Kishorjit Nongmeikapam

• Ph D.
• Professor (Assistant) at Indian Institute of Information Technology (IIIT) Manipur

Many researchers have preferred non-invasive techniques for recognizing the exact type of physiological abnormality in the vocal tract by training machine learning algorithms with feature descriptors extracted from the voice signal. However, until now, most techniques have been limited to classifying whether a voice is normal or abnormal. It is cru...

Deep learning is known to be data-intensive. In this light, low-resource voice datasets face a great disadvantage. The current study proposes a novel method of fine-grained voice discrimination. The available voice signal dataset is increased multifold by splitting uniformly into shorter samples and converting them into continuous wavelet rransform...

Lack of parallel corpus is one of the main roadblocks for neural machine translation in Low-Resource languages. Collecting parallel sentences corpus from web are noisy and requires alignment. This work attempts to create an English-Manipuri parallel corpus crawled from ‘Maan Ki Baat’ translated data by devising an efficient English-Manipuri automat...

Named Entity Recognition and Classification (NER) serves as a foundation for many natural language processing tasks such as question answering, text summarization, news/document clustering and machine translation. Manipuri’s early NER systems are based on machine learning approaches and employ handcrafted morphological features and domain-specific...

The ability to extract roads, detect buildings, and identify land cover types from satellite images is critical for sustainable development, agriculture, forestry, urban planning, and climate change research. Semantic segmentation with satellite images to extract vegetation covers and urban planning is essential for sustainable development and is a...

A multi-spectral imaging technique for the swift fusion of red–green–blue (RGB) and near infrared (NIR) image pairs with a deep learning based resolution enhancement technique is proposed, mpirically investigated and compared to some state-of-the-art techniques in the current work. The results of the proposed multi-spectral image fusion demonstrate...

Speech is the simplest mode of expression, and any alteration of the vocal cord disrupts its smooth flow. Speech disorders increase vocal exhaustion, pressure, dysphonia, roughness, glottal attack, sore throat, etc. Disruption of a smooth voice in most situations leads to a wide range of psychiatric disorders resulting from stigmatization from peer...

In a variety of areas from diagnosis and prediction to treatment based on the course of a disease, medical imaging plays a pivotal role. Image segmentation is a process that extracts the area of interest automatically or semi-automatically. Multimodality imaging is a concept used to capture an area of interest in the format used by various types, s...

Non-invasive identification of abnormal voice using feature descriptors and machine learning classifiers has been the preference of many literatures. Using feature descriptors and time-frequency image with deep learning is a better alternative. Most voice pathology deep learning frameworks are based on binary classification model. Implementing a ha...

There are existing problems of finding relation between sentences for quite a few years. A system that can find the relation between a phrase and a document can be used for search engines, article finder and many more. This paper is focused on the problem statement of deciding whether given two sentences or two set of sentences are unrelated or rel...

It is a known fact that on the daily basis significant amount of information is produced due to large number of people being connected to social networking sites. Online interaction is now included in our lifestyle whether it is through a tweet, a message or through commenting on each other posts on different platforms. Online interaction contribut...

The ability of a machine to capture 3D information from the real world duplicating the ability of human vision is one of the great interest in science and industry. Works on stereo vision duplicating the real world environment for machines to adapt the ability of human vision by many researchers.

There are existing problems of finding relation between sentences for quite a few years. A system that can find the relation between a phrase and a document can be used for search engines, article finder and many more. This paper is focused on the problem statement of deciding whether given two sentences or two set of sentences are unrelated or rel...

Image classification is one of the popular fields for researchers in computer vision. This study highlights the use of simple linear iterative clustering (SLIC) superpixel in combination with fast and automatically adjustable Gaussian radial basis function kernel‐based fuzzy C‐means (FAAGKFCM) for image segmentation along with the deep learning tec...

Sensor fusion is the combination of sensory data or data derived from sensors such that the information obtained would be more accurate and complete than when they were used individually. Sensor fusion is applicable for object detection and autonomous navigation systems. The techniques that have been developed for object detection and object size c...

One of the great interest in science and industry is the ability for a machine to capture 3D information from the real world which can duplicate the ability of human vision. Many research has been conducted in stereo vision to duplicate the real world environment for a machine to adapt the ability of human vision. The distance of an object from an...

In this study, a method for fusing of visible (or standard RGB) with near-infrared (NIR) image pair for enhancing a hazy image is proposed. Better image enhancement in terms of contrast, sharpness, increased perception is realised by combining the components from both the spectra. While there are a number of applications that use NIR images, very f...

This paper presents the idea of measuring the distance between the object and the center of two cameras placed at any distance from each other. The distance is calculated with the concept of Digital Image Processing. The input given to the algorithm is the only difference between the x coordinate of the left camera image and the right camera image....

A new technique for classifying all 56 different characters of the Manipuri Meetei-Mayek (MMM) is proposed herein. The characters are grouped under five categories, which are Eeyek Eepee (original alphabets), Lom Eeyek (additional letters), Cheising Eeyek (digits), Lonsum Eeyek (letters with short endings), and Cheitap Eeyek (vowel signs. Two relat...

