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

Machine Learning for Signal Processing

Mobile Bayesian Spectrum Learning for Heterogeneous Networks


Spectrum sensing in heterogeneous networks is very challenging as it usually requires a large number of static secondary users (SUs) to obtain the global spectrum states. In this paper, we tackle the spectrum sensing in heterogeneous networks from a new perspective. We exploit the mobility of multiple SUs to simultaneously collect spatial-temporal spectrum sensing data. Then, we propose a novel non-parametric Bayesian learning model, referred to as beta process hidden Markov model to capture the spatio-temporal correlation in the collected spectrum data.

Paper Details

Authors:
Submitted On:
19 April 2018 - 3:01pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP Poster.pdf

(74 downloads)

Keywords

Subscribe

[1] , "Mobile Bayesian Spectrum Learning for Heterogeneous Networks", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3007. Accessed: Jun. 20, 2018.
@article{3007-18,
url = {http://sigport.org/3007},
author = { },
publisher = {IEEE SigPort},
title = {Mobile Bayesian Spectrum Learning for Heterogeneous Networks},
year = {2018} }
TY - EJOUR
T1 - Mobile Bayesian Spectrum Learning for Heterogeneous Networks
AU -
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3007
ER -
. (2018). Mobile Bayesian Spectrum Learning for Heterogeneous Networks. IEEE SigPort. http://sigport.org/3007
, 2018. Mobile Bayesian Spectrum Learning for Heterogeneous Networks. Available at: http://sigport.org/3007.
. (2018). "Mobile Bayesian Spectrum Learning for Heterogeneous Networks." Web.
1. . Mobile Bayesian Spectrum Learning for Heterogeneous Networks [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3007

ICASSP2018-SADL

Paper Details

Authors:
Submitted On:
19 April 2018 - 2:53pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP2018-SADL.pdf

(37 downloads)

Keywords

Subscribe

[1] , "ICASSP2018-SADL", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3005. Accessed: Jun. 20, 2018.
@article{3005-18,
url = {http://sigport.org/3005},
author = { },
publisher = {IEEE SigPort},
title = {ICASSP2018-SADL},
year = {2018} }
TY - EJOUR
T1 - ICASSP2018-SADL
AU -
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3005
ER -
. (2018). ICASSP2018-SADL. IEEE SigPort. http://sigport.org/3005
, 2018. ICASSP2018-SADL. Available at: http://sigport.org/3005.
. (2018). "ICASSP2018-SADL." Web.
1. . ICASSP2018-SADL [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3005

Deformation Stability of Deep Convolutional Neural Networks on Sobolev Spaces


Our work is based on a recently introduced mathematical theory of deep convolutional neural networks (DCNNs).
It was shown that DCNNs are stable with respect to deformations of bandlimited input functions.
In the present paper, we generalize this result: We prove deformation stability on Sobolev spaces.
Further, we show a weak form of deformation stability for the whole input space L2.
The basic components of DCNNs are semi-discrete frames.
For practical applications, a concrete choice is necessary.

talk.pdf

PDF icon talk.pdf (29 downloads)

Paper Details

Authors:
Michael Koller, Johannes Großmann, Ullrich Mönich, Holger Boche
Submitted On:
19 April 2018 - 2:26pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

talk.pdf

(29 downloads)

