## Using social network and semantic analysis to analyze online travel forums and forecast tourism demand

Forecasting tourism demand has important implications for both policy makers and companies operating in the tourism industry . We analyzed forums of 7 major Europeancapital cities, over a period of 10 years, collecting more than 2,660,000 posts, written by about 147,000 users .…

## Acceleration of the kernel herding algorithm by improved gradient approximation

Kernel herding is a method used to construct quadrature formulas in areproducing kernel Hilbert space . However, the convergence speed of worst-case integration error is low compared to other methods . To address this problem, we propose two improved versions of the kernel herding algorithm .…

## Improving Vulnerability Prediction of JavaScript Functions Using Process Metrics

The first step towards this is to automaticallyrecognize the vulnerable parts in our code . Researchers put a lot of effort into creating machine learning models that could determine if a given piece ofcode contains any vulnerabilities . We aim at improving the existing models, building on previous results in predicting vulnerabilities at the level of functions in JavaScript code .…

## TopicsRanksDC Distance based Topic Ranking applied on Two Class Data

TopicsRanksDC is a novel approach to ranking topics based on the distance between two clusters that are generated by each topic . The algorithm detects topics using Latent Dirichlet Allocation (LDA) The results show that the rank for LDA topics is much higher than random topics .…

## Prototype supervised Adversarial Network for Targeted Attack of Deep Hashing

ProS-GAN is the first generation-based method to attack deep hashing networks . The proposed framework consists of three parts, i.e., a PrototypeNet, a generator, and a discriminator . The prototype code is adopted to supervise the generatorto construct the targeted adversarial example by minimizing the Hammingdistance between the hash code and the prototypecode .…

## Koopman NMPC Koopman based Learning and Nonlinear Model Predictive Control of Control affine Systems

Using the Koopman canonical transform, control-affine dynamics can be expressed by a lifted bilinear model . The model is used for nonlinear model predictive control (NMPC) design . The benefits are highlighted through an example of a simulated planarquadrotor . Prediction error is greatly reduced and closed loop performancesimilar to NMPC with full model knowledge is achieved .…

## Cortado An Interactive Tool for Data Driven Process Discovery and Modeling

Processmining techniques allow analyzing the event data generated and recorded during the execution of (business processes) to gain valuable insights . Cortado unifies the world of manual process modeling with that of automated process discovery . The tool leverages domain knowledge while incrementally discovering a process model from given event data.…

## Deep Learning Models in Software Requirements Engineering

Thegenerated sentences are not plausible English and contain only a few meaningful words . We believe that applying the model to a larger dataset may produces significantly better results . Further research is needed to improve the quality of generated data .…

## Collaborative Mapping of Archaeological Sites using multiple UAVs

UAVs have found an important application in archaeological mapping . Majority of existing methods employ offline method to process data collected from an archaeological site . They are time-consuming and computationallyexpensive . In this paper, we present a multi-UAV approach for faster mapping ofarchaeological sites .…

## Studying the association of online brand importance with museum visitors An application of the semantic brand score

This paper explores the association between brand importance and growth in museum visitors . We analyzed 10 years of online forum discussions and applied the Semantic Brand Score (SBS) to assess the brand importance of five European museums . Results suggest that in order to attract more visitors, museum brand managers should focus on increasing the volume of online posting and the richness of information generated by users around the brand, rather than controlling for the posts’ overall positivity or negativity .…

## Distributed Computation over MAC via Kolmogorov Arnold Representation

Kolmogorov’s representation theorem provides a framework for decomposing anyarbitrary real-valued, multivariate, and continuous function into a two-layernested superposition of a finite number of functions . This paper capitalizes on such modularity and universality infunctional representation to propose two frameworks for distributed computation .…

Task-based programming models like OmpSss-2 and OpenMP provide a flexibledata-flow execution model to exploit dynamic, irregular and nested parallelism . We propose individual solutions for each of the challenges, including a wait-free dependency system and a novel scalablescheduler design based on delegation .…

Density tracking by quadrature (DTQ) is a numerical procedure for computingsolutions to Fokker-Planck equations . We propose and describe the procedure for $N$-dimensions . We demonstrate that the resulting adaptive procedure issignificantly more efficient than a tensorized approach . Although we considertwo-dimensional examples, all our computational procedures are extendable to higher dimensional problems .…

## Parallel and Flexible Sampling from Autoregressive Models via Langevin Dynamics

Autoregressive models are typically sampled sequentially according to transition dynamics defined by the model . Instead, we propose a samplingprocedure that initializes a sequence with white noise and follows a Markovchain defined by Langevin dynamics . This approach parallelizes the sampling process and generalizes toconditional sampling .…

