Portfolio item number 1
Short description of portfolio item number 1
Short description of portfolio item number 1
Short description of portfolio item number 2
Published in Ground/Air Multisensor Interoperability, Integration, and Networking for Persistent ISR VIII, 2017
Recommended citation: Jayarajah, K., Subbaraju, V., Weerakoon, D., Misra, A. and Athaide, N., 2017, May. Discovering anomalous events from urban informatics data. In Ground/Air Multisensor Interoperability, Integration, and Networking for Persistent ISR VIII (Vol. 10190, pp. 70-83). SPIE.
Published in IEEE INFOCOM 2019-IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS), 2019
Recommended citation: Misra, A., Weerakoon, D. and Jayarajah, K., 2019, April. The challenge of collaborative iot-based inferencing in adversarial settings. In IEEE INFOCOM 2019-IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS) (pp. 1-6). IEEE.
Published in Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications, 2019
Recommended citation: Misra, A., Jayarajah, K., Weerakoon, D., Tandriansyah, R., Yao, S. and Abdelzaher, T., 2019, May. Dependable machine intelligence at the tactical edge. In Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications (Vol. 11006, pp. 64-77). SPIE.
Published in 2019 22th International Conference on Information Fusion (FUSION), 2019
Recommended citation: Weerakoon, D., Jayarajah, K., Tandriansyah, R. and Misra, A., 2019, July. Resilient Collaborative Intelligence for Adversarial IoT Environments. In 2019 22th International Conference on Information Fusion (FUSION) (pp. 1-8). IEEE
Published in 2019 IEEE 39th International Conference on Distributed Computing Systems (ICDCS), 2019
Recommended citation: Yao, S., Hao, Y., Zhao, Y., Piao, A., Shao, H., Liu, D., Liu, S., Hu, S., Weerakoon, D., Jayarajah, K. and Misra, A., 2019, July. Eugene: Towards deep intelligence as a service. In 2019 IEEE 39th International Conference on Distributed Computing Systems (ICDCS) (pp. 1630-1640). IEEE.
Published in ACM Transactions on Internet Technology (TOIT), 2020
Recommended citation: Abdelzaher, T., Hao, Y., Jayarajah, K., Misra, A., Skarin, P., Yao, S., Weerakoon, D. and Årzén, K.E., 2020. Five challenges in cloud-enabled intelligence and control. ACM Transactions on Internet Technology (TOIT), 20(1), pp.1-19.
Published in Proceedings of the 2020 International Conference on Multimodal Interaction, 2020
Recommended citation: Weerakoon, D., Subbaraju, V., Karumpulli, N., Tran, T., Xu, Q., Tan, U.X., Lim, J.H. and Misra, A., 2020, October. Gesture enhanced comprehension of ambiguous human-to-robot instructions. In Proceedings of the 2020 International Conference on Multimodal Interaction (pp. 251-259).
Published in IEEE Robotics and Automation Letters (RA-L), 2022
Recommended citation: Weerakoon, D., Subbaraju, V., Tran, T. and Misra, A., 2022. Cosm2ic: Optimizing real-time multi-modal instruction comprehension. IEEE Robotics and Automation Letters, 7(4), pp.10697-10704.
Published in Proceedings of the 30th ACM International Conference on Multimedia, 2022
Recommended citation: Weerakoon, D., Subbaraju, V., Tran, T. and Misra, A., 2022, October. SoftSkip: Empowering Multi-Modal Dynamic Pruning for Single-Stage Referring Comprehension. In Proceedings of the 30th ACM International Conference on Multimedia (pp. 3608-3616).
Published in 2023 15th International Conference on COMmunication Systems & NETworkS (COMSNETS), 2023
Recommended citation: Weerakoon, D., Subbaraju, V., Tran, T. and Misra, A., 2023, January. Demonstrating Multi-modal Human Instruction Comprehension with AR Smart Glass. In 2023 15th International Conference on COMmunication Systems & NETworkS (COMSNETS) (pp. 231-233). IEEE.
Published in 21th ACM Conference on Embedded Networked Sensor Systems (SenSys 2023), 2023
Recommended citation: Rathnayake, D., Weerakoon, D., Radhakrishnan, M., Subbaraju, V., Hwang, I. and Misra, A., 2023, November. VGGlass - Demonstrating Visual Grounding and Localization Synergy with a LiDAR-enabled Smart-Glass. In 21th ACM Conference on Embedded Networked Sensor Systems (SenSys 2023) [In Press]
Published:
Many IoT networks, including for battlefield deployments, involve the deployment of resource-constrained sensors with varying degrees of redundancy/overlap (i.e., their data streams possess significant spatiotemporal correlation). Collaborative intelligence, whereby individual nodes adjust their inferencing pipelines to incorporate such correlated observations from other nodes, can improve both inferencing accuracy and performance metrics (such as latency and energy overheads). Using realworld data from a multicamera deployment, we first demonstrate the significant performance gains (up to 14% increase in accuracy) from such collaborative intelligence, achieved through two different approaches: (a) one involving statistical fusion of outputs from different nodes, and (b) another involving the development of new collaborative deep neural networks (DNNs). We then show that these collaboration-driven performance gains are susceptible to adversarial behaviour by one or more nodes, and thus need resilient mechanisms to provide robustness against such malicious behaviour. We also introduce an under-development testbed at Singapore Management University (SMU), specifically designed to enable real-world experimentation with such collaborative IoT intelligence techniques.
Published:
Published:
Supporting real-time, on-device execution of multi- modal referring instruction comprehension models is an important challenge to be tackled in embodied Human-Robot Interaction. However, state-of-the-art deep learning models are resource intensive and unsuitable for real-time execution on embedded devices. While model compression can achieve reduction in computational resources upto a certain point, further optimizations result in a severe drop in accuracy (upto 50%). To minimize this loss in accuracy, we propose the COSM2IC framework, with a lightweight Task Complexity Predictor, that uses multiple sensor inputs to assess the instructional complexity and thereby dynamically switch between a set of models of varying computational intensity such that computationally less demanding models are invoked whenever possible. To demonstrate the benefits of COSM2IC, we utilize a representative human-robot collaborative “table-top target acquisition” task, to curate a new multi-modal instruction dataset where a human issues instructions in a natural manner using a combination of visual, verbal and gestural (pointing) cues. We show that COSM2IC achieves a 3-fold reduction in comprehension latency when compared to a baseline DNN model while suffering an accuracy loss of only ∼5%. When compared to state-of-the-art model compression methods COSM2IC is able to achieve a further 30% reduction in latency and energy consumption for a comparable performance.
Undergraduate course, University 1, Department, 2014
This is a description of a teaching experience. You can use markdown like any other post.
Workshop, University 1, Department, 2015
This is a description of a teaching experience. You can use markdown like any other post.