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.

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.

Nurturing attachments in looked after children: a feasibility study of a group-based programme for carers

Introduction: The attachment related difficulties of Looked after Children are well recognised in literature with difficulties linked to early experiences hypothesised to be perpetuated by experiences of the care system itself. Recent policy guidelines have emphasised the importance of relationships for children in care, one of the most important being with their primary carer. Golding (2014) published a group format training resource entitled ‘Nurturing Attachments’ which aims to promote ‘therapeutic parenting’; however there is limited knowledge on the feasibility of this intensive approach.
Aims: To assess the feasibility of Nurturing Attachments through exploring (i.) recruitment, retention and attrition, (ii.) initial outcomes, (iii.) acceptability and (iv.) ability of the programme to be delivered in line with the manual content and structure.
Method Two Health and Social Care Trusts in NI participated in the study by facilitating a Nurturing Attachments group in each site with adoptive parents, foster carers and kinship carers (N = 26). Carers completed pre and post measures to explore initial outcome, completing an evaluation questionnaire to explore acceptability. Acceptability was also explored with Trust stakeholders and group facilitators through focus group and interview. To explore if the manual can be delivered as intended, each group completed debrief tools.
Results: The overall response rate for uptake was 13.9%, which impacted on engagement for a ‘treatment as usual’ group. Once engaged in the programme, attrition was low and attendance was high. Initial outcomes have shown positive effects for both young person and carers. Feedback suggests a positive response regarding acceptability with limited expressed concern. The manual can be delivered in a standardised way; however can be flexible enough to allow for group processes.
Conclusions: Further research is needed to continue to explore efficacy, however the current study has provided supporting evidence that Nurturing Attachments as an intervention has positively impacted on many levels of the LAAC system.

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.