Journal of Research in Computer Science and Engineering ISSN: 2457-0818 (Online)

Authors: Archana Bhalla, Rohan Kediyal, Sachin Chaudhary, Prateek Agarwal

Abstract: This paper describes research into automated support for air traffic controllers performing tactical air traffic management. It describes the system developed to help alleviate air traffic congestion. The system achieves this by maximizing runway utilization, achieved through arranging landing aircraft into an optimal order, assigning them a landing time, and then monitoring the progress of each individual aircraft in real time, its major components are independent agents, each solving a part of the overall problem. The system's flexible behavior results in part from this co-operative problem solving approach, and in part from the multiple levels of feedback employed between agents in the system and between the system and its environment.

 

Authors: Yadav Dhanashri M., Yadav Gauri B., Zargad Vrushali S., Shinde Varsha N.

Abstract: Many peoples are caring about the health and medical diagnosis problems. However,according to the admin-istrations report, more than 200 thousand people in China and 100 thousand in USA, die each year due to medication errors. More than 42 % medication errors are caused by doctors because experts write the prescription according to their experiences which are quite limited. Many Data mining and recommender technologies provide possible knowledge from diagnosis history details and help doctors to provide suggestion medication correctly to reduce medication error successfully. We suggest and implement a medicine recommender system that applies data mining technologies to the recommendation system. We study the medicine recommendation algorithms of the SVM (Support Vector Machine),BP neural network,ID3 decision tree algorithms based on diagnosis data. For better performance SVM recommendation model is selected. We also recommend a mistake-check method to ensure the diagnosis correctness and service quality. Our system can give medication recommendation with an excellent efficiency, accuracy and scalability.

Authors: Taware Shruti S., Yadav Krushna M., Khatri Pavan D.

Abstract: Nowadays most of the india market is moving towards an online world with an adroit to have an maximum market scope .So we are connecting the business of gift article to online world with the evolved versions of current algorithm of recommendation systems. Ecommerce is an online site where the sale or purchases of goods are ordered electronically. The available ecommerce system has some issues with the recommendation so we are collaborating the multiple algorithms to increase the product sale and convenient in user interaction.

Authors: Vinu Thadevus Williams, Dr, K.S Angel Viji

Abstract: This paper introduces different algorithms that increases the efficiency of the current cloud-based smart-parking system or different methodology to implement the car parking system. The network architecture based on the Internet-of-Things technology has more advancement in future than other technologies. Proposed a system that helps users automatically find a free parking space at the least cost based on new performance metrics to calculate the user parking cost by considering the distance and the total number of free places in each car park that is comparing here in different parking technology. The simulation results in different literature of parking system technology, how to show that the algorithm helps improve the probability of successful parking and minimizes the user waiting time, cost, complexity etc. Successfully implemented the proposed systems comparison in the real world implementation. Here I compared the technologies with cloud-based parking system using IoT to others. And justify which is the better technology. Here we are mainly discussed car parking system based on two technologies, NFC based and cloud-based using IoT technologies.

Authors: Vedant Nigam, Atishay Jain, Damanjit Singh, Sundeep Raj

Abstract: The main idea of “Intelligent Tourist Guide System†is to design a system that will help the user in picking up a destination to visit. The system will ask the user a series of questions and with the help of Artificial Intelligence & Machine Learning, it will provide the user with a list of recommended places to visit. The system would suggest all the possible ways to reach that destination. It would provide the links of various ticket booking websites to book the tickets for the place. Along that, it will also give short descriptions, photos of the place to be visited. It would also estimate the time needed to travel to the destination, and would suggest which route or means of transport must be used. It would be helpful for people who want to visit a city without having much information about it.

Authors: Dalavi Mayuri T., Jadhav Bhagyashri D., Barge Snehal D., Chavan Swapnali J.

