2 results
Search Results
Now showing 1 - 2 of 2
Article Citation - WoS: 47Citation - Scopus: 67Deep Learning Based Fall Detection Using Smartwatches for Healthcare Applications(Elsevier Sci Ltd, 2022) Sengul, Gokhan; Karakaya, Murat; Misra, Sanjay; Abayomi-Alli, Olusola O.; Damasevicius, RobertasWe implement a smart watch-based system to predict fall detection. We differentiate fall detection from four common daily activities: sitting, squatting, running, and walking. Moreover, we separate falling into falling from a chair and falling from a standing position. We develop a mobile application that collects the acceleration and gyroscope sensor data and transfers them to the cloud. In the cloud, we implement a deep learning algorithm to classify the activity according to the given classes. To increase the number of data samples available for training, we use the Bica cubic Hermite interpolation, which allows us to improve the accuracy of the neural network. The 38 statistical data features were calculated using the rolling update approach and used as input to the classifier. For activity classification, we have adopted the bi-directional long short-term memory (BiLSTM) neural network. The results demonstrate that our system can detect falling with an accuracy of 99.59% (using leave-one-activityout cross-validation) and 97.35% (using leave-one-subject-out cross-validation) considering all activities. When considering only binary classification (falling vs. all other activities), perfect accuracy is achieved.Article Citation - WoS: 5Citation - Scopus: 6Enhancing Misuse Cases With Risk Assessment for Safety Requirements(Ieee-inst Electrical Electronics Engineers inc, 2020) Arogundade, Oluwasefunmi T.; Misra, Sanjay; Abayomi-Alli, Olusola O.; Fernandez-Sanz, LuisRisk-driven requirements elicitation represents an approach that allows assignment of appropriate countermeasure for the protection of the Information System (IS) depending on the risk level. Elicitation of safety requirements based on risk analysis is essential for those IS which will run on the open and dynamic Internet platform. Traditionally, misuse cases are used to find the weak points of an IS but cannot differentiate between the weak point that can lead to lenient hazard and/or serious hazard. In this paper, we present an enhanced misuse case approach to support IS safety risk assessment at the early stages of software process. We extensively examined and identified concepts which constitute a modelling technique for IS safety risk assessment and build a conceptual model for achieving IS safety risk assessment during the requirement analysis phase of software process. The risk assessment process follows an approach of consequential analysis based on misuse cases for safety hazard identification and qualitative risk measurement. The safety requirements are elicited according to the results of the risk assessment. A medical IS is used as a case study to validate the proposed model.
