Sivaji Satrasupalli
Sivaji Satrasupalli has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Anil B. Kumar
Department of ECE, GMR Institute of Technology (GMRIT)-Deemed to be University, Rajam, India
1 shared publication - B. Srinivas
Electronics and Communication Engineering, MVGR College of Engineering (A), Vizianagaram, India
1 shared publication Ch. Vijayakumar
School of Electronics, Vignan University, Vadlamudi, A.P, India
1 shared publicationEbenezer Daniel
Vignan's Foundation for Science Technology and Research Department of Electronics and Communications Engineering, Vadlamudi Guntur AP 522213 India
1 shared publicationK. Vijay Kumar
School of Electronics, Vignan University, Vadlamudi, A.P, India
1 shared publication- Lavanya Bagadi
MVGR College of Engineering (A), Vizianagaram, India
1 shared publication
Latest Publications
- Open Access
- 1 January 2024
- Published by National Library of Serbia in Facta universitatis - series: Electronics and Energetics
- Vol. 37 (2) , 261-276
Deep learning-based modified transformer model for automated news article summarization
The amount of textual data on the internet is increasing enormously, so data summarization into text has become essential. As generating text summaries manually is an arduous task and humans are generally prone to make mistakes, deep learning techniques have evolved to overcome this problem. Modified transformer-based deep learning models with varying encoder-decoder and feed-forward network layers are proposed to develop an abstractive summary of the news articles. The proposed transformer model provides the advantage of parallelization with the help of multiple attention head layers to process long sentences, and hence, better text summarization performance is achieved. These models are trained on an ?in-shorts? dataset, and the proposed model is compared with the PEGASUS-CNNdaily-mail, BART-large-CNN, and DistilBART-CNN-12-6 models on the CNN/DailyMail dataset. The performance is evaluated in terms of the ROUGE score by comparing it with the existing Recurrent Neural Network (RNN) model. The suggested transformer model achieved a ROUGE score of 0.33, surpassing the RNN model score of 0.17. This innovative approach can be employed on extensive textual data to extract summaries or headlines.
- 1 January 2024
- Published by National Library of Serbia in Facta universitatis - series: Electronics and Energetics
- Vol. 37 (2) , 261-276
Open AccessDeep learning-based modified transformer model for automated news article summarization
The amount of textual data on the internet is increasing enormously, so data summarization into text has become essential. As generating text summaries manually is an arduous task and humans are generally prone to make mistakes, deep learning techniques have evolved to overcome this problem. Modified transformer-based deep learning models with varying encoder-decoder and feed-forward network layers are proposed to develop an abstractive summary of the news articles. The proposed transformer model provides the advantage of parallelization with the help of multiple attention head layers to process long sentences, and hence, better text summarization performance is achieved. These models are trained on an ?in-shorts? dataset, and the proposed model is compared with the PEGASUS-CNNdaily-mail, BART-large-CNN, and DistilBART-CNN-12-6 models on the CNN/DailyMail dataset. The performance is evaluated in terms of the ROUGE score by comparing it with the existing Recurrent Neural Network (RNN) model. The suggested transformer model achieved a ROUGE score of 0.33, surpassing the RNN model score of 0.17. This innovative approach can be employed on extensive textual data to extract summaries or headlines.
- Open Access
- 1 December 2020
- Published by Institution of Engineering and Technology (IET) in IET Image Processing
- Vol. 14 (17) , 4736-4743
End to end system for hazy image classification and reconstruction based on mean channel prior using deep learning network
Outdoor images are having several applications including autonomous vehicles, geo‐mapping, and surveillance. It is a common phenomenon that the images captured outdoor are prone to noise, which arises due to natural and manmade extreme atmospheric conditions such as haze, fog, and smog. Importantly in autonomous vehicle navigation, it is very important to recover the ground truth image to get the better decision by the system. Estimation of the transmission map and air‐light is very crucial in recovering the ground truth image. In this study, the authors proposed a new method to estimate the transmission map based on a mean channel prior (MCP), which represents the depth map to estimate the transmission map. The authors proposed a deep neural network to identify the hazy image for the further dehazing process. In this study, the authors presented, two novel contributions, first an MCP‐based image dehazing and second, a deep neural network‐based identification of hazy images as a pre‐processing block in the proposed end to end system. The proposed deep learning network using the TensorFlow platform provided validation accuracy of 93.4% for hazy image classification. Finally, the proposed MCP‐based dehazing network showed better performance in terms of peak‐signal‐to‐noise ratio, structural similarity index, and computational time than that of existing methods.
