Browsing by Author "Bekele, Dawit (PhD)"

Now showing 1 - 4 of 4
  • No Thumbnail Available
    Item
    Context Information Refinement for Pervasive Medical Systems
    (Addis Ababa University, 2007-06) Mekuria, Birhanu; Bekele, Dawit (PhD)
    In pervasive medical systems with context-aware computing facility, the quality of decisions made by medical professionals is influenced by the quality of context information supplied by the context management sub-system. Central to context management is context information refinement aimed at deriving context information that can assist applications in making valuable decisions about what to deliver to users. In this thesis, we identified the shortcomings of existing works in relation to context information refinement in pervasive medical systems. The shortcomings are lack of adequate consideration for: quality parameters of context information, relevance of context information and particular requirements of the pervasive healthcare domain. In order to overcome these shortcomings, we proposed a context information refinement architecture that facilitates and coordinates the refinement procedure starting from acquisition of context information up until the refined context information is delivered to the target application (user) in a pervasive medical system by addressing the abovementioned shortcomings. The architecture is composed of the client mobile device end and the context refinement server. The client mobile device end consists of components responsible for tracking the device context (E.g. location), listening to incoming events from the server, providing interface for specifying service constraints and local caching services. On the context refinement server side, the major components are the reasoning and decision engine that performs ontology-supported context reasoning, the service parameters manager that maintains up-to-date list of service constraints, the context ontology that models the concepts and relationships between concepts in the pervasive healthcare domain and the context acquisition component that collects and aggregates context data from potential context data sources like sensors. To demonstrate the validity of the proposed architecture, we developed a prototype that implements the core components of the proposed architecture. The implementation has been evaluated with a real-life pervasive healthcare scenario and encouraging initial results have been obtained as an indication to the usability of the proposed architecture in a reallife setting.
  • No Thumbnail Available
    Item
    Context Information Refinement for Pervasive Medical Systems
    (Addis Ababa University, 2007-06) Mekuria, Birhanu; Bekele, Dawit (PhD)
    In pervasive medical systems with context-aware computing facility, the quality of decisions made by medical professionals is influenced by the quality of context information supplied by the context management sub-system. Central to context management is context information refinement aimed at deriving context information that can assist applications in making valuable decisions about what to deliver to users. In this thesis, we identified the shortcomings of existing works in relation to context information refinement in pervasive medical systems. The shortcomings are lack of adequate consideration for: quality parameters of context information, relevance of context information and particular requirements of the pervasive healthcare domain. In order to overcome these shortcomings, we proposed a context information refinement architecture that facilitates and coordinates the refinement procedure starting from acquisition of context information up until the refined context information is delivered to the target application (user) in a pervasive medical system by addressing the abovementioned shortcomings. The architecture is composed of the client mobile device end and the context refinement server. The client mobile device end consists of components responsible for tracking the device context (E.g. location), listening to incoming events from the server, providing interface for specifying service constraints and local caching services. On the context refinement server side, the major components are the reasoning and decision engine that performs ontology-supported context reasoning, the service parameters manager that maintains up-to-date list of service constraints, the context ontology that models the concepts and relationships between concepts in the pervasive healthcare domain and the context acquisition component that collects and aggregates context data from potential context data sources like sensors. To demonstrate the validity of the proposed architecture, we developed a prototype that implements the core components of the proposed architecture. The implementation has been evaluated with a real-life pervasive healthcare scenario and encouraging initial results have been obtained as an indication to the usability of the proposed architecture in a reallife setting.
  • No Thumbnail Available
    Item
    Medical Pervasive Systems
    (Addis Ababa University, 2007-07) Asfaw, Biniyam; Bekele, Dawit (PhD)
    Pervasive computing is being applied to different areas of specialization. This is basically because of the features of pervasive computing like context-awareness, invisibility, nonintrusiveness, and mobility. The medical area is one where such devices are hugely deployed. In this case, the pervasive devices; PDA (Personal Digital Assistant), mobile phones and the like, are used for manipulating medical records on the move. The use of pervasive devices also comes with new challenges that did not exist with traditional computing systems. Among these challenges, security is probably the major one. In fact, insuring security with pervasive systems is difficult due to the use of wireless communication, the physical nature and the low processing and low power nature of the devices. In this research, we deal with intrusion detection, ID, to secure such systems. ID Systems, IDSs, are used to monitor a resource and notify someone in the event of a specific occurrence for an appropriate response. Based on attack identification, they can be those which implement misuse detection, matching against known attack patterns, and those which implement anomaly detection, deviation from normal patterns. Misuse detection is used for matching only known patterns of attacks while anomaly detection is capable of identifying new attacks by matching with an already established normal profile. Based on source of information for the IDS, it may be host-based, network-based or application-based. For our case, we deal with application based anomaly detection modeling issues through building normal users’ application usage profiles
  • No Thumbnail Available
    Item
    Medical Pervasive Systems
    (Addis Ababa University, 2007-07) Asfaw, Biniyam; Bekele, Dawit (PhD)
    Pervasive computing is being applied to different areas of specialization. This is basically because of the features of pervasive computing like context-awareness, invisibility, nonintrusiveness, and mobility. The medical area is one where such devices are hugely deployed. In this case, the pervasive devices; PDA (Personal Digital Assistant), mobile phones and the like, are used for manipulating medical records on the move. The use of pervasive devices also comes with new challenges that did not exist with traditional computing systems. Among these challenges, security is probably the major one. In fact, insuring security with pervasive systems is difficult due to the use of wireless communication, the physical nature and the low processing and low power nature of the devices. In this research, we deal with intrusion detection, ID, to secure such systems. ID Systems, IDSs, are used to monitor a resource and notify someone in the event of a specific occurrence for an appropriate response. Based on attack identification, they can be those which implement misuse detection, matching against known attack patterns, and those which implement anomaly detection, deviation from normal patterns. Misuse detection is used for matching only known patterns of attacks while anomaly detection is capable of identifying new attacks by matching with an already established normal profile. Based on source of information for the IDS, it may be host-based, network-based or application-based. For our case, we deal with application based anomaly detection modeling issues through building normal users’ application usage profiles