Saurabh Mukherjee

Layered approach for intrusion detection using naïve Bayes classifier

Intrusion detection is the process of monitoring and analyzing the events occurring in a computer system in order to detect signs of security problems. In real world environment, the minority intrusion attacks namely R2L and U2R/Data attacks are more dangerous than the majority attacks like Probe and DoS. The present day standalone intrusion detection systems are not effective in detecting the minority attacks. Hence, it is essential to improve the detection performance for the minority intrusions, while maintaining a reasonable overall detection rate. In this paper we propose layered approach for improving the minority attack detection rate without hurting the prediction performance of the majority attacks. The proposed model used Naive Bayes classifier on reduced dataset for each attack class. In this system every layer is separately trained to detect a single type of attack category.

A Thorough Insight into Theoretical and Practical Developments in MultiAgent Systems

Multiagent systems have been a fascination for research community and are often seen as an intelligent solution to many complex real world problems. Researchers have been active in the domain since last three decades and many developments pertaining to theoretical design and practical developments of multiagent systems are worth appreciating. The growth in MAS is multidirectional ranging from conceptual ideas to practical implementations and from the wide range of applications; it appears that multiagent systems are proving to be universal. The paper presents a concise survey of developments in MAS highlighting the important contributions in the field and also questions the universal applicability of agents.

A comparative study on thyroid disease detection using K-nearest neighbor and Naive Bayes classification techniques

Data mining is an important research activity in the field of medical sciences since there is a requirement of efficient methodologies for analyzing and detecting diseases. Data mining applications are used for the management of healthcare, health information, patient care system, etc. It also plays a major role in analyzing survivability of a disease. Classification and clustering are the popular data mining techniques used to understand the various parameters of the health data set. In this research work, various classification models are used to classify thyroid disease based on the parameters like TSH, T4U and goiter. Several classification techniques like K-nearest neighbour, support vector machine and Naive Bayes are used. The experimental study has been conducted using Rapid miner tool and the results shows that the accuracy of K-nearest neighbour is better than Naive Bayes to detect thyroid disease.

Integration of GIS, Spatial Data Mining, and Fuzzy Logic for Agricultural Intelligence

With increasing population and decreasing crop production, there is an enormous need to increase land under cultivation. This paper attempts to explore the applicability of spatial data mining integrated with Geographic Information System (GIS) and fuzzy logic for Agricultural Intelligence. The research uses thematic agricultural data of Jodhpur District of Rajasthan state and mines spatial association rules between groundwater, wastelands, and soils of Jodhpur District which are then used to create Mamdani fuzzy inference system for determining the utilization of wastelands. A taluk-wise map of Jodhpur district is created from the fuzzy values showing the utilization of wastelands. Analysis of results showed that out of 36,063 hectares of mined pattern, Phalodi taluk of Jodhpur district contains the largest wasteland area and the area under the medium type of utilization is the largest. It could be suggested that wastelands having a substantial groundwater underneath can be irrigated for agriculture and/or producing fodder and firewood.

A novel algorithm of weighted fuzzy spatial association rule mining (WFSARM) for wasteland reclamation

Abstract Wasteland reclamation is one of the ways in which the arable land can be increased. Weighted fuzzy spatial association rules could be used for associating wastelands with ground water and soil quality. The quality of wasteland, ground water and soil are used to provide weight. The association rules mined need to be further subjected to an interestingness measure that defines their utility. For the given challenge the authors propose a new algorithm for weighted fuzzy spatial association rule mining for wasteland reclamation (WFSARM) and ranking them on interestingness measures. Here, two new measures called faith and weight-area score are introduced. Multiple minimum faith thresholds are used for pruning of itemsets. The comparative analysis shows that the proposed algorithm is ef ficient and scalable and mines more number of rules as compared to Apriori algorithm. The results are viewed using GIS tool.

Information Retrieves from Brain MRI Images for Tumor Detection Using Hybrid Technique K-means and Artificial Neural Network (KMANN)

Medical imaging plays a significant role in the field of medical science. In present scenario image segmentation is used to extract abnormal tissues from normal tissues clearly in medical images. Tumor detection through brain MRI using automatic system is effective and consumes lesser time which helps doctor in diagnosis. A Tumor can convert into cancer, which is major leading cause of death. Automation of tumor detection is required for detecting tumor on early stage. Proposed work presents hybrid technique for information retrieval from brain MRI images. This research work presents an efficient technique based on K-means and artificial neural network (KMANN). GLCM (Grey Level co-occurrence matrix) used for feature extraction. Fuzzy Inference System is created using extracted feature which followed by thresholding, morphological operator and Watershed segmentation for brain tumor detection. Proposed method is used to identifying affected part of brain and size of tumor from MRI image with the help of MATLAB R2013b is used.

An Agricultural Intelligence Decision Support System: Reclamation of Wastelands Using Weighted Fuzzy Spatial Association Rule Mining

The increase in GDP of the country has given a flight to industrialization and urbanization, causing more and more utilization of agricultural lands for non-agricultural purposes. Since the availability of agricultural lands is limited, requisite measures must be taken to restore wastelands for cultivation. Therefore to filter out the suitable wastelands for reclamation and predict their level of utilization, this paper proposes the agricultural intelligence decision support system. The proposed system has two phases. The first phase consists of the mining technique in which required attributes are selected, intersection is applied as spatial predicate and weights are assigned to linguistic terms for obtaining weighted fuzzy rules. In the second phase the fuzzy inference system is constructed in accord of the weighted fuzzy spatial rules mined in the previous phase. This will assist agriculture-related organizations and persons to take well informed decisions for effective utilization of wastelands.

Empirical analysis of SIFT, Gabor and fused feature classification using SVM for multispectral satellite image retrieval

High Level image understanding and Content extraction is becoming a challenging task in Content based image retrieval system for satellite images. Retrieval based on the low level extraction techniques does not bridge the semantic gap. In the experiment high level feature extraction techniques i.e. scale invariant feature transform and Gabor descriptors are used. The novel approach is proposed in which both the feature descriptors are fused to retrieve the results with more accuracy rate. The experiment is conducted on the multispectral satellite images, of Landsat 8 sensor. The similarity of the query image to that of stored database images is matched by the Manhattan distance. The Precision and Recall is computed for the data set. The results have shown the improved retrieval rate. The retrieval efficiency is further increased by using the SVM classifier by classifying the satellite images based on Urban area, Water body and Vegetation. The experimental results shows that the fusion technique gives better result and more accuracy can be obtained by classifying the dataset using SVM.

A Clustering-Based Generic Interaction Protocol for Multiagent Systems

The paper proposes a clustering based Generic Interaction Protocol for Multiagent Systems (GIPMAS) that exploits clustering methodology for establishing interaction among agents operating in a network of multiagent systems. GIPMAS is a hierarchical protocol that supports intelligent formation of clusters and dynamic election of cluster head and executive cluster head as well. It also describes a recovery mechanism in case cluster head relocates from its respective cluster.

IDENTIFICATION OF DIFFERENT LIVER DISEASES BY USING IMAGERY TECHNIQUES: A REVIEW.

Chetna Garg 1 , Megha Bhadauria 1 , Saurabh Mukherjee 2 and K. F. Rahman 2 . 1. Mtech Scholar, Department of Computer Science, AIM & ACT, Banasthali University, Rajasthan, India. 2. Associate Professor, Department of Computer Science, AIM & ACT, Banasthali University, Rajasthan, India. ...................................................................................................................... Manuscript Info Abstract ......................... ........................................................................ Manuscript History