scholarly journals Jaundice Detection System Using Physiological Characteristics

Author(s):  
Ekereke, Layefa ◽  
Prince O. Asagba

Jaundice is the abnormal accumulation of Bilirubin in the blood, constant checking of their content level in the blood of new born children is vital as going for Anti-natal because its effect is dangerous and irreversible. At the moment, the standard method to determining the concentration of bilirubin in neonates is Laboratory Blood Test (TSB) test and this method can be traumatic for babies due to the constant blood extraction. Our goal in this research is to use hybridized machine learning techniques to develop a jaundice detection system using all the possible physiological characteristics or symptoms. The developed jaundice detection system is capable of detecting the presence of jaundice in neonate non-invasively, it also has a 0.07% standard error coefficient and a Percentage Value of 0.001 when the outcome was compared to TSB of all Test and Validation samples.

2019 ◽  
Vol 28 (1) ◽  
pp. 343-384 ◽  
Author(s):  
Gamal Eldin I. Selim ◽  
EZZ El-Din Hemdan ◽  
Ahmed M. Shehata ◽  
Nawal A. El-Fishawy

The Intrusion is a major threat to unauthorized data or legal network using the legitimate user identity or any of the back doors and vulnerabilities in the network. IDS mechanisms are developed to detect the intrusions at various levels. The objective of the research work is to improve the Intrusion Detection System performance by applying machine learning techniques based on decision trees for detection and classification of attacks. The methodology adapted will process the datasets in three stages. The experimentation is conducted on KDDCUP99 data sets based on number of features. The Bayesian three modes are analyzed for different sized data sets based upon total number of attacks. The time consumed by the classifier to build the model is analyzed and the accuracy is done.


2020 ◽  
Vol 8 (6) ◽  
pp. 3949-3953

Nowadays there is a significant study effort due to the popularity of CCTV to enhance analysis methods for surveillance videos and video-based images in conjunction with machine learning techniques for the purpose of independent assessment of such information sources. Although recognition of human intervention in computer vision is extremely attained subject, abnormal behavior detection is lately attracting more research attention. In this paper, we are interested in the studying the two main steps that compose abnormal human activity detection system which are the behavior representation and modelling. And we use different techniques, related to feature extraction and description for behavior representation as well as unsupervised classification methods for behavior modelling. In addition, available datasets and metrics for performance evaluation will be presented. Finally, this paper will be aimed to detect abnormal behaved object in crowd, such as fast motion in a crowd of walking people


Author(s):  
N. Ravi ◽  
G. Ramachandran

Recent advancement in technologies such as Cloud, Internet of Things etc., leads to the increase usage of mobile computing. Present day mobile computing are too sophisticated and advancement are reaching great heights. Moreover, the present day mobile network suffers due to external and internal intrusions within and outside networks. The existing security systems to protect the mobile networks are incapable to detect the recent attacks. Further, the existing security system completely depends on the traditional signature and rule based approaches. Recent attacks have the property of not fluctuating its behaviour during attack. Hence, a robust Intrusion Detection System (IDS) is desirable. In order to address the above mentioned issue, this paper proposed a robust IDS using Machine Learning Techniques (MLT). The key of using MLT is to utilize the power of ensembles. The ensembles of classifier used in this paper are Random Forest (RF), KNN, Naïve Bayes (NB), etc. The proposed IDS is experimentally tested and validated using a secure test bed. The experimental results also confirms that the proposed IDS is robust enough to withstand and detect any form of intrusions and it is also noted that the proposed IDS outperforms the state of the art IDS with more than 95% accuracy.


Sign in / Sign up

Export Citation Format

Share Document