12244 research outputs found
Sort by
Science 5-11: a guide for teachers. 4th ed
No full textThis fully updated fourth edition of the bestselling textbook provides a comprehensive introduction to current research and professional practice for teaching science in the primary school.
Chapters are organised into five sections, first introducing theory and practice, then providing specific guidance on teaching topics in biology, chemistry and physics, and finally discussing supporting science across the whole school
Creating a resource that captures the social histories and lived experiences of the PMLD community: which stories should be collected and shared, and how?
Get PDFIn this short article we introduce a new project that aims to develop a resource that shares the stories of the PMLD community. By ‘PMLD community’ we mean people with profound and multiple learning disabilities (PMLD), their loved ones such as family and friends, and those who regularly support people with PMLD, including day centre staff and paid carers. Our project involves working with the PMLD community to identify what stories they would like to share, with whom, and how. We will then work with the community to co-create a resource and share this with readers of PMLD Link in a future issue
A comparative study of methods for topic modelling in news articles
No full textThe past few decades have seen an increase in textual data and influence from the news media. With the rise in available data, especially in regard to textual data from news media, it is imperative to quickly categorise news topics. In this research, the primary aim is to suggest a method for automatically identifying news topics in articles. The dataset used in this research was the news category published on Kaggle and comprised of 210,294 headlines and abstracts from HuffPost between 2012 and 2022. The dataset consisted of a total of 42 categories and six columns. Traditional modelling techniques did not perform well in comparison with Top2Vec, NMF or BERTopic. This research confirms the efficacy of Top2Vec and BERTopic, followed by NMF, LDA and LSA for analysing, news category data from a human-interpretation perspective. Though BERTopic was able to deduce 1145 topics from the data, it could not chuck unwanted words like “to”, “say”, “for” which do not add any value to the topic semantics. In summary, TF-IDF proved to be the best feature extraction technique and Top2Vec the best topic modelling technique
Application of deep learning algorithms to terahertz images for detection of concealed objects
No full textSafety of the public at large venues is of utmost importance, and therefore, it is important to detect threats encountered due to concealed objects, especially on human bodies. Terahertz imaging has gained popularity over the last few years due to its ability to detect concealed objects inside fabric without harm to humans or invasion to their privacy. However, terahertz images suffer from poor resolution and low signal-to-noise ratio. Deep learning has shown high performance in classifying images lately, especially feedforward neural networks. Therefore, this study utilised deep learning for the detection of concealed objects on human bodies using the public active terahertz imaging (ATZ) dataset that contained images of 11 tiny objects. An end-to-end framework was applied and involved image enhancement using wavelet filtering, locating object using skip attention generative adversarial networks (SAGAN) and forward-forward mixed convolution with Gaussian affinity network (FMCGNet). The results showed that wavelet filtering did not affect the performance of the deep learning models. The SAGAN showed performance accuracy of 68.4% and that was related to the insufficient training of the model that required high computational power. However, the accuracy of classifying images with anomalies was high when FMCGNet was applied and was featured in the true positive rate of 91.9% though it was applied to imbalanced dataset. In summary, the proposed end-to-end framework successfully identified concealed objects on human bodies in an efficient way. Future work involves adopting this approach to different types of imaging datasets to further understand its strengths and limitations
Evaluating machine learning and deep learning analytics for predicting bankruptcy of companies
No full textCorporate bankruptcy is a global issue that has increased over the last few years. Due to lack of adequate historical data, current models have not been able to correctly predict cases of bankruptcy. This research proposed a composite procedure at four stages which includes pre-processing and data rebalancing methods to curate the data, perform feature selection, use various machine learning and deep learning models to construct a robust predictive bankruptcy model and the use of explainable AI to understand the various features that contribute to the model prediction. Models were based on the labelled historic data of various bankrupted and non-bankrupted Polish companies between the period of 2007–2013. Prior to models’ application, data were split to training and test sets that consisted of 25,122 and 12,375 datapoints, respectively. Models were evaluated on various metrics: ROC-AUC, recall, and F-Beta score to determine the best predictive model. Our comparative study showcases that missing data imputation performed using KNN Imputer, skewness reduction using Yeo-Johnson transformation, feature elimination using Recursive Feature Elimination technique along with cost sensitive learning used in tandem with XGBoost algorithm produces the best model with test AUC score of 96.1%, recall score as 96%, and F-Beta score of 92.42%. Implementation of Explainable AI has also helped in realizing top four significant features that impact negatively to bankruptcy prediction globally and locally across all the models created are the ratios “total_cost_overtotal_sales”, “gross_profit_in_3_years_over_total_assests”, “profit_on_sales_over_sales”, and “profit_on_sales_over_total_assests”. Such insights on the classification outcome which instils confidence amongst the decision makers about the validity of the model and its prediction capabilities
