Data mining extracts useful information from a large data set among heterogeneous data base. This paper shows how the data mining techniques can be used in Automobile industry. Data mining Techniques such as Classification, Association rules, Clustering etc. can be appropriately applied to arrive a solution which will enable the vehicle manufacturing companies to take decision on model preferences and choice, create stimuli to push customers to choose among choice of variance and to aid help and support to customers in the aspects of financial and insurance products. By applying these techniques, the car manufacturers can identify the potential customers; develop products according to customer choice and to build customer relationship to promote business by attracting new customers while retaining the existing customers. The Automobile manufacturing companies are investing millions of rupees to understand, absorb, and listen their customers and their changing preferences to choose the vehicle of their choice. Market environment determines the buying behavior of customers. This is inevitable because the competition is emerging though it is a healthy situation but a potential threat to the automobile manufactures to come out with lot of innovative ideas on invention and development of their product to delight the customers

Sales management is an important aspect of all Business analytics outfits. However, in today’s digital world we need to find on-the-go solutions. We can find these by targeting the mobile Apps. We find that there are numerous mobile solutions offered by android Apps in the market. They are so popular because of compatibility on various mobile platforms. But a major problem faced by many outfits today is their compatibility with backend systems in use, namely the ERPs like SAP. In this paper we aim to solve this problem. We also portray a successful use of the upcoming SAP Fiori technology which works on multiple mobile platforms. Another major issue is business analytics on such mobile platforms. Using SAP ERP and the latest HANA databases, we can perform robust data mining algorithms on vast amounts of data. Infact, some data- mining essential algorithms are already a part of such systems in the form of libraries. However, these databases are expensive and are unsuitable for small outfits using SAP services. Today, there exists virtually no library for data-mining on mobile devices without a Hana database. In our experiments we aim to solve this issue. We have created a market basket-analysis system to be deployed as a mobile App on SAP Fiori from scratch without a Hana database. We implemented an Apriori algorithm, to generate rules. We found that such a system can be developed with said requirements and has very low operational delay

Shortages of available drugs suitable for pediatric patients (infants, children, and adolescents) play a central role in the increased demand for compounded medicines. A doctor tends to give the similar prescription for the patients with the same clinical condition. This will form a pattern in prescribing. This research aims to find the pattern of compounded medicines prescribing (in the form of association rules) done by the doctors and stored in forms of data mining using Algorithm FP Growth Analysis. The result of this pattern can be used as the proposal to determine the supplies of brandname medicine in the hospital pharmacy.

In the year 1999, when T. R Golub first presented an idea for classifying cancer at the molecular level, this boosted research in cancer diagnosis to a whole new level. The researchers began to analyze the disease at the genetic level with the help of microarray databases. Then there were many new algorithms designed by researchers to classify different types of cancer. The objective of this paper is to present a tool designed exclusively to predict and classify leukemia into its types. The leukemia dataset published by Golub is used for this purpose. The first step is to identify the most significant genes causing cancer from the training set. These selected genes then are used to build the classifier based on decision rules, and eventually to predict the type of leukamia. This classifier which is modeled based on decision rules is found to work with an accuracy of 94%. The algorithm is quite simple in terms of complexity. It is possible to use a minimum number of genes for classification purposes rather than using a large set of genes. The genes that are responsible for prognosis of cancer are mainly selected for designing the classifier.

The survey report titled “Search Engine Optimization using Page Ranking Algorithms” presents various page ranking algorithms for optimizing the search engine results. There are various page ranking algorithms which aids the search engines in listing the pages with higher degree of relevance. The page ranking algorithms discussed in this report are page rank algorithm, HITS algorithm and semantic similarity algorithm.

Outlier is the data object which does not comply with the general behaviour or model of data. Which are grossly different from entire set of data. From large data set detecting outliers present different challenge resulting from curse of dimensionality. As the data size is double every year, there is a need to detect outlier in large datasets as early as possible. If there are lot of outliers in data set there might de misclassification of data and outlier data might be classified as normal data. More contrasting outlier score gives by SVM in high dimensional data in which training the data set is relatively easy. SVM mainly focusing on high dimensionality of data, this method will be allowed to use a training data set to train the classifier while detecting outliers from high dimensional data.

Data mining techniques are widely used in various areas of marketing management for extracting useful information. Particularly in a business-to-customer (B2C) setting, it plays an important role in customer segmentation. A retailer not only tries to improve its relationship with its customers, but also enhances its business in a manufacturerretailer-consumer chain with respect to this information. Although there are various approaches for customer segmentation, we have used an analytic hierarchical process based data mining technique in this regard. Customers are segmented into six clusters based on Davis-Bouldin (DB) index and K-Means algorithm. Customer lifetime value (CLV) along four dimensions, viz., Length (L), Recency (R), Frequency (F) and Monetary value (M) are considered for these clusters. Then, we apply Saaty’s analytical hierarchical process (AHP) to determine the weights of these criteria, which in turn, helps in computing the CLV value for each of the clusters and their individual rankings. This information is quite important for a retailer to design promotional strategies for improving relationship between the retailer and its customers. To demonstrate the effectiveness of this methodology, we have implemented the model, taking a real life data-base of customers of an organization in the context of an Indian retail industry.

