Papers by Ramchandra Manthalkar
GVIP-Volume8-Issue5-P1151547442
GVIP-Volume8-Issue3-P1151547440
Decoding Asynchronous Electroencephalogram (A-EEG) signals is a crucial challenge in the emerging... more Decoding Asynchronous Electroencephalogram (A-EEG) signals is a crucial challenge in the emerging field of EEG based Brain-Computer Interface (BCI). In the case of A-EEG signals, the time markers of motor activity are absent. The paper proposes a method to decompose the A-EEG signals using Gabor Elementary Function (GEF) designed with Gabor frames. The scale-space analysis extracts Gabor dominant frequencies from A-EEG signals. Statistical and temporal moment dependent features are used to create the feature vector for each estimated Gabor Band (GB). The statistical significance of the features is tested with the Kruskal-Wallis test. The deep neural network is implemented with Bi-directional Long Short-Term Memory (BiLSTM) block to classify the upper limb movement. The EEG data of healthy volunteers have been collected using the Enobio-20 electrode system and ArmeoSpring rehabilitation device. The proposed methodology has achieved an average classification accuracy of 96.83%, precis...
Computing in Cardiology Conference, Sep 1, 2013
In recent years, telecardiology has been growing in significance, due to the shortage of local ca... more In recent years, telecardiology has been growing in significance, due to the shortage of local caregivers in various parts of the world. As the cardiac data volume grows, compact representation becomes imperative in view of bandwidth, storage, power and other constraints. In this backdrop, we present empirical studies on electrocardiogram (ECG) signal representation using a wide variety of wavelet bases. Specifically, we arrange the transform coefficients in decreasing order of magnitude, and count the number of coefficients accounting for 99% of the signal energy (a sparser representation requires less number). We observe that 'Symlet' and 'Daubechies' families generally offer more compact representation compared to Meyer wavelet as well as biorthogonal and reverse biorthogonal families. In particular, the sparsest representation is provided by the 'sym4' (closely followed by the 'db4') wavelet basis for a broad class of ECG signals. Interestingly, this behavior is observed quite consistently across all fifteen (twelve standard and three Frank) leads. Our study assumes significance in the context of basis selection for various ECG signal processing applications, including compression, denoising and compressive sensing.
Addressing architectural distortion in mammogram using AlexNet and support vector machine
Informatics in Medicine Unlocked, 2021
Abstract Objective To address the architectural distortion (AD) which is an irregularity in the p... more Abstract Objective To address the architectural distortion (AD) which is an irregularity in the parenchymal pattern of breast. The nature of AD is extremely complex; still, the study is very much essential because AD is viewed as a primitive sign of breast cancer. In this study, a new convolutional neural network (CNN) based system is developed that performs classification of AD distorted mammograms and other mammograms. Methods In the first part, mammograms undergo pre-processing and image augmentation techniques. In the other half, learned and handcrafted features are retrieved. The AlexNet Pretrained CNN is utilized for extraction of learned features. The support vector machine (SVM) validates the existence of AD. For improved classification, the scheme is tested for various conditions. Results A sophisticated CNN based system is developed for stepwise analysis of AD. The maximum accuracy, sensitivity and specificity yielded as 92%, 81.50% and 90.83% respectively. The results outperform the conventional methods. Conclusion Based on the overall study, it is recommended that a combination of CNN pre-trained network and support vector machine is a good option for identification of AD. The study will motivate researchers to find improved methods of high performance. Further, it will also help the radiologists. Significance The AD can develop up to two years before the growth of any anomaly. The proposed system will play an essential role in the detection of early manifestations of breast cancer. The system will aid society to go for better treatment options for women all over the world and curtail the mortality rate.
