23 research outputs found
Keyword Extraction Using Particle Swarm Optimization
No full textAbstractWithout formal structure data are those that have no prearranged form or structure and are full of textual data. Typical unstructured systems include emails, reports, telephone or messaging conversations, etc. The main goal of this work is to extract the keywords from a conversation using particle swarm optimization. Keywords are grouped together under their classification and then suggested to the user. In existing work, using diverse keyword extraction, to find topic modelling information, representation of the main topics of transcript and diverse keyword selection. It maximizes the coverage of topics that are automatically recognized in transcript of conversation fragment. Once a set of keywords is extracted, it is clustered according to their user queries and recommended to the user. At the end of result, a single implicit query cannot improve user's satisfaction with the recommended documents. So, swarm intelligence technique is to be applied, it will minimize redundancy in a short list of Keywords and provide accurate query result compared to greedy algorithm
Improved Unsupervised Framework for Solving Synonym, Homonym, Hyponymy & Polysemy Problems from Extracted Keywords and Identify Topics in Meeting Transcripts
No full textABSTRACT
Keyword is the important item in a document that provides efficient access to the content of a document. In the Existing system, Synonym, Homonym, Hyponymy and Polysemy problems were solved from only trained extracted keywords in the meeting transcripts. Synonym problem means different words which have similar meaning they are grouped and single keyword is extracted. Hyponymy problem means one word denoting subclass that is considered and super class keyword is extracted. Homonym means a word which can have two or more different meanings.. A Polysemy means word with different, but related senses. Hidden topics from meeting transcripts can be found using LDA model. MaxEnt classifier is used for extracting keywords and topics which will be used for information retrieval Training the keyword from the dataset is separately needed for all the problems, it is not an automatic one .In this proposed frame work, a dataset has been designed to solve the above mentioned four problems automatically.
KEYWORDS
Keyword, Meeting transcripts, LDA, MaxEnt, Synonym, Homonym, Polysemy, Hyponymy, Datase
A HYBRID MORPHOLOGICAL ACTIVE CONTOUR FOR NATURAL IMAGES
No full textABSTRACT
Morphological active contours for image segmentation have become popular due to their low computational complexity coupled with their accurate approximation of the partial differential equations involved in the energy minimization of the segmentation process. In this paper, a morphological active contour which mimics the energy minimization of the popular Chan-Vese Active Contour without Edges is coupled with a morphological edge-driven segmentation term to accurately segment natural images. By using morphological approximations of the energy minimization steps, the algorithm has a low computational complexity. Additionally, the coupling of the edge-based and region-based segmentation techniques allows the proposed method to be robust and accurate. We will demonstrate the accuracy and robustness of the algorithm using images from the Weizmann Segmentation Evaluation Database and report on the segmentation results using the Sorensen-Dice similarity coefficient.
KEYWORDS
Natural Images, Segmentation, Hybrid Contour, Morphology, Active Contours, Object Extractio
Online Social Network Bullying Detection Using Intelligence Techniques
No full textAbstractSocial networking sites (SNS) is being rapidly increased in recent years, which provides platform to connect people all over the world and share their interests. However, Social Networking Sites is providing opportunities for cyberbullying activities. Cyberbullying is harassing or insulting a person by sending messages of hurting or threatening nature using electronic communication. Cyberbullying poses significant threat to physical and mental health of the victims.Detection of cyberbullying and the provision of subsequent preventive measures are the main courses of action to combat cyberbullying. The proposed method is an effective method to detect cyberbullying activities on social media. The detection method can identify the presence of cyberbullying terms and classify cyberbullying activities in social network such as Flaming, Harassment, Racism and Terrorism, using Fuzzy logic and Genetic algorithm. The effectiveness of the system is increased using Fuzzy rule set to retrieve relevant data for classification from the input. In the proposed method Genetic algorithm is also used, for optimizing the parameters and to obtain precise output
A Review of Blockchain Technology Based Techniques to Preserve Privacy and to Secure for Electronic Health Records
