Sri Sivasubramaniya Nadar College of Engineering

About: Sri Sivasubramaniya Nadar College of Engineering is a based out in . It is known for research contribution in the topics: Crystal & Single crystal. The organization has 3745 authors who have published 4329 publications receiving 35038 citations.

IoT Based Health Monitoring System for Autistic Patients

Abstract: The transition towards the field of Internet of Things is occurring exponentially and with the advent of sensors and automation, a revolution in the healthcare sector is certain. A persistent deficit in social communication and the social interaction among people, especially children is termed as Autistic Spectrum Disorder. Our system provides an automatic monitoring framework, using sensors, for persons affected by autism. The system keeps track of the sensor readings that are obtained from the brain signals of affected persons. The analytics are performed on the collected data and a notification is constantly sent to their care-takers.

A Novel Method for Detection and Elimination of Modification Attack and TTL Attack in NTP Based Routing Algorithm

Abstract: An ad-hoc network is a multi-hop wireless network where all nodes cooperatively maintain network connectivity without a centralized infrastructure. If these nodes change their positions dynamically, it is called a mobile ad-hoc network (MANET). Since the network topology changes frequently, efficient adaptive routing protocols such as AODV, DSR, and NTP are used. As the network is wireless, security becomes the major issue in Mobile Ad hoc Networks. Some of the attacks such as modification, fabrication, impersonation and denial of service attacks are due to misbehavior of malicious nodes, which disrupts the transmission. To avoid such attacks some of cryptographic algorithms and key management schemes are used. There are some existing security protocols such as ARAN, SAODV and SEAD etc and will be compared with the proposed algorithm. In this paper, new key management scheme is implemented in NTP protocol, since Node Transition Probability (NTP) based algorithm provides maximum utilization of bandwidth during heavy traffic with less overhead. NTP determines stable routes using received power, but the packet delivery cannot be guaranteed since it is a non secured protocol. The proposal detects the modification, impersonation attacks and TTL attacks and, avoids the effects of malicious node and determines appropriate measures to discard such malicious nodes in dynamic condition.

PALM-CSS: a high accuracy and intelligent machine learning based cooperative spectrum sensing methodology in cognitive health care networks

Abstract: Spectrum sensing is the most crucial importance in cognitive radios. We propose a novel machine-learning algorithm for spectrum sensing in cognitive radio networks, which plays an essential role in medical data transmission. In this regard, high-speed pre-emptive decision-based multi-layer extreme learning machines are implemented for co-operative spectrums sensing in CR health care networks. For a radio channel, different vectors such as energy levels, distance, Channel ID, sensor values are determined at CR devices and are considered as a feature vector and thus used to feed into the proposed classifier for the determination of the availability of the channel. The classifier further categorizes the parameters such as user identification i.e., primary and secondary users, availability of channels, and the most crucial predictive decision of the available channels. The proposed PALM-CSS consists of two major phases, such as classification and prediction. Before the online classification and prediction, datasets are generated, and these datasets are used for the training of the proposed classifier. The proposed classifier uses the principle of high-speed priority-based multi-layer extreme learning machines for the classification and prediction. The experimental testbed has designed based Multicore CoxtexM-3 boards for implementing the real-time cognitive scenario and various performance parameters such as prediction accuracy, training and testing time, Receiver operating characteristics, and accuracy of detection. Furthermore, the proposed algorithms has also compared with the other existing machine learning algorithm such as artificial neural networks, support vector machines, K-nearest neighbor, Naive Bayes and ensemble machine learning algorithms in which the proposed algorithm outperforms the other existing algorithms and finds its more suitable for cognitive health care networks.