Keywords

Subscribe

[1] Michael Koller, Johannes Großmann, Ullrich Mönich, Holger Boche, "Deformation Stability of Deep Convolutional Neural Networks on Sobolev Spaces", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2996. Accessed: Jun. 20, 2018.
@article{2996-18,
url = {http://sigport.org/2996},
author = {Michael Koller; Johannes Großmann; Ullrich Mönich; Holger Boche },
publisher = {IEEE SigPort},
title = {Deformation Stability of Deep Convolutional Neural Networks on Sobolev Spaces},
year = {2018} }
TY - EJOUR
T1 - Deformation Stability of Deep Convolutional Neural Networks on Sobolev Spaces
AU - Michael Koller; Johannes Großmann; Ullrich Mönich; Holger Boche
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2996
ER -
Michael Koller, Johannes Großmann, Ullrich Mönich, Holger Boche. (2018). Deformation Stability of Deep Convolutional Neural Networks on Sobolev Spaces. IEEE SigPort. http://sigport.org/2996
Michael Koller, Johannes Großmann, Ullrich Mönich, Holger Boche, 2018. Deformation Stability of Deep Convolutional Neural Networks on Sobolev Spaces. Available at: http://sigport.org/2996.
Michael Koller, Johannes Großmann, Ullrich Mönich, Holger Boche. (2018). "Deformation Stability of Deep Convolutional Neural Networks on Sobolev Spaces." Web.
1. Michael Koller, Johannes Großmann, Ullrich Mönich, Holger Boche. Deformation Stability of Deep Convolutional Neural Networks on Sobolev Spaces [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2996

Language and Noise Transfer in Speech Enhancement Generative Adversarial Network

Paper Details

Authors:
Maruchan Park, Joan Serrà, Antonio Bonafonte, Kang-Hun Ahn
Submitted On:
19 April 2018 - 4:40pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

language-noise-transfer.pdf

(23 downloads)

Keywords

Subscribe

[1] Maruchan Park, Joan Serrà, Antonio Bonafonte, Kang-Hun Ahn, "Language and Noise Transfer in Speech Enhancement Generative Adversarial Network", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2979. Accessed: Jun. 20, 2018.
@article{2979-18,
url = {http://sigport.org/2979},
author = {Maruchan Park; Joan Serrà; Antonio Bonafonte; Kang-Hun Ahn },
publisher = {IEEE SigPort},
title = {Language and Noise Transfer in Speech Enhancement Generative Adversarial Network},
year = {2018} }
TY - EJOUR
T1 - Language and Noise Transfer in Speech Enhancement Generative Adversarial Network
AU - Maruchan Park; Joan Serrà; Antonio Bonafonte; Kang-Hun Ahn
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2979
ER -
Maruchan Park, Joan Serrà, Antonio Bonafonte, Kang-Hun Ahn. (2018). Language and Noise Transfer in Speech Enhancement Generative Adversarial Network. IEEE SigPort. http://sigport.org/2979
Maruchan Park, Joan Serrà, Antonio Bonafonte, Kang-Hun Ahn, 2018. Language and Noise Transfer in Speech Enhancement Generative Adversarial Network. Available at: http://sigport.org/2979.
Maruchan Park, Joan Serrà, Antonio Bonafonte, Kang-Hun Ahn. (2018). "Language and Noise Transfer in Speech Enhancement Generative Adversarial Network." Web.
1. Maruchan Park, Joan Serrà, Antonio Bonafonte, Kang-Hun Ahn. Language and Noise Transfer in Speech Enhancement Generative Adversarial Network [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2979

Bayesian inference for multi-line spectra in linear sensor array

Paper Details

Authors:
Submitted On:
19 April 2018 - 6:39pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

VietHung_ICASSP_2018.pdf

(31 downloads)

Keywords

Additional Categories

Subscribe

[1] , "Bayesian inference for multi-line spectra in linear sensor array", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2910. Accessed: Jun. 20, 2018.
@article{2910-18,
url = {http://sigport.org/2910},
author = { },
publisher = {IEEE SigPort},
title = {Bayesian inference for multi-line spectra in linear sensor array},
year = {2018} }
TY - EJOUR
T1 - Bayesian inference for multi-line spectra in linear sensor array
AU -
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2910
ER -
. (2018). Bayesian inference for multi-line spectra in linear sensor array. IEEE SigPort. http://sigport.org/2910
, 2018. Bayesian inference for multi-line spectra in linear sensor array. Available at: http://sigport.org/2910.
. (2018). "Bayesian inference for multi-line spectra in linear sensor array." Web.
1. . Bayesian inference for multi-line spectra in linear sensor array [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2910

