## Evaluating the performance of personal social health related biomarker and genetic data for predicting an individuals future health using machine learning A longitudinal analysis

The study compares the performance of five types of measures: age, sex, social, health-related, biomarker and genetic single nucleotidepolymorphisms (SNPs) The predicted outcome variable was limiting long-termillness one and five years from baseline . Health-related measures had the strongest prediction of future health status, with genetic data performing poorly .…

## Spatio Temporal Pruning and Quantization for Low latency Spiking Neural Networks

Spiking Neural Networks (SNNs) are a promising alternative to traditional deep learning methods since they perform event-driven information processing . The efficiency of SNNs could be enhanced using compression methods such as pruning andquantization . Thespatiotemporally pruned SNNS achieve 89.04% and 66.4% accuracy on CIFAR10 and 66%.…

## Unified Spatio Temporal Modeling for Traffic Forecasting using Graph Neural Network

Research in deep learning models to forecast traffic intensities has gainedgreat attention in recent years due to their capability to capture the complexspatio-temporal relationships within the traffic data . We propose a UnifiedSpatio-Temporal Graph Convolution Network (USTGCN) for traffic forecasting that performs both spatial and temporal aggregation through direct informationpropagation across different timestamp nodes .…

## Wasserstein distance estimates for the distributions of numerical approximations to ergodic stochastic differential equations

We present a framework that allows for the non-asymptotic study of the $2$-Wasserstein distance between the invariant distribution of an ergodicstochastic differential equation and the distribution of its numericalapproximation in the strongly log-concave case . This allows us to study in aunified way a number of different integrators proposed in the literature for the overdamped and underdamped Langevin dynamics .…

## The Relative Consistency of the Axiom of Choice Mechanized Using Isabelle ZF

The proof of the relative consistency of the axiom of choice has beenmechanized using Isabelle/ZF . It builds upon a previous mechanization of the reflection theorem . The heavy reliance on metatheory in the original proof is not entirely satisfactory .…

## Syft 0 5 A Platform for Universally Deployable Structured Transparency

Syft is a general-purpose framework that combines a core group of privacy-enhancing technologies that facilitate a universal set of structured transparency systems . This framework is demonstrated through the design and implementation of a novel privacy-preserving inference information flow wherewe pass homomorphically encrypted activation signals through a split neuralnetwork for inference .…

## Finite sample approximations of exact and entropic Wasserstein distances between covariance operators and Gaussian processes

This work studies finite sample approximations of the exact and entropic regularized Wasserstein distances between centered Gaussian processes and, moregenerally, covariance operators of functional random processes . We first show that these distances/divergences are fully represented by reproducing kernelHilbert space (RKHS) covariance and cross-covariance operators associated with the corresponding covariance functions .…

## One parameter family of acquisition functions for efficient global optimization

Bayesian optimization (BO) with Gaussian processes is a powerful methodology to optimize an expensive black-box function . The expected improvement (EI) and probability of improvement (PI) are among the most widely used schemes for BO . The proposed method isnumerically inexpensive, is easy to implement, can be easily parallelized, and on benchmark tasks shows a performance superior to EI and GP-UCB .…

## Improved Bounded Model Checking of Timed Automata

Timed Automata (TA) are a very popular modeling formalism for systems with time-sensitive properties . A common task is to verify if a network of TAsatisfies a given property, usually expressed in Linear Temporal Logic (LTL) The produced CLTLoc formula can then be solved by toolssuch as Zot, which transforms CLTLOC properties into the input logics of SMT solvers .…

## Towards Knowledge Graphs Validation through Weighted Knowledge Sources

The performance of applications rely on high-quality knowledge bases, a.k.a. Knowledge Graphs . To ensure their quality one important task is KnowledgeValidation, which measures the degree to which statements or triples of a Knowledge Graph (KG) are correct . We propose and implement a validation approach that computes a confidence score for everytriple and instance in a KG .…

## Dense Point Prediction A Simple Baseline for Crowd Counting and Localization

In this paper, we propose a simple yet effective crowd counting and localization network named SCALNet . We consider those tasks as a pixel-wisedense prediction problem and integrate them into an end-to-end framework . We adopt a counting head supervised by theMean Square Error (MSE) loss .…

## DABT A Dependency aware Bug Triaging Method

The Dependency-aware Bug Triaging (DABT) leverages natural language processing and integer programming to assign bugs to developers . DABT is able to reduce the number of overdue bugs up to 12\% . It also decreases the average fixing time of the bugs by half .…

