Automatic detection and classification of football players

Color segmentation of images usually requires a manual selection and classification of samples to train the system. This paper presents an automatic system that performs these tasks without the need of a long training, providing a useful tool to detect and identify figures. In real situations, it is necessary to repeat the training process if light conditions change, or if, in the same scenario, the colors of the figures and the background may have changed, being useful a fast training method. A direct application of this method is the detection and identification of football players.

Robust face recognition with partial occlusion, illumination variation and limited training data by optimal feature selection

This study investigates face recognition with partial occlusion, illumination variation and their combination, assuming no prior information about the mismatch, and limited training data for each person. The authors extend their previous posterior union model (PUM) to give a new method capable of dealing with all these problems. PUM is an approach for selecting the optimal local image features for recognition to improve robustness to partial occlusion. The extension is in two stages. First, authors extend PUM from a probability-based formulation to a similarity-based formulation, so that it operates with as little as one single training sample to offer robustness to partial occlusion. Second, they extend this new formulation to make it robust to illumination variation, and to combined illumination variation and partial occlusion, by a novel combination of multicondition relighting and optimal feature selection. To evaluate the new methods, a number of databases with various simulated and realistic occlusion/illumination mismatches have been used. The results have demonstrated the improved robustness of the new methods.

An efficient feature selection method for mobile devices with application to activity recognition

This paper presents a feature selection method for data classification, which combines a model-based variable selection technique and a fast two-stage subset selection algorithm. The relationship between a specified (and complete) set of candidate features and the class label is modelled using a non-linear full regression model which is linear-in-the-parameters. The performance of a sub-model measured by the sum of the squared-errors (SSE) is used to score the informativeness of the subset of features involved in the sub-model. The two-stage subset selection algorithm approaches a solution sub-model with the SSE being locally minimized. The features involved in the solution sub-model are selected as inputs to support vector machines (SVMs) for classification. The memory requirement of this algorithm is independent of the number of training patterns. This property makes this method suitable for applications executed in mobile devices where physical RAM memory is very limited. An application was developed for activity recognition, which implements the proposed feature selection algorithm and an SVM training procedure. Experiments are carried out with the application running on a PDA for human activity recognition using accelerometer data. A comparison with an information gain based feature selection method demonstrates the effectiveness and efficiency of the proposed algorithm.

Speaker Recognition In Noisy Conditions With Limited Training Data

In this paper we present a novel method for performing speaker recognition with very limited training data and in the presence of background noise. Similarity-based speaker recognition is considered so that speaker models can be created with limited training speech data. The proposed similarity is a form of cosine similarity used as a distance measure between speech feature vectors. Each speech frame is modelled using subband features, and into this framework, multicondition training and optimal feature selection are introduced, making the system capable of performing speaker recognition in the presence of realistic, time-varying noise, which is unknown during training. Speaker identi?cation experiments were carried out using the SPIDRE database. The performance of the proposed new system for noise compensation is compared to that of an oracle model; the speaker identi?cation accuracy for clean speech by the new system trained with limited training data is compared to that of a GMM trained with several minutes of speech. Both comparisons have demonstrated the effectiveness of the new model. Finally, experiments were carried out to test the new model for speaker identi?cation given limited training data and with differing levels and types of realistic background noise. The results have demonstrated the robustness of the new system.

Robust Multimodal Person Identification With Limited Training Data

This paper presents a novel method of audio-visual feature-level fusion for person identification where both the speech and facial modalities may be corrupted, and there is a lack of prior knowledge about the corruption. Furthermore, we assume there are limited amount of training data for each modality (e.g., a short training speech segment and a single training facial image for each person). A new multimodal feature representation and a modified cosine similarity are introduced to combine and compare bimodal features with limited training data, as well as vastly differing data rates and feature sizes. Optimal feature selection and multicondition training are used to reduce the mismatch between training and testing, thereby making the system robust to unknown bimodal corruption. Experiments have been carried out on a bimodal dataset created from the SPIDRE speaker recognition database and AR face recognition database with variable noise corruption of speech and occlusion in the face images. The system's speaker identification performance on the SPIDRE database, and facial identification performance on the AR database, is comparable with the literature. Combining both modalities using the new method of multimodal fusion leads to significantly improved accuracy over the unimodal systems, even when both modalities have been corrupted. The new method also shows improved identification accuracy compared with the bimodal systems based on multicondition model training or missing-feature decoding alone.

