A comparison of conventional and deep learning methods of image classification

The aim of the research is to compare traditional and deep learning methods in image classification tasks. The conducted research experiment covers the analysis of five different models of neural networks: two models of multi–layer perceptron architecture: MLP with two hidden layers, MLP with three hidden layers; and three models of convolutional architecture: the three VGG blocks model, AlexNet and GoogLeNet. The models were tested on two different datasets: CIFAR–10 and MNIST and have been applied to the task of image classification. They were tested for classification performance, training speed, and the effect of the complexity of the dataset on the training outcome.

Competencies required for the implementation of an efficient supply chain from the perspectives of students and the labour market

The supply chain, the system granting customer satisfaction, is an important field in our changing world. This field’s profit-oriented companies seek employees with the competencies to achieve their goals. This research’s aim was to raise awareness of those competencies that should be developed. The authors questioned 110 supply chain management (SCM) master’s degree (MSc) students from Corvinus University of Budapest (CUB) and performed a significance test on their answers. They were asked to assess 17 competency groups and state the extent to which – on a scale from 0 to 100 – supply chain managers need them. One of the most interesting results was the assessment of presentation skills, which indicated differences between the competencies that companies expected and those that students believed were required. This study not only lays the groundwork for further research but also emphasizes the relevance of those competencies to be developed and the rethinking of training outcome requirements.

No add-on effects of Unilateral and Bilateral Transcranial Direct Current Stimulation on Fine Motor Skill Training Outcome in Chronic Stroke. A Randomized Controlled Trial

Background: Transcranial direct current stimulation (tDCS) may improve motor recovery after stroke. This study investigated if uni- and bihemispheric tDCS of the motor cortex can enhances fine motor training outcome and transfer to clinical assessments of upper motor function. Methods: In a randomized, double-blinded, sham-controlled trial, forty chronic stroke patients underwent five days of fine motor skill training of the paretic hand with either unilateral or bilateral (N=15/group) or placebo tDCS (N=10). Immediate and long-term (three months) effects on training outcome and motor recovery (Upper Extremity Fugl-Meyer, UE-FM, Wolf Motor Function Test, WMFT) were investigated. Results: Trained task performance significantly improved independently of tDCS in a curvilinear fashion. Anodal, but not dual tDCS resulted in a steeper learning curve on the UE-FM. Neither training nor combined training-tDCS improved WMFT performance.Conclusions: Fine motor skill training can facilitate recovery of upper extremity function. Minimal add-on effects of tDCS were observed.Clinical Trial Registration-URL: NCT01969097 retrospectively registered on 25/10/2013.

Concurrent and Predictive Criterion Validity of a Puppy Behaviour Questionnaire for Predicting Training Outcome in Juvenile Guide Dogs

Working dog organisations regularly assess the behaviour of puppies to monitor progression. Here, we tested the predictive validity (for predicting success in guide dog training) of a shortened version of a previously developed juvenile dog behaviour questionnaire (the refined puppy walker questionnaire, r-PWQ) and compared it with the Canine Behavioral Assessment and Research Questionnaire (C-BARQ). The r-PWQ is used by Guide Dogs UK, whereas the C-BARQ was designed for pet dogs and is used by some other guide dog schools internationally. A cohort of dogs aged eight months (n = 359) were scored concurrently on the r-PWQ and C-BARQ. Analogous traits between the questionnaires were evaluated for internal consistency and association with training outcome and compared for concurrent validity. The r-PWQ was associated with training outcome for five scales (r-Excitability, Trainability, Animal Chase, r-Attachment and attention seeking and Distractibility) and the C-BARQ for two scales (Excitability and Separation-related behaviour). There were significant correlations between analogous C-BARQ and r-PWQ trait scores (p < 0.001) except for Separation-related behaviour and questionnaire scales had similar internal consistencies. The r-PWQ may be more suitable to use with guide dog schools. However, due to the correlation between analogous scales (except for “Distractibility”) some scales could be substituted for one another when reviewing the behaviour of dogs between guide dog schools using different questionnaires.

The Influence of Training Outcome and Competency on Effective Utilization of Malaria Microscopy Result by Health Professionals In South Eastern Nigeria

BackgroundMalaria diagnosis in Nigeria was largely done based on clinical presentations until recently when the policy on parasitological confirmation of all suspected malaria cases before treatment was released by the government in 2011. One of the possible causes of over-diagnosis and over treatment of malaria in Nigeria is poor utilization of Malaria test results in health care delivery. This study demonstrates the influence of in-service training on malaria microscopy amongst medical laboratory scientists on the utilization of malaria microscopy results in a selected Government Health Facility in Nigeria.MethodThe base line study was conducted in 2014 while a follow up study where pre tested questionnaire on perception and utilization of malaria microscopy results by Health care providers in malaria case management were administered to end users of laboratory results in selected secondary health facilities; Basic malaria microscopy training was subsequently conducted for medical laboratory scientists working in these selected facilities in accordance with the World Health Organization (WHO) basic microscopy training manual. The training was followed up by a supportive supervision visit to the Medical Laboratories where other factors that can adversely affect microscopy results such as the necessary equipment and reagents for staining and visualization, good working conditions were addressed and put in place by the participating health facilities.Furthermore, During the basic and refresher training, Test scores was extracted using Microsoft Office Excel® 2010 template; data was cleaned and exported to Stata 11, Stata Corp. 2009. Stata Statistical Software: Release 11. College Station, TX: Stata Corp LP for data analysis. To assess the performance after the training intervention, paired-test was used to determine if there was any significant difference between the performance scores before and after the training and between the basic and refresher training.ResultThe study demonstrates a significant improvement in both the basic and refresher training mean parasite detection pre-and post-tests scores from 56.3% (95% CI 53.6-58.8%) to 77.7% (95% CI 74.4-80.2%) and 76.7 (95% CI 74.2-79.2%) to 91.2% (95% CI 88.3-94.1%)(P< 0.001). Comparing the baseline and follow up study, and the assessment of facilities’ malaria test request and utilization pattern within the study period,there was significant difference when comparing the rate of utilization of malaria result from the trained Medical Laboratory Scientists (p< 0.001).ConclusionThe increase in utilization of malaria microscopy result for effective case management of malaria in the study area was influenced by training outcome and competency of Medical Laboratory Scientists.