TOPS (Task optimization in the presence of signal-dependent noise) model

This paper proposes a movement trajectory planning model, which is a maximum task achievement model in which signal-dependent noise is added to the movement command. In the proposed model, two optimization criteria are combined, maximum task achievement and minimum energy consumption. The proposed model has the feature that the end-point boundary conditions for position, velocity, and acceleration need not be prespecified. Consequently, the method can be applied not only to the simple point-to-point movement, but to any task. In the method in this paper, the hand trajectory is derived by a psychophysical experiment and a numerical experiment for the case in which the target is not stationary, but is a moving region. It is shown that the trajectory predicted from the minimum jerk model or the minimum torque change model differs considerably from the results of the psychophysical experiment. But the trajectory predicted from the maximum task achievement model shows good qualitative agreement with the hand trajectory obtained from the psychophysical experiment. © 2004 Wiley Periodicals, Inc.

Task-level control of the lateral leg spring model of cockroach locomotion

The Lateral Leg Spring model (LLS) was developed by Schmitt and Holmes to model the horizontal-plane dynamics of a running cockroach. The model captures several salient features of real insect locomotion, and demonstrates that horizontal plane locomotion can be passively stabilized by a well-tuned mechanical system, thus requiring minimal neural reflexes. We propose two enhancements to the LLS model. First, we derive the dynamical equations for a more flexible placement of the center of pressure (COP), which enables the model to capture the phase relationship between the body orientation and center-of-mass (COM) heading in a simpler manner than previously possible. Second, we propose a reduced LLS "plant model" and biologically inspired control law that enables the model to follow along a virtual wall, much like antenna-based wall following in cockroaches. © 2006 Springer.

Discriminative language model adaptation for Mandarin broadcast speech transcription and translation

This paper investigates unsupervised test-time adaptation of language models (LM) using discriminative methods for a Mandarin broadcast speech transcription and translation task. A standard approach to adapt interpolated language models to is to optimize the component weights by minimizing the perplexity on supervision data. This is a widely made approximation for language modeling in automatic speech recognition (ASR) systems. For speech translation tasks, it is unclear whether a strong correlation still exists between perplexity and various forms of error cost functions in recognition and translation stages. The proposed minimum Bayes risk (MBR) based approach provides a flexible framework for unsupervised LM adaptation. It generalizes to a variety of forms of recognition and translation error metrics. LM adaptation is performed at the audio document level using either the character error rate (CER), or translation edit rate (TER) as the cost function. An efficient parameter estimation scheme using the extended Baum-Welch (EBW) algorithm is proposed. Experimental results on a state-of-the-art speech recognition and translation system are presented. The MBR adapted language models gave the best recognition and translation performance and reduced the TER score by up to 0.54% absolute. © 2007 IEEE.

Language model combination and adaptation using weighted finite state transducers

In speech recognition systems language model (LMs) are often constructed by training and combining multiple n-gram models. They can be either used to represent different genres or tasks found in diverse text sources, or capture stochastic properties of different linguistic symbol sequences, for example, syllables and words. Unsupervised LM adaptation may also be used to further improve robustness to varying styles or tasks. When using these techniques, extensive software changes are often required. In this paper an alternative and more general approach based on weighted finite state transducers (WFSTs) is investigated for LM combination and adaptation. As it is entirely based on well-defined WFST operations, minimum change to decoding tools is needed. A wide range of LM combination configurations can be flexibly supported. An efficient on-the-fly WFST decoding algorithm is also proposed. Significant error rate gains of 7.3% relative were obtained on a state-of-the-art broadcast audio recognition task using a history dependently adapted multi-level LM modelling both syllable and word sequences. ©2010 IEEE.

Structure learning in a sensorimotor association task.

Learning is often understood as an organism's gradual acquisition of the association between a given sensory stimulus and the correct motor response. Mathematically, this corresponds to regressing a mapping between the set of observations and the set of actions. Recently, however, it has been shown both in cognitive and motor neuroscience that humans are not only able to learn particular stimulus-response mappings, but are also able to extract abstract structural invariants that facilitate generalization to novel tasks. Here we show how such structure learning can enhance facilitation in a sensorimotor association task performed by human subjects. Using regression and reinforcement learning models we show that the observed facilitation cannot be explained by these basic models of learning stimulus-response associations. We show, however, that the observed data can be explained by a hierarchical Bayesian model that performs structure learning. In line with previous results from cognitive tasks, this suggests that hierarchical Bayesian inference might provide a common framework to explain both the learning of specific stimulus-response associations and the learning of abstract structures that are shared by different task environments.

