Sumit Srivastava

A comprehensive review on automation of Indian sign language

Hearing impaired people uses signs to communicate with others. Just like verbally spoken languages, there is no universal language as every country has its own spoken language so every country has their own dialect of sign language and in India they uses Indian Sign Language (ISL). In the last few years, researchers take interest in the automation of ISL. Some attempts have been made in India and other countries. In this study we try to explore and analyze the work have been made with automation of sign language and gesture recognition. We tried to explore the challenges comes in the real time sign recognition system. This review also includes the progress of standard corpus creation of the ISL.

Gradient Local Auto-Correlation for handwritten Devanagari character recognition

This manuscript is focus on the utilization of object detection algorithm GLAC (Gradient Local Auto-Correlation) for the handwritten character recognition (HCR) problem. HOG and SIFT are already used in this (HCR) field except GLAC which produced good results than HOG and SIFT for object detection problem like human in images, pedestrian detection and image patch matching. This paper utilized GLAC algorithm to recognize the handwritten Devanagari characters. GLAC applied on two handwritten Devanagari databases, ISIDCHAR and V2DMDCHAR. The images of databases are also normalized with and without preserving aspect ratio. Using GLAC method and SVM classifier, the best results obtained on ISIDCHAR and V2DMDCHAR are 93.21%, 95.21 % respectively that justified the utilization of GLAC algorithm for character recognition problem.

Handwritten Devanagari Character Recognition Using Layer-Wise Training of Deep Convolutional Neural Networks and Adaptive Gradient Methods

Handwritten character recognition is currently getting the attention of researchers because of possible applications in assisting technology for blind and visually impaired users, human–robot interaction, automatic data entry for business documents, etc. In this work, we propose a technique to recognize handwritten Devanagari characters using deep convolutional neural networks (DCNN) which are one of the recent techniques adopted from the deep learning community. We experimented the ISIDCHAR database provided by (Information Sharing Index) ISI, Kolkata and V2DMDCHAR database with six different architectures of DCNN to evaluate the performance and also investigate the use of six recently developed adaptive gradient methods. A layer-wise technique of DCNN has been employed that helped to achieve the highest recognition accuracy and also get a faster convergence rate. The results of layer-wise-trained DCNN are favorable in comparison with those achieved by a shallow technique of handcrafted features and standard DCNN.

Dynamicity of the Himalayan Landslide - A Tectono-Geotechnical Appraisal of the 13 th Mile Landslide, Sikkim

Understanding the causes of slope development with movement initiation of land sliding requires knowledge on dynamicity, displacement, strain concentration and factor of safety. The 13th mile landslide on Gangtok-Nathula road of the Sikkim Himalaya has seriously affected the Indo-China trade route. To quantify the spatial movement pattern, strain analysis and identification of zones of safety were attempted which indicates that differential movement activity of the landslide zone is co-relatable with differential strain pattern with an overall imprint of the Himalaya collision tectonics.

Educational data classification using selective Naïve Bayes for quota categorization

Education data classification is a growing interest in the research of data mining. Correctly identifying the education data into particular category is still presenting challenge because of large and vast amount of features in the dataset. In regards to the existing classifying approaches, Naïve Bayes is potentially good at serving as a classification model due to its simplicity and accuracy. Naive Bayes is one of the most efficient and effective algorithms for data mining. The aim of this paper is to highlight the performance of employing Naïve Bayes in education data classification. The data extracted could be used to Find Meaningful Pattern for the students on the real time problem scenario application to be monitored at college level. Also the model can be used for the future planning of student selection criteria at college level.

Deep ConvNet with Different Stochastic Optimizations for Handwritten Devanagari Character

In this paper, we present a deep learning model to recognize the handwritten Devanagari characters, which is the most popular language in India. This model aims to use the deep convolutional neural networks (DCNN) to eliminate the feature extraction process and the extraction process with the automated feature learning by the deep convolutional neural networks. It also aims to use the different optimizers with deep learning where the deep convolution neural network was trained with different optimizers to observe their role in the enhancement of recognition rate. It is discerned that the proposed model gives a 96.00% recognition accuracy with fifty epochs. The proposed model was trained on the standard handwritten Devanagari characters dataset.

GAE: A Genetic-Based Approach for Software Workflow Improvement by Unhiding Hidden Transactions of a Legacy Application

In organization numbers are increasing day by day with a drastic pace which prefers the extraction of the workflow of processes to interpret the operational processes. For a viably and sorted out approach to drive the development in the realm of digitization is utilized by the approach of work process extraction. The work process extraction/mining is otherwise called process mining. The goal of workflow mining is to get the extraction of data of an association’s method of business by changing over the logs of occasion information recorded in association’s frameworks. This impact to the enhance conformation of processes to organization regulation where workflow mining approach for analysis is actualized. Work process mining strategies absolutely rely upon the nearness of framework occasion log information. We accept to involve setting various endeavors on building our strategies or frameworks to record the greater part of the old information. The urge to comprehend and expand their procedures of businesses entails the process exploration practices. This paper displays a philosophy how programming occasion log information is analyzed to grasp and advance the product work process by utilizing arrangement which best in class utilized as a part of the product code clone streamlining for the human services area application.

Analysis of Online News Popularity and Bank Marketing Using ARSkNN

Data mining is a process of evaluating practice of examining large preexisting databases in order to generate new information. The amount of data has been growing at an enormous rate ever since the development of computers and information technology. Many methods and algorithms have been developed in the last half-century to evaluate data and extract useful information to help develop faster. Due to the wide variety of algorithms and different approaches to evaluate data, several algorithms are compared. The performance of any algorithm on a particular dataset cannot be predicted without evaluating it with the same constraints and parameters. The following paper is a comparison between the trivial kNN algorithm and the newly proposed ARSkNN algorithm on classifying two datasets and subsequently evaluating their performance on average accuracy percentage and average runtime parameters.

GAE: A Novel Approach for Software Workflow Improvement by Unhidding Hidden Transactions

Organizations are increasing day by day at a drastic pace which prefers the extraction of the workflow of processes to interpret the operational processes. For an adequately and sorted out approach to drive the advancement in the realm of digitization is utilized by the approach of work process extraction. The work process extraction/mining is otherwise called process mining. The target of workflow mining is to get the extraction of data of an association’s strategy of business by changing over the logs of occasion information recorded in association’s frameworks. This effect to the improve adaptation of procedures to association direction where work process digging approach for investigation is completed. Work process mining methods absolutely rely upon the nearness of framework occasion log information. We accept to involve setting various endeavors on building our techniques or frameworks to record the greater part of the ancient information. The desire to appreciate and extend the systems of organizations involves the procedure investigation rehearses. This paper shows a procedure how programming occasion log information is inspected to fathom and advance the product work process by utilizing the order which is best in class and utilized as a part of the product code clone streamlining for the medicinal services space application.

Real-Time Bottle Detection Using Histogram of Oriented Gradients

Object detection (Mohan et al. in PAMI, 2001 [1]; Lowe in IJCV 60(2):91–110, 2004 [2]) is one of the pivotal computer vision problems, which is still welcoming new and improved solutions. This area of object detection has seen many attempts made toward the detection of different objects. In this paper, we described a method of bottle detection based on histogram of oriented gradients which proves to be superior to the rest, in terms of both detection rate and error rate when used with a linear SVM classifier. This work is to serve the purpose of water bottle detection and classification in a video feed captured by a robot in the office to serve the needs of person. This will help in automating the servant work and reduce human involvement as well as dependency.