Search

Your search keyword '"Kavitha, K R"' showing total 500 results
Start Over Author "Kavitha, K R"
500 results on '"Kavitha, K R"'

6. Forest Fire Detection and Prevention System

Author

Kavitha, K. R., Vijayalakshmi, S., Babu, B. Murali, Roshan, D. Rini, Kalaivani, K., Kacprzyk, Janusz, Series Editor, Gomide, Fernando, Advisory Editor, Kaynak, Okyay, Advisory Editor, Liu, Derong, Advisory Editor, Pedrycz, Witold, Advisory Editor, Polycarpou, Marios M., Advisory Editor, Rudas, Imre J., Advisory Editor, Wang, Jun, Advisory Editor, Gupta, Deepak, editor, Khanna, Ashish, editor, Hassanien, Aboul Ella, editor, Anand, Sameer, editor, and Jaiswal, Ajay, editor

Published
2023
Full Text
View/download PDF

7. Profile-Based Calibration for AR/VR Glass

Author

Vijayalakshmi, S., Kavitha, K. R., Subhash, S. M., Sujith Kumar, D., Sharveshvarr, S. V., Bharathi, P., Kacprzyk, Janusz, Series Editor, Gomide, Fernando, Advisory Editor, Kaynak, Okyay, Advisory Editor, Liu, Derong, Advisory Editor, Pedrycz, Witold, Advisory Editor, Polycarpou, Marios M., Advisory Editor, Rudas, Imre J., Advisory Editor, Wang, Jun, Advisory Editor, Gupta, Deepak, editor, Khanna, Ashish, editor, Hassanien, Aboul Ella, editor, Anand, Sameer, editor, and Jaiswal, Ajay, editor

Published
2023
Full Text
View/download PDF

10. Liver Tumor Detection Using CNN

Author

Vijayalakshmi, S., Kavitha, K. R., Tamilarasi, M., Soundharya, R., Kacprzyk, Janusz, Series Editor, Gomide, Fernando, Advisory Editor, Kaynak, Okyay, Advisory Editor, Liu, Derong, Advisory Editor, Pedrycz, Witold, Advisory Editor, Polycarpou, Marios M., Advisory Editor, Rudas, Imre J., Advisory Editor, Wang, Jun, Advisory Editor, Suma, V., editor, Baig, Zubair, editor, Kolandapalayam Shanmugam, Selvanayaki, editor, and Lorenz, Pascal, editor

Published
2022
Full Text
View/download PDF

11. Handwritten Character Recognition for Tamil Language Using Convolutional Recurrent Neural Network

Author

Vijayalakshmi, S., Kavitha, K. R., Saravanan, B., Ajaybaskar, R., Makesh, M., Kacprzyk, Janusz, Series Editor, Gomide, Fernando, Advisory Editor, Kaynak, Okyay, Advisory Editor, Liu, Derong, Advisory Editor, Pedrycz, Witold, Advisory Editor, Polycarpou, Marios M., Advisory Editor, Rudas, Imre J., Advisory Editor, Wang, Jun, Advisory Editor, Suma, V., editor, Baig, Zubair, editor, Kolandapalayam Shanmugam, Selvanayaki, editor, and Lorenz, Pascal, editor

Published
2022
Full Text
View/download PDF

16. Colour correction using open computer vision & python.

Author

Kavitha, K. R. and Rakshandha, C. Janani

Subjects
*COLOR, *LIGHT sources, *COMPUTER vision, *PYTHON programming language
Abstract

In a practical and real-world, colour matching is achieved effectively only by the colour constancy. This colour matching plays a very important role in each and every fields of our daily uses. Colour constancy refers to the study of how every humans will perceive the colours. The goal of colour correction is to obtain the colour of objects correctly regardless of the differences in light sources, illumination, etc. In this paper, we will learn to achieve the colour correction of the objects or materials used in our day to day life with the help pf the open computer vision and python programming. This respective technique can be effectively used for photographers, and also the computer vision practitioners. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

