Dr. Anitha G - Academia.edu (original) (raw)

Papers by Dr. Anitha G

International Advanced Research Journal in Science, Engineering and Technology, 2024

The Chronic Obstructive Pulmonary Disease Prediction System aims to revolutionize early detection... more The Chronic Obstructive Pulmonary Disease Prediction System aims to revolutionize early detection and prognosis through the integration of deep learning and health data analysis using dataset that includes X-Ray obtained from a diverse range of patients. Deep learning algorithms are used together with the integration of data gathered from several hospitals. The prediction model identifies patterns in the data that has been gathered and determines early signs of COPD. The COPD aims to mitigate the impact of this chronic respiratory condition. This project carries significant implications for advancing early identification of COPD using Convolutional Neural Networks (CNNs) and aspires to enhance health care efficiency.

International Journal of Innovative Research in Science, Engineering and Technology (IJIRSET), 2023

Sign language is a universal way of communication for challenged people with speaking and hearing... more Sign language is a universal way of communication for challenged people with speaking and hearing limitations. Multiple mediums are accessible to translate or to acknowledge sign language and convert them to text. However, the text to signing conversion systems has been rarely developed; this is often thanks tothe scarcity of any sign language dictionary. Our projectaims at creating a system that consists of a module that initially transforms voice input to English text and which parses the sentence, then to which Indian sign language grammar rules are applied. This is done by eliminating stop words from the reordered sentence. Indian SignLanguage (ISL) does not sustain the inflections of theword. Hence, stemming is applied to vary over the wordsto their root/ stem class. All words of the sentence are then Checked against the labels in the dictionary containingvideos representing each of the words. The present systems are limited to only straight conversion of wordsinto ISL, whereas the proposed system is innovative, as our system aims to rework these sentences into ISL as pergrammar in the real domain.

International Journal of Innovative Research in Science, Engineering and Technology (IJIRSET), 2023

Every human being is widely accessing knowledge and information through internet. However, blind ... more Every human being is widely accessing knowledge and information through internet. However, blind people face difficulties in accessing these text materials, also with using any service provided through the internet. The advancement in computer-based accessible systems has opened up many avenues for the visually impaired across the globe in a wide way. Audio feedback-based virtual environments like, screen readers have helped visually impaired people to access internet applications immensely. The proposed Voicemail system architecture will help the visuallyimpaired person to access e-Mails easily and efficiently.

Turkish Journal of Computer and Mathematics Education x, 2021

The Morphological analyser & generator (MAG) plays an important Natural LanguageProcessing applic... more The Morphological analyser & generator (MAG) plays an important Natural LanguageProcessing application and are compulsory apparatuses in Machine Translation. In the work proposed, MAG for Kannada language were created utilizing rule based just as factual methodology by fusing morphological data and characteristics of the language. The classification of words into various paradigms dependent on their inflections and orthographic changes, structuring the morphological framework, rule and corpus creations are the primary difficulties in the advancement of generator.The MAG tool is constructed for Kannada texts using machine learning strategies and produced theoutcomes using numerouskinds of eight input data sets. The validation of GUIs and processing of tool is carried out and the snapshots along with the tabulated and graphical performance analysis are published in the work.

International Journal of Advanced Science and Technology, 2020

The Morphological analysis tool recognizes and investigates the structure of the words given inte... more The Morphological analysis tool recognizes and investigates the structure of the words given internally and provides the syntactical and morphological info related to words given as input. The Kannada language is morphologically much richer, inflectional and agglutinative dialect. Constructing the better placed morphological analysis tool for Kannada language is much challenging work. In this work, the Natural Language Processing is discussed to investigate the nouns and verbal words of the language. The Morphological analysis tool is for Kannada verbs and nouns is developed using machine learning approaches and presented the results using various types of eight input data sets. The analyser discussed is constructed making use of regulation-dependent, stripping of suffix based and paradigm-dependent methodologies.

This paper presents sentence similarity Measure for the matching of two sentences using convoluti... more This paper presents sentence similarity Measure for the matching of two sentences using convolutional neural networks. This model also checks the degree of similarity between the matched sentences. A self-learning model is designed to detect the similarity and degree of similarity between the two matched sentences also identifies the dissimilar sentences. Matching two potential sentences is central to many natural language applications. It generalizes the conventional notion of similarity or relevance, since it aims to model the correspondence between "linguistic objects" of different nature at different levels of abstractions. It will require a maxpooling in every two-unit window. The twofold pooling effects are: shrink the size of the representation by half, thus quickly absorbing the differences in length for sentence representation; filter out undesirable composition of words.

