K. Bhanu Rekha
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
K. Bhanu Rekha has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- S. Safinaz
Department of Electronics & Communications Engineering, Presidency University, Bangalore, India
3 shared publications N. Chitra
Department of Electronics and Communication Engineering, Presidency University, Bangalore
1 shared publication- P. P. Pavitha
Department of Electronics & Communication, Presidency University, India
1 shared publication Safinaz S
Presidency University
1 shared publication- Thangimi Swarna Latha
Department of Electronics and Communications Engineering, School of Electronics Engineering, Presidency University, Bangalore 560064, Karnataka, India
1 shared publication
Latest Publications
- Open Access
- 8 February 2024
- Published by Engineering, Technology & Applied Science Research in Engineering, Technology & Applied Science Research
- Vol. 14 (1) , 13052-13057
RIOD:Reinforced Image-based Object Detection for Unruly Weather Conditions
Deep Neural Network (DNN) object detectors have proved their efficiency in the detection and classification of objects in normal weather. However, these models suffer a lot during bad weather conditions (foggy, rain, haze, night, etc.). This study presents a new scheme to reduce the aforementioned issue by attenuating the noise in the input image before feeding it to any kind of neural network-based object detector. In this study, the image optimization function transforms subpar-quality images due to bad weather into pictures with the optimal possible quality by estimating the proper illumination and transmission function. These optimized images showed improved object detection rates in the YOLOv4 and YOLOv5 models. This improvement in object detection was also noticed in the case of video input. This scheme was tested with images/videos from various weather conditions, and the results showed an encouraging improvement in detection rates.
- 8 February 2024
- Published by Engineering, Technology & Applied Science Research in Engineering, Technology & Applied Science Research
- Vol. 14 (1) , 13052-13057
Open AccessRIOD:Reinforced Image-based Object Detection for Unruly Weather Conditions
Deep Neural Network (DNN) object detectors have proved their efficiency in the detection and classification of objects in normal weather. However, these models suffer a lot during bad weather conditions (foggy, rain, haze, night, etc.). This study presents a new scheme to reduce the aforementioned issue by attenuating the noise in the input image before feeding it to any kind of neural network-based object detector. In this study, the image optimization function transforms subpar-quality images due to bad weather into pictures with the optimal possible quality by estimating the proper illumination and transmission function. These optimized images showed improved object detection rates in the YOLOv4 and YOLOv5 models. This improvement in object detection was also noticed in the case of video input. This scheme was tested with images/videos from various weather conditions, and the results showed an encouraging improvement in detection rates.
- Open Access
- 20 December 2023
- Published by MDPI AG in Engineering Proceedings
- Vol. 59 (1) , 91
A Novel DV-HOP and APIT Localization Algorithm with BAT-SA Algorithm
Localization technology is essential for making wireless sensor networks(WSN)’s information processing and information collecting applications actually feasible. The beacon information is made available to the unknown nodes using the route exchange protocol. These data are more useful for determining the coordinates of neighboring nodes. Consequently, it was discovered that the algorithm for localizing nodes always has a flaw. Consequently, a brand-new metaheuristic termed Bat with simulated annealing is proposed to fix the flaw in the WSN standard node localization technique. The overall effectiveness of identifying the nodes is enhanced as a result of the large reduction in localization errors. The most popular localization estimation methods are the distance vector hop (DV-Hop) technique and approximate point-in-triangulation (APIT), which have high node localization accuracy and simple deployment in real-time environments. The primary benefits and their disadvantages, which give it a slight disadvantage in preference, are presented in this work. Both strategies are compared for their conventional performance and efficiency when combined with the Bat-SA algorithm.
- 20 December 2023
- Published by MDPI AG in Engineering Proceedings
- Vol. 59 (1) , 91
Open AccessA Novel DV-HOP and APIT Localization Algorithm with BAT-SA Algorithm
Localization technology is essential for making wireless sensor networks(WSN)’s information processing and information collecting applications actually feasible. The beacon information is made available to the unknown nodes using the route exchange protocol. These data are more useful for determining the coordinates of neighboring nodes. Consequently, it was discovered that the algorithm for localizing nodes always has a flaw. Consequently, a brand-new metaheuristic termed Bat with simulated annealing is proposed to fix the flaw in the WSN standard node localization technique. The overall effectiveness of identifying the nodes is enhanced as a result of the large reduction in localization errors. The most popular localization estimation methods are the distance vector hop (DV-Hop) technique and approximate point-in-triangulation (APIT), which have high node localization accuracy and simple deployment in real-time environments. The primary benefits and their disadvantages, which give it a slight disadvantage in preference, are presented in this work. Both strategies are compared for their conventional performance and efficiency when combined with the Bat-SA algorithm.