Abstract: Cloud computing is the set of services offered through internet that enable the several users to share common resources and store their personal information. Cloud network storage is being used in several highly developed sectors. Security must be provided to outsource data so that client are not apprehensive while uploading their confidential information. The author of this paper addresses the problem by using a framework that integrate several Infrastructure as a service cloud level in order to combine storage space of two or more storage clouds . Author of this paper provide a level of security above these storage system by spreading files to each cloud.

Authors: Vinu Thadevus Williams, Dr, K.S Angel viji

Abstract: Fingerprint-based authentication systems have developed rapidly in the recent years. However, current fingerprint-based biometric systems are vulnerable to spoofing attacks. Moreover, single feature-based static approach does not perform equally over different fingerprint sensors and spoofing materials. In this paper, propose a static software approach. Propose to combine low-level gradient features from speeded-up robust features, pyramid extension of the histograms of oriented gradient and texture features from Gabor wavelet using dynamic score level integration. Extract these features from a single fingerprint image to overcome the issues faced in dynamic software approaches, which require user cooperation and longer computational time.

Authors: Vinu Thadevus Williams, Dr K.S Angel Viji

Abstract: Android malware constantly evolves so as to evade detection. The entire malware population to be non-stationary, contrary to this fact, most of the prior works on machine learning based android malware detection have assumed that the distribution of the observed malware characteristics (i.e., features) does not change over time. The problem of malware population drift and propose a novel online learning based framework to detect malware, named CASANDRA (Context-aware, Adaptive and Scalable Android malware detector). In order to perform accurate detection, a novel graph kernel that facilitates capturing apps security-sensitive behaviors along with their context information from dependence graphs is proposed. Besides being accurate and scalable, CASANDRA has specific advantages: first, being adaptive to the evolution in malware features over time; second, explaining the significant features that led to an apps classification as being malicious or benign.

 

Authors: Banumathi D, Shinu Koshy, Aruna J

Abstract: Green computing is a Go-Green eco-friendly approach that reduces the carbon footprint. Green computing promotes a safe, sound and secure environment for the humanity. Reduction of energy consumption and hence cost savings is becoming a significant concern in the area of computer communications and networking. Green networking refers to energy-aware, energy-efficient, sustainable and environmentally aware communications and networking. This paper focuses on the different practices and concepts adopted in green networks.

Authors: Pranjali v. Gurnule, Pratik Kubal, Akshay Bhosale

Abstract: In this paper, we have sampled data to predict the homicidal Incidences of crime in India. To achieve this, we have collected data as Crime in India, along with Poverty and Unemployment data. After Preliminary analysis, we process the data and fit various Models – Linear and Polynomial. Furthermore, we compare these models and choose a model which explains the resultant data. Consequently, we highlight that Poverty in Rural and Urban areas and Unemployment in Urban Areas is necessary to predict the Homicidal Incidences in India.

Authors: Shilpa Kanoongo, Shubhi Shrivastava

Abstract: Data mining is the best method for finding out the Prediction of data through various sources. It Provide the information about the methodology we are presenting. Through data mining techniques, useful evidence can be collected from such source, which can help fitness seekers to get immediate support for their fitness related problems. This paper presents investigation on small data mining method mainly in mental disease dataset. Three various algorithms of data mining i.e. KNN, SVM, Naïve Bayes are applied on a disease dataset, to analyze the performance of the classifiers. The predictive rate is evaluated using four evaluation parameters i.e. Correctness, exactness, recollection and measuring point. The implementation is performed in Matlab 7.15 tool shows that Naïve Bayes outdoes as compared to remaining classifiers. This gives performance measure in various techniques in a single dataset and also comparison with previous result.

Authors: Gunjan Raghav, Harsh Khatter

Abstract: The main problems for the developed and under-developed countries which they are facing many difficulties or problems in treatment of their medical patients (J.B. Awotunde, O.E. Matiluko, O.W Fatai (2014) Medical Diagnosis System Using Fuzzy Logic Afr J. of Comp & ICTs Vol 7, No. 2 Pp 99- 106.)They have less no of resources in terms of medical expertise in many of the hospitals, most of the countries are spending a lot of their resources to meet this challenge, but still they fail to complete the demands of providing better medical services for their patients and that’s why it’s overcame as a big concern for researchers to get a different from this old method. To make something different research Dept is developing algorithms and technologies, and one name which is Fuzzy Logic came as a relief for them to ensure accuracy and precision in the field of medicine and it is also a branch of Artificial Intelligence.

