Unsupervised Phonocardiogram Analysis With Distribution Density Based Variational Auto-Encoders

This paper proposes an unsupervised way for Phonocardiogram (PCG) analysis, which uses a revised auto encoder based on distribution density estimation in the latent space. Auto encoders especially Variational Auto-Encoders (VAEs) and its variant β−VAE are considered as one of the state-of-the-art methodologies for PCG analysis. VAE based models for PCG analysis assume that normal PCG signals can be represented by latent vectors that obey a normal Gaussian Model, which may not be necessary true in PCG analysis. This paper proposes two methods DBVAE and DBAE that are based on estimating the density of latent vectors in latent space to improve the performance of VAE based PCG analysis systems. Examining the system performance with PCG data from the a single domain and multiple domains, the proposed systems outperform the VAE based methods. The representation of normal PCG signals in the latent space is also investigated by calculating the kurtosis and skewness where DBAE introduces normal PCG representation following Gaussian-like models but DBVAE does not introduce normal PCG representation following Gaussian-like models.

Download Full-text

Hyperprior Induced Unsupervised Disentanglement of Latent Representations

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v33i01.33013175 ◽

2019 ◽

Vol 33 ◽

pp. 3175-3182 ◽

Cited By ~ 1

Author(s):

Abdul Fatir Ansari ◽

Harold Soh

Keyword(s):

Lower Bound ◽

Covariance Matrix ◽

State Of The Art ◽

Generative Models ◽

The State ◽

Experimental Results ◽

Hierarchical Bayesian ◽

Statistical Independence ◽

Latent Space ◽

Latent Representations

We address the problem of unsupervised disentanglement of latent representations learnt via deep generative models. In contrast to current approaches that operate on the evidence lower bound (ELBO), we argue that statistical independence in the latent space of VAEs can be enforced in a principled hierarchical Bayesian manner. To this effect, we augment the standard VAE with an inverse-Wishart (IW) prior on the covariance matrix of the latent code. By tuning the IW parameters, we are able to encourage (or discourage) independence in the learnt latent dimensions. Extensive experimental results on a range of datasets (2DShapes, 3DChairs, 3DFaces and CelebA) show our approach to outperform the β-VAE and is competitive with the state-of-the-art FactorVAE. Our approach achieves significantly better disentanglement and reconstruction on a new dataset (CorrelatedEllipses) which introduces correlations between the factors of variation.

Download Full-text

Dialogue State Tracking with Incremental Reasoning

Transactions of the Association for Computational Linguistics ◽

10.1162/tacl_a_00384 ◽

2021 ◽

Vol 9 ◽

pp. 557-569

Author(s):

Lizi Liao ◽

Le Hong Long ◽

Yunshan Ma ◽

Wenqiang Lei ◽

Tat-Seng Chua

Keyword(s):

Large Scale ◽

State Of The Art ◽

The State ◽

Policy Learning ◽

Dialogue Management ◽

Empirical Results ◽

Art Methods ◽

State Tracking ◽

Incremental Reasoning ◽

Multiple Domains

Abstract Tracking dialogue states to better interpret user goals and feed downstream policy learning is a bottleneck in dialogue management. Common practice has been to treat it as a problem of classifying dialogue content into a set of pre-defined slot-value pairs, or generating values for different slots given the dialogue history. Both have limitations on considering dependencies that occur on dialogues, and are lacking of reasoning capabilities. This paper proposes to track dialogue states gradually with reasoning over dialogue turns with the help of the back-end data. Empirical results demonstrate that our method outperforms the state-of-the-art methods in terms of joint belief accuracy for MultiWOZ 2.1, a large-scale human--human dialogue dataset across multiple domains.

Download Full-text

A Multilingual and Multidomain Study on Dialog Act Recognition Using Character-Level Tokenization

Information ◽

10.3390/info10030094 ◽

2019 ◽

Vol 10 (3) ◽

pp. 94 ◽

Cited By ~ 1

Author(s):

Eugénio Ribeiro ◽

Ricardo Ribeiro ◽

David de Matos

Keyword(s):

