Ändra sökning
Avgränsa sökresultatet
1 - 8 av 8
RefereraExporteraLänk till träfflistan
Permanent länk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • apa.csl
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Träffar per sida
  • 5
  • 10
  • 20
  • 50
  • 100
  • 250
Sortering
  • Standard (Relevans)
  • Författare A-Ö
  • Författare Ö-A
  • Titel A-Ö
  • Titel Ö-A
  • Publikationstyp A-Ö
  • Publikationstyp Ö-A
  • Äldst först
  • Nyast först
  • Skapad (Äldst först)
  • Skapad (Nyast först)
  • Senast uppdaterad (Äldst först)
  • Senast uppdaterad (Nyast först)
  • Disputationsdatum (tidigaste först)
  • Disputationsdatum (senaste först)
  • Standard (Relevans)
  • Författare A-Ö
  • Författare Ö-A
  • Titel A-Ö
  • Titel Ö-A
  • Publikationstyp A-Ö
  • Publikationstyp Ö-A
  • Äldst först
  • Nyast först
  • Skapad (Äldst först)
  • Skapad (Nyast först)
  • Senast uppdaterad (Äldst först)
  • Senast uppdaterad (Nyast först)
  • Disputationsdatum (tidigaste först)
  • Disputationsdatum (senaste först)
Markera
Maxantalet träffar du kan exportera från sökgränssnittet är 250. Vid större uttag använd dig av utsökningar.
  • 1.
    Afifi, Haitham
    et al.
    Hasso Platter Institute, Germany.
    Ramaswamy, Arunselvan
    Karlstads universitet, Fakulteten för hälsa, natur- och teknikvetenskap (from 2013), Institutionen för matematik och datavetenskap (from 2013).
    Karl, Holger
    Hasso Platter Institute, Germany.
    Reinforcement learning for autonomous vehicle movements in wireless multimedia applications2023Ingår i: Pervasive and Mobile Computing, ISSN 1574-1192, E-ISSN 1873-1589, Vol. 92, artikel-id 101799Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    We develop a Deep Reinforcement Learning (DeepRL)-based, multi-agent algorithm to efficiently control autonomous vehicles that are typically used within the context of Wireless Sensor Networks (WSNs), in order to boost application performance. As an application example, we consider wireless acoustic sensor networks where a group of speakers move inside a room. In a traditional setup, microphones cannot move autonomously and are, e.g., located at fixed positions. We claim that autonomously moving microphones improve the application performance. To control these movements, we compare simple greedy heuristics against a DeepRL solution and show that the latter achieves best application performance. As the range of audio applications is broad and each has its own (subjective) per-formance metric, we replace those application metrics by two immediately observable ones: First, quality of information (QoI), which is used to measure the quality of sensed data (e.g., audio signal strength). Second, quality of service (QoS), which is used to measure the network's performance when forwarding data (e.g., delay). In this context, we propose two multi-agent solutions (where one agent controls one microphone) and show that they perform similarly to a single-agent solution (where one agent controls all microphones and has a global knowledge). Moreover, we show via simulations and theoretical analysis how other parameters such as the number of microphones and their speed impacts performance.

  • 2.
    Khalid, Hifza
    et al.
    Tufts University, United States.
    Ramaswamy, Arunselvan
    Karlstads universitet, Fakulteten för hälsa, natur- och teknikvetenskap (from 2013), Institutionen för matematik och datavetenskap (from 2013).
    Ferlin, Simone
    Karlstads universitet, Fakulteten för hälsa, natur- och teknikvetenskap (from 2013), Institutionen för matematik och datavetenskap (from 2013). Red Hat.
    Couch, Alva
    Tufts University, United States.
    Modeling Batch Tasks Using Recurrent Neural Networks in Co-Located Alibaba Workloads2024Ingår i: / [ed] Modesto Castrillon-Santana; Maria De Marsico; Ana Fred, SciTePress, 2024, Vol. 1, s. 558-569Konferensbidrag (Refereegranskat)
    Abstract [en]

    Accurate predictive models for cloud workloads can be helpful in improving task scheduling, capacity planning and preemptive resource conflict resolution, especially in the setting of co-located jobs. Alibaba, one of the leading cloud providers co-locates transient batch tasks and high priority latency sensitive online jobs on the same cluster. In this paper, we consider the problem of using a publicly released dataset by Alibaba to model the batch tasks that are often overlooked compared to online services. The dataset contains the arrivals and resource requirements (CPU, memory, etc.) for both batch and online tasks. Our trained model predicts, with high accuracy, the number of batch tasks that arrive in any 30 minute window, their associated CPU and memory requirements, and their lifetimes. It captures over 94% of arrivals in each 30 minute window within a 95% prediction interval. The F1 scores for the most frequent CPU classes exceed 75%, and our memory and lifetime predictions incur less than 1% test data loss. The prediction accuracy of the lifetime of a batch-task drops when the model uses both CPU and memory information, as opposed to only using memory information. 