Authors: Andhe Dharani, Vijayalakshmi M.N, Manjuprasad B

Abstract: The recent development in the Information technology and the increase in the advanced digital application has contributed majorly for vast data generation. This increase in data rose with the problem for storing and retrieving it, causing the need for efficient information and storage management. This paper focused on the recent trends in Storage area network contributing towards Information storage and management system. The importance of Storage area network in recent industry development is discussed in motivation students to contribute in this domain. A case study has been discussed with respect to the application in this same domain.

Authors: Shubham Jain, Sunira Jain

Abstract: In this paper, we have introduced an individual human computer interface system using eye motion. 

The human-computer interface uses keyboard and mouse as an input device. This study presents a hands-free interface between human and computer . This new technology is meant to replace the traditional computer screen displaying devices for the use of disabled and handicapped. The paper offers a unique approach to regulate the computer mouse cursor movement with the help of human eyes. It commands mouse-moving by automatically changing the position where eyesight focuses on and affects mouse-click by affecting blinking action.

Authors: Parneet Kaur, Anil Kumar Verma, Rajiv Kumar

Abstract: In today’s market, companies in the financial services have a common requirement to handle large amount of information with a high level of security and accuracy and provide on demand services. Innovative technology has been leveraged to endorse progressively complicated network of worldwide financial transactions which is managed by the financial services industry. Service Oriented Architecture (SOA) is becoming a popular access for integrating and designing enterprise applications. SOA enforce business services to deliver well defined services using a set of loosely couple services. Web services intended to be independent building blocks of Service Oriented Architecture. Web services are self contained. It gives a better adjustment to IT with business insight, practical and effective reuse of services, lower cost of development and interoperability.  SOA has it some limitations and internal issues.. In this paper, principles of SOA, benefits, limitations and challenges of SOA are discussed. We develop Currency exchange application based on Simple Object Access Protocol (SOAP).

Authors: Sanjay, Prajjwal Mishra, Pooja Tripathi

Abstract: It is a very simple “Come, take and go†cycle. Users will come and draw the flowchart and with respective to the flowchart a code will be generated at the backend and then user can easily save or download the generated code for future references. The user interface should be simple and smooth so user can easily create the flowchart and can get the respective code as per requirements. Our platform will provide options to user like they can directly export their code to Ms Office applications or they can download or save the code for future use and user can also contact the developers if user finds any error in the code. User will find ease to draw flowcharts through drag and drop options.

Author: Rummana Firdaus

Abstract: A generic framework is provided that, with the help of a preprocessing phase that is independent of the inputs of the users, allows an arbitrary number of users to securely outsource a computation to two non-colluding external servers. The approach is shown to be provably secure in an adversarial model where one of the servers may arbitrarily deviate from the protocol specification, as well as employ an arbitrary number of dummy users. These techniques are used to implement a secure recommender system based on collaborative filtering that becomes more secure, and significantly more efficient than previously known implementations of such systems, when the preprocessing efforts are excluded. Different alternatives are suggested for preprocessing, and discuss their merits and demerits.

Authors: Kavyashree E.D, Kavya P

Abstract: Recent evolution in computer technology is Cloud computing. Cloud computing can be accessed anywhere in the world. Cloud computing also known as cloud, technically cloud refers to internet and high speed internet is must for cloud users. It has enormous prospect such as eliminating infrastructure of hardware and software results in reducing complexities in IT and provides services to user with a new choice, lower cost, and also offers digital services irrespective to large and small scale organization. The threat in cloud is security this is beneficial to attackers who gain information on unsecured network. This paper outlines the importance of cloud delivery models, deployment models, and security issues.

