The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
We introduce a dynamical spatio-temporal model formalized as a recurrent neural network for forecasting time series of spatial processes, i.e. series of observations sharing temporal and spatial dependencies. The model learns these dependencies through a structured latent dynamical component, while a decoder predicts the observations from the latent representations. We consider several variants of...
The paper presents theoretical grounds of recurrent-and-parallel computing applying in combinatorial GMDH algorithm for modeling and prediction of complex multidimensional interrelated processes in the class of vector autoregressive models. The effectiveness of the constructed algorithm is demonstrated by modeling of interrelated processes in the field of Ukraine energy sphere with the purpose of...
Typical techniques for sequence classification are designed for well-segmented sequences which have been edited to remove noisy or irrelevant parts. Therefore, such methods cannot be easily applied on noisy sequences expected in real-world applications. In this paper, we present the Temporal Attention-Gated Model (TAGM) which integrates ideas from attention models and gated recurrent networks to better...
With the continuous development of online learning platforms, educational data analytics and prediction have become a promising research field, which are helpful for the development of personalized learning system. However, the indicator's selection process does not combine with the whole learning process, which may affect the accuracy of prediction results. In this paper, we induce 19 behavior indicators...
The optimization of a model that expresses time series data for a given period is a problem associated with the development of a regression model that estimates future data on the extension of the past data time series. This is a two-step optimization problem where the order of past data used in the regression model (number of orders of the solution space) is decided, and weighted coefficients for...
In this paper, we compare different deep neural network approaches for motion prediction within a highway entrance scenario. The focus of our work lies on models that operate on limited history of data in order to fulfill the Markov property1 and be usable within an integrated prediction and motion planning framework for automated vehicles. We examine different model structures and feature combinations...
Understanding the dynamics of urban environments is crucial for path planning and safe navigation. However, the dynamics might be extremely complex making learning the environment an unfathomable task. Within the methods available for learning dynamic environments, dynamic Gaussian process occupancy maps (DGPOM) are very attractive because they can produce spatially-continuous occupancy maps taking...
We develop the Weibull partition model (WPM), which defines a novel nonparametric stochastic process over distributions of partitions of sequential data, aiming at directly modeling the boundaries of segments comprising the sequence. The Weibull partition model employs a Dirichlet process mixture with a Weibull kernel. Weibull distributions having a closed-form cumulative density function plays an...
In active learning for Automatic Speech Recognition (ASR), a portion of data is automatically selected for manual transcription. The objective is to improve ASR performance with retrained acoustic models. The standard approaches are based on confidence of individual sentences. In this study, we look into an alternative view on transcript label quality, in which Gaussian Supervector Distance (GSD)...
Classification of sparsely and irregularly sampled time series data is a challenging machine learning task. To tackle this problem, we present a learning in model space framework in which time-continuous dynamical system models are first inferred from individual time series and then the inferred models are used to represent these time series for the classification task. In contrast to the existing...
Spatio-temporal data is intrinsically high dimensional, so unsupervised modeling is only feasible if we can exploit structure in the process. When the dynamics are local in both space and time, this structure can be exploited by splitting the global field into many lower-dimensional “light cones”. We review light cone decompositions for predictive state reconstruction, introducing three simple light...
With the rapid development of biology, its relevant literature will be more and more important for researchers to dig out more valuable knowledge. Named Entity Recognition (NER) for biology literature is a very common and important task in these works. With the increase of the literature amount, the recognition speed becomes slower and less accurate. In order to tackle this problem, a MapReduce based...
This paper presents an image recognition technique based on discriminative models using features generated from separable lattice hidden Markov models (SL-HMMs). A major problem in image recognition is that the recognition performance is degraded by geometric variations such as that in position and size of the object to be recognized. SL-HMMs have been proposed to solve this problem. SL-HMMs are an...
Evolution of Internet of Things (IoT) demands interconnection of many autonomous and heterogeneous devices. Several such devices have very limited power. Every bit transmission consumes power and it is critical. The efficient power usage is a challenge. In this paper, we model an IoT device as a simple Hidden Markov Model (HMM) with a finite number of states and well determined emission probabilities...
This paper addresses the problem of identifying signals of interest from discrete-time sequences contaminated by erroneous segments, which we define as the part of time series whose dynamic patterns are inconsistent with that of the signals. Assuming the signals of interest consist of consecutive samples with arbitrary starting point, duration and following a stationary dynamic pattern, we propose...
Due to increasing urban population and growing number of motor vehicles, traffic congestion is becoming a major problem of the 21st century. One of the main reasons behind traffic congestion is accidents which can not only result in casualties and losses for the participants, but also in wasted and lost time for the others that are stuck behind the wheels. Early detection of an accident can save lives,...
We introduce a novel dynamic model for discrete time-series data, in which the temporal sampling may be nonuniform. The model is specified by constructing a hierarchy of Poisson factor analysis blocks, one for the transitions between latent states and the other for the emissions between latent states and observations. Latent variables are binary and linked to Poisson factor analysis via Bernoulli-Poisson...
Automatic identification of the relevant frames of references (or external task parameters) in programming by demonstration using the task-parameterized Gaussian mixture regression (TP-GMM) is addressed in this paper. While performing a given task, there may be several external task parameters, some of which are relevant to the specific task, while some others are not relevant. Identifying the irrelevant...
In recent years Unmanned Aerial Vehicles (UAVs) have become a very popular topic in many different research fields and industrial applications. These technologies, and the related industries, are expected to grow dramatically by 2020. Although the systems designed to control UAVs are increasingly autonomous, the role of UAV operators is still a critical aspect that guarantee the mission success, specially...
This paper outlines preliminary steps towards the development of an audio-based room-occupancy analysis model. Our approach borrows from speech recognition tradition and is based on Gaussian Mixtures and Hidden Markov Models. We analyse possible challenges encountered in the development of such a model, and offer several solutions including feature design and prediction strategies. We provide results...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.