2,962 Hits in 1.7 sec

Segmentation of Roots in Soil with U-Net [article]

Abraham George Smith, Jens Petersen, Raghavendra Selvan, Camilla Ruø Rasmussen
2019 arXiv   pre-print
We investigate the effectiveness of an automated image segmentation method based on the U-Net Convolutional Neural Network (CNN) architecture to enable such measurements.  ...  Raghavendra Selvan and Jens Petersen provided valuable machine learning expertise.  ...  (a) photo (b) annotation (c) U-Net segmentation (d) U-Net errors Original photo, annotation, segmentation output from U-Net and errors.  ... 
arXiv:1902.11050v2 fatcat:e3rkizoavbbdzo6pibisjojyta

Segmentation of roots in soil with U-Net

Abraham George Smith, Jens Petersen, Raghavendra Selvan, Camilla Ruø Rasmussen
2020 Plant Methods  
We have demonstrated the feasibility of a U-Net based CNN system for segmenting images of roots in soil and for replacing the manual line-intersect method.  ...  We investigate the effectiveness of an automated image segmentation method based on the U-Net Convolutional Neural Network (CNN) architecture to enable such measurements.  ...  from U-Net and errors.  ... 
doi:10.1186/s13007-020-0563-0 pmid:32055251 pmcid:PMC7007677 fatcat:qrrj2tuienaijnvofxhgwckwxy

Artificial Intelligence Techniques for Automated Diagnosis of Neurological Disorders

U. Raghavendra, U. Rajendra Acharya, Hojjat Adeli
2019 European Neurology  
DOI: 10.1159/000504292 7 Raghavendra/Acharya/AdeliEur Neurol 2019;82:41-64 Eur Neurol 2019;82:41-64  ... 
doi:10.1159/000504292 pmid:31743905 fatcat:frg5lwwt7vauxm6rjgc7sepy6y

Entropy based Log Chromaticity Projection for Real-time Stereo Matching

U. Raghavendra, Makkithaya Krishnamoorthi, A.K. Karunakar
2012 Procedia Technology - Elsevier  
Most of the existing stereo matching algorithms will assume a similar corresponding color values between stereo images. In the real scenario, these color values are effected by several radiometric factors such as illumination direction, illumination color, camera parameters, etc, which results in different color values between the corresponding points. Hence, applying the stereo algorithm directly on the raw color values is not appropriate for the real-time environment. This paper proposes an
more » ... paper proposes an entropy minimization based log chromaticity projection for stereo image, thereby extracting the invariant image, which is independent of illumination and color. The developed invariant image is the perfect measure for finding the similarity between the corresponding points. Normalized cross correlation based similarity measure is applied on the generated invariant image and the obtained disparity outperforms some of the local and global stereo algorithms.
doi:10.1016/j.protcy.2012.10.027 fatcat:jxft4tk54fgqvlky2oaqxo6nh4

Automated categorization of multi-class brain abnormalities using decomposition techniques with MRI images: A comparative study

Anjan Gudigar, U Raghavendra, Edward J Ciaccio, N Arunkumar, Enas Abdulhay, U Rajendra Acharya
2019 IEEE Access  
U. RAGHAVENDRA received the Ph.D. degree from the Manipal Academy of Higher Education, India.  ...  U. RAJENDRA ACHARYA received the Ph.D. degree from the National Institute of Technology Karnataka, Surathkal, India, and the D.Eng. degree from Chiba University, Japan.  ... 
doi:10.1109/access.2019.2901055 fatcat:vlct7fxghzha7mitnfsskoqlzu

Continuous data assimilation for downscaling large-footprint soil moisture retrievals

