scholarly journals Temporal refinement of 3D CNN semantic segmentations on 4D time-series of undersampled tomograms using hidden Markov models

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Dimitrios Bellos ◽  
Mark Basham ◽  
Tony Pridmore ◽  
Andrew P. French
Keyword(s):  
Neural Networks ◽  
Time Series ◽  
Hidden Markov Models ◽  
Convolutional Neural Networks ◽  
Markov Models ◽  
Hidden Markov ◽  
Large Data ◽  
Prediction Confidence ◽  
3D Cnn ◽  
2D Images

AbstractRecently, several convolutional neural networks have been proposed not only for 2D images, but also for 3D and 4D volume segmentation. Nevertheless, due to the large data size of the latter, acquiring a sufficient amount of training annotations is much more strenuous than in 2D images. For 4D time-series tomograms, this is usually handled by segmenting the constituent tomograms independently through time with 3D convolutional neural networks. Inter-volume information is therefore not utilized, potentially leading to temporal incoherence. In this paper, we attempt to resolve this by proposing two hidden Markov model variants that refine 4D segmentation labels made by 3D convolutional neural networks working on each time point. Our models utilize not only inter-volume information, but also the prediction confidence generated by the 3D segmentation convolutional neural networks themselves. To the best of our knowledge, this is the first attempt to refine 4D segmentations made by 3D convolutional neural networks using hidden Markov models. During experiments we test our models, qualitatively, quantitatively and behaviourally, using prespecified segmentations. We demonstrate in the domain of time series tomograms which are typically undersampled to allow more frequent capture; a particularly challenging problem. Finally, our dataset and code is publicly available.

scholarly journals Comparison of Two Objects Classification Techniques using Hidden Markov Models and Convolutional Neural Networks

2020 ◽  
Vol 19 (6) ◽  
pp. 1222-1254
Author(s):  
Carlos Sarmiento ◽  
Jesus Savage
Keyword(s):  
Neural Networks ◽  
Hidden Markov Models ◽  
Convolutional Neural Networks ◽  
Markov Models ◽  
Hidden Markov ◽  
Classification Systems ◽  
Battery Life ◽  
Data Set ◽  
Classification Of Images ◽  
Symbol Sequences

This paper presents a comparison between discrete Hidden Markov Models and Convolutional Neural Networks for the image classification task. By fragmenting an image into sections, it is feasible to obtain vectors that represent visual features locally, but if a spatial sequence is established in a fixed way, it is possible to represent an image as a sequence of vectors. Using clustering techniques, we obtain an alphabet from said vectors and then symbol sequences are constructed to obtain a statistical model that represents a class of images. Hidden Markov Models, combined with quantization methods, can treat noise and distortions in observations for computer vision problems such as the classification of images with lighting and perspective changes.We have tested architectures based on three, six and nine hidden states favoring the detection speed and low memory usage. Also, two types of ensemble models were tested. We evaluated the precision of the proposed methods using a public domain data set, obtaining competitive results with respect to fine-tuned Convolutional Neural Networks, but using significantly less computing resources. This is of interest in the development of mobile robots with computers with limited battery life, but requiring the ability to detect and add new objects to their classification systems.

scholarly journals FIND: Identifying Functionally and Structurally Important Features in Protein Sequences with Deep Neural Networks

2019 ◽  
Author(s):  
Ranjani Murali ◽  
James Hemp ◽  
Victoria Orphan ◽  
Yonatan Bisk
Keyword(s):  
Neural Networks ◽  
Amino Acid ◽  
Hidden Markov Models ◽  
Markov Models ◽  
Genomic Sequence ◽  
Hidden Markov ◽  
Amino Acid Sequences ◽  
Homologous Proteins ◽  
Biological Studies ◽  
Insight Into

