Varun Badrinath Krishna
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Varun Badrinath Krishna has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- William H. Sanders
University of Illinois at Urbana-Champaign, Champaign, Illinois 61820 United States
2 shared publications - Carl A. Gunter
School of Computing and Data Science, University of Illinois Urbana-Champaign, Urbana, IL 61801, USA
1 shared publication Ravishankar K. Iyer
Advanced Digital Sciences Center, Information Trust Institute, University of Illinois at Urbana-Champaign
1 shared publicationRichard Macwan
University of Illinois at Urbana-Champaign, Champaign, Illinois 61820 United States
1 shared publicationVaidehi V. Ambardekar
University of Illinois at Urbana-Champaign, Champaign, Illinois 61820 United States
1 shared publicationWilliam H. Sanders
Advanced Digital Sciences Center, Information Trust Institute, University of Illinois at Urbana-Champaign
1 shared publication
Latest Publications
- Open Access
Ballroom Dance Movement Recognition Using a Smart Watch
Inertial Measurement Unit (IMU) sensors are being increasingly used to detect human gestures and movements. Using a single IMU sensor, whole body movement recognition remains a hard problem because movements may not be adequately captured by the sensor. In this paper, we present a whole body movement detection study using a single smart watch in the context of ballroom dancing. Deep learning representations are used to classify well-defined sequences of movements, called \emph{figures}. Those representations are found to outperform ensembles of random forests and hidden Markov models. The classification accuracy of 85.95\% was improved to 92.31\% by modeling a dance as a first-order Markov chain of figures and correcting estimates of the immediately preceding figure.
Open AccessBallroom Dance Movement Recognition Using a Smart Watch
Inertial Measurement Unit (IMU) sensors are being increasingly used to detect human gestures and movements. Using a single IMU sensor, whole body movement recognition remains a hard problem because movements may not be adequately captured by the sensor. In this paper, we present a whole body movement detection study using a single smart watch in the context of ballroom dancing. Deep learning representations are used to classify well-defined sequences of movements, called \emph{figures}. Those representations are found to outperform ensembles of random forests and hidden Markov models. The classification accuracy of 85.95\% was improved to 92.31\% by modeling a dance as a first-order Markov chain of figures and correcting estimates of the immediately preceding figure.
- 1 November 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Computer
- Vol. 51 (11) , 37-45
Cyberattacks on Primary Frequency Response Mechanisms in Power Grids
Primary frequency response (PFR) is an important mechanism for making power grids resilient to faults that could lead to outages. We present the first study of cyberattacks that could cause power outages by infiltrating operational technology networks in generation control systems to inhibit the PFR.
- 1 November 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Computer
- Vol. 51 (11) , 37-45
Cyberattacks on Primary Frequency Response Mechanisms in Power Grids
Primary frequency response (PFR) is an important mechanism for making power grids resilient to faults that could lead to outages. We present the first study of cyberattacks that could cause power outages by infiltrating operational technology networks in generation control systems to inhibit the PFR.
- 7 May 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Signal Processing
- Vol. 12 (4) , 790-805
Evaluating Detectors on Optimal Attack Vectors That Enable Electricity Theft and DER Fraud
Worldwide, utilities are losing billions of dollars annually because of electricity theft. The detection of electricity theft has been a topic of research for decades. In this paper, we extend our prior work in the context of advanced metering infrastructures, wherein smart meters are compromised and made to under-report consumption. To the best of our knowledge, this paper presents the first study of meter fraud in the context of distributed energy resources (DERs). With an increased penetration of DERs in modern power grids, and with the decline in electricity prices, we show that there is incentive for electricity generators to over-report generation. We quantify the economic impact of cyber-attacks (on meters) that are optimal in that they maximize fraud while circumventing detectors. In doing so, we use consumption data from Ireland, solar generation data from the U.S. and Australia, and wind generation data from France.
- 7 May 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Signal Processing
- Vol. 12 (4) , 790-805
Evaluating Detectors on Optimal Attack Vectors That Enable Electricity Theft and DER Fraud
Worldwide, utilities are losing billions of dollars annually because of electricity theft. The detection of electricity theft has been a topic of research for decades. In this paper, we extend our prior work in the context of advanced metering infrastructures, wherein smart meters are compromised and made to under-report consumption. To the best of our knowledge, this paper presents the first study of meter fraud in the context of distributed energy resources (DERs). With an increased penetration of DERs in modern power grids, and with the decline in electricity prices, we show that there is incentive for electricity generators to over-report generation. We quantify the economic impact of cyber-attacks (on meters) that are optimal in that they maximize fraud while circumventing detectors. In doing so, we use consumption data from Ireland, solar generation data from the U.S. and Australia, and wind generation data from France.
- 18 May 2016
- Published by Springer Nature
- p. 199-210
ARIMA-Based Modeling and Validation of Consumption Readings in Power Grids
- 18 May 2016
- Published by Springer Nature
- p. 199-210
ARIMA-Based Modeling and Validation of Consumption Readings in Power Grids