The Experts below are selected from a list of 17367 Experts worldwide ranked by ideXlab platform
Amar R Marathe - One of the best experts on this subject based on the ideXlab platform.
-
task conversions for integrating human and Machine Perception in a unified task
Intelligent Robots and Systems, 2016Co-Authors: Hyungtae Lee, Heesung Kwon, Ryan M Robinson, Daniel Donavanik, William D Nothwang, Amar R MaratheAbstract:The different strategies for feature extraction and synthesis employed by humans and computers are often complementary, hence combining the two into an integrated object recognition system may considerably improve performance over either used in isolation. Rapid Serial Visual Presentation (RSVP) is one well-established technique that has shown promise integrating human Perception into a Machine Perception system. In this paper, we apply computer vision techniques to image data filtered through human RSVP. We introduce “task conversions” to integrate the two modalities, applying the precise localization capabilities of computer vision with the detection capabilities of RSVP. We employ naive Bayesian fusion and a novel method, dynamic belief fusion (DBF), in a joint scheme as fusion approaches. Preliminary experiments demonstrate that DBF extracts complementary information from both human and Machine sources to improve performance for both target classification and object detection.
-
IROS - Task-conversions for integrating human and Machine Perception in a unified task
2016 IEEE RSJ International Conference on Intelligent Robots and Systems (IROS), 2016Co-Authors: Hyungtae Lee, Heesung Kwon, Ryan M Robinson, Daniel Donavanik, William D Nothwang, Amar R MaratheAbstract:The different strategies for feature extraction and synthesis employed by humans and computers are often complementary, hence combining the two into an integrated object recognition system may considerably improve performance over either used in isolation. Rapid Serial Visual Presentation (RSVP) is one well-established technique that has shown promise integrating human Perception into a Machine Perception system. In this paper, we apply computer vision techniques to image data filtered through human RSVP. We introduce “task conversions” to integrate the two modalities, applying the precise localization capabilities of computer vision with the detection capabilities of RSVP. We employ naive Bayesian fusion and a novel method, dynamic belief fusion (DBF), in a joint scheme as fusion approaches. Preliminary experiments demonstrate that DBF extracts complementary information from both human and Machine sources to improve performance for both target classification and object detection.
Amit P Sheth - One of the best experts on this subject based on the ideXlab platform.
-
an efficient bit vector approach to semantics based Machine Perception in resource constrained devices
International Semantic Web Conference, 2012Co-Authors: Cory Henson, Krishnaprasad Thirunarayan, Amit P ShethAbstract:The primary challenge of Machine Perception is to define efficient computational methods to derive high-level knowledge from low-level sensor observation data. Emerging solutions are using ontologies for expressive representation of concepts in the domain of sensing and Perception, which enable advanced integration and interpretation of heterogeneous sensor data. The computational complexity of OWL, however, seriously limits its applicability and use within resource-constrained environments, such as mobile devices. To overcome this issue, we employ OWL to formally define the inference tasks needed for Machine Perception --- explanation and discrimination --- and then provide efficient algorithms for these tasks, using bit-vector encodings and operations. The applicability of our approach to Machine Perception is evaluated on a smart-phone mobile device, demonstrating dramatic improvements in both efficiency and scale.
-
International Semantic Web Conference (1) - An efficient bit vector approach to semantics-based Machine Perception in resource-constrained devices
The Semantic Web – ISWC 2012, 2012Co-Authors: Cory Henson, Krishnaprasad Thirunarayan, Amit P ShethAbstract:The primary challenge of Machine Perception is to define efficient computational methods to derive high-level knowledge from low-level sensor observation data. Emerging solutions are using ontologies for expressive representation of concepts in the domain of sensing and Perception, which enable advanced integration and interpretation of heterogeneous sensor data. The computational complexity of OWL, however, seriously limits its applicability and use within resource-constrained environments, such as mobile devices. To overcome this issue, we employ OWL to formally define the inference tasks needed for Machine Perception --- explanation and discrimination --- and then provide efficient algorithms for these tasks, using bit-vector encodings and operations. The applicability of our approach to Machine Perception is evaluated on a smart-phone mobile device, demonstrating dramatic improvements in both efficiency and scale.