Scene Image Classification using ReducedVirtual Feature Representation in Sparse Framework

Paper Details

Authors:
KRISHAN SHARMA, SHIKHA GUPTA, DILEEP A.D, RENU RAMESHAN
Submitted On:
15 April 2018 - 12:22pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP_3200.pdf

(24 downloads)

Keywords

Subscribe

[1] KRISHAN SHARMA, SHIKHA GUPTA, DILEEP A.D, RENU RAMESHAN, "Scene Image Classification using ReducedVirtual Feature Representation in Sparse Framework", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2897. Accessed: Jun. 20, 2018.
@article{2897-18,
url = {http://sigport.org/2897},
author = {KRISHAN SHARMA; SHIKHA GUPTA; DILEEP A.D; RENU RAMESHAN },
publisher = {IEEE SigPort},
title = {Scene Image Classification using ReducedVirtual Feature Representation in Sparse Framework},
year = {2018} }
TY - EJOUR
T1 - Scene Image Classification using ReducedVirtual Feature Representation in Sparse Framework
AU - KRISHAN SHARMA; SHIKHA GUPTA; DILEEP A.D; RENU RAMESHAN
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2897
ER -
KRISHAN SHARMA, SHIKHA GUPTA, DILEEP A.D, RENU RAMESHAN. (2018). Scene Image Classification using ReducedVirtual Feature Representation in Sparse Framework. IEEE SigPort. http://sigport.org/2897
KRISHAN SHARMA, SHIKHA GUPTA, DILEEP A.D, RENU RAMESHAN, 2018. Scene Image Classification using ReducedVirtual Feature Representation in Sparse Framework. Available at: http://sigport.org/2897.
KRISHAN SHARMA, SHIKHA GUPTA, DILEEP A.D, RENU RAMESHAN. (2018). "Scene Image Classification using ReducedVirtual Feature Representation in Sparse Framework." Web.
1. KRISHAN SHARMA, SHIKHA GUPTA, DILEEP A.D, RENU RAMESHAN. Scene Image Classification using ReducedVirtual Feature Representation in Sparse Framework [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2897

An Unsupervised Anomalous Event Detection Framework with Class-Aware Source Separation


This paper presents a novel problem of detection and localization of anomalous events due to a certain class of objects in video data with applications to smart surveillance. A baseline system is proposed that uses a convolutional neural network (CNN) to generate pixel level masks corresponding to objects of a class of interest. A Restricted Boltzmann Machine (RBM) is then trained on the mask to learn patterns of normal behavior. The free energy of the RBM is used to detect the presence of an anomaly while the reconstruction error is used to localize the anomaly.

Paper Details

Authors:
Burhan Ahmad Mudassar, Jong Hwan Ko, Saibal Mukhopadhyay
Submitted On:
16 April 2018 - 11:54am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP 2018 Poster.pptx

(29 downloads)

Keywords

Subscribe

[1] Burhan Ahmad Mudassar, Jong Hwan Ko, Saibal Mukhopadhyay, "An Unsupervised Anomalous Event Detection Framework with Class-Aware Source Separation", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2895. Accessed: Jun. 20, 2018.
@article{2895-18,
url = {http://sigport.org/2895},
author = {Burhan Ahmad Mudassar; Jong Hwan Ko; Saibal Mukhopadhyay },
publisher = {IEEE SigPort},
title = {An Unsupervised Anomalous Event Detection Framework with Class-Aware Source Separation},
year = {2018} }
TY - EJOUR
T1 - An Unsupervised Anomalous Event Detection Framework with Class-Aware Source Separation
AU - Burhan Ahmad Mudassar; Jong Hwan Ko; Saibal Mukhopadhyay
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2895
ER -
Burhan Ahmad Mudassar, Jong Hwan Ko, Saibal Mukhopadhyay. (2018). An Unsupervised Anomalous Event Detection Framework with Class-Aware Source Separation. IEEE SigPort. http://sigport.org/2895
Burhan Ahmad Mudassar, Jong Hwan Ko, Saibal Mukhopadhyay, 2018. An Unsupervised Anomalous Event Detection Framework with Class-Aware Source Separation. Available at: http://sigport.org/2895.
Burhan Ahmad Mudassar, Jong Hwan Ko, Saibal Mukhopadhyay. (2018). "An Unsupervised Anomalous Event Detection Framework with Class-Aware Source Separation." Web.
1. Burhan Ahmad Mudassar, Jong Hwan Ko, Saibal Mukhopadhyay. An Unsupervised Anomalous Event Detection Framework with Class-Aware Source Separation [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2895

