Dataset Information

Resource Usage and Performance Trade-offs for Machine Learning Models in Smart Environments.

ABSTRACT: The application of artificial intelligence enhances the ability of sensor and networking technologies to realize smart systems that sense, monitor and automatically control our everyday environments. Intelligent systems and applications often automate decisions based on the outcome of certain machine learning models. They collaborate at an ever increasing scale, ranging from smart homes and smart factories to smart cities. The best performing machine learning model, its architecture and parameters for a given task are ideally automatically determined through a hyperparameter tuning process. At the same time, edge computing is an emerging distributed computing paradigm that aims to bring computation and data storage closer to the location where they are needed to save network bandwidth or reduce the latency of requests. The challenge we address in this work is that hyperparameter tuning does not take into consideration resource trade-offs when selecting the best model for deployment in smart environments. The most accurate model might be prohibitively expensive to computationally evaluate on a resource constrained node at the edge of the network. We propose a multi-objective optimization solution to find acceptable trade-offs between model accuracy and resource consumption to enable the deployment of machine learning models in resource constrained smart environments. We demonstrate the feasibility of our approach by means of an anomaly detection use case. Additionally, we evaluate the extent that transfer learning techniques can be applied to reduce the amount of training required by reusing previous models, parameters and trade-off points from similar settings.

SUBMITTER: Preuveneers D

PROVIDER: S-EPMC7070423 | biostudies-literature | 2020 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Resource Usage and Performance Trade-offs for Machine Learning Models in Smart Environments.

Preuveneers Davy D Tsingenopoulos Ilias I Joosen Wouter W

Sensors (Basel, Switzerland) 20200220 4

The application of artificial intelligence enhances the ability of sensor and networking technologies to realize smart systems that sense, monitor and automatically control our everyday environments. Intelligent systems and applications often automate decisions based on the outcome of certain machine learning models. They collaborate at an ever increasing scale, ranging from smart homes and smart factories to smart cities. The best performing machine learning model, its architecture and paramete ...[more]

PMID: 32093354

Similar Datasets

Project description:BACKGROUND:Speciation is driven by many different factors. Among those are trade-offs between different ways an organism utilizes resources, and these trade-offs can constrain the manner in which selection can optimize traits. Limited migration among allopatric populations and species interactions can also drive speciation, but here we ask if trade-offs alone are sufficient to drive speciation in the absence of other factors. RESULTS:We present a model to study the effects of trade-offs on specialization and adaptive radiation in asexual organisms based solely on competition for limiting resources, where trade-offs are stronger the greater an organism's ability to utilize resources. In this model resources are perfectly substitutable, and fitness is derived from the consumption of these resources. The model contains no spatial parameters, and is therefore strictly sympatric. We quantify the degree of specialization by the number of ecotypes evolved and the niche breadth of the population, and observe that these are sensitive to resource influx and trade-offs. Resource influx has a strong effect on the degree of specialization, with a clear transition between minimal diversification at high influx and multiple species evolving at low resource influx. At low resource influx the degree of specialization further depends on the strength of the trade-offs, with more ecotypes evolving the stronger trade-offs are. The specialized organisms persist through negative frequency-dependent selection. In addition, by analyzing one of the evolutionary radiations in greater detail we demonstrate that a single mutation alone is not enough to establish a new ecotype, even though phylogenetic reconstruction identifies that mutation as the branching point. Instead, it takes a series of additional mutations to ensure the stable coexistence of the new ecotype in the background of the existing ones. CONCLUSIONS:Trade-offs are sufficient to drive the evolution of specialization in sympatric asexual populations. Without trade-offs to restrain traits, generalists evolve and diversity decreases. The observation that several mutations are required to complete speciation, even when a single mutation creates the new species, highlights the gradual nature of speciation and the importance of phyletic evolution.

Project description:Value-based decision-making involves trading off the cost associated with an action against its expected reward. Research has shown that both physical and mental effort constitute such subjective costs, biasing choices away from effortful actions, and discounting the value of obtained rewards. Facing conflicts between competing action alternatives is considered aversive, as recruiting cognitive control to overcome conflict is effortful. Moreover, engaging control to proactively suppress irrelevant information that could conflict with task-relevant information would presumably also be cognitively costly. Yet, it remains unclear whether the cognitive control demands involved in preventing and resolving conflict also constitute costs in value-based decisions. The present study investigated this question by embedding irrelevant distractors (flanker arrows) within a reversal-learning task, with intermixed free and instructed trials. Results showed that participants learned to adapt their free choices to maximize rewards, but were nevertheless biased to follow the suggestions of irrelevant distractors. Thus, the perceived cost of investing cognitive control to suppress an external suggestion could sometimes trump internal value representations. By adapting computational models of reinforcement learning, we assessed the influence of conflict at both the decision and learning stages. Modelling the decision showed that free choices were more biased when participants were less sure about which action was more rewarding. This supports the hypothesis that the costs linked to conflict management were traded off against expected rewards. During the learning phase, we found that learning rates were reduced in instructed, relative to free, choices. Learning rates were further reduced by conflict between an instruction and subjective action values, whereas learning was not robustly influenced by conflict between one's actions and external distractors. Our results show that the subjective cognitive control costs linked to conflict factor into value-based decision-making, and highlight that different types of conflict may have different effects on learning about action outcomes.

Project description:Network attacks pose a significant challenge for smart grid networks, mainly due to the existence of several multi-directional communication devices coupling consumers to the grid. One of the network attacks that can affect the smart grid is the distributed denial of service (DDoS), where numerous compromised communication devices/nodes of the grid flood the smart grid network with false data and requests, leading to disruptions in smart meters, data servers, and the state estimator, ultimately effecting the services for end-users. Machine learning-based strategies show distinctive benefits in resolving the challenge of securing the network from DDoS attacks. Regardless, a notable hindrance in deploying machine learning-based techniques is the requirement of model retraining whenever new attack classes arise. Practically, disrupting the normal operations of smart grid is really discouraged. To handle this challenge effectively and detect DDoS attacks without major disruptions, we propose the deployment of reconstructive deep learning techniques. A primary benefit of our proposed technique is the minimum disruption during the introduction of a new attack class, even after complete deployment. We trained several deep and shallow reconstructive models to get representations for each attack type separately, and we performed attack detection by class-specific reconstruction error-based classification. Our technique experienced rigid evaluation via multiple experiments using two well-acknowledged standard databases exclusively for DDoS attacks, including their subsets. Later, we performed a comparative estimation of our outcomes against six methods prevalent within the same domain. Our outcomes reveal that our technique attained higher accuracy, and notably eliminates the requirement of a complete model retraining in the event of the introduction of new attack classes. This method will not only boost the security of smart grid networks but also ensure the stability and reliability of normal operations, protecting the critical infrastructure from ever-evolving network attacks. As smart grid is advancing rapidly, our approach proposes a robust and adaptive way to overcome the continuous challenges posed by network attacks.

Dataset Information

Resource Usage and Performance Trade-offs for Machine Learning Models in Smart Environments.

Publications

Resource Usage and Performance Trade-offs for Machine Learning Models in Smart Environments.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets