Transfer Learning for Human & AI

Caregivers in eldercare can benefit from telepresence robots that allow them to perform a variety of tasks remotely . We examine if and how the robotic system’s level of automation (LOA) impacts their performance . Results revealed that performance improved at high LOA whenthe task complexity was low .…

The effectiveness of the code review is that it ensures the quality of software and makes it updated . Code review is the best process that helps the developers to develop asystem errorless . This report contains two different code review papers to beevaluated and find the influences that can affect the code reviewing process .…

Envy-freeness is one of the most widely studied notions in fair division . Since envy-free allocations do not always exist when items are indivisible . We show that an EFXallocation always exists (i) when all agents have one of two general valuationsor (ii) when the number of items is at most $n+3$ .…

A priori-estimates on the unknownsare obtained, and along with a topological degree argument they lead to theexistence of a solution of the discrete scheme at each time step . We conclude the proof of the convergence of the scheme toward the continuous problem as mesh size and time step tend toward zero with the limit of the sequence ofdiscrete solutions being a solution to the weak formulation of the problem .…

Cohesive subgraph mining on attributed graphs is a fundamental problem ingraph data analysis . Existing mining algorithms on attributedgraphs do not consider the fairness of attributes in the subgraph . In this paper, we for the first time introduce fairness into the widely-used cliquemodel to mine fairness-aware cohesive subgraphs .…

The Anonymisation Decision-making Framework (ADF) operationalizes the riskmanagement of data exchange between organizations . The second edition of ADF has increased its emphasis on modeling data flows . We show how data environments can be implemented within the W3CPROV in four different ways .…

An important property of concurrent objects is whether they support progress-a special case of liveness-guarantees, which ensure the termination of method calls under system fairness assumptions . Typical liveness propertiesincludelock-freedom,wait-freedom,.deadlock-freedom and starvation-freedom are undecidable on TSO for a bounded number of processes, while obstruction-freedom is decidable .…

In this paper, we proposed a multi-objective approach for the EEG InverseProblem . This formulation does not need unknown parameters that involveempirical procedures . Due to the combinatorial characteristics of the problem, this alternative included evolutionary strategies to resolve it .…

In this paper we extend PeerNomination, the most accurate peer reviewing algorithm to date, into WeightedPeerNomination . We show analytically that a weighting scheme can improve the overall accuracy of the selection significantly . We explicitly formulate assessors’ reliability weights in a way that doesn’t violate strategyproofness, and use this information to reweight their scores .…

A decision maker wants to predict weather tomorrow by eliciting andaggregating information from crowd . How can the decision maker incentivize the crowd to report their information truthfully? Ignoring the heterogeneity among the agent may lead to inefficient of biased information, which would lead to suboptimal decisions .…

This paper is concerned with the error estimates of the fully discrete generalized finite element method (GFEM) with optimal local approximationspaces for solving elliptic problems with heterogeneous coefficients . The error bound of the discrete GFEM approximation isproved to converge as $h\rightarrow 0$ towards that of the continuous GFEMapproximation, which was shown to decay nearly exponentially in previous works .…

We study fair allocation of indivisible public goods subject to cardinality(budget) constraints . In this model, we have n agents and m available publicgoods, and we want to select $k \leq m$ goods in a fair and efficient manner . We prove that MNW allocations provide fairness guarantees of Proportionality upto one good (Prop1), $1/n$ approximation to Round Robin Share (RRS) and theefficiency guarantee of Pareto Optimality (PO) Further, we show that theproblems of finding MNW or leximin-optimal allocations are NP-hard, even in thecase of constantly many agents, or binary valuations .…

Electrocardiogram (ECG) is an authoritative source to diagnose and countercritical cardiovascular syndromes such as arrhythmia and myocardial infarction(MI) Current machine learning techniques either depend on manually extractedfeatures or large and complex deep learning networks which merely utilize the1D ECG signal directly .…

Unmanned aerial vehicles (UAVs) and Terahertz (THz) technology are envisioned to play paramount roles in next-generation wireless communications . We present a secure two-phase transmission strategy with cooperative jamming . We assume that the UAV-mounted relay may act, besides providing services, as a potential adversary called the untrusted UAV relay.…

Coordination in multi-agent systems is challenging for agile robots such as UAVs, where relative agent positions frequentlychange due to unconstrained movement . This work proposes autonomous hierarchical multi-level clustering (MLC), which forms aclustering hierarchy utilizing decentralized methods . Using observation aggregation, compression, and dissemination, agentsshare local observations throughout the hierarchy, giving every agent a totalsystem belief with spatially dependent resolution and freshness .…

State-of-the-art driver-assist systems have failed to effectively mitigatedriver inattention and had minimal impacts on the ever-growing number of roadmishaps . This is because traditional human-machine interaction settings are modeled in classical and behavioralgame-theoretic domains . We propose a novel equilibrium notion in human-systeminteraction games, where the system maximizes its expected utility and humandecisions can be characterized using any general decision model .…

