Estimating the electrical power output of industrial devices with end to end time series classification in the presence of label noise

The proposed approach targets to gradually correct themislabelled data samples during training in a self-supervised fashion, without any prior assumption on the amount of label noise . We benchmark our approach on several time-series classification datasets and find it to be comparable and sometimes better than state-of-the-art methods .…

Markov Rewards Processes with Impulse Rewards and Absorbing States

We study the expected accumulated reward for a discrete-time Markov rewardmodel . The rewards are impulse rewards, where a reward is accumulated when transitioning from state $i$ to state $j$. Wederive an explicit, single-letter expression for the expected reward as a function of the number of time steps $n$ and include in ouranalysis the limit in which $n \to \infty$.…

Lane Graph Estimation for Scene Understanding in Urban Driving

Lane-level scene annotations provide invaluable data in autonomous vehiclesfor trajectory planning in complex environments such as urban areas and cities . However, obtaining such data is time-consuming and expensive since laneannotations have to be annotated manually by humans . In this work, we propose a novel approach for lanegeometry estimation from bird’s-eye-view images .…

Stochastic Mutual Information Gradient Estimation for Dimensionality Reduction Networks

Feature ranking and selection is a widely used approach in various applications of supervised dimensionality reduction in discriminative machinelearning . We introduce emerginginformation theoretic feature transformation protocols as an end-to-end neuralnetwork training approach . The network projects high-dimensional features onto an output feature space where lower dimensional representations of features carry maximum mutual information with their associated class labels .…

Inversion free feedforward hysteresis control using Preisach operator

We introduce a new type of inversion-free feedforward hysteresis control with the Preisach operator . We show the achievable bandwidth and accuracy of the proposed control . Remarkable fact is that the control bandwidth is theoretically infinite . Numerical controlexamples with the preisach model in differential form are shown anddiscussed in detail .…

A Brief Survey And Investigation Of Hybrid Beamforming For Millimeter Waves In 5G Massive MIMO Systems

Millimeter-wave (mm-wave) is a promising technique to enhance the networkcapacity and coverage of next-generation (5G) networks . Improving the 5Gnetwork requires enhancing and employing mm-wave beamforming channelpropagation characteristics . The trade-off between the energy consumption of RF chains and cost efficiency depends on reducing the number of radio frequency (RF) chains and the distributed number of users .…

Waypoint Planning Networks

Waypoint planning networks (WPN) is a hybrid algorithm based on LSTMs with alocal kernel – a classic algorithm such as A* . WPN produces a more computationally efficient and robust solution . It is shown that WPN’s search space is considerably less than A* while being able to generate near optimal results.…

Distributed Energy Trading Management for Renewable Prosumers with HVAC and Energy Storage

Heating, ventilating, and air-conditioning (HVAC) systems consume a largeamount of energy in residential houses and buildings . Effective energymanagement of HVAC is a cost-effective way to improve energy efficiency and reduce the energy cost of residential users . This work develops a noveldistributed method for the residential transactive energy system that enables multiple users to interactively optimize their energy management .…

Signature Based Abduction with Fresh Individuals and Complex Concepts for Description Logics Extended Version

ABox abduction aims at computing a hypothesis that, when added to the knowledge base, is insufficient to entail the observation . This form of abduction has applications such as diagnosis, KB repair, or explaining missing details . It is possible that hypotheses for a given observation only exist if we admit the use of fresh individuals and/or complex concepts built from the given signature .…

Blockchain Based Decentralized Energy Management Platform for Residential Distributed Energy Resources in A Virtual Power Plant

The advent of distributed energy resources (DERs), such as distributedrenewables, energy storage, electric vehicles, and controllable loads, is a significantly disruptive and transformational impact on the centralized power system . Virtual power plant emerges as a promisingparadigm for managing DERs to participate in the power system, says the authors .…

A Robust Object Encoding Method

Object encoding and identification is crucial for many robotic tasks such as autonomous exploration and semantic relocalization . In this paper, we propose a novel object encoding method based on agraph of key-points . It is a plug-and-play module and we expect that it will play an important role in the robotic applications .…

WfChef Automated Generation of Accurate Scientific Workflow Generators

WfChef is a framework that fully automates the process of constructing a synthetic workflow generator for any scientific application . It is based on an input set of workflow instances and automatically produces asynthetic workflow generator . We find that the Wfchef generators not only require zero development effort(because it is automatically produced), but also generate workflows that are more realistic than those generated by hand-crafted generators .…

Designing Games for Enabling Co creation with Social Agents

Digital tools have long been used for supporting children’s creativity . Digital games that allow children to create artifacts and express themselves in a playful environment serve as efficient Creativity Support Tools (or CSTs) Creativity is also scaffolded by social interactions with others in the environment .…

Pedestrian Collision Avoidance for Autonomous Vehicles at Unsignalized Intersection Using Deep Q Network

Thispaper explores AV navigation in crowded, unsignalized intersections . DDQN/PER outperforms the other two methods . It shows the smallest average intersection crossing time, the greatest average crossing time and the greatest distance from the closest pedestrian . For both scenarios, the rule-based method achieves less than 40\% collision-free episodes, whereas our methods result in a performance of approximately 100\%.…