## The Theory of Functional Connections A journey from theory to application

Theory of Functional Connections (TFC) is a general methodology forfunctional interpolation that can embed a set of user-specified linearconstraints . The functionals derived from this method, called \emph{constrainedexpressions}, analytically satisfy the imposed constraints and can be leveraged to transform constrained optimization problems to unconstrained ones .…

## Thin Film Smoothed Particle Hydrodynamics Fluid

We propose a particle-based method to simulate thin-film fluid that jointlyfacilitates aggressive surface deformation and vigorous tangential flows . We can simulate complexvortical swirls, fingering effects due to Rayleigh-Taylor instability,capillary waves, Newton’s interference fringes, and the Marangoni effect onliberally deforming surfaces by presenting both realistic visual results andnumerical validations .…

## On Decentralization of Bitcoin An Asset Perspective

Since its advent in 2009, Bitcoin, a cryptography-enabled peer-to-peer digital payment system, has been gaining increasing attention from bothacademia and industry . We present in this paper the first systematicinvestigation of the degree of decentralization for Bitcoin based on its entiretransaction history .…

## Stochastic Control through Approximate Bayesian Input Inference

Optimal control under uncertainty is a prevailing challenge in control . By framing the control problem as one of inputestimation, advanced approximate inference techniques can be used to handle thestatistical approximations in a principled and practical manner . Analyzing theGaussian setting, we present a solver capable of several stochastic controlmethods, and was found to be superior to popular baselines on nonlinearsimulated tasks .…

## A hierarchical preconditioner for wave problems in quasilinear complexity

The paper introduces a novel, hierarchical preconditioner based on nesteddissection and hierarchical matrix compression . It is intended for continuous and discontinuous Galerkin formulations of elliptic problems . We demonstrate the viability of the preconditionser on arange of 2D problems, including the Helmholtz equation and the elastic waveequation .…

## Adaptive Interference Coordination over Channels with Unknown State at the Encoder and the Decoder

We generalize the problem of controlling the interference created to anexternal observer while communicating over a discrete memoryless channel (DMC) In particular, we consider the scenario where the transmission is established over a compound DMC channel withunknown state at both the encoder and the decoder .…

## A Unified Adaptive Recoding Framework for Batched Network Coding

Batched network coding is a variation of random linear network coding which has low computational and storage costs . In order to adapt random fluctuations in the number of erasures in individual batches, it is not optimal to recodeand transmit the same number of packets for all batches .…

## Designer User Communication for XAI An epistemological approach to discuss XAI design

Most of the available frameworks and methods for XAI focus on data scientists and ML developers as users . Weargue: We need to discuss XAI early in the AI-system design process and with all stakeholders. We took the SignifyingMessage as our conceptual tool to structure and discuss X AI scenarios.…

## p robust equilibrated flux reconstruction in boldsymbol H mathrm curl based on local minimizations Application to a posteriori analysis of the curl curl problem

We present a local construction of H(curl)-conforming piecewise polynomialssatisfying a prescribed curl constraint . The outcome is, up to a generic constant independent of the underlying polynomorphic degree, as accurate as the best-approximations over the entire local versions ofH(Curl) This allows to design guaranteed, fully computable, constant-free, andpolynomial-degree-robust a posteriori error estimates of Prager-Synge type forN\’ed\’elec finite element approximations of the curl-curl problem .…

## Buying time in software development how estimates become commitments

Despite years of research for improving accuracy, software practitioners still face software estimation difficulties . Researchers’ focus on raising realism inestimates when using it seems not to be enough for the much-expectedimprovements . Instead of focusing on the estimation process’s technicalities, we investigated interaction of the establishment of commitments with customers and software estimation .…

## Towards Demystifying Serverless Machine Learning Training

The appeal of serverless (FaaS) has triggered a growing interest on how touse it in data-intensive applications such as ETL, query processing, or machinelearning (ML) Several systems exist for training large-scale ML models on topof serverless infrastructures (e.g., AWS Lambda) but with inconclusive results .…

## Controlling an Inverted Pendulum with Policy Gradient Methods A Tutorial

This paper provides the details of implementing two important policy gradient algorithms to solve the inverted pendulum problem . These are namely the DeepDeterministic Policy Gradient (DDPG) and the Proximal Policy Optimization (PPO) The problem is solved by using an actor-critic model where anactor-network is used to learn the policy function and a critic network is toevaluate the actor-network by learning to estimate the Q function .…

## Distributionally Robust Chance Constrained Flexibility Planning for Integrated Energy System

Inflexible combined heat and power plants and uncertain wind power production result in excess power in distribution networks . Power-to-X facilities such aselectrolyser and electric boilers can offer extra flexibility to theintegrated energy system . A case study validates the effectiveness of introducing the electrolyserand electric boiler into the integrated energy system, with respect to the decreased system cost, expanded CHP plant flexibility and reduced inverse powerflow .…