How Do Trainees Rate the Impact of a Short Cognitive Behavioural Training Programme on their Knowledge and Skills?

Background: A strong evidence base for cognitive behavioural therapy has led to CBT models becoming available within mainstream mental health services. As the concept of stepped care develops, new less intensive mental health interventions such as guided self-help are emerging, delivered by staff not trained to the level of accredited Cognitive Behavioural Therapists. Aim: The aim of this study was to determine how mental health staff evaluated the usefulness of a short training programme in CBT concepts, models and techniques for routine clinical practice.
Method: A cohort of mental health staff (n = 102) completed pre- and posttraining self-report questionnaires measuring trainee perceptions of the impact of a short training programme on knowledge and skills. Mentors and managers were also asked to comment on perceived impact of the training.
Results: Trainees and mentors reported perceived gains in knowledge and skills posttraining and at 1-year follow-up. Managers and trainees reported perceived improvements in skills and practice. Conclusion: A short Cognitive Behavioural skills programme can enable mental health staff to integrate basic CB knowledge and skills into routine clinical practice.

Prevalence and Causes of Prescribing ErrorsL The PRescribing Outcomes for Trainee Doctors Engaged in Clinical Training (PROTECT) Study

Objectives: Study objectives were to investigate the prevalence and causes of prescribing errors amongst foundation doctors (i.e. junior doctors in their first (F1) or second (F2) year of post-graduate training), describe their knowledge and experience of prescribing errors, and explore their self-efficacy (i.e. confidence) in prescribing.

Method: A three-part mixed-methods design was used, comprising: prospective observational study; semi-structured interviews and cross-sectional survey. All doctors prescribing in eight purposively selected hospitals in Scotland participated. All foundation doctors throughout Scotland participated in the survey. The number of prescribing errors per patient, doctor, ward and hospital, perceived causes of errors and a measure of doctors’ self-efficacy were established.

Results: 4710 patient charts and 44,726 prescribed medicines were reviewed. There were 3364 errors, affecting 1700 (36.1%) charts (overall error rate: 7.5%; F1:7.4%; F2:8.6%; consultants:6.3%). Higher error rates were associated with : teaching hospitals (p,0.001), surgical (p = ,0.001) or mixed wards (0.008) rather thanmedical ward, higher patient turnover wards (p,0.001), a greater number of prescribed medicines (p,0.001) and the months December and June (p,0.001). One hundred errors were discussed in 40 interviews. Error causation was multi-factorial; work environment and team factors were particularly noted. Of 548 completed questionnaires (national response rate of 35.4%), 508 (92.7% of respondents) reported errors, most of which (328 (64.6%) did not reach the patient. Pressure from other staff, workload and interruptions were cited as the main causes of errors. Foundation year 2 doctors reported greater confidence than year 1 doctors in deciding the most appropriate medication regimen.

Conclusions: Prescribing errors are frequent and of complex causation. Foundation doctors made more errors than other doctors, but undertook the majority of prescribing, making them a key target for intervention. Contributing causes included work environment, team, task, individual and patient factors. Further work is needed to develop and assess interventions that address these.

Attitudes of Irish dental graduates to vocational training

INTRODUCTION: Vocational training (VT) is a mandatory 12 month period for UK dental graduates after graduation. Graduates of Irish Dental Schools are eligible to enter the general dental service in Ireland or obtain an NHS performers list number in the UK immediately after qualification. Reports would suggest that some graduates of Irish Dental Schools are choosing to take part in VT in the UK and find the experience beneficial. This study aimed to record the uptake of VT amongst recent graduates from University College Cork and to document their experiences. It was designed to compare the attitudes and experiences of graduates of Irish Dental Schools who undertook VT compared with those who entered the general dental service.