27. Galactic Swarm-based Harris Hawks Optimization for Handling the Upstream/Downstream Configuration in PON-SDN-DSVM Systems: A Deep Learning Concept

Author

MALINI P and kavitha K R

Abstract

Owing to the strategic benefits, recent broadband ONs have attracted the interest of academics and business (cost-efficiency, flexibility, vast bandwidth, and mobility). Simultaneously, the rise of SDN allows for effective dynamic reconfiguration of fundamental network elements via SDN controllers. As a result, efficient traffic-aware strategies for automatically identifying appropriate specifications to improve network performance are possible. In order to do this, a new deep learning technique for an SDN-defined hybrid PON is suggested. A PON-SDN-DSVM makes up the proposed design. The introduced hybrid deep learning model called DSVM is formed by combining the DNN and SVM and it is optimized by the integration of two well performing algorithms such as GSO and HHO in order to produce the hybrid meta heuristic algorithm called as GS-HHO with the consideration of accuracy maximization. The suggested technique obtains traffic-aware knowledge from SDN controllers and adjusts the communication's upstream-downstream configuration. On the basis of the traffic dynamics of the complete hybrid network, this traffic-aware method can determine the best configuration. Real-world traffic traces are used to test the proposed method in a realistic context. The suggested technique, according to the attained numerical findings, provides considerable increases in network performance with respect to accuracy, precision, f1 score, recall, comparison, and confusion matrix analysis.

Published
2022

33. A Mathematical Model for Increasing Incidence ofTuberculosis in Poverty Driven Confined Areas and Measures for Control

Author

RAMANA MURTHY and Kavitha K R

Subjects
Environmental Engineering, General Engineering, Computer Science Applications
Abstract

Tuberculosis is observed to be most prevalent airborne infectious diseases killing hundreds and thousands of people every year. Mostly, the disease spreads in poverty driven poor countries and also to some extent in developing nations. The disease transmits in situations where infected persons are in close contact with others in confined spaces and also living in poor and unhygienic conditions. It is well recognized that overcrowding increases the risk of transmission. A detailed analysis is presented in this paper with respect to the various participating parameters. Interestingly, the results presented in this paper illustrate the occurrence and propagation of the disease as a mathematical model. The results are in agreement with the real life situations and the number of new infections is observed to be linear. It is seen that for fixed time (t), as the room volume (V) increases, the new infections(C) decreases gradually. In general it is seen that as the ventilation rate (N) increases, the new infections decreases quite rapidly. Further, it is observed that as time increases for a constant ventilation rate, an increase in the new infections is noted. Also, for a constant room volume as time increases, the number of new infections is found to be increasing. An interesting feature is that as the ventilation is progressive, a steep fall in the new infections is noted in the initial stages and subsequently, the drop is not that significant. The influence of time gradually seems to be diminishing as the ventilation rate increases. As the room volume increases, the new infections decrease at a faster rate. However, in each of these observations, it is seen that as ventilation rate increases, the number of new infections are found to be inversely proportional. Such a decrease is more predominant in the initial stages but decreases subsequently

Published
2019

35. Ensemble-based Feature Selection using Symmetric Uncertainty and SVM classification

Author

Kavitha K R, Achu S S, and Rizwana Rasheed

Subjects
Support vector machine, Statistical classification, Filter methods, Computer science, business.industry, Classifier (linguistics), Feature extraction, Redundancy (engineering), Pattern recognition, Feature selection, Artificial intelligence, business, Curse of dimensionality
Abstract

Feature selection plays a significant role in gene expression data due to its dimensionality. Microarray gene expression data is particularly important and significant in clinical diagnosis. Our aim is to improve the feature selection technique using the ensembling method. The ranked subset from three filter methods namely spearman, Pearson, MI is used in the EFS-SU algorithm. Symmetric Uncertainty is used to find C-Correlation and F-Correlation. This algorithm will help the SVM classifier in reducing computational cost and finding relevant and efficient genes, without redundancy. Due to the elimination of redundant and non-relevant genes,we were able to increase the classifier accuracy.

