Computer Science
Permanent URI for this communityhttps://repository.ui.edu.ng/handle/123456789/354
Browse
19 results
Search Results
Item Predictive analysis for journal abstracts using polynomial neural networks algorithm(2017-07) Ojo, A. K.Academic journals are an important outlet for dissemination of academic research. In this study, Neural Networks model was used in the prediction of abstracts from The Institute of Electrical and Electronics Engineers (IEEE) Transactions on Computers. Simulation of results was done using the Polynomial Neural Networks algorithm. This algorithm, which is based on Group Method of Data Handling (GMDH) method, utilizes a class of polynomials such as linear, quadratic and modified quadratic. The prediction was done for a period of twenty-four months using a predictive model of three layers and two coefficients. The performance measures used in this study were mean square errors, mean absolute error and root mean square error.Item Projecting the future direction of publication patternsUsing text mining(2017-07) Ojo, A. K.In this study, text mining techniques were used to identify various research trends in academic journal publications. These techniques were applied to figure out trends in research patterns related to various specialisation areas in Computer Science academic journal articles within a period of two decades. The corpus mined were crawled online, pre-processed and transformed into structured data using filtering and stemming algorithms. The data were grouped into series of word features based on bag of words document representation. Abstracts and the keywords of the articles selected from these journal articles were used as the dataset. It was discovered that the publication trends have changed tremendously from communications and security to artificial intelligence over time.Item Characterisation of academic journal publications using text mining techniques(Science and Education Publishing, 2017) Ojo, A. K.; Adeyemo, A. B.The ever-growing volume of published academic journals and the implicit knowledge that can be derived from them has not fully enhanced knowledge development but rather resulted into information and cognitive overload. However, publication data are textual, unstructured and anomalous. Analysing such high dimensional data manually is time consuming and this has limited the ability to make projections and trends derivable from the patterns hidden in various publications. This study was designed to develop and use intelligent text mining techniques to characterise academic journal publications. Journals Scoring Criteria by nineteen rankers from 2001 to 2013 of 50th edition of Journal Quality List (JQL) were used as criteria for selecting the highly rated journals. The text-miner software developed was used to crawl and download the abstracts of papers and their bibliometric information from the articles selected from these journal articles. The datasets were transformed into structured data and cleaned using filtering and stemming algorithms. Thereafter, the data were grouped into series of word features based on bag of words document representation. The highly rated journals were clustered using Self-Organising Maps (SOM) method with attribute weights in each cluster.Item Trend analysis in academic journals in computer science using text mining(IJCSIS Publication, 2015-04) Ojo, A. K.; Adeyemo, A. B.Text mining is the process of discovering new, hidden information from texts- structured, semi-structured and unstructured. There are so many benefits, valuable insights, discoveries and useful information that can be derived from unstructured or semi- unstructured data. In this study, text mining techniques were used to identify trends of different topics that exist in the text and how they change over time. Keywords were crawled from the abstracts in Journal of Computer Science and Technology (JCST), one of the ISI indexed journals in the field of Computer Science from 1993 to 2013. Results of our analysis clearly showed a varying trend in the representation of various subfields in a Computer Science journal from decade to decade. It was discovered that the research direction was changing from pure mathematical foundations, Theory of Computation to Applied Computing, Artificial Intelligence in form of Robotics and Embedded Systems.Item Improving information acquisition via text mining for efficient e-governance(2015-03) Adeyemo, A. B.; Ojo, A. K.In this paper we proposed a framework for integrating text mining with E-Governance. We suggested that the users of electronic governance can use the text terms to describe their interest which can be processed for clustering and term extraction. The words thus expressed by users are tracked and subjected to processing wherein it is possible to generate content. We have provided the framework and tested it in a few web sites. We have used the clustering and pre-processing for the content management. The results are encouraging and it is possible to extent such exercises for other text minging processes.Item A comparison of the predictive capabilities of artificial neural networks and regression models for knowledge discovery(2013) Ojo, A. K.; Adeyemo, A. B.In this paper, Artificial Neural Networks (ANN) and Regression Analysis models were considered to determine which of them performs better. Prediction was done using one hidden layer and three processing elements in the ANN model. Furthermore, prediction was done using regression analysis. The