Computerscience and Engineering

Intrusion Detection Systems (IDS) are playing a critical role in present day data security systems, wherein there are so many intrusion detection techniques contributing to the purpose partially or fully. In particular, Ant Colony Optimization (ACO) based intrusion detection methods are in action for effective intrusion detection. In this paper, an enhanced heuristic algorithm has been proposed with sensitivity and specificity factors for increasing the success rate in the intrusion detection. Data Patterns have been extracted from the network data effectively using the proposed heuristic algorithm. The Knowledge discovery from databases (KDD) dataset is used as input and the proposed approach increased the percentage of intrusion detection as compared with the conventional methods.

Background /Objectives: In today's world, finding a feasible solution for combinatorial problems becoming a crucial task. The main objective of this paper is to analyze and comprehend different nature based algorithms enabling to find optimal solution. Methods/statistical analysis: Bacterial Foraging Algorithm (BFOA), firefly algorithm, Ant Colony Optimization (ACO), bee colony optimization, cuckoo optimization etc. Which have been used in power load balancing, cost estimating, optimal routing, color segmentation were discussed. This paper also highlights the constraints and convergence properties of each algorithm to solve certain problems encountered in various fields of application. Findings: Ant colony algorithms were successful in finding solutions within 1% of known optimal solutions. Optimal solution was found in BFOA by adjusting chemo taxis step size. Also, this paper analyzes results of various research works done in numerous fields using the swarm intelligence techniques.

This paper presents a novel data mining approach for fault diagnosis of turbine-generator units. The proposed rough set theory based approach generates the diagnosis rules from inconsistent and redundant information using genetic algorithm and process of rule generalization. In this paper, a fault diagnosis decision table is obtained from discretization of continuous symptom attributes in the data set. Then, the proposed genetic algorithm is used to achieve the minimal reduct from the discretized symptom attributes. In addition, a set of maximal generalized decision rules is obtained from the proposed rule generalization process.

The Open Source Cluster Application Resources (OSCAR) is a fully integrated cluster software stack designed for building, and maintaining a Linux Beowulf cluster. As OSCAR has become a popular tool for building the cost effective HPC cluster, undoubtedly, High Availability (HA) will equally be an important aspect that enables HPC systems, as clearly an unavailable cluster equals no performance. To embrace both HA and HPC features, we created the HA-OSCAR solution which eliminates the numerous single-point-of-failure in HPC systems and alleviates unplanned downtime through sophisticated self-healing mechanisms and component redundancy. In this paper, we report our newly introduced ideas and experiments on hardware level failure detection and prediction based on the Service Availability Forum's Hardware Platform Interface (OpenHPI). Service monitoring and Policy-based head node recovery is also discussed in detail. Furthermore, we investigate a Network File system issue during server failover and resolution via the High Reliable Network File System (HR-NFS), without the need for an expensive hardware-based shared storage solution. Furthermore, our solution enables a graceful recovery with a deliberate job checkpointing and migration upon head node failure prediction. Finally, we introduce our web-based management module that provides a customizable service monitoring, recovery/failover management mechanism with an effective cluster monitoring ability.

The demand for an efficient fault tolerance system has led to the development of complex monitoring infrastructure, which in turn has created an overwhelming task of data and event management. The increasing level of details at the hardware and software layer clearly affects the scalability and performance of monitoring and management tools. In this paper, we propose a problem notification framework that directly addresses the issue of monitor scalability. We first present the design and implementation of our step-by-step approach to analyzing, filtering, and classifying the plethora of node statistics. Then, we present experimental results to show that our approach only needs minimal system resource and thus has low overhead. Finally, we introduce our web-based cluster management system that provides hardware controls at both cluster and nodal levels.

The concept of steganography is used in the paper to transmit the data secretly and safely from one user toanother as it hides the data behind image. In this sender encrypt data using AES algorithm, hides encrypteddata in image using LSB technique and the system auto generate the hide key. Sender sends the file with the helpof existing mailing system. Receiver can perform action based on key like if he is having only data hiding thenhe can only get the image in original form and if he have data hiding and data decryption key then he will beable to get the original data, it also provides protection for the keys. All these are done with proper loginprocess. The system generates imitative data if the user is not authenticated in the process of login. In such away only the authorized user, who was supposed to get the keys, is able to get the original data.

