons potential. Agreement with this expectation is obtained in the infinite-volume, continuum limit of the lattice calculation, providing non-trivial evidence that EDT is in fact a theory of gravity in four dimensions. Furthermore, this result allows us to determine the lattice spacing within an EDT calculation for the first time, and we find that the various lattice spacings are smaller than the Planck length, suggesting that we can achieve a separation of scales and that there is no obstacle to taking a continuum limit. This lends further support to the asymptotic safety scenario for gravity.

Existence of solutions for singular double phase problems via the Nehari manifold method

In this paper we study quasilinear elliptic equations driven by the double phase operator and a right-hand side which has the combined effect of a singular and of a parametric term. Based on the Nehari manifold method we are going to prove the existence of at least two weak solutions for such problem when the parameter is sufficiently small.

Radial profile of bottom quarks in jets in high-energy nuclear collisions

Angular correlations between heavy quark (HQ) and its tagged jet are potentially new tools to gain insight into the in-medium partonic interactions in relativistic heavy-ion collisions. In this work, we present the first theoretical study on the radial profiles of B mesons in jets in Pb+Pb collisions at the LHC. The initial production of bottom quark tagged jet in p+p is computed by SHERPA which matches the next-to-leading order matrix elements with contributions of parton shower, whereas the massive quark traversing the QGP described by a Monte Carlo model SHELL which can simultaneously simulate light and heavy flavor in-medium energy loss within the framework of Langevin evolution. In p+p collisions, we find that at lower $p_T^Q$ the radial profiles of heavy flavors in jets are sensitive to the heavy quark mass. In $0-10%$ Pb+Pb collisions at $rm sqrt{s_{NN}}=5.02$ TeV, we observe an inverse modification pattern of the B mesons radial profiles in jets at $rm 4<p_T^Q<20$ GeV compared to that of D mesons: the jet quenching effects narrow the jet radial profile of B mesons in jets while broaden that of D mesons in jets. We find that in A+A collisions, the contribution dissipated from the higher $rm p_T^Q> 20$ GeV region naturally has a narrower initial distribution and consequently leads to a narrower modification pattern of radial profile; however the diffusion nature of the heavy flavor in-medium interactions will give rise to a broader modification pattern of radial profile. These two effects consequently compete and offset with each other, and the b quarks in jets benefit more from the former and suffers less diffusion effect compared to that of c quarks in jets. These findings can be tested in the future experimental measurements at the LHC to gain better understanding of the mass effect of jet quenching.