Dinesh Reddy - Academia.edu (original) (raw)

Papers by Dinesh Reddy

Lecture Notes in Mechanical Engineering

Detecting multiple planes in images is a challenging problem, but one with many applications. Rec... more Detecting multiple planes in images is a challenging problem, but one with many applications. Recent work such as J-Linkage and Ordered Residual Kernels have focussed on developing a domain independent approach to detect multiple structures. These multiple structure detection methods are then used for estimating multiple homographies given feature matches between two images. Features participating in the multiple homographies detected, provide us the multiple scene planes. We show that these methods provide locally optimal results and fail to merge detected planar patches to the true scene planes. These methods use only residues obtained on applying homography of one plane to another as cue for merging. In this paper, we develop additional cues such as local consistency of planes, local normals, texture etc. to perform better classification and merging. We formulate the classification as an MRF problem and use TRWS message passing algorithm to solve non metric energy terms and complex sparse graph structure. We show results on challenging dataset common in robotics navigation scenarios where our method shows accuracy of more than 85 percent on average while being close or same as the actual number of scene planes.

International Journal of Innovative Research in Advanced Engineering

By providing immediate monitoring of commodities, people, the environment, and property, video su... more By providing immediate monitoring of commodities, people, the environment, and property, video surveillance has established its significance and advantages as a crucial part of many organizations' security and safety concerns. The goal of this project is to build an Embedded Real-Time Surveillance System (ERTSS) based on the Raspberry Pi SBC for intruder detection, which improves surveillance technology and provides essential security for our daily life. The suggested security system is built on our ground-breaking integration of cameras and motion detectors into a web application. The Raspberry Pi runs and manages motion sensors and cameras for remote sensing and monitoring, sends live footage, and records it for later replay. The goal of this study is to develop a surveillance system that can recognize strangers and act fast by taking pictures and sending them to a wireless owner-based module. Additionally, this project will show how to detect and track motion using image proc...

Past research on Self-efficacy in information security gives clues about the failure of individua... more Past research on Self-efficacy in information security gives clues about the failure of individuals with high Self-efficacy in information security to exhibit high compliance to information security. This is evidenced by research results that show a negative correlation between Self-efficacy in information security and compliance behavior (Tsai et al. 2016), although there are research results from many papers that show a positive correlation between Self-efficacy in information security and compliance behavior (Sommestad et al. 2014). Tsai et al. (2016) also had many factors positively influencing Self-efficacy in information security such as threat severity, threat vulnerability, safety habit strength, personal responsibility, and perceived security support. So, it is highly curious to know the context and situations in which individuals with high Self-efficacy in information security exhibit low compliance to information security. There may be a pointer to individual personality ...

Indian Journal of Urology, 2021

Posterior urethral valves have myriad presentations based on the severity of obstruction with the... more Posterior urethral valves have myriad presentations based on the severity of obstruction with the milder end of spectrum often termed as mini-valves. The simultaneous occurrence of ureteropelvic junction obstruction and urethral valves has not been described before and is most likely coincidental. Herein, we discuss the management of three boys who had febrile urinary tract infection following pyeloplasty and on evaluation were found to have valves. This article highlights the need for considering these mini-valves as a possibility in boys presenting with symptoms following pyeloplasty so as to avoid delay in diagnosis and unnecessary morbidity in these children.

Open Forum Infectious Diseases, 2021

Background Sleeping sickness is an infectious disease transmitted mainly by the Trypanosoma Bruce... more Background Sleeping sickness is an infectious disease transmitted mainly by the Trypanosoma Brucei, with the tsetse fly as a vector. The condition has two stages: The hemolymphatic and the meningo-encephalitic stage. The second stage is caused mainly by the Trypanosoma Brucei Gambiense. The treatment of the second stage has changed from melarsoprol, eflornithine, to now nifurtimox-eflornithine (NECT). This systematic review will focus on the efficacy and the toxicity of the medication. Methods We use PRISMA and MOOSE protocol for this review. On figure 1, we detail the methodology used for the extraction of information from the systematic review. To assess the study's bias, we used Cochrane Collaboration’s tool for risk assessment of the clinical trials and the Robins I tool for the observational studies. Results We collected four clinical trials and two observational studies after an extensive search. Three clinical trials showed that NECT was non-inferior to eflornithine with ...

