JavaScript is disabled for your browser. Some features of this site may not work without it.
| dc.contributor.author | TEGISTU, BIYADG SEWNET | |
| dc.date.accessioned | 2021-10-01T10:50:53Z | |
| dc.date.available | 2021-10-01T10:50:53Z | |
| dc.date.issued | 2021-07-15 | |
| dc.identifier.uri | http://ir.bdu.edu.et/handle/123456789/12685 | |
| dc.description.abstract | In this paper, a model of screening patients for stroke predictions is proposed using DNN (DEEP NEURAL NETWORK) for diagnosis. And after all, the level of consumers behavioral intention to adopt and accept the proposed model is assessed by using extended unified theory of acceptance and use of technology (UTAUT2). Around much more of radiologists/doctor’s time is spent by focusing on a medical history. And also, there is a knowledge gap for treatment of patients from radiologists/doctors to radiologists/doctors. It is a very difficult to reach 100% in healthcare. The proposed model was tested among consumers of the model. The UTAUT2 model is developed to examine /assess user’s behavioral intention to accept the proposed DNN model. Anaconda3(Jupyter Notebook-python) is used to implement the brain stroke prediction model using DNN. Questionnaires are prepared and distributed among consumers mainly medical students and for medical doctors and hence around 99 valid responses were obtained. The Model is design based on the obtained responses using UTAUT2. Based on the designed DNN model, we analyzed statistically significance of the constructs of the UTAUT2 model. Of these constructs, Performance expectancy, Effort expectancy, social influence and Hedonic Motivation have gotten statistical significance while habit, and facilitating conditions became statistically insignificant. The medical error can be reduced and the patient safety can be enhanced. The model result shows that its’ accuracy is 98.17% | en_US |
| dc.language.iso | en_US | en_US |
| dc.subject | ELECTRICAL AND COMPUTER ENGINEERING | en_US |
| dc.title | BRAIN STROKE PREDICTION MODEL USING DEEP NEURAL NETWORK (DNN) | en_US |
| dc.type | Thesis | en_US |
