IJFANS International Journal of Food and Nutritional Sciences

ISSN PRINT 2319 1775 Online 2320-7876

INTRUSION DETECTION AND CRIME PREDICTION WITH MACHINE LEARNING AND IoT

Main Article Content

Anirudh Kumar Tiwari, Bhavana Narain

Abstract

Crime prediction is a foremost requirement of the current time. Technology helps to process crime prediction in advance form. In this era of digitalization crime investigation and prediction are a top and foremost necessity. An action or commission which constitutes an offense and is punishable by Law is called a crime in today's time, crime has increased a lot and if the crime is identified at the right time and informed to the police or the government, then IoT and computer applications like IDS are a blessing of digital technology and are used to find criminal information, and it helps the police to get data. The purpose of our work is to design a prototype that helps the police in detecting crime locations. We have collected data set from IoT-based sensor. Data collected is pre-processed and arranged in an excel sheet. This data set is used in an ensemble classifier of machine learning to predict the crime. Ensemble classifier is an improved technique of classification which support azure machine learning. It gives high accuracy and avoids overfitting and classification. It helps improve machine learning results by comminuting several models. It creates multiple data set and at last various classifier to give an accurate result. When we use an ensemble classifier in our work, we get high accuracy if different base models misclassify different training. Ex- even if the base classifier accuracy is slow.Crime can be performed by an individual or group. It can commit against the government or private sector it may harm someone’s reputation, physical harm or mental harm crime can cause direct harm or indirect harm to whomever the victim is. We have taken a condition that if any person is going somewhere and after seeing an accident when the photo of that accident is taken then automatically it will be sent to nearest police Station. For this, it is necessary to have an application designed by us both for the sender and the receiver. This whole matter will directly connect the police with the crime location which eases the police can reach that location. GPS will be used for location detection. In our work, we have collected datasets with the help of a digital camera that is attached to an IoT device. In the first part of our paper, we have discussed the grounds of our work under the introduction of crime, digital image processing, GPS, and IoT. In the second part of our work, we have discussed the methodology of our work here sensor board, and GPS setting has been discussed along with the dataset. There is a number of data collection technologies in the IoT. The most widely used technology is the Wireless sensor network (WSN) uses multi-hopping and self-organization to maintain control over the communication nodes.

Article Details