Information retrieval is a branch of computer science which is gaining exponential popularity due... more Information retrieval is a branch of computer science which is gaining exponential popularity due to ever increasing amount of data being hosted on Internet. With increase in amount of data hosted on Internet, comes an increase in need of a search engine. Ranking models are techniques used in search engine to find the query relevant documents and to rank them in decreasing order of relevance and hence is an integral part of a search engine. This ranking depends on many factors one of which is the link structure of the web. In this paper, we will provide some of the methods which can be used to exploit this link structure of the web-graph.

The Proposed system investigates the utility and reports our experiences of deploying a prototype... more The Proposed system investigates the utility and reports our experiences of deploying a prototype windturbine monitoring solution based on the recently developed low power wide area network (LPWAN) technology named Lora WAN. When it comes to machine-to-machine communication having a Wireless Sensor Network (WNS) is the best option. Network should be able to support longer distance with less power consumption otherwise system becomes more economical. The proposed system has been implemented using LoRa chips having 433 MHz frequency range, these chips can't be programmed directly hence they are interfaced with ESP32 development board, these boards have all facilities to develop prototype, they have GPIOS, Wi-Fi module, dual core processor, along with LoRa chips sensors too connected to ESP boards, sensors gives the information such as voltage, current, temperature to board, these information are sent by means of packets to receiver located at distant place, while communicating open frequency band is used, the information packets after being processed at receiver dumped to centralized server which is later displayed to concerned authorities for monitoring purpose.

International Journal of Innovative Research in Computer and Communication Engineering , 2022

Software development is complex, time consuming and it requires knowledge on many different level... more Software development is complex, time consuming and it requires knowledge on many different levels such as understanding algorithm, programming language and frameworks. There has been advancement in neural network where researchers have tried to close the gap between Natural Language description of the system and actual
implementation in code using NLP techniques. Python has close gap between natural language descriptions compared to other languages. So, it is better to choose python for code generation. In this paper transformer is used, it is a deep learning model used primarily in the field of natural language process. Transformers are better than all the other architectures because transformers totally avoid recursion, by processing sentences as a whole and by learning relationships between words. GPT-3 is the transformer used in the paper for the generation of code. GPT-3 is a pre–trained transformer model developed by Open AI. GPT-3, a pre–trained transformer accepts natural language comments as input then do the analysis of comments and generate corresponding code in python. The gap is to be closed by analysis of programming comments and generating the required code snippet.

International Advanced Research Journal in Science, Engineering and Technology, 2024

The Chronic Obstructive Pulmonary Disease Prediction System aims to revolutionize early detection... more The Chronic Obstructive Pulmonary Disease Prediction System aims to revolutionize early detection and prognosis through the integration of deep learning and health data analysis using dataset that includes X-Ray obtained from a diverse range of patients. Deep learning algorithms are used together with the integration of data gathered from several hospitals. The prediction model identifies patterns in the data that has been gathered and determines early signs of COPD. The COPD aims to mitigate the impact of this chronic respiratory condition. This project carries significant implications for advancing early identification of COPD using Convolutional Neural Networks (CNNs) and aspires to enhance health care efficiency.

International Journal of Innovative Research in Science, Engineering and Technology (IJIRSET), 2023

Sign language is a universal way of communication for challenged people with speaking and hearing... more Sign language is a universal way of communication for challenged people with speaking and hearing limitations. Multiple mediums are accessible to translate or to acknowledge sign language and convert them to text. However, the text to signing conversion systems has been rarely developed; this is often thanks tothe scarcity of any sign language dictionary. Our projectaims at creating a system that consists of a module that initially transforms voice input to English text and which parses the sentence, then to which Indian sign language grammar rules are applied. This is done by eliminating stop words from the reordered sentence. Indian SignLanguage (ISL) does not sustain the inflections of theword. Hence, stemming is applied to vary over the wordsto their root/ stem class. All words of the sentence are then Checked against the labels in the dictionary containingvideos representing each of the words. The present systems are limited to only straight conversion of wordsinto ISL, whereas the proposed system is innovative, as our system aims to rework these sentences into ISL as pergrammar in the real domain.

International Journal of Innovative Research in Science, Engineering and Technology (IJIRSET), 2023

Every human being is widely accessing knowledge and information through internet. However, blind ... more Every human being is widely accessing knowledge and information through internet. However, blind people face difficulties in accessing these text materials, also with using any service provided through the internet. The advancement in computer-based accessible systems has opened up many avenues for the visually impaired across the globe in a wide way. Audio feedback-based virtual environments like, screen readers have helped visually impaired people to access internet applications immensely. The proposed Voicemail system architecture will help the visuallyimpaired person to access e-Mails easily and efficiently.

