Unlike traditional terrestrial scenarios, communication channels in underwater environments face severe limitations in bandwidth and experience long propagation delay. In order to address these ...issues, reliable techniques capable to dynamically adapt transmission parameters to time-varying channel conditions are necessary. Actually, their effectiveness primarily relies on an accurate characterization of the underwater communication channels, which is often obtained through predictive models. In this paper, we compare the performance of different types of SNR-based predictive models (i.e., Markov models, Hidden Markov models) in terms of balance between accuracy and complexity. We also provide a Kalman filter-based prediction of SNR values and compare this prediction with the performance achieved with the Markov models above mentioned. The models we have considered to carry out the comparison analysis have been developed based on real shallow water traces taken over the Tyrrhenian Sea, Italy.
In time series forecasting, a challenging and important task is to realize long-term forecasting that is both accurate and transparent. In this study, we propose a long-term prediction approach by ...transforming the original numerical data into some meaningful and interpretable entities following the principle of justifiable granularity. The obtained sequences exhibiting sound semantics may have different lengths, which bring some difficulties when carrying out predictions. To equalize these temporal sequences, we propose to adjust their lengths by involving the dynamic time warping (DTW) distance. Two theorems are included to ensure the correctness of the proposed equalization approach. Finally, we exploit hidden Markov models (HMM) to derive the relations existing in the granular time series. A series of experiments using publicly available data are conducted to assess the performance of the proposed prediction method. The comparative analysis demonstrates the performance of the prediction delivered by the proposed model.
This article is concerned with the problem of imperfect premise matching asynchronous <inline-formula><tex-math notation="LaTeX">H_{\infty }</tex-math></inline-formula> output tracking control for ...Takagi-Sugeno fuzzy Markov jump systems. A hidden Markov model is established due to the fact that the modes information of the system may not be accurately transmitted to the controller, which is used to depict the asynchronous phenomenon between the system modes and controller modes. The packet loss in the communication process is described by a stochastic variable subject to Bernoulli distribution. Then, based on a novel Lyapunov function, the mode-dependent and fuzzy-basis-dependent stability criteria are derived and the asynchronous control scheme is developed subject to an <inline-formula><tex-math notation="LaTeX">H_{\infty }</tex-math></inline-formula> tracking performance. Finally, two examples are provided to demonstrate the effectiveness of the proposed approach.
Generative Kernels for Tree-Structured Data Bacciu, Davide; Micheli, Alessio; Sperduti, Alessandro
IEEE transaction on neural networks and learning systems,
10/2018, Volume:
29, Issue:
10
Journal Article
Open access
This paper presents a family of methods for the design of adaptive kernels for tree-structured data that exploits the summarization properties of hidden states of hidden Markov models for trees. We ...introduce a compact and discriminative feature space based on the concept of hidden states multisets and we discuss different approaches to estimate such hidden state encoding. We show how it can be used to build an efficient and general tree kernel based on Jaccard similarity. Furthermore, we derive an unsupervised convolutional generative kernel using a topology induced on the Markov states by a tree topographic mapping. This paper provides an extensive empirical assessment on a variety of structured data learning tasks, comparing the predictive accuracy and computational efficiency of state-of-the-art generative, adaptive, and syntactical tree kernels. The results show that the proposed generative approach has a good tradeoff between computational complexity and predictive performance, in particular when considering the soft matching introduced by the topographic mapping.
This paper concentrates on the fuzzy-model-based H∞ control for Markov jump nonlinear slow sampling singularly perturbed systems with partial information. The partial information problems including ...partial information on the transition probabilities of the Markov chain, on the Markov state, and on detection probabilities are taken into account simultaneously. A new hidden Markov model (HMM), in which some elements need not be known, is introduced to formulate the partial information problems. Some criteria on H∞ performance analysis and the existence of the desired HMM-based asynchronous fuzzy controller are derived. An optimized relaxation matrix is introduced to improve the decoupling method such that the obtained HMM-based asynchronous fuzzy controller is less conservative. Finally, two examples show the availability of the HMM-based asynchronous controller design procedures.
