Selected Inventions and Research Contributions
For Dr. S.S. Iyengar
Dr. S.S. Iyengar is the Ryder Professor of Computer Science and Director of the School of Computing and Information Sciences (SCIS) at Florida International University (FIU), Miami, FL. He is also the Founding Director of the Discovery Lab—an innovation and creation station for undergraduate students. His research for the last four decades includes High-Performance Algorithms, Biomedical Computing, Sensor Fusion, and Intelligent Systems, and have significantly impacted a wide variety of fields, including computer science, biomedical engineering, and medicine.
This page highlights some of his most significant work. A full description of his research work and commercialization, as well as its impact, can be found at: https://people.cis.fiu.edu/iyengar/
Some of the specific technical, professional engineering and computer science research work by Dr. S.S. Iyengar includes;
- a) Co-inventor of Cognitive Information Processing(CIM) Shell, an architecture & engine which recognizes and responds to complex patterns in mission-critical, real-time applications. CIM Fuses disparate data streams, including text & video, to create an interactive inspection and visualization system that provides real-time monitoring, analysis & online diagnosis for manufacturing, agricultural and oil production. It can reconfigure itself on the fly to isolate critical events and fix failures, unlike IBM’s Watson which only identifies failures.
- b) Co-inventor of Brooks–Iyengar (BI) foundational algorithm for noise tolerant distributed control, which bridges sensor fusion and Byzantine fault tolerance, providing optimal solutions to fault-event disambiguation in sensor-networks, and a computationally inspired, real-time fault tolerance solution with applications in distributed control and software reliability.
- c) Discovered a breakthrough approach for optimal sensor coverage in 2D/3D grid fields, determining precise location/trajectory of moving objects and optimizing communications between sensors, with applications in surveillance & environmental monitoring.
Continue reading for details of this body of work.
(https://cacm.acm.org/news/91343-lsu-scientists-develop-new-efficiency- software/fulltext).
………………………………………………………………………………………………….
Invention A)
a) Co-inventor of Cognitive Information Processing(CIM) Shell, an architecture & engine which recognizes and responds to complex patterns in mission-critical, real-time applications. CIM Fuses disparate data streams, including text & video, to create an interactive inspection and visualization system that provides real-time monitoring, analysis & online diagnosis for manufacturing, agricultural and oil production. It can reconfigure itself on the fly to isolate critical events and fix failures, unlike IBM’s Watson which only identifies failures.
(CIM) (https://cacm.acm.org/news/91343-lsu-scientists-develop-new-efficiency-software/fulltext).
Details: Dr. Iyengar is a co-inventor of the Cognitive Information Processing (CIM) shell, a system which recognizes and responds to complex patterns in mission-critical, real-time applications (see https://cacm.acm.org/news/91343-lsu-scientists-develop-new-efficiency- software/full text). CIM fuses disparate data streams, including text and video, to create an interactive inspection and visualization system that provides real-time monitoring, analysis, and online diagnosis for industrial applications. CIM can reconfigure itself on the fly to isolate critical events and fix failures, and underlies technologies used in manufacturing, agricultural, and oil production spaces, with notable applications and impact.
Impact:
(1) The Online Diagnosis of Manufacturing Machines (ODMM) system, developed by SpotCheck Inc., licensed by AIlectric, and used by Novatec and ProphecySensorLytics to diagnose systems failures in factories, with a Total Addressable Market (TAM) of $9.1B in 2014, which is predicted by ABIResearch to grow to over $24.7B by 2019;
(2) The DeepSAT Video and Image Analytics application, developed by LSU and used by the NASA Ames Research Center to provide decision support for satellite missions, with a TAM of over $41B; and
(3) The DeepDrug System to shorten the developmental timeline of new drugs, developed by SynthLab, and ranked one of the top 10 systems worldwide competing for $3M in the IBM Watson AI XPrize competition. https://cacm.acm.org/news/91343-lsu-scientists-develop-new-efficiency-software/fulltext
Applications and Other Links:
Article 1. http://searchbusinessanalytics.techtarget.com/feature/Cognitive-computing-for-all-Think-about-it
The hypergraph based search technique of the cognitive information management has been used for automated drug discovery. Our team at LSU is participating in the AI Xprize under the name “DeepDrug” and in the first year was ranked within the top 10 teams worldwide.