Muhammad U. Altaf, Raghavendra B. Jana, Ibrahim Hoteit, Matthew F. McCabe, Christopher M. U. Neale, Antonino Maltese
2016 Remote Sensing for Agriculture, Ecosystems, and Hydrology XVIII  
Soil moisture is a key component of the hydrologic cycle, influencing processes leading to runoff generation, infiltration and groundwater recharge, evaporation and transpiration. Generally, the measurement scale for soil moisture is found to be different from the modeling scales for these processes. Reducing this mismatch between observation and model scales in necessary for improved hydrological modeling. An innovative approach to downscaling coarse resolution soil moisture data by combining
more » ... data by combining continuous data assimilation and physically based modeling is presented. In this approach, we exploit the features of Continuous Data Assimilation (CDA) which was initially designed for general dissipative dynamical systems and later tested numerically on the incompressible Navier-Stokes equation, and the Benard equation. A nudging term, estimated as the misfit between interpolants of the assimilated coarse grid measurements and the fine grid model solution, is added to the model equations to constrain the model's large scale variability by available measurements. Soil moisture fields generated at a fine resolution by a physically-based vadose zone model (HYDRUS) are subjected to data assimilation conditioned upon coarse resolution observations. This enables nudging of the model outputs towards values that honor the coarse resolution dynamics while still being generated at the fine scale. Results show that the approach is feasible to generate fine scale soil moisture fields across large extents, based on coarse scale observations. Application of this approach is likely in generating fine and intermediate resolution soil moisture fields conditioned on the radiometerbased, coarse resolution products from remote sensing satellites.
doi:10.1117/12.2241042 fatcat:ekn7ijscmvf5heb4x6ibx3xnwy

Role of Artificial Intelligence in COVID-19 Detection

Anjan Gudigar, U Raghavendra, Sneha Nayak, Chui Ping Ooi, Wai Yee Chan, Mokshagna Rohit Gangavarapu, Chinmay Dharmik, Jyothi Samanth, Nahrizul Adib Kadri, Khairunnisa Hasikin, Prabal Datta Barua, Subrata Chakraborty (+2 others)
2021 Sensors  
The global pandemic of coronavirus disease (COVID-19) has caused millions of deaths and affected the livelihood of many more people. Early and rapid detection of COVID-19 is a challenging task for the medical community, but it is also crucial in stopping the spread of the SARS-CoV-2 virus. Prior substantiation of artificial intelligence (AI) in various fields of science has encouraged researchers to further address this problem. Various medical imaging modalities including X-ray, computed
more » ... ray, computed tomography (CT) and ultrasound (US) using AI techniques have greatly helped to curb the COVID-19 outbreak by assisting with early diagnosis. We carried out a systematic review on state-of-the-art AI techniques applied with X-ray, CT, and US images to detect COVID-19. In this paper, we discuss approaches used by various authors and the significance of these research efforts, the potential challenges, and future trends related to the implementation of an AI system for disease detection during the COVID-19 pandemic.
doi:10.3390/s21238045 pmid:34884045 fatcat:s6myy3c6dfbcje3356sqkcbtbu

Teaching Learning in Biochemistry: Medical College Students' Perceptions and Opinions

Jyothi MP D'Souza, U Raghavendra, Deepak Herald D'Souza, Neevan DR D'Souza
2013 Education in Medicine Journal  
Biochemistry is one of the important basic science subjects that are taught in the pre-clinical phase of the undergraduate medical curriculum. Very little is known about the students' perceptions towards improving the teaching learning process of biochemistry. Methods: Data was analysed from 139 feedback forms of a questionnaire study from second year students of a medical college in India (n=139 of 157 students). The self administered questionnaire contained 36 items which were related to
more » ... ere related to liking the subject of biochemistry, rating of the different topics (difficulty in learning) and the effectiveness of teaching methods. Results: Majority (57%) of the students liked the subject of biochemistry. Metabolisms and molecular biology were difficult topics to learn. Practical exercises, lectures, exams, and other methods have been found by majority of the students to be the excellent or very good methods, for effectively teaching biochemistry. Opinion by students was suggesting a clear mandate in several issues such as, usefulness of biochemistry practicals, learning minute details of biochemical reactions, and a clinician teaching the interpretation of lab investigations. Majority of them have perceived that the subject of biochemistry can be covered meaningfully within a year. Conclusions: Students perceive the usefulness of teaching methods and the varying difficulties in learning different topics in biochemistry. Teaching learning process in biochemistry can be improved, by understanding students' perceptions.
doi:10.5959/eimj.v5i2.109 fatcat:ad54tfqmajcqtbvxecrz3t7nj4

Automated Intracranial Hematoma Classification in Traumatic Brain Injury (TBI) Patients Using Meta-Heuristic Optimization Techniques

