Gaussian Process training with input noise

In standard Gaussian Process regression input locations are assumed to be noise free. We present a simple yet effective GP model for training on input points corrupted by i.i.d. Gaussian noise. To make computations tractable we use a local linear expansion about each input point. This allows the input noise to be recast as output noise proportional to the squared gradient of the GP posterior mean. The input noise variances are inferred from the data as extra hyperparameters. They are trained alongside other hyperparameters by the usual method of maximisation of the marginal likelihood. Training uses an iterative scheme, which alternates between optimising the hyperparameters and calculating the posterior gradient. Analytic predictive moments can then be found for Gaussian distributed test points. We compare our model to others over a range of different regression problems and show that it improves over current methods.

Automated Detection of Concrete Columns from Visual Data

After earthquakes, licensed inspectors use the established codes to assess the impact of damage on structural elements. It always takes them days to weeks. However, emergency responders (e.g. firefighters) must act within hours of a disaster event to enter damaged structures to save lives, and therefore cannot wait till an official assessment completes. This is a risk that firefighters have to take. Although Search and Rescue Organizations offer training seminars to familiarize firefighters with structural damage assessment, its effectiveness is hard to guarantee when firefighters perform life rescue and damage assessment operations together. Also, the training is not available to every firefighter. The authors therefore proposed a novel framework that can provide firefighters with a quick but crude assessment of damaged buildings through evaluating the visible damage on their critical structural elements (i.e. concrete columns in the study). This paper presents the first step of the framework. It aims to automate the detection of concrete columns from visual data. To achieve this, the typical shape of columns (long vertical lines) is recognized using edge detection and the Hough transform. The bounding rectangle for each pair of long vertical lines is then formed. When the resulting rectangle resembles a column and the material contained in the region of two long vertical lines is recognized as concrete, the region is marked as a concrete column surface. Real video/image data are used to test the method. The preliminary results indicate that concrete columns can be detected when they are not distant and have at least one surface visible.

Fractal dimension, wavelet shrinkage and anomaly detection for mine hunting

An anomaly detection approach is considered for the mine hunting in sonar imagery problem. The authors exploit previous work that used dual-tree wavelets and fractal dimension to adaptively suppress sand ripples and a matched filter as an initial detector. Here, lacunarity inspired features are extracted from the remaining false positives, again using dual-tree wavelets. A one-class support vector machine is then used to learn a decision boundary, based only on these false positives. The approach exploits the large quantities of 'normal' natural background data available but avoids the difficult requirement of collecting examples of targets in order to train a classifier. © 2012 The Institution of Engineering and Technology.

Factor analysis based VTS discriminative adaptive training

Vector Taylor Series (VTS) model based compensation is a powerful approach for noise robust speech recognition. An important extension to this approach is VTS adaptive training (VAT), which allows canonical models to be estimated on diverse noise-degraded training data. These canonical model can be estimated using EM-based approaches, allowing simple extensions to discriminative VAT (DVAT). However to ensure a diagonal corrupted speech covariance matrix the Jacobian (loading matrix) relating the noise and clean speech is diagonalised. In this work an approach for yielding optimal diagonal loading matrices based on minimising the expected KL-divergence between the diagonal loading matrix and "correct" distributions is proposed. The performance of DVAT using the standard and optimal diagonalisation was evaluated on both in-car collected data and the Aurora4 task. © 2012 IEEE.

N-best error simulation for training spoken dialogue systems

A recent trend in spoken dialogue research is the use of reinforcement learning to train dialogue systems in a simulated environment. Past researchers have shown that the types of errors that are simulated can have a significant effect on simulated dialogue performance. Since modern systems typically receive an N-best list of possible user utterances, it is important to be able to simulate a full N-best list of hypotheses. This paper presents a new method for simulating such errors based on logistic regression, as well as a new method for simulating the structure of N-best lists of semantics and their probabilities, based on the Dirichlet distribution. Off-line evaluations show that the new Dirichlet model results in a much closer match to the receiver operating characteristics (ROC) of the live data. Experiments also show that the logistic model gives confusions that are closer to the type of confusions observed in live situations. The hope is that these new error models will be able to improve the resulting performance of trained dialogue systems. © 2012 IEEE.

Complementary Phone Error training

This paper introduces a novel method for the training of a complementary acoustic model with respect to set of given acoustic models. The method is based upon an extension of the Minimum Phone Error (MPE) criterion and aims at producing a model that makes complementary phone errors to those already trained. The technique is therefore called Complementary Phone Error (CPE) training. The method is evaluated using an Arabic large vocabulary continuous speech recognition task. Reductions in word error rate (WER) after combination with a CPE-trained system were obtained with up to 0.7% absolute for a system trained on 172 hours of acoustic data and up to 0.2% absolute for the final system trained on nearly 2000 hours of Arabic data.

Training and assignment of multi-skilled workers for implementing seru production systems

Confronted with high variety and low volume market demands, many companies, especially the Japanese electronics manufacturing companies, have reconfigured their conveyor assembly lines and adopted seru production systems. Seru production system is a new type of work-cell-based manufacturing system. A lot of successful practices and experience show that seru production system can gain considerable flexibility of job shop and high efficiency of conveyor assembly line. In implementing seru production, the multi-skilled worker is the most important precondition, and some issues about multi-skilled workers are central and foremost. In this paper, we investigate the training and assignment problem of workers when a conveyor assembly line is entirely reconfigured into several serus. We formulate a mathematical model with double objectives which aim to minimize the total training cost and to balance the total processing times among multi-skilled workers in each seru. To obtain the satisfied task-to-worker training plan and worker-to-seru assignment plan, a three-stage heuristic algorithm with nine steps is developed to solve this mathematical model. Then, several computational cases are taken and computed by MATLAB programming. The computation and analysis results validate the performances of the proposed mathematical model and heuristic algorithm. © 2013 Springer-Verlag London.

Use of microbial community to evaluate performance of a wetland system in treating Pb/Zn mine drainage

The performance of a wetland system in treating lead (Pb)/zinc (Zn) mine drainage was evaluated by using the polyurethane foam unit (PFU) microbial community (method), which has been adopted by China as a standardized procedure for monitoring water quality. The wetland system consisted of four cells with three dominant plants: Typha latifolia, Phragmites australis and Paspalum distichum. Physicochemical characteristics [pH, EC, content of total suspended solid (TSS) and metals (Pb, Zn, Cd, and Cu)] and PFU microbial community in water samples had been investigated from seven sampling sites. The results indicated that the concentrations of Pb, Zn, Cd, Cu, and TSS in the mine drainage were gradually reduced from the inlet to the outlet of the wetland system and 99%, 98%, 75%, 83%, and 68% of these metals and TSS respectively, had been reduced in concentration after the drainage passed through the wetland system. A total of 105 protozoan species were identified, the number of protozoa species and the diversity index (DI) gradually increased, while the heterotrophic index (HI) gradually decreased from the inlet to the outlet of the wetland system. The results indicated that DI, HI, and total number species of protozoa could be used as biological indicators indicating the improvement of water quality.