Search results for "Neural"
showing 10 items of 2783 documents
Researches regarding cutting tool condition monitoring
2017
The paper main purpose is monitoring of tool wear in metal cutting using neural networks due to their ability of learning and adapting their self, based on experiments. Monitoring the cutting process is difficult to perform on-line because of the complexity of tool wear process, which is the most important parameter that defines the tool state at a certain moment. Most of the researches appraise the tool wear by indirect factors such as forces, consumed power, vibrations or the surface quality. In this case, it is important to combine many factors for increasing the accuracy of tool wear prediction and establish the admissible size of wear. For this, paper both the theoretical data obtained…
Learning From Errors: Detecting Cross-Technology Interference in WiFi Networks
2018
In this paper, we show that inter-technology interference can be recognized using commodity WiFi devices by monitoring the statistics of receiver errors. Indeed, while for WiFi standard frames the error probability varies during the frame reception in different frame fields (PHY, MAC headers, and payloads) protected with heterogeneous coding, errors may appear randomly at any point during the time the demodulator is trying to receive an exogenous interfering signal. We thus detect and identify cross-technology interference on off-the-shelf WiFi cards by monitoring the sequence of receiver errors (bad PLCP, bad FCS, invalid headers, etc.) and propose two methods to recognize the source of in…
Superfluid density and quasi-long-range order in the one-dimensional disordered Bose–Hubbard model
2015
We study the equilibrium properties of the one-dimensional disordered Bose-Hubbard model by means of a gauge-adaptive tree tensor network variational method suitable for systems with periodic boundary conditions. We compute the superfluid stiffness and superfluid correlations close to the superfluid to glass transition line, obtaining accurate locations of the critical points. By studying the statistics of the exponent of the power-law decay of the correlation, we determine the boundary between the superfluid region and the Bose glass phase in the regime of strong disorder and in the weakly interacting region, not explored numerically before. In the former case our simulations are in agreem…
Unusual target selectivity of perisomatic inhibitory cells in the hilar region of the rat hippocampus.
2000
Perisomatic inhibitory innervation of all neuron types profoundly affects their firing characteristics and vulnerability. In this study we examined the postsynaptic targets of perisomatic inhibitory cells in the hilar region of the dentate gyrus where the proportion of potential target cells (excitatory mossy cells and inhibitory interneurons) is approximately equal. Both cholecystokinin (CCK)- and parvalbumin-immunoreactive basket cells formed multiple contacts on the somata and proximal dendrites of mossy cells. Unexpectedly, however, perisomatic inhibitory terminals arriving from these cell types largely ignored hilar GABAergic cell populations. Eighty-ninety percent of various GABAergic…
Immunohistochemical analysis of KCNQ2 potassium channels in adult and developing mouse brain
2005
The syndrome of benign familial neonatal convulsions (BFNC) is characterized by seizures starting within the first days of life and disappearing within weeks to months. BFNC is caused by loss-of-function mutations in the potassium channels KCNQ2 and KCNQ3 which can well explain the resulting neuronal hyperexcitability. However, it is not understood why seizures predominantly occur in the neonatal period. A potential explanation might be a change in the expression pattern of these channels during development. We therefore performed an immunohistochemical analysis of mouse brain slices at different stages of postnatal development using an antibody recognizing the C-terminus of the KCNQ2 chann…
Functional correlate and delineated connectivity pattern of human motion aftereffect responses substantiate a subjacent visual-vestibular interaction.
2018
The visual motion aftereffect (MAE) is the most prominent aftereffect in the visual system. Regarding its function, psychophysical studies suggest its function to be a form of sensory error correction, possibly also triggered by incongruent visual-vestibular stimulation. Several observational imaging experiments have deducted an essential role for region MT+ in the perception of a visual MAE but not provided conclusive evidence. Potential confounders with the MAE such as ocular motor performance, attention, and vection sensations have also never been controlled for. Aim of this neuroimaging study was to delineate the neural correlates of MAE and its subjacent functional connectivity pattern…
Motion analysis using the novelty filter
1991
Abstract An original approach to the motion analysis, based on the novelty filter, is proposed. The novelty filter stresses the novelties occurring in a pattern representing an image of the scene under consideration with respect to patterns representing previous images of the same scene, so that visual information about the motion of the objects is obtained. The novelty filter may be implemented by a neural network architecture, taking advantage of the capabilities of massive parallelism, adaptive learning and noise robustness. The novelty filter may learn the entire trajectory of an object, through an incremental learning of a sequence of images capturing the scene, thus emphasizing if the…
Using deep neural networks for kinematic analysis: Challenges and opportunities
2020
Kinematic analysis is often performed in a lab using optical cameras combined with reflective markers.\ud With the advent of artificial intelligence techniques such as deep neural networks, it is now possible\ud to perform such analyses without markers, making outdoor applications feasible. In this paper I summarise\ud 2D markerless approaches for estimating joint angles, highlighting their strengths and limitations.\ud In computer science, so-called ‘‘pose estimation” algorithms have existed for many years. These methods\ud involve training a neural network to detect features (e.g. anatomical landmarks) using a process called\ud supervised learning, which requires ‘‘training” images to be …
Translational Model of Cortical Premotor-Motor Networks.
2021
Abstract Deciphering the physiological patterns of motor network connectivity is a prerequisite to elucidate aberrant oscillatory transformations and elaborate robust translational models of movement disorders. In the proposed translational approach, we studied the connectivity between premotor (PMC) and primary motor cortex (M1) by recording high-density electroencephalography in humans and between caudal (CFA) and rostral forelimb (RFA) areas by recording multi-site extracellular activity in mice to obtain spectral power, functional and effective connectivity. We identified a significantly higher spectral power in β- and γ-bands in M1compared to PMC and similarly in mice CFA layers (L) 2/…
The Random Neural Network Model for the On-line Multicast Problem
2005
In this paper we propose the adoption of the Random Neural Network Model for the solution of the dynamic version of the Steiner Tree Problem in Networks (SPN). The Random Neural Network (RNN) is adopted as a heuristic capable of improving solutions achieved by previously proposed dynamic algorithms. We adapt the RNN model in order to map the network characteristics during a multicast transmission. The proposed methodology is validated by means of extensive experiments.