Sorry, you need to enable JavaScript to visit this website.

Other applications of machine learning (MLR-APPL)

Compressing Unstructured Mesh Data Using Spline Fits, Compressed Sensing, and Regression Methods


Compressing unstructured mesh data from computer simulations poses several challenges that are not encountered in the compression of images or videos. Since the spatial locations of the points are not on a regular grid, as in an image, it is difficult to identify near neighbors of a point whose values can be exploited for compression.

Paper Details

Authors:
Chandrika Kamath, Ya Ju Fan
Submitted On:
3 December 2018 - 5:12pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Kamath_ComparingCompression_final.pdf

Subscribe

[1] Chandrika Kamath, Ya Ju Fan, "Compressing Unstructured Mesh Data Using Spline Fits, Compressed Sensing, and Regression Methods", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3839. Accessed: Mar. 26, 2019.
@article{3839-18,
url = {http://sigport.org/3839},
author = {Chandrika Kamath; Ya Ju Fan },
publisher = {IEEE SigPort},
title = {Compressing Unstructured Mesh Data Using Spline Fits, Compressed Sensing, and Regression Methods},
year = {2018} }
TY - EJOUR
T1 - Compressing Unstructured Mesh Data Using Spline Fits, Compressed Sensing, and Regression Methods
AU - Chandrika Kamath; Ya Ju Fan
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3839
ER -
Chandrika Kamath, Ya Ju Fan. (2018). Compressing Unstructured Mesh Data Using Spline Fits, Compressed Sensing, and Regression Methods. IEEE SigPort. http://sigport.org/3839
Chandrika Kamath, Ya Ju Fan, 2018. Compressing Unstructured Mesh Data Using Spline Fits, Compressed Sensing, and Regression Methods. Available at: http://sigport.org/3839.
Chandrika Kamath, Ya Ju Fan. (2018). "Compressing Unstructured Mesh Data Using Spline Fits, Compressed Sensing, and Regression Methods." Web.
1. Chandrika Kamath, Ya Ju Fan. Compressing Unstructured Mesh Data Using Spline Fits, Compressed Sensing, and Regression Methods [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3839

Self-Supervised Anomaly Detection for Narrowband SETI Presentation

Paper Details

Authors:
Ki Hyun, Seungwoo Son, Steve Croft, Andrew Siemion
Submitted On:
29 November 2018 - 8:40pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

zhang_globalsip2018.pdf

Subscribe

[1] Ki Hyun, Seungwoo Son, Steve Croft, Andrew Siemion, "Self-Supervised Anomaly Detection for Narrowband SETI Presentation", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3833. Accessed: Mar. 26, 2019.
@article{3833-18,
url = {http://sigport.org/3833},
author = {Ki Hyun; Seungwoo Son; Steve Croft; Andrew Siemion },
publisher = {IEEE SigPort},
title = {Self-Supervised Anomaly Detection for Narrowband SETI Presentation},
year = {2018} }
TY - EJOUR
T1 - Self-Supervised Anomaly Detection for Narrowband SETI Presentation
AU - Ki Hyun; Seungwoo Son; Steve Croft; Andrew Siemion
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3833
ER -
Ki Hyun, Seungwoo Son, Steve Croft, Andrew Siemion. (2018). Self-Supervised Anomaly Detection for Narrowband SETI Presentation. IEEE SigPort. http://sigport.org/3833
Ki Hyun, Seungwoo Son, Steve Croft, Andrew Siemion, 2018. Self-Supervised Anomaly Detection for Narrowband SETI Presentation. Available at: http://sigport.org/3833.
Ki Hyun, Seungwoo Son, Steve Croft, Andrew Siemion. (2018). "Self-Supervised Anomaly Detection for Narrowband SETI Presentation." Web.
1. Ki Hyun, Seungwoo Son, Steve Croft, Andrew Siemion. Self-Supervised Anomaly Detection for Narrowband SETI Presentation [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3833

RANDOM ENSEMBLE OF LOCALLY OPTIMUM DETECTORS FOR DETECTION OF ADVERSARIAL EXAMPLES

Paper Details

Authors:
Amish Goel, Pierre Moulin
Submitted On:
25 November 2018 - 12:48pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Poster_GlobalSIP.pdf