Vidhya V, U. Raghavendra, Anjan Gudigar, Praneet Kasula, Yashas Chakole, Ajay Hegde, Girish Menon R, Chui Ping Ooi, Edward J. Ciaccio, U. Rajendra Acharya
2022 Informatics  
Approaches CT Dataset Method Classifier Performance Raghavendra et al. [15] 1603 Entropy-based non-linear features PNN Acc: 97.37% Modified Distance Shahangian and Pourghassem [17] 627 Regularized Level  ...  Approaches CT Dataset Method Classifier Performance Raghavendra et al. [15] 1603 Entropy-based non-linear features PNN Acc: 97.37% Shahangian and Pourghassem [17] 627 Modified Distance Regularized Level  ... 
doi:10.3390/informatics9010004 fatcat:b66ctceshrbtfoqfbjfxfjjdcm

A clinical study of traumatic tympanic membrane perforation

Fida Harish A. T., Raghavendra Prasad K. U.
2021 International Journal of Otorhinolaryngology and Head and Neck Surgery  
<p><strong>Background:</strong> Tympanic membrane (TM) which forms the partition between external auditory canal and middle ear may be ruptured by trauma. Traumatic TM perforation is a commonly observed condition. Though, several therapeutic interventions have been described, conservative follow-up until spontaneous complete recovery is the most common choice.</p><p><strong>Methods:</strong> It was a prospective cohort study conducted during a period of 10 months from July 2020 to April 2021,
more » ... 20 to April 2021, carried out in 30 patients who presented to outpatient department of ENT and casualty of Hassan institute of medical sciences hospital with traumatic TM perforation. After taking informed consent, detailed history was taken, thorough examination of ear was performed and characteristics of perforation were noted. Pure tone audiometry (PTA) was conducted, data was statistically analysed.</p><p><strong>Results:</strong> Mean age group was 33.1 years and 73.3% were males. Ear pain was the commonest symptom with accidental trauma being the most common cause. 70% of them had left TM perforation and posteroinferior quadrant was mostly involved.</p><p><strong>Conclusions:</strong> Traumatic TM perforation is commonly seen in young adults following accidental trauma and assault. Earache, sudden hearing loss and tinnitus are the common symptoms. Most of the cases heal spontaneously with conservative management.</p>
doi:10.18203/issn.2454-5929.ijohns20213903 fatcat:vk3yfbtwrvhlzin5m77q6dd6yq

Scene-Independent Motion Pattern Segmentation in Crowded Video Scenes using Spatio-Angular Density-based Clustering

Abhilash K. Pai, Karunakar A. K., U. Raghavendra
2020 IEEE Access  
The value of θ t i ∈ (0, 2π − 1) varies according to the values of the vectors u and u and is equal to zero when there is no motion.  ...  v], consists of an x-component (u) and a y-component (v).  ... 
doi:10.1109/access.2020.3015375 fatcat:7hvhwmxz6zg55gbkzxaf2cdeym

Novel and accurate non-linear index for the automated detection of haemorrhagic brain stroke using CT images

U. Raghavendra, The-Hanh Pham, Anjan Gudigar, V. Vidhya, B. Nageswara Rao, Sukanta Sabut, Joel Koh En Wei, Edward J. Ciaccio, U. Rajendra Acharya
2021 Complex & Intelligent Systems  
AbstractBrain stroke is an emergency medical condition which occurs mainly due to insufficient blood flow to the brain. It results in permanent cellular-level damage. There are two main types of brain stroke, ischemic and hemorrhagic. Ischemic brain stroke is caused by a lack of blood flow, and the haemorrhagic form is due to internal bleeding. The affected part of brain will not function properly after this attack. Hence, early detection is important for more efficacious treatment.
more » ... atment. Computer-aided diagnosis is a type of non-invasive diagnostic tool which can help in detecting life-threatening disease in its early stage by utilizing image processing and soft computing techniques. In this paper, we have developed one such model to assess intracerebral haemorrhage by employing non-linear features combined with a probabilistic neural network classifier and computed tomography (CT) images. Our model achieved a maximum accuracy of 97.37% in discerning normal versus haemorrhagic subjects. An intracerebral haemorrhage index is also developed using only three significant features. The clinical and statistical validation of the model confirms its suitability in providing for improved treatment planning and in making strategic decisions.
doi:10.1007/s40747-020-00257-x fatcat:ztjnd45syvcp3gpnsdy5ukzdmy

Local Preserving Class Separation Framework to Identify Gestational Diabetes Mellitus Mother Using Ultrasound Fetal Cardiac Image