Speaker and noise factorisation on the AURORA4 task

For many realistic scenarios, there are multiple factors that affect the clean speech signal. In this work approaches to handling two such factors, speaker and background noise differences, simultaneously are described. A new adaptation scheme is proposed. Here the acoustic models are first adapted to the target speaker via an MLLR transform. This is followed by adaptation to the target noise environment via model-based vector Taylor series (VTS) compensation. These speaker and noise transforms are jointly estimated, using maximum likelihood. Experiments on the AURORA4 task demonstrate that this adaptation scheme provides improved performance over VTS-based noise adaptation. In addition, this framework enables the speech and noise to be factorised, allowing the speaker transform estimated in one noise condition to be successfully used in a different noise condition. © 2011 IEEE.

Towards the development of an integrated design framework using the Blackboard model

Current research into the process of engineering design is extending the use of computers towards the acquisition, representation and application of design process knowledge in addition to the existing storage and manipulation of product-based models of design objects. This is a difficult task because the design of mechanical systems is a complex, often unpredictable process involving ill-structured problem solving skills and large amounts of knowledge, some which may be of an incomplete and subjective nature. Design problems require the integration of a variety of modes of working such as numerical, graphical, algorithmic or heuristic and demand products through synthesis, analysis and evaluation activities.

This report presents the results of a feasibility study into the blackboard approach and discusses the development of an initial prototype system that will enable an alphanumeric design dialogue between a designer and an expert to be analysed in a formal way, thus providing real-life protocol data on which to base the blackboard message structures.

Facilitation of learning induced by both random and gradual visuomotor task variation.

Motor task variation has been shown to be a key ingredient in skill transfer, retention, and structural learning. However, many studies only compare training of randomly varying tasks to either blocked or null training, and it is not clear how experiencing different nonrandom temporal orderings of tasks might affect the learning process. Here we study learning in human subjects who experience the same set of visuomotor rotations, evenly spaced between -60° and +60°, either in a random order or in an order in which the rotation angle changed gradually. We compared subsequent learning of three test blocks of +30°→-30°→+30° rotations. The groups that underwent either random or gradual training showed significant (P < 0.01) facilitation of learning in the test blocks compared with a control group who had not experienced any visuomotor rotations before. We also found that movement initiation times in the random group during the test blocks were significantly (P < 0.05) lower than for the gradual or the control group. When we fit a state-space model with fast and slow learning processes to our data, we found that the differences in performance in the test block were consistent with the gradual or random task variation changing the learning and retention rates of only the fast learning process. Such adaptation of learning rates may be a key feature of ongoing meta-learning processes. Our results therefore suggest that both gradual and random task variation can induce meta-learning and that random learning has an advantage in terms of shorter initiation times, suggesting less reliance on cognitive processes.

Content Based Integration of Construction Site Images in AEC/FM Model Based Systems

The Architecture, Engineering, Construction and Facilities Management (AEC/FM) industry is rapidly becoming a multidisciplinary, multinational and multi-billion dollar economy, involving large numbers of actors working concurrently at different locations and using heterogeneous software and hardware technologies. Since the beginning of the last decade, a great deal of effort has been spent within the field of construction IT in order to integrate data and information from most computer tools used to carry out engineering projects. For this purpose, a number of integration models have been developed, like web-centric systems and construction project modeling, a useful approach in representing construction projects and integrating data from various civil engineering applications. In the modern, distributed and dynamic construction environment it is important to retrieve and exchange information from different sources and in different data formats in order to improve the processes supported by these systems. Previous research demonstrated that a major hurdle in AEC/FM data integration in such systems is caused by its variety of data types and that a significant part of the data is stored in semi-structured or unstructured formats. Therefore, new integrative approaches are needed to handle non-structured data types like images and text files. This research is focused on the integration of construction site images. These images are a significant part of the construction documentation with thousands stored in site photographs logs of large scale projects. However, locating and identifying such data needed for the important decision making processes is a very hard and time-consuming task, while so far, there are no automated methods for associating them with other related objects. Therefore, automated methods for the integration of construction images are important for construction information management. During this research, processes for retrieval, classification, and integration of construction images in AEC/FM model based systems have been explored. Specifically, a combination of techniques from the areas of image and video processing, computer vision, information retrieval, statistics and content-based image and video retrieval have been deployed in order to develop a methodology for the retrieval of related construction site image data from components of a project model. This method has been tested on available construction site images from a variety of sources like past and current building construction and transportation projects and is able to automatically classify, store, integrate and retrieve image data files in inter-organizational systems so as to allow their usage in project management related tasks.

