manjunatha kumar | Sri Siddhartha Academy Of Higher Education (original) (raw)

Uploads

Papers by manjunatha kumar

Research paper thumbnail of Business analysis and modelling of flight delays using artificial intelligence

International journal of health sciences

In the current day, with the growth of technology the number of people travelling by flights has ... more In the current day, with the growth of technology the number of people travelling by flights has increased. Consistently a significant number of flights are delayed or crossed out because of numerous of reasons. These delays bother travelers. These delays also cost a lot to the aircraft organization. Flight delays negatively affect carriers, air terminals and travelers. There are different methodologies used to manufacture flight delays expectation models from the Data Science point of view. The key resource of a flight includes aircraft, cockpit crew and cabin crew. For purposes of dispatching resources effectively, the three resources may be distributed independently. If the initial flight of a flight plan is delayed due to bad weather or other factors, it may result in the delays of the directly downstream flights that need to await its resources. If the delays continue to spread to the lower downstream flights, it may result in large area delay propagation. The method proposed h...

Research paper thumbnail of Designing of Special Purpose Macs for Building More Efficient Secure Channels

Cryptography is the art and science of keeping messages Secure. In this paper, we propose the dep... more Cryptography is the art and science of keeping messages Secure. In this paper, we propose the deployment of a new cryptographic primitive for the construction of secure channels using the Generic composition method of Cryptography. We introduce the design of E-MACs, Message Authentication Codes for Encrypted messages. By proposing the first instance of E-MACs, we show how the structure of the Encrypt-and-Authenticate Composition system can be utilized to increase the efficiency and security of the authentication process. The paper shows how a universal hash function based E-MAC can be computed with fewer operations than what standard universal hash functions based MACs require. Moreover, we will also show how E-MACs can further utilize the special structure of the E&A system to improve the security of the authentication process.

Research paper thumbnail of Survey on Automated Medical Image Classification Using Deep Learning

International Journal of Health Sciences (IJHS), Apr 30, 2022

Learning has indeed been widely used in many fields/areas of medicinal images classification, and... more Learning has indeed been widely used in many fields/areas of medicinal images classification, and a large number of publications have been published documenting its success. The key for achieving effective diagnosis and therapy is accurate characterization of medical pictures. However, because image interpretation is highly dependent on the subjective opinion of doctors, the results of image processing vary greatly amongst clinicians at different levels. Picture classification, target identification, and image analysis have all improved dramatically in recent years with environmental image data sets in domain of Image Processing. In this paper, we have presented a systematic survey on feature extracting and classifying the medical images using deep learning methods. Two new ideas are presented in this work. First and foremost, we classified presently trendy publications in a multi-level configuration. Second, this research article concentrates on supervised and poorly supervised learning techniques.

Research paper thumbnail of A Survey on Word Sense Disambiguation

In natural language processing (NLP), word sense disambiguation (WSD) is an automatic process car... more In natural language processing (NLP), word sense disambiguation (WSD) is an automatic process carried out by a machine to sense the appropriate meaning of a word in a particular context or in a discourse. Natural language is ambiguous, so that many words may be interpreted in multiple methods depending on the context wherein they occur. The computational identification of which means for words in context is known as word sense disambiguation (WSD). In this paper, we will discuss the ambiguity of the words in the languages and the essential measures to deal with the ambiguous words.

Research paper thumbnail of Kannada word sense disambiguation by finding the overlaps between the concepts

International Journal of Engineering & Technology, 2018

We propose three approaches for disambiguating the Kannada word based on an adaptation of diction... more We propose three approaches for disambiguating the Kannada word based on an adaptation of dictionary-based Lesk’s word sense disambiguation technique. Instead of making use of the regular dictionary as the repository of glosses, we used Indo – WordNet lexical database as the source of senses. Here we adopt a current method of measuring semantic relatedness between the concepts of the Kannada words taken from Indo – WordNet. This measure is dependent on identifying and counting the number of common words present between the glosses of a pair of concepts in accordance with Indo – WordNet.

Research paper thumbnail of Kannada word sense disambiguation using semantic relations

Journal of Physics: Conference Series

In this paper, a method is proposed to use the semantic relations of words to solve Word Sense Di... more In this paper, a method is proposed to use the semantic relations of words to solve Word Sense Disambiguation (WSD) for the Kannada language. Semantic relationships like hypernymy and hyponymy are used in finding the overlaps between two concepts. Integrating the idea proposed in this paper with original Lesk’s technique improves the accuracy of the Lesk’s algorithm. Indo-WordNet is used as the lexical resource to gain the knowledge about the semantic relations of words and this knowledge is exploited to disambiguate the target word of the Kannada language. Since the approach used in this paper is unsupervised, so it can be scalable to other languages also.

