scholarly journals Theoretical statistical correlation for biometric identification performance

Author(s):  
Michael E. Schuckers
2019 ◽  
Vol 17 (1) ◽  
pp. 118-127
Author(s):  
Sanaa Ghouzali ◽  
Souad Larabi

Most biometric identification applications suffer from the curse of dimensionality as the database size becomes very large, which could negatively affect both the identification performance and speed. In this paper, we use Projection Pursuit (PP) methods to determine clusters of individuals. Support Vector Machine (SVM) classifiers are then applied on each cluster of users separately. PP clustering is conducted using Friedman and Kurtosis projection indices optimized by Genetic Algorithm and Particle Swarm Optimization methods. Experimental results obtained using YALE face database showed improvement in the performance and speed of face identification system


2012 ◽  
Author(s):  
Shannon M. Andersen ◽  
Curt A. Carlson ◽  
Maria Carlson ◽  
Scott D. Gronlund

2020 ◽  
pp. 41-45
Author(s):  
G. R. Kuchava ◽  
E. V. Eliseev ◽  
B. V. Silaev ◽  
D. A. Doroshenko ◽  
Yu. N. Fedulaev

The aim of the study was to assess the course and outcome of cerebral infarction, depending on the age factor and duration of stay in the neuroblock. Materials and methods: a dynamic observation of 494 patients, men and women, aged 38–84 years with acute ischemic stroke of hemispheric localization, which were divided into the three groups depending on age, was performed. Group 1 – younger than 60 years old, group 2–60–70 years old, group 3 – older than 60 years. All patients underwent standard therapy, according to the recommendations for the treatment of ischemic stroke. The patients underwent comprehensive clinical and instrumental monitoring, which included assessment of somatic and neurological status according to the NIH‑NINDS scales at 1st, 3rd, 10th days and at discharge or death; assessment of the level of social adaptation according to the Bartel scale on 1st, 3rd, 10th days and at discharge, clinical and biochemical blood tests, computed tomography of the brain. Assessment of the quality of therapy was carried out according to specially developed maps using methods of statistical correlation analysis. Results: the most pronounced positive dynamics of neurological status was in the 1st group of patients. The regression of neurological deficit in the 2nd group was worse. The minimal dynamics of neurological deficit was in the 3rd group of patients with cerebral stroke. Most often, the death of patients with cerebral stroke occurred from the development of multiple organ disorders. Conclusions: patients over 70 years of age have the greatest risk of death, due to: a decrease in the reactivity of the body, the presence of initially severe concomitant somatic pathology in patients with admission to hospital; accession of secondary somatic and purulent‑septic complications.


2019 ◽  
Vol 2019 (11) ◽  
pp. 268-1-268-9
Author(s):  
Herman G.J Groot ◽  
Egor Bondarev ◽  
Peter H.N. de With

Author(s):  
A. Nagesh

The feature vectors of speaker identification system plays a crucial role in the overall performance of the system. There are many new feature vectors extraction methods based on MFCC, but ultimately we want to maximize the performance of SID system.  The objective of this paper to derive Gammatone Frequency Cepstral Coefficients (GFCC) based a new set of feature vectors using Gaussian Mixer model (GMM) for speaker identification. The MFCC are the default feature vectors for speaker recognition, but they are not very robust at the presence of additive noise. The GFCC features in recent studies have shown very good robustness against noise and acoustic change. The main idea is  GFCC features based on GMM feature extraction is to improve the overall speaker identification performance in low signal to noise ratio (SNR) conditions.


Author(s):  
A.A. Astapov ◽  
◽  
D.V. Davydov ◽  
A.I. Egorov ◽  
D.V. Drozdov ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document