Published
2021

37. Evaluating wear characteristics of self-lubricating composition for spools used in pneumatic valves.

Author

Palaniswamy, Sivashankari, Ajaykumar, K., Kumar, S. Harish, Kavitha, K. R., Prakash, S., Sasipraba, T, Subramaniam, Prakash, Jayaprabakar, J, Joy, Nivin, Anish, M, Ganesan, S, and Kavitha, K R

Subjects
ALUMINUM composites, ALUMINUM alloys, MECHANICAL wear, WEAR resistance, COMPOSITE materials
Abstract

Aluminum Composite materials are mainly used for the application of light weight material in many aspects, the main application is considered for the front and rear spools in automobile. Apart from automobile field it is also used in various structural application and valves of transportation. The Aluminum Composites is to increase the strength and life span of the components. Basically, Most of the Aluminum Alloy does not satisfactory wear resistance. The focus of this research paper is to select a suitable Aluminum Alloy and composition that compensates high strength, wear resistance, and self-lubricating property. It is noted that spools are manufactured by using stainless steel which are more weight when compared to Aluminum alloy. Aluminum Alloy is reinforced with the composite material Molybdenum-Di-Sulphide which has a low friction, very good self-lubrication system in it. In this work, influence of Molybdenum-Di-Sulphide (MoS2) is added to increase the performance of the spools using Aluminum Alloy-7075 was studied. Stir casting technique is used to fabricate the hybrid composite with AA7075 with Molybdenum-Di-Sulphide (MoS2) at varying weight fractions such as 3%, 6% and 9% for improving wear properties. The Mechanical characteristics and Wear characteristics are analyzed to prove the strength and life span of the material composition. The wear and friction tests yield good results at higher sliding speed, low load and high composition. The main motive of this project is to increase the wear resistance and life time of the spools. [ABSTRACT FROM AUTHOR]

Published
2020
Full Text
View/download PDF

38. Laplacian Score and Top Scoring Pair Feature Selection Algorithms

Author

Neeradha K, Sreelakshmi Sajith, Athira, Kavitha K R, and Vyshna K

Subjects
Clustering high-dimensional data, Computer science, 0206 medical engineering, Feature selection, 02 engineering and technology, Filter (signal processing), Prediction system, Division (mathematics), Support vector machine, Identification (information), 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Laplace operator, Algorithm, 020602 bioinformatics
Abstract

the method by which data from the gene of a human body is converted into a protein, where it can be used to infer how active a gene is called gene expression. Recently, gene expression is applied for disease identification in human body. As the gene data is high dimensional when compared with the number of samples available, gene expression data can be used for the prognosis of diseases like cancer, which is caused when the cells undergo an uncontrollable division and spread into the surrounding tissues. In the case of a prediction system, we need effective datasets to deliver maximum prediction accuracy. In order to transform data from high dimensional data to the most effective data Feature selection is used. Feature selection selects the most appropriate or required features into consideration. This technique has different methods by which it can be executed, they are open-loop method/filter method, close-loop method/wrapper method, embedded method, and the ensemble method. The proposed research work is based on two feature selection algorithms namely, Laplacian score, an open-loop method, and Top scoring pair, a hybrid method.

Published
2020

43. SEGMENTATION, FEATURE EXTRACTION AND CLASSIFICATION OF BRAIN TUMOR THROUGH MRI IMAGE.

Author

Vijayalakshmi, S., Kavitha, K. R., and Hariharan, S.

