Search results for "Neural Networks"
showing 10 items of 599 documents
OH-related Infrared Absorption Bands in Oxide Glasses
2005
We report the infrared activity, in the spectral region of the OH stretching modes, of different composite silicate glasses whose chemical composition is established by X-ray fluorescence measurements. The analysis of the absorption line profiles is made in terms of different spectral contributions, Gaussian in shape. The comparison with analogous spectra obtained in vitreous silica samples with impurity concentrations < 100 part per million moles is evidence of the effects of the different oxides on the vibrational properties of the OH groups. In particular, for oxide glasses a red shift of the composite band at about 3670 cm(-1), assigned to the OH stretching modes of free Si-OH groups an…
Dropping out of school as a meaningful action for adolescents with social, emotional and behavioural difficulties
2013
This study examines and discusses dropping out of school related to adolescents with social, emotional and behavioural difficulties (SEBD). It is based on in-depth interviews of 10 adolescents between the ages of 16 and 20, three girls and two boys with internalised problems, and two girls and three boys with extroverted behavioural problems. Given this group of students' challenges at school, the aim of this paper is to explore the narratives of this adolescent group as they relate to the significance they attach to their dropout behaviour. An additional objective is to draw attention to what these findings are likely to mean for implementing preventive practices in school. Results show th…
A New Adaptive Neural Harmonic Compensator for Inverter Fed Distributed Generation
2004
This paper deals with the command of inverters in DG (distributed generation) systems by use of linear neural networks in such a way that, with a slight upgrade of their control software, they can be used also to compensate for the harmonic distortion in the node where they are connected (local compensation), that is in the in the point of common coupling (PCC). To this purpose a neural estimator based on linear neurons (ADALINEs) has been developed which is able to act as a selective noise cancellers for each harmonic of the node voltage. The use of linear neurons permits the drawbacks of classical neural networks to be overcome and moreover the neural estimator is easy to implement, thus …
Is the nonREM–REM sleep cycle reset by forced awakenings from REM sleep?
2002
In selective REM sleep deprivation (SRSD), the occurrence of stage REM is repeatedly interrupted by short awakenings. Typically, the interventions aggregate in clusters resembling the REM episodes in undisturbed sleep. This salient phenomenon can easily be explained if the nonREM–REM sleep process is continued during the periods of forced wakefulness. However, earlier studies have alternatively suggested that awakenings from sleep might rather discontinue and reset the ultradian process. Theoretically, the two explanations predict a different distribution of REM episode duration. We evaluated 117 SRSD treatment nights recorded from 14 depressive inpatients receiving low dosages of Trimipram…
Dosage individualization of erythropoietin using a profile-dependent support vector regression
2003
The external administration of recombinant human erythropoietin is the chosen treatment for those patients with secondary anemia due to chronic renal failure in periodic hemodialysis. The objective of this paper is to carry out an individualized prediction of the EPO dosage to be administered to those patients. The high cost of this medication, its side-effects and the phenomenon of potential resistance which some individuals suffer all justify the need for a model which is capable of optimizing dosage individualization. A group of 110 patients and several patient factors were used to develop the models. The support vector regressor (SVR) is benchmarked with the classical multilayer percept…
Factors associated with non-participation and dropout among cancer patients in a cluster-randomised controlled trial
2017
We investigated the impact of demographic and disease related factors on non-participation and dropout in a cluster-randomised behavioural trial in cancer patients with measurements taken between hospitalisation and 6 months thereafter. The percentages of non-participation and dropout were documented at each time point. Factors considered to be potentially related with non-participation and dropout were as follows: age, sex, marital status, education, income, employment status, tumour site and stage of disease. Of 1,338 eligible patients, 24% declined participation at baseline. Non-participation was higher in older patients (Odds Ratio [OR] 2.1, CI: 0.6-0.9) and those with advanced disease …
A deep learning framework for automatic diagnosis of unipolar depression.
2019
Abstract Background and purpose In recent years, the development of machine learning (ML) frameworks for automatic diagnosis of unipolar depression has escalated to a next level of deep learning frameworks. However, this idea needs further validation. Therefore, this paper has proposed an electroencephalographic (EEG)-based deep learning framework that automatically discriminated depressed and healthy controls and provided the diagnosis. Basic procedures In this paper, two different deep learning architectures were proposed that utilized one dimensional convolutional neural network (1DCNN) and 1DCNN with long short-term memory (LSTM) architecture. The proposed deep learning architectures au…
Dropout from Court-Mandated Intervention Programs for Intimate Partner Violence Offenders: The Relevance of Alcohol Misuse and Cognitive Impairments
2019
There is considerable interest in offering insight into the mechanisms that might explain why certain perpetrators of intimate partner violence against women (IPVAW) drop out of interventions. Although several socio-demographic variables and attitudes towards IPVAW have been proposed as risk factors for IPVAW perpetrators&rsquo
Neural net classification of REM sleep based on spectral measures as compared to nonlinear measures
2001
In various studies the implementation of nonlinear and nonconventional measures has significantly improved EEG (electroencephalogram) analyses as compared to using conventional parameters alone. A neural network algorithm well approved in our laboratory for the automatic recognition of rapid eye movement (REM) sleep was investigated in this regard. Originally based on a broad range of spectral power inputs, we additionally supplied the nonlinear measures of the largest Lyapunov exponent and correlation dimension as well as the nonconventional stochastic measures of spectral entropy and entropy of amplitudes. No improvement in the detection of REM sleep could be achieved by the inclusion of …
Individuality of movements in music--finger and body movements during playing of the flute.
2013
The achievement of mastery in playing a composition by means of a musical instrument typically requires numerous repetitions and corrections according to the keys and notations of the music piece. Nevertheless, differences in the interpretation of the same music piece by highly skilled musicians seem to be recognizable. The present study investigated differences within and between skilled flute players in their finger and body movements playing the same piece several times on the same and on different days. Six semiprofessional and four professional musicians played an excerpt of Mozart’s Flute Concerto No. 2 several times on three different days. Finger and body movements were recorded by …