Abstract
The choice of users’ activity in a context-aware environment depends on users’ preferences and background. Users tend to rank concurrent activities and select their preferred activity. Researchers and developers of context-aware applications have sought various mechanisms to implement context reasoning engines. Recent implementations use Artificial Neural Networks (ANN) and other machine learning techniques to develop a context-aware reasoning engine to predict users’ activities. However, the complexities of these mechanisms overwhelm the processing capabilities and storage capacity of mobile devices. The study models a context-aware reasoning engine using a multi-layered perceptron with a gradient descent back-propagation algorithm to predict activity from user-ranked activities using a stochastic learning mode with a constant learning rate. The work deduced that working with specific rules in training a neural network is not always applicable. Training a network without approximation of neuron’s output to the nearest whole number increases the accuracy level of the network at the end of the training.
Highlights
The choice of users’ activity in a context-aware environment depends on users’ preferences and background
Following the use of ontology-based models complemented with other technologies in acquiring activity context, Dey [2], Naeem et al [3] and Sherif and Alesheikh [4] suggested the need to use machine learning approach in designing context-aware applications
Among them was the complex nature of these mechanisms which required extensive computing power and memory that cannot be offered by the current mobile devices
Summary
The ability to design an intelligent reasoning engine for context-aware mobile applications has prompted many researchers to devise various mechanisms. Recurrent neural networks are usually used [8] They are, not desirable for mobile devices with limited processing capability. Neural Networks (ANNs) to develop context-aware applications for mobile devices. Among them was the complex nature of these mechanisms which required extensive computing power and memory that cannot be offered by the current mobile devices They recommended that the learning algorithms and architectures of ANN have to be controlled. With a sigmoid activation function instead of a recurrent network in a supervised environment using the gradient descent mechanism of the back-propagation algorithm for training due to its simplicity and adaptability [18] with a constant learning rate. The third section looks at the ANN context-aware reason engine modelling and implementation whilst the final section discusses the findings and concludes the paper
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: European Journal of Electrical Engineering and Computer Science
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