The term knowledge discovery in databases (KDD) is the analysis step of data mining. The data mining goal is to extract the knowledge and patterns from large data sets, not the data extraction itself. Big-Data Computing is a critical challenge for the ICT industry. Engineers and researchers are dealing with the cloud computing paradigm of petabyte data sets. Thus the demand for building a service stack to distribute, manage and process massive data sets has risen drastically. We investigate the problem for a single source node to broadcast the big chunk of data sets to a set of nodes to minimize the maximum completion time. These nodes may locate in the same datacenter or across geo-distributed data centers. The Big-data broadcasting problem is modeled into a LockStep Broadcast Tree (LSBT) problem. And the main idea of the LSBT is defining a basic unit of upload bandwidth, r, a node with capacity c broadcasts data to a set of [c=r] children at the rate r. Note that r is a parameter to be optimized as part of the LSBT problem. The broadcast data are further divided into m chunks. In a pipeline manner, these m chunks can then be broadcast down the LSBT. In a homogeneous network environment in which each node has the same upload capacity c, the optimal uplink rate r, of LSBT is either c=2 or 3, whichever gives the smaller maximum completion time. For heterogeneous environments, an O(nlog2n) algorithm is presented to select an optimal uplink rate r, and to construct an optimal LSBT. With lower computational complexity and low maximum completion time, the numerical results shows better performance.The methodology includes Various Web applications Building and Broadcasting followed by the Gateway Application and Batch Processing over the TSV Data after which the Web Crawling for Resources and MapReduce process takes place and finally Picking Products from Recommendations and Purchasing it.

Facial Expressions of the human being is the one which is the outcome of the inner feelings of the mind. It is the person’s internal emotional states and intentions.A person’s face provides a lot of information such as age, gender, identity, mood, expressions and so on. Faces play an important role in the recognition of the expressions of persons. In this research, an attempt is made to design a model to classify human facial expressions according to the features extracted f0rom human facial images by applying 3 Sigma limits inSecond level decision using Neural Network (NN). Now a days, Artificial Neural Network (ANN) has been widely used as a tool for solving many decision modeling problems. In this paper a feed forward propagation Neural networks are constructed for expression classification system for gray-scale facial images. Three groups of expressions including Happy, Sad and Anger are used in the classification system. In this paper, a Second level decision has been proposed in which the output obtained from the Neural Network(Primary Level) has been refined at the Second level in order to improvise the accuracy of the recognition rate. The accuracy of the system is analyzed by the variation on the range of the expression groups. The efficiency of the system is demonstrated through the experimental results.

The use of recent technology creates more impact in the teaching and learning process nowadays. Improvement of students’ knowledge by using the various technologies like smart class room environment, internet, mobile phones, television programs, use of iPods and etc. are play a very important role. Most of the education institutions used classroom teaching using advanced technologies such as smart class environment, visualization by power point projector and etc. This research work focusses on such technologies used for the improvement of student’s performance using some of the Data Mining (DM) techniques particularly classification and clustering. Information repositories (Educational Data Bases, Data Warehouses) are the source place for collecting study materials and use them for their learning purposes is the number one source for preparation of examinations. Particularly, this research work analyzes about the use of clustering and classification algorithms to enable the student’s performances and their learning capabilities using these modern technologies. During the study period, the student’s family background and their economic status are also play a very important role in their daily activities. These things are not considered in this survey work. A comparative study is carried out in this work by comparing students performance based on their results. The comparison is carried out based on the results of some of the classification and clustering algorithms. Finally, it states that the best algorithm for the improvement of students performance using these algorithms.

Breast tissue identification is the task of finding and identifying breast tissues in digital mammograms. This paper presents a different type of edge detection methods that use digital image processing techniques, which is to detect and identifies the breast tissue from digital mammograms. Basically to identify and detect the tissue here we use two important steps are image enhancement and edge detection. To identify a breast tissue from digital image is a major task in digital image processing.

Face Recognition is a vital role in the field of computer Science and Engineering. Face recognition presents a challenging problem in the field of image processing and computer vision, and as such has received a great deal of attention over the last few years because of its many applications in various domains. A lot of algorithms and techniques have been proposed for solving authenticated a person and face recognition system. Social Networking has become today’s lifestyle and anyone can easily receive information about everyone in the world. It is very useful if a personal identity can be obtained from the any device and also connected to social networking. Cloud computing is a new technology in the IT industry. In that, identifying authorized user is a major problem. The user wanting to access the data or services needs to be registered and before every access to data or services; his/her identity must be authenticated for authorization. There are several authentication techniques including traditional and biometrics but it has some drawbacks. In this paper, we have proposed new face recognition system (FRS) which overcome all drawbacks of traditional and other biometric authentication techniques and enables only authorized users to access data or services from cloud server.

