Dr.Ramesh Babu Vallabhaneni
@nriit.edu.in
Professor ECE
NRI Institute of Technoloy Agiripalli
RESEARCH INTERESTS
Image processing
VLSI Design
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
Scopus Publications
Battula Balnarsaiah, B. Ashok Nayak, G. Spica Sujeetha, B. Surendra Babu, and Ramesh Babu Vallabhaneni
Springer Science and Business Media LLC
Ramesh Babu Vallabhaneni, Pankaj Sharma, Vinit Kumar, Vyom Kulshreshtha, Koya Jeevan Reddy, S. Selva Kumar, V. Sandeep Kumar, and Surendra Kumar Bitra
Institute of Electrical and Electronics Engineers (IEEE)
In recent years, deep learning algorithms have been developed rapidly, and they are becoming a powerful tool in biomedical engineering. Especially, there has been an increasing focus on the use of deep learning algorithms for decoding physiological or pathological status of the brain from electroencephalographic (EEG). This paper overviews current application of deep learning algorithms in various EEG decoding tasks, and introduces commonly used algorithms, typical application scenarios, important progresses and existing problems. Firstly, the basic principles of deep learning algorithms used in EEG decoding is briefly described, including convolutional neural network, deep belief network, auto-encoder and recurrent neural network. In this paper, existing applications of deep learning on EEG is discussed, including brain-computer interfaces, cognitive neuroscience and diagnosis of brain disorders. Finally, this paper outlines some key problems that will be addressed in future applications of deep learning for EEG decoding, such as parameter selection, computational complexity, and the capability of generalization.
Ramesh Babu Vallabhaneni and V. Rajesh
Elsevier BV
Ramesh Babu Vallabhaneni and V. Rajesh
IEEE
Segmentation is a process for classifying different pixels which are in different range but color segmentation process of identifying the color of the pixel and segmenting the image into different color image. This color segmentation process is carried out by using WATERSHED algorithm which has been proposed earlier to identifying the pixels of same range and noise reduction process. This is applied in medical field for segmenting the MRI and CT scanned image for detecting the tumour present in the brain.
Ramesh Babu Vallabhaneni and V. Rajesh
Praise Worthy Prize
Detection of tumour in brain has most prominence in the recent years. Various processes are proposed for detecting BRAIN TUMOUR which comprises with image segmentation and classification process. But classification process has dominant and suppressed most of the techniques by its advantages of detecting and classifying brain tumour. In this paper a novel approach of Wavelet watershed technique is proposed with MULTI RBF SVM classifier process for segmentation and classification processes respectively. The feature extraction and region segmentation processes were completed by Wavelet Watershed technique for this we used to calculate the energy of the image for a texture level classification mode. Under Multi SVM classifier the weight comes into play for training datasets along with classification mode. Experimental results are acquired from the proposed technique is about 95%.
Lakshmana Phaneendra Maguluri, Ramesh Babu Vallabhaneni, and V. Rajesh
IEEE
Clustering algorithms are used for segmenting Digital images however noise are introduced into images during image acquisition, due to switching, sensor temperature. They may also occur due to interference in the channel and due to atmospheric disturbances during image transmission and affecting the segmentation results Noise reduction is a pulmonary step prior to feature extraction attempts from digital images. In order to overcome this drawback, this paper presents a new clustering based segmentation technique that can be used in segmenting noise in Digital images. We named this approach as De noising based Optimized K-means clustering algorithm (DOKM).where De noising is fully data driven approach. The qualitative and quantitative analyses have been performed to investigate the robustness of the OKM algorithm. And this new approach is effective to avoid dead centre and trapped centre in segmented Digital Images.