59 Hits in 1.3 sec

FPGA Implementation of Particle Filters for Robotic Source Localization

Adithya Krishna, Andre Van Schaik, Chetan Singh Thakur
2021 IEEE Access  
Particle filtering is very reliable in modelling non-Gaussian and non-linear elements of physical systems, which makes it ideal for tracking and localization applications. However, a major drawback of particle filters is their computational complexity, which inhibits their use in real-time applications with conventional CPU or DSP based implementation schemes. The re-sampling step in the particle filters creates a computational bottleneck since it is inherently sequential and cannot be
more » ... zed. This paper proposes a modification to the existing particle filter algorithm, which enables parallel re-sampling and reduces the effect of the re-sampling bottleneck. We then present a high-speed and dedicated hardware architecture incorporating pipe-lining and parallelization design strategies to supplement the modified algorithm and lower the execution time considerably. From an application standpoint, we propose a novel source localization model to estimate the position of a source in a noisy environment using the particle filter algorithm implemented on hardware. The design has been prototyped using Artix-7 field-programmable gate array (FPGA), and resource utilization for the proposed system is presented. Further, we show the execution time and estimation accuracy of the high-speed architecture and observe a significant reduction in computational time. Our implementation of particle filters on FPGA is scalable and modular, with a low execution time of about 5.62 µs for processing 1024 particles (compared to 64 ms on Intel Core i7-7700 CPU with eight cores clocking at 3.60 GHz) and can be deployed for real-time applications. INDEX TERMS Particle filters, field programmable gate array, bearings-only tracking, Bayesian filtering, unmanned ground vehicle, hardware architectures, real-time processing. 98186 VOLUME 9, 2021
doi:10.1109/access.2021.3094962 fatcat:djylugiq7ncp7b2ymqxaxkeabe

A Comparative Study of Real-time Object Detection Systems for Navigation of the Visually Impaired

B. R. Karthik, Manish N, Adithya Krishna V, Y. V. Sai Keerthana, S. Prabhanjan, Archit Krishna K, Varun C. Shekar
2021 Zenodo  
The visually impaired face a plethora of problems. The primary problem they face is navigating from one place to another. The detection of obstacles in the user's proximity is another challenge that needs to be addressed. This paper provides a comparative study of various real-time image recognition and object detection methods that might help develop effective navigation systems for the visually impaired.
doi:10.5281/zenodo.4902962 fatcat:iz2vfmypwfb3ppeim5eeixc2be

Source localization using particle filtering on FPGA for robotic navigation with imprecise binary measurement [article]

Adithya Krishna, André van Schaik, Chetan Singh Thakur
2020 arXiv   pre-print
Krishna significant challenge to the unmanned vehicles to navigate and locate a target in an unknown environment autonomously.  ... 
arXiv:2010.11911v1 fatcat:pgvi2foz3zgntlyifbfarm6q7e

Automated binary and multiclass classification of Diabetic Retinopathy using Haralick and Multiresolution Features

Gayathri S, Adithya K. Krishna, Varun P Gopi, P Palanisamy
2020 IEEE Access  
ADITHYA K. KRISHNA is currently pursuing the B.Tech. degree in electronics and communication engineering with the National Institute of Technology at Tiruchirappalli, Tiruchirappalli, India.  ... 
doi:10.1109/access.2020.2979753 fatcat:peo2awwqrzcbjcg3xnnmoem4au

Kodaikanal calcium images: Detection of plages, Fixing the heliographic coordinates and Estimation of Area [article]

K. M. Hiremath, Shreyam Krishna, Adithya H. N, S. R. Chinmaya and Shashanka R Gurumath
2019 arXiv   pre-print
Kodaikanal Observatory is a veritable treasure trove of data, with the data repository covering almost 100 years of observations. For the years 1909-2007, we use calibrated Ca II K spectroheliograms from the Kodaikanal Observatory to detect the plages, fix their heliographic coordinates and also estimate the plage areas. We adopt the following procedure. After ensuring that, for all the years, Kodai calcium images have very negligible ellipcity, a circle is fitted and two central coordinates
more » ... radius of calcium images are determined uniquely. For each pixel of the calcium image, we then fix heliographic coordinates and extract plages along with their weighted average coordinates. The heliographic coordinates of these extracted plages are then compared with the heliographic coordinates of photospheric sunspots from the Greenwich sunspot database and chromospheric magnetic plages detected from the SOHO/MDI magnetograms. We find that the heliographic coordinates of calcium plages match very well with the heliographic coordinates of sunspots and magnetic plages authenticating our method of detection of plages and computation of positional coordinates. A code is developed in Python and all the nearly century scale plages data, with accurately estimated heliographic coordinates and areas, is available to the public.
arXiv:1909.00406v1 fatcat:zu3sjd2esrfypdiw2a2iohrsiy

