Heba Ayeldeen

Distance Similarity as a CBR Technique for Early Detection of Breast Cancer: An Egyptian Case Study

Case-based reasoning as a concept covers almost a lot of technologies and techniques including knowledge management, artificial intelligence, machine learning techniques as well as database technology. The usage of all these technologies can easily aid in early detection of breast cancer as well as help other decision makers take the right decision on time and all the times. Of the main hot topics nowadays concerning executive managers and decision makers is measuring the similarity between objects. For better performance most organizations are in need on semantic similarity and similarity measures. This article presents mathematically different distance metrics used for measuring the binary similarity between quantitative data within cases. The case study represents a quantitative data of breast cancer patients within Faculty of medicine Cairo University. The experimental results show that the squared chord distance yields better with a 96.76 % without normalization that correlate more closely with human assessments compared to other distance measures used in this study.

Case Selection Strategy Based on K-Means Clustering

Knowledge acquisition is considered as an extraordinary issue concerning organizations and decision makers nowadays. Learning from previous failures and successes saves plenty of time in understanding the problems and visualizing data. Case-based Reasoning (CBR) as a process is one of the most used methods to solve the problem of knowledge capture and data understanding. In this paper we proposed an approach for clustering theses documents based on CBR combined with lexical similarity and k-means algorithm for cluster-dependent keyword weighting. The cluster dependent keyword weighting help in partitioning and categorizing the theses documents into more meaningful categories. The proposed approach yield to 91.95 % increase of using CBR in comparison to human assessments.

Evaluation of Semantic Similarity across MeSH Ontology: A Cairo University Thesis Mining Case Study

Knowledge exaction and text representation are considered as the main concepts concerning organizations nowadays. The estimation of the semantic similarity between words provides a valuable method to enable the understanding of texts. In the field of biomedical domains, using Ontologies have been very effective due to their scalability and efficiency. The problem of extracting knowledge from huge amount of data is recorded as an issue in the medical sector. In this paper, we aim to improve knowledge representation by using MeSH Ontology on medical theses data by analyzing the similarity between the keywords within the theses data and keywords after using the MeSH ontology. As a result, we are able to better discover the commonalities between theses data and hence, improve the accuracy of the similarity estimation which in return improves the scientific research sector. Then, K-means cluster algorithm was applied to get the nearest departments that can work together based on medical ontology. Experimental evaluations using 4, 878 theses data set in the medical sector at Cairo University indicate that the proposed approach yields results that correlate more closely with human assessments than other by using the standard ontology (MeSH). Results show that using ontology correlates better, compared to related works, with the similarity assessments provided by experts in biomedicine.

Effective Classification and Categorization for Categorical Sets: Distance Similarity Measures

Measuring the similarity between objects is considered one of the main hot topics nowadays and the main core requirement for several data mining and knowledge discovery task. For better performance most organizations are in need on semantic similarity and similarity measures. This article presents different distance metrics used for measuring the similarity between qualitative data within a text. The case study represents a qualitative data of Faculty of medicine Cairo University for theses. The dataset is about 5,000 thesis document with 35 departments and about 16,000 keyword. As a result, we are able to better discover the commonalities between theses data and hence, improve the accuracy of the similarity estimation which in return improves the scientific research sector. The experimental results show that Kulczynksi distance yields better with a 92.51 % without normalization that correlate more closely with human assessments compared to other distance measures.

Case-Based Reasoning: A Knowledge Extraction Tool to Use

Case-based reasoning (CBR) is a relative newcomer to AI and is commonly described as an AI as well as KM technology. Case-Based Reasoning is considered as a methodology not a technology to use. Finding the similarities between objects as well as knowledge extraction sometimes is a complicated issue to handle concerning decision makers and executive managers. Learning from previous failures and successes saves plenty of time in understanding the problems and visualizing the data. CBR as a process is one of the most used methods to solve the problem of knowledge capture and data understanding. In this paper we show mathematically the usage of CBR in clustering documents and finding correlations between medical data by using CBR with DB technology as an application. Results yield to an increase in comparison to human assessments and not using CBR methods.

Fuzzy clustering and categorization of text documents

The fuzzy Euclidean distance clustering algorithm has been well studied and used in information retrieval society for clustering documents. However, the fuzzy logic algorithm poses problems in dealing with large amount of data. In this paper we proposed results for clustering theses documents based on Euclidean distances and cluster-dependent keyword weighting. The proposed approach is based on the Fuzzy Euclidean distance clustering algorithm. The cluster dependent keyword weighting help in partitioning and categorizing the theses documents into more meaningful categories.

Classification of Liver Fibrosis Patients by Multi-dimensional Analysis and SVM Classifier: An Egyptian Case Study

One of the most critical concerns in different fields, particularly in the medical domain, is the time taken to arrive at a decision. In Egypt, Liver fibrosis is one of the medical conditions affecting a large number of people across different genders and ages. Thus, early detection of fibrosis in hepatic patients is considered a challenging area for many physicians. The using of machine learning techniques and strategic information systems highly aid in solving the problem of classification of data and knowledge acquisition. In this study linear and even multi-dimensional analysis combined with K-Nearest Neighbor (KNN) and Support Vector Machine (SVM) classifiers are applied. Results yield to an accuracy of 98% to cubic SVM classifier compared to 75% accuracy to medium KNN.

Case-Based Retrieval Approach of Clinical Breast Cancer Patients

Breast cancer is a syndrome that needs to be evaluated and well treated on the early stages to avoid any metastasis stage upgrading. Not just medical treatment is acquired, but also the usage of artificial intelligence and software technologies aid in the early detection of breast cancer. After using Case based Reasoning as a knowledge management as well as artificial intelligence system with Random Forest classifier, result yields to overall accuracy of 99%.