Authors: Palak Agarwal, Vikas Srivastava

Abstract: Data Mining techniques have moved to a new level due to exponential growth of data and users query types in knowledge management systems. As knowledge is an essential and volatile asset and web is the only available hub from where it can be retrieved, most of the search engine techniques focuses on keyword searching and simulating existing results. To achieve more prominent results and relevant URLs for the users query, the problems of crawlers (polysemy and synonymy) must be removed. In this paper, we have focused on removing these existing problems by introducing the concept of adaptive web searching based on structural ontology. Contexts are related with each other on the basis of properties and meta-keywords. Further, simulation of architecture is also shown which provides promising results.

Authors: Anna Dominic, Jubna T, Neenu Baby, Surekha Mariam Varghese

Abstract: Long running transactions always take long time to finish, which needs the resources - often the database - to be locked for a long time. This would bring down the performance of the transaction processing system. The normal solution is compensating transaction, which creates a relative transaction with the opposite effect. The sub-transactions are allowed to commit independently without waiting for other subtransactions. If the transaction fails, the corresponding compensating transaction will be executed so that the effect brought by the original transaction can be cancelled. However, compensating transaction model has several drawbacks. This paper proposes a novel pipeline based processing model of long transaction mainly aimed at the serially executed long transaction whose subtransactions cannot be executed concurrently since it require the result of other subtransactions. This model parallelizes the transaction processing resulting in better system performance. Our experiments show that the pipeline based processing model of serial long transaction has notable improvement when executing the long transaction.

Authors: Kavyashree E.D, Kavya P

Abstract: Recent evolution in computer technology is Cloud computing. Cloud computing can be reached anytime, anywhere in the world. Cloud computing also known as cloud, technically cloud refers to internet and high speed internet is must for cloud users. It has enormous prospect such as eliminating infrastructure of hardware and software results in reducing complexities in IT and provides services to user with a new choice, lower cost, and also offers digital services irrespective to large and small scale organization. The threat in cloud is security this is beneficial to attackers who gain information on unsecured network. This paper outlines the importance of cloud delivery models, deployment models, and security issues.

Author:Prof. K. B. Vayadande

Abstract:Faults in software document can really affect the entire behavior of the software. Many types of faults exist in the software code document after its development. Software becomes less reliable if these faults are not removed from it.  A proper knowledge of the various types of software errors and a good classification of these errors are required before implementing any techniques related to their correction or detection. Manual inspection of the code document is also possible but disadvantage of this technique is, it requires too much time and manpower. So employing large teams for inspection of code is very costly. Thus, correction and automatic detection of these software errors, with the lack of automated tools, are vital to easing the maintenance of software.  Most of the techniques available today only focus on the detection of fault, so in order to remove these faults in significant and reliable way is a challenging task. So many techniques are available for detection and corrections. This paper discusses these techniques.

AUTHORS: Aswathy K.R , Jisha A K , Nadim Haroon 

ABSTRACT: More than 200 different currencies and their denominations are used all over the world. The new technique of currency recognition intends to investigate,  explore and derive the noticeable as well as invisible marks on paper currency. A currency recognition and conversion system are executed to decrease human effort and labor by automatically identifying the monetary value of the currency and convert the currency into other currencies without human help. The interface of software which we are introducing here can be utilized for various currencies. Several times, currency notes are damaged or blurred, and many of them have complicated designs to enhance the security.

Author: Nidhi Shri G

Abstract: Cloud Computing is a platform that provides various computing resources and storage for execution of any exhaustive or complicated task. In this paper, we discuss the concept of load balancing in a cloud computing framework. Load balancing in the cloud computing environment divides the workload among multiple nodes to avoid overloading of a single node. Proper load balancing algorithm improves efficiency and user satisfaction. The load balance algorithm introduced in this paper is based on the cloud partitioning technique. The algorithm makes use of game theory.