State Of The Art ◽

Morphological Characteristics ◽

The State ◽

Complementary Information ◽

Dialog Systems ◽

Word Level ◽

Morphological Aspects ◽

Multiple Domains ◽

Domain Independent ◽

Multiple Character

Automatic dialog act recognition is an important step for dialog systems since it reveals the intention behind the words uttered by its conversational partners. Although most approaches on the task use word-level tokenization, there is information at the sub-word level that is related to the function of the words and, consequently, their intention. Thus, in this study, we explored the use of character-level tokenization to capture that information. We explored the use of multiple character windows of different sizes to capture morphological aspects, such as affixes and lemmas, as well as inter-word information. Furthermore, we assessed the importance of punctuation and capitalization for the task. To broaden the conclusions of our study, we performed experiments on dialogs in three languages—English, Spanish, and German—which have different morphological characteristics. Furthermore, the dialogs cover multiple domains and are annotated with both domain-dependent and domain-independent dialog act labels. The achieved results not only show that the character-level approach leads to similar or better performance than the state-of-the-art word-level approaches on the task, but also that both approaches are able to capture complementary information. Thus, the best results are achieved by combining tokenization at both levels.

Download Full-text

A Multi-Task Approach to Open Domain Suggestion Mining (Student Abstract)

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v34i10.7180 ◽

2020 ◽

Vol 34 (10) ◽

pp. 13817-13818

Author(s):

Minni Jain ◽

Maitree Leekha ◽

Mononito Goswami

Keyword(s):

Deep Learning ◽

State Of The Art ◽

Class Imbalance ◽

Sampling Technique ◽

Experimental Results ◽

Single Domain ◽

Learning Approach ◽

Open Domain ◽

Consumer Reviews ◽

Multiple Domains

Consumer reviews online may contain suggestions useful for improving the target products and services. Mining suggestions is challenging because the field lacks large labelled and balanced datasets. Furthermore, most prior studies have only focused on mining suggestions in a single domain. In this work, we introduce a novel up-sampling technique to address the problem of class imbalance, and propose a multi-task deep learning approach for mining suggestions from multiple domains. Experimental results on a publicly available dataset show that our up-sampling technique coupled with the multi-task framework outperforms state-of-the-art open domain suggestion mining models in terms of the F-1 measure and AUC.

Download Full-text

Efficient resource allocation for decentralized heterogeneous system using density estimation approach

Encyclopedia with Semantic Computing and Robotic Intelligence ◽

10.1142/s2529737618500089 ◽

2018 ◽

Vol 02 (01) ◽

pp. 1850008 ◽

Cited By ~ 2

Author(s):

J. Senthilnath ◽

K. Harikumar ◽

S. Suresh

Keyword(s):

Density Estimation ◽

State Of The Art ◽

Average Distance ◽

Optimal Number ◽

The State ◽

Ground Vehicles ◽

Mission Duration ◽

Efficient Resource ◽

Initial Placement ◽

Charging Stations

This paper focuses on enhancing the mission duration by deploying secondary agents to coordinate with the primary agents to accomplish the mission with a minimal interruption. The interruption considered here is due to limited fuel carrying capability of primary agents. In this study, primary and secondary agents refer to unmanned aerial vehicles (UAVs) and unmanned ground vehicles (UGVs), respectively. Conventionally, UAVs are refueled with the fixed main charging stations which lead to interruption during the ongoing mission. In this work, we propose two-stage density estimation approach for efficiently distributing the swarm of UGVs to act as mobile refueling stations for UAVs. In the first stage, the optimal number of UGVs and their initial placement are computed. In the final stage, the UGVs minimize the average distance for the nearest UAVs to refuel. The performance of the proposed method is compared with the state of the art. The numerical simulation shows a better performance with the distributed UGVs than the state of the art.

Download Full-text

Practical Picture Processing

Proceedings, annual meeting, Electron Microscopy Society of America ◽

10.1017/s0424820100051700 ◽

1974 ◽

Vol 32 ◽

pp. 338-339

Author(s):

T. A. Welton

Keyword(s):

Radiation Damage ◽

Coherence Length ◽

Spatial Information ◽

State Of The Art ◽

Coherent Radiation ◽

The State ◽

Energy Spread ◽

Electron Micrograph ◽

Picture Processing ◽

Molecular Skeleton

Various authors have emphasized the spatial information resident in an electron micrograph taken with adequately coherent radiation. In view of the completion of at least one such instrument, this opportunity is taken to summarize the state of the art of processing such micrographs. We use the usual symbols for the aberration coefficients, and supplement these with £ and 6 for the transverse coherence length and the fractional energy spread respectively. He also assume a weak, biologically interesting sample, with principal interest lying in the molecular skeleton remaining after obvious hydrogen loss and other radiation damage has occurred.

Download Full-text