## Improving 6TiSCH Reliability and Latency with Simultaneous Multi Band Operation

The Internet Engineering Task Force (IETF) group “IPv6 over the TSCH mode ofIEEE 802.15.4e” (6TiSCH) introduced a protocol, utilizing Time-Slotted ChannelHopping (TSCH) from IEEE802.15 .4e due to its high reliability andtime-deterministic characteristic, that achieves industrial performancerequirements while offering the benefits of IP connectivity .…

## Recalibration of Aleatoric and Epistemic Regression Uncertainty in Medical Imaging

The consideration of predictive uncertainty in medical imaging with deeplearning is of utmost importance . We apply $\sigma$ scaling with a single scalarvalue; a simple, yet effective calibration method for both types ofuncertainty . The performance of our approach is evaluated on a variety of common medical regression data sets using different state-of-the-artconvolutional network architectures .…

dualFace consists of two-stage drawing assistance toprovide global and local visual guidance: global guidance, which helps users draw contour lines of portraits, and local guidance, inspired by traditional artist workflows in portrait drawing . In the stage of local guidance users synthesize detailed portrait images with a deep generative model, but use the synthesized results as detailed drawing guidance .…

Channel sensing consists of probing the channel from time to time to check whether or not it is active – say of an incoming message . When communication is sparse with information being sent once in a long while,channel sensing becomes a significant source of energy consumption .…

## Evaluating Query Languages and Systems for High Energy Physics Data

High-energy physics (HEP) physicists have found limited acceptance in the domain of data analysis . This is surprising since dataanalysis in HEP matches the SQL model well . Those offering the best possibilities in expressiveness, conciseness, and usability turn out to be the slowest and most expensive .…

NOMAD is software for optimizing blackbox problems . New architecture provides moreflexible code, added functionalities and reusable code . New features include MegaSearchPoll component, warm and hot restarts, and revised version of PSD-MADS algorithm . NOMad is freely available at www.gerad.ca/nomad…

## Geometric approximation of the sphere by triangular polynomial spline patches

A sphere is a fundamental geometric object widely used in (computer aided)geometric design . It possesses rational parameterizations but no parametricpolynomial parameterization exists . The present study provides an approach to the optimal approximation of equilateral spherical triangles by parametric polynomial patches if the measure of quality is the (simplified) radial error .…

## A Priori Analysis of Discontinuous Galerkin Finite Element Method for Dynamic Viscoelastic Models

Deformations of viscoelastic materials such as soft tissues, metals at hightemperature, and polymers can be described as Volterra integral equations of the second kind . We use a spatially discontinuous Galerkin finite element method and a finitedifference method in time to formulate the fully discrete problem .…

## The Influence of Audio on Video Memorability with an Audio Gestalt Regulated Video Memorability System

Memories are the tethering threads that tie us to the world, and memorability is measure of their tensile strength . Unfurling these fibres is the key tounderstanding the nature of their interaction, and how we can ultimately createmore meaningful media content .…

## Spatially Coherent Clustering Based on Orthogonal Nonnegative Matrix Factorization

Classical approaches in cluster analysis are typically based on a featurespace analysis . Many applications lead to datasets with additionalspatial information and ground truth with spatially coherent classes . We propose several approaches with different optimization techniques, where the TV regularization is either performed as a subsequent postprocessing step or included into the clustering algorithm .…

## Communication Efficient Federated Learning with Dual Side Low Rank Compression

Federated learning (FL) is a promising and powerful approach for training deep learning models without sharing the raw data of clients . We propose a new training method, referred to as federated learning with dual-side low-rank compression . FedDLR reduces the communication overhead during the training stage but also generates a compact model to speed up the inference process .…

## 3D Scene Compression through Entropy Penalized Neural Representation Functions

The method significantly outperforms a state-of-the-art approach for scene compression, achieving simultaneously higherquality reconstructions and lower bitrates . The function is implemented as a neural network and jointly trained for reconstruction as well as compression, in an end-to-end manner, with the use of an entropy penalty on the parameters .…

## A PGAS Communication Library for Heterogeneous Clusters

This work presents a heterogeneous communication library for clusters ofprocessors and FPGAs . This library, Shoal, supports the Partitioned GlobalAddress Space (PGAS) memory model for applications . PGAS is a shared memorymodel for clusters that creates a distinction between local and remote memory access .…