Machine learning-based approach for segmentation of intervertebral disc degeneration from lumbar section of spine using MRI images
Bio-Algorithms and Med-Systems, 2021
Objectives Intervertebral disc segmentation is one of the methods to diagnose spinal disease thro... more Objectives Intervertebral disc segmentation is one of the methods to diagnose spinal disease through the degeneration in asymptomatic and symptomatic patients. Even though numerous intervertebral disc segmentation techniques are available, classifying the grades in the intervertebral disc is a hectic challenge in the existing disc segmentation methods. Thus, an effective Whale Spine-Generative Adversarial Network (WSpine-GAN) method is proposed to segment the intervertebral disc for effective grade classification. Methods The proposed WSpine-GAN method effectively performs the disc segmentation, wherein the weights of Spine-GAN are optimally tuned using Whale Optimization Algorithm (WOA). Then, the refined disc features, such as pixel-based features and the connectivity features are extracted. Finally, the K-Nearest Neighbor (KNN) classifier based on the pfirrmann’s grading system performs the grade classification. Results The implementation of the grade classification strategy base...
In order to advance the goal of anywhere anytime computing, the exposure to the risky transaction... more In order to advance the goal of anywhere anytime computing, the exposure to the risky transactions in mobile ad hoc networks has to be reduced as much as possible. This requires an existence of a trust management framework that enables nodes to form, maintain and exchange trust opinions. These opinions can then be used to customize the way interactions take place. A trust management framework for mobile ad hoc network (MANET) must be fully decentralized, highly customizable and selfish. In this paper, a fuzzy logic based trust management framework to establish, evaluate and propagate trust in MANET has been presented. In the proposed framework, trust is established by directly monitoring the evidences and obtaining fuzzy logic based recommendations from the neighboring nodes. A membership function is devised to take trust decision in a more accurate manner. This approach is optimistic in the sense that it allows more and more number of nodes to participate in network operations with...
PC Based Ecg Inte
Today no tool is available which can be used to analyze the routine 12 lead ECG dah. Computers wi... more Today no tool is available which can be used to analyze the routine 12 lead ECG dah. Computers with higher capabilities are available at reasonable cost. The capabilities of the computers allow us to use the Digital Signal Processing concepts at least for low frequency signals. ECG signal has frequencies in1 the range 0 to 40 Wz. Only patients having heart diseases will have fre- quencies in their ECG which will be above 50 Hz. At the most frequencies would be around 100 Hz. This is defi- nitely a low frequency range and we can use todays PCs in this range. A tool is evolved to analyze the routine 12 lead ECG data and to interpret it. Here the sampling frequency chosen to digitize ECG signal is 500 Hz with 12 bit resolution (Prescribed standard). Each lead is digi- tized for 3 second duration. This tool will be of great help as the doctors need not go through ECG paper roll. The record and transport of data would be simplified. The developed tool is for a certain classes of ECG only.
Intervertebral Disc Classification Using Deep Learning Technique
Proceedings of the International Conference on ISMAC in Computational Vision and Bio-Engineering 2018 (ISMAC-CVB), 2019
This paper describes the semiautomatic method for diagnosis of intervertebral disc degeneration a... more This paper describes the semiautomatic method for diagnosis of intervertebral disc degeneration according to Pfirrmann’s five scale (1–5) grading system, which is used in the assessment of disc degeneration severity. Total 1123 discs are obtained after augmentation from 120 subject’s T2-weighted lumbar scans. Manual classification into five grades is done by experts. Our method is extracting 59 features using Local Binary Pattern for texture analysis and 4096 features using pretrained CNN. 1 × 59 and 1 × 4096 feature vectors are fused to form 1 × 4155 feature vector to train our multiclass Support Vector Machine classifier. This feature level fusion method is able to achieve 80.40% accuracy. A Quantitative analysis is done using parameters, viz.,—Accuracy, Sensitivity, Specificity, Precision, Recall, F1 score, etc.
