No abstract

IoT devices frequently generate large volumes of streaming data and in order to take advantage of this data, their temporal patterns must be learned and identified. Streaming data analysis has become popular after being successfully used in many applications including forecasting electricity load, stock market prices, weather conditions, etc. Artificial Neural Networks (ANNs) have been successfully utilized in understanding the embedded interesting patterns/behaviors in the data and forecasting the future values based on it. One such pattern is modelled and learned in the present study to identify the occurrence of a specific pattern in a Water Management System (WMS). This prediction aids in making an automatic decision support system, to switch OFF a hydraulic suction pump at the appropriate time. Three types of ANN, namely Multi-Input Multi-Output (MIMO), Multi-Input Single-Output (MISO), and Recurrent Neural Network (RNN) have been compared, for multi-step-ahead forecasting, on a sensor’s streaming data. Experiments have shown that RNN has the best performance among three models and based on its prediction, a system can be implemented to make the best decision with 86% accuracy.

No abstract

Abstract-We are living in the era of minute by minute developments and new technologies; the demand of easy way of life is the talk of the day. Engineering industries are focusing on the projects which advance and facilitate their customers with comfortable and secure living. This paper discusses the most advanced idea of Domotics, in which the comprehensive controlling and monitoring of all home appliances are done by simple instant message service. However, one of the most successful applications of image analysis and understanding, face recognition has recently received significant attention especially in the field of security. Moreover, globally available GSM is the cheapest wireless medium for any time communication with your deployed device. Above all, embedded designing on FPGA emerged a new way of technology which allows coupling of multi-dimensional features of system in to a single chip package.

Identification of the opinion leaders in the world's largest microblogging site,Twitter, is crucial problem of social network analysis.Twitter has quick information flow and has high impact on forming opinion on mass public.This paper presents the study based on various centrality mesaure approaches for finding key players for a specific political trend on twitter. A novel weighted approach has been proposed for finding opinion leaders based on the centrality measures. Experiment has been conducted on the twitter's data for the sit in procession of Pakistani politician Imran Khan in 2014. It has been found that Twitter opinion leadership makes a significant contribution to individuals' involvement in political reforms.