4101 research outputs found
Sort by
Evaluating the performance of a hybrid model for classification of bicycle crash severity and identification of associated risk factors
No full textThis study conducted an exploratory analysis of bicycle crash data from Great Britain with the aim of identifying the key variables that influence the classification of such incidents. It also analysed data on a range of factors that may contribute to bicycle crashes, including the age of the cyclist, lighting conditions, weather conditions, road types, road conditions, and speed limits. Results indicated that these variables are among the most significant predictors of bicycle crashes, with road conditions, time of day, and lighting conditions being particularly vital factors. In addition, the study sought to compare the efficacy of different machine learning and deep learning models in predicting the severity of such incidents. Results indicated that these models demonstrated poor performance in predicting the severity of bicycle crashes. As a result, a hybrid model that combines the K-Nearest Neighbor and eXtreme Gradient Boosting algorithms was developed to improve accuracy. The hybrid model outperformed all other models, achieving an accuracy rate of 83.56%. The study, additionally, has put forward several recommendations, including the mandatory use of reflective clothing and the installation of Intelligent Transportation Systems (ITS) to enhance the safety of cyclists
Tensions in managing the online network development of autoethnographers
No full textAlthough literature exists on the methodological development of autoethnographers in the classroom context, little has been written about achieving such development in online networks of dispersed individuals, and the social psychological difficulties between senior members of such networks that might ensue. This conversational autoethnography developed after Alec Grant, the first author, angrily withdrew by email from the South Coast Autoethnography Network (SCAN). Since its inception in 2013, the hub, or centre of operating activity of SCAN has historically been mostly shared between a small number of academics working in, or associated with, Sussex University and the University of Brighton in the south coast of England. With around 65 participants, SCAN aims to facilitate the development of autoethnographers, with many of its members inexperienced in the approach to differing degrees. In their conversational exchange, the authors explore, respond to, and try to make sense of and resolve, the tensions that developed in the group before and after Alec’s withdrawal from it. The authors believe that this article captures many of the interpersonal difficulties that might inevitably arise between senior members, in autoethnographic networks internationally. They therefore hope that it will serve as a useful resource for individual readers and network groups
Modeling and Validation of Base Pressure for Aerodynamic Vehicles Based on Machine Learning Models
No full textThe application of abruptly enlarged flows to adjust the drag of aerodynamic vehicles using machine learning models has not been investigated previously. The process variables (Mach number (M), nozzle pressure ratio (& eta;), area ratio (& alpha;), and length to diameter ratio (& gamma; )) were numerically explored to address several aspects of this process, namely base pressure (& beta;) and base pressure with cavity (& beta;cav). In this work, the optimal base pressure is determined using the PCA-BAS-ENN based algorithm to modify the base pressure presetting accuracy, thereby regulating the base drag required for smooth flow of aerodynamic vehicles. Based on the identical dataset, the GA-BP and PSO-BP algorithms are also compared to the PCA-BAS-ENN algorithm. The data for training and testing the algorithms was derived using the regression equation developed using the Box-Behnken Design (BBD). The results show that the PCA-BAS-ENN model delivered highly accurate predictions when compared to the other two models. As a result, the advantages of these results are two-fold, providing: (i) a detailed examination of the efficiency of different neural network algorithms in dealing with a genuine aerodynamic problem, and (ii) helpful insights for regulating process variables to improve technological, operational, and financial factors, simultaneously
Restructuring priorities: rethinking economic growth for a more active future
No full textPhysical inactivity is among the most formidable public health challenges of our time. The World Health Organization recently revealed that physical inactivity is on the rise and predicted that globally, there will be around 500 million new cases of preventable non-communicable diseases between 2020 and 2030 if physical inactivity levels remain as they are. But why? What’s driving this formidable public health challenge? In this commentary article, I illustrate how the continual pursuit of economic growth is a key driver underpinning physical inactivity at the population level. I contend that if the priority really is to address physical inactivity at the population level, then the metrics we use to define social progress will need recalibratin
Transformation invariant Pashto handwritten text classification and prediction