METHOD: A self-completion questionnaire was distributed by e-mail to dental graduates from University College Cork who had graduated 2001-2007. Responses were returned by e-mail or post.

RESULTS: The response rate was 68.9%. There has been an increase in the numbers of graduates taking part in VT each year since 2004. 92.5% of Vocational Dental Practitioners (VDPs) found their experience beneficial as they received a guaranteed source of income, had a supportive peer network and worked in a positive learning environment. However, some felt that they earned a lower income than their associate colleagues, others found the pace of practice slow and that the duration of the training period was excessive. Eighty-five per cent of VDPs would choose the same position again after graduation as compared with 61.8% of associates (P < 0.001). Ninety per cent of VDPs would advise current undergraduates to take part in VT as compared with 51% of associates (P < 0.001). A larger proportion of VDPs had taken part in postgraduate studies but there was no significant difference between the two groups.

CONCLUSIONS: Larger proportions of recent graduates are undertaking vocational training.--The majority of VDPs and associates find their initial employment position beneficial.--VDPs benefit from a guaranteed source of income, a supportive peer network and a positive learning environment.--Some associates suffered from a lack of support, feeling isolated and overwhelmed with patients.--The majority of previous VDPs and associates would recommend VT to current undergraduates.--Almost 40% of associates would now choose to take part in VT if given the opportunity.

Graduate Attitudes towards Vocational Training

Introduction: Vocational training (VT) is a mandatory requirement for all UK dental graduates prior to entering NHS practice. The VT period provides structured, supervised experience supported by study days and interaction with peers. It is not compulsory for Irish dental graduates working in either Ireland or the UK to undertake VT but yet a proportion voluntarily do so each year.

Objectives: This study was designed to explore the choices made by Irish dental graduates. It aimed to record any benefits of VT and its impact upon future career choices.

Method: A self-completion questionnaire was developed and piloted before being circulated electronically to recent dental graduates from University College Cork. After collecting demographic information respondents were asked to indicate if they pursued vocational training on graduation, give their perception of their post-graduation experience, describe their current work profile and detail any formal postgraduate studies.

Results: 35% of respondents opted to undertake VT and 79% did so in the UK. Those who completed VT regarded it as a very positive experience with benefits including: working in a positive learning environment, help on demand and interaction with peers. Of those who chose VT, 49% have pursued some form of further formal postgraduate study as compared to 40% of those who did not. All of the respondents who completed VT indicated they would recommend it to current Irish graduates. The majority of those who took up an associate position immediately after graduation reported that this was beneficial but up to three quarters would recommend current graduates undertake VT and 45% would now chose to do so themselves.

Conclusions: Increasing numbers of Irish graduates are moving to the UK to undertake VT and they find it a beneficial experience. In addition, those who undertook VT were more likely to undertake formal postgraduate study.

An Efficient LS-SVM-Based Method for Fuzzy System Construction

This paper proposes an efficient learning mechanism to build fuzzy rule-based systems through the construction of sparse least-squares support vector machines (LS-SVMs). In addition to the significantly reduced computational complexity in model training, the resultant LS-SVM-based fuzzy system is sparser while offers satisfactory generalization capability over unseen data. It is well known that the LS-SVMs have their computational advantage over conventional SVMs in the model training process; however, the model sparseness is lost, which is the main drawback of LS-SVMs. This is an open problem for the LS-SVMs. To tackle the nonsparseness issue, a new regression alternative to the Lagrangian solution for the LS-SVM is first presented. A novel efficient learning mechanism is then proposed in this paper to extract a sparse set of support vectors for generating fuzzy IF-THEN rules. This novel mechanism works in a stepwise subset selection manner, including a forward expansion phase and a backward exclusion phase in each selection step. The implementation of the algorithm is computationally very efficient due to the introduction of a few key techniques to avoid the matrix inverse operations to accelerate the training process. The computational efficiency is also confirmed by detailed computational complexity analysis. As a result, the proposed approach is not only able to achieve the sparseness of the resultant LS-SVM-based fuzzy systems but significantly reduces the amount of computational effort in model training as well. Three experimental examples are presented to demonstrate the effectiveness and efficiency of the proposed learning mechanism and the sparseness of the obtained LS-SVM-based fuzzy systems, in comparison with other SVM-based learning techniques.

