Monalisa Dey

Followers

Following

Public Views

Interests

Uploads

Papers by Monalisa Dey

Sentiment Analysis using Machine Translation

CRC Press eBooks, Apr 5, 2022

A novel approach to overcome network failure

2017 8th IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON), 2017

A distributed network can have faulty links and nodes. In such a case, reaching a decision amongs... more A distributed network can have faulty links and nodes. In such a case, reaching a decision amongst themselves become extremely difficult. The current work describes an effective solution for reaching an agreement in a distributed system in the presence of such faults. Furthermore, a partitioning method is used to reduce the overhead of exchanging messages.

Chatbot: An automated conversation system for the educational domain

2018 International Joint Symposium on Artificial Intelligence and Natural Language Processing (iSAI-NLP), 2018

Speech and textual information play a crucial role in communicating between humans. An article in... more Speech and textual information play a crucial role in communicating between humans. An article in “The New York Times” published that now-a-days the adults are spending more than 8 hours a day on screens of computers or mobiles. So the major communication between humans is conducted through web applications such as WhatsApp, Facebook, and Twitter etc as a form of speech and textual conversation. In the present paper, we have focused on designing a textual communication application namely chatbot in the educational domain. The proposed chatbot assists in answering questions provided by the users. To develop the system, we have employed an ensemble learning method as random forest in the presence of extracted features from our prepared dataset. Besides, the validation system offers an average F-measure 0.870 score on various K-values under random forest for the proposed chatbot. Finally, we have deployed the proposed system in a from of telegram bot.

SETA- Extractive to Abstractive Summarization with a Similarity-Based Attentional Encoder-Decoder Model

ECTI Transactions on Computer and Information Technology, Jun 21, 2024

Article information: Summarizing information provided within tables of scientic documents has alw... more Article information: Summarizing information provided within tables of scientic documents has always been a problem. A system that can summarize this vital information, which a table encapsulates, can provide readers with a quick and straightforward solution to comprehend the contents of the document. To train such systems, we need data, and nding a quality one is tricky. To mitigate this challenge, we developed a high-quality corpus that contains both extractive and abstractive summaries derived from tables, using a rule-based approach. This dataset was validated using a combination of automated and manual metrics. Subsequently, we developed a novel Encoder-Decoder framework, along with attention, to generate abstractive summaries from extractive ones. This model works on a mix of extractive summaries and inter-sentential similarity embeddings and learns to map them to corresponding abstractive summaries. On experimentation, we discovered that our model addresses the saliency factor of summarization, an aspect overlooked by previous works. Further experiments show that our model develops coherent abstractive summaries, validated by high BLEU and ROUGE scores.

Download

How to Analyze the Overall Performance of a Student: Strong or Weak

2018 IEEE 5th International Congress on Information Science and Technology (CiSt), 2018

Recent advancements in Natural Language Processing (NLP) techniques, especially in the educationa... more Recent advancements in Natural Language Processing (NLP) techniques, especially in the educational domain, have increased to address the needs of teachers, students, parents, educators, and general authors for providing assistance. The assistance can be measured in terms of performance analysis for evaluating and guiding students for their career perspectives. So, in the present work, we have prepared an annotated dataset which helps to design an automated performance analysis system in the presence of two well-known machine learning classifiers namely Naïve Bayes and Logistic Regression. The system is able to recognize five different classes of subjects like soft skills, quantitative and logical ability, programming skills, domain knowledge, and advanced knowledge and overall performance of a student in the form of strength and weakness.

An Automated System to Identify Sentiment from Micro-Blog Texts of Tweets

The recent trends of Internet help to produce the sentiment and emotion-based opinion at the time... more The recent trends of Internet help to produce the sentiment and emotion-based opinion at the time of conversation between human beings. During the Coronavirus disease (COVID-19) pandemic, we are spending maximum time of the day on Internet especially on social networking Web sites. The Web sites are Twitter, Facebook, and WhatsApp, which are taking a crucial role to communicate with each other in the form of messages. The messages are representing such as short-texts and micro-texts and carrying sentiment. The sentiment identification is challenging due to the length of the message. In the present paper, we are motivated to design a sentiment analysis system for Twitter micro-texts in the topic of Coronavirus disease (COVID-19). Hence, we have scrawled a dataset from Twitter using Twitter API and presented as our experimental dataset. Additionally, we have developed two state-of-the-art techniques, viz. unsupervised and supervised to build this system. The unsupervised technique hel...

