International Journal of Computer Science and Technology
IJCST 9.3 (July-Sept 2018)

S.No. Research Topic Paper ID Download

Detecting Malicious Webpages using Virustotal API



Cell phone specific webpages differ significantly from their desktop equivalent in content, layout and functionality. Consequently, existing techniques to find malicious websites are not likely to work for such webpages. In this work we use a Virustotal API. Virustotal API is a mechanism that identifies malicious webpages. Virustotal makes this determination based on dynamic features. The Virustotal API lets the user scan the URL’s and search through the dataset to determine malicious web pages. We tentatively exhibit the requirement for mobile specific procedures and after that recognize a scope of new successful highlights that exceptionally correspond with mobile malicious sites. Moreover, we discover, define, report quantity of webpages missed by Google safe browsing, and detected by our application.
Full Paper


Facet Browsing in E-Commerce for Searching best Faceted Product form Product Search Engine

Fizza Taimoor Khan


Faceted browsing is analytic search model where facets benefit in the interactive navigation of search results. Facets are attributes that have been assigned to describe product being look into. A faceted classification is a collection of facets provided by the interface and is often organized as sets, hierarchies, or graphs. Because of the large amount of product count, web shops usually make a static information to determine which facet should be displayed yet the process is still difficult to theoretically handle the model in a manner that supports the development of faceted search. We propose an approach for faceted browsing and demonstrate how the targeted faceted product can be computed in minimal amount of time period.
Full Paper


Security Issues in MANET: A Review of Black Hole Attacks in MNET

Anshita Dharmawat, Dr. Sanjay Agal


Security in Mobile Ad-Hoc Network (MANET) is the most important concern for the basic functionality of network. Availability of network services, confidentiality and integrity of the data can be achieved by assuring that security issues have been met. MANET often suffer from security attacks because of its features like open medium, changing its topology dynamically, lack of central monitoring and management, cooperative algorithms and no clear defense mechanism. These factors have changed the battle field situation for the MANET against the security threats.
Full Paper


Developing Augmented Reality Application for Booths in Event using Natural Feature Tracking as a Marker

Indrawan, Desi Ramayanti


This paper presents an approach of using Information Technology as a tools that could attract larger audience for booths in certain event. By using Augmented Reality, this paper try to ease the problem that businesses faced on event, that is to give information to visitor about their products or company profile. In this paper, we use NFT (Natural Feature Tracking) as main marker. It’s easier for layman to use AR if the marker is NFT. Even though on testing state, we found out that using NFT have a problem in distance from camera to marker. If the camera too far from the marker, the virtual data won’t show up on the screen. On testing phase, if the marker on the screen of laptop or computer, we have at maximum 2 meters until the virtual data won’t show up on our phone screen, while if the marker was printed on the A4 paper, we could scanned the marker at maximum 3, 5 meters. The result of this paper is application that easy to use for user and businesses could create their own content to their own application.
Full Paper


Facial Expression Classification using Distance Measures for Emotion Detection

Ritika Sharma, Ritika Mehra


Facial Expression Recognition (FER) has essential real world applications. Its applications include, but are not limited to, Human Computer Interaction (HCI), psychology and telecommunications. It remains a challenging problem and active research topic in computer vision, and many novel methods have been proposed to tackle the automatic facial expression recognition problem. The main challenge here is to perform decoupling of the rigid facial changes due to the head-pose and non-rigid facial changes due to the expression, as they are non-linearly coupled in images. Another challenge is how to effectively exploit the information from multiple views (or different facial features) in order to facilitate the expression classification. Thus, accounting for the fact that each view of a facial expression is just a different manifestation of the same underlying facial expression related content is expected to result in more effective classifiers for the target task. The facial expression image sequence contains not only image appearance information in the spatial domain, but also evolution details in the temporal domain. The image appearance information together with the expression evolution information can further enhance recognition performance. Although the dynamic information provided is useful, there are challenges regarding how to capture this information reliably and robustly. For instance, a facial expression sequence normally constitutes of one or more onset, apex and offset phases. In order to capture temporal information and make temporal information of training and query sequences comparable, correspondences between different temporal phases need to be established. As facial actions over time are different across subjects, it remains an open issue how a common temporal feature for each expression among the population can be effectively encoded while suppressing subject-specific facial shape variations. In this work, a new dynamic facial expression process is created using Efficient Distance Measures for Emotion detection.
Full Paper


