Browsing by Author "Admassu, Daniel"

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    A Proposal and Implementation of a Neural Network Based Hierarchical Temporal Memory to Realize Cognitive Functions
    (A Proposal and Implementation of a Neural Network Based Hierarchical Temporal Memory to Realize Cognitive Functions, 2008-06) Admassu, Daniel; Raimond, Kumudha (PhD)
    Hierarchical Temporal Memory (HTM) is a recent innovation in cognition science. Developed in 2005 by Numenta Inc., an artificial intelligence research firm in the US, HTMs attempt to capture the way the human brain learns and infers its environment. One of the most notable characteristics of this model is the consideration of the hierarchical organization of objects in the world. Data in the world is made up of elementary features that aggregate in successive layers to form perceivable objects. This data can be visual, auditory or from other abstract spaces such as stock markets and scientific studies. The amount of raw data that the brain is exposed to throughout its lifetime is beyond imagination. However the brain is known to use a very noble and systematic approach to handle the perception, storage, and inference of this data. Several studies in neuroscience and psychology indicate that the brain makes use of the hierarchies that features in the world exhibit in their organization to form objects. Hence, for instance, ‘corners’ and ‘lines’ can aggregate to form a ‘table’ object in the visual world. These elementary features, however, can use a different aggregation to form a ‘chair’ object. The same is true for data in other types of worlds such as audio. HTMs directly apply a similar handling of world data for their cognition. Furthermore, the structure of HTMs, made up of data processing nodes arranged in a hierarchical tree, mimic the physical arrangement of cortical layers in the brain. The various data analysis algorithms in the nodes of HTMs were, however, found by the researcher to be limiting in several aspects, one of which is handling of unforeseen (untrained) data. For this purpose neural network data structures were used to replace some of the operations in these nodes for their ability in approximating untrained data to nearest matches. This research work discusses the proposed model, implementation constraints, the operational characteristics, and performance enhancements observed in this modified model with a selected test application. A substantial improvement in cognitive functionality has been observed with the newly proposed model.
  • No Thumbnail Available
    Item
    Web Based System for Route Finding to the Road Network of Addis Ababa
    (Addis Ababa University, 2005-07) Admassu, Daniel; Fekerseliassie, Daneal (PhD)
    In Africa, though the potentials for tourism is said to be much higher, the n umber of tours ts arrived at the continent and revenue generated from this sector is very low as compared with the other continents. This is because la ck of technical person to provide relevant and sufficient information to the tourist is one of the main stumbling blocks for development of tourism in Africa. Ethiopia is no exception to this. Ethiopia having higher potential of tourist sites can promote its tourism industry using expert system technology. Information makes tourism possible from the very onset of promoting places to making the experience worthwhile. It empowers tourists in their choices and makes them become more comfortable about the experience they are going to have. There uses a bi g responsibility for making that infom1ation accessible intonation that is desirabl e and easily accessible. Our country fosters hu ge potentials in the touri sm sector, which if taken advantage of can certainl y provide enom10U S reve nues to aid development. The tourism industry, however, lags behind with inadequate infrastructure facilities and manpower rendering the potential benefits unexploited . One of the major problems in this regard relates to access to information for tourists: when they need it and where they need it. Given the circumstance, the question is, Is/are there any areas or possible applications of expert systems that could make this problem easier to overcome? In an attempt to address such problems, the present stud y, specifically, explores the potentiality of applying expert systems technology in adv using to urist to find the direction of the route(s) in a convenient and comfortable manner. A Web Based Expert System F or Route Finding To The Road Network of Addis Ababa (AARFExSys) is developed by using maps and textbooks in the area of transportation as source of knowledge. The system is not only meant to replace the tour guides but also to assist them in providing sufficient information regarding routes of Addis Ababa with the users preferred mode of transportation. It helps to avoid the scarcity of manpower, the language barrier and the level of understanding that may face with the experts. The knowledge acquired for this study is then modeled using hierarchical structure that represents concepts and parameters involved in finding direction. A GIS based software (Arc View) is used as an automated knowledge acquisition tool to extract quantitative data such as distance from the road map of the city. Based on this model, the knowledge is represented using production rules. These rules are then implemented in the Knowledge Pro Gold expert system shell. Back ward reasoning is used in inferring the rules and extracting recommendations. The needs of users are assessed before the recommendation is extracted so that users are being able to select according to their interest in finding the direction. The AARFExSys has been developed to assist users particularly of tourists, who are coming from different countries of the world. Since these users are scattered through out the world, they need to access this system published on the Internet so that they could be able to get the information wherever possible. That is why the necessity of this system being developed as a web based. AARFExSys has been tested by users and experienced travel and tour agents at the selected Travel and Tour Agencies found in Addis Ababa. Based on an encouraging result obtained, they have established its acceptability and accuracy.