A thesis submitted in partial fulfilment of the requirement of Sheffield Hallam University for the degree of Doctor of Philosophy In the Cultural Communication and Computing Research Institute (C3RI) June 2018 Chapter 3: Literature review: This chapter presents a review of the literature on speech to text technology, various acceptance models, code-switching, language and politics, and on orthography. Chapter 4: Methods: This chapter deals with the research methods. It introduces the research philosophy that this research has adopted. The chapter discussess employment of software engineering as a design method and explains how the prototype was conceptualised, developed and evaluated. It also briefly deals with the sampling and pilot which is crucial to provide a useful insight on decisions taken on methods. Chapter 5: Evaluation of prototype: This chapter deals with the evaluation of the prototype and the rationale for some of the decisions in relation to prototype evaluation. Chapter 6: Proposed Mode: The proposed model to predict the user acceptance of speech to text in Tamil is introduced in this chapter. The proposed user acceptance model is one the main contributions of this research. Chapter 7: The studies: This chapter discusses the various studies and findings that were done in order to answer the main research question of predicting the user acceptance of speech to text in Tamil. It starts from the study of transliteration followed by a comparative study between two similar social groups which led to the observation of 'zha' pronunciation which in turn led to the target audience of this research-the Tamil Brahmans. Chapter 8: Discussion: The chapter discusses on the findings and studies along with relevant literature. The chapter also provides a reflection on the user acceptance model proposed in this thesis. The section on researcher's own experience is in the first person. Chapter 9: Personal reflection: This chapter provides a brief insight on researcher's own experiences, practices and observations as an insider. The chapter enables the reader to see through the researcher's lens. This chapter has used first person. Chapter 10: Conclusion: In addition to predicting the user acceptance, it provides an insight on the feasibility of such applications along with some suggestions that could be incorporated when designing and developing such applications. Finally, it enumerates the contribution to the knowledge and further work. * So what is your opinion/ experience, very specifically on pronunciation of the Brahmins and the non Brahmins? (clarifies: தமிழ் , தமிலழ பபாறுத் த வலரக் கும்
There have been many changes in the medical field due to technological advances. The progression in technologies provides lot of opportunities to extract valuable insights from huge amount of unstructured data. The literature documents published by the researchers in medical domain consists enormous amount of knowledge. Many organizations are involving in retrieving the hidden information from the literature documents. Extracting the drug names, diseases, symptoms, route of administration, species and dosage forms from the textual document is an easy task due to the innovation of technologies in the Natural Language Processing. In this article, a new hybrid based approach is proposed to identify named entity from the medical literature documents. New dictionary has been built for route of administration, dosage forms and symptoms to annotate the entities in the medical documents. The annotated entities are trained by the blank Spacy machine learning model. The trained model provide a decent accuracy when compared with the existing model. The hybrid model is validated with the dictionary and human (optional)to calculate the confusion matrix. It is able to identify more entities than the prevailing model. The average F1 score for five entities of the proposed hybrid based approach 73.79%.
People who have dementia (PwD) experience deteriorating executive functions, in particular their working memory, and therefore find it hard to complete multistep tasks or activities of daily living. There is no doubt that during the pandemic, PwD and their caregivers were particularly vulnerable, often isolated which affected their mental and physical health. Their ability to live independently was hampered, fomenting depression in the PwD and burnout on informal caregivers. Information technology can support dementia care improving the quality of life of PwD and easing the burden on caregivers. There is an increasing demand to support informal caregivers and improve their well-being by making dementia challenges less severe. This study uses qualitative techniques to design a model with technological strategies based on semi-structured interviews applied to seven informal caregivers from two different countries. Based on these interviews we developed design insights for implementing solutions to help informal caregivers take care of their PwD at home using conversational agents. We hope that the findings presented in this study will help researchers, and developers design solutions that can support PwD and informal caregivers.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.