Use of contexts in language model interpolation and adaptation

Language models (LMs) are often constructed by building multiple individual component models that are combined using context independent interpolation weights. By tuning these weights, using either perplexity or discriminative approaches, it is possible to adapt LMs to a particular task. This paper investigates the use of context dependent weighting in both interpolation and test-time adaptation of language models. Depending on the previous word contexts, a discrete history weighting function is used to adjust the contribution from each component model. As this dramatically increases the number of parameters to estimate, robust weight estimation schemes are required. Several approaches are described in this paper. The first approach is based on MAP estimation where interpolation weights of lower order contexts are used as smoothing priors. The second approach uses training data to ensure robust estimation of LM interpolation weights. This can also serve as a smoothing prior for MAP adaptation. A normalized perplexity metric is proposed to handle the bias of the standard perplexity criterion to corpus size. A range of schemes to combine weight information obtained from training data and test data hypotheses are also proposed to improve robustness during context dependent LM adaptation. In addition, a minimum Bayes' risk (MBR) based discriminative training scheme is also proposed. An efficient weighted finite state transducer (WFST) decoding algorithm for context dependent interpolation is also presented. The proposed technique was evaluated using a state-of-the-art Mandarin Chinese broadcast speech transcription task. Character error rate (CER) reductions up to 7.3 relative were obtained as well as consistent perplexity improvements. © 2012 Elsevier Ltd. All rights reserved.

Multi-Modal Image Retrieval from Construction Databases and Model-Based Systems

In the modern and dynamic construction environment it is important to access information in a fast and efficient manner in order to improve the decision making processes for construction managers. This capability is, in most cases, straightforward with today’s technologies for data types with an inherent structure that resides primarily on established database structures like estimating and scheduling software. However, previous research has demonstrated that a significant percentage of construction data is stored in semi-structured or unstructured data formats (text, images, etc.) and that manually locating and identifying such data is a very hard and time-consuming task. This paper focuses on construction site image data and presents a novel image retrieval model that interfaces with established construction data management structures. This model is designed to retrieve images from related objects in project models or construction databases using location, date, and material information (extracted from the image content with pattern recognition techniques).

A crowding model of visual clutter.

Visual information is difficult to search and interpret when the density of the displayed information is high or the layout is chaotic. Visual information that exhibits such properties is generally referred to as being "cluttered." Clutter should be avoided in information visualizations and interface design in general because it can severely degrade task performance. Although previous studies have identified computable correlates of clutter (such as local feature variance and edge density), understanding of why humans perceive some scenes as being more cluttered than others remains limited. Here, we explore an account of clutter that is inspired by findings from visual perception studies. Specifically, we test the hypothesis that the so-called "crowding" phenomenon is an important constituent of clutter. We constructed an algorithm to predict visual clutter in arbitrary images by estimating the perceptual impairment due to crowding. After verifying that this model can reproduce crowding data we tested whether it can also predict clutter. We found that its predictions correlate well with both subjective clutter assessments and search performance in cluttered scenes. These results suggest that crowding and clutter may indeed be closely related concepts and suggest avenues for further research.

A Hierarchical Model for Ordinal Matrix Factorization

This paper proposes a hierarchical probabilistic model for ordinal matrix factorization. Unlike previous approaches, we model the ordinal nature of the data and take a principled approach to incorporating priors for the hidden variables. Two algorithms are presented for inference, one based on Gibbs sampling and one based on variational Bayes. Importantly, these algorithms may be implemented in the factorization of very large matrices with missing entries. The model is evaluated on a collaborative filtering task, where users have rated a collection of movies and the system is asked to predict their ratings for other movies. The Netflix data set is used for evaluation, which consists of around 100 million ratings. Using root mean-squared error (RMSE) as an evaluation metric, results show that the suggested model outperforms alternative factorization techniques. Results also show how Gibbs sampling outperforms variational Bayes on this task, despite the large number of ratings and model parameters. Matlab implementations of the proposed algorithms are available from cogsys.imm.dtu.dk/ordinalmatrixfactorization.