10 results on '"Usha Rani, B."'
Search Results
2. Image Denoising Using Deblur Generative Adversarial Network Denoising U-Net.
- Author
-
Usha Rani, B., Aruna, R., Velrajkumar, P., Amuthan, N., and Sivakumar, N.
- Subjects
- *
CONVOLUTIONAL neural networks , *GENERATIVE adversarial networks , *IMAGE denoising , *SIGNAL-to-noise ratio , *RANDOM noise theory - Abstract
Convolutional neural networks (CNNs) are becoming increasingly popular for image denoising. U-Nets, a type of CNN architecture, have been shown to be effective for this task. However, the impact of shallow layers on deeper layers decreases as the depth of the network increases. To address this issue, the authors propose a new image denoising method called DGANDU-Net. DGANDU-Net combines the DeblurGAN design with a U-Net architecture. This combination allows DGANDU-Net to effectively remove noise from images while preserving fine details. The authors also propose the use of two loss functions, mean square error (MSE) and perceptual loss, to improve the performance of DGANDU-Net. MSE is used to learn and improve the extracted features, while perceptual loss is used to produce the final denoised image. The authors evaluate the performance of DGANDU-Net on a variety of noise levels and find that it outperforms other state-of-the-art denoising algorithms in terms of both visual quality and two evaluation indices, including peak signal-to-noise ratio (PSNR) and Structural Similarity Index Measure (SSIM). Specifically, for extremely noisy environments with a noise standard deviation of 75, DGANDU-Net achieves an average PSNR of 37.39dB in the test dataset. The authors conclude that DGANDU-Net is a promising new method for image denoising that has the potential to significantly improve the quality of medical images used for diagnosis and treatment. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
3. Optimizing solar power plant efficiency through advanced analytical framework and comparative analysis
- Author
-
Senthil Kumar, V., primary, Aruna, R., additional, Varalatchoumy, M., additional, Manikannan, P., additional, Santhana Krishnan, T., additional, Usha Rani, B., additional, Kumar, Ashok, additional, and Rajaram, A., additional
- Published
- 2024
- Full Text
- View/download PDF
4. SELECTIVE MAC FOR OBSTACLE AWARE CEV ENVIRONMENTAL MODEL FOR VANET (V2V)
- Author
-
Suraiya Tarannum and Usha Rani B
- Subjects
VANET ,lcsh:Computer engineering. Computer hardware ,Vehicular ad hoc network ,lcsh:T58.5-58.64 ,lcsh:Information technology ,business.industry ,Computer science ,ComputerSystemsOrganization_COMPUTER-COMMUNICATIONNETWORKS ,lcsh:TK7885-7895 ,Path Loss ,V2V ,Obstacle ,WAVE ,DSRC ,IEEE 802.11p ,business ,Computer network ,Environmental model - Abstract
Vehicular Ad Hoc Network (VANET) adopts or resembles a similar structure of Mobile adhoc network (MANET). VANET using the IEEE 802.11p standard has great potential of achieving objectives of Smart intelligent transport system (SITS) for improving transport and road safety efficiency. To guarantee QoS and provide efficient network performance, a prioritized MAC need to be designed. Many priority based MAC has been designed in recent times to improve the quality of data delivery to end user. However these do not consider the impact of environment and presence of obstacle which affects the signal attenuation at the receiver end and affecting the QoS of channel availability. To address, this work present an obstacle based radio propagation model, obstacle based CEV (City, Expressway and Village) environmental model and a selective MAC to provide QoS for different services. The proposed model efficiency is evaluated in term of throughput achieved per channel, Collison and success packet transmission. To evaluate the adaptive performance of proposed AMAC experiment are conducted under CEV environment and are compared with existing MAC NCCMA. The outcome achieved shows that the proposed model is efficient in term of reducing Collison, improving packet transmission and throughput performance considering two types of services.
- Published
- 2017
- Full Text
- View/download PDF
5. Selective MAC for Obstacle Aware CEV Environmental Model for V2V
- Author
-
Usha Rani B and Suraiya Tarannum
- Subjects
Engineering ,VANET ,Control and Optimization ,Computer Networks and Communications ,Wireless ad hoc network ,Throughput ,02 engineering and technology ,01 natural sciences ,0202 electrical engineering, electronic engineering, information engineering ,Network performance ,IEEE 802.11p ,Electrical and Electronic Engineering ,Path loss ,Vehicular ad hoc network ,business.industry ,Quality of service ,010401 analytical chemistry ,ComputerSystemsOrganization_COMPUTER-COMMUNICATIONNETWORKS ,020206 networking & telecommunications ,Mobile ad hoc network ,Dedicated short-range communications ,0104 chemical sciences ,Hardware and Architecture ,V2V ,Signal Processing ,DSRC ,business ,Information Systems ,Computer network - Abstract
Vehicular adhoc network (VANET) adopts or resembles a similar structure of Mobile adhoc network (MANET). The communication in VANET are generally classified into following three categories such as Vehicle to Infrastructure (V2I), Vehicle to Vehicle (V2V) and Hybrid network which is a combination of V2V and V2I network. VANET using the IEEE 802.11p standard has great potential of achieving objectives of Smart intelligent transport system (SITS) for improving transport and road safety efficiency. As more and more services is been provided for V2V based VANET network. It is a challenging task to provide QoS to end user, due to wireless medium that has limited channel availability for transmission. To guarantee QoS and provide efficient network performance, a prioritized MAC need to be designed. Many priority based MAC has been designed in recent times to improve the quality of data delivery to end user. However these do not consider the impact of environment and presence of obstacle which affects the signal attenuation at the receiver end and affecting the QoS of channel availability. To address, this work present an obstacle based radio propagation model, obstacle based CEV (City, Expressway and Village) environmental model and a selective MAC to provide QoS for different services. The proposed model efficiency is evaluated in term of throughput achieved per channel, Collison and success packet transmission. To evaluate the adaptive performance of proposed AMACexperiment are conducted under CEV environment and are compared with existing MAC NCCMA. The outcome achieved shows that the proposed model is efficient in term of reducing Collison, improving packet transmission and throughput performance considering two types of services.