Detection and reading of the text from natural images is a difficult computer vision task, which is essential in a variety of emerging applications. Document character recognition is one such problem, which has been widely studied and documented by many machine learning and computer vision researchers, which is practically used for solving applicat...

In this paper different type of classifiers such as Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Naive Bayes classifier (NB) and Random Forest classifier are studied while changing the amount of data along with different Principal Component Analysis (PCA) technique like standard deviation, mean and variance to analyse the emotion signal...

The traditional Fuzzy C-means (FCM) has been adopted worldwide to perform different kinds of image segmentation. However, owing to the fact that it is very susceptible to noise and other image artifacts, its usage is no longer a priority in the constantly changing real world application. The motivation of this paper is to propose a robust & unsuper...

Although character recognition for major Indian, and otherglobal languages have reached the status of the ‘state-of-the-art’, yet there is no record of work being done to classify all the 56 different classes of the Manipuri Meetei-Mayek by a single baseline classifier. In the current paper, a novel architecture for classifying these classes by usi...

In this paper, a new approach for efficiently extracting cognition out of a total of 56 different classes of handwritten Manipuri Meetei-Mayek (Indian language) is being described. Although character recognition algorithms has been researched and developed for other Indian scripts, no research work has been reported so far for recognising all the c...

Fuzzy C-means algorithm is a popular image segmentation algorithm and many researchers in the past have introduced several improved versions of it. However, they still lacked robustness for segmenting key regions of magnetic resonance (MR) human brain transversal images such as white matter, grey matter, and cerebro spinal fluid with an almost simi...

Detection and reading of text from natural im-ages is a difficult computer vision task which is essential in a variety of emerging applica-tions. Document character recognition is one such problem which has been widely studied by many machine learning and computer vi-sion researchers which practicably solved for applications like recognizing handwr...

Feature selection is a major hurdle for the CRF and SVM based POS tagging. The features are of course listed which will have a very good impact with the identification of POS. Among the listed features, the feature selection is purely a manual effort with hit and trail methods among them. The best way for better output is to design a system where t...

This paper records the work of Manipuri Chunking by using the commonly use tool of Support Vector Machine (SVM). Manipur being a very highly agglutinative language have to be careful in selecting the features for running the SVM. An experiment is being performed with 35,000 words to check whether the POS tagged and the Reduplicated Multiword Expres...

This paper records the work of Manipuri Chunking by using the commonly use tool of Support Vector Machine (SVM). Manipur being a very highly agglutinative language have to be careful in selecting the features for running the SVM. An experiment is being performed with 35,000 words to check whether the POS tagged and the Reduplicated Multiword Expres...

This paper manifests a primary attempt on building a word sense disambiguation system in Manipuri language. The paper discusses related attempts made in the Manipuri language followed by the proposed plan. A database, consisting of 650 sentences, is collected in Manipuri language in the course of the study. Conventional positional and context ba...

This paper deals about the sentiment analysis of the Manipuri article. The language is very highly agglutinative in Nature. The document files are the letters to the editor of few local daily newspapers. The text is processed for Part of Speech (POS) tagging using Conditional Random Field (CRF). The lexicon of verbs is modified with the sentiment p...

This paper deals about the chunking of the Manipuri language, which is very highly agglutinative in Nature. The system works in such a way that the Manipuri text is clean upto the gold standard. The text is processed for Part of Speech (POS) tagging using Conditional Random Field (CRF). The output file is treated as an input file for the CRF based...

The Morphemes of the Manipuri word are the real bottleneck for any of the Manipuri Natural Language Processing (NLP) works. It is one of the Indian Scheduled Language with less advancement so far in terms of NLP applications. This is because the nature of the language is highly agglutinative. Segmentation of a word and identifying the morphemes bec...

This paper contains the detailed approach of automatic extraction of Keyphrases from scientific articles (i.e. research paper) using supervised tool like Conditional Random Fields (CRF). Keyphrase is a word or set of words that describe the close relationship of content and context in the document. Keyphrases are sometimes topics of the document th...

Transliteration is common to all those language which have multiple scripts. Manipuri, which is one of the Schedule Indian Languages, is one of them. This language has two scripts: a borrowed Bengali Script and the original Meitei Mayek (Script). Part of Speech (POS) tagging of the Bengali Script Manipuri text is performed using Conditional Random...

The Reduplicated Multiword Expression (RMWE) is identified using Support Vector Machine (SVM) and these identified RMWE is used as a feature for the SVM based POS tagging of Manipuri, which is a very highly agglutinative Indian Schedule Language. A common feature approach for both RMWE identification and POS tagging is tried. Identification of RMWE...

The work of automatic segmentation of a Manipuri language (or Meiteilon) word into syllabic units is demonstrated in this paper. This language is a scheduled Indian language of Tibeto-Burman origin, which is also a very highly agglutinative language. This language usages two script: a Bengali script and Meitei Mayek (Script). The present work is ba...