parameters of regression model were estimated using Least Square method. To determine the better prediction, mean square errors (MSE) attached to ANN and regression models were used. Seven real series were fitted and predicted with in both models. It was found out that the mean square error attached to ANN model was smaller than regression model which made ANN a better model in prediction.Item Knowledge discovery in academic electronic resources using text mining(2013-02) Ojo, A. K.; Adeyemo, A. B.Academic resources documents contain important knowledge and research results. They have highly quality information. However, they are lengthy and have much noisy results such that it takes a lot of human efforts to analyse. Text mining could be used to analyse these textual documents and extract useful information from large amount of documents quickly and automatically. In this paper, abstracts of electronic publications from African Journal of Computing and ICTs, an IEEE Nigerian Computer Chapter Publication were analysed using text mining techniques. A text mining model was developed and was used to analyse the abstracts collected. The texts were transformed into structured data in frequency form, cleaned up and the documents split into series of word features (adjectives, verbs, adverbs, nouns) and the necessary words were extracted from the documents. The corpus collected had 1637 words. The word features were then analysed by classifying and clustering them. The text mining model developed is capable of mining texts from academic electronic resources thereby identifying the weak and strong issues in those publications.Item Ensuring QoS with adaptive frame rate and feedback control mechanism in video streaming(2012-12) Onifade, O. F. W.; Ojo, A. K.Video over best-effort packet networks is cumbered by a number of factors including unknown and time- varying bandwidth, delay and losses, as well as many additional issues such as how to fairly share the network resources amongst many flows and how to efficiently perform one-to-many communication for popular content. This research investigates video streaming formats, encoding and compression techniques towards the development and simulation of a rate adaptation model to reduce packet loss. The thrust of this research aimed at enriching and enhancing the quality of video streaming over the wireless network. We developed both mathematical models which were thereafter simulated to depict the need for advancing the existing solution for packet scheduling towards recovery from packet loss and error handling in video streaming.Item Improving node reachability QoS during broadcast storm in Manets using neighbourhood density kowledge (NDK)(2008-12) Onifade, O. F. W.; Ojo, A. K.; Lala, O. G.The Counter-based scheme was developed to reduce Broadcast Storm problem. However, to be able to maintain high delivery ratio in either a sparse or dense networks, different thresholds are required. Because of the nature of MANETs determining this threshold require a level of dynamism, without which its operation will be marred. Our earlier research work proposed an algorithmic framework to address the BSP problem, using the knowledge of it neighbourhood density to dynamically determine the threshold so as to adapt to both dense and sparse network while limiting the above stated constrains. In this work, we present the simulation result of our attempt to improve reachability of nodes in MANETs using Neighbourhood Density Knowledge (NDK). While the major characteristics of MANETs remain indeterminate behaviours in the number of participating nodes, mobility and sporadic topology changes based on nodal movement, ability of any supporting protocol to function under both sparsely and densely population of nodes. With the Counter based threshold value based on the neighbourhood information, an important metric considered is the reacheability which is defined in terms of the ratio of nodes that received the broadcast message out of the entire node in the network. Overall, the NDK approach performs best on both sparser and dense networks.Item Angular displacement scheme (ADS): providing reliable geocast transmission for mobile ad-hoc networks (MANETs)(2008-08) Onifade, O. F. W.; Ojo, A. K.; Akande, O. O.In wireless ad hoc environments, two approaches can be used for multicasting: multicast flooding or multicast tree-based approach. Existing multicast protocols mainly based on the latter approach, may not work properly in mobile ad hoc networks as dynamic movement of group members can cause the frequent tree reconfiguration with excessive channel overhead and resulting into loss of datagram. Since the task of keeping the tree structure up-to-date in the multicast tree-based approach is nontrivial, sometimes, multicast flooding is considered as an alternative approach for multicasting in MANET. The scheme presented in this research attempts to reduce the forwarding space for multicast packets beyond earlier presented scheme and also examine the effect of our improvements upon control packet overhead, data packet delivery ratio, and end-to-end delay by further reduction in the number of nodes that rebroadcasts multicast packets while still maintaining a high degree of accuracy of delivered packets. The simulated result was carried out with OMNeT++ to present the comparative analysis on the performance of angular scheme with flooding and LAR box scheme. Our result showed a better improvement compared to flooding and LAR box schemes.