Gaussian-Bernoulli restricted Boltzmann machines and automatic feature extraction for noise robust missing data mask estimation

Keronen, Sami; Cho, Kyunghyun; Raiko, Tapani; Ilin, Alexander; Palomäki, Kalle

doi:10.1109/icassp.2013.6638964

Cited by 9 publications

(3 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is not appropriate to construct the RBM with the binary visible layer when the input is a continuous valued data. So this paper is to develop the Gauss-Binary RBM (GBRBM) [43,44,45] instead of standard RBM, and the energy function of the standard RBM in Equation (8) is changed to Equation (18). E(boldnormalv,boldnormalhfalse|θ)=−true∑i=1nfalse(vi−cifalse)22σi2−true∑j=1mbjhj−true∑i=1ntrue∑j=1mviσi2wijhj where σi2 is the variance of Gaussian distribution.…”

Section: The Proposed Methodsmentioning

confidence: 99%

A Novel Method for Early Gear Pitting Fault Diagnosis Using Stacked SAE and GBRBM

et al. 2019

Sensors

View full text Add to dashboard Cite

Research on data-driven fault diagnosis methods has received much attention in recent years. The deep belief network (DBN) is a commonly used deep learning method for fault diagnosis. In the past, when people used DBN to diagnose gear pitting faults, it was found that the diagnosis result was not good with continuous time domain vibration signals as direct inputs into DBN. Therefore, most researchers extracted features from time domain vibration signals as inputs into DBN. However, it is desirable to use raw vibration signals as direct inputs to achieve good fault diagnosis results. Therefore, this paper proposes a novel method by stacking spare autoencoder (SAE) and Gauss-Binary restricted Boltzmann machine (GBRBM) for early gear pitting faults diagnosis with raw vibration signals as direct inputs. The SAE layer is used to compress the raw vibration data and the GBRBM layer is used to effectively process continuous time domain vibration signals. Vibration signals of seven early gear pitting faults collected from a gear test rig are used to validate the proposed method. The validation results show that the proposed method maintains a good diagnosis performance under different working conditions and gives higher diagnosis accuracy compared to other traditional methods.

show abstract

Section: The Proposed Methodsmentioning

confidence: 99%

A Novel Method for Early Gear Pitting Fault Diagnosis Using Stacked SAE and GBRBM

et al. 2019

Sensors

View full text Add to dashboard Cite

show abstract

“…Another deep learning based B-PET was proposed by Rafique et al in [209]. Here, the authors explored Gaussian-Bernoulli Restricted Boltzmann Machines (GBRBMs) [235], [236] as means for face deidentification and exploited the generative nature of GBRBMs to design two separate deidentification solutions. The first is capable of pixelating faces with the goal of hiding identity, whereas the second (auto-encoder based) allows to produce smoother, higher quality images that also preserve information on the expressed (facial) emotions.…”

Section: Deep Learning Approachesmentioning

confidence: 99%

Privacy–Enhancing Face Biometrics: A Comprehensive Survey

Meden

Rot

Terhörst

et al. 2021

IEEE Trans.Inform.Forensic Secur.

111

View full text Add to dashboard Cite

Biometric recognition technology has made significant advances over the last decade and is now used across a number of services and applications. However, this widespread deployment has also resulted in privacy concerns and evolving societal expectations about the appropriate use of the technology. For example, the ability to automatically extract age, gender, race, and health cues from biometric data has heightened concerns about privacy leakage. Face recognition technology, in particular, has been in the spotlight, and is now seen by many as posing a considerable risk to personal privacy. In response to these and similar concerns, researchers have intensified efforts towards developing techniques and computational models capable of ensuring privacy to individuals, while still facilitating the utility of face recognition technology in several application scenarios. These efforts have resulted in a multitude of privacy-enhancing techniques that aim at addressing privacy risks originating from biometric systems and providing technological solutions for legislative requirements set forth in privacy laws and regulations, such as GDPR. The goal of this overview paper is to provide a comprehensive introduction into privacy-related research in the area of biometrics and review existing work on Biometric Privacy-Enhancing Techniques (B-PETs) applied to face biometrics. To make this work useful for as wide of an audience as possible, several key topics are covered as well, including evaluation strategies used with B-PETs, existing datasets, relevant standards, and regulations and critical open issues that will have to be addressed in the future.

show abstract

“…When inputs are real-valued images, we formulate the energy function of the Gaussian-Bernoulli RBM over the state

as follows [ 23 ]:

where

are the model parameters,

and

are biases corresponding to visible and hidden variables, respectively,

is the matrix of weights connecting visible and hidden nodes, and

is the standard deviation associated with a Gaussian visible variable

.…”

Section: Related Workmentioning

confidence: 99%

Visual Object Tracking Based on Cross-Modality Gaussian-Bernoulli Deep Boltzmann Machines with RGB-D Sensors

Jiang

Pan

Tang

2017

Sensors

View full text Add to dashboard Cite

Visual object tracking technology is one of the key issues in computer vision. In this paper, we propose a visual object tracking algorithm based on cross-modality featuredeep learning using Gaussian-Bernoulli deep Boltzmann machines (DBM) with RGB-D sensors. First, a cross-modality featurelearning network based on aGaussian-Bernoulli DBM is constructed, which can extract cross-modality features of the samples in RGB-D video data. Second, the cross-modality features of the samples are input into the logistic regression classifier, andthe observation likelihood model is established according to the confidence score of the classifier. Finally, the object tracking results over RGB-D data are obtained using aBayesian maximum a posteriori (MAP) probability estimation algorithm. The experimental results show that the proposed method has strong robustness to abnormal changes (e.g., occlusion, rotation, illumination change, etc.). The algorithm can steadily track multiple targets and has higher accuracy.

show abstract

Gaussian-Bernoulli restricted Boltzmann machines and automatic feature extraction for noise robust missing data mask estimation

Cited by 9 publications

References 19 publications

A Novel Method for Early Gear Pitting Fault Diagnosis Using Stacked SAE and GBRBM

A Novel Method for Early Gear Pitting Fault Diagnosis Using Stacked SAE and GBRBM

Privacy–Enhancing Face Biometrics: A Comprehensive Survey

Visual Object Tracking Based on Cross-Modality Gaussian-Bernoulli Deep Boltzmann Machines with RGB-D Sensors

Contact Info

Product

Resources

About