Using Convolutions and Image Processing Techniques to Segment Lungs from CT Data

Advances in Intelligent Systems and Computing, 2019

In this paper, we put forward a novel approach of lung segmentation using convolutional neural ne... more In this paper, we put forward a novel approach of lung segmentation using convolutional neural networks (CNNs). CNNs have outperformed traditional techniques in many visual recognition tasks over the years. In the traditional methods, the features of the images to be recognized and then segmented are often hand-coded. This might seem quite simple at first and easy to implement but then as the complexity of the problems increases, these methods start to crumble. Moreover, these methods do not handle edge cases accurately as the programs do not know what to do when the images deviate from the expected nature. This is where deep learning methods (CNNs in our case) come to the rescue. Instead of hard-coding, we have built a CNN which is fed with a dataset consisting of CT images and the segmented images of the lungs. CNN automatically detects the features, and the accuracy is increased by tuning the parameters as well as using other techniques. The model once trained is then tested usin...

(034–035) Proposals to amend Article 9.6 and Example 6

TAXON, 2020

Tamper detection of electrocardiographic signal using watermarked bio-hash code in wireless cardiology

International Journal of Signal and Imaging Systems Engineering, 2015

The current globalised era is marked with a rapid increase in the use of wireless media to exchan... more The current globalised era is marked with a rapid increase in the use of wireless media to exchange information over globally distributed locations. This advancement and growth of technologically mediated information helps to provide medical care from a distant location by exchanging biomedical information amongst various hospitals and diagnostic centres across the world. However, while transmitting, the medical information becomes highly vulnerable to miscellaneous attacks like tampering and hacking. A watermark is added in the Electrocardiographic (ECG) signal to increase the level of security to help protect the integrity of the data and decrease the chances of wrong diagnosis. In this current work, a technique is proposed to detect undesirable modifications, if present, in a transmitted biomedical ECG signal. The proposed method is based on bio-hashing and reversible watermarking techniques.

Download

An Efficient Cellular Automata based Leader Election Scheme

International Journal of Computer Applications, 2012

This work reports an efficient scheme of electing a leader, in a fully connected distributed syst... more This work reports an efficient scheme of electing a leader, in a fully connected distributed system, having n number of nodes. In the proposed scheme, the system state is modeled using Cellular Automata. Each node is initialized with status information. This information has to be maintained by the nodes at all times so that they are aware of the current working coordinator in the system. The proposed scheme requires only O(n) messages for decision making.

Download

SciSumm 2017: Employing Word Vectors for Identifying, Classifying and Summarizing Scientific Documents

This paper describes our approach on ”Recognizing Reference Spans,Classifying Their Discourse Fac... more

Download

A Novel Approach for Block-Based Data Encryption

Abstract—With the growth of data communication over the internet, the need for security has obtai... more Abstract—With the growth of data communication over the internet, the need for security has obtained utmost importance. Data needs to be kept hidden from all the internet users apart from the authorized ones. Data should be encrypted before sending it through the internet. Here, an algorithm based on Block-Based data encryption is introduced, where the encryption and decryption process is done on binary data, so it will be applicable to all data in the field of computer science.

Heart Disease Prediction—An Online Consultation Software

JUNLP at IJCNLP-2017 Task 3: A Rank Prediction Model for Review Opinion Diversification

IJCNLP-17 Review Opinion Diversification (RevOpiD-2017) task has been designed for ranking the to... more IJCNLP-17 Review Opinion Diversification (RevOpiD-2017) task has been designed for ranking the top-k reviews of a product from a set of reviews, which assists in identifying a summarized output to express the opinion of the entire review set. The task is divided into three independent subtasks as subtask-A,subtask-B, and subtask-C. Each of these three subtasks selects the top-k reviews based on helpfulness, representativeness, and exhaustiveness of the opinions expressed in the review set individually. In order to develop the modules and predict the rank of reviews for all three subtasks, we have employed two well-known supervised classifiers namely, Naïve Bayes and Logistic Regression on the top of several extracted features such as the number of nouns, number of verbs, and number of sentiment words etc from the provided datasets. Finally, the organizers have helped to validate the predicted outputs for all three subtasks by using their evaluation metrics. The metrics provide the s...