No full textResearch has been done to broaden the block chain’s use cases outside of finance since Bitcoin introduced it. One sector where block chain is anticipated to have a big influence is healthcare. Researchers and practitioners in health informatics constantly struggle to keep up with the advancement of this field's new but quickly expanding body of research. This paper provides a thorough analysis of recent studies looking into the application of block chain based technology within the healthcare sector. Electronic health records (EHRs) are becoming a crucial tool for health care practitioners in achieving these objectives and providing high-quality treatment. Technology and regulatory barriers, such as concerns about results and privacy issues, make it difficult to use these technologies. Despite the fact that a variety of efforts have been introduced to focus on the specific privacy and security needs of future applications with functional parameters, there is still a need for research into the application, security and privacy complexities, and requirements of block chain based healthcare applications, as well as possible security threats and countermeasures. The primary objective of this article is to determine how to safeguard electronic health records (EHRs) using block chain technology in healthcare applications. It discusses contemporary HyperLedgerfabrics techniques, Interplanar file storage systems with block chain capabilities, privacy preservation techniques for EHRs, and recommender systems
Technological Singularity in Sujatha Ranganathan’s En Iniya Iyanthira and Meendum Jeeno
No full textThe research paper aims at exploring the narrative aesthetics of Tamil science fiction in which the author takes twenty-first-century politics in India within the context of technological singularity. The article presents the political situation and totalitarianism in the age of technological singularity. The research focuses on the social impacts of artificial intelligence’s ability to read, learn, think, and act against its pre-programmed mechanism. A robotic dog struggles to restore a democratic political system from autocracy. The dystopian fictions “En Iniya Iyanthira” and “Meendum Jeeno” written by Sujatha Ranganathan depict the cognitive power of super intelligence behind a woman’s political actions to protect the people of India from exploitation, and corruption to create a better future. The paper demonstrates what a world without individual freedom looks like under the digital surveillance system of a totalitarian regime. The paper raises the question of what happens when a robot develops its rationality and mimics human behaviour. In these fictions, humans attempt to destroy the robotic dog. The robotic dog reaches a standard where nothing can destroy it. The paper explores the ways the robotic dog gains the knowledge to understand and practice the concept of humanity. The paper concludes with the post-humanistic conflicts between a woman and a robotic dog in emotional, ethical, and political aspects
Neutrosophic graph cut-based segmentation scheme for efficient cervical cancer detection
No full textCervical cancer is the most serious category of cancer that has very low survival rate in the women’s community around the globe. This survival probability of women society affected by this cervical cancer can be potentially enhanced if it is detected at an early stage as they do not provide any realizable degree of symptoms in the early phase
Neutrosophic graph cut-based segmentation scheme for efficient cervical cancer detection
No full textCervical cancer is the most serious category of cancer that has very low survival rate in the women’s community around the globe. This survival probability of women society affected by this cervical cancer can be potentially enhanced if it is detected at an early stage as they do not provide any realizable degree of symptoms in the early phase. This cervical cancer needs to be detected at an early stage through periodical checkups. Hence, the objective of the proposed work focuses on the merits of Neutrosophic Graph Cut-based Segmentation (NGCS) facilitated over the pre-processed cervical images. This NGCS-based segmentation is mainly employed for investigating the overlapping contexts of cervical smear pre-processed images for better classification accuracy. This NGCS-based segmentation is responsible for partitioning the input preprocessed image into a diversified number of non-overlapping regions that aids in better perception at the convenience. In NGCS-based segmentation, the preprocessed input image is transformed into a Neutrosophic set and indeterminacy filter depending on the estimated indeterminacy value that integrates the intensity and spatial information the preprocessed image. The utilized indeterminacy filter plays the anchor role in minimizing the indeterminacy value associated with each intensity and spatial information. Then a graph is defined over the image with unique weights are assigned to each of the image pixels based on the estimated indeterminacy value. Finally, the maximum flow graph approach is applied over the graph for determining optimal segmentation results. The results of this NGCS-based cervical cancer detection technique is proved to be excellent on an average by 13% compared to the traditional graph cut oriented cancer detection approaches