- Published
- 2017
6. CONVEX TRAVERSAL IN POLYGON WITH SEGMENT STABBING
- Author
-
Usha Rani B. and Elango S.
- Subjects
Polygon, Convex hull, Convexation, PTIME, Segment Stabbing, LOG-SPACE bounded ,TheoryofComputation_ANALYSISOFALGORITHMSANDPROBLEMCOMPLEXITY ,Computer Science::Computational Geometry ,MathematicsofComputing_DISCRETEMATHEMATICS - Abstract
Given a set S of disjoint simple polygons on a bounded 2D-Plane, we studied the problem of finding a set of polygon P, such that stabbing S by segment stabbing region in optimal way. We present a novel approach for solving the convex traversing method in PTIME. Convex traversing is a mechanism of layering continues convex hull extracted from points P. Whenever adding a point in the convex traversing plane, it is necessary to compute the whole convexation again, which contradict the better runtime. We introduce the new notion of dynamic algorithm to reduce the runtime of this problem into LOG-SPACE bounded. Hence output produced at every dynamic modification results only a LOG-SPACE bounded reconstruction.  
- Published
- 2016
- Full Text
- View/download PDF
7. Regulation of flowering in acid lime (Citrus aurantifolia Swingle)
- Author
-
Prabhu, M., primary, Parthiban, S., additional, Kumar, A. Ramesh, additional, Usha Rani, B., additional, and Jayasamundeeswari, A., additional
- Published
- 2017
- Full Text
- View/download PDF
8. Deforestation Factors Using Classification Techniques – a Survey
- Author
-
K.Saritha K.Saritha, S. Jyothi S. Jyothi, K.R. Manjula K.R. Manjula, and B. Usha Rani B. Usha Rani
- Subjects
education.field_of_study ,Land use ,business.industry ,Logging ,Environmental resource management ,Population ,Land cover ,Habitat ,Environmental protection ,Deforestation ,Environmental science ,Forest farming ,Arable land ,business ,education - Abstract
Forests serve a number of ecological purposes including important roles in the water cycle, providing habitat for plant which are most useful in medicines. Deforestation is the conversion of forested areas to non-forest land use such as arable land, urban use, logged area or wasteland. It is a process leading to a temporary or permanent deterioration in the density or structure of vegetation cover or its species composition. Deforestation has been attributed to socio-demographic factors, such as population growth and the political economy of class structure, and specific exploitation activities like growth in population, commercial logging, construction of roads, forest farming, agriculture, fuel wood gathering and other factors. But it is most important to know the factors in destruction of forests like the amount and location, the rate and speed and the causes of deforestation.Data collection techniques for forest inventories range from selecting ground surveys to using topographic maps, remote sensing. The composition and viability of a forest may be determined using a combination of remote sensing images and geographical information system. Classification is a method in which it defines small areas, on the image which are representative of each desired land cover category. The main aim of this paper is to study deforestation factors using data mining techniques to analyze the effects on forests loss are direct or indirect.
- Published
- 2011
- Full Text
- View/download PDF
9. Differential Space Time Frequency Codes for MIMO OFDM Systems
- Author
-
Usha Rani, B., primary and Ramanjaneyulu, K., additional
- Published
- 2016
- Full Text
- View/download PDF
10. SELECTIVE MAC FOR OBSTACLE AWARE CEV ENVIRONMENTAL MODEL FOR VANET (V2V).
- Author
-
Usha Rani B. and Tarannum, Suraiya
- Subjects
VEHICULAR ad hoc networks ,INTELLIGENT transportation systems ,IEEE 802.11 (Standard) - Abstract
Vehicular Ad Hoc Network (VANET) adopts or resembles a similar structure of Mobile adhoc network (MANET). VANET using the IEEE 802.11p standard has great potential of achieving objectives of Smart intelligent transport system (SITS) for improving transport and road safety efficiency. To guarantee QoS and provide efficient network performance, a prioritized MAC need to be designed. Many priority based MAC has been designed in recent times to improve the quality of data delivery to end user. However these do not consider the impact of environment and presence of obstacle which affects the signal attenuation at the receiver end and affecting the QoS of channel availability. To address, this work present an obstacle based radio propagation model, obstacle based CEV (City, Expressway and Village) environmental model and a selective MAC to provide QoS for different services. The proposed model efficiency is evaluated in term of throughput achieved per channel, Collison and success packet transmission. To evaluate the adaptive performance of proposed AMAC experiment are conducted under CEV environment and are compared with existing MAC NCCMA. The outcome achieved shows that the proposed model is efficient in term of reducing Collison, improving packet transmission and throughput performance considering two types of services. [ABSTRACT FROM AUTHOR]
- Published
- 2017
- Full Text
- View/download PDF
Catalog
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.