Histogram of directional derivative based spatio-temporal descriptor for human action recognition
2017 International Conference on Data Management, Analytics and Innovation (ICDMAI), 2017
In this paper, we introduced a novel local spatio-temporal feature descriptor for human action re... more In this paper, we introduced a novel local spatio-temporal feature descriptor for human action recognition. Our proposed descriptor is based on the Histogram of Directional Derivative (HODD). Histogram of gradient (HOG) has been widely used to generate the descriptor for local features for human action recognition. The distinctiveness of descriptor is essential to match similar action and differentiate different action. However most of the techniques in literature for HOG is based on orientation quantization leading to the reduction of the distinctiveness. Our proposed descriptor describes the local object shape and appearance within cuboid effectively and distinctively.
In typical real time systems, tasks need to communicate so as to achieve effective resource utili... more In typical real time systems, tasks need to communicate so as to achieve effective resource utilization. Tasks should be scheduled considering their precedence constraints. Modified rate monotonic scheduling, earliest deadline scheduling algorithm and latest deadline first scheduling algorithm do well in precedence constraint tasks scheduling; however these algorithms do not take care about overall contribution of individual tasks in tasks network. This paper suggests novel idea which is considering both contribution of individual tasks and deadline. This algorithm is modification of performance contribution and deadline (PCD) algorithm. It is proved through analysis that, number of missing deadlines and context switching is less as compared to PCD. Important feature of this algorithm is that it supports both cyclic and acyclic process structure for scheduling.
Segmentation, Detection, and Classification of Liver Tumors for Designing a CAD System
Advances in Intelligent Systems and Computing, 2019
Globally cancer is the foremost threat to public health. Out of the world population, the deaths ... more Globally cancer is the foremost threat to public health. Out of the world population, the deaths caused by liver cancer are increasing by 3% every year. Liver tumors are the pathological disorders which can be detected with the help of various image processing methods. A Computer-Aided Diagnosis (CAD) system use image processing tools and techniques for detecting liver tumors which acts as an assistance to the radiologists, oncologists, and hepatologists for effective diagnosis. The main objective of this survey is to analyze the available techniques that can aid in developing or designing a CAD system for liver tumors. Various methods and outcome of available techniques for segmentation, detection and classification of liver tumors from Computed Tomography (CT) or Dynamic Contrast-Enhanced Magnetic Resonance (DCE-MR) images are discussed and compared in detail.
IETE Journal of Research, 2020
Grading of discs is essential for the assessment of degeneration progression which subsequently p... more Grading of discs is essential for the assessment of degeneration progression which subsequently plays a vital role in decision making in the removal of a disc. In particular, Pfirrmann's five-scale (1-5) scoring system is widely used in MR image modality for grading the discs. In this study, we have presented a contemporary semiautomatic feature level fusion approach for the classification of intervertebral discs. The data of T2-weighted lumbar MR scans in sagittal plane were collected from 120 distinct subjects. In total, 1123 inter-vertebral disc images were obtained upon performing image augmentation. The experts have segregated the discs into five categories as per Pfirrmann's criteria. This segregation is utilized as ground truth label data for classification. Furthermore, two feature extraction techniques are exploited, one from spatial domain and other follows deep learning process. A popular Local Binary Pattern (LBP) texture descriptor extracts features from spatial domain. In addition, a popular pre-trained Convolution Neural Network (CNN), which acts as a feature extractor, extracts deep features. The training procedure using SVM classifier yields a model built from postfusion feature vectors. Furthermore, to estimate the model's performance, a 5-fold cross-validation is performed by computing principal component analysis as well as without dimensionality reduction. Experiment results obtained on our dataset indicate that after dimensionality reduction, SVM classifier with various kernel functions yields the accuracy up to 92%. A quantitative analysis of the classifier model is presented for parameters, namely-Accuracy, Area Under Curve (AUC), Specificity, Sensitivity, and F1 measure.