Coupling purposes with status functions in artificial institutions

In multi-agent systems, agents may have goals that depend on a social, shared interpretation about the facts occurring in the system . Artificial institutions provide such a socialinterpretation by assigning statuses to concrete elements that compose thesystem . These statuses are supposed to enable the assignee element to perform functions that are not exclusively inherent to their design features .…

Run time Norms Synthesis in Multi Objective Multi Agent Systems

Normative systems enablecoordinating synthesised norms of heterogeneous agents in complex multi-agentsystems autonomously . Norms represent behavioural aspects that are encouraged by a social group of agents or the majority of agents in a system . In real applications, agents have multiple objectivesthat may contradict each other .…

lr Multisemigroups and Modal Convolution Algebras

We show how modal quantales arise as convolution algebras of functions fromlr-multisemigroups . The class generalises Schweizer and Sklar’s function systems and object-free categories . We also discuss how these results can be combined with previous ones for concurrent quantales andgeneralised to a setting that supports reasoning with stochastic matrices orprobabilistic predicate transformers.…

Theoretical Analysis for Determining Geographical Route of Cable Network with Various Disaster Endurance Levels

This paper theoretically analyzes cable network disconnection due to randomlyoccurring natural disasters . The disaster-endurance (DE) levels of thenetwork are determined by network entity such as the type of shielding method used for a duct containing cables . When a part of a network can be protected, the placement of that part can be specified to decrease the probability of connecting two given nodes with a partially protected network are provided .…

Science as a Public Good Public Use and Funding of Science

Common depictions suggest that scientificresearch remains an isolated or ‘ivory tower’ activity, with weak connectivity to public use . Yet, we find key forms of alignment in theinterface between science and society . Despite myriad factors underpinning the public funding of science, the resulting allocation across fields presents a striking alignment with the field’s collective public use.…

Learning for Detecting Norm Violation in Online Communities

In this paper, we focus on normative systems for online communities . We propose aframework capable of detecting norm violations and providing the violator withinformation about the features of their action that makes this action violate anorm. We build our framework using Machine Learning, with Logistic Model Treesas the classification algorithm.…

A structural operational semantics for interactions with a look at loops

Message Sequence Charts & Sequence Diagrams are graphical models that represent the behavior of distributed and concurrent systems via the scheduling of discrete and local emission and reception events . We propose an InteractionLanguage (IL) to formalize such models, defined as a term algebra which includes strict and weak sequencing, alternative and parallel composition and four kinds of loops .…

Types are Internal infty Groupoids

By extending type theory with a universe of definitionally associative and unital polynomial monads, we show how to arrive at a definition of opetopictype which is able to encode a number of fully coherent algebraic structures . We prove that the type of such $infty$-groupoids isequivalent to the universe of types .…

Towards Certified Analysis of Software Product Line Safety Cases

Safety-critical software systems are in many cases designed and implemented as families of products, usually referred to as Software Product Lines . We apply this infrastructure to formalize and lift a Change Impact Assessment (CIA) algorithm . We present a formal definition of the lifted algorithm, outline its correctness proof (with the full machine-checked proof available online), and discuss its implementation within a model managementframework .…

Asymptotic behavior of fronts and pulses of the bidomain model

The bidomain model is the standard model for cardiac electrophysiology . In this paper, we investigate the instability and asymptotic behavior of planarfronts and planar pulses . We find that, afterthe planar front is destabilized, a rotating zigzag front develops whose shape can be explained by simple geometric arguments using a suitable Frank diagram .…

Generative Art Using Neural Visual Grammars and Dual Encoders

A novel algorithm for producing generative art isdescribed which allows a user to input a text string, and which in a creative response to this string, outputs an image which interprets that string . It doesso by evolving images using a hierarchical neural Lindenmeyer system, andevaluating these images along the way using an image text dual encoder trained on billions of images and their associated text from the internet .…

Neko a Library for Exploring Neuromorphic Learning Rules

The field of neuromorphic computing is in a period of active exploration . While many tools have been developed to simulate neuronal dynamics or convertdeep networks to spiking models, general software libraries for learning rules remain underexplored . We present Neko, a modular, extensible library with a focus on aiding the design of new learning algorithms .…

Normalization of regressor excitation as a part of dynamic regressor extension and mixing procedure

The method of excitation normalization of the regressor is used in theestimation loop to solve the plant identification problem . It is based on the dynamic regressor extension and mixing procedure . Its application allows to obtain the same upper bound of the parameter identification error for the scalar regressors with different excitation levels, using a constant value of the adaptation rate for all of them .…

A robust high order implicit shock tracking method for simulation of complex high speed flows

High-order implicit shock tracking is a new class of numerical methods toroximate solutions of conservation laws with non-smooth features . The key challenge is robustly solving the centraloptimization problem . The proposed method integrates practical robustness measures into a sequentialquadratic programming method, including dimension- and order-independentsimplex element collapses, mesh smoothing, and element-wise solutionre-initialization .…

Three terminal Erasure Source Broadcast with Feedback

We study the effects of introducing a feedback channel in the erasuresource-broadcast problem for the case of three receivers . We propose a queue-based hybrid digital-analog coding scheme that achieves optimal performance for the duration of analog transmissions . The second method is a novel chaining algorithm that involves the transmitter targeting point-to-point performance for two users as if they were the only users in the network.…