Download

NTCIR-12 MOBILECLICK: Sense-based Ranking and Summarization of English Queries

NTCIR-12 MobileClick task has been designed to rank and summarize English queries. The primary ai... more NTCIR-12 MobileClick task has been designed to rank and summarize English queries. The primary aim of this task was to develop a system which is capable of minimizing interaction between the human users and mobile phones while extracting relevant data with respect to given queries. Organizers provided the data represented as information units (iUnits). Each of the iUnits describes a pertinent query associated with other information like type or category, relevance, sense and knowledge-based relations [1] [2] [4]. The task is divided into two sub-tasks namely ranking and summarization. The ranking sub-task focuses on identifying the important iUnits related to a query. In the summarization sub-task, the output has to be designed as a two-layered model where the first layer will identify the important iUnits and the second layer will compile those important iUnits and generate a summarized output for the query. In this present task, we have employed several sentiment lexicons like Sen...

Download

A Deep Dive into Supervised Extractive and Abstractive Summarization from Text

Since the advent of World Wide Web, the world has seen an exponential growth in the information o... more Since the advent of World Wide Web, the world has seen an exponential growth in the information on the internet. In the web, today, a lot of digital articles are available for users to read. However, these documents lack a concise summary. Automatic systems that summarize such information are very rare. Moreover, these systems also lack the ability of getting information from multiple places and presenting the user with a coherent, informative summary. Summarization are of two types, viz. Extractive and Abstractive. While a lot of work has been done on extractive summary, abstractive summary generation is still an unexplored area. In the current work, the focus is essentially on producing abstractive summary of a document by first getting relevant and important sentences from the corpus and feeding these sentences as input in a trained deep neural network. For extracting salient sentences two models has been proposed, both these models not only consider syntactic similarity but also...

Classification of COVID19 tweets using Machine Learning Approaches

Proceedings of the Sixth Social Media Mining for Health (#SMM4H) Workshop and Shared Task, 2021

The reported work is a description of our participation in the "Classification of COVID19 tweets ... more The reported work is a description of our participation in the "Classification of COVID19 tweets containing symptoms" shared task, organized by the "Social Media Mining for Health Applications (SMM4H)" workshop. The literature describes two machine learning approaches that were used to build a threeclass classification system, that categorizes tweets related to COVID19, into three classes, viz., self-reports, non-personal reports, and literature/news mentions. The steps for preprocessing tweets, feature extraction, and the development of the machine learning models, are described extensively in the documentation. Both the developed learning models, when evaluated by the organizers, garnered F1 scores of 0.93 and 0.92 respectively.

Download

An Improved Approach of Cryptography using Triangulation and MSB Iteration Technique

Ijca Special Issue on International Conference on Computing Communication and Sensor Network, Apr 3, 2013

Download

Electrocardiogram Feature Based Inter-human Biometric Authentication System

2014 International Conference on Electronic Systems, Signal Processing and Computing Technologies, 2014

ABSTRACT Biometrics integrates various technologies to identify an individual by exploiting their... more ABSTRACT Biometrics integrates various technologies to identify an individual by exploiting their physiological and behavioral characteristics, which are unique and measurable. This paper proposes a novel technique for the development of a robust and secure biometric authentication system. In this current work, an interhuman ECG-Hash code is generated by performing an inner product between the Electrocardiogram (ECG) feature matrices of two different individuals located remotely. The individuals will have each other&amp;#39;s ECG features, stored in their database. The accuracy of the system increases as the authentication mechanism requires traits from both the individuals, amongst whom the transmission is taking place. Moreover, the use of ECG features as a biometric trait enhances the security aspects of the system as traits like fingerprints or facial features maybe compromised with age or otherwise.

A Novel Approach to Cryptography using Modified Substitution Cipher and Hybrid Crossover Technique

Ijca Proceedings on Computing Communication and Sensor Network 2013, Dec 26, 2013

In the modern globally connected world, with the internet growing continually, the exchange of in... more In the modern globally connected world, with the internet growing continually, the exchange of information over the web has made the data quite vulnerable. The need for data security is thus increasing exponentially day by day. Cryptography is a scientific measure used for the protection of sensitive communications. In this paper, a novel approach for information security is introduced. The encryption technique is incorporated using two methods namely, a modified approach to substitution cipher and a two step hybrid crossover technique. The devised algorithm uses two keys, thereby, increasing the security aspect. Moreover the entire process is done on alphabetical data thus increasing the scope of its implementation.

Download

Monalisa Dey

Uploads

Papers by Monalisa Dey

Log In