## MUSER MUltimodal Stress Detection using Emotion Recognition as an Auxiliary Task

The capability to automatically detect human stress can benefit artificialintelligent agents involved in affective computing and human-computer interaction . Stress and emotion are both human affective states, and stress has important implications on the regulation and expression of emotion . We propose MUSER — a transformer-based model architecture and a novelmulti-task learning algorithm .…

## Enhancing the Usability of Self service Kiosks for Older Adults Effects of Using Privacy Partitions and Chairs

This study aimed to evaluate the effects of possible physical design features of self-service kiosks (SSK), side and back partitions and chairs, on workloadand task performance of older users . Older participants showed a large variation in task performance across the design alternatives indicating stronger impacts of the physical features .…

## TSDF A Multi Object Formulation for Dynamic Object Tracking and Reconstruction

The ability to simultaneously track and reconstruct multiple objects moving in the scene is of the utmost importance for robotic tasks such as autonomous navigation and interaction . We introduce a novel multi-object TSDF formulation that can encodemultiple object surfaces at any given location in the map .…

## On exploration requirements for learning safety constraints

Enforcing safety for dynamical systems is challenging, since it requiresconstraint satisfaction along trajectory predictions . Equivalent controlconstraints can be computed in the form of sets that enforce positiveinvariance . However, these constraints are cumbersome to compute from models, and it is not yet well established how to infer constraints from data .…

## A Scalable Concurrent Algorithm for Dynamic Connectivity

Dynamic Connectivity is a fundamental algorithmic graph problem, motivated by a wide range of applications to social and communication networks . In brief, we wish to maintain theconnected components of the graph under dynamic edge insertions and deletions . The most efficient variant improves the performance of a coarse-grained based implementation on realistic scenarios up to 6x on average and up to 30x when connectivity queries dominate .…

## Choice Set Confounding in Discrete Choice

Standard methods in preference learning involve estimating parameters of choice models from data of selections (choices) made by individuals from a discrete set of alternatives . Ignoring these assignment mechanisms can mislead choice models into making biased estimates of preferences .…

## StRETcH a Soft to Resistive Elastic Tactile Hand

Soft optical tactile sensors enable robots to manipulate deformable objects . StRETcH, a Soft to Resistive Elastic Tactile Hand, is easily manufactured and integrated with a robotic arm . An elasticmembrane is suspended between two robotic fingers, and a depth sensor captures deformations of the elastic membrane .…

## Dual Stage Low Complexity Reconfigurable Speech Enhancement

This paper proposes a dual-stage, low complexity, and reconfigurabletechnique to enhance the speech contaminated by various types of noise sources . The proposed speechenhancement scheme can be easily adopted in both capture path and speech renderpath for speech communication and conferencing systems, and voice-triggerapplications .…

## A Data Efficient Approach to Behind the Meter Solar Generation Disaggregation

With the emergence of battery storage and the decline in thesolar photovoltaic (PV) levelized cost of energy (LCOE), the number ofbehind-the-meter solar PV systems is expected to increase steadily . The ability to estimate solar generation from these latent systems is crucial for a range of applications, including distribution system planning and operation, demandresponse, and non-intrusive load monitoring .…

## To be a fast adaptive learner using game history to defeat opponents

In real-world games, it is very hard for a single AI trader to make good deals with customers in a few turns . Webelieve that past game history plays a vital role in such a learning procedure . They propose a novel framework (named, F3) to fuse the past and current game history with an Opponent Action Estimator (OAE) module that uses past history to estimate the opponent’s future behaviors .…

## Exploring Self Supervised Representation Ensembles for COVID 19 Cough Classification

The usage of smartphone-collected respiratory sound, trained with deeplearning models, for detecting and classifying COVID-19 becomes popular . However, existing sound-based diagnostic approaches are trained in a fully supervised manner, which requires large scale well-labelleddata . In this paper, we propose a novel self-supervised learning enabled framework for cough classification.…

## Mean Field Games Flock The Reinforcement Learning Way

We present a method enabling a large number of agents to learn how to flock, which is a natural behavior observed in large populations of animals . We phrase this problem as a MeanField Game, where each individual chooses its acceleration depending on the population behavior .…

## EasyFL A Low code Federated Learning Platform For Dummies

EasyFL requires only three lines of code to build avanilla FL application, at least 10x lesser than other platforms . EasyFL expedites training by 1.5x. It also improves the efficiency of experiments and deployment. EasyFL will increase the productivity of data scientists and democratize FL to wideraudiences.…

## The Confluence of Networks Games and Learning

Recent years have witnessed significant advances in technologies and services in modern network applications, including smart grid management, wirelesscommunication, cybersecurity as well as multi-agent autonomous systems . Emerging network applications call for game-theoretic models and learning-based approaches in order to create distributed network intelligence that responds to uncertainties and disruptions in a dynamic or an adversarial environment .…