Electroencephalography (EEG)-based emotion recognition attempts to detect the affective states of humans directly via spontaneous EEG signals, bypassing the peripheral nervous system. In this thesis, we explore variou...
详细信息
Electroencephalography (EEG)-based emotion recognition attempts to detect the affective states of humans directly via spontaneous EEG signals, bypassing the peripheral nervous system. In this thesis, we explore various machine learning techniques for EEG-based emotion recognition, and focus on the three research gaps outlined as follows. 1. Stable feature selection for recalibration-less affective Brain-Computer Interfaces 2. Cross-subject transfer learning for calibration-less affective Brain- Computer Interfaces 3. Unsupervised feature learning for affective Brain-Computer Interfaces We propose several novel methods in this thesis to address the three research gaps and validate our proposed methods by experiments. Extensive comparisons between our methods and other existing methods justify the advantages of our methods.
One approach in training a deep neural network to perform effectively is to do unsupervised pretraining on each layer, followed by fine-tuning the whole network. A common way is to train an unsupervised model of neura...
详细信息
ISBN:
(纸本)9781538626337
One approach in training a deep neural network to perform effectively is to do unsupervised pretraining on each layer, followed by fine-tuning the whole network. A common way is to train an unsupervised model of neural network such as restricted Boltzmann machines or autoencoders and stack them on top of another. Although these unsupervised pretraining approaches yield good performance, relying on back-propagation, due to iterative learning process, they still suffer from a long pretraining time. Extreme learning machine (ELM) is an analytical training approach which is extremely fast and gives a solution with a good generalization performance. In this paper, we apply a new ELM based unsupervised learning, named backward ELM based autoencoder (BELM-AE), to pretrain each layer of a neural network before using a back-propagation based learning algorithm to fine-tune the whole network. Experimental results show that the new pretraining method requires significantly shorter training time and also yields better testing performance on various datasets.
Increasing demand for high field magnetic resonance (MR) scanner indicates the need for high-quality MR images for accurate medical diagnosis. However, cost constraints, instead, motivate a need for algorithms to enha...
详细信息
ISBN:
(纸本)9783030008895;9783030008888
Increasing demand for high field magnetic resonance (MR) scanner indicates the need for high-quality MR images for accurate medical diagnosis. However, cost constraints, instead, motivate a need for algorithms to enhance images from low field scanners. We propose an approach to process the given low field (3T) MR image slices to reconstruct the corresponding high field (7T-like) slices. Our framework involves a novel architecture of a merged convolutional autoencoder with a single encoder and multiple decoders. Specifically, we employ three decoders with random initializations, and the proposed training approach involves selection of a particular decoder in each weight-update iteration for back propagation. We demonstrate that the proposed algorithm outperforms some related contemporary methods in terms of performance and reconstruction time.
This paper deals with robust speaker verification (SV) in far field sensing. The robustness is verified on a subset of NIST SRE 2010 corpus retransmitted in multiple real rooms of different acoustics and captured with...
详细信息
ISBN:
(纸本)9781510872219
This paper deals with robust speaker verification (SV) in far field sensing. The robustness is verified on a subset of NIST SRE 2010 corpus retransmitted in multiple real rooms of different acoustics and captured with multiple microphones. We experimented with various data preprocessing steps including different approaches to dereverberation and beamforming applied to ad-hoc microphone arrays. We found that significant improvements in accuracy can be achieved with neural network based generalized eigenvalue beamformer preceded by weighted prediction error dereverberation. We also explored the effect of data augmentation by adding various real or simulated room acoustic properties to the Probabilistic Linear Discriminant Analysis (PLDA) training dataset. As a result, we developed a speaker recognition system whose performance is stable across different room acoustic conditions. It yields 41.4% relative improvement in performance over the system without multi-channel processing tested on the cleanest microphone data. With the best combination of data preprocessing and augmentation, we obtained a performance close to the one we achieved with the original clean test data.
For session control servers of carriers networks, the scale out type session control server architecture that could control system performance flexibly has been studied. Network anomaly detection technology using auto...
详细信息
ISBN:
(纸本)9781450365390
For session control servers of carriers networks, the scale out type session control server architecture that could control system performance flexibly has been studied. Network anomaly detection technology using autoencoder has attracted attention. An autoencoder is one of the dimensionality reduction algorithm using neural network. We propose methods to prevent data loss when serious trouble occurred in network equipment, such as servers and routers, of a high availability distributed cluster using consistent hashing. The methods control data redundancy before serious failure of servers or networks occur using anomaly detection technology. We evaluated three anomalous server selection methods by calculation and computer simulation. We also verified the operation of the data redundancy dynamic control methods by software implementation and operation experiment.
