Browsing by Author "Abhishek, M.B."

Now showing 1 - 4 of 4

Cyber physical system perspective for smart water management in a campus
(Desalination Publications dwt@deswater.com, 2019) Abhishek, M.B.; Shet, N.S.V.
Smart water management in a large-scale campus is a good instance of cyber physical system (CPS). For realising this instantiation calls, a systematic framework together with the actual implementation of the associated modules needs to be devised. In this paper, the key issues of monitoring/sensing, networking, and computation parts put forward toward a deployable solution are proposed. Monitoring and Networking involving appropriate sensing and data transmission to monitor the water flow in the storage tanks at National Institute of Technology, Surathkal, Karnataka, India, are worked out to a mature stage. This paper captures essential details of these technical contributions, including necessary customisation and enhancement of the existing technologies. In the direction of addressing the data analytics of the computing part, the issue of imputing the missing values has been considered. An extensive set of results and comparisons obtained by applying different algorithms to the collected data are also presented. The technical contributions of this paper form a strong base toward the CPS realisation in the Campus, resulting in efficient water management when augmented with further analytics and modeling to address scalability. © ?2019 Desalination Publications.
Data Processing and deploying missing data algorithms to handle missing data in real time data of storage tank: A Cyber Physical Perspective
(2019) Abhishek, M.B.; Shet, N.S.V.
Water forecasting is crucial for planning, designing the infrastructure, and also for operating and managing water supply systems. Forecasting in the computation unit plays a very significant role in Cyber-Physical System. Real-time monitoring of water flow rates information helps us to conserve water when it is needed the most. Hence, we summarize in this paper the first impediment in forecasting which is; handling missing data in the real-time monitoring system using the different imputation techniques such as k-Nearest Neighbor, Expectation-Maximization, Matrix Completion. The performance of the respective method is evaluated using traditional methods like Root Mean Square Error (RMSE), Mean Absolute Error (MAE) and Mean Absolute Percentage Error (MAPE). Missingness simply refers to the manner in which a demographic sample lacks data. The two types of missingness considered here are: 'missing at random' and 'missing at burst'. Using the different imputation methods, the validation is performed by computing for a range of 'missingness' varying from 0% to 60%. In our experiment setup, we synthetically omitted missing values continuously and randomly in the datasets for the rationale of imputing omitted values in the datasets. In this work, we are choosing the best-fitted model for our application. � 2019 IEEE.
Data Processing and deploying missing data algorithms to handle missing data in real time data of storage tank: A Cyber Physical Perspective
(Institute of Electrical and Electronics Engineers Inc., 2019) Abhishek, M.B.; Shet, N.S.V.
Water forecasting is crucial for planning, designing the infrastructure, and also for operating and managing water supply systems. Forecasting in the computation unit plays a very significant role in Cyber-Physical System. Real-time monitoring of water flow rates information helps us to conserve water when it is needed the most. Hence, we summarize in this paper the first impediment in forecasting which is; handling missing data in the real-time monitoring system using the different imputation techniques such as k-Nearest Neighbor, Expectation-Maximization, Matrix Completion. The performance of the respective method is evaluated using traditional methods like Root Mean Square Error (RMSE), Mean Absolute Error (MAE) and Mean Absolute Percentage Error (MAPE). Missingness simply refers to the manner in which a demographic sample lacks data. The two types of missingness considered here are: 'missing at random' and 'missing at burst'. Using the different imputation methods, the validation is performed by computing for a range of 'missingness' varying from 0% to 60%. In our experiment setup, we synthetically omitted missing values continuously and randomly in the datasets for the rationale of imputing omitted values in the datasets. In this work, we are choosing the best-fitted model for our application. Â© 2019 IEEE.
Data transmission unit and web server interaction to monitor water distribution: A cyber-physical system perspective
(Insight Society ijaseit@insightsociety.org, 2018) Abhishek, M.B.; V.Shet, N.S.
Cyber-Physical System (CPS) is the concept of converging physical devices with cyber systems, CPS shares environmental information globally and improves resource utilization. The major aim of our work is to use the CPS technology to overcome improper handling and care of water supply infrastructure. Our experimental water pipileing infrastructure test bed set up at National Institute of Technology Karnataka Surathkal (NITK), India includes analysis of water distribution in three storage tanks using minimal wireless communication technology. This requires monitoring and wireless networking of the monitored data. In order to obtain water usage of each storage tanks, we have proposed low cost customization of water pipeline infrastructure. Monitoring unit (MU) includes 865-867Mhz RF module. In this paper, we deal with the networking part of CPS to perform water monitoring distribution in each storage tanks. Networking of CPS includes communication between Data transfer unit (DTU) and Aggregator unit (AU) used in the MU and also communication between DTU and web server unit (WS). Communication between DTU and AU involves analyzing the amount of water flow in the Inlet and Outlet of storage tanks in the campus. The WS unit contains resultant data of water usage in each storage tanks. The extensive group of resultant data sets of water usage, obtained in each storage tanks, gives importance to data analytics. Initially, we came up with a small-scale experimental set up at NITK campus; which is then extended to large scale area. The waterflow rate graphs show average daily and monthly usage of water of each storage tank. © IJASEIT.