TENSOR-BASED NONLINEAR CLASSIFIER FOR HIGH-ORDER DATA ANALYSIS

Paper Details

Authors:
Konstantinos Makantasis, Anastasios Doulamis, Nikolaos Doulamis, Antonis Nikitakis, Athanasios Voulodimos
Submitted On:
14 April 2018 - 1:07pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Presentation_ICASSP.pdf

(29 downloads)

Keywords

Subscribe

[1] Konstantinos Makantasis, Anastasios Doulamis, Nikolaos Doulamis, Antonis Nikitakis, Athanasios Voulodimos, "TENSOR-BASED NONLINEAR CLASSIFIER FOR HIGH-ORDER DATA ANALYSIS", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2842. Accessed: Jun. 20, 2018.
@article{2842-18,
url = {http://sigport.org/2842},
author = {Konstantinos Makantasis; Anastasios Doulamis; Nikolaos Doulamis; Antonis Nikitakis; Athanasios Voulodimos },
publisher = {IEEE SigPort},
title = {TENSOR-BASED NONLINEAR CLASSIFIER FOR HIGH-ORDER DATA ANALYSIS},
year = {2018} }
TY - EJOUR
T1 - TENSOR-BASED NONLINEAR CLASSIFIER FOR HIGH-ORDER DATA ANALYSIS
AU - Konstantinos Makantasis; Anastasios Doulamis; Nikolaos Doulamis; Antonis Nikitakis; Athanasios Voulodimos
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2842
ER -
Konstantinos Makantasis, Anastasios Doulamis, Nikolaos Doulamis, Antonis Nikitakis, Athanasios Voulodimos. (2018). TENSOR-BASED NONLINEAR CLASSIFIER FOR HIGH-ORDER DATA ANALYSIS. IEEE SigPort. http://sigport.org/2842
Konstantinos Makantasis, Anastasios Doulamis, Nikolaos Doulamis, Antonis Nikitakis, Athanasios Voulodimos, 2018. TENSOR-BASED NONLINEAR CLASSIFIER FOR HIGH-ORDER DATA ANALYSIS. Available at: http://sigport.org/2842.
Konstantinos Makantasis, Anastasios Doulamis, Nikolaos Doulamis, Antonis Nikitakis, Athanasios Voulodimos. (2018). "TENSOR-BASED NONLINEAR CLASSIFIER FOR HIGH-ORDER DATA ANALYSIS." Web.
1. Konstantinos Makantasis, Anastasios Doulamis, Nikolaos Doulamis, Antonis Nikitakis, Athanasios Voulodimos. TENSOR-BASED NONLINEAR CLASSIFIER FOR HIGH-ORDER DATA ANALYSIS [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2842

Crime incidents embedding using Restricted Boltzmann machine


We present a new approach for detecting related crime series, by unsupervised learning of the latent feature embeddings from narratives of crime record via the Gaussian-Bernoulli Restricted Boltzmann Machines (RBM). This is a drastically different approach from prior work on crime analysis, which typically considers only time and location and at most category information.