No full textThe use of handwritten recognition tools has increased yearly in various commercialized fields. Due to this, handwritten classification, recognition, and detection have become an exciting research subject for many scholars. Different techniques have been provided to improve character recognition accuracy while reducing time for languages like English, Arabic, Chinese and European languages. The local or regional languages need to consider for research to increase the scope of handwritten recognition tools to the global level. This paper presents a machine learning-based technique that provides an accurate, robust, and fast solution for handwritten Pashto text classification and recognition. Pashto belongs to cursive script division, which has numerous challenges to classify and recognize. The first challenge during this research is de-veloping efficient and full-fledged datasets. The efficient recognition or prediction of Pashto handwritten text is impossible by using ordinary feature extraction due to natural transformations and handwriting variations. We propose some useful invariant features extracting techniques for handwritten Pashto text, i.e., radial, orthographic grid, perspective projection grid, retina, the slope of word trajectories, and cosine angles of tangent lines. During the dataset creation, salt and pepper noise was generated, which was removed using the statistical filter. Another challenge to face was the invalid disconnected handwritten stroke trajectory of words. We also proposed a technique to minimize the problem of disconnection of word trajectory. The proposed approach uses a linear support vector machine (SVM) and RBF-based SVM for classification and recognition
A recommendation system based on AI for storing Block data in the Electronic Health Repository
No full textA proliferation of wearable sensors that record physiological signals has resulted in an exponential growth of data on digital health. To select the appropriate repository for the increasing amount of collected data, intelligent procedures are becoming increasingly necessary. However, allocating storage space is a nuanced process. Generally, patients have some input in choosing which repository to use, although they are not always responsible for this decision. Patients are likely to have idiosyncratic storage preferences based on their unique circumstances. The purpose of the current study is to develop a new predictive model of health data storage to meet the needs of patients while ensuring rapid storage decisions, even when data is streaming from wearable devices. To create the machine learning classifier, we used a training set synthesized from small samples of experts who exhibited correlations between health data and storage features. The results confirm the validity of the machine learning methodolog
Developing an online practicum in professional education: a case study from UK teacher education
No full textA ‘practicum’, ‘clinical experience’ or ‘internship’ is an established component of professional preparation in education, health, social work, law, accountancy and engineering. Across diverse occupational fields, employability and work readiness are gaining prominence in college marketing strategies. The disruption to work placements during the Covid-19 pandemic in programmes linked to licensure rapidly increased the pace and scale of virtualisation and the need for systematic evaluation of curriculum re-design. This chapter presents a case study of the transition to a fully online practicum for UK university students training to be teachers during 2020/21. Drawing on interviews with students, university tutors and school partners, the chapter outlines key learning about partnership formation and innovation. The evaluation suggests that online supervision requires participants to work harder to establish a positive working alliance and sense of belonging across time–space-digital media. The study highlights the importance of iterative review to promote reciprocity, transparency and voice
Deep Learning for Cognitive Computing Systems Technological Advancements and Applications
No full textCognitive computing simulates human thought processes with self-learning algorithms that utilize data mining, pattern recognition, and natural language processing. The integration of deep learning improves the performance of Cognitive computing systems in many applications, helping in utilizing heterogeneous data sets and generating meaningful insights
The supply, recruitment, and retention of teachers.
No full textChallenges to the supply of well-prepared and effective teachers persist across diverse education systems. This chapter considers the sociopolitical and technical complexity of reconciling demand and supply in the recruitment and retention of teachers. Within finite expenditure, workforce planning must balance need across school phases, subjects, and localities, taking into account teacher mobility and turnover, changing demographics, curriculum policy, and future learning needs. As a result, it is not uncommon for teacher shortages, underrepresentation, and oversupply to coexist. This chapter outlines the impact of patterns of differential attrition on teaching quality and educational equity, and considers alternative policy strategies to secure and diversify the teacher workforce