Automatic detection of glaucoma via fundus imaging and artificial intelligence: A review [article]

Lauren Coan, Bryan Williams, Krishna Adithya Venkatesh, Swati Upadhyaya, Silvester Czanner, Rengaraj Venkatesh, Colin E. Willoughby, Srinivasan Kavitha, Gabriela Czanner
2022 arXiv   pre-print
Glaucoma is a leading cause of irreversible vision impairment globally and cases are continuously rising worldwide. Early detection is crucial, allowing timely intervention which can prevent further visual field loss. To detect glaucoma, examination of the optic nerve head via fundus imaging can be performed, at the centre of which is the assessment of the optic cup and disc boundaries. Fundus imaging is non-invasive and low-cost; however, the image examination relies on subjective,
more » ... ng, and costly expert assessments. A timely question to ask is can artificial intelligence mimic glaucoma assessments made by experts. Namely, can artificial intelligence automatically find the boundaries of the optic cup and disc (providing a so-called segmented fundus image) and then use the segmented image to identify glaucoma with high accuracy. We conducted a comprehensive review on artificial intelligence-enabled glaucoma detection frameworks that produce and use segmented fundus images. We found 28 papers and identified two main approaches: 1) logical rule-based frameworks, based on a set of simplistic decision rules; and 2) machine learning/statistical modelling based frameworks. We summarise the state-of-art of the two approaches and highlight the key hurdles to overcome for artificial intelligence-enabled glaucoma detection frameworks to be translated into clinical practice.
arXiv:2204.05591v1 fatcat:4vuterhtpvhgrka42euetn7hii

Post-stroke mRNA expression profile of MMPs: effect of genetic deletion of MMP-12

Koteswara Rao Nalamolu, Bharath Chelluboina, Ian B Magruder, Diane N Fru, Adithya Mohandass, Ishwarya Venkatesh, Jeffrey D Klopfenstein, David M Pinson, Krishna M Boini, Krishna Kumar Veeravalli
2018 Stroke and Vascular Neurology  
Recent reports from our laboratory demonstrated the post-ischaemic expression profile of various matrix metalloproteinases (MMPs) in rats and the detrimental role of MMP-12 in post-stroke brain damage. We hypothesise that the post-stroke dysregulation of MMPs is similar across species and that genetic deletion of MMP-12 would not affect the post-stroke expression of other MMPs. We tested our hypothesis by determining the pre-ischaemic and post-ischaemic expression profile of MMPs in wild-type and MMP-12 knockout mice.
doi:10.1136/svn-2018-000142 pmid:30294471 pmcid:PMC6169614 fatcat:i6ns3nl3ffavvgmbswmreswlhq

Removal of Power Line Interference in ECG Signal by Adaptive LMS, NLMS and RLS Algorithms

Pavani P, Adithya N.V.R., K. Hari Krishna, M.V. Siva Kumar
2014 IJARCCE  
Filtering of power line interference is very meaningful in the measurement of biomedical events recording, particularly in the case of recording signals as weak as the ECG signal. ECG is a biomedical signal which gives electrical activity of heart. This ECG signal is corrupted by various noises like power line interference, baseline wandering, channel noise, contact noise, muscle artifacts etc. Frequency range of ECG signal is nearly same as the frequency of power line interference. ECG signal
more » ... as frequency range from 0.5 Hz to 80 Hz and power line interference introduces 50 to 60 Hz frequency component in that signal which is the major cause of corruption of ECG. From various artifacts contaminate electrocardiogram (ECG) recording, the most common are power line interference. Power line interference is not easily recognizable since the interfering voltage in the ECG may have frequency 50 Hz. The most common cause of 50 Hz interference is the disconnected electrode resulting in a very strong disturbing signal, and therefore needs quick action. Electromagnetic interference from the power lines also results in poor quality tracings. Electrical equipment's such as air conditioner, elevators and X-ray units draw heavy power line current, which induce 50 Hz signals in the input circuits of the ECG machine. This project focuses on a technique for de noising of such non stationary ECG signal using adaptive filter algorithms like LMS, NLMS, RLS and compares their performance characteristics using MATLAB. The objective of this report is to separate the valid signal component from the undesired noises so that the accurate interpretation of ECG signals could be done. Recently, Adaptive filtering has become one of the effective and popular methods for the processing and analysis of the ECG signal because of its non-stationary nature. And in this study, Adaptive LMS, NLMS, and RLS algorithms are used to filter power line interference from the ECG signal and compare their performance based on SNR value [1]- [4] .
doi:10.17148/ijarcce.2017.64149 fatcat:mla3nx6kfrdufcryxpi47n4veq