- Open Access
- 23 February 2023
- Published by International Association of Online Engineering (IAOE) in International Journal of Interactive Mobile Technologies (iJIM)
- Vol. 17 (04) , 75-88
Divergence Based Feature Selection for Pattern Recognizing of the Performance of Intrusion Detection in Mobile Communications Merged with the Computer Communication Networks
The Feature Selection concept is the procedure where in the data is simplified removing the irrelevant features. Divergence method is another strategy of method where in the relation among the attributes and class is measured to understand their contribution to performance. Nowadays the mobile network is integrated with the other networks like the computer networks transmitting all kinds of data leading to attacks in networks known as intrusion in computer networks equally applicable to mobile communications. So in this paper the intrusion detection method involving the other other mode of communication is considered in mobile interaction network. The proposed algorithm performs feature selection using the divergence evaluation method to reduce the feature set. A 10% KDDCUP99 data set was used for the evaluation of the proposed algorithm, and performance metrics were evaluated using the C4.5 classifier. The metrics TPR, FPR and consistency were compared with the mutual information based DMIFSA, RMIFSA, MMIFSA methods and the proposed method is implemented on Python 3.8 that proved to achieve the high accuracy of 99.94% as compared to other methods and also reduce the redundant features. The consistency in Accuracy is maintained almost from 4 features to 10 features in proposed method as compared to other methods that indicates the stability of the system is achieved.
- 23 February 2023
- Published by International Association of Online Engineering (IAOE) in International Journal of Interactive Mobile Technologies (iJIM)
- Vol. 17 (04) , 75-88
Open AccessDivergence Based Feature Selection for Pattern Recognizing of the Performance of Intrusion Detection in Mobile Communications Merged with the Computer Communication Networks
The Feature Selection concept is the procedure where in the data is simplified removing the irrelevant features. Divergence method is another strategy of method where in the relation among the attributes and class is measured to understand their contribution to performance. Nowadays the mobile network is integrated with the other networks like the computer networks transmitting all kinds of data leading to attacks in networks known as intrusion in computer networks equally applicable to mobile communications. So in this paper the intrusion detection method involving the other other mode of communication is considered in mobile interaction network. The proposed algorithm performs feature selection using the divergence evaluation method to reduce the feature set. A 10% KDDCUP99 data set was used for the evaluation of the proposed algorithm, and performance metrics were evaluated using the C4.5 classifier. The metrics TPR, FPR and consistency were compared with the mutual information based DMIFSA, RMIFSA, MMIFSA methods and the proposed method is implemented on Python 3.8 that proved to achieve the high accuracy of 99.94% as compared to other methods and also reduce the redundant features. The consistency in Accuracy is maintained almost from 4 features to 10 features in proposed method as compared to other methods that indicates the stability of the system is achieved.
- Open Access
- 24 June 2022
- Published by Springer Nature in Research Square
Hybrid Image Compression technique using Deep Learning model for enhanced reliability and data transmission
Image compression is the way of data compression which could be applicable to digital form of images for the purpose of reducing the cost of storage or transmission and any algorithm would consider visual perception or statistical properties of an image to establish enhanced results. The compression techniques might be lossy or lossless type. The supreme image quality at a particular compression rate is the major aim of any image compression approach. Objective: In this current research, image compression is carried out with the support of hybrid Convolution Neural Network (CNN) and Random Forest (RF) approach. Data description: The proposed methodology is executed in python environment and the performance metrics is evaluated and outcomes attained are compared with existing research works to verify the effectiveness of suggested concept.
- 24 June 2022
- Published by Springer Nature in Research Square
Open AccessHybrid Image Compression technique using Deep Learning model for enhanced reliability and data transmission
Image compression is the way of data compression which could be applicable to digital form of images for the purpose of reducing the cost of storage or transmission and any algorithm would consider visual perception or statistical properties of an image to establish enhanced results. The compression techniques might be lossy or lossless type. The supreme image quality at a particular compression rate is the major aim of any image compression approach. Objective: In this current research, image compression is carried out with the support of hybrid Convolution Neural Network (CNN) and Random Forest (RF) approach. Data description: The proposed methodology is executed in python environment and the performance metrics is evaluated and outcomes attained are compared with existing research works to verify the effectiveness of suggested concept.