Ameliorate Fuzzy C-Means: An Ameliorate Fuzzy C-Means Clustering Algorithm for Ct-Lung Image Segmentation

Detection and segmentation of fissures is useful in the clinical interpretation of CT lung images to diagnose the presence of pathologies in the human lungs. A new automated method based on marker-based watershed transformation has been proposed to segment the fissures considering its unique structure as a long connected component. Marker based watershed transformation is applied and morphological operations are employed to specify the internal and external markers. The smaller regions in the resulting image are removed by a novel procedure called Small Segment Removal Algorithm (SSRA) to segment the fissures alone. The performance of the method is validated by experimenting with 6 CT image sets. An expert radiologist observation is used as reference to assess the performance. A promising accuracy of 96.61% is shown with the rms error in the range of 0.877±0.224 mm for the left oblique fissure and 0.803±0.262 mm for the right oblique fissure.

Section: Jcsmentioning

confidence: 99%

A Novel Approach to Detect Fissures in Lung Ct Images Using Marker-Based Watershed Transformation

Devaki¹,

Bhaskaran²

2014

“…Most existing algorithms involving cluster become hihgly susceptible if the measure of similarity is evaluted among data points in full-dimensional space. To address this issue, Bridget Nirmala and Gowri (2013) enhanced the existing FCM algorithm and designed a new technique called Ameliorate FCM (AFCM). During the initial stage, the input image is preprocessed for noise removal applying Contrast Limited Adaptive Histogram Equalization (CLAHE) technique.…”

Section: Literature Reviewmentioning

confidence: 99%

Combination of Difference Subspace and Oppurtunistic Clustering on High Dimensional Data

Ravichandran¹,

Shanmugam²

2014

Clustering is recognized as sigificant technique for analysing data and concentric effort has been taken in different domains comprises of recognition of pattern, statistical analysis and data mining for decades. Subspace clustering is developed from the group of cluster objects from all subspaces of a dataset. During clustering of objects involing higher dimension, the accuracy and effectiveness of traditional clustering algorithms are very poor, because data objects may present in different clusters involving different subspaces of differing level of dimensions. To address the above issue, a new technique termed Difference Subspace and Opportunistic Clustering (DSOC) model is presented for high dimensional data to improve the accuracy during the search process and also considers the problem of accuracy in clustering the high dimensional data. Methods for obtaining subspace and designing clustering model for DSOC are specified and demonstrated, where the subspace identify the possibility of each cluster center with the detection of attackers based on multiple locations and estimation points with derived centroid points. Through comprehensive mathematical analysis, we show that DSOC improves the accuracy in high dimensional data with efficient cluster validation obtained using different subspace and opportunistic algorithm. As validated by extensive experiments on CORTINA and Ski Resort Data Set datasets DSOC produces high quality clusters by detecting the attackers and the efficiency of DSOC outperforms previous works.

“…For anomaly detection, data mining has been applied (Lunt et al, 1992;Lee and Stolfo, 2000). Statistics (Debar et al, 1992;Anderson et al, 1995), Artificial Neural Network (ANN) (Lippmann and Cunningham, 2000;Cho and Park, 2003), Support Vector Machines (SVM) (Premanode et al, 2013), Neuro-Fuzzy (NF) computing (Mukkamala et al, 2005;Nirmala and Gowri, 2013), Multivariate Adaptive Regression Splines (MARS) (Banzhaf et al, 1998) and Linear Genetic Programming (LGP) (Mukkamala et al, 2006), Rough Set (Guo et al, 2010), Rough-DPSO (Rahman et al, 2009), BA (Alomari and Othman, 2012). These methods are commonly applied for misuse and anomaly detections.…”

Section: Related Workmentioning

confidence: 99%

Hybrid Feature Selection Algorithm for Intrusion Detection System

Hasani

Othman

Kahaki

2014

Network security is a serious global concern. Usefulness Intrusion Detection Systems (IDS) are increasing incredibly in Information Security research using Soft computing techniques. In the previous researches having irrelevant and redundant features are recognized causes of increasing the processing speed of evaluating the known intrusive patterns. In addition, an efficient feature selection method eliminates dimension of data and reduce redundancy and ambiguity caused by none important attributes. Therefore, feature selection methods are well-known methods to overcome this problem. There are various approaches being utilized in intrusion detections, they are able to perform their method and relatively they are achieved with some improvements. This work is based on the enhancement of the highest Detection Rate (DR) algorithm which is Linear Genetic Programming (LGP) reducing the False Alarm Rate (FAR) incorporates with Bees Algorithm. Finally, Support Vector Machine (SVM) is one of the best candidate solutions to settle IDSs problems. In this study four sample dataset containing 4000 random records are excluded randomly from this dataset for training and testing purposes. Experimental results show that the LGP_BA method improves the accuracy and efficiency compared with the previous related research and the feature subcategory offered by LGP_BA gives a superior representation of data.