Browsing by Author "Williams, Quentin"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Open Access
    An architecture for user preference-based IoT service selection in cloud computing using mobile devices for smart campus
    (2015) Manqele, Lindelweyizizwe Siziwe; Dlodlo, Mqhele E; Williams, Quentin; Coetzee, Louis
    The Internet of things refers to the set of objects that have identities and virtual personalities operating in smart spaces using intelligent interfaces to connect and communicate within social environments and user context. Interconnected devices communicating to each other or to other machines on the network have increased the number of services. The concepts of discovery, brokerage, selection and reliability are important in dynamic environments. These concepts have emerged as an important field distinguished from conventional distributed computing by its focus on large-scale resource sharing, delivery and innovative applications. The usage of Internet of Things technology across different service provisioning environments has increased the challenges associated with service selection and discovery. Although a set of terms can be used to express requirements for the desired service, a more detailed and specific user interface would make it easy for the users to express their requirements using high-level constructs. In order to address the challenge of service selection and discovery, we developed an architecture that enables a representation of user preferences and manipulates relevant descriptions of available services. To ensure that the key components of the architecture work, algorithms (content-based and collaborative filtering) derived from the architecture were proposed. The architecture was tested by selecting services using content-based as well as collaborative algorithms. The performances of the algorithms were evaluated using response time. Their effectiveness was evaluated using recall and precision. The results showed that the content-based recommender system is more effective than the collaborative filtering recommender system. Furthermore, the results showed that the content-based technique is more time-efficient than the collaborative filtering technique.
  • Thumbnail Image
    Item
    Open Access
    Estimating Poverty from Aerial Images Using Convolutional Neural Networks Coupled with Statistical Regression Modelling
    (2019) Maluleke, Vongani; Er, Sebnem; Williams, Quentin
    Policy makers and the government rely heavily on survey data when making policyrelated decisions. Survey data is labour intensive, costly and time consuming, hence it cannot be frequently or extensively collected. The main aim of this research is to demonstrate how Convolutional Neural Network (CNN) coupled with statistical regression modelling can be used to estimate poverty from aerial images supplemented with national household survey data. This provides a more frequent and automated method for updating data that can be used for policy making. This aerial poverty estimation approach is executed in two phases; aerial classification and detection phase and poverty modelling phase. The aerial classification and detection phase use CNN to perform settlement typology classification of the aerial images into three broad geotype classes namely; urban, rural and farm. This is then followed by object detection to detect three broad dwelling type classes in the aerial images namely; brick house, traditional house, and informal settlement. Mask Region-based Convolutional Neural Network (Mask R-CNN) model with a resnet101 CNN backbone model is used to perform this task. The second phase, poverty modelling phase, involves using NIDS data to compute the poverty measure Sen-Shorrocks-Thon (SST) index. This is followed by using regression models to model the poverty measure using aggregated results from the aerial classification and detection phase. The study area for this research is Kwa-Zulu Natal (KZN), South Africa. However, this approach can be extended to other provinces in South Africa, by retraining the models on data associated with the location in question.