-
an ontological approach to focusing attention and enhancing Machine Perception on the web
Applied Ontology, 2011Co-Authors: Cory Henson, Krishnaprasad Thirunarayan, Amit P ShethAbstract:Today, many sensor networks and their applications employ a brute force approach to collecting and analyzing sensor data. Such an approach often wastes valuable energy and computational resources by unnecessarily tasking sensors and generating observations of minimal use. People, on the other hand, have evolved sophisticated mechanisms to efficiently perceive their environment. One such mechanism includes the use of background knowledge to determine what aspects of the environment to focus our attention. In this paper, we develop an ontology of Perception, IntellegO, that may be used to more efficiently convert observations into Perceptions. IntellegO is derived from cognitive theory, encoded in set-theory, and provides a formal semantics of Machine Perception. We then present an implementation that iteratively and efficiently processes low level, heterogeneous sensor data into knowledge through use of the Perception ontology and domain specific background knowledge. Finally, we evaluate IntellegO by collecting and analyzing observations of weather conditions on the Web, and show significant resource savings in the generation and storage of perceptual knowledge.
Cory Henson - One of the best experts on this subject based on the ideXlab platform.
-
"A semantics-based approach to Machine Perception" by Cory Andrew Henson, with Prateek Jain as coordinator
ACM SIGWEB Newsletter, 2014Co-Authors: Cory HensonAbstract:Machine Perception can be formalized using semantic web technologies in order to derive abstractions from sensor data using background knowledge on the Web, and efficiently executed on resource-constrained devices.
-
an efficient bit vector approach to semantics based Machine Perception in resource constrained devices
International Semantic Web Conference, 2012Co-Authors: Cory Henson, Krishnaprasad Thirunarayan, Amit P ShethAbstract:The primary challenge of Machine Perception is to define efficient computational methods to derive high-level knowledge from low-level sensor observation data. Emerging solutions are using ontologies for expressive representation of concepts in the domain of sensing and Perception, which enable advanced integration and interpretation of heterogeneous sensor data. The computational complexity of OWL, however, seriously limits its applicability and use within resource-constrained environments, such as mobile devices. To overcome this issue, we employ OWL to formally define the inference tasks needed for Machine Perception --- explanation and discrimination --- and then provide efficient algorithms for these tasks, using bit-vector encodings and operations. The applicability of our approach to Machine Perception is evaluated on a smart-phone mobile device, demonstrating dramatic improvements in both efficiency and scale.
-
International Semantic Web Conference (1) - An efficient bit vector approach to semantics-based Machine Perception in resource-constrained devices
The Semantic Web – ISWC 2012, 2012Co-Authors: Cory Henson, Krishnaprasad Thirunarayan, Amit P ShethAbstract:The primary challenge of Machine Perception is to define efficient computational methods to derive high-level knowledge from low-level sensor observation data. Emerging solutions are using ontologies for expressive representation of concepts in the domain of sensing and Perception, which enable advanced integration and interpretation of heterogeneous sensor data. The computational complexity of OWL, however, seriously limits its applicability and use within resource-constrained environments, such as mobile devices. To overcome this issue, we employ OWL to formally define the inference tasks needed for Machine Perception --- explanation and discrimination --- and then provide efficient algorithms for these tasks, using bit-vector encodings and operations. The applicability of our approach to Machine Perception is evaluated on a smart-phone mobile device, demonstrating dramatic improvements in both efficiency and scale.
-
an ontological approach to focusing attention and enhancing Machine Perception on the web
Applied Ontology, 2011Co-Authors: Cory Henson, Krishnaprasad Thirunarayan, Amit P ShethAbstract:Today, many sensor networks and their applications employ a brute force approach to collecting and analyzing sensor data. Such an approach often wastes valuable energy and computational resources by unnecessarily tasking sensors and generating observations of minimal use. People, on the other hand, have evolved sophisticated mechanisms to efficiently perceive their environment. One such mechanism includes the use of background knowledge to determine what aspects of the environment to focus our attention. In this paper, we develop an ontology of Perception, IntellegO, that may be used to more efficiently convert observations into Perceptions. IntellegO is derived from cognitive theory, encoded in set-theory, and provides a formal semantics of Machine Perception. We then present an implementation that iteratively and efficiently processes low level, heterogeneous sensor data into knowledge through use of the Perception ontology and domain specific background knowledge. Finally, we evaluate IntellegO by collecting and analyzing observations of weather conditions on the Web, and show significant resource savings in the generation and storage of perceptual knowledge.
