Search

Battery-free sensor tags are devices that leverage backscatter techniques to communicate with standard IoT devices, thereby augmenting a network's sensing capabilities in a scalable way. For communicating, a sensor tag relies on an unmodulated carrier provided by a neighboring IoT device, with a schedule coordinating this provisioning across the network. Carrier scheduling--computing schedules to interrogate all sensor tags while minimizing energy, spectrum utilization, and latency--is an NP-Hard optimization problem. Recent work introduces learning-based schedulers that achieve resource savings over a carefully-crafted heuristic, generalizing to networks of up to 60 nodes. However, we find that their advantage diminishes in networks with hundreds of nodes, and degrades further in larger setups. This paper introduces RobustGANTT, a GNN-based scheduler that improves generalization (without re-training) to networks up to 1000 nodes (100x training topology sizes). RobustGANTT not only achieves better and more consistent generalization, but also computes schedules requiring up to 2x less resources than existing systems. Our scheduler exhibits average runtimes of hundreds of milliseconds, allowing it to react fast to changing network conditions. Our work not only improves resource utilization in large-scale backscatter networks, but also offers valuable insights in learning-based scheduling., Comment: 15 Pages, 12 Figures. Pre-print, under review

The recent increase in data and model scale for language model pre-training has led to huge training costs. In scenarios where new data become available over time, updating a model instead of fully retraining it would therefore provide significant gains. We study the pros and cons of updating a language model when new data comes from new languages -- the case of continual learning under language shift. Starting from a monolingual English language model, we incrementally add data from Danish, Icelandic, and Norwegian to investigate how forward and backward transfer effects depend on pre-training order and characteristics of languages, for three different model sizes. Our results show that, while forward transfer is largely positive and independent of language order, backward transfer can be positive or negative depending on the order and characteristics of new languages. We explore a number of potentially explanatory factors and find that a combination of language contamination and syntactic similarity best fits our results., Comment: Accepted to TSD 2024

Detecting anomalies in electrocardiogram data is crucial to identifying deviations from normal heartbeat patterns and providing timely intervention to at-risk patients. Various AutoEncoder models (AE) have been proposed to tackle the anomaly detection task with ML. However, these models do not consider the specific patterns of ECG leads and are unexplainable black boxes. In contrast, we replace the decoding part of the AE with a reconstruction head (namely, FMM-Head) based on prior knowledge of the ECG shape. Our model consistently achieves higher anomaly detection capabilities than state-of-the-art models, up to 0.31 increase in area under the ROC curve (AUROC), with as little as half the original model size and explainable extracted features. The processing time of our model is four orders of magnitude lower than solving an optimization problem to obtain the same parameters, thus making it suitable for real-time ECG parameters extraction and anomaly detection., Comment: 23 pages, 14 figures

Novel backscatter communication techniques enable battery-free sensor tags to interoperate with unmodified standard IoT devices, extending a sensor network's capabilities in a scalable manner. Without requiring additional dedicated infrastructure, the battery-free tags harvest energy from the environment, while the IoT devices provide them with the unmodulated carrier they need to communicate. A schedule coordinates the provision of carriers for the communications of battery-free devices with IoT nodes. Optimal carrier scheduling is an NP-hard problem that limits the scalability of network deployments. Thus, existing solutions waste energy and other valuable resources by scheduling the carriers suboptimally. We present DeepGANTT, a deep learning scheduler that leverages graph neural networks to efficiently provide near-optimal carrier scheduling. We train our scheduler with relatively small optimal schedules obtained from a constraint optimization solver, achieving a performance within 3% of the optimal scheduler. Without the need to retrain, DeepGANTT generalizes to networks 6x larger in the number of nodes and 10x larger in the number of tags than those used for training, breaking the scalability limitations of the optimal scheduler and reducing carrier utilization by up to 50% compared to the state-of-the-art heuristic. Our scheduler efficiently reduces energy and spectrum utilization in backscatter networks., Comment: 11 pages (excluding references). Submitted version that was accepted to IPSN 2023 (not the camera-ready version). Camera-ready version available here: https://doi.org/10.1145/3583120.3586957