Research paper thumbnail of Business analysis and modelling of flight delays using artificial intelligence

International journal of health sciences

In the current day, with the growth of technology the number of people travelling by flights has ... more In the current day, with the growth of technology the number of people travelling by flights has increased. Consistently a significant number of flights are delayed or crossed out because of numerous of reasons. These delays bother travelers. These delays also cost a lot to the aircraft organization. Flight delays negatively affect carriers, air terminals and travelers. There are different methodologies used to manufacture flight delays expectation models from the Data Science point of view. The key resource of a flight includes aircraft, cockpit crew and cabin crew. For purposes of dispatching resources effectively, the three resources may be distributed independently. If the initial flight of a flight plan is delayed due to bad weather or other factors, it may result in the delays of the directly downstream flights that need to await its resources. If the delays continue to spread to the lower downstream flights, it may result in large area delay propagation. The method proposed h...

Research paper thumbnail of Designing of Special Purpose Macs for Building More Efficient Secure Channels

Cryptography is the art and science of keeping messages Secure. In this paper, we propose the dep... more Cryptography is the art and science of keeping messages Secure. In this paper, we propose the deployment of a new cryptographic primitive for the construction of secure channels using the Generic composition method of Cryptography. We introduce the design of E-MACs, Message Authentication Codes for Encrypted messages. By proposing the first instance of E-MACs, we show how the structure of the Encrypt-and-Authenticate Composition system can be utilized to increase the efficiency and security of the authentication process. The paper shows how a universal hash function based E-MAC can be computed with fewer operations than what standard universal hash functions based MACs require. Moreover, we will also show how E-MACs can further utilize the special structure of the E&A system to improve the security of the authentication process.

Research paper thumbnail of Survey on Automated Medical Image Classification Using Deep Learning

International Journal of Health Sciences (IJHS), Apr 30, 2022

Learning has indeed been widely used in many fields/areas of medicinal images classification, and... more Learning has indeed been widely used in many fields/areas of medicinal images classification, and a large number of publications have been published documenting its success. The key for achieving effective diagnosis and therapy is accurate characterization of medical pictures. However, because image interpretation is highly dependent on the subjective opinion of doctors, the results of image processing vary greatly amongst clinicians at different levels. Picture classification, target identification, and image analysis have all improved dramatically in recent years with environmental image data sets in domain of Image Processing. In this paper, we have presented a systematic survey on feature extracting and classifying the medical images using deep learning methods. Two new ideas are presented in this work. First and foremost, we classified presently trendy publications in a multi-level configuration. Second, this research article concentrates on supervised and poorly supervised learning techniques.

Research paper thumbnail of A Survey on Word Sense Disambiguation

In natural language processing (NLP), word sense disambiguation (WSD) is an automatic process car... more In natural language processing (NLP), word sense disambiguation (WSD) is an automatic process carried out by a machine to sense the appropriate meaning of a word in a particular context or in a discourse. Natural language is ambiguous, so that many words may be interpreted in multiple methods depending on the context wherein they occur. The computational identification of which means for words in context is known as word sense disambiguation (WSD). In this paper, we will discuss the ambiguity of the words in the languages and the essential measures to deal with the ambiguous words.

Research paper thumbnail of Kannada word sense disambiguation by finding the overlaps between the concepts

International Journal of Engineering & Technology, 2018

We propose three approaches for disambiguating the Kannada word based on an adaptation of diction... more We propose three approaches for disambiguating the Kannada word based on an adaptation of dictionary-based Lesk’s word sense disambiguation technique. Instead of making use of the regular dictionary as the repository of glosses, we used Indo – WordNet lexical database as the source of senses. Here we adopt a current method of measuring semantic relatedness between the concepts of the Kannada words taken from Indo – WordNet. This measure is dependent on identifying and counting the number of common words present between the glosses of a pair of concepts in accordance with Indo – WordNet.

Research paper thumbnail of Kannada word sense disambiguation using semantic relations

Journal of Physics: Conference Series

In this paper, a method is proposed to use the semantic relations of words to solve Word Sense Di... more In this paper, a method is proposed to use the semantic relations of words to solve Word Sense Disambiguation (WSD) for the Kannada language. Semantic relationships like hypernymy and hyponymy are used in finding the overlaps between two concepts. Integrating the idea proposed in this paper with original Lesk’s technique improves the accuracy of the Lesk’s algorithm. Indo-WordNet is used as the lexical resource to gain the knowledge about the semantic relations of words and this knowledge is exploited to disambiguate the target word of the Kannada language. Since the approach used in this paper is unsupervised, so it can be scalable to other languages also.