Face recognition based door locking system

The security sector is experiencing diversification. This has brought about
the need to review the reliability of already existing systems and look into the possibility of creating better systems that are smarter and more secure. The old door security systems made use of keys, locks and chains. However, the locks can be easily broken and keys can get stolen or can be duplicated. In order to overcome this drawback, mechanical locking system was
introduced, that is, latches were used. Latches had better security than the
locks. Although, latches cannot be broken as easily as the locks, they make
the use of keys, which are not so reliable and can get stolen. Further, to
avoid these drawbacks, password based system was introduced. This
system used numeric combination to permit entrance to user.

But security is entirely based on confidentiality and the strength of the password.Modification was made in the password from numeric to alpha-numeric.Security describes protection of life and property. moved to biometric security system to ensure better security. Biometric security system includes fingerprint based system was the first biometric locking system. Using the fingerprints of a person for unlocking the door is main parameter for this system. However, like any other systems, they also have drawbacks. Fingerprints of a person can be duplicated. This can lead to opening of the door for unauthorized person. Finally research moved to image processing system. This system provides high security. When a person wants to access his locker, initially at the main door of locker and PIR sensor will be placed. This sensor will sense the body temperature of a person, standing near the door. And then, his/her image will be captured by
the camera installed at the main gate. This image will be given to the PC
where the Python software will compare this image with the authentic
images stored in the PC. If authentic, then only the door will open otherwise
it will remain closed and the alarm will buzz for further action.


Drowsy driver detection

Drowsy driver detection is one of the potential applications of intelligent vehicle systems. Previous approaches to drowsiness detection primarily make pre-assumptions about the relevant behavior, focusing on blink rate, eye closure, and yawning. Here we employ machine learning to datamine actual human behavior during drowsiness episodes.

Automatic classifiers for facial actions from the facial action coding system were developed using machine learning on a separate database of spontaneous expressions. These facial actions include blinking and yawn motions, as well as a number of other facial movements


Soil prediction for modern agriculture


Agriculture is a non technical sector where in technology can be incorporated for the betterment. Agricultural technology needs to be quick inimplementation and easy in adoption. Farmers usually follow a method called crop mutation after every consequent crop yield. The crop mutation allowsthe soil to regain the minerals that were used by the crop previously and use the left over minerals for cultivating the new crop. To know if the soil hasreached the point where it is unfit to yield the particular crop, farmer has to experience a loss in yield. One financial year for a farmer is very crucial toaccept the loss. This paper implements a that would help in maintaining the soil fertility consistently.

This method is traditionally implemented in manycountries where the change in crop is done after a loss in yield for cultivating the same crop continuously. There are soil parameters that come into consideration when we have to predict the soil quality. This method suggests the solution for the above stated problem using Machine Learning Techniques. This paper suggests a software enabled solution considering crucial soil parameters and soil factors to predict the soil quality.