Publications

Refine Results

(Filters Applied) Clear All

Building low-power trustworthy systems: cyber-security considerations for real-time physiological status monitoring

November 1, 2016
  |
Conference Paper
Author:
John Holliman
…
Published in:
IEEE MILCOM, 1-3 November 2016.
Topic:
systems analysis
R&D area:
R&D group:

Summary

Real-time monitoring of physiological data can reduce the likelihood of injury in noncombat military personnel and first-responders. MIT Lincoln Laboratory is developing a tactical Real-Time Physiological Status Monitoring (RT-PSM) system architecture and reference implementation named OBAN (Open Body Area Network), the purpose of which is to provide an open, government-owned framework for integrating multiple wearable sensors and applications. The OBAN implementation accepts data from various sensors enabling calculation of physiological strain information which may be used by squad leaders or medics to assess the team's health and enhance safety and effectiveness of mission execution. Security in terms of measurement integrity, confidentiality, and authenticity is an area of interest because OBAN system components exchange sensitive data in contested environments. In this paper, we analyze potential cyber-security threats and their associated risks to a generalized version of the OBAN architecture and identify directions for future research. The threat analysis is intended to inform the development of secure RT-PSM architectures and implementations.
READ LESS

Summary

Real-time monitoring of physiological data can reduce the likelihood of injury in noncombat military personnel and first-responders. MIT Lincoln Laboratory is developing a tactical Real-Time Physiological Status Monitoring (RT-PSM) system architecture and reference implementation named OBAN (Open Body Area Network), the purpose of which is to provide an open, government-owned...

READ MORE
Building low-power trustworthy systems: cyber-security considerations for real-time physiological status monitoring

Writing your first paper: from code to research

October 19, 2016
  |
Conference Paper
Author:
Kara B. Greenfield
Published in:
Grace Hopper Celebration of Women in Computing, 19-21 October 2016.
Topic:
mentorship
R&D area:
R&D group:

Summary

'Publish or perish,' once a term used to refer to the pressure placed on professors to publish their research has since expanded to apply to students and professionals in industry. There are numerous benefits to doing research and publishing the results, including personal satisfaction, career advancement, and prestige. In this session we will discuss how to begin doing research and write a first paper.
READ LESS

Summary

'Publish or perish,' once a term used to refer to the pressure placed on professors to publish their research has since expanded to apply to students and professionals in industry. There are numerous benefits to doing research and publishing the results, including personal satisfaction, career advancement, and prestige. In this...

READ MORE
Writing your first paper: from code to research

Multi-modal audio, video and physiological sensor learning for continuous emotion prediction

October 16, 2016
  |
Conference Paper
Author:
Kevin Brady
…
Published in:
ACM Multimedia Conf. AVEC Workshop, 15-19 October 2016.
Topic:
biometrics
R&D area:
R&D group:

Summary

The automatic determination of emotional state from multimedia content is an inherently challenging problem with a broad range of applications including biomedical diagnostics, multimedia retrieval, and human computer interfaces. The Audio Video Emotion Challenge (AVEC) 2016 provides a well-defined framework for developing and rigorously evaluating innovative approaches for estimating the arousal and valence states of emotion as a function of time. It presents the opportunity for investigating multimodal solutions that include audio, video, and physiological sensor signals. This paper provides an overview of our AVEC Emotion Challenge system, which uses multi-feature learning and fusion across all available modalities. It includes a number of technical contributions, including the development of novel high- and low-level features for modeling emotion in the audio, video, and physiological channels. Low-level features include modeling arousal in audio with minimal prosodic-based descriptors. High-level features are derived from supervised and unsupervised machine learning approaches based on sparse coding and deep learning. Finally, a state space estimation approach is applied for score fusion that demonstrates the importance of exploiting the time-series nature of the arousal and valence states. The resulting system outperforms the baseline systems [10] on the test evaluation set with an achieved Concordant Correlation Coefficient (CCC) for arousal of 0.770 vs 0.702 (baseline) and for valence of 0.687 vs 0.638. Future work will focus on exploiting the time-varying nature of individual channels in the multi-modal framework.
READ LESS

Summary

The automatic determination of emotional state from multimedia content is an inherently challenging problem with a broad range of applications including biomedical diagnostics, multimedia retrieval, and human computer interfaces. The Audio Video Emotion Challenge (AVEC) 2016 provides a well-defined framework for developing and rigorously evaluating innovative approaches for estimating the...