YMER Digital, 2021

Looking at the environmental hazards being posed by indiscriminate use of synthetic plastics, abu... more Looking at the environmental hazards being posed by indiscriminate use of synthetic plastics, abundant research is being done to explore various bio-degradable polymers. In the present study, Cellulose Nano Fibers (CNFs) were extracted from Pineapple Crown using mechano chemical treatment, PLA was synthesized by Simultaneous Saccharification and Fermentation using cellulase enzyme on Acacia Arabica as substrate. Further, ZnO nanoparticles were synthesized by using different precursors. The biocomposite sheets of PLA, PLA+ 5%-20% CNFs, PLA+5% ZnO+5-20 % CNFs and PLA+10% ZnO+5-20 % CNFs were solvent casted. Microbial efficacy test was done using E.coli and with inclusion of ZnO nanoparticles the microbial resistance has increased. Noteworthy vibration band of the sheets were observed in the wavelength range of 3700 to 2800 cm-1 from the FTIR analysis, which shows that there is only a physical interaction rather than chemical. The crystallinity increased for initial concentration, but ...

In this paper, we present a crowdsourced dataset which adds entity salience (importance) annotati... more In this paper, we present a crowdsourced dataset which adds entity salience (importance) annotations to the Reuters-128 dataset, which is subset of Reuters-21578. The dataset is distributed under a free license and publish in the NLP Interchange Format, which fosters interoperability and re-use. We show the potential of the dataset on the task of learning an entity salience classifier and report on the results from several experiments.

Proceedings of the 2017 ACM SIGMIS Conference on Computers and People Research, 2017

Self-efficacy in information security (SEIS) is one of the most researched predictors of end user... more Self-efficacy in information security (SEIS) is one of the most researched predictors of end user security behavior that hinges on end user acceptance and use of the protective technologies such as anti-virus and anti-spyware. SEIS is also modeled as a mediator between factors affecting SEIS and the end user cybersecurity behavior. However, it is not clearly established in past literature on whether SEIS is better modeled as a predictor or as a mediator. It is stressed in literature that we should find new ways to improve SEIS. Accordingly, the purpose of this research is to empirically investigate what factors influence SEIS, and to examine the relative effect of each theorized factor (including self-efficacy) in increasing information security.

We tackle the problem of reconstructing moving vehicles in autonomous driving scenarios using onl... more We tackle the problem of reconstructing moving vehicles in autonomous driving scenarios using only a monocular camera. Though the problem appears to be ill-posed, we demonstrate that prior knowledge about how 3D shapes of vehicles project to an image can be used to reason about the reverse process, i.e., how shapes (back-)project from 2D to 3D. We encode this knowledge in shape priors, which are learnt over a small dataset comprising of annotated RGB images of vehicles. Each shape prior comprises of a deformable wireframe model whose vertices are semantically unique keypoints of that vehicle. The first contribution is an approach for reconstructing vehicles from just a single (RGB) image. To obtain a 3D wireframe representing the shape, we first localize the vertices of the wireframe (keypoints) in 2D using a Convolutional Neural Network (CNN). We then formulate a shape-aware optimization problem that uses the learnt shape priors to lift the detected 2D keypoints to 3D, thereby reco...

Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, 2017

Dynamic scene understanding is a challenging problem and motion segmentation plays a crucial role... more Dynamic scene understanding is a challenging problem and motion segmentation plays a crucial role in solving it. Incorporating semantics and motion enhances the overall perception of the dynamic scene. For applications of outdoor robotic navigation, joint learning methods have not been extensively used for extracting spatiotemporal features or adding different priors into the formulation. The task becomes even more challenging without stereo information being incorporated. This paper proposes an approach to fuse semantic features and motion clues using CNNs, to address the problem of monocular semantic motion segmentation. We deduce semantic and motion labels by integrating optical flow as a constraint with semantic features into dilated convolution network. The pipeline consists of three main stages i.e Feature extraction, Feature amplification and Multi Scale Context Aggregation to fuse the semantics and flow features. Our joint formulation shows significant improvements in monocular motion segmentation over the state of the art methods on challenging KITTI tracking dataset. Deep learning architectures used for scene understanding incorporate semantic labels for learning