Subscribe

[1] Amish Goel, Pierre Moulin, "RANDOM ENSEMBLE OF LOCALLY OPTIMUM DETECTORS FOR DETECTION OF ADVERSARIAL EXAMPLES", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3774. Accessed: Mar. 26, 2019.
@article{3774-18,
url = {http://sigport.org/3774},
author = {Amish Goel; Pierre Moulin },
publisher = {IEEE SigPort},
title = {RANDOM ENSEMBLE OF LOCALLY OPTIMUM DETECTORS FOR DETECTION OF ADVERSARIAL EXAMPLES},
year = {2018} }
TY - EJOUR
T1 - RANDOM ENSEMBLE OF LOCALLY OPTIMUM DETECTORS FOR DETECTION OF ADVERSARIAL EXAMPLES
AU - Amish Goel; Pierre Moulin
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3774
ER -
Amish Goel, Pierre Moulin. (2018). RANDOM ENSEMBLE OF LOCALLY OPTIMUM DETECTORS FOR DETECTION OF ADVERSARIAL EXAMPLES. IEEE SigPort. http://sigport.org/3774
Amish Goel, Pierre Moulin, 2018. RANDOM ENSEMBLE OF LOCALLY OPTIMUM DETECTORS FOR DETECTION OF ADVERSARIAL EXAMPLES. Available at: http://sigport.org/3774.
Amish Goel, Pierre Moulin. (2018). "RANDOM ENSEMBLE OF LOCALLY OPTIMUM DETECTORS FOR DETECTION OF ADVERSARIAL EXAMPLES." Web.
1. Amish Goel, Pierre Moulin. RANDOM ENSEMBLE OF LOCALLY OPTIMUM DETECTORS FOR DETECTION OF ADVERSARIAL EXAMPLES [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3774

Tensor Ensemble Learning


In big data applications, classical ensemble learning is typically infeasible on the raw input data and dimensionality reduction techniques are necessary. To this end, novel framework that generalises classic flat-view ensemble learning to multidimensional tensor- valued data is introduced. This is achieved by virtue of tensor decompositions, whereby the proposed method, referred to as tensor ensemble learning (TEL), decomposes every input data sample into multiple factors which allows for a flexibility in the choice of multiple learning algorithms in order to improve test performance.

Paper Details

Authors:
Ahmad Moniri
Submitted On:
23 November 2018 - 1:09pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

IK_AM_DPM_GlobalSIP_2018_presentation.pdf

Keywords

Additional Categories

Subscribe

[1] Ahmad Moniri, "Tensor Ensemble Learning", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3751. Accessed: Mar. 26, 2019.
@article{3751-18,
url = {http://sigport.org/3751},
author = {Ahmad Moniri },
publisher = {IEEE SigPort},
title = {Tensor Ensemble Learning},
year = {2018} }
TY - EJOUR
T1 - Tensor Ensemble Learning
AU - Ahmad Moniri
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3751
ER -
Ahmad Moniri. (2018). Tensor Ensemble Learning. IEEE SigPort. http://sigport.org/3751
Ahmad Moniri, 2018. Tensor Ensemble Learning. Available at: http://sigport.org/3751.
Ahmad Moniri. (2018). "Tensor Ensemble Learning." Web.
1. Ahmad Moniri. Tensor Ensemble Learning [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3751

Backdoor Attacks on Neural Network Operations


Machine learning is a rapidly growing field that has been expanding into various aspects of technology and science in recent years. Unfortunately, it has been shown recently that machine learning models are highly vulnerable to well-crafted adversarial attacks. This paper develops a novel method for maliciously inserting a backdoor into a well-trained neural network causing misclassification that is only active under rare input keys.

Paper Details

Authors:
Yingjie Lao
Submitted On:
22 November 2018 - 6:26pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

GlobalSIP2018Joseph.pdf

Subscribe

[1] Yingjie Lao, "Backdoor Attacks on Neural Network Operations", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3721. Accessed: Mar. 26, 2019.
@article{3721-18,
url = {http://sigport.org/3721},
author = {Yingjie Lao },
publisher = {IEEE SigPort},
title = {Backdoor Attacks on Neural Network Operations},
year = {2018} }
TY - EJOUR
T1 - Backdoor Attacks on Neural Network Operations
AU - Yingjie Lao
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3721
ER -
Yingjie Lao. (2018). Backdoor Attacks on Neural Network Operations. IEEE SigPort. http://sigport.org/3721
Yingjie Lao, 2018. Backdoor Attacks on Neural Network Operations. Available at: http://sigport.org/3721.
Yingjie Lao. (2018). "Backdoor Attacks on Neural Network Operations." Web.
1. Yingjie Lao. Backdoor Attacks on Neural Network Operations [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3721