International Journal of Communication Networks and Distributed Systems, 2017
The route cache scheme used by on-demand routing protocol is significant in MANET. This paper pre... more The route cache scheme used by on-demand routing protocol is significant in MANET. This paper presents, new cache update algorithm which determine broken link information to all neighbour's that can cache the route in routing table using distributed cache update algorithm in first stage. Then new time-to-live (TTL) field is attached with every cache entry to remove when it is expired at second stage. The proposed cache updated scheme not only maintains cache structure but also stores the information required for cache update. The proposed cache update scheme has been experimentally evaluated using network simulation (NS2). The analysis shows improved performance of updated dynamic source routing (UDSR) protocol up to 60% to 70% in terms of QoS parameters like packet delivery ratio, delay, routing overhead, drop rate compared to conventional dynamic source routing (DSR) protocol and 30% to 40% improvement compared to method presented in literature.
Parallel computing based iterative approach for the substantial weather forecasting
2016 International Conference on Signal and Information Processing (IConSIP), 2016
The need of computational environment and processing power increases per day due to the large amo... more The need of computational environment and processing power increases per day due to the large amount of data generating real-time applications like e-Healthcare systems, manufacturing systems, e-Government sites, online shopping portals, social networking sites, and weather and agricultural forecasting applications. For the purpose of handling large data, and to find insights from such data, a platform with methodologies is mandatory. In this paper, we proposed a parallel computing based iterative approach to give the analytics and improve the performance of the system. We tested the approach on the historical data of weather published by Open Government Data Platform of India. The proposed system based approach are used to handle a large amount of data and capable of processing it on the parallel computing platform. The approach is used to forecast the results by applying different parameters present in the database. The main aim of the work is to reduce the execution time required and forecast the results. In this study, the experiments are tested on parallel computing workers and gives multiple of 100 times better performance than the single worker system.
International Journal of Information Technology and Computer Science, 2012
Efficient compression reduces memory requirement in long term recording and reduces power and tim... more Efficient compression reduces memory requirement in long term recording and reduces power and time requirement in transmission. A new compression algorithm combining Linear Predictive coding (LPC) and Discrete Wavelet transform is proposed in this study. Our coding algorithm offers compression ratio above 85% for records of MIT-BIH compression database. The performance of algorithm is quantified by computing distortion measures like percentage root mean square difference (PRD), wavelet-based weighted PRD (WWPRD) and Wavelet energy based diagnostic distortion (WEDD). The PRD is found to be below 6 %, values of WWPRD and WEDD are less than 0.03. Classification of decompressed signals, by employing fuzzy c means method, is achieved with accuracy of 97%.
Assessing the Effect on Cognitive Workload Index, EEG Band Ratios, and Band Frequencies Using Band Power and Implementing Machine Learning Classification
Lecture notes in electrical engineering, 2023
In this paper, A 10 bit, 80 MS/s pipeline ADC is design using opamp sharing technique. The opamp ... more In this paper, A 10 bit, 80 MS/s pipeline ADC is design using opamp sharing technique. The opamp is shared between all the consecutive pipeline stages, so that power consumption and die area can minimize. The A/D is designed, implemented and analysed in standard gpdk 180 nm technology library using cadence tool. This converter achieves 68 dB spurious free dynamic range, 59 dB signal-tonoise-plus-distortion ratio,9.58 effective number of bits for a 90 MHz input at full sampling rate, and consumes 30 mW from a 1.8 V supply.
Image fusion is one of the most modern, accurate and useful diagnostic techniques in medical imag... more Image fusion is one of the most modern, accurate and useful diagnostic techniques in medical imaging today. The Fusion of Computed Tomography (CT) image and Magnetic Resonance (MR) image forms a new image with improved information content for diagnosis. The fused image can significantly benefit medical diagnosis and also the further image processing in computer aided diagnosis. The maximum frequency fusion rule is used for fusing the
Intelligent Aperiodic Server for Scheduling Aperiodic Tasks in Greenhouse Monitoring and Control Real Time System
Uploads
Papers by Ramchandra Manthalkar