This work aims at analyzing twitter data to identify communities of Brazilian Senators. To do so, we collected data from 76 Brazilian Senators and used autoencoder and bi-gram to the content of tweets to find similar ...
详细信息
ISBN:
(纸本)9783319914855;9783319914848
This work aims at analyzing twitter data to identify communities of Brazilian Senators. To do so, we collected data from 76 Brazilian Senators and used autoencoder and bi-gram to the content of tweets to find similar subjects and hence cluster the senators into groups. Thereafter, we applied an unsupervised sentiment analysis to identify the communities of senators that share similar sentiments about a selected number of relevant topics. We find that is able to create meaningful clusters of tweets of similar contents. We found 13 topics all of them relevant to the current Brazilian political scenario. The unsupervised sentiment analysis shows that, as a result of the complex political system (with multiple parties), many senators were identified as independent (19) and only one (out of 11) community can be classified as a community of senators that support the current government. All other detected communities are not relevant.
This paper proposes rollable latent space (RLS) for an azimuth invariant synthetic aperture radar (SAR) target recognition. Scarce labeled data and limited viewing direction are critical issues in SAR target recogniti...
详细信息
ISBN:
(纸本)9781538671504
This paper proposes rollable latent space (RLS) for an azimuth invariant synthetic aperture radar (SAR) target recognition. Scarce labeled data and limited viewing direction are critical issues in SAR target recognition. The RLS is a designed space in which rolling of latent features corresponds to 3D rotation of an object. Thus latent features of an arbitrary view can be inferred using those of different views. This characteristic further enables us to augment data from limited viewing in RLS. RLS-based classifiers with and without data augmentation and a conventional classifier trained with target front shots are evaluated over untrained target back shots. Results show that the RLS-based classifier with augmentation improves an accuracy by 30% compared to the conventional classifier.
Making computer-generated (CG) images more difficult to detect is an interesting problem in computer graphics and security. While most approaches focus on the image rendering phase, this paper presents a method based ...
详细信息
ISBN:
(纸本)9781538617373
Making computer-generated (CG) images more difficult to detect is an interesting problem in computer graphics and security. While most approaches focus on the image rendering phase, this paper presents a method based on increasing the naturalness of CG facial images from the perspective of spoofing detectors. The proposed method is implemented using a convolutional neural network (CNN) comprising two autoencoders and a transformer and is trained using a black-box discriminator without gradient information. Over 50% of the transformed CG images were not detected by three state-of-the-art spoofing detectors. This capability raises an alarm regarding the reliability of facial authentication systems, which are becoming widely used in daily life.
We propose a real-time RGB-based pipeline for object detection and 6D pose estimation. Our novel 3D orientation estimation is based on a variant of the Denoising autoencoder that is trained on simulated views of a 3D ...
详细信息
ISBN:
(纸本)9783030012311;9783030012304
We propose a real-time RGB-based pipeline for object detection and 6D pose estimation. Our novel 3D orientation estimation is based on a variant of the Denoising autoencoder that is trained on simulated views of a 3D model using Domain Randomization. This so-called Augmented autoencoder has several advantages over existing methods: It does not require real, pose-annotated training data, generalizes to various test sensors and inherently handles object and view symmetries. Instead of learning an explicit mapping from input images to object poses, it provides an implicit representation of object orientations defined by samples in a latent space. Experiments on the T-LESS and LineMOD datasets show that our method outperforms similar model-based approaches and competes with state-of-the art approaches that require real pose-annotated images.
As more and more single-cell RNA-seq (scRNA-seq) datasets become available, carrying out compare between them is key. However, this task is challengeable due to differences caused by different experiment. We proposed ...
详细信息
ISBN:
(纸本)9781728118680
As more and more single-cell RNA-seq (scRNA-seq) datasets become available, carrying out compare between them is key. However, this task is challengeable due to differences caused by different experiment. We proposed a single cell alignment method using deep autoencoder followed by k-nearst-neighbor cells (scadKNN), which learns the feature representation of the data while eliminating batch effects and dropouts through deep autoencoder and uses the low-dimensional feature to align cell types, thereby reducing calculation effort and improving alignment accuracy. Experiments using different real datasets are employed to showcase the effectiveness of the proposed approach.
暂无评论