Purpose To validate the predictive power for determining breast cancer risk of an automated breast density measurement system with full-fi eld digital mammography (FFDM). Materials and methods Two hundred cancers and 200 controls were imaged with FFDM. Density was measured separately on MLO and CC images using an integral automated volumetric breast density measurement system (Hologic, Quantra). For each cancer, the contralateral mammogram was used. Each cancer was matched to a control case by date of birth, age at examination and laterality of mammogram used for density determination. Breast density (percentage of fi broglandular tissue) was analyzed by Quantra. Data were analyzed by conditional logistic regression to determine the eff ect on breast cancer risk. Results The percentage of breast density ranged from 6% to 63%. Density declined signifi cantly with age (P <0.001). Overall, there was no signifi cant association of density with risk of breast cancer (P = 0.4). There was a suggestive increase in risk with dense volume higher than 35% (OR = 1.80, 95% CI = 0.96 to 3.39, P = 0.07). There was signifi cant heterogeneity by age in the eff ect of density on risk (P = 0.04). In women aged <50, density was signifi cantly associated with increased risk (P = 0.02), with odds ratios of 6.06, 3.98 and 10.59 for density volumes of 15 to 24%, 25 to 34% and ≥35% respectively, relative to those with <15%. In women aged ≥50 years there was no association of density with risk (P = 0.5). Conclusions Quantra automated volumetric breast density measurement is strongly associated with breast cancer risk in women aged under 50, but not in women aged ≥50 years or over.

A medicinal services framework incredibly upgrades the patient social insurance records which are putaway in the cloud server. Accessible encryption conspire is utilized which improves the inquiry system.Conjunctive watchword look encourages the approved clients to get to the records by giving numerouscatchphrases, so it ends up plainly troublesome for the aggressors to figure the watchword and recover therecords. Re-encryption conspire gives greater security to the records by re-scrambling the encoded list beforetransferring them into cloud server. Since the patient&#39;s social insurance records comprise of touchy data, itmight be badly designed for the patient when his records are gotten to by everybody. To beat the issue in ourproposed work we present the idea called K-Anonymity which is utilized so it gives just an incomplete accessto the approved clients by utilizing two techniques concealment and speculation. This has been exceptionallyproductive in the standard model.

The materialization of mobile equipment with fast Internet connectivity and geo-tagged capabilities has led to a revolution in personalized position-based services where clients are enabled to admittance information about points of interest that are pertinent to their interests and are also close to their geo tagged coordinates. The important type of queries that absorb location attributes is symbolized by nearest-neighbor queries, where a client wants to retrieve the k- Point of interests that are nearest to the user&#39;s current location. Entities specialized in various areas of interest and gather large amounts of geo-tagged data that appeal to subscribed users. In this paper we proposes development and implementation of frame work to provide more complex protected evaluation method on cipher texts, like skyline queries and security protection guarantees against the client, to prevent it from learning anything other than the received k query results.

Cloud applications that offer data management services are emerging. Such clouds support caching of data in order toprovide quality query services. The users can query the cloud data, paying the price for the infrastructure they use. Cloud management necessitates an economy that manages the service of multiple users in an efficient, but also, resource-economic way that allows for cloud profit. Naturally, the maximization of cloud profit given some guarantees for user satisfaction presumes an appropriatepricedemand model that enables optimal pricing of query services. The model should be plausible in that it reflects thecorrelation of cache structures involved in the queries. Optimal pricing is achieved based on a dynamic pricing scheme that adapts to time changes. This paper proposes a novel price-demand model designed for a cloud cache and a dynamic pricing scheme for queries executed in the cloud cache. The pricing solution employs a novel method that estimates the correlations of...

Abstract: A novel a novel price demand model designed for a cloud cache and a dynamic pricing scheme for queries executed in the cloud cache is presented in this paper. It also defined an appropriate price-demand model and we formulate the optimal pricing problem. This allows: on onehand, long term profit maximization, and, on the other, dynamic calibration to the actual behavior of the cloud application, while the optimization process is in progress. This also discussed the qualitative aspects of the solution and a variation of the problem that allows the consideration of user satisfaction together with profit maximization. Theviability of the pricing solution is ensured with the proposal of a method that estimates the correlations of the cache services in an time efficient manner.

Abstract: An approach for resilient multipath routing with independent directed acyclic graphs is presented in this paper and developed polynomial time algorithms to construct node independent and link independent DAGs using all possible edges in the network. In this multiple pairs of colored trees approaches to prove the validity of thealgorithm. The IDAGs approach performs significantly better than the independent trees approach in terms of increasing no. of paths offered, reducing the probability of a two-link failure disconnecting a node from the destination and average link load. The trees based on the shortest paths on the IDAGs have better performance than that of the ITrees approach since the average shortest path length on the IDAGs is shorter than the average path length on the ITrees. Multiple pairs of colored trees approach is better in terms of the product of the no. of critical links and average link load compared to the ITrees and IDAGs approaches.