  • 3.
    Mahjoubi, Ayeh
    et al.
    Karlstads universitet, Fakulteten för hälsa, natur- och teknikvetenskap (from 2013), Institutionen för matematik och datavetenskap (from 2013).
    Ramaswamy, Arunselvan
    Karlstads universitet, Fakulteten för hälsa, natur- och teknikvetenskap (from 2013), Institutionen för matematik och datavetenskap (from 2013).
    Grinnemo, Karl-Johan
    Karlstads universitet, Fakulteten för hälsa, natur- och teknikvetenskap (from 2013), Institutionen för matematik och datavetenskap (from 2013).
    An Online Simulated Annealing-based Task Offloading Strategy for a Mobile Edge Architecture2024Ingår i: IEEE Access, E-ISSN 2169-3536, Vol. 12, s. 70707-70718Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    This paper presents a novel online task scheduling strategy called SATS, designed for a hierarchical Mobile Edge Computing (MEC) architecture. SATS utilizes a Simulated Annealing-based method for scheduling tasks and demonstrates that Simulated Annealing can be a viable solution for online task scheduling, not just for offline task scheduling. However, the paper also emphasizes that the effectiveness of SATS depends on the precision of service request predictions. The paper evaluates three types of predictors: neutral, conservative, and optimistic. It concludes that when using a conservative predictor that overestimates the number of service requests, SATS performs the best in terms of higher acceptance rates and shorter processing times. In fact, when using a conservative predictor, SATS can offer an acceptance ratio that is only 5% lower than what it could have been if SATS had known the frequency of service request arrivals beforehand and deviates less than 20% from this acceptance ratio in all conducted experiments.

    Ladda ner fulltext (pdf)
    fulltext
  • 4.
    Nammouchi, Amal
    et al.
    Karlstads universitet, Fakulteten för hälsa, natur- och teknikvetenskap (from 2013), Institutionen för matematik och datavetenskap (from 2013).
    Cuadrado, Nicolas
    Mohamed bin Zayed University of Artificial Intelligence, the United Arab Emirates.
    Ramaswamy, Arunselvan
    Karlstads universitet, Fakulteten för hälsa, natur- och teknikvetenskap (from 2013), Institutionen för matematik och datavetenskap (from 2013).
    Kassler, Andreas
    Karlstads universitet, Fakulteten för hälsa, natur- och teknikvetenskap (from 2013), Institutionen för matematik och datavetenskap (from 2013).
    Multi-Objective Microgrid Control Using Deep Reinforcement Learning2024Rapport (Övrigt vetenskapligt)
    Abstract [en]

    Optimizing renewable energy usage in smart microgrids that contain photovoltaic production and battery storage is important due to the potential to reduce overall CO2 emissions and thus lead to more environmental friendly energy systems. However, due to the complex nature of energy management in smart grids and the volatile nature of energy production from PV systems, the problem is complex to solve. In this work we aim to optimize the energy in a microgrid comprising six houses using a digital twin based approach based on Deep Reinforcement Learning. We develop a Soft Actor-Critic (SAC) agent to address this intricate challenge, with the aim to simultaneously reduce emissions, maintain user comfort, while maximizing grid efficiency and resiliency to cope with spurious grid outages. We propose and evaluate different reward functions that guide the agent in finding its optimal policy.. Furthermore, we discuss the implications of our results and outline potential future steps, envisioning ongoing refinement and advancements in our pursuit of optimal solutions for the complex interplay of severaal objectives in microgrid management.

  • 5.
    Ramaswamy, Arunselvan
    Karlstads universitet, Fakulteten för hälsa, natur- och teknikvetenskap (from 2013), Institutionen för matematik och datavetenskap (from 2013).
    Gradient Clipping in Deep Learning: A Dynamical Systems Perspective2023Ingår i: Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - ICPRAM, SciTePress, 2023, Vol. 1, s. 107-114Konferensbidrag (Refereegranskat)
    Abstract [en]

    Neural networks are ubiquitous components of Machine Learning (ML) algorithms. However, training them is challenging due to problems associated with exploding and vanishing loss-gradients. Gradient clipping is shown to effectively combat both the vanishing gradients and the exploding gradients problems. As the name suggests, gradients are clipped in order to prevent large updates. At the same time, very small neural network weights are updated using larger step-sizes. Although widely used in practice, there is very little theory surrounding clipping. In this paper, we analyze two popular gradient clipping techniques-the classic norm-based gradient clipping method and the adaptive gradient clipping technique. We prove that gradient clipping ensures numerical stability with very high probability. Further, clipping based stochastic gradient descent converges to a set of neural network weights that minimizes the average scaled training loss in a local sense. The averaging is with respect to the distribution that generated the training data. The scaling is a consequence of gradient clipping. We use tools from the theory of dynamical systems for the presented analysis. 