Manipuri is a Scheduled Indian language which has two script: a borrowed Bengali Script and the original Meitei Mayek (Script). Manipuri is a resource poor language specially the Meitei Mayek text Manipuri. This paper deals with Support Vector Machine (SVM) based Part of Speech (POS) tagging of the Bengali Script text and then are transliterated to...

This paper gives a detail overview about the modified features selection in CRF (Conditional Random Field) based Manipuri POS (Part of Speech) tagging. Selection of features is so important in CRF that the better are the features then the better are the outputs. This work is an attempt or an experiment to make the previous work more efficient. Mult...

Reduplicated Multiword Expressions (RMWEs) are abundant in Manipuri, the highly agglutinative India language. The Part of Speech (POS) tagging of Manipuri using Support Vector Machine (SVM) has been developed and evaluated. The POS tagger has been updated with identified RMWEs as another feature. The performance of the SVM based POS tagger before a...

This paper gives a detail overview about the modified features selection in CRF (Conditional Random Field) based Manipuri POS (Part of Speech) tagging. Selection of features is so important in CRF that the better are the features then the better are the outputs. This work is an attempt or an experiment to make the previous work more efficient. Mult...

This paper deals with the identification of Multiword Expressions (MWEs) in Manipuri, a highly agglutinative Indian Language. Manipuri is listed in the Eight Schedule of Indian Constitution. MWE plays an important role in the applications of Natural Language Processing(NLP) like Machine Translation, Part of Speech tagging, Information Retrieval, Qu...

This paper deals about the Name Entity Recognition (NER) of Manipuri, a highly agglutinative Indian Language. This language is an Eight Scheduled Language of Indian Constitution. NER plays an important role in the applications of Natural Language Processing like Machine Translation, Part of Speech tagging, Information Retrieval, Question Answering...

This paper deals with the identification of Reduplicated Multiword Expressions (RMWEs) which is important for any natural language applications like Machine Translation, Information Retrieval etc. In the present task, reduplicated MWEs have been identified in Manipuri language texts using CRF tool. Manipuri is highly agglutinative in nature and red...

The transformation of the words into their grammatical root form is performed in the stemmer. This Stemmer is designed for Manipuri which is a Tibeto-Burman language and which is also an Eight Scheduled language of Indian Constitution. Manipuri is a language which has 61 suffixes and 12 prefixes and is highly agglutinative. The inflection plays an...

The transformation of the words into their grammatical root form is performed in the stemmer. This Stemmer is designed for Manipuri which is a Tibeto-Burman language and which is also an Eight Scheduled language of Indian Constitution. Manipuri is a language which has 61 suffixes and 12 prefixes and is highly agglutinative. The inflection plays an...

This paper describes about the transliteration of Manipuri from Bengali Script to Meitei Mayek (Meitei script). So far no work of Manipuri transliteration is done and being an Eight Schedule Language of Indian Constitution we felt necessary to start through a rule based. A model and algorithm is being designed for transliterating Manipuri from Beng...

This paper describes about the transliteration of Manipuri, an Eight Schedule Language of Indian Constitution from Meitei Mayek (Meitei script) to English Script. Transliteration is the conversion from one script to target script by preserving the pronunciation of the source script. Manipuri transliteration is hardly found so far. A model and algor...

This paper deals with the identification of Multiword Expressions (MWE) in the Mani-puri text using Conditional Random Field (CRF) machine learning techniques. Manipuri is a language spoken mainly in Manipur, a state in the North Eastern part of India as well as in some parts of Myanmar and Bangladesh. It is highly agglutinative in nature and thus...

The identification of reduplicated Multiword Expressions (MWEs) is part of the general task of multiword expressions identifications that is important for any natural language applications like Machine Translation, Information Retrieval etc. In the present task, reduplicated MWEs have been identified in Manipuri language texts. Manipuri is a less c...

This paper deals about the tagging of Part of Speech (POS) in the Manipuri text using Conditional Random Field (CRF) which is an unsupervised learning approach. Manipuri is a language spoken mainly in Manipur, a state in the North Eastern Part of India also in some other part of Myanmar and Bangladesh. It is highly agglutinative in nature thus choo...

This paper reports about the development of a Manipuri NER system, a less computerized Indian language. Two different models, one using an active learning technique based on the context patterns generated from an unlabeled news corpus and the other based on the well known Support Vector Machine (SVM), have been developed. The active learning techni...

This paper reports about the development of a Manipuri NER system, a less computerized Indian language. Two different models, one using an active learning technique based on the context patterns generated from an unlabeled news corpus and the other based on the well known Support Vector Machine (SVM), have been developed. The active learning techni...

This paper deals with the identification of Multiword Expressions (MWE) in the Mani-puri text using Conditional Random Field (CRF) machine learning techniques. Manipuri is a language spoken mainly in Manipur, a state in the North Eastern part of India as well as in some parts of Myanmar and Bangladesh. It is highly agglutinative in nature and thus...

The identification of reduplicated Multiword Expressions (MWEs) is part of the general task of multiword expressions identifications that is important for any natural language applications like Machine Translation, Information Retrieval etc. In the present task, reduplicated MWEs have been identified in Manipuri language texts. Manipuri is a less c...