Illumination invariant facial recognition using a piecewise-constant lighting model

In this paper we demonstrate a simple and novel illumination model that can be used for illumination invariant facial recognition. This model requires no prior knowledge of the illumination conditions and can be used when there is only a single training image per-person. The proposed illumination model separates the effects of illumination over a small area of the face into two components; an additive component modelling the mean illumination and a multiplicative component, modelling the variance within the facial area. Illumination invariant facial recognition is performed in a piecewise manner, by splitting the face image into blocks, then normalizing the illumination within each block based on the new lighting model. The assumptions underlying this novel lighting model have been verified on the YaleB face database. We show that magnitude 2D Fourier features can be used as robust facial descriptors within the new lighting model. Using only a single training image per-person, our new method achieves high (in most cases 100%) identification accuracy on the YaleB, extended YaleB and CMU-PIE face databases.

Online Multiperson Tracking With Occlusion Reasoning and Unsupervised Track Motion Model

We address the problem of multi-target tracking in realistic crowded conditions by introducing a novel dual-stage online tracking algorithm. The problem of data-association between tracks and detections, based on appearance, is often complicated by partial occlusion. In the first stage, we address the issue of occlusion with a novel method of robust data-association, that can be used to compute the appearance similarity between tracks and detections without the need for explicit knowledge of the occluded regions. In the second stage, broken tracks are linked based on motion and appearance, using an online-learned linking model. The online-learned motion-model for track linking uses the confident tracks from the first stage tracker as training examples. The new approach has been tested on the town centre dataset and has performance comparable with the present state-of-the-art

Experimentally validated partial least squares model for dynamic line rating

This study presents a model based on partial least squares (PLS) regression for dynamic line rating (DLR). The model has been verified using data from field measurements, lab tests and outdoor experiments. Outdoor experimentation has been conducted both to verify the model predicted DLR and also to provide training data not available from field measurements, mainly heavily loaded conditions. The proposed model, unlike the direct measurement based DLR techniques, enables prediction of line rating for periods ahead of time whenever a reliable weather forecast is available. The PLS approach yields a very simple statistical model that accurately captures the physical performance of the conductor within a given environment without requiring a predetermination of parameters as required by many physical modelling techniques. Accuracy of the PLS model has been tested by predicting the conductor temperature for measurement sets other than those used for training. Being a linear model, it is straightforward to estimate the conductor ampacity for a set of predicted weather parameters. The PLS estimated ampacity has proven its accuracy through an outdoor experiment on a piece of the line conductor in real weather conditions.

3D Morphable Model Construction for Robust Ear and Face Recognition

Recent work suggests that the human ear varies significantly between different subjects and can be used for identification. In principle, therefore, using ears in addition to the face within a recognition system could improve accuracy and robustness, particularly for non-frontal views. The paper describes work that investigates this hypothesis using an approach based on the construction of a 3D morphable model of the head and ear. One issue with creating a model that includes the ear is that existing training datasets contain noise and partial occlusion. Rather than exclude these regions manually, a classifier has been developed which automates this process. When combined with a robust registration algorithm the resulting system enables full head morphable models to be constructed efficiently using less constrained datasets. The algorithm has been evaluated using registration consistency, model coverage and minimalism metrics, which together demonstrate the accuracy of the approach. To make it easier to build on this work, the source code has been made available online.

A Tree Augmented Classifier Based on Extreme Imprecise Dirichlet Model

In this paper we present TANC, i.e., a tree-augmented naive credal classifier based on imprecise probabilities; it models prior near-ignorance via the Extreme Imprecise Dirichlet Model (EDM) (Cano et al., 2007) and deals conservatively with missing data in the training set, without assuming them to be missing-at-random. The EDM is an approximation of the global Imprecise Dirichlet Model (IDM), which considerably simplifies the computation of upper and lower probabilities; yet, having been only recently introduced, the quality of the provided approximation needs still to be verified. As first contribution, we extensively compare the output of the naive credal classifier (one of the few cases in which the global IDM can be exactly implemented) when learned with the EDM and the global IDM; the output of the classifier appears to be identical in the vast majority of cases, thus supporting the adoption of the EDM in real classification problems. Then, by experiments we show that TANC is more reliable than the precise TAN (learned with uniform prior), and also that it provides better performance compared to a previous (Zaffalon, 2003) TAN model based on imprecise probabilities. TANC treats missing data by considering all possible completions of the training set, but avoiding an exponential increase of the computational times; eventually, we present some preliminary results with missing data.