The classification algorithms are very frequently used algorithms for analyzing various kinds of data available in different repositories which have real world applications. The main objective of this research work is to find the performance of classification algorithms in analyzing Breast Cancer data via analyzing the mammogram images based its characteristics. Different attribute values of cancer affected mammogram images are considered for analysis in this work. The Patients food habits, age of the patients, their life styles, occupation, their problem about the diseases and other information are taken into account for classification. Finally, performance of classification algorithms J48, CART and ADTree are given with its accuracy. The accuracy of taken algorithms is measured by various measures like specificity, sensitivity and kappa statistics (Errors).

With the sophistication of life of the human with many embedded technologies use of sensors in all the intelligent systems has become unavoidable. The robot vehicle designed here is wirelessly controlled with the joystick and can find application in the areas where human cannot have access. The first objective of the work is to create the Graphical User Interface (GUI) in PC to interface joy stick with the industrial robot. The robot movement and its position can be controlled easily by a joystick and monitored through application software. Microsoft visual studio is used to develop Graphical User Interface for the application. The Joystick Reference Value is stored in joystick library code and robot control code accesses the joystick reference data and process to send the command to the robot. The interfacing is done through the USB port. The combination of joystick library code and robot control code is used to implement a user friendly robot. The second objective of the system is to provide live video monitoring and temperature and Gas detection in hazardous environment in industries. ZigBee protocol is used as the communication medium between rover robot and PC.

Facial recognition systems are biometric methods used to pinpoint the identities of faces present in various digital formats by comparing them to facial databases. The variation in illuminating conditions is a huge hindrance for efficient operation of facial verification systems. The effects of change in ambient lighting conditions and formation of shadows can be nullified by an effortless pre-processing system. This paper presents an effectual Facial Recognition System which consists of three stages: the illumination insensitive preprocessing method, Feature Extraction and Score Fusion. In the preprocessing stage, the light-sensitive images are converted to light-insensitive images so that uncontrolled lighting will no more be a liability for any kind of identification. In the feature extraction stage, hybrid Fourier classifiers are used to obtain transforms which are projected into subspaces using PCLDA Theory. And the output is passed onto the Score Fusion stage where the discriminating powers of the classifiers are unified by using LLR and knowing the ground truth optimizations. This proposal has passed the Face Recognition Grand Challenge (FRGC) Version-2 Experiment, Extended Yale B and FERET datasets. Keywords:

With the fame of visual sensor on smart phone devices, ( i.e. camera) it becomes a habit for many people to capture photos everyday and everywhere. This led to the rapid developing of more personal images and becomes a nuisance to the users in storing and organizing them, which had not been used before. Lu c k i l y, cloud storage provided a comprehensive solution at the right moment, and it facilitates the synchronization and sharing of images acquired. However, organizing this bulk number of personal images is still a tedious and difficult task. Common needs in photo organization may involve tagging, destroying replicated or same images, and collecting photos into albums. In our proposed system, we target to provide a features similarity images, face detection and recognition, avoid redundancy on smart mobile application which makes use of existing sensors and related technologies to help users to manage replicate or same images more effectively. By sharpening the power of cloud computing for SSIM algorithm, our system significantly reduce the time spent on managing photos in a neat and simple way which reduce user stress and increase user experience.

Attention Deficit Hyperactivity Disorder (ADHD) is a neurological state that involves problems in inattention, hyperactivity and impulsivity that are developed inconsistent with the age. ADHD may occur due to brain disorder namely Brain injury, Brain damage and Brain abnormalities. Brain injury is a more expressive term than “Head Injury” in which Caudate nucleus will be affected. The abnormality of Caudate nucleus is to be found by its size and volume. The grey and white matter of brain also is abnormal due to brain damage. The main aim to detect and diagnose ADHD depends on the parts of the brain. By means of efficient Brain segmentation techniques, it can be easily identified. So, in this paper, to extract the brain parts various brain segmentation techniques are surveyed and discussed. A simple thresholding technique is proposed to extract Gray and white matter as well as “Active contour with region based Techniques” is implemented to extract the Caudate nucleus portion. The experimental results of various images are examined and discussed.

