## KPop Fandoms drive COVID 19 Public Health Messaging on Social Media

This report examines an unexpected but significant source of positive public health messaging during the COVID-19 pandemic . Analyses reveal theSouth Korean boyband BTS as the most significant driver of health discourse . Tweets from health agencies and prominent figures that mentioned K-pop generate111 times more of online response compared to tweets that did not .…

## Fair Regression under Sample Selection Bias

All previous fair regressionresearch assumed training data and testing data are drawn from the samedistributions . This assumption is often violated in real world due to sample selection bias between training and testing . In this paper, wedevelop a framework for fair regression under sample selection .…

## TranSalNet Visual saliency prediction using transformers

Convolutional neural networks (CNNs) have significantly advancedcomputational modeling for saliency prediction . But the inherent inductivebiases of convolutional architectures cause insufficient long-range contextualencoding capacity, which potentially makes a saliency model less humanlike . The proposed model achieves promising results in predicting saliency, and the new components make improvements, according to the paper .…

## Representation of professions in entertainment media Insights into frequency and sentiment trends through computational text analysis

Media portrayal of culture, education, government, religion, and family affect function and evolution over time as people interpret and perceive theserepresentations and incorporate them into their beliefs and actions . In this work, we examine media representation ofprofessions and provide computational insights into their incidence, andsentiment expressed, in entertainment media content .…

## Uniform Guarded Fragments

In this paper we prove that the uniform one-dimensional guarded fragment is a natural polyadic generalization of the guarded two-variable logic . We will also prove that . the satisfactioniability problem of uniform guarded fragment of uniform . fragment is NEXPTIME-complete .…

## Toward a Wearable Biosensor Ecosystem on ROS 2 for Real time Human Robot Interaction Systems

The package standardizes biosensor HRIintegration, lowers the technical barrier of entry, and expands the biosensorecosystem into the robotics field . The wearable biosensor package is made publicly available on GitHub atÂhttps://://https://github.com/SMARTlab-Purdue/ros2-foxy-wearable-biosensors. We expect that standardization of this biosensors package for ROS2 will greatly simplify use and cross-collaboration across many disciplines.…

## Affective Burst Detection from Speech using Kernel fusion Dilated Convolutional Neural Networks

In the continuous emotionrecognition (CER) problem, tracking changes across affective states is animportant and desired capability . The proposed classifier is a kernel-fusion dilated convolutionalneural network (KFDCNN) architecture driven by speech spectral features to segment the affective attribute contour into idle and burst sections.…

## GaitPrivacyON Privacy Preserving Mobile Gait Biometrics using Unsupervised Learning

GaitPrivacyON is a novel mobile gait biometrics verification approach that provides accurate authentication results while preserving the sensitive information of the subject . It comprises two modules: i) a convolutionalAutoencoder that transforms attributes of the biometric raw data, such as the gender or the activity being performed, into a new privacy-preservingrepresentation .…

## Chromatic Aberration Recovery on Arbitrary Images

Digital imaging sensor technology has continued to outpace development inoptical technology in modern imaging systems . The resulting quality lossattributable to lateral chromatic aberration is becoming increasinglysignificant as sensor resolution increases . The goals ofhigher-performance and lighter lens systems drive a recent need to find new ways to overcome resulting image quality limitations .…

## Snowy Recommending Utterances for Conversational Visual Analysis

SNOWY is a prototype system that generates and recommends utterances for visual analysis based on a combination of data interestingness metrics and language pragmatics . It supports conversational visual analysis by guiding theparticipants’ analytic workflows and making them aware of the system’s languageinterpretation capabilities .…

## Bounds for the Twin width of Graphs

Bonnet, Kim, Thomass\'{e, and Watrigant (2020) introduced the twin-width of a graph . We show that the twin width of an $n$-vertex graph is less than $(n+\sqrt{n\ln n}+\qrt {n}+2\lt n}$ asymptotically almost surely for any positive $varepsilon$ We also calculate the twinwidth of randomgraphs $G(n,p)$ with $p\leq c/n$ for a constant $c <1$ and $1$ to $2$ . …

