Online ISSN: 2515-8260

Author : J, Yogapriya


IOT based urban surveillance using RaspberryPi and Deep learning with Mobile-Net Pre-trained model

Sathya Vignesh R; Vaishnavi.R. G; G. Aravind; G. SreeHarsha; B. HariKrishnaReddy; Yogapriya J

European Journal of Molecular & Clinical Medicine, 2020, Volume 7, Issue 4, Pages 2473-2477

The object detection is required to have a stronger protection in the surveillance areas. some of the surveillance systems uses cc cameras to monitor the area .It needs someone to check the output in particular area with-out rest. It is a difficult process for people who have to secure distant areas like fields , homes ,roads, restricted areas which cannot be monitored continuously by a person. object detection using raspberry pi and deep learning with pre-trained model can able to secure the place even without the person. It continuously monitors the area and identifies if any unwanted presence is detected and immediately sends an alert message to the respective device. The setup is fed with a lot of sample images like person, dog ,cat etc .The system checks the unwanted object to the sample images using mobile-net single shot detection by determining the accuracy of common features .Thus it helps to detect the unwanted presence with more accuracy than the previous existing systems.

Opinion Mining on Customer Product Reviews Using Supervised Machine Learning Techniques

Sivakumar A; Jagadeesh Babu S; Sathya Vignesh R; Shyam M; Yogapriya J

European Journal of Molecular & Clinical Medicine, 2020, Volume 7, Issue 4, Pages 1402-1412

In last decades online product sale is increased. The customers want to buy a quality product is very difficult in recent year. After buying only we know the problems in the product. After lancing many months users buying the product with problems. But many users put their Opinion in the review pages. Customers are very difficult to find the best product. Opinion Mining (OM) is the best tool for selecting the best product. OM on Product reviews refers to the process of analyzing the sentiment associated with it. This paper discussed about an attribute – level sentiment analysis of the product was done and also performs a three – class classification

LDPC BASED HARDWARE TROJAN DETECTION

Sathya Vignesh R; Sivakumar A; Shyam M; Jagadeesh Babu S; Yogapriya J

European Journal of Molecular & Clinical Medicine, 2020, Volume 7, Issue 4, Pages 1383-1388

Hardware Trojan (HT) can be introduced by an adversary at an untrusted design or fabrication house. Depending on the interests of the adversary the HT can cause change in functionality, denial-of-service, and information leakage or reliability reduction. In the existing system, a self-referencing based HT detection method using path delays which eliminates the requirement of golden ICs, is used. Further, we developed a procedure to select paths that minimizes the effect of both inter-die and intra-die PV. We have used topologically symmetric paths to mitigate inter-die variations and selected closer paths to exploit the spatial correlation to reduce the impact of intra-die variations. In the proposed system, Low density parity check with majority logic gate is used to predict the unknown post silicon errors occur in the integrated chips. Those small errors produce a large variation in the development of complex circuitry which utilizes maximum space of the FPGA. The proposed system uses Quartus II software and provides the simulation model showing the normal establishment of data transfer and Hardware Trojan affected system separately

AUTONOMOUS STANDALONE FIRE ENGINE WITH LIDAR-ROS

Sivakumar A; Jagadeesh Babu S; Sathya Vignesh R; Shyam M; Yogapriya J

European Journal of Molecular & Clinical Medicine, 2020, Volume 7, Issue 4, Pages 2494-2498

In recent year fire accidents increased rapidly. Firefighting and rescue, is very dangers for firefighters engaged in the field. So robots intended for firefighting have been introduced. However, Robots mobility is limited so it is difficult for them to directly approach fire sources. Here we proposed a solution by designing an autonomous firefighting robot with help of Lidar technology. Lidar can map surrounding environment and create a map of the locality using this pre-map robot can navigate the area by comparing current input from the Lidar. Here each node can be considered as a location point and every building is embedded with number of sensors for fire detection if fire is detected this information is sent to robot. Robot then activates and finds the location by itself and navigate to this location to extinguish fire. The robot-using camera also does fire detection tracking autonomously and water is sprinkled until fire is extinguished.