Robust bimodal person identification using face and speech with limited training data and corruption of both modalities

This paper presents a novel method of audio-visual fusion for person identification where both the speech and facial modalities may be corrupted, and there is a lack of prior knowledge about the corruption. Furthermore, we assume there is a limited amount of training data for each modality (e.g., a short training speech segment and a single training facial image for each person). A new representation and a modified cosine similarity are introduced for combining and comparing bimodal features with limited training data as well as vastly differing data rates and feature sizes. Optimal feature selection and multicondition training are used to reduce the mismatch between training and testing, thereby making the system robust to unknown bimodal corruption. Experiments have been carried out on a bimodal data set created from the SPIDRE and AR databases with variable noise corruption of speech and occlusion in the face images. The new method has demonstrated improved recognition accuracy.

A realistic evaluation of track and trigger systems and acute care training for early recognition and treatment of deteriorating ward-based patients: research protocol.

Aim The aim of the study is to evaluate factors that enable or constrain the implementation and service delivery of early warnings systems or acute care training in practice. Background To date there is limited evidence to support the effectiveness of acute care initiatives (early warning systems, acute care training, outreach) in reducing the number of adverse events (cardiac arrest, death, unanticipated Intensive Care admission) through increased recognition and management of deteriorating ward based patients in hospital [1-3]. The reasons posited are that previous research primarily focused on measuring patient outcomes following the implementation of an intervention or programme without considering the social factors (the organisation, the people, external influences) which may have affected the process of implementation and hence measured end-points. Further research which considers the social processes is required in order to understand why a programme works, or does not work, in particular circumstances [4]. Method The design is a multiple case study approach of four general wards in two acute hospitals where Early Warning Systems (EWS) and Acute Life-threatening Events Recognition and Treatment (ALERT) course have been implemented. Various methods are being used to collect data about individual capacities, interpersonal relationships and institutional balance and infrastructures in order to understand the intended and unintended process outcomes of implementing EWS and ALERT in practice. This information will be gathered from individual and focus group interviews with key participants (ALERT facilitators, nursing and medical ALERT instructors, ward managers, doctors, ward nurses and health care assistants from each hospital); non-participant observation of ward organisation and structure; audit of patients' EWS charts and audit of the medical notes of patients who deteriorated during the study period to ascertain whether ALERT principles were followed. Discussion & progress to date This study commenced in January 2007. Ethical approval has been granted and data collection is ongoing with interviews being conducted with key stakeholders. The findings from this study will provide evidence for policy-makers to make informed decisions regarding the direction for strategic and service planning of acute care services to improve the level of care provided to acutely ill patients in hospital. References 1. Esmonde L, McDonnell A, Ball C, Waskett C, Morgan R, Rashidain A et al. Investigating the effectiveness of Critical Care Outreach Services: A systematic review. Intensive Care Medicine 2006; 32: 1713-1721 2. McGaughey J, Alderdice F, Fowler R, Kapila A, Mayhew A, Moutray M. Outreach and Early Warning Systems for the prevention of Intensive Care admission and death of critically ill patients on general hospital wards. Cochrane Database of Systematic Reviews 2007, Issue 3. www.thecochranelibrary.com 3. Winters BD, Pham JC, Hunt EA, Guallar E, Berenholtz S, Pronovost PJ (2007) Rapid Response Systems: A systematic review. Critical Care Medicine 2007; 35 (5): 1238-43 4. Pawson R and Tilley N. Realistic Evaluation. London; Sage: 1997

Clustering-Based Ensemble Method as an Alternative to Stacking

One of the most popular techniques of generating classifier ensembles is known as stacking which is based on a meta-learning approach. In this paper, we introduce an alternative method to stacking which is based on cluster analysis. Similar to stacking, instances from a validation set are initially classified by all base classifiers. The output of each classifier is subsequently considered as a new attribute of the instance. Following this, a validation set is divided into clusters according to the new attributes and a small subset of the original attributes of the instances. For each cluster, we find its centroid and calculate its class label. The collection of centroids is considered as a meta-classifier. Experimental results show that the new method outperformed all benchmark methods, namely Majority Voting, Stacking J48, Stacking LR, AdaBoost J48, and Random Forest, in 12 out of 22 data sets. The proposed method has two advantageous properties: it is very robust to relatively small training sets and it can be applied in semi-supervised learning problems. We provide a theoretical investigation regarding the proposed method. This demonstrates that for the method to be successful, the base classifiers applied in the ensemble should have greater than 50% accuracy levels.