Abstract:- Now a days XML is becoming a standard in data representation and data exchanging. Due to its simplicity and lightweight most of the real time applications adopted XML as a DB to store the frequently updating enterprise data, which have complex schema and design with thousands of xml elements. To retrieve the data from XML databases effectively, most previous information retrieval(IR) approaches used XQuery and XSEarch, which are schema and design based mechanisms and allows only the DB experts for querying data. Lack of knowledge on the database schema and design can be a significant obstacle for common users who want to access the information in an XML database.Inspired by the great success of information retrieval (IR) style keyword search on the web, keyword search on XML has emerged recently, which is schema independent approach and allows all the user to query XML databases by using keyword combination without the knowledge of complex query languages and the database...

Abstract: An approach for resilient multipath routing with independent directed acyclic graphs is presented in this paper and developed polynomial time algorithms to construct node independent and link independent DAGs using all possible edges in the network. In this multiple pairs of colored trees approaches to prove the validity of the algorithm. The IDAGs approach performs significantly better than the independent trees approach in terms of increasing no. of paths offered, reducing the probability of a two-link failure disconnecting a node from the destination and average link load. The trees based on the shortest paths on the IDAGs have better performance than that of the ITrees approach since the average shortest path length on the IDAGs is shorter than the average path length on the ITrees. Multiple pairs of colored trees approach is better in terms of the product of the no. of critical links and average link load compared to the ITrees and IDAGs approaches.Keywords: Multipath...

An increasing number of databases have become web accessible through HTML form-based search interfaces. The data units returned from the underlying database are usually encoded into the result pages dynamically for human browsing. For the encoded data units to be machine process able, which is essential for many applications such as deep web data collection and Internet comparison shopping, they need to be extracted out and assigned meaningful labels. In this paper, we present an automatic annotation approach that first aligns the data units on a result page into different groups such that the data in the same group have the same semantic. Then, for each group we annotate it fromdifferent aspects and aggregate the different annotations to predict a final annotation label for it. An annotation wrapper for the search site is automatically constructed and can be used to annotate new result pages from the same web database. Our experiments indicate that the proposed approach is highly e...

- Data mining manages the way toward finding data from data. With the wide accessibility of data there are different applications and requirements for data mining. Data can be of any sort specifically message, pictures, recordings and some more. This work concentrates on characterization of content data utilizing a semi-regulated grouping calculation. The principle issue in any data mining assignment is the treatment of gigantic data. Immense dimensionality does not demonstrate more data rather itmight incorporate irregularities and commotions. To make the data predictable powerful pre-preparing strategies are finished. Notwithstanding this element choice system chooses valuable highlights and evacuate superfluous ones along these lines making the data significant for mining. A semi managed bunching calculation TESC was utilized as a part of this investigation. It was then changed by actualizing a component determination strategy, record recurrence thresholding by which the tremendo...

Abstract— A medicinal services framework incredibly upgrades the patient social insurance records which are put away in the cloud server. Accessible encryption conspire is utilized which improves the inquiry system. Conjunctive watchword look encourages the approved clients to get to the records by giving numerous catchphrases, so it ends up plainly troublesome for the aggressors to figure the watchword and recover the records. Re-encryption conspire gives greater security to the records by rescramblingthe encoded list before transferring them into cloud server. Since the patient&#39;s social insurance records comprise oftouchy data, it might be badly designed for the patient when his records are gotten to by everybody. To beat the issue in our proposed work we present the idea called K-Anonymity which is utilized so it gives just an incomplete access to the approved clients by utilizing two techniques concealment and speculation. This has been exceptionally productive in the standa...

Abstract: Presently , Smartphones are generally utilized asa part of every day life. Individuals utilize them to storeexceedingly imperative information including email, secretkey, money related records points of interest like chargecard number, ledger number and therapeutic records andso forth. With the ascent in advanced mobile phones andtheir inherent sensors and also web applications, anexpanding measure of private information is by and largequietly got to. Android framework gives office to storeandroid application information and other data on googlecloud and synchronize this information with ourapplication while utilizing application. Yet, thistransmission in broad daylight correspondence frameworkisn&#39;t secure a result of block attempt and uncalled forcontrol. These makes android framework as an essentialstage for security protecting application. Along these lines,elective answer for this issue is to served multilayersecurity to information. In this paper, we give multilev...

With the surge in the development of various applications in the field of Computer Vision and Digital Image Processing, a significant amount of medical pictures are being produced. Thus, the patient-specific scan pictures represent the boundless volume of data that requires careful organization and supervision to assist clinical decision support systems. Now that retrieval, classification, segmentation, and other procedures have been completed, these devices assist doctors to uncover serious illnesses including skin conditions, tumors, and cancer. This imaging largely depends on characteristics to detect the afflicted region and perform the diagnosis visually. The authors of this paper present an overview of numerous feature extraction approaches used to extract features from medical images obtained via different modalities, but only used a handful of these techniques for this job and provided the findings.