In addition, cognitive information technology-based SpotCheck System for predictive maintenance has been licensed by AutoPredictiveCoding (Now AIlectric). J K Technosoft (part of JK Group, a $30 billion) conglomerate has signed a master services agreement with AIectric to use SpotCheck (and other technologies from AIlectric) within their own factories as well as their customers. A paper describing SpotCheck had been among the most downloaded article in the Integration Journal in June 2017. See https://www.journals.elsevier.com/integration/most-downloaded-articles
Cited Papers:
- Iyengar, S. Mukhopadhyay, C. Steinmuller, X. Li,”Preventing Future Oil Spills with Software-based Event Detection”, IEEE Computer, 2010 V43 N8, pp.95-97 2)
- Iyengar, K. Boroojeni, N. Balakrishnan,”Mathematical Theories of Distributed Sensor Networks”, Springer Verlag, 2014.
…………………………………………………………………………………………………..
Invention B)
- b) Co-inventor of Brooks–Iyengar (BI) foundational algorithm for noise tolerant distributed control, which bridges sensor fusion and Byzantine fault tolerance, providing optimal solutions to fault-event disambiguation in sensor-networks, and a computationally inspired, real-time fault tolerance solution with applications in distributed control and software reliability.
Details: Co-inventor of the Brooks-Iyengar Hybrid Distributed Fusion Algorithm (B-I Algorithm) which, for the first time, unified the disparate fields of sensor fusion and Byzantine fault tolerance. Brooks–Iyengar algorithm is a seminal work and a major milestone in distributed sensing, and could be used as a fault tolerant solution for many redundancy scenarios. This work has resulted in a large body of applied research and real-world applications that today can be found across systems in distributed control, software reliability, and high-performance computing.
Impact:
The B-I algorithm has been incorporated into many systems: DARPA’s SensIT technology, which allows the combination of sensor readings in real time from acoustic, seismic, and motion sensors; modern day Linux and Android operating systems, impacting majority of the world’s computers, smart phones, and internet users; applications sold by Raytheon BBN and Thales Group UK and used by the US Navy; and a widely deployed system to provide robust fault-tolerant railcar door monitoring systems to provide enhanced passenger safety in trains. Moreover, the B-I algorithm has served for more than a quarter of a century as a baseline for new research developments, used by many scientists to extend the consequences of Iyengar’s original insight.
Applications and Other Links:
- Evaluation of the Brooks-Iyengar Distributed Sensing Algorithm and impact on the cost-effective processing of real-time sensor data streams. V. Kumar, “Impact of Brooks-Iyengar Distributed Sensing Algorithm on Real Time Systems,” in IEEE Transactions on Parallel and Distributed Systems, vol. 25, no. 5, pp. 1370-1370, May 2014.
- Brooks-Iyengar algorithm used in rail transportation systems for the safety of passengers when embarking and disembarking. This requires a fusion of sensor inputs to provide accurate automatic opening and closing with minimum traction, Brooks – Iyengar algorithm provides a fault-tolerant automatic sensing platform for closing doors. Buke Ao, “Robust Fault Tolerant Rail Door State Monitoring Systems: Applying the Brooks-Iyengar Sensing Algorithm to Transportation Applications,” in International Journal of Next-Generation Computing, Vol. 6, No. 3, November 2015.
Cited Papers:
- Brooks, S. Iyengar,”Robust Distributed Computing and Sensing Algorithm”, IEEE Computer V29 N6, 1996, pp.53-60 3)
- Brooks, S. Iyengar,”Multi-sensor Fusion: Fundamentals and Applications with Software”, Prentice-Hall, 1998
………………………………………………………………………………………………….
Invention C)
c)Discovered a breakthrough approach for optimal sensor coverage in 2D/3D grid fields, determining precise location/trajectory of moving objects and optimizing communications between sensors, with applications in surveillance & environmental monitoring.