- 1 December 2020
- Published by Institution of Engineering and Technology (IET) in IET Image Processing
- Vol. 14 (17) , 4736-4743
Open AccessEnd to end system for hazy image classification and reconstruction based on mean channel prior using deep learning network
Outdoor images are having several applications including autonomous vehicles, geo‐mapping, and surveillance. It is a common phenomenon that the images captured outdoor are prone to noise, which arises due to natural and manmade extreme atmospheric conditions such as haze, fog, and smog. Importantly in autonomous vehicle navigation, it is very important to recover the ground truth image to get the better decision by the system. Estimation of the transmission map and air‐light is very crucial in recovering the ground truth image. In this study, the authors proposed a new method to estimate the transmission map based on a mean channel prior (MCP), which represents the depth map to estimate the transmission map. The authors proposed a deep neural network to identify the hazy image for the further dehazing process. In this study, the authors presented, two novel contributions, first an MCP‐based image dehazing and second, a deep neural network‐based identification of hazy images as a pre‐processing block in the proposed end to end system. The proposed deep learning network using the TensorFlow platform provided validation accuracy of 93.4% for hazy image classification. Finally, the proposed MCP‐based dehazing network showed better performance in terms of peak‐signal‐to‐noise ratio, structural similarity index, and computational time than that of existing methods.
- 1 December 2013
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 439-443
Sensors based automated wheelchair
Physically challenged persons may not be able to steer their wheelchair conveniently with the available assistive technologies. Though there are many methods available in recent times to enable their motility, they require efficient and precise control which is most of the times not possible. In recent times there are various control systems that are developed and under developing stage especially for people with various disorders and disabilities. In this project each eye will be having IR transmitter and receiver. Transmitter IR will transmit the light over iris and reflected light will received by IR receiver. Depending upon the intensity of reflected light falling on the receiver, the controller will be understand the user intention of wheelchair movement. Now controller will take the decision of moving forward, left or right as long as IR receiver receives the directions information from the user. DC motors are used to apply torque to the individual wheels so that direction control can be ensured. This system enables the patient to have command over the chair, its direction of movement and the system will also will also sense and alarm the user about the obstacles in the path to avoid any severe consequences the accelerometer monitors the inclination of the wheelchair. This wheelchair helps the patient to move in environments with ramps and doorways of little space by establishing communication between human eye iris and IR sensor.
- 1 December 2013
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 439-443
Sensors based automated wheelchair
Physically challenged persons may not be able to steer their wheelchair conveniently with the available assistive technologies. Though there are many methods available in recent times to enable their motility, they require efficient and precise control which is most of the times not possible. In recent times there are various control systems that are developed and under developing stage especially for people with various disorders and disabilities. In this project each eye will be having IR transmitter and receiver. Transmitter IR will transmit the light over iris and reflected light will received by IR receiver. Depending upon the intensity of reflected light falling on the receiver, the controller will be understand the user intention of wheelchair movement. Now controller will take the decision of moving forward, left or right as long as IR receiver receives the directions information from the user. DC motors are used to apply torque to the individual wheels so that direction control can be ensured. This system enables the patient to have command over the chair, its direction of movement and the system will also will also sense and alarm the user about the obstacles in the path to avoid any severe consequences the accelerometer monitors the inclination of the wheelchair. This wheelchair helps the patient to move in environments with ramps and doorways of little space by establishing communication between human eye iris and IR sensor.