The outcome of the effect of Self-efficacy in information security (SEIS) on compliance to secure... more The outcome of the effect of Self-efficacy in information security (SEIS) on compliance to secure behavior has been positive to most extent. However, in some studies, the relationship between SEIS and compliance has shown a negative effect, thus signaling mixed results. The importance of unlocking this mixed result is significant since any proven deviation in results (about the effect of SEIS on compliance) will challenge the past empirical findings. Past research has ignored to explain why the results of the effect of SEIS on compliance are mixed. In this article, we explore the multi level nature of SEIS, measurement process involved, and context specific conceptualizations of SEIS as possible reasons that explain the reversal of security behavior. This research will guide future research on what could cause people with high SEIS to not exhibit secure compliance behavior, where SEIS and compliance are more often modeled in behavioral security research

: Many researchers are attempting to develop an alternative fuel which is economical, environment... more : Many researchers are attempting to develop an alternative fuel which is economical, environment friendly and a simple technology which is easy to understand and to implement. From the studies of many researchers we came to know that, biofuels are having the potential to serve as a fuel in compression ignition engine. In this review studies of various research pertaining to Oxidation stability of biodiesel is presented in detail. As oxidation stability is one of the major drawback in bringing biodiesel to main stream this review will assist in understanding this problem along with that also provides various solutions to overcome this problem.

Imperial journal of interdisciplinary research, 2017

Background: Tuberculosis continues to be major health problem in India. In India, under the Revis... more Background: Tuberculosis continues to be major health problem in India. In India, under the Revised National Tuberculosis Control Program (RNTCP), the percentage of smear-positive re-treatment cases out of all smear-positive cases is 24%.The Revised National Tuberculosis Programme (RNTCP), was launched in 1997 needs continuous evaluation. India alone accounts for approximately 1/5th of total global tuberculosis incidence. Every year 1.8 million new cases occur in India of which 0.8 million are infectious. Aims: Compare Prevalence of relapse tuberculosis in two different regimen of Anti-tubercular treatment. Materials and Methods: Its Prospective observational study .we have conducted study on 39 patients diagnosed to have relapse pulmonary tuberculosis on sputum and chest x-ray basis in Respiratory Medicine Department of Dhiraj Hospital, Vadodara. We have asked detailed past history regarding Anti-tubercular treatment and divided the two groups government and private all declared ...

Cybersecurity threat is one of the major national security challenges confronting the United Stat... more Cybersecurity threat is one of the major national security challenges confronting the United States, making it imperative to achieve safe user security behavior on information systems. Safe user security behavior hinges on the attitude of a computer user to accept the usage of Protective information technologies (PIT), including security software. Past studies focused on user acceptance of PIT with antecedents such as usefulness, capabilities, and self-efficacy but rarely addressed specific cybersecurity skills needed to improve the user attitude and acceptance of security software use. The purpose of this study is to examine what category of cybersecurity skills can improve the user acceptance of PIT. We propose a theoretical model that examines the effect of cybersecurity computing skills, cybersecurity initiative skills and cybersecurity action skills on user attitude and acceptance of PIT. This research addresses the national cybersecurity threat and has both theoretical and pra...

Prof. Srinivasa Narasimhan School of Computer Science

In order to effectively combat cybersercurity threats at home and in organizations, it is imperat... more In order to effectively combat cybersercurity threats at home and in organizations, it is imperative to achieve higher end-user cybersecurity compliance. Cybersecurity training is generally accepted as a means to increase compliance behavior. Training can influence compliance by one or more of three causal pathways: by increasing cybersecurity awareness, by increasing cybersecurity proficiency (i.e., improve cybersecurity skills) and by raising cybersecurity self-efficacy. The effects of awareness and self-efficacy on compliance have been empirically examined and reported in literature, but the effect of cybersecurity skills has not received much attention. In an effort to understand the pathways through which training affects compliance, we develop a theoretical model and offer propositions. The model helps us understand how cybersecurity training should be designed and executed to optimally influence each of the three pathways to compliance and finally to have an optimal impact on...

In this proposed method the content of ripples in current is reduced without requirement of extra... more In this proposed method the content of ripples in current is reduced without requirement of extra switching devices. Due to the current ripples the lifetime of capacitors, fuel cells are decreased. In this proposed circuit the energy buffer capacitor is connected to the centre tap of the isolation transformer so this circuit realizes a dc active filter function without increasing the number of switching devices. Due to the common-mode voltage of the inverter the buffer capacitor voltage is controlled in additionally. The features of the proposed circuit are explained and Simulation results are presented. Simulation result proves the ripple reduction, to approximately 25% that of the conventional circuit.