Guyeon Wei - One of the best experts on this subject based on the ideXlab platform.
-
a 3mm 2 programmable bayesian inference accelerator for unsupervised Machine Perception using parallel gibbs sampling in 16nm
Symposium on VLSI Circuits, 2020Co-Authors: Yuji Chai, Marco Donato, Paul N Whatmough, Thierry Tambe, Rob A Rutenbar, David Brooks, Guyeon WeiAbstract:This paper describes a 16nm programmable accelerator for unsupervised probabilistic Machine Perception tasks that performs Bayesian inference on probabilistic models mapped onto a 2D Markov Random Field, using MCMC. Exploiting two degrees of parallelism, it performs Gibbs sampling inference at up to 1380× faster with 1965× less energy than an Arm Cortex-A53 on the same SoC, and 1.5× faster with 6.3× less energy than an embedded FPGA in the same technology. At 0.8V, it runs at 450MHz, producing 44.6 MSamples/s at 0.88 nJ/sample.
-
VLSI Circuits - A 3mm 2 Programmable Bayesian Inference Accelerator for Unsupervised Machine Perception using Parallel Gibbs Sampling in 16nm
2020 IEEE Symposium on VLSI Circuits, 2020Co-Authors: Yuji Chai, Marco Donato, Paul N Whatmough, Thierry Tambe, Rob A Rutenbar, David Brooks, Guyeon WeiAbstract:This paper describes a 16nm programmable accelerator for unsupervised probabilistic Machine Perception tasks that performs Bayesian inference on probabilistic models mapped onto a 2D Markov Random Field, using MCMC. Exploiting two degrees of parallelism, it performs Gibbs sampling inference at up to 1380× faster with 1965× less energy than an Arm Cortex-A53 on the same SoC, and 1.5× faster with 6.3× less energy than an embedded FPGA in the same technology. At 0.8V, it runs at 450MHz, producing 44.6 MSamples/s at 0.88 nJ/sample.
Hyungtae Lee - One of the best experts on this subject based on the ideXlab platform.
-
task conversions for integrating human and Machine Perception in a unified task
Intelligent Robots and Systems, 2016Co-Authors: Hyungtae Lee, Heesung Kwon, Ryan M Robinson, Daniel Donavanik, William D Nothwang, Amar R MaratheAbstract:The different strategies for feature extraction and synthesis employed by humans and computers are often complementary, hence combining the two into an integrated object recognition system may considerably improve performance over either used in isolation. Rapid Serial Visual Presentation (RSVP) is one well-established technique that has shown promise integrating human Perception into a Machine Perception system. In this paper, we apply computer vision techniques to image data filtered through human RSVP. We introduce “task conversions” to integrate the two modalities, applying the precise localization capabilities of computer vision with the detection capabilities of RSVP. We employ naive Bayesian fusion and a novel method, dynamic belief fusion (DBF), in a joint scheme as fusion approaches. Preliminary experiments demonstrate that DBF extracts complementary information from both human and Machine sources to improve performance for both target classification and object detection.
-
IROS - Task-conversions for integrating human and Machine Perception in a unified task
2016 IEEE RSJ International Conference on Intelligent Robots and Systems (IROS), 2016Co-Authors: Hyungtae Lee, Heesung Kwon, Ryan M Robinson, Daniel Donavanik, William D Nothwang, Amar R MaratheAbstract:The different strategies for feature extraction and synthesis employed by humans and computers are often complementary, hence combining the two into an integrated object recognition system may considerably improve performance over either used in isolation. Rapid Serial Visual Presentation (RSVP) is one well-established technique that has shown promise integrating human Perception into a Machine Perception system. In this paper, we apply computer vision techniques to image data filtered through human RSVP. We introduce “task conversions” to integrate the two modalities, applying the precise localization capabilities of computer vision with the detection capabilities of RSVP. We employ naive Bayesian fusion and a novel method, dynamic belief fusion (DBF), in a joint scheme as fusion approaches. Preliminary experiments demonstrate that DBF extracts complementary information from both human and Machine sources to improve performance for both target classification and object detection.