M Tech ( CSE )

With the growth of data in biomedical and health care communities in large amounts, accurate analysis of medical data benefits early disease detection, patient care, and community services. However, the analysis accuracy is reduced when the quality of medical data is incomplete. Moreover, different regions exhibit unique characteristics of certain regional diseases, which may weaken the prediction of disease outbreaks. Machine learning algorithms are used for effective prediction of chronic disease like Cardiac Arrhythmia, is of a group of conditions in which the electrical activity of the heart is irregular or is faster or slower than normal. It is the leading cause of death for both men and women in the world. For optimization Stochastic Gradient Descent Algorithm is used.

In today's world there is a tremendous increase in the number of users using the Internet. As a result the e-commerce websites have been emerging to encourage the users of Internet. But these e-commerce websites are facing the problem in recommending the items to the users. In view of this challenge, an Agglomerative Hierarchical Clustering for Hybrid Recommender Systems approach is proposed in this paper which aims at recruiting similar items in the same clusters to recommend items which are similar both at content as well as at rating. Technically, this approach can be performed in two stages. In the first stage, the available items are divided into small-scale clusters, for further processing. And in the second stage, Hybrid Recommender Systems algorithm is imposed on one of the clusters. As the number of the items in a cluster is much less than the total number of the item available on the web, it is expected that the online execution time of Hybrid Recommender Systems can be reduced. At last, to verify the availability of this approach several experiments are conducted.

The objective of this study was to evaluate the effects of Transcutaneous Electric Nerve stimulation (TENS) on whole salivary flow rate in healthy adult subjects and to find out whether the protocol utilized for collection of saliva influence the quantity of saliva stimulated. Materials and Methods: Using an extraoral TENS applied over parotid glands stimulated whole saliva flow rate in fifty healthy adult subjects was measured Collection of TENS stimulated saliva was performed on day 1 after collection of unstimulated saliva, on day 2 only TENS stimulated saliva was measured. The data obtained was subjected to statistical analysis using paired 't' test. Results: Thirty nine patients on day one and thirty six patients on day two out of 50 (75 % of the subjects tested) responded to TENS therapy with an increase of stimulated whole saliva flow rate .There was a reduction in quantity of TENS stimulated saliva on day one and two with a difference of 4% which statistically significant with p value 0.009. Conclusions: Transcutaneous electric nerve stimulation (TENS) as an extra-oral device can be considered as a safe, non-pharmacological measure in order to achieve an increase of the rate of unstimulated saliva. Further studies should be conducted to evaluate the possibility of using TENS in relieving the symptoms of xerostomia.

Internet of Things (IoT) is an emerging technology where things of everyday objects can be connected to Internet. In IoT technology devices are supposed to be deployed 'everywhere' and to be accessed 'any time' from 'anywhere'. In this network gateways would have an important role for connecting heterogeneous networks to internet. The IoT Gateways must be smart enough to perform collected operations depending on the thing application. The significant actions of IoT Gateway are integration of wireless sensor network and mobile network, protocol mapping, managing the endpoint network, providing secure and safe communication between various end point networks. Here we are proposing a smart and secured framework of IoT Gateway using Raspberry Pi. This proposal makes the IoT Gateway as a smart thing just like other smart things in IoT technology. Apart from native Gateway functionalities this paper emphasize the security of IoT Gateway, since the present IoT Gateways are venerable to attacks. The Raspberry Pi board which is meant for IoT having some precautionary measures for security. In this paper we proposed those measures to provide security for IoT Gateways. Compared to the other smart Gateways the proposed Gateway is flexible, cost effective and provides security. And we implemented an architecture of smart irrigation system using our Gateway Pi.

Cloud computing technology provides assistance to companies and users to share computing resources instead of having personal devices or local servers to handle the applications. Mobile cloud computing networking [MCCN] is a novel approach. MCCN is an integration of cloud-based resources and mobility. This paper gives an overview of mobile cloud network model, their challenges and technology of LTE. But sometimes it is difficult in cloud to built spontaneous network and configures its parameters. This paper gives brief view of the routing algorithm used to enhance the capacity of access network in mobile cloud services based on merging of computation and networking in heterogeneous mobile cloud networks.

A mobile ad hoc network is a collection of self-organized mobile nodes. This network doesn’t require existing infrastructure or central administration. As the nodes have mobility, the biggest challenge in this kind of networks is to find a path i.e., routing between the communications end points. Ant colony optimization (ACO) is a technique to solve problems like routing in ad hoc networks based on food searching behavior of ants. All ant colony algorithms are subset of Swarm Intelligence which means collective behavior of individual ants. All the ant based algorithms are mainly depended on pheromone concentration. Pheromone is a volatile chemical substance secreted by ants from nest to food source in order to influence other ants to follow them. The route will be discovered by the concentration of pheromone values. AntHocNet is based on ideas from ACO. It is a hybrid algorithm consisting of both reactive and proactive components. AntHocNet has a reactive path setup but a proactive ...