WILD ANIMAL DETECTION USING MULTI-CLUSTER FEATURE SELECTION

In recent years the whole world witnessed several natural and manmade disasters. 2015 Earthquake in Nepal and India with 7.8 magnitudes which killed 9000 people and injured 22000 as per Government Records. 2018 Flood in North Korea left 10,700 people as per the report of International Federation of Red Cross (IFRC) and Wikipedia. Floods in India 2018, killed more than 300 in the state of Kerala. 2016, Forest fire in Uttarakhand, India burnt 10,000 acres of Forest area. In between April 2014 – May 2017, 1,144 people killed by wild animals as per the report of Indian Environment Ministry (IEM). All the reports stated above represents indications that regardless of several advancements and technical skill development to disaster management is not considered efficiently worldwide. There are plenty of disasters which could be taken care of much efficiently and wisely. If we see the disasters like flood, fire and animal attack we can easily notice that they are manageable to much extent with expert technical advancements. Our paper is about the disaster management of the tribrid series (Flood, Fire, Wild Animal Attack) with the eminent usage of technology. We create a flood sensing unit, a fire detection unit, and a wild animal detection unit with the help of sensors and we create the alert and remedial action unit to protect the common men from sub disasters. We use Embedded and IOT technologies together to provide worldwide coverage and accurate detection of the calamities.

Download Full-text

Cluster feature selection in high-dimensional linear models

Random Matrices Theory and Application ◽

10.1142/s2010326317500150 ◽

2018 ◽

Vol 07 (01) ◽

pp. 1750015

Author(s):

Bingqing Lin ◽

Zhen Pang ◽

Qihua Wang

Keyword(s):

Feature Selection ◽

Linear Correlation ◽

Linear Models ◽

Feature Space ◽

Elastic Net ◽

High Dimensional ◽

Variable Screening ◽

Sure Independence Screening ◽

Cluster Feature ◽

Highly Correlated

This paper concerns with variable screening when highly correlated variables exist in high-dimensional linear models. We propose a novel cluster feature selection (CFS) procedure based on the elastic net and linear correlation variable screening to enjoy the benefits of the two methods. When calculating the correlation between the predictor and the response, we consider highly correlated groups of predictors instead of the individual ones. This is in contrast to the usual linear correlation variable screening. Within each correlated group, we apply the elastic net to select variables and estimate their parameters. This avoids the drawback of mistakenly eliminating true relevant variables when they are highly correlated like LASSO [R. Tibshirani, Regression shrinkage and selection via the lasso, J. R. Stat. Soc. Ser. B 58 (1996) 268–288] does. After applying the CFS procedure, the maximum absolute correlation coefficient between clusters becomes smaller and any common model selection methods like sure independence screening (SIS) [J. Fan and J. Lv, Sure independence screening for ultrahigh dimensional feature space, J. R. Stat. Soc. Ser. B 70 (2008) 849–911] or LASSO can be applied to improve the results. Extensive numerical examples including pure simulation examples and semi-real examples are conducted to show the good performances of our procedure.

Download Full-text