scispace - formally typeset
Search or ask a question
Author

Vinit Kumar Gunjan

Bio: Vinit Kumar Gunjan is an academic researcher from CMR Institute of Technology. The author has contributed to research in topics: Computer science & Biometrics. The author has an hindex of 7, co-authored 60 publications receiving 152 citations. Previous affiliations of Vinit Kumar Gunjan include G H Patel College Of Engineering & Technology & DST Systems.

Papers published on a yearly basis

Papers
More filters
Book ChapterDOI
01 Jan 2020
TL;DR: This paper aims to study deep learning based face representation under several different conditions like lower and upper face occlusions, misalignment, different angles of head poses, changing illuminations, flawed facial feature localization using deep learning approaches.
Abstract: Face Recognition is one of the challenging process due to huge amount of wild datasets. Deep learning has been provided good solution in terms of recognition performance, as day by day this have been dominating the field of biometric. In this paper our goal is to study deep learning based face representation under several different conditions like lower and upper face occlusions, misalignment, different angles of head poses, changing illuminations, flawed facial feature localization using deep learning approaches. For extraction of face representation two different popular models of Deep learning based called Lightened CNN and VGG-Face and have reflected in this paper. As both of this model show that deep learning model is robust to different types of misalignment and can tolerate localizations error of the intraocular distance.

49 citations

Journal ArticleDOI
TL;DR: In this paper , the authors proposed a real-time surveillance helmet that incorporates IoT Sensors that can rescue with early warning intelligence on the presence of fire, silicosis dust particles, temperature, harmful gases, and others that will reduce worker health risks.

33 citations

Book ChapterDOI
01 Jan 2020
TL;DR: The solution to this problem is discussed by using a Machine Learning Model which is trained with past records of attendance of students to find a pattern of class attendance and predict accurate class strength for any future date according to which the lesson plans can be made or modified.
Abstract: An important task of a teacher is to make every student learn and pass the end examination. For this, teachers make lesson plans for year/semester according to number of working days with a goal to complete syllabus prior to final examination. The lesson plans are made without knowledge of the class attendance for any particular day, since it is hard for a teacher to make a correct guess. Therefore, when class strength is unexpectedly low on a given day, the teacher can either postpone the lecture to next day or continue and let the absent students be at loss. Postponing the lecture will not complete the syllabus on expected time and letting students be at loss is also not a solution. This paper will discuss the solution to this problem by using a Machine Learning Model which is trained with past records of attendance of students to find a pattern of class attendance and predict accurate class strength for any future date according to which the lesson plans can be made or modified. Teachers having prior knowledge of class strength will help them to act accordingly to achieve their goals.

29 citations

Book ChapterDOI
01 Jan 2020
TL;DR: In this paper, a project which senses soil moisture and based on the data this system automatically turns ON the water pump into the field, and when the soil reaches enough moisture level, then water pump automatically gets turned OFF.
Abstract: Agriculture and Cultivation of paddy, wheat and vegetables basically takes place in Rural areas where technology isn’t available to that extend where this kind of huge production of grains and vegetables can be automated to help farmers. Farmers spend most of their time in the Agriculture field for watering the crop by leaving other works. Hence to help farmers from staying on the field whole day, we came up with a project which senses soil moisture and based on the data this system automatically turns ON the water pump into the field, and when the soil reaches enough moisture level, then water pump automatically gets turned OFF. Hence this concept may provide a long term solution to the farmers for a maintenance free agriculture where farmers don’t have to stay on the field breathing toxic chemicals and spoiling their health. The proposed project also have other features like sensing the Ambient temperature and humidity in the Agricultural field, sensing daylight intensity and rainfall detection on the field. Hence this inexpensive project can provide a solution for many agricultural and health related problems. To implement this project in a ease of access and updated way, we have incorporated IoT platform where the farmer can monitor all these field parameters over internet on their smart phone application. Therefore this could be a milestone in rebuilding the future.

28 citations

Journal ArticleDOI
TL;DR: This research paper presents a comprehensive study on Lung Cancer detection in terms of simulation of medical images and clinical analysis wherein one of the KRAS mutations has been analysed in lung cancer patients and their lung images have been used for developing medical images with better tumour spot detection.

28 citations


Cited by
More filters
Journal Article
TL;DR: The simulated visual impairment significantly decreased driving performance, even though all drivers satisfied the legal visual requirements for driving.
Abstract: BACKGROUND. The effect of simulated visual impairment on the driving performance of elderly subjects and the relation between changes in driving performance and vision were investigated. METHODS. Vision was impaired by goggles simulating the effects of cataracts, binocular visual field restriction, and monocularity. Driving was assessed on a road circuit free of other vehicles. Visual performance was measured using the Humphrey Field Analyser (HFA), the Useful Field of View (UFOV), and the Pelli-Robson chart. RESULTS. The simulated visual impairment significantly decreased driving performance, even though all drivers satisfied the legal visual requirements for driving. Significant correlations between driving performance and the UFOV and Pelli-Robson chart were found.