Turkish Journal of Computer and Mathematics Education x, 2021

The Morphological analyser & generator (MAG) plays an important Natural LanguageProcessing applic... more The Morphological analyser & generator (MAG) plays an important Natural LanguageProcessing application and are compulsory apparatuses in Machine Translation. In the work proposed, MAG for Kannada language were created utilizing rule based just as factual methodology by fusing morphological data and characteristics of the language. The classification of words into various paradigms dependent on their inflections and orthographic changes, structuring the morphological framework, rule and corpus creations are the primary difficulties in the advancement of generator.The MAG tool is constructed for Kannada texts using machine learning strategies and produced theoutcomes using numerouskinds of eight input data sets. The validation of GUIs and processing of tool is carried out and the snapshots along with the tabulated and graphical performance analysis are published in the work.

International Journal of Advanced Science and Technology, 2020

The Morphological analysis tool recognizes and investigates the structure of the words given inte... more The Morphological analysis tool recognizes and investigates the structure of the words given internally and provides the syntactical and morphological info related to words given as input. The Kannada language is morphologically much richer, inflectional and agglutinative dialect. Constructing the better placed morphological analysis tool for Kannada language is much challenging work. In this work, the Natural Language Processing is discussed to investigate the nouns and verbal words of the language. The Morphological analysis tool is for Kannada verbs and nouns is developed using machine learning approaches and presented the results using various types of eight input data sets. The analyser discussed is constructed making use of regulation-dependent, stripping of suffix based and paradigm-dependent methodologies.

This paper presents sentence similarity Measure for the matching of two sentences using convoluti... more This paper presents sentence similarity Measure for the matching of two sentences using convolutional neural networks. This model also checks the degree of similarity between the matched sentences. A self-learning model is designed to detect the similarity and degree of similarity between the two matched sentences also identifies the dissimilar sentences. Matching two potential sentences is central to many natural language applications. It generalizes the conventional notion of similarity or relevance, since it aims to model the correspondence between "linguistic objects" of different nature at different levels of abstractions. It will require a maxpooling in every two-unit window. The twofold pooling effects are: shrink the size of the representation by half, thus quickly absorbing the differences in length for sentence representation; filter out undesirable composition of words.

Information retrieval is a branch of computer science which is gaining exponential popularity due... more Information retrieval is a branch of computer science which is gaining exponential popularity due to ever increasing amount of data being hosted on Internet. With increase in amount of data hosted on Internet, comes an increase in need of a search engine. Ranking models are techniques used in search engine to find the query relevant documents and to rank them in decreasing order of relevance and hence is an integral part of a search engine. This ranking depends on many factors one of which is the link structure of the web. In this paper, we will provide some of the methods which can be used to exploit this link structure of the web-graph.

The Proposed system investigates the utility and reports our experiences of deploying a prototype... more The Proposed system investigates the utility and reports our experiences of deploying a prototype windturbine monitoring solution based on the recently developed low power wide area network (LPWAN) technology named Lora WAN. When it comes to machine-to-machine communication having a Wireless Sensor Network (WNS) is the best option. Network should be able to support longer distance with less power consumption otherwise system becomes more economical. The proposed system has been implemented using LoRa chips having 433 MHz frequency range, these chips can't be programmed directly hence they are interfaced with ESP32 development board, these boards have all facilities to develop prototype, they have GPIOS, Wi-Fi module, dual core processor, along with LoRa chips sensors too connected to ESP boards, sensors gives the information such as voltage, current, temperature to board, these information are sent by means of packets to receiver located at distant place, while communicating open frequency band is used, the information packets after being processed at receiver dumped to centralized server which is later displayed to concerned authorities for monitoring purpose.

International Journal of Innovative Research in Computer and Communication Engineering , 2022

Software development is complex, time consuming and it requires knowledge on many different level... more Software development is complex, time consuming and it requires knowledge on many different levels such as understanding algorithm, programming language and frameworks. There has been advancement in neural network where researchers have tried to close the gap between Natural Language description of the system and actual
implementation in code using NLP techniques. Python has close gap between natural language descriptions compared to other languages. So, it is better to choose python for code generation. In this paper transformer is used, it is a deep learning model used primarily in the field of natural language process. Transformers are better than all the other architectures because transformers totally avoid recursion, by processing sentences as a whole and by learning relationships between words. GPT-3 is the transformer used in the paper for the generation of code. GPT-3 is a pre–trained transformer model developed by Open AI. GPT-3, a pre–trained transformer accepts natural language comments as input then do the analysis of comments and generate corresponding code in python. The gap is to be closed by analysis of programming comments and generating the required code snippet.