Impact of Residual Transmit RF Impairments on Training-Based MIMO Systems

Radio-frequency (RF) impairments, which intimately exist in wireless communication systems, can severely limit the performance of multiple-input-multiple-output (MIMO) systems. Although we can resort to compensation schemes to mitigate some of these impairments, a certain amount of residual impairments always persists. In this paper, we consider a training-based point-to-point MIMO system with residual transmit RF impairments (RTRI) using spatial multiplexing transmission. Specifically, we derive a new linear channel estimator for the proposed model, and show that RTRI create an estimation error floor in the high signal-to-noise ratio (SNR) regime. Moreover, we derive closed-form expressions for the signal-to-noise-plus-interference ratio (SINR) distributions, along with analytical expressions for the ergodic achievable rates of zero-forcing, maximum ratio combining, and minimum mean-squared error receivers, respectively. In addition, we optimize the ergodic achievable rates with respect to the training sequence length and demonstrate that finite dimensional systems with RTRI generally require more training at high SNRs than those with ideal hardware. Finally, we extend our analysis to large-scale MIMO configurations, and derive deterministic equivalents of the ergodic achievable rates. It is shown that, by deploying large receive antenna arrays, the extra training requirements due to RTRI can be eliminated. In fact, with a sufficiently large number of receive antennas, systems with RTRI may even need less training than systems with ideal hardware.

A survey of perceived training differences between ophthalmology residents in Hong Kong and China.

Background: To study the differences in ophthalmology resident training between China and the Hong Kong Special Administrative Region (HKSAR).Methods: Training programs were selected from among the largest and best-known teaching hospitals. Ophthalmology residents were sent an anonymous 48-item questionnaire by mail. Work satisfaction, time allocation between training activities and volume of surgery performed were determined.Results: 50/75 residents (66.7 %) from China and 20/26 (76.9 %) from HKSAR completed the survey. Age (28.9 ± 2.5 vs. 30.2 ± 2.9 years, p = 0.15) and number of years in training (3.4 ± 1.6 vs. 2.8 ± 1.5, p = 0.19) were comparable between groups. The number of cataract procedures performed by HKSAR trainees (extra-capsular, median 80.0, quartile range: 30.0, 100.0; phacoemulsification, median: 20.0, quartile range: 0.0, 100.0) exceeded that for Chinese residents (extra-capsular: median = 0, p < 0.0001; phacoemulsification: median = 0, p < 0.0001). Chinese trainees spent more time completing medical charts (>50 % of time on charts: 62.5 % versus 5.3 %, p < 0.0001) and received less supervision (≥90 % of training supervised: 4.4 % versus 65 %, p < 0.0001). Chinese residents were more likely to feel underpaid (96.0 % vs. 31.6 %, p < 0.0001) and hoped their children would not practice medicine (69.4 % vs. 5.0 %, p = 0.0001) compared HKSAR residents.Conclusions: In this study, ophthalmology residents in China report strikingly less surgical experience and supervision, and lower satisfaction than HKSAR residents. The HKSAR model of hands-on resident training might be useful in improving the low cataract surgical rate in China.

Using a Discrete Hidden Markov Model Kernel for lip-based biometric identification

In this paper, a novel and effective lip-based biometric identification approach with the Discrete Hidden Markov Model Kernel (DHMMK) is developed. Lips are described by shape features (both geometrical and sequential) on two different grid layouts: rectangular and polar. These features are then specifically modeled by a DHMMK, and learnt by a support vector machine classifier. Our experiments are carried out in a ten-fold cross validation fashion on three different datasets, GPDS-ULPGC Face Dataset, PIE Face Dataset and RaFD Face Dataset. Results show that our approach has achieved an average classification accuracy of 99.8%, 97.13%, and 98.10%, using only two training images per class, on these three datasets, respectively. Our comparative studies further show that the DHMMK achieved a 53% improvement against the baseline HMM approach. The comparative ROC curves also confirm the efficacy of the proposed lip contour based biometrics learned by DHMMK. We also show that the performance of linear and RBF SVM is comparable under the frame work of DHMMK.

