. Biometrics
. Computer Vision
. Signal Processing
. Data Analytics
. Evolutionary Computing
. Next Gen Computing
. Predictive Analytics & IoT
. Human Computer Interaction
Smart Climate Monitoring for Large Scale Buildings
Company: Robert Bosch Engineering and Business Solutions Private Limited, Coimbatore
Abstract
Air conditioning systems in large scale buildings contribute a major portion of the energy requirements. A centralized temperature monitoring system would result in the enhancement of air conditioning services in large scale buildings. Here we develop a centralized temperature monitoring scheme suitable for office environments. Wireless sensors are placed inside a compartmentalized office area, which collects the surrounding temperature data and sends it to the cloud. The application in the cloud will receive this data, store the data and present this data graphically to the end user. In order to reduce the redundant data as well as for making the sensor network energy efficient, we carry out a data analytics algorithm to identify the redundant sensors in the network based on data correlation.
Hybrid Localization Algorithm for Indoor Asset Tracking
Abstract
Main focus of this research work is to design an efficient and scalable RFID based hybrid indoor localization algorithm that operates over long-range RFID readers. The major objectives of this work are to design an approach that is extensible to large environments with minimal calibration and to provide high accuracy. Asset tracking is important for resource utilization and recovery. It is a service that helps locate objects instantly by providing easy access of item locations without much manual effort. We design a hybrid localization algorithm to accurately estimate the position of an object within a finite indoor space. Our approach uses power level and signal strength parameters which are readily available without the requirement of additional hardware. Furthermore, our algorithm applies intelligent region elimination techniques, thereby avoiding the use of heavy calibration and computationally complex algorithms.
Securing Image Posts in Social Networking
Abstract
The most unbeatable technology, Internet brings to people for communication is social networks. With the exponential growth of users in internet, there is an equivalent growth among internet users to regularly visit social websites for linking with their friends, sharing thoughts, photos, videos and even discuss about their day today activities. The fact these social networks are available to all the users for free, leads to various types of security issues. Image security has been a topic of research over decades. Enhancements to individual techniques and combinations proposed till date have offered different levels of security assurances. This work aim to present a technique for secure sharing of image posts in social network. The significant feature of the scheme lies in the selection of security technique based on image content, evaluation of peers with whom the image can be shared based on text classification, transliteration and tone analysis. The proposed scheme a cost effective solution as it does not require any additional hardware. The utility of the model is demonstrated by mapping the scheme with Facebook and analyzing its performance through simulation.