Existing approaches to solving combinatorial optimization problems on graphs suffer from the need to engineer each problem algorithmically, with practical problems recurring in many instances. The practical side of theoretical computer science, such as computational complexity, then needs to be addressed. Relevant developments in machine learning research on graphs are surveyed for this purpose. We organize and compare the structures involved with learning to solve combinatorial optimization problems, with a special eye on the telecommunications domain and its continuous development of live and research networks., Comment: 29 pages, 1 figure, open access journal publication

We formulate, using the discrete nonlinear Schroedinger equation (DNLS), a general approach to encode and process information based on reservoir computing. Reservoir computing is a promising avenue for realizing neuromorphic computing devices. In such computing systems, training is performed only at the output level, by adjusting the output from the reservoir with respect to a target signal. In our formulation, the reservoir can be an arbitrary physical system, driven out of thermal equilibrium by an external driving. The DNLS is a general oscillator model with broad application in physics and we argue that our approach is completely general and does not depend on the physical realisation of the reservoir. The driving, which encodes the object to be recognised, acts as a thermodynamical force, one for each node in the reservoir. Currents associated to these thermodynamical forces in turn encode the output signal from the reservoir. As an example, we consider numerically the problem of supervised learning for pattern recognition, using as reservoir a network of nonlinear oscillators., Comment: 5 pages, 4 figures

Permission-less blockchains can realise trustless trust, albeit at the cost of limiting the complexity of computation tasks. To explain the implications for scalability, we have implemented a trust model for smart contracts, described as agents in an open multi-agent system. Agent intentions are not necessarily known and autonomous agents have to be able to make decisions under risk. The ramifications of these general conditions for scalability are analysed for Ethereum and then generalised to other current and future platforms., Comment: 16 pages, 2 figures

Location and mobility patterns of individuals are important to environmental planning, societal resilience, public health, and a host of commercial applications. Mining telecommunication traffic and transactions data for such purposes is controversial, in particular raising issues of privacy. However, our hypothesis is that privacy-sensitive uses are possible and often beneficial enough to warrant considerable research and development efforts. Our work contends that peoples behavior can yield patterns of both significant commercial, and research, value. For such purposes, methods and algorithms for mining telecommunication data to extract commonly used routes and locations, articulated through time-geographical constructs, are described in a case study within the area of transportation planning and analysis. From the outset, these were designed to balance the privacy of subscribers and the added value of mobility patterns derived from their mobile communication traffic and transactions data. Our work directly contrasts the current, commonly held notion that value can only be added to services by directly monitoring the behavior of individuals, such as in current attempts at location-based services. We position our work within relevant legal frameworks for privacy and data protection, and show that our methods comply with such requirements and also follow best-practices

Our hypothesis is that by equipping certain agents in a multi-agent system controlling an intelligent building with automated decision support, two important factors will be increased. The first is energy saving in the building. The second is customer value---how the people in the building experience the effects of the actions of the agents. We give evidence for the truth of this hypothesis through experimental findings related to tools for artificial decision making. A number of assumptions related to agent control, through monitoring and delegation of tasks to other kinds of agents, of rooms at a test site are relaxed. Each assumption controls at least one uncertainty that complicates considerably the procedures for selecting actions part of each such agent. We show that in realistic decision situations, room-controlling agents can make bounded rational decisions even under dynamic real-time constraints. This result can be, and has been, generalized to other domains with even harsher time constraints., Comment: Appears in Proceedings of the Fifteenth Conference on Uncertainty in Artificial Intelligence (UAI1999)

A content-based network representation of web logs (blogs) using a basic word-overlap similarity measure is presented. Due to a strong signal in blog data the approach is sufficient for accurately classifying blogs. Using Swedish blog data we demonstrate that blogs that treat similar subjects are organized in clusters that, in turn, are hierarchically organized in higher-order clusters. The simplicity of the representation renders it both computationally tractable and transparent. We therefore argue that the approach is suitable as a baseline when developing and analyzing more advanced content-based representations of the blogosphere., Comment: 6 pages, 4 figures New version has higher resolution for figures 2 and 3