Anjan Gudigar, Jyothi Samanth, U Raghavendra, Chinmay Dharmik, Akhila Vasudeva, R Padmakumar, Ru-San Tan, Edward J Ciaccio, Filippo Molinari, U Rajendra Acharya
2020 IEEE Access  
doi:10.1109/access.2020.3042594 fatcat:ptojacgpr5fv3p25ho4n7rcdeu

Interfacial molecular interactions of cellobiohydrolase Cel7A and its variants on cellulose

Akshata R. Mudinoor, Peter M. Goodwin, Raghavendra U. Rao, Nardrapee Karuna, Alex Hitomi, Jennifer Nill, Tina Jeoh
2020 Biotechnology for Biofuels  
Molecular-scale mechanisms of the enzymatic breakdown of cellulosic biomass into fermentable sugars are still poorly understood, with a need for independent measurements of enzyme kinetic parameters. We measured binding times of cellobiohydrolase Trichoderma reesei Cel7A (Cel7A) on celluloses using wild-type Cel7A (WTintact), the catalytically deficient mutant Cel7A E212Q (E212Qintact) and their proteolytically isolated catalytic domains (CD) (WTcore and E212Qcore, respectively). The binding
more » ... ly). The binding time distributions were obtained from time-resolved, super-resolution images of fluorescently labeled enzymes on cellulose obtained with total internal reflection fluorescence microscopy. Binding of WTintact and E212Qintact on the recalcitrant algal cellulose (AC) showed two bound populations: ~ 85% bound with shorter residence times of < 15 s while ~ 15% were effectively immobilized. The similarity between binding times of the WT and E212Q suggests that the single point mutation in the enzyme active site does not affect the thermodynamics of binding of this enzyme. The isolated catalytic domains, WTcore and E212Qcore, exhibited three binding populations on AC: ~ 75% bound with short residence times of ~ 15 s (similar to the intact enzymes), ~ 20% bound for < 100 s and ~ 5% that were effectively immobilized. Cel7A binding to cellulose is driven by the interactions between the catalytic domain and cellulose. The cellulose-binding module (CBM) and linker increase the affinity of Cel7A to cellulose likely by facilitating recognition and complexation at the substrate interface. The increased affinity of Cel7A to cellulose by the CBM and linker comes at the cost of increasing the population of immobilized enzyme on cellulose. The residence time (or inversely the dissociation rates) of Cel7A on cellulose is not catalysis limited.
doi:10.1186/s13068-020-1649-7 pmid:31988662 pmcid:PMC6969433 fatcat:2f6ylaikvvg5tgtag3i2rqwii4

An integrated index for breast cancer identification using histogram of oriented gradient and kernel locality preserving projection features extracted from thermograms

U. Raghavendra, U. Rajendra Acharya, E. Y. K. Ng, Jen-Hong Tan, Anjan Gudigar
2016 Quantitative InfraRed Thermography Journal  
Breast cancer is one of the prime causes of death in women worldwide. Thermography has shown a great potential in screening the breast cancer and overcomes the limitations of mammography. Moreover, interpretations of thermogram images are dependent on the specialists, which may lead to errors and uneven results. Preliminary screening method should detect the hazardous, destructive tumors effectively to improve the accuracy. The growth of malignant tumor can increase the internal temperature
more » ... nal temperature which can be captured by thermograms. Thus in this work, locally normalized Histogram of Oriented Gradients (HOG) based preliminary screening Computer Aided Diagnosis (CAD) tool is proposed. HOG is able to record the minute internal variations in thermograms. In order to reduce the dimensions of extracted HOG descriptors Kernel Locality Preserving Projection (KLPP) is used. The resulting KLPP features are then ranked to form an efficient classification model. Various machine learning algorithms are used to validate the proposed method. Our method shows a promising performance with an average accuracy, sensitivity, and specificity of 98 %, 96.66 % and 100 % respectively. We have also developed a Breast Cancer Risk Index (BCRI) using significant KLPP features which can discriminate the two classes using a single integrated index. This can help the radiologists to discriminate the normal and malignant classes during screening to validate their findings.
doi:10.1080/17686733.2016.1176734 fatcat:2ltemlu5mbdk7kz3aq2i7vbtvy
« Previous Showing results 1 — 15 out of 2,962 results