Paper Details

Authors:
Shixiang Zhu, Yao Xie
Submitted On:
14 April 2018 - 12:16am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP-Slides.pdf

(26 downloads)

Keywords

Subscribe

[1] Shixiang Zhu, Yao Xie, "Crime incidents embedding using Restricted Boltzmann machine", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2793. Accessed: Jun. 20, 2018.
@article{2793-18,
url = {http://sigport.org/2793},
author = {Shixiang Zhu; Yao Xie },
publisher = {IEEE SigPort},
title = {Crime incidents embedding using Restricted Boltzmann machine},
year = {2018} }
TY - EJOUR
T1 - Crime incidents embedding using Restricted Boltzmann machine
AU - Shixiang Zhu; Yao Xie
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2793
ER -
Shixiang Zhu, Yao Xie. (2018). Crime incidents embedding using Restricted Boltzmann machine. IEEE SigPort. http://sigport.org/2793
Shixiang Zhu, Yao Xie, 2018. Crime incidents embedding using Restricted Boltzmann machine. Available at: http://sigport.org/2793.
Shixiang Zhu, Yao Xie. (2018). "Crime incidents embedding using Restricted Boltzmann machine." Web.
1. Shixiang Zhu, Yao Xie. Crime incidents embedding using Restricted Boltzmann machine [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2793

MULTI-KERNEL, DEEP NEURAL NETWORK AND HYBRID MODELS FOR PRIVACY PRESERVING MACHINE LEARNING


The rapid rise of IoT and Big Data can facilitate the use of data to enhance our quality of life. However, the omnipresent and sensitive nature of data can simultaneously generate privacy concerns. Hence, there is a strong need to develop techniques that ensure the data serve the intended purposes, but not for prying into one’s sensitive information. We address this challenge via utility maximizing lossy compression of data.

Poster.pdf

PDF icon Poster.pdf (474 downloads)

Paper Details

Authors:
Mert Al, Thee Chanyaswad, Sun-Yuan Kung
Submitted On:
13 April 2018 - 3:55pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Poster.pdf

(474 downloads)

Keywords

Subscribe

[1] Mert Al, Thee Chanyaswad, Sun-Yuan Kung, "MULTI-KERNEL, DEEP NEURAL NETWORK AND HYBRID MODELS FOR PRIVACY PRESERVING MACHINE LEARNING", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2756. Accessed: Jun. 20, 2018.
@article{2756-18,
url = {http://sigport.org/2756},
author = {Mert Al; Thee Chanyaswad; Sun-Yuan Kung },
publisher = {IEEE SigPort},
title = {MULTI-KERNEL, DEEP NEURAL NETWORK AND HYBRID MODELS FOR PRIVACY PRESERVING MACHINE LEARNING},
year = {2018} }
TY - EJOUR
T1 - MULTI-KERNEL, DEEP NEURAL NETWORK AND HYBRID MODELS FOR PRIVACY PRESERVING MACHINE LEARNING
AU - Mert Al; Thee Chanyaswad; Sun-Yuan Kung
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2756
ER -
Mert Al, Thee Chanyaswad, Sun-Yuan Kung. (2018). MULTI-KERNEL, DEEP NEURAL NETWORK AND HYBRID MODELS FOR PRIVACY PRESERVING MACHINE LEARNING. IEEE SigPort. http://sigport.org/2756
Mert Al, Thee Chanyaswad, Sun-Yuan Kung, 2018. MULTI-KERNEL, DEEP NEURAL NETWORK AND HYBRID MODELS FOR PRIVACY PRESERVING MACHINE LEARNING. Available at: http://sigport.org/2756.
Mert Al, Thee Chanyaswad, Sun-Yuan Kung. (2018). "MULTI-KERNEL, DEEP NEURAL NETWORK AND HYBRID MODELS FOR PRIVACY PRESERVING MACHINE LEARNING." Web.
1. Mert Al, Thee Chanyaswad, Sun-Yuan Kung. MULTI-KERNEL, DEEP NEURAL NETWORK AND HYBRID MODELS FOR PRIVACY PRESERVING MACHINE LEARNING [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2756

Pages