119 citations

Journal ArticleDOI
TL;DR: This research work addresses the competency and limitations of the existing IE techniques related to data pre-processing, data extraction and transformation, and representations for huge volumes of multidimensional unstructured data and presents a systematic literature review of state-of-the-art techniques for a variety of big data.
Abstract: Process of information extraction (IE) is used to extract useful information from unstructured or semi-structured data. Big data arise new challenges for IE techniques with the rapid growth of multifaceted also called as multidimensional unstructured data. Traditional IE systems are inefficient to deal with this huge deluge of unstructured big data. The volume and variety of big data demand to improve the computational capabilities of these IE systems. It is necessary to understand the competency and limitations of the existing IE techniques related to data pre-processing, data extraction and transformation, and representations for huge volumes of multidimensional unstructured data. Numerous studies have been conducted on IE, addressing the challenges and issues for different data types such as text, image, audio and video. Very limited consolidated research work have been conducted to investigate the task-dependent and task-independent limitations of IE covering all data types in a single study. This research work address this limitation and present a systematic literature review of state-of-the-art techniques for a variety of big data, consolidating all data types. Recent challenges of IE are also identified and summarized. Potential solutions are proposed giving future research directions in big data IE. The research is significant in terms of recent trends and challenges related to big data analytics. The outcome of the research and recommendations will help to improve the big data analytics by making it more productive.

102 citations

Journal ArticleDOI
TL;DR: Functional near-infrared spectroscopy (fNIRS) and machine learning are proposed for the identification of a possible biomarker of pain to improve pain management, reduce risk factors, and contribute to a more objective, valid, and reliable diagnosis.
Abstract: Pain is a highly unpleasant sensory and emotional experience, and no objective diagnosis test exists to assess it. In clinical practice there are two main methods for the estimation of pain, a patient’s self-report and clinical judgement. However, these methods are highly subjective and the need of biomarkers to measure pain is important to improve pain management, reduce risk factors, and contribute to a more objective, valid, and reliable diagnosis. Therefore, in this study we propose the use of functional near-infrared spectroscopy (fNIRS) and machine learning for the identification of a possible biomarker of pain. We collected pain information from 18 volunteers using the thermal test of the quantitative sensory testing (QST) protocol, according to temperature level (cold and hot) and pain intensity (low and high). Feature extraction was completed in three different domains (time, frequency, and wavelet), and a total of 69 features were obtained. Feature selection was carried out according to three criteria, information gain (IG), joint mutual information (JMI), and Chi-squared (χ2). The significance of each feature ranking was evaluated using three learning models separately, linear discriminant analysis (LDA), the K-nearest neighbour (K-NN) and support vector machines (SVM) using the linear and Gaussian and polynomial kernels. The results showed that the Gaussian SVM presented the highest accuracy (94.17%) using only 25 features to identify the four types of pain in our database. In addition, we propose the use of the top 13 features according to the JMI criteria, which exhibited an accuracy of 89.44%, as promising biomarker of pain. This study contributes to the idea of developing an objective assessment of pain and proposes a potential biomarker of human pain using fNIRS.

61 citations

Book ChapterDOI
01 Jan 2020
TL;DR: This paper aims to study deep learning based face representation under several different conditions like lower and upper face occlusions, misalignment, different angles of head poses, changing illuminations, flawed facial feature localization using deep learning approaches.
Abstract: Face Recognition is one of the challenging process due to huge amount of wild datasets. Deep learning has been provided good solution in terms of recognition performance, as day by day this have been dominating the field of biometric. In this paper our goal is to study deep learning based face representation under several different conditions like lower and upper face occlusions, misalignment, different angles of head poses, changing illuminations, flawed facial feature localization using deep learning approaches. For extraction of face representation two different popular models of Deep learning based called Lightened CNN and VGG-Face and have reflected in this paper. As both of this model show that deep learning model is robust to different types of misalignment and can tolerate localizations error of the intraocular distance.

49 citations

Journal ArticleDOI
TL;DR: In this article, the authors identify and review scientifically validated literature on IoT communication technologies in smart agriculture, and summarize the recent research pertinent to the smart agriculture with IoT communication technology, and provide reference for researchers, and more burgeoning communication technologies should be applied in agriculture to realize the great-leap forward development of smart agriculture.

47 citations