Breast cancer was one of the most common reasons for death among the women in the world. Limited awareness of the seriousness of this disease, shortage number of specialists in hospitals and waiting the diagnostic for a long period time that might increase the probability of expansion the injury cases. Consequently, various machine learning techniques have been formulated to decrease the time taken of decision making for diagnoses the breast cancer and that might minimize the mortality rate. The proposed system consists of two phases. Firstly, data pre-processing (data cleaning, selection) of the data mining are used in the breast cancer dataset taken from the University of California, Irvine machine learning repository in this stage we modified the Correlation Feature Selection (CFS) with Best First Search (BFS) established on the Discriminant Index (DI) so as to reduce the complexity of time and get high accuracy. Secondly, Bayesian Rough Set (BRS) classifier is applied to predict the breast cancer and help the inexperienced doctors to make decisions without need the direct discussion with the specialist doctors. The result of experiments showed the proposed system give high accuracy with less time of predication the disease.
A Bayesian formulation of the ridge regression problem is considerd, which derives from a direct specification of prior informations about parameters of general linear regression model when data suffer from a high degree of multicollinearity.A new approach for deriving the conventional estimator for the ridge parameter proposed by Hoerl and Kennard (1970) as well as Bayesian estimator are presented. A numerical example is studied in order to compare the performance of these estimators.
The significance of the work is to introduce the new class of open sets, which is said Ǥ- -open set with some of properties. Then clarify how to calculate the boundary area for these sets using the upper and lower approximation and obtain the best accuracy.
Relation on a set is a simple mathematical model to which many real-life data can be connected. A binary relation on a set can always be represented by a digraph. Topology on a set can be generated by binary relations on the set . In this direction, the study will consider different classical categories of topological spaces whose topology is defined by the binary relations adjacency and reachability on the vertex set of a directed graph. This paper analyses some properties of these topologies and studies the properties of closure and interior of the vertex set of subgraphs of a digraph. Further, some applications of topology generated by digraphs in the study of biological systems are cited.
(1)
Carbohydrate antigen 19-9 (CA 19-9) levels were measured in sera and tissues of 40 patients with breast cancer (01), 8 patients with prostate cancer (G2)and 12 patients with thyroid cancer (G3), by the enzyme linked immunosorbent assay (ELISA) technique.
The patients were admitted to Medical City Hospitals (Baghdad Teaching Hospital and Nursing Home Hospital). The sera were taken just before surgery, where the specimens were taken immediately after surgery and kept in saline solution at -20°C until the time of homogenizing process.
The results of CA 19-9 levels in sera were (16.309±7.143; 31.281±0.766;
11.5±0.707 U/ml respectively compared with serum CA 19-9 level of control group G4 which was 7.74
... Show MoreThis work implements an Electroencephalogram (EEG) signal classifier. The implemented method uses Orthogonal Polynomials (OP) to convert the EEG signal samples to moments. A Sparse Filter (SF) reduces the number of converted moments to increase the classification accuracy. A Support Vector Machine (SVM) is used to classify the reduced moments between two classes. The proposed method’s performance is tested and compared with two methods by using two datasets. The datasets are divided into 80% for training and 20% for testing, with 5 -fold used for cross-validation. The results show that this method overcomes the accuracy of other methods. The proposed method’s best accuracy is 95.6% and 99.5%, respectively. Finally, from the results, it
... Show More
This research introduces a proposed hybrid Spam Filtering System (SFS) which consists of Ant Colony System (ACS), information gain (IG) and Naïve Bayesian (NB). The aim of the proposed hybrid spam filtering is to classify the e-mails with high accuracy. The hybrid spam filtering consists of three consequence stages. In the first stage, the information gain (IG) for each attributes (i.e. weight for each feature) is computed. Then, the Ant Colony System algorithm selects the best features that the most intrinsic correlated attributes in classification. Finally, the third stage is dedicated to classify the e-mail using Naïve Bayesian (NB) algorithm. The experiment is conducted on spambase dataset. The result shows that the accuracy of NB
... Show MoreThe cancer is one of the biggest health problems that facing the world . And the bladder cancer has a special place among the most spread cancers in Arab countries specially in Iraq and Egypt(2) . It is one of the diseases which can be treated and cured if it is diagnosed early . This research is aimed at studying the assistant factors that diagnose bladder cancer such as (patient's age , gender , and other major complains of hematuria , burning or pain during urination and micturition disorders) and then determine which factors are the most effective in the possibility of diagnosing this disease by using the statistical model (logistic regression model) and depending on a random sample of (128) patients . After
... Show More