A proposed simple method for measurement in the anterior chamber angle: biometric gonioscopy

OBJECTIVE:

To design a system of gonioscopy that will allow greater interobserver reliability and more clearly defined screening cutoffs for angle closure than current systems while being simple to teach and technologically appropriate for use in rural Asia, where the prevalence of angle-closure glaucoma is highest.

DESIGN:

Clinic-based validation and interobserver reliability trial.

PARTICIPANTS:

Study 1: 21 patients 18 years of age and older recruited from a university-based specialty glaucoma clinic; study 2: 32 patients 18 years of age and older recruited from the same clinic.

INTERVENTION:

In study 1, all participants underwent conventional gonioscopy by an experienced observer (GLS) using the Spaeth system and in the same eye also underwent Scheimpflug photography, ultrasonographic measurement of anterior chamber depth and axial length, automatic refraction, and biometric gonioscopy with measurement of the distance from iris insertion to Schwalbe's line using a reticule based in the slit-lamp ocular. In study 2, all participants underwent both conventional gonioscopy and biometric gonioscopy by an experienced gonioscopist (NGC) and a medical student with no previous training in gonioscopy (JK).

MAIN OUTCOME MEASURES:

Study 1: The association between biometric gonioscopy and conventional gonioscopy, Scheimpflug photography, and other factors known to correlate with the configuration of the angle. Study 2: Interobserver agreement using biometric gonioscopy compared to that obtained with conventional gonioscopy.

RESULTS:

In study 1, there was an independent, monotonic, statistically significant relationship between biometric gonioscopy and both Spaeth angle (P = 0.001, t test) and Spaeth insertion (P = 0.008, t test) grades. Biometric gonioscopy correctly identified six of six patients with occludable angles according to Spaeth criteria. Biometric gonioscopic grade was also significantly associated with the anterior chamber angle as measured by Scheimpflug photography (P = 0.005, t test). In study 2, the intraclass correlation coefficient between graders for biometric gonioscopy (0.97) was higher than for Spaeth angle grade (0.72) or Spaeth insertion grade (0.84).

CONCLUSION:

Biometric gonioscopy correlates well with other measures of the anterior chamber angle, shows a higher degree of interobserver reliability than conventional gonioscopy, and can readily be learned by an inexperienced observer.

A Wii Bit of Fun: A Novel Platform to Deliver Effective Balance Training to Older Adults

BACKGROUND: Falls and fall-related injuries are symptomatic of an aging population. This study aimed to design, develop, and deliver a novel method of balance training, using an interactive game-based system to promote engagement, with the inclusion of older adults at both high and low risk of experiencing a fall.

STUDY DESIGN: Eighty-two older adults (65 years of age and older) were recruited from sheltered accommodation and local activity groups. Forty volunteers were randomly selected and received 5 weeks of balance game training (5 males, 35 females; mean, 77.18 ± 6.59 years), whereas the remaining control participants recorded levels of physical activity (20 males, 22 females; mean, 76.62 ± 7.28 years). The effect of balance game training was measured on levels of functional balance and balance confidence in individuals with and without quantifiable balance impairments.

RESULTS: Balance game training had a significant effect on levels of functional balance and balance confidence (P < 0.05). This was further demonstrated in participants who were deemed at high risk of falls. The overall pattern of results suggests the training program is effective and suitable for individuals at all levels of ability and may therefore play a role in reducing the risk of falls.

CONCLUSIONS: Commercial hardware can be modified to deliver engaging methods of effective balance assessment and training for the older population.