In this paper, we consider the IoT data discovery problem in very large and growing scale networks . We investigate in depth the routing tablesummarization techniques to support effective and space-efficient IoT datadiscovery routing . Novel summarization algorithms, including alphabeticalbased, hash based, and meaning based summarization, are proposed .…

We construct a computationally inexpensive 3D extension of Andrew’s plots . We consider linear isometries from a Euclidean data space to infinite dimensional spaces of 2D curves . Weparametrize the linear isometry that produces (on average) optimally smoothcurves over a given dataset .…

This paper investigates adaptive streaming of one or multiple tiled 360videos from a multi-antenna base station . We aim to maximize the video quality while keeping rebuffering time small via encoding rate adaptationat each group of pictures (GOP) and transmission adaptation at each(transmission) slot .…

Causal relations (e.g., If A, then B) are prevalent in functional requirements . For various applications of AI4RE, automatically extracting such causal statements are a basic necessity . We lack an approach that is able to extract causal relations from natural language requirements in fine-grainedform .…

Skyline computation is an essential database operation that has many applications in multi-criteria decision making scenarios such as recommendersystems . Existing algorithms have focused on checking point domination, which lack efficiency over large datasets . We propose a grid-based structure that enables grid cell domination checks .…

We present a new method for assessing homophily in networks whose verticeshave categorical attributes, namely when the vertices of networks comepartitioned into classes . We apply this method to Protein- Protein Interactionnetworks, where vertices correspond to proteins, partitioned according to theyfunctional role, and edges represent potential interactions between proteins .…

Canned patterns (i.e. small subgraph patterns) in visual graph queryinterfaces (a.k.a GUI) facilitate efficient query formulation by enablingpattern-at-a-time construction mode . TATTOO takes a data-driven approach to automaticallyselecting canned patterns for a . GUI from large networks . It first decomposes the underlying network into truss-infested and truss .oblivious…

Interdisciplinary application fields show an increasing need for reliable andresilient wireless communication even under high load conditions . We propose STING, a spatially distributed traffic and interference generation framework . STING is evaluated in a remote control test case of an Unmanned Ground Vehicle that serves as a scout in Search and Rescue missions .…

Due to power consumption and high circuit cost in antenna arrays, thepractical application of massive multiple input multiple-input multiple-output (MIMO) in thesixth generation (6G) and future wireless networks is still challenging . Employing lowresolution analog-to-digital converters (ADCs) and hybrid analogand digital (HAD) structure is two low-cost choice with acceptable performanceloss .…

Emotion recognition is an important research field for Human-ComputerInteraction . Audio-Video Emotion Recognition (AVER) is now attacked withDeep Neural Network (DNN) modeling tools . We hypothesize that for fuzzycategories of emotional events, the higher noise of one modality can amplify the lower noise of the second modality represented indirectly in the parameters of the modeling neural network .…

There is an urgent need for a tool that can detect musicplagiarism automatically . The increasing number of musical pieces have made the problem of music plagiarism prominent . Researchers have proposed various methods to extractlow-level and high-level features of music and compute their similarities .…

Woodpeckers can cause significant damage to homes, especially in suburban areas . There are a number of preventing and repelling methods including passivedecoys . Subsequently, it may bemore efficient to implement a woodpecker deterrent, such as motion, light,sound, or ultrasound that would be triggered by detection of woodpeckery drumming .…

The support for ultra-reliable communication is a key distinction betweentoday’s and tomorrow’s mobile networks, enabling emergingcritical-communication services such as factory automation, remote-controlledvessels, mobile cloud computing, and yet-to-come applications . We consider two network design assets, bandwidthand network density, and network models by the 3GPP .…

The motivation of this paper is to introduce a cell-free adaptation of the strongest-user collision resolution (SUCRe) protocol . The SUCRe protocol was originally proposed forcellular massive multiple-input multiple- input multiple-output (MIMO) networks . The goal with this adaptation is to show that a cell free network can better handle the attempts of users’ equipment (UEs) due to the augmented macro-diversity brought by the disposition of access points (APs) over the coverage area .…

Symbolic music generation has attracted increasing attention . Generating long music calls for effective expression of the coherentmusic structure . Self-attention based models can generate music sequences (up to 100 bars) with interpretablestructures . The generated 3,000sets of music is uploaded as supplemental material.…

A well-known result due to Fannes is a certain upper bound on the modulus ofcontinuity of the von Neumann entropy with respect to the trace distance between density matrices . This distance is the maximum probability of distinguishing between quantum states .…

Audio captioning aims to automatically generate a natural languaged description of an audio clip . Most captioning models follow an encoder-decoderarchitecture, where the decoder predicts words based on the audio featuresextracted by the encoder . Convolutional neural networks (CNNs) and recurrentneural networks (RNNs) are often used as the audio encoder.…