## A subexponential view of domains in session types

Linear logic (LL) has inspired the design of many computational systems,offering reasoning techniques built on top of its meta-theory . The subexponentials in LL have played an important role in concurrent systems since they can beinterpreted in different ways, including timed, spatial and even epistemicmodalities in distributed systems .…

## Toward a Theory of Programming Language and Reasoning Assistant Design Minimizing Cognitive Load

Current approaches to making programming languages and reasoning assistants focus on leveraging feedback from users and onevaluating the success of particular techniques . These approaches, although helpful, may not result in systems that are as usable as possible, and may not lead to general design principles .…

## Measure Twice Cut Once Quantifying Bias and Fairness in Deep Neural Networks

Bias in AI is more abstract and unintuitive forms of discrimination and can be more difficult to detect andmitigate . A clear gap exists in the current literature on evaluating therelative bias in the performance of multi-class classifiers . In this work, we propose two simple yet effective metrics, Combined Error Variance (CEV) andSymmetric Distance Error (SDE) to quantitatively evaluate the class-wise bias of two models in comparison to one another .…

## A Framework for Aspectual Requirements Validation An Experimental Study

Aspect-Oriented Requirements Engineering (AORE) extends the existing software engineering approaches to cope with the issue of tangling andscattering resulted from crosscutting concerns . The proposed framework comprises a high-level and low-levelvalidation to implement on software requirements specification (SRS) Validation of requirements artefacts is an essential task in software development .…

## Symbolic Register Automata for Complex Event Recognition and Forecasting

We propose an automaton model which is a combination of symbolic and registerautomata . We call such automataSymbolic Register Automata (SRA) SRA extend the expressive power of symbolic automata, by allowing arbitrary Boolean formulas to be applied to multiple elements stored in their registers .…

## Knowledge aware Coupled Graph Neural Network for Social Recommendation

Social recommendation task aims to predict users’ preferences over items with the incorporation of social connections among users . KCGN enables the high-order user- and item-wise relation encoding byexploiting the mutual information for global graph structure awareness . We further augment KCGN with the capability of capturing dynamicmulti-typed user-item interactive patterns .…

## Towards Math Aware Automated Classification and Similarity Search of Scientific Publications Methods of Mathematical Content Representations

In this paper, we investigate mathematical content representations suitablefor the automated classification of and the similarity search in STEM documents . The methods are evaluated on asubset of arXiv.org papers with the Mathematics Subject Classification (MSC) as a reference classification and using the standard precision/recall/F1-measuremetrics .…

## Relationship between low discrepancy sequence and static solution to multi bodies problem

The main interest of this paper is to study the relationship between the low-discrepancy sequence and the static solution to the multi-bodies problem in high-dimensional space . We also combine the DEM with therestarting technique to generate a series of low-Discrepancy sequences .…

## The similarity index of mathematical and other scientific publications with equations and formulas and the problem of self plagiarism identification

The problems of estimating the similarity index of inhomogeneous scientific publications containing equations and formulas are discussed for the firsttime . The presence of equations, formulas (as well asfigures, drawings, and tables) is a complicating factor that significantlycomplicates the study of such texts .…

## Simulations for novel problems in recommendation analyzing misinformation and data characteristics

In this position paper, we discuss recent applications of simulation approaches for recommender systems tasks . In particular, we describe how they were used to analyze the problem of misinformation spreading . We also present potential lines of future work wheresimulation methods could advance the work in the recommendation community .…

## Core Elements of Social Interaction for Constructive Human Robot Interaction

We present a discovery-based, first version of social interaction model that provides a basis for measuring the quality of interaction of a human user with a social robot . The two core elements of the social interactionmodel are engagement and co-regulation .…

## A Study of Low Resource Speech Commands Recognition based on Adversarial Reprogramming

In this study, we propose a novel adversarial reprogramming (AR) approach for low-resource spoken command recognition . The AR procedure aims to modify the acoustic signals (from the target domain) to repurpose a pretrained SCR model . We evaluate the proposed AR-SCR system on three low- resource SCR datasets, including Arabic,Lithuanian, and dysarthric Mandarin speech .…