Summary
The expectation–maximization (EM) algorithm is a familiar tool for computing the maximum likelihood estimate of the parameters in hidden Markov and semi‐Markov models. This paper carries out ...a detailed study on the influence that the initial values of the parameters impose on the results produced by the algorithm. We compare random starts and partitional and model‐based strategies for choosing the initial values for the EM algorithm in the case of multivariate Gaussian emission distributions (EDs) and assess the performance of each strategy with different assessment criteria. Several data generation settings are considered with varying number of latent states, of variables as well as of the level of fuzziness in the data, and discussion on how each factor influences the obtained results is provided. Simulation results show that different initialization strategies may lead to different log‐likelihood values and, accordingly, to different estimated partitions. A clear indication of which strategies should be preferred is given. We further include two real‐data examples, widely analysed in the hidden semi‐Markov model literature.
The problem of asynchronous dissipative control is investigated for Takagi-Sugeno fuzzy systems with Markov jump in this paper. Hidden Markov model is introduced to represent the nonsynchronization ...between the designed controller and the original system. By the fuzzy-basis-dependent and mode-dependent Lyapunov function, a sufficient condition is achieved such that the resulting closed-loop system is stochastically stable with a strictly (<inline-formula> <tex-math notation="LaTeX"> {\mathcal {Q}} </tex-math></inline-formula>, <inline-formula> <tex-math notation="LaTeX"> {\mathcal {S}} </tex-math></inline-formula>, <inline-formula> <tex-math notation="LaTeX"> {\mathcal {R}} </tex-math></inline-formula>)-<inline-formula> <tex-math notation="LaTeX"> {\alpha } </tex-math></inline-formula>-dissipative performance. The controller parameter is derived by applying MATLAB to solve a set of linear matrix inequalities. Finally, we present two examples to confirm the validity and correctness of our developed approach.
This article presents an optimal reduced-dimension Kalman filter for a family of triplet Markov models (TMMs). The problem is to estimate the state vector in the case when the auxiliary process in ...the TMM can be eliminated. Sufficient conditions for this elimination to be feasible are established and we give a selection of illustrative real-life TMM examples, where these conditions are satisfied. We subsequently show that the original TMM boils down to a pairwise Markov model (PMM) of second order. Then, we derive a new optimal Kalman filter applicable to any linear PMM of second order. Our numerical results confirm that the proposed estimator can provide substantial complexity reduction with either no or minor accuracy loss, depending on the use of model approximation.
Land cover and land use affect a wide range of regional-scale to global-scale ecosystem processes, and many Earth system models rely on accurate land cover information. However, multitemporal land ...cover products often show unrealistically high levels of year-to-year label change, particularly at coarse spatial resolution (i.e., 300-500 m). Much of this apparent land cover change arises from errors in classification and does not indicate real change in land cover or land use. In this paper, we present a novel framework that uses a hidden Markov model (HMM) to help distinguish real land cover change from spurious land cover changes in classification time series. We apply the HMM as a postprocessing step to supervised classification, and we solve for the optimal label sequence using existing HMM algorithms. Our results demonstrate that the HMM provides a rigorous framework for capturing temporal context and likelihood of land cover change at each pixel. We evaluated our approach using the MODIS Collection 5.1 Land Cover Type product (MCD12Q1), focusing on areas that have experienced little change over the MODIS time series, and areas that have experienced well characterized change (e.g., deforestation). We show that the HMM method provides label sequences that are more accurate and that exhibit less year-to-year variability than label sequences produced by ensemble-decision-tree classification or by postprocessing heuristics that have been used in recent versions of MCD12Q1 product. The framework that we present offers an improvement over conventional multitemporal land cover classification methods, and it is widely applicable to problems in multitemporal land cover and land use monitoring.
Deep Audio-Visual Speech Recognition Afouras, Triantafyllos; Chung, Joon Son; Senior, Andrew ...
IEEE transactions on pattern analysis and machine intelligence,
12/2022, Volume:
44, Issue:
12
Journal Article
Peer reviewed
Open access
The goal of this work is to recognise phrases and sentences being spoken by a talking face, with or without the audio. Unlike previous works that have focussed on recognising a limited number of ...words or phrases, we tackle lip reading as an open-world problem - unconstrained natural language sentences, and in the wild videos. Our key contributions are: (1) we compare two models for lip reading, one using a CTC loss, and the other using a sequence-to-sequence loss. Both models are built on top of the transformer self-attention architecture; (2) we investigate to what extent lip reading is complementary to audio speech recognition, especially when the audio signal is noisy; (3) we introduce and publicly release a new dataset for audio-visual speech recognition, LRS2-BBC, consisting of thousands of natural sentences from British television. The models that we train surpass the performance of all previous work on a lip reading benchmark dataset by a significant margin.
PDF
