Search results for "Machine"
showing 10 items of 2592 documents
Visual dynamic environment for distributed systems
2002
Algorithms, based on information fusion, are often embodied in visual perception systems. Distributed architectures have been recently proposed to perform integrated computation. The complexity of distributed systems regards both their design, and the software environment to develop applications. Visual and iconic programming style intends to provide expressive tools to implement, to debug, and to execute programs in distributed environment. Multi-layers graphs languages seem suitable to handle such complexity. This paper describes the design of a visual dynamic environment (VDE), which is based on a graph-grammar. A new class of dynamic visual interfaces is also introduced, and its propert…
Visualizations for Decision Support in Scenario-based Multiobjective Optimization
2021
Reproducibility artifacts for: Babooshka Shavazipour, Manuel López-Ibáñez, and Kaisa Miettinen. Visualizations for Decision Support in Scenario-based Multiobjective Optimization. Information Sciences, 2021. doi:10.1016/j.ins.2021.07.025. Abstract: We address challenges of decision problems when managers need to optimize several conflicting objectives simultaneously under uncertainty. We propose visualization tools to support the solution of such scenario-based multiobjective optimization problems. Suitable graphical visualizations are necessary to support managers in understanding, evaluating, and comparing the performances of management decisions according to all objec…
Improving Classification of Tweets Using Linguistic Information from a Large External Corpus
2016
The bag of words representation of documents is often unsatisfactory as it ignores relationships between important terms that do not co-occur literally. Improvements might be achieved by expanding the vocabulary with other relevant word, like synonyms.
What Conclusions does Rapid Image Classification by Eye Movements Provide for Machine Vision?
2008
Human ability to rapidly classify images of natural objects has been a matter of study for more than a decade. Recently eye movements have been exploited as a behavioural response, which has lead to alternative hypotheses of natural image processing. In this research, twelve volunteers made a movement towards a briefly displayed digital image if it was an animal, and a movement away otherwise. In both cases, the average response time was more than 400 milliseconds.
Practical Volcano-Independent Recognition of Seismic Events: VULCAN.ears Project
2021
Recognizing the mechanisms underlying seismic activity and tracking temporal and spatial patterns of earthquakes represent primary inputs to monitor active volcanoes and forecast eruptions. To quantify this seismicity, catalogs are established to summarize the history of the observed types and number of volcano-seismic events. In volcano observatories the detection and posterior classification or labeling of the events is manually performed by technicians, often suffering a lack of unified criteria and eventually resulting in poorly reliable labeled databases. State-of-the-art automatic Volcano-Seismic Recognition (VSR) systems allow real-time monitoring and consistent catalogs. VSR systems…
One size hardly fits all
2013
This paper casts recent accomplishments in the field of Wireless MAC programmability into the emerging Software Defined Networking perspective. We argue that an abstract (but formal) description of the MAC protocol logic in terms of extensible finite state machines appears a convenient and viable data-plane programming compromise for modeling and deploying realistic MAC protocol logics. Our approach is shown to comply with existing control frameworks, and entails the ability to dynamically change the MAC protocol operation based on context and scenario conditions; in essence, move from the traditional idea of "one-size-fits-all" MAC protocol stack to the innovative paradigm of opportunistic…
ELM Regularized Method for Classification Problems
2016
Extreme Learning Machine (ELM) is a recently proposed algorithm, efficient and fast for learning the parameters of single layer neural structures. One of the main problems of this algorithm is to choose the optimal architecture for a given problem solution. To solve this limitation several solutions have been proposed in the literature, including the regularization of the structure. However, to the best of our knowledge, there are no works where such adjustment is applied to classification problems in the presence of a non-linearity in the output; all published works tackle modelling or regression problems. Our proposal has been applied to a series of standard databases for the evaluation o…
Numerical and experimental investigation of a cross-flow water turbine
2016
ABSTRACTA numerical and experimental study was carried out for validation of a previously proposed design criterion for a cross-flow turbine and a new semi-empirical formula linking inlet velocity to inlet pressure. An experimental test stand was designed to conduct a series of experiments and to measure the efficiency of the turbine designed based on the proposed criterion. The experimental efficiency was compared to that from numerical simulations performed using a RANS model with a shear stress transport (SST) turbulence closure. The proposed semi-empirical velocity formula was also validated against the numerical solutions for cross-flow turbines with different geometries and boundary c…
Comparison of machine learning models for gully erosion susceptibility mapping
2020
© 2019 China University of Geosciences (Beijing) and Peking University Gully erosion is a disruptive phenomenon which extensively affects the Iranian territory, especially in the Northern provinces. A number of studies have been recently undertaken to study this process and to predict it over space and ultimately, in a broader national effort, to limit its negative effects on local communities. We focused on the Bastam watershed where 9.3% of its surface is currently affected by gullying. Machine learning algorithms are currently under the magnifying glass across the geomorphological community for their high predictive ability. However, unlike the bivariate statistical models, their structu…
Guidelines proposal for a good and durable WEC design
2017
In this paper, preliminarily a proposal for design guidelines for a “good” design of wave energy converter is presented and successively a small scale prototype of a wave energy converter including the buoyant electrical generator, the power electronics equipment and a sea water electrolyzer is designed on the basis of these guidelines and presented.