READ MORE
Multi-modal audio, video and physiological sensor learning for continuous emotion prediction

Detecting depression using vocal, facial and semantic communication cues

October 15, 2016
  |
Conference Paper
Author:
James R. Williamson
…
Published in:
ACM Multimedia Conf. AVEC Workshop, 15-19 October 2016.
Topic:
biometrics
R&D area:
R&D group:

Summary

Major depressive disorder (MDD) is known to result in neurophysiological and neurocognitive changes that affect control of motor, linguistic, and cognitive functions. MDD's impact on these processes is reflected in an individual's communication via coupled mechanisms: vocal articulation, facial gesturing and choice of content to convey in a dialogue. In particular, MDD-induced neurophysiological changes are associated with a decline in dynamics and coordination of speech and facial motor control, while neurocognitive changes influence dialogue semantics. In this paper, biomarkers are derived from all of these modalities, drawing first from previously developed neurophysiologically motivated speech and facial coordination and timing features. In addition, a novel indicator of lower vocal tract constriction in articulation is incorporated that relates to vocal projection. Semantic features are analyzed for subject/avatar dialogue content using a sparse coded lexical embedding space, and for contextual clues related to the subject's present or past depression status. The features and depression classification system were developed for the 6th International Audio/Video Emotion Challenge (AVEC), which provides data consisting of audio, video-based facial action units, and transcribed text of individuals communicating with the human-controlled avatar. A clinical Patient Health Questionnaire (PHQ) score and binary depression decision are provided for each participant. PHQ predictions were obtained by fusing outputs from a Gaussian staircase regressor for each feature set, with results on the development set of mean F1=0.81, RMSE=5.31, and MAE=3.34. These compare favorably to the challenge baseline development results of mean F1=0.73, RMSE=6.62, and MAE=5.52. On test set evaluation, our system obtained a mean F1=0.70, which is similar to the challenge baseline test result. Future work calls for consideration of joint feature analyses across modalities in an effort to detect neurological disorders based on the interplay of motor, linguistic, affective, and cognitive components of communication.
READ LESS

Summary

Major depressive disorder (MDD) is known to result in neurophysiological and neurocognitive changes that affect control of motor, linguistic, and cognitive functions. MDD's impact on these processes is reflected in an individual's communication via coupled mechanisms: vocal articulation, facial gesturing and choice of content to convey in a dialogue. In...

READ MORE
Detecting depression using vocal, facial and semantic communication cues

Side channel authenticity discriminant analysis for device class identification

September 25, 2016
  |
Conference Paper
Author:
Eric A. Koziel
…
Published in:
ICIP: 2016 IEEE Int. Conf. on Image Processing, 25-28 September 2016.
Topic:
systems architecture
R&D area:
R&D group:

Summary

Counterfeit microelectronics present a significant challenge to commercial and defense supply chains. Many modern anti-counterfeit strategies rely on manufacturer cooperation to include additional identification components. We instead propose Side Channel Authenticity Discriminant Analysis (SICADA) to leverage physical phenomena manifesting from device operation to match suspect parts to a class of authentic parts. This paper examines the extent that power dissipation information can be used to separate unique classes of devices. A methodology for distinguishing device types is presented and tested on both simulation data of a custom circuit and empirical measurements of Microchip dsPIC33F microcontrollers. Experimental results show that power side channels contain significant distinguishing information to identify parts as authentic or suspect counterfeit.
READ LESS

Summary

Counterfeit microelectronics present a significant challenge to commercial and defense supply chains. Many modern anti-counterfeit strategies rely on manufacturer cooperation to include additional identification components. We instead propose Side Channel Authenticity Discriminant Analysis (SICADA) to leverage physical phenomena manifesting from device operation to match suspect parts to a class of...

READ MORE
Side channel authenticity discriminant analysis for device class identification

How deep neural networks can improve emotion recognition on video data

September 25, 2016
  |
Conference Paper
Author:
Pooya R. Khorrami
…
Published in:
ICIP: 2016 IEEE Int. Conf. on Image Processing, 25-28 September 2016.
Topic:
biometrics
R&D area:
R&D group:

Summary

We consider the task of dimensional emotion recognition on video data using deep learning. While several previous methods have shown the benefits of training temporal neural network models such as recurrent neural networks (RNNs) on hand-crafted features, few works have considered combining convolutional neural networks (CNNs) with RNNs. In this work, we present a system that performs emotion recognition on video data using both CNNs and RNNs, and we also analyze how much each neural network component contributes to the system's overall performance. We present our findings on videos from the Audio/Visual+Emotion Challenge (AV+EC2015). In our experiments, we analyze the effects of several hyperparameters on overall performance while also achieving superior performance to the baseline and other competing methods.
READ LESS

Summary

We consider the task of dimensional emotion recognition on video data using deep learning. While several previous methods have shown the benefits of training temporal neural network models such as recurrent neural networks (RNNs) on hand-crafted features, few works have considered combining convolutional neural networks (CNNs) with RNNs. In this...

READ MORE
How deep neural networks can improve emotion recognition on video data

High-throughput ingest of data provenance records in Accumulo

September 13, 2016
  |
Conference Paper
Author:
Thomas M. Moyer
…
Published in:
HPEC 2016: IEEE Conf. on High Performance Extreme Computing, 13-15 September 2016.
Topic:
supercomputing
R&D area:
R&D group:

Summary

Whole-system data provenance provides deep insight into the processing of data on a system, including detecting data integrity attacks. The downside to systems that collect whole-system data provenance is the sheer volume of data that is generated under many heavy workloads. In order to make provenance metadata useful, it must be stored somewhere where it can be queried. This problem becomes even more challenging when considering a network of provenance-aware machines all collecting this metadata. In this paper, we investigate the use of D4M and Accumulo to support high-throughput data ingest of whole-system provenance data. We find that we are able to ingest 3,970 graph components per second. Centrally storing the provenance metadata allows us to build systems that can detect and respond to data integrity attacks that are captured by the provenance system.
READ LESS

Summary

Whole-system data provenance provides deep insight into the processing of data on a system, including detecting data integrity attacks. The downside to systems that collect whole-system data provenance is the sheer volume of data that is generated under many heavy workloads. In order to make provenance metadata useful, it must...

