38 research outputs found
Evaluation de l’importance des variables dans la méthode SIR (Sliced Inverse Regression)
No full textInternational audienc
Variable importance assessment in sliced inverse regression for variable selection
No full textWe are interested in treating the relationship between a dependentvariable and a multivariate covariate in asemiparametric regression model. Since the purpose of most social,biological or environmental science research is the explanation, the determination of theimportance of the variables is a major concern. It is a way todetermine which variables are the most important when predicting. Sliced inverse regression methods allows to reduce the space of thecovariate by estimating the directions that form aneffective dimension reduction (EDR) space. The aim of this paper isto propose a computational method based on importance variable measure (only relying on the EDR space) in order to select the most useful variables. The numerical behavior of this new method, implemented in R, is studied on a simulation study. An illustration on a real data is also provided
Evaluation de l’importance des variables dans la méthode SIR (Sliced Inverse Regression)
No full textInternational audienc
Variable importance assessment in sliced inverse regression for variable selection
No full textInternational audienceThe focus is on treating the relationship between a dependent variable and a -dimensional covariate in a semiparametric regression model. Since the purpose of most social, biological or environmental science research is the explanation, the determination of the importance of the variables is a major concern. It is a way to determine which variables are the most important when predicting . Sliced inverse regression (SIR) methods allows us to reduce the space of the covariate by estimating the directions that form an effective dimension reduction (EDR) space. The aim is to propose a computational method based on importance variable measure (only relying on the EDR space) in order to select the most useful variables in SIR model. The numerical behavior of this approach, implemented in R, is studied on a simulation study. An illustration on a real data is also provided
Variable importance assessment in sliced inverse regression for variable selection
No full textWe are interested in treating the relationship between a dependentvariable and a multivariate covariate in asemiparametric regression model. Since the purpose of most social,biological or environmental science research is the explanation, the determination of theimportance of the variables is a major concern. It is a way todetermine which variables are the most important when predicting. Sliced inverse regression methods allows to reduce the space of thecovariate by estimating the directions that form aneffective dimension reduction (EDR) space. The aim of this paper isto propose a computational method based on importance variable measure (only relying on the EDR space) in order to select the most useful variables. The numerical behavior of this new method, implemented in R, is studied on a simulation study. An illustration on a real data is also provided
Effects of salt stress on growth seedlings of two landrace varieties of durum wheat from the Tunisian centre (Triticum durum)
No full textComparison by multivariate auto-regressive method of seizure prediction for real patients and virtual patients
No full textInternational audienceEpilepsy is one of the most widespread neurological pathologies, which is characterized by localized or generalized brain dysfunction due to abnormal or excessive paroxysmal electrical discharges. These discharges lead to neuronal hyperactivities causing prolonged and involuntary muscle contractions or periods of loss or altered consciousness. A patient's quality of life could be greatly improved with an effective alarm system able to predict future crises. Our article presents a fully specified model for automated seizure prediction based on autoregressive multivariate modeling and stability state analysis from clinical and simulated electroencephalography (EEG) data. Our model allows the calculation of a stability index whose analysis in content makes it possible to predict crises. The approach is validated on 29 crises recorded for 8 patients from a database available in free access and 14 simulated subjects also called virtual patients generated by neuro-computer platform TVB (The Virtual Brain:www.thevirtualbrain.org) using Epileptor as mass neural model for gray matter and “john Doe” matrix as white matter. Our preliminary results exhibit a detection accuracy of 97.87 %, a sensitivity of 100 % and an average prediction time for the eight real patients of 237.21 s and a detection accuracy of 100 %, a sensitivity of 93 % and an average prediction time of 4.427 s for the simulated subjects
Knowledge, attitudes and practices of sheep owners regarding abortion in Northern Tunisia
No full textAbstract Background Abortion in ewes causes high economic losses and represents a threat for human health due to abortive zoonotic pathogens. Objective The present study aimed to assess the knowledge, attitudes and practices (KAP) among sheep owners in the northern Tunisia regarding ewes’ abortions. Methods Between February 2021 and May 2022, a structured questionnaire containing both close and open‐ended questions was applied to 120 sheep owners in northern Tunisia. The data collected were analysed by chi‐square test using Epi info 6 software. Results The majority (75%) of participants reported a history of abortion in their sheep flocks. Sheep owners thought that the most frequent cause of abortion was physical factors, such as trauma, climate and stress (60% ± 5.5%; 48/80), followed by toxicity (15% ± 4%; 12/80), metabolic and nutritional conditions (12.5% ± 3.7%; 10/80), vaccination (5% ± 2.4%; 4/80) and infectious causes (7.5% ± 2.9%; 6/80) (p < 0.001). The majority of animal owners reported that abortions occurred mainly during autumn (39.6% ± 5%; 38/96), followed by summer (27% ± 4.5%; 26/96), winter (23% ± 4.3%; 22/96) and spring (10.4% ± 3.1%; 10/96) (p < 0.001). Approximately, half (45.8% ± 5%; 55/120) of interviewed farmers would not take any action if an abortion occurred. Half of the interviewed farmers (50.5% ± 5.1%; 48/95) did not apply any preventive measures when manipulating aborted ewes, and most of the sheep owners (77.3% ± 3.8%; 92/119) did not know that aborted ewes could transmit zoonotic pathogens. Conclusions Our survey concluded that sheep owners in Northern Tunisia had poor knowledge and attitudes as well as applied limited actions concerning several health aspects related to abortion. Education programmes should be established in order to improve Tunisian sheep owners’ KAP regarding abortion
