Faculty Publications

Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736

Publications by NITK Faculty

Browse

Subject: search.filters.subject.Cyber physical system

Search Results

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Architecture and Deployment Models-SDN Protocols, APIs, and Layers, Applications and Implementations
    (Springer Science and Business Media Deutschland GmbH, 2022) Rudra, B.; S, T.
    The current Internet infrastructure is not anticipating such a growth of IoT and increasing the network complexity. New network architecture for the management of IoT data flow and also catering to the Quality of Service of different IoT services is required. The existing incompatible solutions are limited to the early adoption of IoT. The standardization bodies, industries, researches were involved in developing standards to support end-to-end connection, interoperation between devices from different vendors and also provide cost-efficient solutions. The Working Groups (WG) at the IETF introduced new solutions that have allowed the connection of low-power wireless networks to the Internet. In spite of the vast exploration of solutions for deploying IoT, the management of IoT networks requires complex routing topologies with a simplified user operation. This gives rise to the need for centralized network control which is facilitated by Software Defined Networking (SDN). SDN was a standard technology for Wireless Sensor Networks (WSNs) already available which is the early version of IoT as the world knows it today. SDN provides a framework to ease the complexity involved in the management of sophisticated networks. We discuss various protocols present in the architecture along with the research challenges for the future. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.
  • No Thumbnail Available
    Item
    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. © 2019 IEEE.