Aritra Das

Bio: Aritra Das is an academic researcher from Jadavpur University. The author has contributed to research in topics: Anaerobic digestion & Biogas. The author has an hindex of 7, co-authored 14 publications receiving 177 citations.

An Obstacle Based Realistic Ad-Hoc Mobility Model for Social Networks

Abstract: An efficient deployment of a mobile ad-hoc network (MANET) requires a realistic approach towards the mobility of the hosts who want to communicate with each other over a wireless channel. Since ad-hoc networks are driven by human requirements, instead of considering the random movement of mobile nodes, we concentrate on the social desire of the nodes for getting connected with one another and provide here a framework for the mobility model of the nodes based on Social Network Theory. In this paper, we capture the preferences in choosing destinations of pedestrian mobility pattern on the basis of Social Factor (Y F ) and try to find out the essential impact of Y F on the Pause Time of the nodes. Also, instead of considering an unobstructed terrain, we carry out our simulations in presence of obstacles which block the node movement. Thus, we present here a more realistic mobility distribution pattern. Further, a relative comparison of the proposed model with the popular Random Way-Point (RWP) Model is also done.

Comparative Kinetic Study of Anaerobic Treatment of Thermally Pretreated Source-Sorted Organic Market Refuse

Abstract: The present study deals with extensive investigations of the effect of thermal pretreatment on whole-sale market rejects for their biogas production potential. Market reject considered as biomass for this study has been treated at two different temperatures 85°C and 135°C for 8 h each and subjected as feedstock for anaerobic digestion (AD) process. The AD process has been operated in the mesophilic range (35–38°C) of bacterial growth. Various kinetic models have been used to simulate the experimental data. Kinetic modeling revealed that biogas production rate exhibited better coefficient of determination () in the range of 0.973–0.989 with exponential model for the ascending limb whereas the descending limb resulted in good linear correlation with as 0.911–0.976. Logistic growth model and Gompertz relation simulation of cumulative biogas production resulted in better values in the range of 0.994–0.997 and 0.998–0.999, whereas the values for exponential rise to maximum plots ranged from 0.722 to 0.800.

Production of Biogas from Treated Sugarcane Bagasse

Abstract: Sugarcane bagasse is available in plenty in and around communities of almost all major and minor places of India. Among all the potential lignocellulosic sources of biogas production sugarcane bagasse was selected for this study related to enhancement of biogas production and minimization of retention time. It was clearly observed that biogas generation response from sugarcane bagasse treated mechanically (A) was maximum both in terms of production rate and ultimate yield of biogas. Alkaline (B) and acid (C) treatment also led to biogas production but their corrosive effect on the sample might have been the possible reason for being less effective in enhancement of biogas yield as compared to that of mechanical treatment. The maximum ultimate yield of biogas was 308.7 ml/gVS (A) followed by 272.6 ml/gVS and 240.2 ml/gVS respectively.

Understanding Deep Learning Techniques for Image Segmentation

Abstract: The machine learning community has been overwhelmed by a plethora of deep learning--based approaches. Many challenging computer vision tasks, such as detection, localization, recognition, and segmentation of objects in an unconstrained environment, are being efficiently addressed by various types of deep neural networks, such as convolutional neural networks, recurrent networks, adversarial networks, and autoencoders. Although there have been plenty of analytical studies regarding the object detection or recognition domain, many new deep learning techniques have surfaced with respect to image segmentation techniques. This article approaches these various deep learning techniques of image segmentation from an analytical perspective. The main goal of this work is to provide an intuitive understanding of the major techniques that have made a significant contribution to the image segmentation domain. Starting from some of the traditional image segmentation approaches, the article progresses by describing the effect that deep learning has had on the image segmentation domain. Thereafter, most of the major segmentation algorithms have been logically categorized with paragraphs dedicated to their unique contribution. With an ample amount of intuitive explanations, the reader is expected to have an improved ability to visualize the internal dynamics of these processes.

Improved Handwritten Digit Recognition Using Convolutional Neural Networks (CNN).

Abstract: Traditional systems of handwriting recognition have relied on handcrafted features and a large amount of prior knowledge. Training an Optical character recognition (OCR) system based on these prerequisites is a challenging task. Research in the handwriting recognition field is focused around deep learning techniques and has achieved breakthrough performance in the last few years. Still, the rapid growth in the amount of handwritten data and the availability of massive processing power demands improvement in recognition accuracy and deserves further investigation. Convolutional neural networks (CNNs) are very effective in perceiving the structure of handwritten characters/words in ways that help in automatic extraction of distinct features and make CNN the most suitable approach for solving handwriting recognition problems. Our aim in the proposed work is to explore the various design options like number of layers, stride size, receptive field, kernel size, padding and dilution for CNN-based handwritten digit recognition. In addition, we aim to evaluate various SGD optimization algorithms in improving the performance of handwritten digit recognition. A network's recognition accuracy increases by incorporating ensemble architecture. Here, our objective is to achieve comparable accuracy by using a pure CNN architecture without ensemble architecture, as ensemble architectures introduce increased computational cost and high testing complexity. Thus, a CNN architecture is proposed in order to achieve accuracy even better than that of ensemble architectures, along with reduced operational complexity and cost. Moreover, we also present an appropriate combination of learning parameters in designing a CNN that leads us to reach a new absolute record in classifying MNIST handwritten digits. We carried out extensive experiments and achieved a recognition accuracy of 99.87% for a MNIST dataset.

Handwritten Optical Character Recognition (OCR): A Comprehensive Systematic Literature Review (SLR)

Abstract: Given the ubiquity of handwritten documents in human transactions, Optical Character Recognition (OCR) of documents have invaluable practical worth. Optical character recognition is a science that enables to translate various types of documents or images into analyzable, editable and searchable data. During last decade, researchers have used artificial intelligence/machine learning tools to automatically analyze handwritten and printed documents in order to convert them into electronic format. The objective of this review paper is to summarize research that has been conducted on character recognition of handwritten documents and to provide research directions. In this Systematic Literature Review (SLR) we collected, synthesized and analyzed research articles on the topic of handwritten OCR (and closely related topics) which were published between year 2000 to 2019. We followed widely used electronic databases by following pre-defined review protocol. Articles were searched using keywords, forward reference searching and backward reference searching in order to search all the articles related to the topic. After carefully following study selection process 176 articles were selected for this SLR. This review article serves the purpose of presenting state of the art results and techniques on OCR and also provide research directions by highlighting research gaps.