Differentially Private Sparse Inverse Covariance Estimation

Paper Details

Authors:
Mengdi Huai, Jinhui Xu
Submitted On:
20 November 2018 - 4:05pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

private_sparse_inverse.pdf

Subscribe

[1] Mengdi Huai, Jinhui Xu, "Differentially Private Sparse Inverse Covariance Estimation ", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3694. Accessed: Mar. 26, 2019.
@article{3694-18,
url = {http://sigport.org/3694},
author = {Mengdi Huai; Jinhui Xu },
publisher = {IEEE SigPort},
title = {Differentially Private Sparse Inverse Covariance Estimation },
year = {2018} }
TY - EJOUR
T1 - Differentially Private Sparse Inverse Covariance Estimation
AU - Mengdi Huai; Jinhui Xu
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3694
ER -
Mengdi Huai, Jinhui Xu. (2018). Differentially Private Sparse Inverse Covariance Estimation . IEEE SigPort. http://sigport.org/3694
Mengdi Huai, Jinhui Xu, 2018. Differentially Private Sparse Inverse Covariance Estimation . Available at: http://sigport.org/3694.
Mengdi Huai, Jinhui Xu. (2018). "Differentially Private Sparse Inverse Covariance Estimation ." Web.
1. Mengdi Huai, Jinhui Xu. Differentially Private Sparse Inverse Covariance Estimation [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3694

A TWO-STEP LEARNING METHOD FOR DETECTING LANDMARKS ON FACES FROM DIFFERENT DOMAINS

Paper Details

Authors:
Bruna Frade, Erickson Naecimento
Submitted On:
8 October 2018 - 2:49am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICIP18_Poster.pdf

Keywords

Additional Categories

Subscribe

[1] Bruna Frade, Erickson Naecimento, "A TWO-STEP LEARNING METHOD FOR DETECTING LANDMARKS ON FACES FROM DIFFERENT DOMAINS", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3610. Accessed: Mar. 26, 2019.
@article{3610-18,
url = {http://sigport.org/3610},
author = {Bruna Frade; Erickson Naecimento },
publisher = {IEEE SigPort},
title = {A TWO-STEP LEARNING METHOD FOR DETECTING LANDMARKS ON FACES FROM DIFFERENT DOMAINS},
year = {2018} }
TY - EJOUR
T1 - A TWO-STEP LEARNING METHOD FOR DETECTING LANDMARKS ON FACES FROM DIFFERENT DOMAINS
AU - Bruna Frade; Erickson Naecimento
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3610
ER -
Bruna Frade, Erickson Naecimento. (2018). A TWO-STEP LEARNING METHOD FOR DETECTING LANDMARKS ON FACES FROM DIFFERENT DOMAINS. IEEE SigPort. http://sigport.org/3610
Bruna Frade, Erickson Naecimento, 2018. A TWO-STEP LEARNING METHOD FOR DETECTING LANDMARKS ON FACES FROM DIFFERENT DOMAINS. Available at: http://sigport.org/3610.
Bruna Frade, Erickson Naecimento. (2018). "A TWO-STEP LEARNING METHOD FOR DETECTING LANDMARKS ON FACES FROM DIFFERENT DOMAINS." Web.
1. Bruna Frade, Erickson Naecimento. A TWO-STEP LEARNING METHOD FOR DETECTING LANDMARKS ON FACES FROM DIFFERENT DOMAINS [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3610

SEMI-SUPERVISED LEARNING OF CAMERA MOTION FROM A BLURRED IMAGE


We address the problem of camera motion estimation from a single blurred image with the aid of deep convolutional neural networks.
Unlike learning-based prior works that estimate a space-invariant blur kernel, we solve for the global camera motion which in turn

Paper Details

Authors:
Nimisha T M, Vijay Rengarajan, Rajagopalan Ambasamudram
Submitted On:
6 October 2018 - 8:47am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

SEMI-SUPERVISED LEARNING OF CAMERA MOTION FROM A BLURRED IMAGE.pdf

Keywords

Additional Categories

Subscribe

[1] Nimisha T M, Vijay Rengarajan, Rajagopalan Ambasamudram, "SEMI-SUPERVISED LEARNING OF CAMERA MOTION FROM A BLURRED IMAGE", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3575. Accessed: Mar. 26, 2019.
@article{3575-18,
url = {http://sigport.org/3575},
author = {Nimisha T M; Vijay Rengarajan; Rajagopalan Ambasamudram },
publisher = {IEEE SigPort},
title = {SEMI-SUPERVISED LEARNING OF CAMERA MOTION FROM A BLURRED IMAGE},
year = {2018} }
TY - EJOUR
T1 - SEMI-SUPERVISED LEARNING OF CAMERA MOTION FROM A BLURRED IMAGE
AU - Nimisha T M; Vijay Rengarajan; Rajagopalan Ambasamudram
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3575
ER -
Nimisha T M, Vijay Rengarajan, Rajagopalan Ambasamudram. (2018). SEMI-SUPERVISED LEARNING OF CAMERA MOTION FROM A BLURRED IMAGE. IEEE SigPort. http://sigport.org/3575
Nimisha T M, Vijay Rengarajan, Rajagopalan Ambasamudram, 2018. SEMI-SUPERVISED LEARNING OF CAMERA MOTION FROM A BLURRED IMAGE. Available at: http://sigport.org/3575.
Nimisha T M, Vijay Rengarajan, Rajagopalan Ambasamudram. (2018). "SEMI-SUPERVISED LEARNING OF CAMERA MOTION FROM A BLURRED IMAGE." Web.
1. Nimisha T M, Vijay Rengarajan, Rajagopalan Ambasamudram. SEMI-SUPERVISED LEARNING OF CAMERA MOTION FROM A BLURRED IMAGE [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3575