## Efficient training of physics informed neural networks via importance sampling

Physics-Informed Neural Networks (PINNs) are a class of deep neural networksthat are trained, using automatic differentiation, to compute the response of systems governed by partial differential equations (PDEs) The training of PINNs is simulation-free, and does not require any training dataset to be obtained from numerical PDE solvers .…

## Efficient Hyperparameter Optimization for Physics based Character Animation

Physics-based character animation has seen significant advances in recent years with the adoption of Deep Reinforcement Learning (DRL) However,DRL-based learning methods are usually computationally expensive . Tuninghyperparameters for these methods often requires repetitive training of controlpolicies . In this work, we propose a novel Curriculum-based Multi-Fidelity Bayesian Optimization framework .…

## Dynamic VAEs with Generative Replay for Continual Zero shot Learning

Continual zero-shot learning(CZSL) is a new domain to classify objects sequentially the model has not seen during training . It is more suitable thanzero-shot and continual learning approaches in real-case scenarios when datamay come continually with only attributes for a few classes and attributes andfeatures for other classes .…

## baller2vec A Look Ahead Multi Entity Transformer For Modeling Coordinated Agents

In many multi-agent spatiotemporal systems, the trajectories of the agents are oftenstatistically dependent at any given time step . In this paper, we introduce baller2vec++, amulti-entity Transformer that can effectively model coordinated agents . We show that,unlike the previous model, baller 2vec++ can learn toemulate the behavior of perfectly coordinated agents in a simulated toydataset .…

## A Session Subtyping Tool Extended Version

Session types are becoming popular and have been integrated in several programming languages . The notion of subtyping used in session type implementations is the one defined by Gay and Hole for synchronous communication . The aim of this paper is to make the growing body of knowledge about asynchronous session subtypp more accessible to non-experts and promote its integration in practical applications of sessiontypes .…

## Points2Sound From mono to binaural audio using 3D point cloud scenes

Binaural sound that matches the visual counterpart is crucial to bring immersive experiences to people in augmented reality (AR) and virtual reality (VR) applications . This paper proposes Points2Sound, amulti-modal deep learning model which generates a binaural version from monoaudio using 3D point cloud scenes .…

## Communication Efficient and Personalized Federated Lottery Ticket Learning

LotteryFL relies on unicasttransmission on the downlink, and ignores mitigating stragglers, questioningscalability . CELL is a federated lottery ticket learning algorithm, coinedCELL, which exploits downlink broadcast for communication efficiency. CELL achieves up to 3.6% higher personalized task classification accuracy with 4.3x smaller total communication cost until convergence under the CIFAR-10 dataset .…

## Semi Decentralized Federated Edge Learning for Fast Convergence on Non IID Data

Federated edge learning (FEEL) has emerged as an effective alternative to reduce the large communication latency in Cloud-based machine learningsolutions . Unfortunately, the learningperformance of FEEL may be compromised due to limited training data in a singleedge cluster . By allowing modelaggregation between different edge clusters, SD-FEEL enjoys the benefit of .…

## Intelligent Reflective Transmissive Metasurfaces for Full Dimensional Communications Principles Technologies and Implementation

The concept of intelligent omni-surfaces(IOSs) is able to serve mobile users on both sides of the surface to achieve full-dimensional communications by its reflective and transmissive properties . The working principle of the IOS is introduced and a novel hybridbeamforming scheme is proposed for IOS-based wireless communications .…

## Deep Learning Empowered Predictive Beamforming for IRS Assisted Multi User Communications

The realization of practical intelligent reflecting surface (IRS) systems critically depends on properbeamforming design exploiting accurate channel state information (CSI) However, channel estimation (CE) in IRS-MUC systems requires a significantlylarge training overhead due to the numerous reflection elements involved inIRS .…

## Game Theoretic Mode Scheduling for Dynamic TDD in 5G Systems

Dynamic time-division duplexing (TDD) enables independent uplink/downlinkmode scheduling at each cell, based on the local traffic . However, this createscross-interference among cells. Thus, the joint power allocation and scheduling problem becomes mixed-integer non-convex and turns out to be NP-hard. Wepropose a low-complexity and decentralized solution .…

## The Reachability Problem for Petri Nets is Not Primitive Recursive

We present a way to lift up the tower lowerbound of the reachability problem for Petri nets to match the Ackermannian upperbound closing a long standingopen problem . We also prove that the reachable problem in fix dimension is elementary .…