Subjects
BRAIN tumors, FEATURE extraction, MAGNETIC resonance imaging, TUMOR classification, IMAGE processing, IMAGE segmentation
Abstract

In biomedical, tumor detection and removal is one of the major medical issue. Brain tumor is a disease of the brain where cancer cells arise in the brain tissue to form a mass of cancer tissue that interferes with brain functions such as manage muscle, sense, memory and other body functions. Tumors composed of cancerous cells are called Malignant tumors and those composed of non-cancerous cells are called Benign tumors. There are so many ways to diagnose tumor in brain include Neurologic exam, MRI, CT scan, Angiogram, Spinal tap and Biopsy. Medical imaging has tremendous advantage in diagnosis of the disease where Magnetic Resonance Imaging plays an important role. This paper aims to enhance the accuracy level in the detection of brain tumor and provides better performance than existing method based on high accuracy rate and low computing time. The process of tumor detection comprises three steps (i) Segmentation (ii) Feature extraction (iii) Classification. Various algorithms are developed for image processing in which we take Histogram thresholding for image segmentation and Support Vector Machine (SVM) for classify the image as Benign or Malignant. [ABSTRACT FROM AUTHOR]

Published
2021
Full Text
View/download PDF

44. Investigations on non-biodegradable zirconium dioxide reinforced aluminium alloy (AA6081) matrix composite developed by using powder metallurgy route.

Author

Kavitha, K. R., Prakash, S., and Ravichandran, M.

Subjects
*POWDER metallurgy, *ALUMINUM alloys, *ZIRCONIUM oxide, *IMPACT strength, *SURFACES (Technology), *SLIDING wear
Abstract

Aluminium alloy (AA6081) composites reinforced with Zirconium Dioxide (ZrO2) have been produced through Powder Metallurgy (PM). The ZrO2 particles have been included in the matrix based on the weight percentages to produce various compositions such as AA6081-2 wt. % ZrO2, AA6081-4 wt. % ZrO2, AA6081-6 wt. % ZrO2 and AA6081-8 wt. % ZrO2. The Crystallographic Structure of a material and Surface topology and composition analysis was conducted for the green and sintered composite samples. Theoretical density, green and sintered density of the samples has been reported. The wear rate (WR) of the AA6081-8 wt. % ZrO2 composite was studied using Pin on disc (POD). Taguchi was applied to study the wear parameters (Load P; Sliding distance D; Sliding velocity V) and the systematic and statistical analysis was conducted by L9 array. The mechanical properties such as hardness, compressive strength (CS) and impact strength was enhanced for the inclusion of ZrO2 particles in the AA6081 matrix up to 8 wt. %. Wear studies of AA6081-8 wt. % ZrO2 composite revealed that the P is the most dominant factor for WR. ANOVA analysis revealed that load is highly contributed parameter for the WR of the PM composite. [ABSTRACT FROM AUTHOR]

Published
2021
Full Text
View/download PDF

45. Three factor nonnegative matrix factorization based HE stain unmixing in histopathological images.

Author

Sikkandar, Mohamed Yacin, Jayasankar, T., Kavitha, K. R., Prakash, N. B., Sudharsan, Natteri M., and Hemalakshmi, G. R.

Abstract

Histological staining facilitates the microscopic study of diseased tissues in clinical investigations. Staining by fluorescent dyes enhances the tissue contrast, highlighting the important features. Haematoxylin and Eosin staining protocol is the most common in the histopathological analysis of cells and tissues in cancer diagnosis. HE staining provides a visual representation of tissue abnormalities, distinguishing cell nuclei and acidophilic structures. Stain unmixing is an equally vital procedure which decomposes the multi-stained image into individual stain components. These components are essential for visual examination of the interaction between the dye and the specific tissues. This manuscript put forwards an original cell destaining approach based on a three factor Nonnegative Matrix Factorization which separates the H and E components from the HE stained image. The experimental results with standard datasets and performance metrics demonstrate the robustness of the method yielding better PSNR and SSIM values for stain separation compared to similar works in this context. The PSNR values around 30 dB are achieved by the proposed unmixing approach which is more than 10 dB compared to the benchmark approaches. Similarly, the SSIM values are obtained in the range 0.42–0.73, signifying strong structural elements. The proposed method can be further extended to study the interaction of other activators in the wound repair process under cancer progression. [ABSTRACT FROM AUTHOR]

Published
2021
Full Text
View/download PDF

46. Fabrication of hexagonal shaped CuCo2S4 nanodiscs/graphene composites as advanced electrodes for asymmetric supercapacitors and dye sensitized solar cells (DSSCs).

