Search results for "NETWORKS"
showing 10 items of 3260 documents
A Novel Systolic Parallel Hardware Architecture for the FPGA Acceleration of Feedforward Neural Networks
2019
New chips for machine learning applications appear, they are tuned for a specific topology, being efficient by using highly parallel designs at the cost of high power or large complex devices. However, the computational demands of deep neural networks require flexible and efficient hardware architectures able to fit different applications, neural network types, number of inputs, outputs, layers, and units in each layer, making the migration from software to hardware easy. This paper describes novel hardware implementing any feedforward neural network (FFNN): multilayer perceptron, autoencoder, and logistic regression. The architecture admits an arbitrary input and output number, units in la…
Modeling of Hardy-Weinberg Equilibrium Using Dynamic Random Networks in an ABM Framework
2023
Hardy-Weinberg equilibrium is the fundamental principle of population genetics. In this article, we present a new NetLogo model called “Hardy-Weinberg Basic model v 2.0”, characterized by a strict adherence to the original assumptions made by Hardy and Weinberg in 1908. A particularly significant feature of this model is that the algorithm does not make use of the binomial expansion formula. Instead, we show that using a procedure based on dynamic random networks, diploid equilibrium can be achieved spontaneously by a population of agents reproducing sexually in a Mendelian fashion. The model can be used to conduct simulations with a wide range of initial population sizes and genotype distr…
Prevention of hate speech crimes: digital versus real-life environment
2022
Extending the use of social media and other digital networks, as well as technology development and the impact of the pandemic have raised the problem of how to prevent hateful speech from occurring. Limitations on hate speech closely correlate with restriction of freedom of speech, therefore balance between the two should be met to ensure both fundamental democratic right on the freedom of speech, as well as to restrict limitations on one’s honour, dignity and safety. To answer whether mechanisms for combating the crimes of hate speech in the digital environment are as effective as they are in a real-life situation, the author analyses the international (United Nations) and Council of Euro…
A Spatio-temporal Probabilistic Model of Hazard and Crowd Dynamics in Disasters for Evacuation Planning
2013
Published version of a chapter in the book: Recent Trends in Applied Artificial Intelligence. Also available from the publisher at: http://dx.doi.org/10.1007/978-3-642-38577-3_7 Managing the uncertainties that arise in disasters – such as ship fire – can be extremely challenging. Previous work has typically focused either on modeling crowd behavior or hazard dynamics, targeting fully known environments. However, when a disaster strikes, uncertainty about the nature, extent and further development of the hazard is the rule rather than the exception. Additionally, crowd and hazard dynamics are both intertwined and uncertain, making evacuation planning extremely difficult. To address this chal…
Acceptance of Online Health Services for Self-Help in the Context of Mental Health : Understanding Young Adults Experiences
2018
This paper explores the understanding of the acceptance of online health services from a selfhelp perspective in the context of mental health. By examining the experiences of young adults, this paper develops a framework to leverage the current understanding of the factors that would support the acceptance and use of these types of services. To this end, a multidisciplinary perspective incorporating knowledge from the service marketing, health, and information systems literature is used. The results suggest that the production of online services that are meant for self-help purposes necessitates a focus on the acceptance of technology and, more importantly, instrumental value creation, as t…
Individual Differences in Dispositional Mindfulness Predict Attentional Networks and Vigilance Performance
2022
Acknowledgements The authors wish to thank Tao Coll-Martín, Fernando G. Luna, and Miguel A. Vadillo for the kind and helpful input provided during the development of this research project.
Communities of Communication: Making Sense of the “Social” in Social Media
2012
As social media usage permeates people's lives, an increasing portion of their daily behavior leaves digital traces to be used by researchers. Social scientists can hope to gain new insight into the previously hidden but digitally recorded aspects of our digital social lives. Beyond aggregate and individual-level studies of user behavior, the digital traces also enable scientific examination of the structure of social interaction through networks. At the same time, the large scale and networked nature of social media data pose a new set of challenges to be overcome through the development of sound methodologies. We take stock of current methodological promises and challenges in social media…
Remote ECG Monitoring by ECG247 Smart Heart Sensor
2022
Background. Heart rhythm disorders are common and may be associated with serious complications. The quality of the ECG signal is crucial to detect and classify arrhythmias. Most available devices for assessment arrhythmias do not allow for remote monitoring. The Norwegian ECG247 Smart Heart Sensor is a new remote patch monitor developed to simplify the assessment of arrhythmias. This study was aimed at evaluating the quality of the ECG signal from the ECG247 Smart Heart Sensor compared to standard 12-lead ECG. Methods. ECG recordings with ECG247 Smart Heart Sensor and a standard 12-lead ECG recorder were performed in 97 volunteers at Sorlandet Hospital, Arendal, Norway, in 2019. All ECGs we…
Hadron therapy information sharing prototype
2013
The European PARTNER project developed a prototypical system for sharing hadron therapy data. This system allows doctors and patients to record and report treatment-related events during and after hadron therapy. It presents doctors and statisticians with an integrated view of adverse events across institutions, using open-source components for data federation, semantics, and analysis. There is a particular emphasis upon semantic consistency, achieved through intelligent, annotated form designs. The system as presented is ready for use in a clinical setting, and amenable to further customization. The essential contribution of the work reported here lies in the novel data integration and rep…
Translating the Role of mTOR- and RAS-Associated Signalopathies in Autism Spectrum Disorder: Models, Mechanisms and Treatment
2021
Mutations affecting mTOR or RAS signaling underlie defined syndromes (the so-called mTORopathies and RASopathies) with high risk for Autism Spectrum Disorder (ASD). These syndromes show a broad variety of somatic phenotypes including cancers, skin abnormalities, heart disease and facial dysmorphisms. Less well studied are the neuropsychiatric symptoms such as ASD. Here, we assess the relevance of these signalopathies in ASD reviewing genetic, human cell model, rodent studies and clinical trials. We conclude that signalopathies have an increased liability for ASD and that, in particular, ASD individuals with dysmorphic features and intellectual disability (ID) have a higher chance for disrup…