## Designing Optimal Key Lengths and Control Laws for Encrypted Control Systems based on Sample Identifying Complexity and Deciphering Time

There has been no systematic methodology of constructing cyber-physical systems that can achieve desired control performance while being protected against eavesdropping attacks . We propose a systematic method for designing the both of an optimal key length and an optimal controller to maximize both of the controlperformance and the difficulty of the identification .…

## Joint Activity Detection and Data Decoding in Massive Random Access via a Turbo Receiver

In this paper, we propose a turbo receiver for joint activity detection and data decoding in grant-free massive random access . The detector is developed based on a bilinear inferenceproblem that exploits the common sparsity pattern in the received pilot and data signals .…

## Adaptive Encoding for Constrained Video Delivery in HEVC VP9 AV1 and VVC Compression Standards and Adaptation to Video Content

The dissertation proposes the use of a multi-objective optimization framework for designing and selecting among enhanced GOP configurations in videocompression standards . The proposed methods achieve fine optimization over aset of general modes that include: (i) maximum video quality, (ii) minimumbitrate, (iii) maximum encoding rate (previously minimum encoding time mode) and (iv) can be shown to improve upon the YouTube/Netflix default encoder modesettings over a set of opposing constraints to guarantee satisfactoryperformance .…

## CSI free Rotary Antenna Beamforming for Massive RF Wireless Energy Transfer

Radio frequency (RF) wireless energy transfer (WET) is a key technology that may allow seamlessly powering future low-energy Internet of Things(IoT) networks . To enable efficient massive WET, channel state information(CSI)-limited/free multi-antenna transmit schemes have been recently proposedin the literature .…

## Efficient Evolutionary Models with Digraphons

We present two main contributions which help us in leveraging the theory ofgraphons for modeling evolutionary processes . We show a generative model fordigraphons using a finite basis of subgraphs, which is representative ofbiological networks with evolution by duplication . We also show an efficient implementation to do simulations on finite basis segmentations of digraphons .…

## Spherical formulation of geometric motion segmentation constraints in fisheye cameras

We introduce a visual motion segmentation method employing spherical geometry for fisheye cameras and automoated driving . Three commonly used geometric constraints in pin-hole imagery are reformulated to spherical coordinates . A fourth constraint, known as the anti-parallel constraint, is added to resolve motion-parallax ambiguity, to support the detection of moving objects undergoing parallel or near parallel motion with respect to the hostvehicle .…

## HyperRNN Deep Learning Aided Downlink CSI Acquisition via Partial Channel Reciprocity for FDD Massive MIMO

In frequencydivision duplex systems, full channel reciprocity does not hold, and CSIacquisition generally requires downlink pilot transmission followed by uplinkfeedback . The proposed method is based on a novel deep learningarchitecture — HyperRNN — that combines hypernetworks and recurrent neuralnetworks (RNNs) to optimize the transfer of long-term channel features fromuplink to downlink .…

## International Migration in Academia and Citation Performance An Analysis of German Affiliated Researchers by Gender and Discipline Using Scopus Publications 1996 2020

Germany has become a major country of immigration, as well as a researchpowerhouse in Europe . As Germany spends a higher fraction of its GDP onresearch and development than most countries with advanced economies, there is an expectation that Germany should be able to attract and retain internationalscholars who have high citation performance .…

## Dynamic Degradation for Image Restoration and Fusion

The DDRF-Net is capable of solving twoproblems, i.e., static restoration and fusion, dynamic degradation . In order to solve the static fusion problem of existing methods, dynamic convolution is introduced . In addition, adynamic degradation kernel is proposed to improve the robustness of imagerestoration and fusion .…

## Wise SrNet A Novel Architecture for Enhancing Image Classification by Learning Spatial Resolution of Feature Maps

VGG models used two sets of fully connected layers for the classification part of their architectures, which significantly increasesthe number of models’ weights . ResNet and next deep convolutional models used the Global Average Pooling (GAP) layer to compress the feature map and feed it to the classification layer .…

## Variational Pedestrian Detection

Pedestrian detection in a crowd is a challenging task due to a high number of human instances, which brings ambiguity and optimizationdifficulties to the current IoU-based ground truth assignment procedure inclassical object detection methods . The proposed algorithm serves as an efficient solution to handle the dense pedestrian detection problem for the case of single-stagedetectors .…