Details: Iyengar’s 2001 paper (cited over 1,000 times per Google Scholar) provided an elegant integer linear programming solution for minimizing the cost of sensors for complete coverage in a 2D and 3D grid field, and represented a completely new approach for the important problems of precise location of a stationary target and trajectory determination of a moving target. This
breakthrough of determining the placement of sensors rather than focusing on communication between sensors was of prime importance in many fields such as surveillance and environmental monitoring.
The location and trajectory of a target are of prime importance in many fields. Before 2001, work focused on sensor communication and fusion and had /ignored/ optimal sensor placement. In his now seminal paper which has been cited more than 1000 times, Dr. Iyengar and team provided an elegant integer linear programming solution for sensor placement in 2- and 3-D grids. This simplified target location by allowing every grid point to be covered by a unique subset of sensors, so the sensors reporting a target in time sequence uniquely identifies the target’s location and trajectory.
By formulating the problem as a cost minimization under coverage constraints, he leveraged efficient ILP solvers for combinatorial optimization problems. His solution simplified target location considerably by developing placement strategies leveraging ILP and the theoretical framework of identifying codes to determine the best placement of sensors so that every grid point in the sensor field is covered by a unique subset of sensors. In this way, the set of sensors reporting a target at a given time uniquely identifies the grid location for the target. The determination of the trajectory of a moving target follows in a similar fashion from time series data.
Impact
The optical sensor placement technique has documented impact in a variety of companies and government organizations such as the Department of Defense. Boeing Corporation uses the system for optimal sensor selection and placement for perimeter defense. The process has also had a significant impact in the U.S. Navy (DOD) as documented by Naval Postgraduate School, where the process provided a foundation for the design and implementation of the multiagent simulation that models deployment and coverage of sensors performing collaborative target detection. In addition, NSF awarded grants to researchers building upon and leveraging the pioneering work on sensor deployment and minimalistic sensor networks.
Applications and Other Links:
- Boeing Corporation: Mattikalli, R. Fresnedo, R. Frank, P. Locke, S. Thunemann, Z. Optimal Sensor Selection and Placement for Perimeter Defense, 2007.
- Naval Postgraduate School: Capt. S. Hynes and N. S. Rowe, “Multi-Agent Simulation for Assessing Massive Sensor Deployment”, Article at Naval Postgraduate School, 2004.
- NSF Grants Awarded to build upon/leverage the work:
Award Number: CNS-1054935 (“CAREER: A Theoretical Foundation for Achieving Sustainability and Scalability in 3D Wireless Sensor Network Deployments”)
Award Number: CNS- 1152134 (“Optimal Surface Gateway Deployment for Underwater Acoustic Sensor Networks”)
Award Number: 0449309 (“Collaborative Signal and Information Processing in Sensor Networks”)
Award Number: CNS-1149611 (“SensorFly: Minimalistic Dynamic Sensing and Organization in Groups of Semi-Controllable Mobile Sensing Devices”)
Cited Papers:
- Chakrabarty, S. Iyengar, H. Qi, E. Cho,”Grid Coverage for Surveillance & Target Location in Distributed Sensor Networks”, IEEE Transactions on Computers, 2002 V51 N12, pp.1448-1453
…………………………………………………………………………………………………..
Recent Awards and Recognition
- Times Non-Resident Indian of Year Award 2017-Selected out of 25,000 nominations
- National Engineering Council Distinguished Educator Award 2017
- Mashable’s listing of “14 innovations that improved the world in 2014″, Founding Director of Discovery Lab (in Miami), his innovative work leading efforts to create the Telebot—a telepresence robot for assisting injured law enforcement officers – was ranked second in Mashable’s listing of “14 innovations that improved the world in 2014″, garnered over 400 world-wide media articles and interviews for radio, television and print, and led to US Patent 2015/0310671-A1, to be issued in March 2018, for Systems and Methods for Augmented Reality Interaction.
- Florida Inventors Hall of Fame Nomination 2018
- Professor Ramamurthy’s Distinguished Educator Award for Research and Scholarship 2017 (SPDS)
- Nico Haberman Award Nomination-2018
- His work has been featured on the cover of the National Science Foundation’s breakthrough technologies in both 2014 and again in 2016.
For more awards, recognition, and honors, please see; https://people.cis.fiu.edu/iyengar/