A virtual plague is a process in which a behavior-affecting property spreads among characters in a Massively Multiplayer Online Game (MMOG). The MMOG individuals constitute a synthetic population, and the game can be seen as a form of interactive executable model for studying disease spread, albeit of a very special kind. To a game developer maintaining an MMOG, recognizing, monitoring, and ultimately controlling a virtual plague is important, regardless of how it was initiated. The prospect of using tools, methods and theory from the field of epidemiology to do this seems natural and appealing. We will address the feasibility of such a prospect, first by considering some basic measures used in epidemiology, then by pointing out the differences between real world epidemics and virtual plagues. We also suggest directions for MMOG developer control through epidemiological modeling. Our aim is understanding the properties of virtual plagues, rather than trying to eliminate them or mitigate their effects, as would be in the case of real infectious disease., Comment: Accepted for presentation at Digital Games Research Association (DiGRA) conference in Tokyo in September 2007. All comments to the authors (mail addresses are in the paper) are welcome

An abstract architecture for idealized multi-agent systems whose behaviour is regulated by normative systems is developed and discussed. Agent choices are determined partially by the preference ordering of possible states and partially by normative considerations: The agent chooses that act which leads to the best outcome of all permissible actions. If an action is non-permissible depends on if the result of performing that action leads to a state satisfying a condition which is forbidden, according to the norms regulating the multi-agent system. This idea is formalized by defining set-theoretic predicates characterizing multi-agent systems. The definition of the predicate uses decision theory, the Kanger-Lindahl theory of normative positions, and an algebraic representation of normative systems., Comment: 25 pages

An experimental server for stock trading autonomous agents is presented and made available, together with an agent shell for swift development. The server, written in Java, was implemented as proof-of-concept for an agent trade server for a real financial exchange., Comment: 14 pages, 7 figures, intended for B/W printing

We present some new analytical expressions for the so-called Parrondo effect, where simple coin-flipping games with negative expected value are combined into a winning game. Parrondo games are state-dependent. By identifying the game state variable, we can compute the stationary game state probabilities. Mixing losing games increases the probability of entering into a game state with positive value, as can be seen clearly from our analytical expressions for the Parrondo game value., Comment: 6 pages Changed title, abstract, refs + corrected typos and one algebraic mistake (optimal value approximation)

An anticipatory system for guiding plot development in interactive narratives is described. The executable model is a finite automaton that provides the implemented system with a look-ahead. The identification of undesirable future states in the model is used to guide the player, in a transparent manner. In this way, too radical twists of the plot can be avoided. Since the player participates in the development of the plot, such guidance can have many forms, depending on the environment of the player, on the behavior of the other players, and on the means of player interaction. We present a design method for interactive narratives which produces designs suitable for the implementation of anticipatory mechanisms. Use of the method is illustrated by application to our interactive computer game Kaktus., Comment: 19 pages, 5 figures

Some roaming users need services to manipulate autonomous processes. Trading agents running on agent trade servers are used as a case in point. We present a solution that provides the agent owners with means to upkeeping their desktop environment, and maintaining their agent trade server processes, via a briefcase service., Comment: 5 pages, 1 figure

On markets with receding prices, artificial noise traders may consider alternatives to buy-and-hold. By simulating variations of the Parrondo strategy, using real data from the Swedish stock market, we produce first indications of a buy-low-sell-random Parrondo variation outperforming buy-and-hold. Subject to our assumptions, buy-low-sell-random also outperforms the traditional value and trend investor strategies. We measure the success of the Parrondo variations not only through their performance compared to other kinds of strategies, but also relative to varying levels of perfect information, received through messages within a multi-agent system of artificial traders., Comment: 10 pages, 4 figures

New services based on the best-effort paradigm could complement the current deterministic services of an electronic financial exchange. Four crucial aspects of such systems would benefit from a hybrid stance: proper use of processing resources, bandwidth management, fault tolerance, and exception handling. We argue that a more refined view on Quality-of-Service control for exchange systems, in which the principal ambition of upholding a fair and orderly marketplace is left uncompromised, would benefit all interested parties., Comment: 11 pages, 1 figure

We investigate convergence of the density matrix renormalization group (DMRG) in the thermodynamic limit for gapless systems. Although the DMRG correlations always decay exponentially in the thermodynamic limit, the correlation length at the DMRG fixed-point scales as $\xi \sim m^{1.3}$, where $m$ is the number of kept states, indicating the existence of algebraic order for the exact system. The single-particle excitation spectrum is calculated, using a Bloch-wave ansatz, and we prove that the Bloch-wave ansatz leads to the symmetry $E(k)=E(\pi -k)$ for translationally invariant half-integer spin-systems with local interactions. Finally, we provide a method to compute overlaps between ground states obtained from different DMRG calculations., Comment: 11 pages, RevTex, 5 figures