Trajectory Optimization for Autonomous Flying Base Station via Reinforcement Learning


In this work, we study the optimal trajectory of an unmanned aerial vehicle (UAV) acting as a base station (BS) to serve multiple users. Considering multiple flying epochs, we leverage the tools of reinforcement learning (RL) with the UAV acting as an autonomous agent in the environment to learn the trajectory that maximizes the sum rate of the transmission during flying time. By applying Q-learning, a model-free RL technique, an agent is trained to make movement decisions for the UAV. We compare table-based and neural network (NN) approximations of the Q-function and analyze the results.

Paper Details

Authors:
Harald Bayerlein, Paul de Kerret, David Gesbert
Submitted On:
3 July 2018 - 10:13am
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

Poster_SPAWC2018_final.pdf

Subscribe

[1] Harald Bayerlein, Paul de Kerret, David Gesbert, "Trajectory Optimization for Autonomous Flying Base Station via Reinforcement Learning", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3299. Accessed: Mar. 26, 2019.
@article{3299-18,
url = {http://sigport.org/3299},
author = {Harald Bayerlein; Paul de Kerret; David Gesbert },
publisher = {IEEE SigPort},
title = {Trajectory Optimization for Autonomous Flying Base Station via Reinforcement Learning},
year = {2018} }
TY - EJOUR
T1 - Trajectory Optimization for Autonomous Flying Base Station via Reinforcement Learning
AU - Harald Bayerlein; Paul de Kerret; David Gesbert
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3299
ER -
Harald Bayerlein, Paul de Kerret, David Gesbert. (2018). Trajectory Optimization for Autonomous Flying Base Station via Reinforcement Learning. IEEE SigPort. http://sigport.org/3299
Harald Bayerlein, Paul de Kerret, David Gesbert, 2018. Trajectory Optimization for Autonomous Flying Base Station via Reinforcement Learning. Available at: http://sigport.org/3299.
Harald Bayerlein, Paul de Kerret, David Gesbert. (2018). "Trajectory Optimization for Autonomous Flying Base Station via Reinforcement Learning." Web.
1. Harald Bayerlein, Paul de Kerret, David Gesbert. Trajectory Optimization for Autonomous Flying Base Station via Reinforcement Learning [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3299

On Deep Learning-based Massive MIMO Indoor User Localization


We examine the usability of deep neural networks for multiple-input multiple-output (MIMO) user positioning solely based on the orthogonal frequency division multiplex (OFDM) complex channel coefficients. In contrast to other indoor positioning systems (IPSs), the proposed method does not require any additional piloting overhead or any other changes in the communications system itself as it is deployed on top of an existing OFDM MIMO system. Supported by actual measurements, we are mainly interested in the more challenging non-line of sight (NLoS) scenario.

Paper Details

Authors:
Maximilian Arnold, Stephan ten Brink
Submitted On:
21 June 2018 - 11:57am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

spawc_positioning_poster.pdf

Subscribe

[1] Maximilian Arnold, Stephan ten Brink, "On Deep Learning-based Massive MIMO Indoor User Localization", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3286. Accessed: Mar. 26, 2019.
@article{3286-18,
url = {http://sigport.org/3286},
author = {Maximilian Arnold; Stephan ten Brink },
publisher = {IEEE SigPort},
title = {On Deep Learning-based Massive MIMO Indoor User Localization},
year = {2018} }
TY - EJOUR
T1 - On Deep Learning-based Massive MIMO Indoor User Localization
AU - Maximilian Arnold; Stephan ten Brink
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3286
ER -
Maximilian Arnold, Stephan ten Brink. (2018). On Deep Learning-based Massive MIMO Indoor User Localization. IEEE SigPort. http://sigport.org/3286
Maximilian Arnold, Stephan ten Brink, 2018. On Deep Learning-based Massive MIMO Indoor User Localization. Available at: http://sigport.org/3286.
Maximilian Arnold, Stephan ten Brink. (2018). "On Deep Learning-based Massive MIMO Indoor User Localization." Web.
1. Maximilian Arnold, Stephan ten Brink. On Deep Learning-based Massive MIMO Indoor User Localization [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3286

Pages