Impact of exercise training on cancer-induced cardiac dysfunction

Cachexia is a complex syndrome characterized by severe weight loss frequently observed in cancer patients and associated with poor prognosis. Cancer cachexia is also related to modifications in cardiac muscle structure and metabolism leading to cardiac dysfunction. In order to better understand the cardiac remodeling induced by bladder cancer and the impact of exercise training after diagnosis on its regulation, we used an animal model of bladder cancer induced by exposition to N-butyl-N-(4-hydroxybutyl)-nitrosamine (BBN) in the drinking water. Healthy animals and previously BBN exposed animals were submitted to a training program in a treadmill at a speed of 20m/min, 60 min/day, 5 days/week during 13 weeks. At the end of the protocol, animals exposed to BBN presented a significant decrease of body weight, in comparison with control groups, supporting the presence of cancer cachexia. Morphological analysis of the cardiac muscle sections revealed the presence of fibrosis and a significant decrease of cardiomyocyte’s cross-sectional area, suggesting the occurrence of cardiac dysfunction associated with bladder cancer. These modifications were accompanied by heart metabolic remodeling characterized by a decreased fatty acid oxidation given by diminished levels of ETFDH and of complex II subunit  from the respiratory chain. Exercise training promoted an increment of connexin 43, a protein involved in cardioprotection, and of c-kit, a protein present in cardiac stem cells. These results suggest an improved heart regenerative capacity induced by exercise training. In conclusion, endurance training seems an attractive non-pharmacological therapeutic option for the management of cardiac dysfunction in cancer cachexia.

Spiking neural network model of sound localisation using the interaural intensity difference

In this paper, a spiking neural network (SNN) architecture to simulate the sound localization ability of the mammalian auditory pathways using the interaural intensity difference cue is presented. The lateral superior olive was the inspiration for the architecture, which required the integration of an auditory periphery (cochlea) model and a model of the medial nucleus of the trapezoid body. The SNN uses leaky integrateand-fire excitatory and inhibitory spiking neurons, facilitating synapses and receptive fields. Experimentally derived headrelated transfer function (HRTF) acoustical data from adult domestic cats were employed to train and validate the localization ability of the architecture, training used the supervised learning algorithm called the remote supervision method to determine the azimuthal angles. The experimental results demonstrate that the architecture performs best when it is localizing high-frequency sound data in agreement with the biology, and also shows a high degree of robustness when the HRTF acoustical data is corrupted by noise.

Model comparison for temperature estimation inside buildings

This paper presents a comparison between a physical model and an artificial neural network model (NN) for temperature estimation inside a building room. Despite the obvious advantages of the physical model for structure optimisation purposes, this paper will test the performance of neural models for inside temperature estimation. The great advantage of the NN model is a big reduction of human effort time, because it is not needed to develop the structural geometry and structural thermal capacities and to simulate, which consumes a great human effort and great computation time. The NN model deals with this problem as a “black box” problem. We describe the use of the Radial Basis Function (RBF), the training method and a multi-objective genetic algorithm for optimisation/selection of the RBF neural network inputs and number of neurons.

Training neuro-fuzzy models using evolution based algorithms

The normal design process for neural networks or fuzzy systems involve two different phases: the determination of the best topology, which can be seen as a system identification problem, and the determination of its parameters, which can be envisaged as a parameter estimation problem. This latter issue, the determination of the model parameters (linear weights and interior knots) is the simplest task and is usually solved using gradient or hybrid schemes. The former issue, the topology determination, is an extremely complex task, especially if dealing with real-world problems.

The challenges of integrating the discussion of controversial issues in initial teacher training

In the framework of the Bologna process, and with regard to pre-service teacher education, it is necessary to model student-centred learning experiences in order to promote the required competences for future professional practice and critical participation in society. Despite the potential of discussion in promoting several competences, this methodology does not always integrate the teaching practices. This case study sought to: a) understand the experiences and views of future teachers from a School of Education on the use of discussion in their past education; and b) investigate the impact of an educational experience centred on discussion. Data were collected through narratives, questionnaires, interviews and participant observation. The learning situations experienced through this study contributed to the development of citizens more aware of their role in society and allowed the promotion of skills indispensable for an Elementary Education teacher.

Firing and training costs and labour market segmentation

This dissertation consists of three essays on the labour market impact of firing and training costs. The modelling framework resorts to the search and matching literature. The first chapter introduces firing costs, both liner and non-linear, in a new Keynesian model, analysing business cycle effects for different wage rigidity degrees. The second chapter adds training costs in a model of a segmented labour market, accessing the interaction between these two features and the skill composition of the labour force. Finally, the third chapter analyses empirically some of the issues raised in the second chapter.

Sonae MC: The road model of Kaizen

Sonae MC is considered the first success case of Kaizen in the retail industry. Before becoming a true role model for so many companies, there was a long road to walk. However, it may still be hard to understand the steps taken on the way. How could a training program develop into an integral continuous improvement system, and how did it affect the company – its people, culture, operations and strategy? How was it possible to get everyone on board? How could it be sustained until today, when Kaizen usually fails in the West? What were the critical factors for success?