Tanupriya Choudhury

An efficient automated design to generate UML diagram from Natural Language Specifications

The foremost problem that arises in the Software Development Cycle is during the Requirements specification and analysis. Errors that are encountered during the first phase of the cycle migrate to other phases too which in turn results in the most costly process than the original specified process. The reason is that the specifications of software requirements are termed in the Nature Language Format. One can easily transform the requirements specified into computer model using UML. To minimize the errors that arise in the existing system, we have proposed a new technique that enhances the generation of UML models through Natural Language requirements, which can easily provide automatic assistance to the developers. The main aim of our paper is to focus on the production of Activity Diagram and Sequence Diagram through Natural Language Specifications. Standard POS tagger and parser analyze the input i.e., requirements in English language given by the users and extract phrases, activities, etc. from the text specifies. The technique is beneficial as it reduces the gap between informal natural language and the formal modeling language. The input is the requirements laid down by the users in English language. Some stages like pre-processing, part of speech (POs), tagging, parsing, phrase identification and designing of UML diagrams occur along with the input. The application and its framework is developed in Java and it is tested on by implementing on a few technical documents.

Comparison between significance of usability and security in HCI

Technology pertaining to Human Computer Interaction has seen vast leaps of advancements in recent years. And so, have the hardware using those technologies. But Despite all of these advancements, users are often left disappointed. The major cause of this disappointment is mostly either of lack of usability or lack of security or sometimes both of them. This paper discusses the problem of balance between usability and security as these two are the most significant challenges in the area of HCISec. Significance of both security and usability is discussed in this paper in order to find the more dominating aspect in the design of human computer interaction systems. Also, a case study on usability and security is presented on the iOS and Android operating systems to get a clear idea of the significance of both the factors. In the end, a conclusion is reached highlighting the importance of both usability and security.

Intelligent Classification of Lung & Oral Cancer through Diverse Data Mining Algorithms

Nowadays, the environment of healthcare is quiet richin information, but knowledge wise the data is very poor. There isan availability of ample amount of data within the systems ofhealthcare. Nevertheless, there is a absence of genuine tools ofinvestigation in order to determine hidden associations in data. The main motive of this investigation is towards the speciallydesigned GUI based Interface in order to input the patientsrecord. Thus anticipate whether or not the patient is sufferingfrom the lung and oral cancer by the use of the rule basedclassifier. The forecast is done from the process of mining therecent informative data of the patient and data repository or thereference value for every attributes. The reference values aretaken from specialist doctors, and internet repository. In thisresearch a comparison of Multilayer perceptron and simplelogistic algorithm have been carried out so as to analyse anddetect the lung and oral cancer in an intelligent way.

Fog computing: Common security issues and proposed countermeasures

Fog computing is one of the most important paradigms used in modern world as an extension to cloud computing. Like Cloud Computing, it provides data storage, manipulation and computation of data, but to the edge of the network, i.e. to the user end. This research paper deals with the threat to security issues, especially with location privacy and data confidentiality. The way service providers as well as government can access users data is covered. Furthermore the misconceptions about the rights of users are discussed. Finally the concept of decoy technique with some modification for location and data privacy is also covered.

Blur image detection using Laplacian operator and Open-CV

With the increased usage of digital cameras and picture clicking devices, the number of digital images increases rapidly, which in return demand for image quality assessment in terms of blur. Based on the edge type and sharpness analysis using Laplacian operator, an effective representation of blur image detection scheme is proposed in this paper, which can determine that whether the image is blurred or not, and what is the extent of blur through Variance of Laplacian. In this project a simple, reliable and fast algorithm for image noise estimation is presented. Images taken for the testing is assumed to be corrupted by additive zero mean Gaussian noise. To exclude structures or details from contributive to the noise variance estimation, an easy edge detection algorithm inculcating first-order gradients is applied first. Then a Laplacian operator followed by an averaging over the whole image will provide very accurate noise variance estimation. There is only one parameter which is self-determined and adaptive to the image contents. Simulation results show that the proposed algorithm performs well for different types of images over a large range of noise variances. Performance comparisons against alternative approaches are also provided. Results obtain through screenshots of the experiments demonstrate the effectiveness of the proposed scheme.

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.

Movie Recommendation System: Hybrid Information Filtering System

The movie recommendation system is a hybrid filtering system that performs both collaborative and content-based filtering of data to provide recommendations to users regarding movies. The system conforms to a different approach where it seeks the similarity of users among others clustered around the various genres and utilizes his preference of movies based on their content in terms of genres as the deciding factor of the recommendation of the movies to them. The system is based on the belief that a user rates movies in a similar fashion to other users that harbor the same state as the current user and is also affected by the other activities (in terms of rating) he performs with other movies. It follows the hypothesis that a user can be accurately recommended media on the basis others interests (collaborative filtering) and the movies themselves (content-based filtering).

Smart vehicle identification system using OCR

In recent times the identification and parking of vehicle has become a difficult task because of the increase in the number of automobiles. In the existing surveillance system the maintenance of incoming and outgoing vehicles is difficult. To resolve this problem a number of techniques can be used out of which Optical Character Recognition (OCR) is most the suitable technology. OCR has been the subject of research for more than decades. OCR is defined as the conversion of scanned images into machine encoded text. The proposed system is implementing the OCR technology to park the vehicles in smart way and keep the track of the vehicles which are entering and leaving. The system will capture the image of number plate of the vehicle using the OCR process and will instantly update the database.

A performance based comparison of various symmetric cryptographic algorithms in run-time scenario

Today, with a wide use of internet all across the globe where it has become a significant tool of commerce, security and protection of information becomes a vital issue to deal with. Cryptography is a historical art and in basic terms it refers to the science of writing in secret and covert code. The first use of it dates back to centuries ago. Without any surprise, with the widespread development of computer communications the new forms of cryptography have emerged. It has always been used to safeguard and protect the military and diplomatic communication since its very inception. The primary objective of this paper is to define and briefly explain the fundamental terms and concepts regarding the cryptographic methods and also to assess the various cryptographic schemes that are in use today. It is imperative to mention that this paper is chiefly focussed on the concepts, schemes and terminologies and does not comprise the thesis of the entire field.

The looming visible light communication Li-Fi: An edge over Wi-Fi

In todays fast moving world, Li-Fi is emerging as one of the best technology of the Era. Its promising features like security and speed has made this technology a boom over Wi-Fi. Both Li-Fi and Wi-Fi works on Electromagnetic spectrum for the transfer of data. But Li-Fi uses visible light region whereas Wi-Fi uses Radio Waves for communication. Many Researchers have been currently working on this technology and has come with the speed of 224Gbps. Such innovations have bought greener as well as more secure and less expensive fate of communication. Many researchers are working to introduce the micron size LED bulbs to use them with Li-Fi. In this paper, an attempt is made to prove how the latest technology Li-Fi is better than Wi-Fi also an attempt is made to show how Li-Fi is very much similar to Wi-Fi and how light emitting diode are used to transmit the data which provides us more speed and flexibility then the Wi-Fi technology.