Many preterm infants suffer from neural disorders caused by early birth complications. The detection of children with neurological risk is an important challenge. The electroencephalogram is an important technique for...Many preterm infants suffer from neural disorders caused by early birth complications. The detection of children with neurological risk is an important challenge. The electroencephalogram is an important technique for establishing long-term neurological prognosis. Within this scope, the goal of this study is to propose an automatic detection of abnormal preterm babies’ electroencephalograms (EEG). A corpus of 316 neonatal EEG recordings of 100 infants born after less than 35 weeks of gestation were preprocessed and a time series of standard deviation was computed. This time series was thresholded to detect Inter Burst Intervals (IBI). Temporal features were extracted from bursts and IBI. Feature selection was carried out with classification in one step so as to select the best combination of features in terms of classification performance. Two classifiers were tested: Multiple Linear Regressions and Support Vector Machines (SVM). Performance was computed using cross validations. Methods were validated on a corpus of 100 infants with no serious brain damage. The Multiple Linear Regression method shows the best results with a sensitivity of 86.11% ± 10.01%, a specificity of 77.44% ± 7.62% and an AUC (Area under the ROC curves) of 0.82 ± 0.04. An accurate detection of abnormal EEG for preterm infants is feasible. This study is a first step towards an automatic analysis of the premature brain, making it possible to lighten the physician’s workload in the future.展开更多
Developing a reliable weather forecasting model is a complicated task, as it requires heavy IT resources as well as heavy investments beyond the financial capabilities of most countries. In Lebanon, the prediction mod...Developing a reliable weather forecasting model is a complicated task, as it requires heavy IT resources as well as heavy investments beyond the financial capabilities of most countries. In Lebanon, the prediction model used by the civil aviation weather service at Rafic Hariri International Airport in Beirut (BRHIA) is the ARPEGE model, (0.5) developed by the weather service in France. Unfortunately, forecasts provided by ARPEGE have been erroneous and biased by several factors such as the chaotic character of the physical modeling equations of some atmospheric phenomena (advection, convection, etc.) and the nature of the Lebanese topography. In this paper, we proposed the time series method ARIMA (Auto Regressive Integrated Moving Average) to forecast the minimum daily temperature and compared its result with ARPEGE. As a result, ARIMA method shows better mean accuracy (91%) over the numerical model ARPEGE (68%), for the prediction of five days in January 2017. Moreover, back to five months ago, in order to validate the accuracy of the proposed model, a simulation has been applied on the first five days of August 2016. Results have shown that the time series ARIMA method has offered better mean accuracy (98%) over the numerical model ARPEGE (89%) for the prediction of five days of August 2016. This paper discusses a multiprocessing approach applied to ARIMA in order to enhance the efficiency of ARIMA in terms of complexity and resources.展开更多
文摘Many preterm infants suffer from neural disorders caused by early birth complications. The detection of children with neurological risk is an important challenge. The electroencephalogram is an important technique for establishing long-term neurological prognosis. Within this scope, the goal of this study is to propose an automatic detection of abnormal preterm babies’ electroencephalograms (EEG). A corpus of 316 neonatal EEG recordings of 100 infants born after less than 35 weeks of gestation were preprocessed and a time series of standard deviation was computed. This time series was thresholded to detect Inter Burst Intervals (IBI). Temporal features were extracted from bursts and IBI. Feature selection was carried out with classification in one step so as to select the best combination of features in terms of classification performance. Two classifiers were tested: Multiple Linear Regressions and Support Vector Machines (SVM). Performance was computed using cross validations. Methods were validated on a corpus of 100 infants with no serious brain damage. The Multiple Linear Regression method shows the best results with a sensitivity of 86.11% ± 10.01%, a specificity of 77.44% ± 7.62% and an AUC (Area under the ROC curves) of 0.82 ± 0.04. An accurate detection of abnormal EEG for preterm infants is feasible. This study is a first step towards an automatic analysis of the premature brain, making it possible to lighten the physician’s workload in the future.
文摘Developing a reliable weather forecasting model is a complicated task, as it requires heavy IT resources as well as heavy investments beyond the financial capabilities of most countries. In Lebanon, the prediction model used by the civil aviation weather service at Rafic Hariri International Airport in Beirut (BRHIA) is the ARPEGE model, (0.5) developed by the weather service in France. Unfortunately, forecasts provided by ARPEGE have been erroneous and biased by several factors such as the chaotic character of the physical modeling equations of some atmospheric phenomena (advection, convection, etc.) and the nature of the Lebanese topography. In this paper, we proposed the time series method ARIMA (Auto Regressive Integrated Moving Average) to forecast the minimum daily temperature and compared its result with ARPEGE. As a result, ARIMA method shows better mean accuracy (91%) over the numerical model ARPEGE (68%), for the prediction of five days in January 2017. Moreover, back to five months ago, in order to validate the accuracy of the proposed model, a simulation has been applied on the first five days of August 2016. Results have shown that the time series ARIMA method has offered better mean accuracy (98%) over the numerical model ARPEGE (89%) for the prediction of five days of August 2016. This paper discusses a multiprocessing approach applied to ARIMA in order to enhance the efficiency of ARIMA in terms of complexity and resources.