In this paper, we consider the IoT data discovery problem in very large and growing scale networks . We investigate in depth the routing tablesummarization techniques to support effective and space-efficient IoT datadiscovery routing . Novel summarization algorithms, including alphabeticalbased, hash based, and meaning based summarization, are proposed .…

We describe our approach to create and deliver a custom voice for aconversational AI use-case . Our proposed cloudarchitecture enables for fast voice delivery, making it possible to talk to the digital version of Albert Einstein in real-time . We use a custom dictionary for selected words to ensure their proper pronunciation .…

Remixing separated audio sources trades off interferer attenuation against the amount of audible deteriorations . This paper proposes a non-intrusive audio quality estimation method for controlling this trade-off in a signal-adaptivemanner . Deep neural networks (DNNs) are trained to estimate the 2f-model intrusively using the reference target(iDNN2f), using the input mix as reference (nDNN) and reference-free using only the separated output signal .…

The rapid growth of blockchain systems leads to increasing interest in understanding and comparing blockchain performance at scale . In this paper, we focus on analyzing the performance of Hyperledger Fabric v1.1 – one of the most popular permissioned blockchain systems .…

In this paper, we extend to the block case, the a posteriori bound showingsuperlinear convergence of Conjugate Gradients . We also present a series of computational experiments, illustrating the validity of the bound developed here, as well asthe bound from [SIAM Review, 47 (2005), pp.…

Deep generative models have recently achieved impressive performance inspeech synthesis and music generation . However, the generation of general sounds (such as carhorn, dog barking, and gun shot) has received less attention, despite their potential applications . In this work, we propose to generate sounds conditioned on sound classes via neural discretetime-frequency representation learning .…

Automated Audio captioning (AAC) is a cross-modal translation task that aims to use natural language to describe the content of an audio clip . We propose a novel encoder-decoder framework called Contrastive Lossfor Audio Captioning (CL4AC) In CL4AC, the self-supervision signals derivedfrom the original audio-text paired data are used to exploit thecorrespondences between audio and texts by contrasting samples, which can improve the quality of latent representation .…

Wireless Sensor Networks (WSNs) have recently attracted greater attention due to their practicality in monitoring, communicating, and reportingspecific physical phenomena . The data collected by WSNs is often inaccurate as a result of unavoidable environmental factors, which may include noise, signalweakness, or intrusion attacks depending on the specific situation .…

Symbolic music generation has attracted increasing attention . Generating long music calls for effective expression of the coherentmusic structure . Self-attention based models can generate music sequences (up to 100 bars) with interpretablestructures . The generated 3,000sets of music is uploaded as supplemental material.…

Coordination in multi-agent systems is challenging for agile robots such as UAVs, where relative agent positions frequentlychange due to unconstrained movement . This work proposes autonomous hierarchical multi-level clustering (MLC), which forms aclustering hierarchy utilizing decentralized methods . Using observation aggregation, compression, and dissemination, agentsshare local observations throughout the hierarchy, giving every agent a totalsystem belief with spatially dependent resolution and freshness .…

The matrix formation associated to high-order discretizations is known to benumerically demanding . We design a multiscale assembly procedure to reduce the exorbitant assembly time in the context of isogeometric linear elasticity of complexmicrostructured geometries modeled via spline compositions . The strategy turns out to be of great interest not only to form finite elementoperators but also to compute other quantities in a fast manner as for instancesensitivity analyses commonly used in design optimization .…

Paper develops tools to quantify the importance of agent interactions and its impact on global performance metrics for networks modeled as lineartime-invariant systems . It proposes a novel notion of edge centrality that encodes the first-ordervariation in the metric with respect to the modification of the correspondingedge weight .…

In this work we study and analyze a class of Duhem hysteresis operators that exhibit butterfly loops . We study the consistency property of such operators . We present examples where examples where the Duhem butterfly hyesteresis operator are constructed using two zero-level set curves that satisfy some mild conditions.…

We study how good a lexicographically maximal solution is in weightedmatching and matroid intersection problems . A solution is lexicurallymaximal if it takes as many heaviest elements as possible . We prove that if the ratio is less than $2$, say $2$, then a Lexicurally maximal solution achieves $(\alpha/2)$-approximation,and this bound is tight .…

We present a conditional text generation framework that posits sententialexpressions of possible causes and effects . This framework depends on a very large-scale collection of English sentences expressing causal patterns CausalBank . We extend prior work in lexically-constrained decoding to support disjunctive positive constraints .…

Demonstration-guided reinforcement learning (RL) is a promising approach for learning complex behaviors by leveraging both reward feedback and a set of target task demonstrations . We propose Skill-based Learning with Demonstrations(SkiLD), an algorithm for demonstration-guided RL that efficiently leveragesthe provided demonstrations by following the demonstrated skills instead of theprimitive actions .…

Contact tracing is a key tool for managing epidemic diseases like HIV,tuberculosis, and COVID-19 . Manual investigations by human contact tracers remain a dominant way in which this is carried out . This process is limited by the number of contact tracer tracers available .…