READ MORE
High-throughput ingest of data provenance records in Accumulo

High-throughput ingest of data provenance records in Accumulo

September 13, 2016
  |
Conference Paper
Author:
Thomas M. Moyer
…
Published in:
HPEC 2016: IEEE Conf. on High Performance Extreme Computing, 13-15 September 2016.
Topic:
supercomputing
R&D area:
R&D group:

Summary

Whole-system data provenance provides deep insight into the processing of data on a system, including detecting data integrity attacks. The downside to systems that collect whole-system data provenance is the sheer volume of data that is generated under many heavy workloads. In order to make provenance metadata useful, it must be stored somewhere where it can be queried. This problem becomes even more challenging when considering a network of provenance-aware machines all collecting this metadata. In this paper, we investigate the use of D4M and Accumulo to support high-throughput data ingest of whole-system provenance data. We find that we are able to ingest 3,970 graph components per second. Centrally storing the provenance metadata allows us to build systems that can detect and respond to data integrity attacks that are captured by the provenance system.
READ LESS

Summary

Whole-system data provenance provides deep insight into the processing of data on a system, including detecting data integrity attacks. The downside to systems that collect whole-system data provenance is the sheer volume of data that is generated under many heavy workloads. In order to make provenance metadata useful, it must...

READ MORE
High-throughput ingest of data provenance records in Accumulo

I-vector speaker and language recognition system on Android

September 13, 2016
  |
Conference Paper
Author:
Christian Vazquez-Machado
…
Published in:
HPEC 2016: IEEE Conf. on High Performance Extreme Computing, 13-15 September 2016.
Topic:
language recognition
R&D area:
R&D group:

Summary

I-Vector based speaker and language identification provides state of the art performance. However, this comes as a more computationally complex solution, which can often lead to challenges in resource-limited devices, such as phones or tablets. We present the implementation of an I-Vector speaker and language recognition system on the Android platform in the form of a fully functional application that allows speaker enrollment and language/speaker scoring within mobile contexts. We include a detailed account of the challenges to port the system and its dependencies, which were necessary to optimize matrix operations in the I-Vector implementation. The system was benchmarked on a for a Google Nexus 6, showing a speed increase of 61.68% in scoring and 82.63% in enrollment operations with the implemented optimizations. The application was tested in mobile settings on a Nexus 7 tablet with forty participants, showing a rough accuracy of 84%. The optimized platform showed the capacity to perform near real-time recognition within a mobile setting and showcases the viability of I-Vector systems on resource-limited environments.
READ LESS

Summary

I-Vector based speaker and language identification provides state of the art performance. However, this comes as a more computationally complex solution, which can often lead to challenges in resource-limited devices, such as phones or tablets. We present the implementation of an I-Vector speaker and language recognition system on the Android...

READ MORE
I-vector speaker and language recognition system on Android

Sparse-coded net model and applications

September 13, 2016
  |
Conference Paper
Author:
Youngjune L. Gwon
…
Published in:
2016 IEEE Int. Workshop on Machine Learning for Signal Processing, 13-16 September 2016.
Topic:
artificial intelligence
R&D area:
R&D group:

Summary

As an unsupervised learning method, sparse coding can discover high-level representations for an input in a large variety of learning problems. Under semi-supervised settings, sparse coding is used to extract features for a supervised task such as classification. While sparse representations learned from unlabeled data independently of the supervised task perform well, we argue that sparse coding should also be built as a holistic learning unit optimizing on the supervised task objectives more explicitly. In this paper, we propose sparse-coded net, a feedforward model that integrates sparse coding and task-driven output layers, and describe training methods in detail. After pretraining a sparse-coded net via semi-supervised learning, we optimize its task-specific performance in a novel backpropagation algorithm that can traverse nonlinear feature pooling operators to update the dictionary. Thus, sparse-coded net can be applied to supervised dictionary learning. We evaluate sparse-coded net with classification problems in sound, image, and text data. The results confirm a significant improvement over semi-supervised learning as well as superior classification performance against deep stacked autoencoder neural network and GMM-SVM pipelines in small to medium-scale settings.
READ LESS

Summary

As an unsupervised learning method, sparse coding can discover high-level representations for an input in a large variety of learning problems. Under semi-supervised settings, sparse coding is used to extract features for a supervised task such as classification. While sparse representations learned from unlabeled data independently of the supervised task...

READ MORE
Sparse-coded net model and applications
161-170 of 809