## Nash Convergence of Mean Based Learning Algorithms in First Price Auctions

We consider repeated first price auctions where each bidder, having adeterministic type, learns to bid using a mean-based learning algorithm . We characterize the Nash convergence property of the bidding dynamics in two senses: (1) time-average: the fraction of rounds where bidders play aNash equilibrium approaches to 1 in the limit; (2) last-iterate: the mixedstrategy profile of bidder approaches to a Nash equilibrium in limit .…

## Connection Management xAPP for O RAN RIC A Graph Neural Network and Reinforcement Learning Approach

Connection management is an important problem for any wireless network to ensure smooth and well-balanced operation throughout . Traditional methods for connection management (specifically user-cell association) consider sub-optimaland greedy solutions such as connection of each user to a cell with maximumreceive power .…

## Smart Crawling A New Approach toward Focus Crawling from Twitter

Twitter is a social network that offers a rich and interesting source of information challenging to retrieve and analyze . The available operations allow retrieving tweets on the basis of a set of keywords but with limitations such as the number of calls perminute and the size of results .…

## Graph Meta Network for Multi Behavior Recommendation

Modern recommender systems often embed users and items into low-dimensionallatent representations, based on their observed interactions . Exploring multi-typed behavior patterns is of great importance torecommendation systems, yet is very challenging because of two aspects: i. The complex dependencies across different types of user-item interactions; ii)Diversity of such multi-behavior patterns may vary by users due to their personalized preference .…

## TFix Self configuring Hybrid Timeout Bug Fixing for Cloud Systems

Timeout bugs can cause serious availability and performance issues which are difficult to fix due to the lack of diagnostic information . In this paper, we present TFix+ a self-configuring timeout bug fixingframework for automatically correcting two major kinds of timeout bugs with dynamic timeout valuepredictions .…

## Contextual Sentence Classification Detecting Sustainability Initiatives in Company Reports

We introduce the novel task of detecting sustainability initiatives incompany reports . Given a full report, the aim is to automatically identifymentions of practical activities that a company has performed in order totackle specific societal issues . As a single initiative can often be described over multiples sentences, new methods for identifying continuous sentence spans needs to be developed .…

## A criterion for critical junctions in elastic plastic adhesive wear

We investigate elastic-plastic adhesive wear via a continuum variationalphase-field approach . The model seamlessly captures the transition fromperfectly brittle, over quasi-brittle to elastic-PLastic wear regimes . Simulation results highlight the existence of a critical condition that morphological features and materialductility need to satisfy for the adhesive junction to detach a wear debris .…

## MAPA Multi Accelerator Pattern Allocation Policy for Multi Tenant GPU Servers

Multi-accelerator servers are increasingly being deployed in sharedmulti-tenant environments (such as in cloud data centers) in order to meet thedemands of large-scale compute-intensive workloads . We propose Multi-AcceleratorPattern Allocation (MAPA) a graph pattern mining approach . MAPA is able to improve theexecution time of multi-ACcelerator workloads and that MAPA can provide generalized benefits across various accelerator topologies.…

## On the Optimal Memorization Power of ReLU Neural Networks

We study the memorization power of feedforward ReLU neural networks . We show that such networks can memorize any $N$ points that satisfy a mild separability assumption using $Omega(N/L) parameters . We also give a generalized construction for networks withdepth bounded by$1 \leq L (L) and $1) for memorizing$N samples .…

## Enabling On Device Training of Speech Recognition Models with Federated Dropout

Federated learning can be used to train machine learning models on the edge on local data that never leave devices, providing privacy by default . We propose using federated dropout to reduce the size of client models while training a full-size model server-side .…

## On the Complexity of Inductively Learning Guarded Rules

We investigate the computational complexity of mining guarded clauses through the framework of inductive logic programming (ILP) Weshow that learning guarded clauses is NP-complete and thus one step below the task of learning Horn clauses on the polynomialhierarchy . Motivated by practical applications on large datasets we identify anatural tractable fragment of the problem .…