Author

Kavitha, K. R., Murali Babu, B., and Vadivel, S.

Subjects
SUPERCAPACITOR electrodes, DYE-sensitized solar cells, ENERGY conversion, ENERGY density, ELECTRODES, SPECIFIC gravity
Abstract

In this report, CuCo2S4/graphene (abbreviated as CCS–G) hybrid electrodes were fabricated via facile and one step hydrothermal route. The fabricated electrodes were characterized by XRD, Raman, TEM, BET and XPS to investigate the structural, morphological and elemental composition properties. N2 adsorption–desorption studies showed that CCS–G indicates the maximum specific area of 112 m2 g−1 related to CCS (77 m2 g−1). The CuCo2S4/graphene electrode deliver a high specific capacitance 1625 F g−1 at relative current density of 2 A g−1 and high cyclic retention of 97% after 5000 cycles experiment. Interestingly, asymmetric device CCS–G//AC was fabricated and it shows high energy density of 27 Wh Kg−1 with relative power density of 5100 W Kg−1. The sandwich type dye sensitized solar cell (DSSC) was fabricated and tested the J–V and IPCE analysis. The finding reveals that CuCo2S4/graphene electrode shows high PCE (11.85%) and long term stability. The superior PCE of the composite is due to the heterostructure, mesoporous nature and high surface area with enhanced light harvesting capacity. Due to the high photovoltaic and electrocatalytic activity of CuCo2S4/graphene heterostructure can be useful for energy conversion and storage device applications. [ABSTRACT FROM AUTHOR]

Published
2021
Full Text
View/download PDF

47. Performance analysis of latent heat storage system by fin orientation and nano added PCM for diesel engine waste heat recovery.

Author

Paramasivam, Karthikeyan, Balakrishnan, Kanimozhi, Ramar, Kumarasubramanian, Subramani, Yuvaraja, Samal, Swaraj Bikram, Sinha, Rishabh, Sasipraba, T, Subramaniam, Prakash, Jayaprabakar, J, Joy, Nivin, Anish, M, Ganesan, S, and Kavitha, K R

Subjects
HEAT recovery, HEAT storage, HEAT engines, LATENT heat, DIESEL motors, WASTE heat
Abstract

The Latent Thermal Energy Storage (LHTES) device is most commonly used in waste heat recovery systems because of its high-energy storage capacity. Heat transfer enhancement also with various finned profiles. The current study is carried out to discover the effective waste heat recovery system from single cylinder diesel engine. The LHTES system is developed with inner shell and outer shell made up of steel for storing PCM and water circulation for unloading respectively. The spiral copper tube is placed inside the inner shell, through which heat transfer oil is circulated for loading purpose. The temperature changes inside the LHTES systems is studied for D-sorbitol Phase Change Material (PCM) without Nano material and with Graphite added Nano PCM. In addition, its performance is compared with internally finned inner shell. Results reveals that the heat transfer rate during is increased to 23% for PCM with Nano material compared with PCM without Nano material. Further, more it is increased about 8% for finned LHTES system. [ABSTRACT FROM AUTHOR]

Published
2020
Full Text
View/download PDF

48. Thermal performance of single glazing V-through solar collector using horizontal and vertical nail cut twisted tape insert.