    Ladda ner fulltext (pdf)
    fulltext
  • 6.
    Ramaswamy, Arunselvan
    et al.
    Karlstads universitet, Fakulteten för hälsa, natur- och teknikvetenskap (from 2013), Institutionen för matematik och datavetenskap (from 2013).
    Ma, Yunpeng
    Karlstads universitet, Fakulteten för hälsa, natur- och teknikvetenskap (from 2013), Institutionen för matematik och datavetenskap (from 2013).
    Alfredsson, Stefan
    Karlstads universitet, Fakulteten för hälsa, natur- och teknikvetenskap (from 2013), Institutionen för matematik och datavetenskap (from 2013).
    Collyer, Fran
    University of Wollongong, Australia.
    Brunstrom, Anna
    Karlstads universitet, Fakulteten för hälsa, natur- och teknikvetenskap (from 2013), Institutionen för matematik och datavetenskap (from 2013).
    Information Theoretic Deductions Using Machine Learning with an Application in Sociology2024Ingår i: Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods ICPRAM / [ed] Modesto Castrillon-Santana; Maria De Marsico; Ana Fred, SciTePress, 2024, Vol. 1, s. 320-328Konferensbidrag (Refereegranskat)
    Abstract [en]

    Conditional entropy is an important concept that naturally arises in fields such as finance, sociology, and intelligent decision making when solving problems involving statistical inferences. Formally speaking, given two random variables X and Y, one is interested in the amount and direction of information flow between X and Y . It helps to draw conclusions about Y while only observing X. Conditional entropy H(Y |X) quantifies the amount of information flow from X to Y . In practice, calculating H(Y |X) exactly is infeasible. Current estimation methods are complex and suffer from estimation bias issues. In this paper, we present a simple Machine Learning based estimation method. Our method can be used to estimate H(Y |X) for discrete X and bi-valued Y. Given X and Y observations, we first construct a natural binary classification training dataset. We then train a supervised learning algorithm on this dataset, and use its prediction accuracy to estimate H(Y |X). We also present a simple condition on the prediction accuracy to determine if there is information flow from X to Y. We support our ideas using formal arguments and through an experiment involving a gender-bias study using a part of the employee database of Karlstad University, Sweden. 

  • 7.
    Redder, Adrian
    et al.
    Paderborn University, Germany.
    Ramaswamy, Arunselvan
    Karlstads universitet, Fakulteten för hälsa, natur- och teknikvetenskap (from 2013), Institutionen för matematik och datavetenskap (from 2013).
    Karl, Hogler
    Potsdam University, Germany.
    Age of Information Process under Strongly Mixing Communication - Moment Bound, Mixing Rate and Strong Law2022Konferensbidrag (Refereegranskat)
    Abstract [en]

    The decentralized nature of multi-agent systems requires continuous data exchange to achieve global objectives. In such scenarios, Age of Information (AoI) has become an important metric of the freshness of exchanged data due to the error-proneness and delays of communication systems. Communication systems usually possess dependencies: the process describing the success or failure of communication is highly correlated when these attempts are ’close’ in some domain (e.g. in time, frequency, space or code as in wireless communication) and is, in general, non-stationary. To study AoI in such scenarios, we consider an abstract event-based AoI process Delta (n), expressing time since the last update: If, at time n, a monitoring node receives a status update from a source node (event A(n-1) occurs), then Delta (n) is reset to one; otherwise, Delta (n) grows linearly in time. This A oI process can thus be viewed as a special random walk with resets. The event process A(n) may be non-stationary and we merely assume that its temporal dependencies decay sufficiently, described by alpha -mixing. We calculate moment bounds for the resulting A oI process as a function of the mixing rate of A(n). Furthermore, we prove that the A oI process Delta (n) is itself alpha -mixing from which we conclude a strong law of large numbers for Delta (n). This opens up future work on renewal processes with non-independent interarrival times. 

  • 8.
    Redder, Adrian
    et al.
    Paderborn University, Germany.
    Ramaswamy, Arunselvan
    Karlstads universitet, Fakulteten för hälsa, natur- och teknikvetenskap (from 2013), Institutionen för matematik och datavetenskap (from 2013).
    Karl, Holger
    Potsdam University, Germany.
    Practical Network Conditions for the Convergence of Distributed Optimization2022Ingår i: IFAC-PapersOnLine, E-ISSN 2405-8963, Vol. 55, nr 13, s. 133-138Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    The decentralized nature of multi-Agent learning often requires continuous information exchange over a (wireless) communication network, in order to accomplish common global objectives. Uncertainty and delay in communication induce large Age of Information (AoI) for data available at the agents, possibly affecting algorithm performance. In order to understand this, one needs communication models that are representative of practical wireless networks. In this paper, we present a representative model based on the Signal-To-Interference-plus-Noise Ratio (SINR) between pairs of agents. Further, we present a novel medium access control (MAC) protocol that is sensitive to local AoI. Our SINR model facilitates the representation of practical dependency effects like shadowing, fading, interference and external noise. The model is driven by an underlying geometrically ergodic Markov chain, which can represent agent mobility. Our MAC protocol enables that the aforementioned dependency effects decay over time. With this dependency decay, we then control the asymptotic growth of the AoI, to facilitate the convergence of distributed algorithms. Finally, we illustrate our ideas by analyzing the distributed stochastic gradient descent scheme that uses delayed communicated data. 

    Ladda ner fulltext (pdf)
    fulltext
1 - 8 av 8
RefereraExporteraLänk till träfflistan
Permanent länk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • apa.csl
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf