Rishav Singh - Academia.edu (original) (raw)

Papers by Rishav Singh

Automated Software Engineering, 2022

Violence detection and face recognition of the individuals involved in the violence has an influe... more Violence detection and face recognition of the individuals involved in the violence has an influence that’s noticeable on the development of automated video surveillance research. With increasing risks in society and insufficient staff to monitor them, there is an expanding demand for drones square measure and computerized video surveillance. Violence detection is expeditious and can be utilized as the method to selectively filter the surveillance videos, and identify or take note of the individual who is creating the anomaly. Individual identification from drone surveillance videos in a crowded area is difficult because of the expeditious movement, overlapping features, and bestrew backgrounds. The goal is to come with a better drone surveillance system that recognizes the violent individuals that are implicated in violence and evoke a distress signal so that fast help can be offered. This paper uses the currently developed techniques based on deep learning and proposed the concept of transfer learning using deep learning-based different hybrid models with LSTM for violence detection. Identifying individuals incriminated in violence from drone-captured images involves major issues in variations of human facial appearance, hence the paper uses a CNN model combined with image processing techniques. For testing, the drone captured video dataset is developed for an unconstrained environment. Ultimately, the features extracted from a hybrid of inception modules and residual blocks, with LSTM architecture yielded an accuracy of 97.33% and thereby proved to be noteworthy and thereby, demonstrating its superiority over other models that have been tested. For the individual identification module, the best accuracy of 99.20% obtained on our dataset, is a CNN model with residual blocks trained for face identification.

IoT-Based Data Analytics for the Healthcare Industry, 2021

Abstract In today’s rapidly changing technology, especially within information and computer techn... more Abstract In today’s rapidly changing technology, especially within information and computer technology (ICT), Internet of Things (IoT) is attracting much attention in literature. Following this tremendous growth, IoT has found a growing interest in the field of healthcare. This is mostly due to the pervasive nature and widespread proliferation of smart devices. In this context and considering patient care, we argue that IoT could leverage existing infrastructure to deliver context dependent and more personalized medical services to a patient. Whether online or offline, we further argue that complementing existing healthcare infrastructure with IoT-enabled services would result in better patient care. However, achieving the objective is easier said than done. This is mainly because IoT-based devices have their own set of constraints. The most prominent ones include heterogeneous communication protocols, unavailability of standard IoT architectures, multidimensional nature of data, and communication overhead. Therefore achieving the goal of having an effective IoT enabled ubiquitous healthcare is still a long way to go. In this chapter, we discuss in detail the potential of IoT in giving personalized medical services and the challenges the e-healthcare industry face at this time. Based on the discussion, we then highlight a potential roadmap to enable a seamless integration of IoT with existing healthcare infrastructure. The need for IoT is also justified in this chapter following the major social changes that this society has witnessed recently. Hence, IoT-based healthcare system is presented in this chapter as the need of the hour and changing lifestyle.

Animal Biometrics, 2017

This chapter presents a brief introduction of the animal biometrics followed by the major charact... more This chapter presents a brief introduction of the animal biometrics followed by the major characteristics, advantages, potential applications, and interdisciplinary relevance of animal biometrics recognition system in the field of ecology. Further, the chapter includes the general framework of animal biometrics recognition systems along with major components for detection and identification of species or individual animal along with some state-of-the-art animal biometrics recognition systems. Furthermore, the chapter introduces the population distribution of different species, technological challenges and recommendations for animal biometrics. Finally the community, communication, data and tool sharing are also included to provide the better collaboration to encourage the multidisciplinary researches in the field of animal biometrics.

Numerous advancements have occurred in impression making for fixed prosthesis in the present cent... more Numerous advancements have occurred in impression making for fixed prosthesis in the present century. Use of improvised materials and sophisticated techniques are propagated only with the aim to record the margins and the gingival tissues properly. The gingival retraction is done to displace the tissues laterally to achieve the desired aim of recording the sub-gingival margins. The purpose of this article is to review the latest advancements in the field of tissue retraction and analyse their merits and demerits. Advancements are a never ending process and will continue to advance day by day. It is our responsibility as a dentist to keep an eye on latest developments, choose the appropriate treatment plan and execute it as precisely as possible.

This chapter presents a novel cattle recognition system using hybrid texture feature of muzzle po... more This chapter presents a novel cattle recognition system using hybrid texture feature of muzzle point pattern for identification and classification of cattle breeds. The major contributions of this research are (1) preparation of muzzle point image database, (2) extraction of hybrid texture features of muzzle point images of cattle dataset, (3) classification of cattle using classification models such as K-nearest neighbor (K-NN), Fuzzy-K-NN, Decision Tree (DT), Gaussian Mixture Model (GMM), Probabilistic Neural Network (PNN), Multilayer Perceptron(MLP), and Naive Bays. In addition, the proposed approach is validated by achieving the state-of-the-art accuracy on muzzle point image database of cattle with standard identification settings.

Over dentures is a preferred treatment option in patients which have to go for extraction of rema... more Over dentures is a preferred treatment option in patients which have to go for extraction of remaining teeth for fabrication of complete dentures earlier. The teeth which are preserved, play a vital role by improvement of crown root ratio, provide proprioception, decrease the rate of resorption and improve support to the denture. Rehabilitation using over dentures is a widely accepted preventive approach due to its ease of fabrication and the successful prognosis. The use of ball and socket type of attachments for improved retention is a novel technique and is becoming popular day by day. The advantage of freedom of rotation it provides makes it user friendly for patients. In this case-report, we have rehabilitated the patient with few remaining teeth with over dentures supported by Preci-Clix attachments.

Numerous advancements have occurred in impression making for fixed prosthesis in the present cent... more Numerous advancements have occurred in impression making for fixed prosthesis in the present century. Use of improvised materials and sophisticated techniques are propagated only with the aim to record the margins and the gingival tissues properly. The gingival retraction is done to displace the tissues laterally to achieve the desired aim of recording the sub-gingival margins. The purpose of this article is to review the latest advancements in the field of tissue retraction and analyse their merits and demerits. Advancements are a never ending process and will continue to advance day by day. It is our responsibility as a dentist to keep an eye on latest developments, choose the appropriate treatment plan and execute it as precisely as possible.

Time series data generation is a standing problem in nearly every field, such as science, busines... more Time series data generation is a standing problem in nearly every field, such as science, business, medicine, industry, or even entertainment. As a result, there is a growing demand for analysing this data efficiently for gauging out useful information. The time series data has intrinsic features like noise, multidimensional, and large volume. When we talk about data mining, it requires a wide spectrum searching for similar patterns, such as query by content, clustering, or classification. These data mining tasks can take great help from a good and robust time series representations. It helps in the reduction of dimensions and noise adaptation and also in achieving key aspect, effectiveness, and efficiency of data processing. This chapter aims to review the basic as well as recent approaches for representations along with dimensionality reduction for time series data.

This chapter presents a brief introduction of the animal biometrics followed by the major charact... more This chapter presents a brief introduction of the animal biometrics followed by the major characteristics, advantages, potential applications, and interdisciplinary relevance of animal biometrics recognition system in the field of ecology. Further, the chapter includes the general framework of animal biometrics recognition systems along with major components for detection and identification of species or individual animal along with some state-of-the-art animal biometrics recognition systems. Furthermore, the chapter introduces the population distribution of different species, technological challenges and recommendations for animal biometrics. Finally the community, communication, data and tool sharing are also included to provide the better collaboration to encourage the multidisciplinary researches in the field of animal biometrics.

With the arrival of adequate computer vision techniques, animal biometrics-based recognition syst... more With the arrival of adequate computer vision techniques, animal biometrics-based recognition systems have accomplished attention for the identification and monitoring of jeopardized species and individual animal. In this chapter, a novel fisher locality preserving projection-based cattle recognition framework is proposed for extraction and representation of cattle identification in real time. The biometric muzzle point image of cattle is captured using the surveillance camera and transferred them to the server of cattle recognition framework by using wireless network technology. The motivation of proposed method is to maximize the inter-class (between-class) scatter feature matrix of the muzzle point image and efficiently minimize the intra-class (within-class) scatter matrix of muzzle point images. This strategy of proposed method improves the accuracy of cattle identification. The efficacy of proposed recognition approach for cattle is estimated under different identification sett...

2021 Thirteenth International Conference on Contemporary Computing (IC3-2021), 2021

IEEE Internet of Things Journal, 2021

The Internet of Things (IoT) is one of the fastest growing areas of research. Considering the IoT... more The Internet of Things (IoT) is one of the fastest growing areas of research. Considering the IoT and healthcare simultaneously, classifying brain signals using smart IoT sensors is one of the standing nontrivial problems of literature. The issue is further exacerbated by noise in brain signals, and there is no efficient solution for classifying brain signals as seizorous or nonseizorous, yet. Moreover, research has mostly ignored the security and privacy aspect of this problem. Therefore, in this article, we try to bridge this gap and present a secure privacy-preserving technique for brain signal classification. We first transform a brain signal into an image. Subsequently, we apply transfer learning to solve the classification problem. To do that, we use the pretrained VGG-19 as a base model. In addition, we discuss a scheme to store images in a blockchain so as to make the overall architecture privacy aware. By conducting comprehensive numerical simulations on a supercomputer and using the famous TUH Abnormal EEG data set, we show the efficacy of the proposed work. The work presented here not only makes the storage of patient data secure and private but also outperforms all existing techniques in terms of classification accuracy.

Pattern Recognition, 2021

IEEE Sensors Journal, 2020

The advancement in sensing technology has enabled the development of various applications for act... more The advancement in sensing technology has enabled the development of various applications for activity recognition using smartphone sensor data. One of the useful applications in an intelligent transportation system is the identification of transportation mode to provide context-aware assistance for the execution of systems such as driver assistant. Such real-time critical systems demand the early detection of transportation mode for making effective decisions. This paper proposes a method to detect the transportation mode at an early stage by achieving a decent trade-off between accuracy and earliness based on partially observed sensory time series data. As a result, a hybrid deep learning classifier is developed by utilizing the capabilities of the convolutional neural network, recurrent neural network, and deep neural network to learn the hidden temporal correlation of pattern information for the sensory data. In addition, a decision policy is defined on top of the classifier to perform the transportation mode prediction for the incoming time series by attaining acceptable trade-off. The proposed model is evaluated using two publicly available supervised datasets and demonstrated good performance in terms of accuracy and earliness. Also, the model is compared with the existing alternative for verifying the effectiveness.

Journal of Ambient Intelligence and Humanized Computing, 2019

This article focuses on identifying tiny faces in thermal images using transfer learning. Althoug... more This article focuses on identifying tiny faces in thermal images using transfer learning. Although the issue of identifying faces in images is not new, the problem of tiny face identification is a recently identified research area. Indeed challenging, however, in this paper, we take the problem one step ahead and focus on recognizing tiny faces in thermal images. To do that, we use the paradigm of transfer learning. We use the famous residual network to extract the features in the target domain. Subsequently, with this model as a reference point, we then retrain it in the target domain of thermal images. Through testing performed in Terravic datasets, we have found that the method outperforms existing methods in literature to identify tiny faces in thermal images.

The Journal of Contemporary Dental Practice, 2017

ABSTRACTAimThe aim of this study is to describe the protocol used in the treatment of pulpally ne... more ABSTRACTAimThe aim of this study is to describe the protocol used in the treatment of pulpally necrosed primary molars and to evaluate the effectiveness of ultrasonic instrumentation technique in primary dentition.Materials and methodsA total of 50 primary molars in 40 children, ranging from 8 to 10 years of age, were endodontically treated using standard protocols and ultrasonic instrumentation. The follow-up was done for each case ranging from 1 to 2½ years.ResultsClinical and radiographic controls showed a success rate of 97.5%, considering an evaluation time of 19 ± 9.02 months.ConclusionThe use of ultrasonic instrumentation in primary molars with pulpal necrosis succeeded in reducing appointment time and showed a high success rate.Clinical significanceUltrasonic instrumentation should be used as a standard protocol in instrumentation of endodontic treatment of primary molars so as to increase the success rate of primary teeth pulpectomies.How to cite this articleSingh R, Barua ...

The Journal of Contemporary Dental Practice, 2017

Aim: The present study is undertaken to examine the film thickness of three most commonly used lu... more Aim: The present study is undertaken to examine the film thickness of three most commonly used luting cements and to determine their usage as a luting agent. Materials and methods: This study was carried out strictly according to the guidelines of American Dental Association (ADS) specification no. 8. Two glass slabs of 5 cm in length and 2 cm in width were used. One glass slab was kept over the other glass slab and the space between the two glass slabs was measured using metallurgical microscope at the power of 10×. Two brands of glass ionomer cement (GIC) and one dualcured resin cement were used in this study. The test cement is sandwiched between two glass slabs. A static load of 15 kg was applied using universal testing machine on the glass slabs for 1 hour and the space present between the two glass slabs was measured using metallurgical microscope at the power of 10×. Results: Greatest film thickness was found in group III (Paracore) followed by group II (micron) and lowest in group I

Journal of International Society of Preventive & Community Dentistry

Discrimination by some health care workers, including dentists, against human immunodeficiency vi... more Discrimination by some health care workers, including dentists, against human immunodeficiency virus (HIV) infected persons has been noted. The main aim of the present study was to assess the knowledge, attitude, and practice towards HIV patients among the dentists of Trichur district, Kerala. A cross-sectional survey was conducted among 206 dentists practicing in Trichur district of Kerala. Data was collected using a pretested, self-administered 26-item questionnaire and was statistically analyzed using SPSS software version 20. Out of 206 participants, 39.3% were unwilling to treat HIV patients. A statistical significance was found between willingness to treat HIV infected patients and age groups (P = 0.0001) as well as between the willingness to treat HIV infected patients and ethical responsibility (P = 0.0001). Staff fears and increased personal risk are found to be the most frequently reported concerns in treating HIV patients among dentists of Trichur district, Kerala. Senior...

Multimedia Tools and Applications, 2017

Development of expertise in Face Recognition has led researchers to apply its various techniques ... more Development of expertise in Face Recognition has led researchers to apply its various techniques for newborn recognition as some of the problems such as swapping, kidnapping are still prevalent. The paper proposes to apply Deep Convolutional Neural Network(CNN) to IIT(BHU) newborn database. The database has its own advantages where the quality of images is high and segregation has been done for various expressions of newborn. The Deep CNN applied in this paper is more advantageous when compared to regular MLP. Along with this the results taken from application of proposed technique have been compared to state-of-the-art technique applied on the same database and it shows improved results. It has been found Deep CNN improves PCA by 22.09%, LDA by 12.98%, ICA by 11.35%, LBP by 17.08% and SURF by 10.8% for Neutral-Neutral faces. Along with this results have also been gathered to understand which Deep CNN architecture is most suitable for the database. The CNN architecture with 2 convolutional layers and 1 hidden layer is the best solution. The results have also been cross validated using 10-fold cross validation.

Multimedia Tools and Applications, 2017

With the increasing number of the images, how to effectively manage and use these images becomes ... more With the increasing number of the images, how to effectively manage and use these images becomes an urgent problem to be solved. The classification of the images is one of the effective ways to manage and retrieve images. In this paper, we propose a novel large-scale multimedia image data classification algorithm based on deep learning. We firstly select the image characteristics to represent the flag for retrieval, which represents the color, texture and shape characteristics respectively. A feature of color is the most basic image data, mainly including the average brightness, color histogram and dominant color, etc. What the texture refers to is the image data in the anomalous, macroscopic as well as orderly one key character that on partial has. The contour feature extraction of image data needs to rely on the edge detection, edge of the detected edge through the connection or grouping to form a meaningful image event. Secondly, we revise the convolutional neural network model based on the pooling operation optimization, the pooling is in the process of the convolution operation to extract the image characteristics of the different locations to gather statistics. Furthermore, we integrate the parallel and could storage strategy to enhance the efficiency of the proposed methodology. The performance of the algorithm is verified, compared with the other state-ofthe-art approaches, the proposed one obtains the better efficiency and accuracy.

Automated Software Engineering, 2022

Violence detection and face recognition of the individuals involved in the violence has an influe... more Violence detection and face recognition of the individuals involved in the violence has an influence that’s noticeable on the development of automated video surveillance research. With increasing risks in society and insufficient staff to monitor them, there is an expanding demand for drones square measure and computerized video surveillance. Violence detection is expeditious and can be utilized as the method to selectively filter the surveillance videos, and identify or take note of the individual who is creating the anomaly. Individual identification from drone surveillance videos in a crowded area is difficult because of the expeditious movement, overlapping features, and bestrew backgrounds. The goal is to come with a better drone surveillance system that recognizes the violent individuals that are implicated in violence and evoke a distress signal so that fast help can be offered. This paper uses the currently developed techniques based on deep learning and proposed the concept of transfer learning using deep learning-based different hybrid models with LSTM for violence detection. Identifying individuals incriminated in violence from drone-captured images involves major issues in variations of human facial appearance, hence the paper uses a CNN model combined with image processing techniques. For testing, the drone captured video dataset is developed for an unconstrained environment. Ultimately, the features extracted from a hybrid of inception modules and residual blocks, with LSTM architecture yielded an accuracy of 97.33% and thereby proved to be noteworthy and thereby, demonstrating its superiority over other models that have been tested. For the individual identification module, the best accuracy of 99.20% obtained on our dataset, is a CNN model with residual blocks trained for face identification.

IoT-Based Data Analytics for the Healthcare Industry, 2021

Abstract In today’s rapidly changing technology, especially within information and computer techn... more Abstract In today’s rapidly changing technology, especially within information and computer technology (ICT), Internet of Things (IoT) is attracting much attention in literature. Following this tremendous growth, IoT has found a growing interest in the field of healthcare. This is mostly due to the pervasive nature and widespread proliferation of smart devices. In this context and considering patient care, we argue that IoT could leverage existing infrastructure to deliver context dependent and more personalized medical services to a patient. Whether online or offline, we further argue that complementing existing healthcare infrastructure with IoT-enabled services would result in better patient care. However, achieving the objective is easier said than done. This is mainly because IoT-based devices have their own set of constraints. The most prominent ones include heterogeneous communication protocols, unavailability of standard IoT architectures, multidimensional nature of data, and communication overhead. Therefore achieving the goal of having an effective IoT enabled ubiquitous healthcare is still a long way to go. In this chapter, we discuss in detail the potential of IoT in giving personalized medical services and the challenges the e-healthcare industry face at this time. Based on the discussion, we then highlight a potential roadmap to enable a seamless integration of IoT with existing healthcare infrastructure. The need for IoT is also justified in this chapter following the major social changes that this society has witnessed recently. Hence, IoT-based healthcare system is presented in this chapter as the need of the hour and changing lifestyle.

Animal Biometrics, 2017

This chapter presents a brief introduction of the animal biometrics followed by the major charact... more This chapter presents a brief introduction of the animal biometrics followed by the major characteristics, advantages, potential applications, and interdisciplinary relevance of animal biometrics recognition system in the field of ecology. Further, the chapter includes the general framework of animal biometrics recognition systems along with major components for detection and identification of species or individual animal along with some state-of-the-art animal biometrics recognition systems. Furthermore, the chapter introduces the population distribution of different species, technological challenges and recommendations for animal biometrics. Finally the community, communication, data and tool sharing are also included to provide the better collaboration to encourage the multidisciplinary researches in the field of animal biometrics.

Numerous advancements have occurred in impression making for fixed prosthesis in the present cent... more Numerous advancements have occurred in impression making for fixed prosthesis in the present century. Use of improvised materials and sophisticated techniques are propagated only with the aim to record the margins and the gingival tissues properly. The gingival retraction is done to displace the tissues laterally to achieve the desired aim of recording the sub-gingival margins. The purpose of this article is to review the latest advancements in the field of tissue retraction and analyse their merits and demerits. Advancements are a never ending process and will continue to advance day by day. It is our responsibility as a dentist to keep an eye on latest developments, choose the appropriate treatment plan and execute it as precisely as possible.

This chapter presents a novel cattle recognition system using hybrid texture feature of muzzle po... more This chapter presents a novel cattle recognition system using hybrid texture feature of muzzle point pattern for identification and classification of cattle breeds. The major contributions of this research are (1) preparation of muzzle point image database, (2) extraction of hybrid texture features of muzzle point images of cattle dataset, (3) classification of cattle using classification models such as K-nearest neighbor (K-NN), Fuzzy-K-NN, Decision Tree (DT), Gaussian Mixture Model (GMM), Probabilistic Neural Network (PNN), Multilayer Perceptron(MLP), and Naive Bays. In addition, the proposed approach is validated by achieving the state-of-the-art accuracy on muzzle point image database of cattle with standard identification settings.

Over dentures is a preferred treatment option in patients which have to go for extraction of rema... more Over dentures is a preferred treatment option in patients which have to go for extraction of remaining teeth for fabrication of complete dentures earlier. The teeth which are preserved, play a vital role by improvement of crown root ratio, provide proprioception, decrease the rate of resorption and improve support to the denture. Rehabilitation using over dentures is a widely accepted preventive approach due to its ease of fabrication and the successful prognosis. The use of ball and socket type of attachments for improved retention is a novel technique and is becoming popular day by day. The advantage of freedom of rotation it provides makes it user friendly for patients. In this case-report, we have rehabilitated the patient with few remaining teeth with over dentures supported by Preci-Clix attachments.

Numerous advancements have occurred in impression making for fixed prosthesis in the present cent... more Numerous advancements have occurred in impression making for fixed prosthesis in the present century. Use of improvised materials and sophisticated techniques are propagated only with the aim to record the margins and the gingival tissues properly. The gingival retraction is done to displace the tissues laterally to achieve the desired aim of recording the sub-gingival margins. The purpose of this article is to review the latest advancements in the field of tissue retraction and analyse their merits and demerits. Advancements are a never ending process and will continue to advance day by day. It is our responsibility as a dentist to keep an eye on latest developments, choose the appropriate treatment plan and execute it as precisely as possible.

Time series data generation is a standing problem in nearly every field, such as science, busines... more Time series data generation is a standing problem in nearly every field, such as science, business, medicine, industry, or even entertainment. As a result, there is a growing demand for analysing this data efficiently for gauging out useful information. The time series data has intrinsic features like noise, multidimensional, and large volume. When we talk about data mining, it requires a wide spectrum searching for similar patterns, such as query by content, clustering, or classification. These data mining tasks can take great help from a good and robust time series representations. It helps in the reduction of dimensions and noise adaptation and also in achieving key aspect, effectiveness, and efficiency of data processing. This chapter aims to review the basic as well as recent approaches for representations along with dimensionality reduction for time series data.

This chapter presents a brief introduction of the animal biometrics followed by the major charact... more This chapter presents a brief introduction of the animal biometrics followed by the major characteristics, advantages, potential applications, and interdisciplinary relevance of animal biometrics recognition system in the field of ecology. Further, the chapter includes the general framework of animal biometrics recognition systems along with major components for detection and identification of species or individual animal along with some state-of-the-art animal biometrics recognition systems. Furthermore, the chapter introduces the population distribution of different species, technological challenges and recommendations for animal biometrics. Finally the community, communication, data and tool sharing are also included to provide the better collaboration to encourage the multidisciplinary researches in the field of animal biometrics.

With the arrival of adequate computer vision techniques, animal biometrics-based recognition syst... more With the arrival of adequate computer vision techniques, animal biometrics-based recognition systems have accomplished attention for the identification and monitoring of jeopardized species and individual animal. In this chapter, a novel fisher locality preserving projection-based cattle recognition framework is proposed for extraction and representation of cattle identification in real time. The biometric muzzle point image of cattle is captured using the surveillance camera and transferred them to the server of cattle recognition framework by using wireless network technology. The motivation of proposed method is to maximize the inter-class (between-class) scatter feature matrix of the muzzle point image and efficiently minimize the intra-class (within-class) scatter matrix of muzzle point images. This strategy of proposed method improves the accuracy of cattle identification. The efficacy of proposed recognition approach for cattle is estimated under different identification sett...

2021 Thirteenth International Conference on Contemporary Computing (IC3-2021), 2021

IEEE Internet of Things Journal, 2021

The Internet of Things (IoT) is one of the fastest growing areas of research. Considering the IoT... more The Internet of Things (IoT) is one of the fastest growing areas of research. Considering the IoT and healthcare simultaneously, classifying brain signals using smart IoT sensors is one of the standing nontrivial problems of literature. The issue is further exacerbated by noise in brain signals, and there is no efficient solution for classifying brain signals as seizorous or nonseizorous, yet. Moreover, research has mostly ignored the security and privacy aspect of this problem. Therefore, in this article, we try to bridge this gap and present a secure privacy-preserving technique for brain signal classification. We first transform a brain signal into an image. Subsequently, we apply transfer learning to solve the classification problem. To do that, we use the pretrained VGG-19 as a base model. In addition, we discuss a scheme to store images in a blockchain so as to make the overall architecture privacy aware. By conducting comprehensive numerical simulations on a supercomputer and using the famous TUH Abnormal EEG data set, we show the efficacy of the proposed work. The work presented here not only makes the storage of patient data secure and private but also outperforms all existing techniques in terms of classification accuracy.

Pattern Recognition, 2021

IEEE Sensors Journal, 2020

The advancement in sensing technology has enabled the development of various applications for act... more The advancement in sensing technology has enabled the development of various applications for activity recognition using smartphone sensor data. One of the useful applications in an intelligent transportation system is the identification of transportation mode to provide context-aware assistance for the execution of systems such as driver assistant. Such real-time critical systems demand the early detection of transportation mode for making effective decisions. This paper proposes a method to detect the transportation mode at an early stage by achieving a decent trade-off between accuracy and earliness based on partially observed sensory time series data. As a result, a hybrid deep learning classifier is developed by utilizing the capabilities of the convolutional neural network, recurrent neural network, and deep neural network to learn the hidden temporal correlation of pattern information for the sensory data. In addition, a decision policy is defined on top of the classifier to perform the transportation mode prediction for the incoming time series by attaining acceptable trade-off. The proposed model is evaluated using two publicly available supervised datasets and demonstrated good performance in terms of accuracy and earliness. Also, the model is compared with the existing alternative for verifying the effectiveness.

Journal of Ambient Intelligence and Humanized Computing, 2019

This article focuses on identifying tiny faces in thermal images using transfer learning. Althoug... more This article focuses on identifying tiny faces in thermal images using transfer learning. Although the issue of identifying faces in images is not new, the problem of tiny face identification is a recently identified research area. Indeed challenging, however, in this paper, we take the problem one step ahead and focus on recognizing tiny faces in thermal images. To do that, we use the paradigm of transfer learning. We use the famous residual network to extract the features in the target domain. Subsequently, with this model as a reference point, we then retrain it in the target domain of thermal images. Through testing performed in Terravic datasets, we have found that the method outperforms existing methods in literature to identify tiny faces in thermal images.

The Journal of Contemporary Dental Practice, 2017

ABSTRACTAimThe aim of this study is to describe the protocol used in the treatment of pulpally ne... more ABSTRACTAimThe aim of this study is to describe the protocol used in the treatment of pulpally necrosed primary molars and to evaluate the effectiveness of ultrasonic instrumentation technique in primary dentition.Materials and methodsA total of 50 primary molars in 40 children, ranging from 8 to 10 years of age, were endodontically treated using standard protocols and ultrasonic instrumentation. The follow-up was done for each case ranging from 1 to 2½ years.ResultsClinical and radiographic controls showed a success rate of 97.5%, considering an evaluation time of 19 ± 9.02 months.ConclusionThe use of ultrasonic instrumentation in primary molars with pulpal necrosis succeeded in reducing appointment time and showed a high success rate.Clinical significanceUltrasonic instrumentation should be used as a standard protocol in instrumentation of endodontic treatment of primary molars so as to increase the success rate of primary teeth pulpectomies.How to cite this articleSingh R, Barua ...