Author

Venkatesan, S. P., Annamalai, S., Arun, S., Purusothaman, M., Hemanandh, J., Ganesan, S., Sasipraba, T, Subramaniam, Prakash, Jayaprabakar, J, Joy, Nivin, Anish, M, Ganesan, S, and Kavitha, K R

Subjects
SOLAR collectors, HEAT, SUNGLASSES, GLAZES, HEAT pipes, INTRAMEDULLARY rods, ADHESIVE tape
Abstract

Thermal energy is very lots beneficial in the human day by day lifestyles whereas it is transformed from solar strength. One of the green methods of garnering warm energy is from the sun plate collector. This paper emphasizes an experimental observe of Nusselt range (Nu), Friction element (fr) and Thermal overall performance (η) of the Double-V-Trough solar Collector (DGVT) ready with plain twisted tape (PTT), horizontal wing twisted tape (HWTT) and vertical wing twisted tape(VWTT) bets under one of a kind turning situations (Y=3& 6) and same working mode. DGVT's warmness transfer capacity is better than an unmarried glass V-Trough sun collector (SGVT) with eight.84%. The usage of the double glazing glass within the V-Trough collector reduces the thermal coefficient which improves the thermal performance. Empirical data has been validated with basic equation and its associated errors are less than ± 14.79% & ± 4.17% for Nu and respectively. The experimental results showed that Nu, frand η in DGVT associated with HWTT were significantly higher than in the tube equipped with VWTT and PTT. The additional fluid disruption close to the tube wall persuaded by the wing and the secondary flow near the tube wall represented by HWTT and VWTT relative to the induced by PTT was determined as the cause of enrichment. Correlations are developed for Nu and to match experimental results and deviation falls within ± 9.25% and ± 7.18%, respectively. [ABSTRACT FROM AUTHOR]

Published
2020
Full Text
View/download PDF

49. Visualization of a vortex ring from an evolving plume.

Author

Krishnanand, S., Lingeshwar, R., Thiruvateeswaran, S., Thiagarajan, Kannan Budda, Sasipraba, T, Subramaniam, Prakash, Jayaprabakar, J, Joy, Nivin, Anish, M, Ganesan, S, and Kavitha, K R

Subjects
VISUALIZATION, DIGITAL cameras
Abstract

The present paper is about the vortex ring production and its visualization using laser-based techniques. The tracer used is produced from a smoke emitting incense material via burning. The flow field is illuminated by using a pointer laser to produce a light sheet for image recording. A digital camera is used to capture the images and the captured images are post-processed for further analysis. The flow field show the evolution of plume, ejection of vortex ring and finally the evolution of free vortex ring. [ABSTRACT FROM AUTHOR]

Published
2020
Full Text
View/download PDF

50. Design of smart container in refrigerator for convenience usage.

Author

Mani, Purusothaman, Santhoshkumar, A., Kumar, K. Manoj, Siva, R., Gnanamani, Senthilkumar, Janarthanam, Hemanandh, Ponnappan, Venkatesan Sorakka, Sasipraba, T, Subramaniam, Prakash, Jayaprabakar, J, Joy, Nivin, Anish, M, Ganesan, S, and Kavitha, K R

Subjects
REFRIGERATORS, CONTAINERS, COOLING, HOUSEHOLDS, SMART power grids
Abstract

Now a days everyone has a refrigerator in their home for the purpose to store foods, medicines and eatables etc. Some foods based on its property we can directly use after we taken out from the refrigerator. But under some conditions we can't use the products directly from the refrigerator so we need to bring the product into room temperature for better usage. If not done so some medical issues are being raised so to avoid this, we have a solution smart container in refrigerator which does the de-cooling in the refrigerator itself no need to keep it in temperature and this is a remotely operable from anywhere using IOT. This must be done in an efficient manner and the approach to solve this aspect is discussed further. The following we made cad design for the smart container. Before manufacturing we need the visual proof whether it is suitable are not to our daily household use the factor considered is the refrigerator temperature and the environmental temperature. Under this condition we are going to calculate the time. How long it will take to cool the container. The whole analysis is made in computational manner using the ANSYS software. The final verified result shows the time taken to cool the container is 14 seconds. The analysis result for time taken to de cool the container is 19.5 sec. According to the ANSYS report 20 iterations are need to make the calculation of the time. This will give the better and expected results. [ABSTRACT FROM AUTHOR]

Published
2020
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results