SAAMBE-3D: Predicting Effect of Mutations on Protein–Protein Interactions

Swagata Pahari, Gen Li, Adithya Krishna Murthy, Siqi Liang, Robert Fragoza, Haiyuan Yu, Emil Alexov
2020 International Journal of Molecular Sciences  
Maintaining wild type protein–protein interactions is essential for the normal function of cell and any mutation that alter their characteristics can cause disease. Therefore, the ability to correctly and quickly predict the effect of amino acid mutations is crucial for understanding disease effects and to be able to carry out genome-wide studies. Here, we report a new development of the SAAMBE method, SAAMBE-3D, which is a machine learning-based approach, resulting in accurate predictions and
more » ... s extremely fast. It achieves the Pearson correlation coefficient ranging from 0.78 to 0.82 depending on the training protocol in benchmarking five-fold validation test against the SKEMPI v2.0 database and outperforms currently existing algorithms on various blind-tests. Furthermore, optimized and tested via five-fold cross-validation on the Cornell University dataset, the SAAMBE-3D achieves AUC of 1.0 and 0.96 on a homo and hereto-dimer test datasets. Another important feature of SAAMBE-3D is that it is very fast, it takes less than a fraction of a second to complete a prediction. SAAMBE-3D is available as a web server and as well as a stand-alone code, the last one being another important feature allowing other researchers to directly download the code and run it on their local computer. Combined all together, SAAMBE-3D is an accurate and fast software applicable for genome-wide studies to assess the effect of amino acid mutations on protein–protein interactions. The webserver and the stand-alone codes (SAAMBE-3D for predicting the change of binding free energy and SAAMBE-3D-DN for predicting if the mutation is disruptive or non-disruptive) are available.
doi:10.3390/ijms21072563 pmid:32272725 pmcid:PMC7177817 fatcat:maes246fxng2rmjliq5oacwnae

Variations of Vitamin D in Various Stages of Breast Carcinoma: A Randomized Case Control Study

Aananda Krishna KS, Saai Ram Thejas, Aniruddhan VJ, Sudarsan Adithya
2021 Acta Scientific Cancer Biology  
D status may be a significant regulator of cancer progression in cancer patients be-13 Variations of Vitamin D in Various Stages of Breast Carcinoma: A Randomized Case Control Study Citation: Aananda Krishna  ... 
doi:10.31080/ascb.2021.04.0355 fatcat:2nuvgdyvybgqtn3xmfip6mzqyi

EffUnet-SpaGen: An Efficient and Spatial Generative Approach to Glaucoma Detection

Venkatesh Krishna Adithya, Bryan M. Williams, Silvester Czanner, Srinivasan Kavitha, David S. Friedman, Colin E. Willoughby, Rengaraj Venkatesh, Gabriela Czanner
2021 Journal of Imaging  
Current research in automated disease detection focuses on making algorithms "slimmer" reducing the need for large training datasets and accelerating recalibration for new data while achieving high accuracy. The development of slimmer models has become a hot research topic in medical imaging. In this work, we develop a two-phase model for glaucoma detection, identifying and exploiting a redundancy in fundus image data relating particularly to the geometry. We propose a novel algorithm for the
more » ... p and disc segmentation "EffUnet" with an efficient convolution block and combine this with an extended spatial generative approach for geometry modelling and classification, termed "SpaGen" We demonstrate the high accuracy achievable by EffUnet in detecting the optic disc and cup boundaries and show how our algorithm can be quickly trained with new data by recalibrating the EffUnet layer only. Our resulting glaucoma detection algorithm, "EffUnet-SpaGen", is optimized to significantly reduce the computational burden while at the same time surpassing the current state-of-art in glaucoma detection algorithms with AUROC 0.997 and 0.969 in the benchmark online datasets ORIGA and DRISHTI, respectively. Our algorithm also allows deformed areas of the optic rim to be displayed and investigated, providing explainability, which is crucial to successful adoption and implementation in clinical settings.
doi:10.3390/jimaging7060092 fatcat:dtggkwewxnfyrert3zinwmuum4