With cloud computing, users can remotely store their data into the cloud and use on-demand high-quality applications. Data outsourcing: users are relieved from the burden of data storage and maintenance When users put their data (of large size) on the cloud, the data integrity protection is challenging enabling public audit for cloud data storage security is important Users can ask an external audit party to check the integrity of their outsourced data. Purpose of developing data security for data possession at un-trusted cloud storage servers we are often limited by the resources at the cloud server as well as at the client. Given that the data sizes are large and are stored at remote servers, accessing the entire file can be expensive in input output costs to the storage server. Also transmitting the file across the network to the client can consume heavy bandwidths. Since growth in storage capacity has far outpaced the growth in data access as well as network bandwidth, accessing and transmitting the entire archive even occasionally greatly limits the scalability of the network resources. Furthermore, the input output to establish the data proof interferes with the on-demand bandwidth of the server used for normal storage and retrieving purpose. The Third Party Auditor is a respective person to manage the remote data in a global manner.

Spectrum has been a very valuable resource in wireless communication systems. The available electromagnetic radio spectrum is getting crowded day by day due to manipulation in wireless devices and applications. Underutilization of Spectrum has become a major source of concern for each network user. The present paper attempts to portray “Spectrum Management Techniques using Cognitive Radios”, where the strength and scope of Cognitive Radio Technology are discussed. It also highlights the efficiency and effectiveness of the system when compared to conventional mode of operations. Further, the present paper also lucidly explains the modus operandus of Cognitive Radio Technology Spectrum Management Techniques namely Spectrum Sensing, Spectrum Decision-Making, Spectrum Sharing and Spectrum Mobility. These functionalities make Cognitive Radio Technology an asset to the network domain and easily solves issues like interference, noise and underutilization. The paper also focusses on describing the Transreceiver and network architecture. On the whole, this paper is an overall description about the Spectrum Management Techniques in Cognitive Radio Technology in brief.

A brain tumour is an abnormal growth of cells that are spontaneously grows in uncontrolled manner. We can divide tumors in according to how exponentially they developed i.e. growth rate, with lower-grade tumors often being begin and higher-grade tumors being malignant. Based on interpolation of low frequency sub band images obtained by discrete wavelet transform (DWT) and the input image, the brain tumor detection is obtained by using Haar wavelet transform. Database image is also decomposed by using Haar wavelet transform by two levels and this database image is compared with the input image by using Mutual information principle. Both input image and database image is decomposed into different sub bands by using DWT. Interpolation of low frequency sub bands as well as input image is done. The proposed technique that first one is data base image and another is the input image in which both are decomposed into several bands by using wavelet transform and their coefficients are stored into matrix form with the help of MATLAB and these coefficients are compared with the help of mutual information principle. Corrected interpolated high frequency sub-bands and interpolated input image are combined by using inverse DWT (IDWT), finally. Hence, we get a brain tumour detected output image.

Nephrolithiasis (kidney stone formation) is one of the major threats faced by the human being. Correct identification of the stone plays an important role in identifying and curing it. on developing an advanced and precise technique for this purpose, the graphical processing software is involved. Graphics processing software is used today in a wide range of inspection applications in medical field. This software eases the way of understanding and performs parallel computing. This work gives a clear vision about the identification of kidney stones using Image processing techniques in LabVIEW. This technique uses the images of the kidney obtained from the ultrasound imaging technique. The main idea is based on the binary conversion using threshold range and the morphological filtration of the ultrasound image. The aforementioned access provides information about the location and dimension of the stones in the kidney. In future, this work could be used for identifying kidney stone in laboratories and in hospitals to identify the presence of kidney stones in a precise and cost effective way.

Extraction of information available in various data base repositories is a tedious task. A composed works of Data Mining (DM) method is accessible for different category of applications for the same work. Many researchers involve analyzing the student’s performance using some relevant DM techniques. This attracting little field is named as Learning Data Mining (LDM). The organizations of the syllabus also increase a very big contact about the growth of the student’s information and their performance. Among the different data mining methods, classification plays a vital role in learning data mining. The primary intention of this research work is to cross the data mining methods which are apply for the improvement of the student’s performance and also identify the most excellent appropriate structure of syllabus for the new environment. This study investigates about the use of ID3 and C4.5 classification algorithms for the improvement of student performance evaluation system. A comparative analysis of various works is carried out in this survey to identify the best classification algorithms for LDM.

In recent days, Data Mining (DM) is an emerging area of computational intelligence that provides new techniques, algorithms and tools for processing large volumes of data. Clustering is the most popular data mining technique today. Clustering used to separate a dataset into groups that finds intra-group similarity and inter-group similarity. Outlier detection (Anomaly) is to find small groups of data objects that are different when compared with rest of data. The outlier detection is an essential part of mining in data stream. Data Stream (DS) used to mine continuous arrival of high speed data Items. It plays an important role in the fields of telecommunication services, E-Commerce, Tracking customer behaviors and Medical analysis. Detecting outliers over data stream is an active research area. This survey presents the overview of fundamental outlier detection approaches and various types of outlier detection methods in data stream.