Search results for "Neural"
showing 10 items of 2783 documents
Information Abstraction from Crises Related Tweets Using Recurrent Neural Network
2016
Social media has become an important open communication medium during crises. The information shared about a crisis in social media is massive, complex, informal and heterogeneous, which makes extracting useful information a difficult task. This paper presents a first step towards an approach for information extraction from large Twitter data. In brief, we propose a Recurrent Neural Network based model for text generation able to produce a unique text capturing the general consensus of a large collection of twitter messages. The generated text is able to capture information about different crises from tens of thousand of tweets summarized only in a 2000 characters text.
A Damage Identification Approach for Offshore Jacket Platforms Using Partial Modal Results and Artificial Neural Networks
2018
This paper presents a damage identification method for offshore jacket platforms using partially measured modal results and based on artificial intelligence neural networks. Damage identification indices are first proposed combining information of six modal results and natural frequencies. Then, finite element models are established, and damages in structural members are assumed by reducing the structural elastic modulus. From the finite element analysis for a training sample, both the damage identification indices and the damages are obtained, and neural networks are trained. These trained networks are further tested and used for damage prediction of structural members. The calculation res…
Topology Inference and Signal Representation Using Dictionary Learning
2019
This paper presents a Joint Graph Learning and Signal Representation algorithm, called JGLSR, for simultaneous topology learning and graph signal representation via a learned over-complete dictionary. The proposed algorithm alternates between three main steps: sparse coding, dictionary learning, and graph topology inference. We introduce the “transformed graph” which can be considered as a projected graph in the transform domain spanned by the dictionary atoms. Simulation results via synthetic and real data show that the proposed approach has a higher performance when compared to the well-known algorithms for joint undirected graph topology inference and signal representation, when there is…
Masonry Compressive Strength Prediction Using Artificial Neural Networks
2019
The masonry is not only included among the oldest building materials, but it is also the most widely used material due to its simple construction and low cost compared to the other modern building materials. Nevertheless, there is not yet a robust quantitative method, available in the literature, which can reliably predict its strength, based on the geometrical and mechanical characteristics of its components. This limitation is due to the highly nonlinear relation between the compressive strength of masonry and the geometrical and mechanical properties of the components of the masonry. In this paper, the application of artificial neural networks for predicting the compressive strength of m…
The Impact of Forced Answering and Reactance on Answering Behavior in Online Surveys
2020
Forced answering (FA) is a frequent answer format in online surveys that forces respondents to answer each question in order to proceed through the questionnaire. The underlying rationale is to decrease the amount of missing data. Despite its popularity, empirical research on the impact of FA on respondents’ answering behavior is scarce and has generated mixed findings. In fact, some quasi-experimental studies showed that FA has detrimental consequences such as increased survey dropout rates and faking behavior. Notably, a theoretical psychological process driving these effects has hitherto not been identified. Therefore, the aim of the present study was twofold: First, we sought to experi…
CORENup: a combination of convolutional and recurrent deep neural networks for nucleosome positioning identification
2020
Abstract Background Nucleosomes wrap the DNA into the nucleus of the Eukaryote cell and regulate its transcription phase. Several studies indicate that nucleosomes are determined by the combined effects of several factors, including DNA sequence organization. Interestingly, the identification of nucleosomes on a genomic scale has been successfully performed by computational methods using DNA sequence as input data. Results In this work, we propose CORENup, a deep learning model for nucleosome identification. CORENup processes a DNA sequence as input using one-hot representation and combines in a parallel fashion a fully convolutional neural network and a recurrent layer. These two parallel …
Single neuron binding properties and the magical number 7
2008
When we observe a scene, we can almost instantly recognize a familiar object or can quickly distinguish among objects differing by apparently minor details. Individual neurons in the medial temporal lobe of humans have been shown to be crucial for the recognition process, and they are selectively activated by different views of known individuals or objects. However, how single neurons could implement such a sparse and explicit code is unknown and almost impossible to investigate experimentally. Hippocampal CA1 pyramidal neurons could be instrumental in this process. Here, in an extensive series of simulations with realistic morphologies and active properties, we demonstrate how n radial (ob…
Dorsal Column Nuclei Neural Signal Features Permit Robust Machine-Learning of Natural Tactile- and Proprioception-Dominated Stimuli
2020
Neural prostheses enable users to effect movement through a variety of actuators by translating brain signals into movement control signals. However, to achieve more natural limb movements from these devices, the restoration of somatosensory feedback is required. We used feature-learnability, a machine-learning approach, to assess signal features for their capacity to enhance decoding performance of neural signals evoked by natural tactile and proprioceptive somatosensory stimuli, recorded from the surface of the dorsal column nuclei (DCN) in urethane-anesthetized rats. The highest performing individual feature, spike amplitude, classified somatosensory DCN signals with 70% accuracy. The hi…
A modeling study suggesting how a reduction in the context-dependent input on CA1 pyramidal neurons could generate schizophrenic behavior.
2011
The neural mechanisms underlying schizophrenic behavior are unknown and very difficult to investigate experimentally, although a few experimental and modeling studies suggested possible causes for some of the typical psychotic symptoms related to this disease. The brain region most involved in these processes seems to be the hippocampus, because of its critical role in establishing memories for objects or events in the context in which they occur. In particular, a hypofunction of the N-methyl-D-aspartate (NMDA) component of the synaptic input on the distal dendrites of CA1 pyramidal neurons has been suggested to play an important role for the emergence of schizophrenic behavior. Modeling st…
Computation of Psycho-Acoustic Annoyance Using Deep Neural Networks
2019
Psycho-acoustic parameters have been extensively used to evaluate the discomfort or pleasure produced by the sounds in our environment. In this context, wireless acoustic sensor networks (WASNs) can be an interesting solution for monitoring subjective annoyance in certain soundscapes, since they can be used to register the evolution of such parameters in time and space. Unfortunately, the calculation of the psycho-acoustic parameters involved in common annoyance models implies a significant computational cost, and makes difficult the acquisition and transmission of these parameters at the nodes. As a result, monitoring psycho-acoustic annoyance becomes an expensive and inefficient task. Thi…