Valkyrie—Design and Development of Gaits for Quadruped Robot Using Particle Swarm Optimization

Taarun Srinivas, Adithya Krishna Karigiri Madhusudhan, Lokeshwaran Manohar, Nikhit Mathew Stephen Pushpagiri, Kuppan Chetty Ramanathan, Mukund Janardhanan, Izabela Nielsen
2021 Applied Sciences  
Over the past decades, developments and scientific breakthroughs in the field of robotics have shown the replacement of wheeled robots with legged robots, which are often inspired by the biological characteristics of legged animals. Many industries and urban-based applications promote quadruped robots because of their dexterous ability to efficiently handle multiple tasks in the working environment. Motivated from the recent works in the field of quadruped robots, this research aims to develop
more » ... nd investigate gaits for a 2 DoF mammal-inspired quadruped robot that incorporates 4 hip and 4 knee servo motors as its locomotion element. Forward and inverse kinematic techniques are used to determine the joint angle required for the locomotion and stability calculation are presented to determine the center of mass/center of gravity of the robot. Three types of gaits such as walk, trot, and pace are developed while keeping the center of mass inside the support polygon using a closed-loop control system. To minimize errors and improve the performance of the robot due to its non-linearity, a meta-heuristic algorithm has been developed and addressed in this work. The fitness function is derived based on the Euclidean distance between the target and robot's current position and kinematic equations are used to obtain the relation between joints and coordinates. Based on the literature, particle swarm optimization (PSO) was found to be a promising algorithm for this problem and is developed using Python's 'Pyswarms' package. Experimental studies are carried out quantitatively to determine the convergence characteristics of the control algorithm and to investigate the distance traveled by the robot for different target positions and gaits. Comparison between experimental and theoretical results prove the efficiency of the proposed algorithm and stability of the robot during various gait movements.
doi:10.3390/app11167458 fatcat:re2kt3r56fbevp3iyf66cx3az4

Risk stratification of women with peripartum cardiomyopathy at initial presentation: A dobutamine stress echocardiography study

R.V. Venkata Rao, G. Ramesh, D. Seshagiri Rao, O. Sai Satish, L.S.R. Krishna, M. Adithya
2014 Indian Heart Journal  
Krishna, M. Adithya  ... 
doi:10.1016/j.ihj.2014.10.226 fatcat:p2upfa4zb5birlgvhrhplfnsra

A Novel Splenic Vein Flow Volume to the Portal Vein Flow Velocity Index as a Predictor for the Degree of Esophageal Varices in Liver Cirrhosis Patients

Krishna Pandu Wicaksono, Sahat Matondang, Christopher Silman, Joedo Prihartono, Cosmas Rinaldi Adithya Lesmana
2022 Case Reports in Gastroenterology  
Krishna Pandu Wicaksono performed DOS under the supervision of Sahat Matondang, and Cosmas Rinaldi Adithya Lesmana performed or supervised the endoscopy procedure.  ...  All the authors (Krishna Pandu Wicaksono, Sahat Matondang, Christopher Silman, Joedo Prihartono, Cosmas Rinaldi Adithya Lesmana) significantly contributed to this research.  ... 
doi:10.1159/000523757 pmid:35528777 pmcid:PMC9035959 fatcat:7qbmvnl6vfgcdggo2lfozseqoe

How Does an Interactive Knowledge Platform Influence Decision-making of Novice Researchers in Engineering Education Research?

Xin Chen, Adithya Raghavan, Ji Soo Yi, Krishna Madhavan
2012 ASEE Annual Conference & Exposition Proceedings   unpublished
An interactive visualization knowledge network platform iKNEER (Interactive Knowledge Network for Engineering Education Research, was designed for researchers in the Engineering Education Research (EER) community. This platform is potentially helpful to first-year PhD students in Engineering Education. The major goal of this study is to investigate the role iKNEER could play in first-year PhD students' decision-making upon their research using a qualitative method. It also
more » ... as a qualitative evaluation of the iKNEER platform. Providing a better understanding of how this research tool influences novice researchers' decision-making process, results of this study could inform further development and future design of such tools.
doi:10.18260/1-2--21456 fatcat:nrayatvxlfhzlgcgrekmcxg4sa
« Previous Showing results 1 — 15 out of 59 results