Theses

Permanent URI for this collectionhttps://repository.ui.edu.ng/handle/123456789/409

Browse

Now showing 1 - 2 of 2

CONCEPTUAL KNOWLEDGE MODEL FOR IMPROVING TERM SIMILARITY IN RETRIEVAL OF WEB DOCUMENTS
(2016-05) ABDULLAH, K. A.
Terms Similarity (TS) in retrieval systems are based on lexical matching, which determines if query terms are useful and reflect the users’ information need in related domains. Existing works on TS use Term Frequency-Inverse Document Frequency (TF-IDF) to determine the occurrence of terms in web documents (snippets) is incapable of capturing the problem of semantic language mismatch. This study was designed to develop a conceptual knowledge model to solve the problem of TS in web documents retrieval by amplifying structured semantic network in Multiple Document Sources (MDSs) to reduce mismatch in retrieval results. Four hundred and forty-two IS-A hierarchy concepts were extracted from Internet using a web ontology language. These hierarchies were structured in MDSs to determine similarities. The concepts were used to formulate queries with the addition of terms from knowledge domain. Suffix Tree Clustering (STC) was adapted to cluster, structure the web and reduce dimensionality of features. The IS-A hierarchy concept on parent and child relationship was incorporated into the STC to select the best cluster, consisting of 100 snippets, four web page counts and WordNet as MDSs. Similarity was estimated on Cosine, Euclidean and Radial Basis Function (RBF) on the TF-IDF. Based on STC, TF-IDF was modified to develop Concept Weighting (CW) estimation on snippets and web page count. Similarity was estimated between TF-IDF and developed Concept Weighting; Cosine and CW-Cosine, Euclidean and CW-Euclidean and RBF and CW-RBF. Semantic network (WordNetSimilarity) LIn’ measure was extended with PAth length of the taxonomy concept to develop LIPA. The LIPA was compared with other WordNetSimilarity distance measures: Jiang and Conrath (JCN) and Wu and Palmer (WUP) as well as LIn and PAth length separately. Concept Weighting and WordNetSimilarity scores were combined using machine learning techniques to leverage a robust semantic similarity score and accuracy measure using Mean Absolute Error (MAE). The RBF and CW-RBF generated inconsistent values (0.9 for null and zero snippets. Similarity estimation obtained on Cosine, Euclidean, CW-Cosine and CW-Euclidean were 0.881, 0.446, 0.950 and 0.964, respectively. The retrieved snippets removed irrelevant features and enhanced precisions. WordNetSimilarity JCN, WUP, LIn, PAth, and LIPA values were 0.868, 0.953, 0.995, 0.955 and 0.998, respectively. The WordNetSimilarity improved the semantic similarity of concepts. The Concept Weighting and WordNetSimilarity; CW-Cosine, CW-Euclidean, JCN, WUP, LIn, PAth, and LIPA were combined to generate similarity coefficient scores 0.941, 0.944, 0.661, 0.928, 0.996, 0.924 and 0.998, respectively. The MAE on Cosine, Euclidean, CW-Cosine and CW Euclidean were 0.058, 0.011, 0.014 and 0.009, respectively while for JCN, WUP, LIn, PAth, and LIPA were 0.022, 0.004, 0.022, 0.019 and 0.020, respectively. The accuracy of the combined similarity for JCN, WUP, LIn, PAth, CW-Cosine, CW-Euclidean and LIPA were 0.023, 0.050, 0.008, 0.011, 0.024, 0.015 and 0.009, respectively. The developed conceptual knowledge model improved retrieval of web documents with structured multiple document sources. This improved precision of information retrieval system and solved the problem of semantic language mismatch with robust similarity between the terms.
IMPROVING VISION IMPAIRED USERS ACCESS TO ELECTRONIC RESOURCES IN E-LEARNING ENVIRONMENT WITH MODIFIED ARTIFICIAL NEURAL NETWORK
(2017-05) FASOLA, O. O.
Assistive Technology (ATs) provide means through which persons with visual impairment are empowered with adaptive devices and methods for accessing multimedia information. However, the degree of sensitivity and specificity values for access to electronic resources by visual impaired persons varies. Existing ATs were designed as “one model fits all” (static calibration requirements), thereby limiting the usability by vision impaired users in an e-learning environment. The study presents a Dynamic Thresholding Model (DTM) that adaptively adjusts the vision parameters to meet the calibration requirements of vision impaired users. Data from International Statistical Classification of Diseases and Related Health Problems of World Health Organisation (WHO) containing 1001 instances of visual impairment measures were obtained from 2008 to 2013. The users’ vision parameters of WHO for Visual Acuity Range (VAR) were adopted. These were: VAR ≥ 0.3(299); 0.1 < VAR < 0.3(182); 0.07 ≤ VAR < 0.1(364); 0.05 ≤ VAR < 0.07(120); 0.02 ≤ VAR < 0.05(24); and VAR < 0.02(12). Data for six VAR groups were partitioned into 70% (700) and 30% (301) for training and testing, respectively. Data for the six groups were transformed into 3-bits encoding to facilitate model derivation. The DTM was developed with calibrator parameters (Visual Acuity (Va), Print Size (Ps) and Reading Rate (Rr)) for low acuity, adaptive vision calibrator and dynamic thresholding. The VAR from the developed DTM was used to predict the optimal operating range and accuracy value on observed WHO dataset irrespective of the grouping. Six-epochs were conducted for each thresholding value to determine the sensitivity and specificity values relative to the False Negative Rate (FNR) and False Positive Rate (FPR), respectively, which are evidences of misclassification. The 3-bit encoding coupled with the DTM yielded optimised equations of the form: .1718.172436.14985.834508.07474.19383.128042.5730703.5976073.4631RrPsVaOPRrVaPsOPRrVaPsOP Where OP1, OP2 and OP3 represent the first, second and third bit, respectively. Five local maxima accuracy and one global maximum threshold values were obtained from the DTM. Local maxima threshold values were 0.455, 0.470, 0.515, 0.530, and 0.580, with corresponding percentage accuracy of 99.257, 99.343, 99.171, 99.229, and 99.429. Global maximum accuracy was 99.6 at threshold value of 0.5. The Va, Ps, and Rr produced equal numbers of observations (301) agreeing with the result in WHO report. Correctly classified user impairment was 99.89%, with error rate of 0.11%. The model predicted sensitivity value of 99.79% (0.21 FNR), and specificity value of 99.52% (0.48 FPR). The developed dynamic thresholding model adaptively classified various degrees of visual impairment for vision impaired users.