AbstractThe ability to correctly predict the functional role of proteins from their amino acid sequences would significantly advance biological studies at the molecular level by improving our ability to understand the biochemical capability of biological organisms from their genomic sequence. Existing methods that are geared towards protein function prediction or annotation mostly use alignment-based approaches and probabilistic models such as Hidden-Markov Models. In this work we introduce a deep learning architecture (FunctionIdentification withNeuralDescriptions orFIND) which performs protein annotation from primary sequence. The accuracy of our methods matches state of the art techniques, such as protein classifiers based on Hidden Markov Models. Further, our approach allows for model introspection via a neural attention mechanism, which weights parts of the amino acid sequence proportionally to their relevance for functional assignment. In this way, the attention weights automatically uncover structurally and functionally relevant features of the classified protein and find novel functional motifs in previously uncharacterized proteins. While this model is applicable to any database of proteins, we chose to apply this model to superfamilies of homologous proteins, with the aim of extracting features inherent to divergent protein families within a larger superfamily. This provided insight into the functional diversification of an enzyme superfamily and its adaptation to different physiological contexts. We tested our approach on three families (nitrogenases, cytochromebd-type oxygen reductases and heme-copper oxygen reductases) and present a detailed analysis of the sequence characteristics identified in previously characterized proteins in the heme-copper oxygen reductase (HCO) superfamily. These are correlated with their catalytic relevance and evolutionary history. FIND was then applied to discover features in previously uncharacterized members of the HCO superfamily, providing insight into their unique sequence features. This modeling approach demonstrates the power of neural networks to recognize patterns in large datasets and can be utilized to discover biochemically and structurally important features in proteins from their amino acid sequences.Author summary

A New Modular Strategy For Action Sequence Automation Using Neural Networks And Hidden Markov Models

2013 ◽  
Vol 2 (3) ◽  
pp. 18-35 ◽  
Author(s):  
Mohamed Adel Taher ◽  
Mostapha Abdeljawad
Keyword(s):  
Neural Networks ◽  
Hidden Markov Models ◽  
Fuzzy Systems ◽  
Markov Models ◽  
Hidden Markov ◽  
Current System ◽  
Action Sequence ◽  
Hybrid Strategy ◽  
Automatic Control Theory ◽  
Welding Automation

In this paper, the authors propose a new hybrid strategy (using artificial neural networks and hidden Markov models) for skill automation. The strategy is based on the concept of using an “adaptive desired” that is introduced in the paper. The authors explain how using an adaptive desired can help a system for which an explicit model is not available or is difficult to obtain to smartly cope with environmental disturbances without requiring explicit rules specification (as with fuzzy systems). At the same time, unlike the currently available hidden Markov-based systems, the system does not merely replay a memorized skill. Instead, it takes into account the current system state as reported by sensors. The authors approach can be considered a bridge between the spirit of conventional automatic control theory and fuzzy/hidden Markov-based thinking. To demonstrate the different aspects of the proposed strategy, the authors discuss its application to underwater welding automation.

scholarly journals A Hidden Markov Model for the Linguistic Analysis of the Voynich Manuscript

2019 ◽  
Vol 24 (1) ◽  
pp. 14 ◽  
Author(s):  
Luis Acedo
Keyword(s):  
Time Series ◽  
Markov Model ◽  
Hidden Markov Model ◽  
Hidden Markov Models ◽  
Markov Models ◽  
Hidden Markov ◽  
Mathematical Linguistics ◽  
Underlying Structure ◽  
Internal States ◽  
Consonant Sounds

Hidden Markov models are a very useful tool in the modeling of time series and any sequence of data. In particular, they have been successfully applied to the field of mathematical linguistics. In this paper, we apply a hidden Markov model to analyze the underlying structure of an ancient and complex manuscript, known as the Voynich manuscript, which remains undeciphered. By assuming a certain number of internal states representations for the symbols of the manuscripts, we train the network by means of the α and β -pass algorithms to optimize the model. By this procedure, we are able to obtain the so-called transition and observation matrices to compare with known languages concerning the frequency of consonant andvowel sounds. From this analysis, we conclude that transitions occur between the two states with similar frequencies to other languages. Moreover, the identification of the vowel and consonant sounds matches some previous tentative bottom-up approaches to decode the manuscript.

Sign in / Sign up

Export Citation Format

Share Document