Web GIS Development using Open Source Leaflet and Geoserver Toolkit

Taranjot Singh Bhatia, Harpinder Singh, P.K Litoria, Brijendra Pateriya


Popularity of location based web and mobile applications is increasing day by day. The visualization of locations is bit complicated than tabular data. Specialized software are required to build a web GIS (Geographic Information Systems) application providing easy access to geo-spatial data to a large number of people. This paper reviews a simple and easy to use methodology to create a web GIS application using open source tools. Leaflet, Geoserver and PostgreSQL have been used to create the application. Leaflet is used to create the GUI (Graphical user interface), Geoserver acts as a middleware and PostgreSQL is used as a backend data store. The web GIS has basic functionalities like pan, zoom, home, info window, measure, legend button, geo-location, search bar, layer selection, mini map, attribution, mouse position etc.
Full Paper


Survey and Analysis of Current Methods of Image Encryption Algorithm based on DNA Sequencing

Priyanka, Deepika Arora


The normal software system reliability estimation ways typically believe assumptions like statistical distributions that are typically unrealistic. The power to predict the amount of faults throughout development part and a correct testing method helps in specifying timely unharnessed of software system and economical management of project resources. The normal approach of fault prediction using software system reliability growth models needs an outsized variety of failures which could not be on the market at the start of the testing. models when compared for results, revealed that the Goel-Okumoto model performed better than Yamada Delayed S-Shaped model for estimation of failures for given data.
Full Paper


Enhanced Integrity Preserving Homomorphic Scheme for Cloud Using Diffie Hellman

Tamanna Gupta, Ritika Mehra


Distributed computing, the new term for the since quite a while ago imagined vision of processing as an utility empowers helpful, onrequest organize access to a unified pool of configurable figuring assets (e.g., systems, applications, and administrations) that can be quickly sent with incredible effectiveness and insignificant administration overhead. The stunning preferences of Cloud Computing include: on-request self-benefit, pervasive system get to, area autonomous asset pooling, quick asset versatility, utilization based valuing, transference of hazard, and so forth… Thus, Cloud Computing could without much of a stretch advantage its clients in maintaining a strategic distance from huge capital costs in the arrangement and administration of both programming and equipment. Without a doubt, Cloud Computing brings remarkable outlook changing and benefits ever of. As Cloud Computing winds up common, more touchy data are being incorporated into the cloud, for example, messages, individual well being records, private recordings and photographs, organization back information, government archives, and so forth. By putting away their information into the cloud, the information proprietors can be eased from the weight of information stockpiling and support in order to appreciate the on-request excellent information stockpiling administration. Be that as it may, the way that information proprietors and cloud server are not in the same trusted area may put the outsourced information in danger, as the cloud server may never again be completely confided in such a cloud domain because of various reasons: the cloud server may spill information data to unapproved elements or be hacked. Information security and protection are the basic issues for remote information stockpiling. A protected client upheld information get to control component must be given before cloud clients have the freedom to outsource touchy information to the cloud for capacity. With the development of sharing secret corporate information on cloud servers, it is basic to receive a proficient encryption framework with a fine-grained get to control to scramble outsourced information. Quality based encryption is an open key based encryption that empowers get to control over scrambled information utilizing access arrangements and credited properties. In this work, we are going to examination completely Homomorphic plans for encryption and honesty check utilizing MD5 Algorithm.
Full Paper


Designing and Implementation of a Flexible Institution System According to New Standards to Ensure the Quality of Educational Process in Higher Education Institutions

Dr. Mozamel M. Saeed


This paper aims to benefit from advanced Information and Communication Technology (ICT) to improve teaching and learning process. This will be done through the design of a flexible system to measure the performance and quality of educational institutions according to new standards to ensure quality in the educational process, based on the components of the educational process, represented in members of the academic staff, the level of students, academic programs, university administration and buildings & utilities, in order to cope with the difficulties encountering the educational process in its current situation, which acts as an obstacle for ensuring the quality of its output.
The paper concluded (through the designed model) to provide a flexible standard that commensurate with the various educational environments, through which measurement of standard implementation range, quality standards and practices in the institution, in addition to points of weakness that necessitate improvement process to guarantee quality of its output by what achieves the entire targets of the institution.
Full Paper


Artificial Intelligence and its Application as an Integrated Approach

Sandeep Kulkarni, Vipan Kumari


As technology, and, importantly, our understanding of how our minds work, has progressed, our concept of what constitutes AI has changed. Rather than increasingly complex calculations, work in the field of AI concentrated on mimicking human decision making processes and carrying out tasks in ever more human ways.
AI devices, which are designed to act very intelligently are often categorized into one of two fundamental groups, applied or general. Applied AI systems can intelligently trade stocks and shares, or even stretch as far as maneuvering an autonomous vehicle. These type of AI systems are generally widespread.
Neural networks have been instrumental in teaching machines to understand world the same way we do. They accomplish this objective, while retaining innate advantages, such as speed, accuracy.
Full Paper