The Journal of Contemporary Dental Practice, 2017

Aim: The present study is undertaken to examine the film thickness of three most commonly used lu... more Aim: The present study is undertaken to examine the film thickness of three most commonly used luting cements and to determine their usage as a luting agent. Materials and methods: This study was carried out strictly according to the guidelines of American Dental Association (ADS) specification no. 8. Two glass slabs of 5 cm in length and 2 cm in width were used. One glass slab was kept over the other glass slab and the space between the two glass slabs was measured using metallurgical microscope at the power of 10×. Two brands of glass ionomer cement (GIC) and one dualcured resin cement were used in this study. The test cement is sandwiched between two glass slabs. A static load of 15 kg was applied using universal testing machine on the glass slabs for 1 hour and the space present between the two glass slabs was measured using metallurgical microscope at the power of 10×. Results: Greatest film thickness was found in group III (Paracore) followed by group II (micron) and lowest in group I

Journal of International Society of Preventive & Community Dentistry

Discrimination by some health care workers, including dentists, against human immunodeficiency vi... more Discrimination by some health care workers, including dentists, against human immunodeficiency virus (HIV) infected persons has been noted. The main aim of the present study was to assess the knowledge, attitude, and practice towards HIV patients among the dentists of Trichur district, Kerala. A cross-sectional survey was conducted among 206 dentists practicing in Trichur district of Kerala. Data was collected using a pretested, self-administered 26-item questionnaire and was statistically analyzed using SPSS software version 20. Out of 206 participants, 39.3% were unwilling to treat HIV patients. A statistical significance was found between willingness to treat HIV infected patients and age groups (P = 0.0001) as well as between the willingness to treat HIV infected patients and ethical responsibility (P = 0.0001). Staff fears and increased personal risk are found to be the most frequently reported concerns in treating HIV patients among dentists of Trichur district, Kerala. Senior...

Multimedia Tools and Applications, 2017

Development of expertise in Face Recognition has led researchers to apply its various techniques ... more Development of expertise in Face Recognition has led researchers to apply its various techniques for newborn recognition as some of the problems such as swapping, kidnapping are still prevalent. The paper proposes to apply Deep Convolutional Neural Network(CNN) to IIT(BHU) newborn database. The database has its own advantages where the quality of images is high and segregation has been done for various expressions of newborn. The Deep CNN applied in this paper is more advantageous when compared to regular MLP. Along with this the results taken from application of proposed technique have been compared to state-of-the-art technique applied on the same database and it shows improved results. It has been found Deep CNN improves PCA by 22.09%, LDA by 12.98%, ICA by 11.35%, LBP by 17.08% and SURF by 10.8% for Neutral-Neutral faces. Along with this results have also been gathered to understand which Deep CNN architecture is most suitable for the database. The CNN architecture with 2 convolutional layers and 1 hidden layer is the best solution. The results have also been cross validated using 10-fold cross validation.

Multimedia Tools and Applications, 2017

With the increasing number of the images, how to effectively manage and use these images becomes ... more With the increasing number of the images, how to effectively manage and use these images becomes an urgent problem to be solved. The classification of the images is one of the effective ways to manage and retrieve images. In this paper, we propose a novel large-scale multimedia image data classification algorithm based on deep learning. We firstly select the image characteristics to represent the flag for retrieval, which represents the color, texture and shape characteristics respectively. A feature of color is the most basic image data, mainly including the average brightness, color histogram and dominant color, etc. What the texture refers to is the image data in the anomalous, macroscopic as well as orderly one key character that on partial has. The contour feature extraction of image data needs to rely on the edge detection, edge of the detected edge through the connection or grouping to form a meaningful image event. Secondly, we revise the convolutional neural network model based on the pooling operation optimization, the pooling is in the process of the convolution operation to extract the image characteristics of the different locations to gather statistics. Furthermore, we integrate the parallel and could storage strategy to enhance the efficiency of the proposed methodology. The performance of the algorithm is verified, compared with the other state-ofthe-art approaches, the proposed one obtains the better efficiency and accuracy.