Conference Papers
Permanent URI for this collectionhttps://idr.nitk.ac.in/handle/123456789/28506
Browse
56 results
Search Results
Item A Transfer Learning Approach for Diabetic Retinopathy Classification Using Deep Convolutional Neural Networks(Institute of Electrical and Electronics Engineers Inc., 2018) Krishnan, A.S.; Clive, D.R.; Bhat, V.; Ramteke, P.B.; Koolagudi, S.G.Diabetic Retinopathy is a disease in which the retina is damaged due to diabetes mellitus. It is a leading cause for blindness today. Detection and quantification of such mellitus from retinal images is tedious and requires expertise. In this paper, an automatic identification of severity of Diabetic Retinopathy using Convolutional Neural Networks (CNNs) with a transfer learning approach has been proposed to aid the diagnostic process. A comparison of different CNN architectures such as ResNet, Inception-ResNet-v2 etc. is done using the quadratic weighted kappa metric. The qualitative and quantitative evaluation of the proposed approach is carried out on the Diabetic Retinopathy detection dataset from Kaggle. From the results, we observe that the proposed model achieves a kappa score of 0.76. © 2018 IEEE.Item Stock price movements classification using machine and deep learning techniques-the case study of indian stock market(Springer Verlag service@springer.de, 2019) Naik, N.; Mohan, B.R.Stock price movements forecasting is an important topic for traders and stock analyst. Timely prediction in stock yields can get more profits and returns. The predicting stock price movement on a daily basis is a difficult task due to more ups and down in the financial market. Therefore, there is a need for a more powerful predictive model to predict the stock prices. Most of the existing work is based on machine learning techniques and considered very few technical indicators to predict the stock prices. In this paper, we have extracted 33 technical indicators based on daily stock price such as open, high, low and close price. This paper addresses the two problems, first is the technical indicator feature selection and identification of the relevant technical indicators by using Boruta feature selection technique. The second is an accurate prediction model for stock price movements. To predict stock price movements we have proposed machine learning techniques and deep learning based model. The performance of the deep learning model is better than the machine learning techniques. The experimental results are significant improves the classification accuracy rate by 5% to 6%. National Stock Exchange, India (NSE) stocks are considered for the experiment. © Springer Nature Switzerland AG 2019.Item TAGS: Towards Automated Classification of Unstructured Clinical Nursing Notes(Springer Verlag service@springer.de, 2019) Gangavarapu, T.; Jayasimha, A.; S. Krishnan, G.S.; Kamath S․, S.K.Accurate risk management and disease prediction are vital in intensive care units to channel prompt care to patients in critical conditions and aid medical personnel in effective decision making. Clinical nursing notes document subjective assessments and crucial information of a patient’s state, which is mostly lost when transcribed into Electronic Medical Records (EMRs). The Clinical Decision Support Systems (CDSSs) in the existing body of literature are heavily dependent on the structured nature of EMRs. Moreover, works which aim at benchmarking deep learning models are limited. In this paper, we aim at leveraging the underutilized treasure-trove of patient-specific information present in the unstructured clinical nursing notes towards the development of CDSSs. We present a fuzzy token-based similarity approach to aggregate voluminous clinical documentations of a patient. To structure the free-text in the unstructured notes, vector space and coherence-based topic modeling approaches that capture the syntactic and latent semantic information are presented. Furthermore, we utilize the predictive capabilities of deep neural architectures for disease prediction as ICD-9 code group. Experimental validation revealed that the proposed Term weighting of nursing notes AGgregated using Similarity (TAGS) model outperformed the state-of-the-art model by 5% in AUPRC and 1.55% in AUROC. © 2019, Springer Nature Switzerland AG.Item Audio Replay Attack Detection for Speaker Verification System Using Convolutional Neural Networks(Springer, 2019) Kemanth, P.J.; Supanekar, S.; Koolagudi, G.K.An audio replay attack is one of the most popular spoofing attacks on speaker verification systems because it is very economical and does not require much knowledge of signal processing. In this paper, we investigate the significance of non-voiced audio segments and deep learning models like Convolutional Neural Networks (CNN) for audio replay attack detection. The non-voiced segments of the audio can be used to detect reverberation and channel noise. FFT spectrograms are generated and given as input to CNN to classify the audio as genuine or replay. The advantage of the proposed approach is, because of the removal of the voiced speech, the feature vector size is reduced without compromising the necessary features. This leads to significant amount of reduction on training time of the networks. The ASVspoof 2017 dataset is used to train and evaluate the model. The Equal Error Rate (EER) is computed and used as a metric to evaluate model performance. The proposed system has achieved an EER of 5.62% on the development dataset and 12.47% on the evaluation dataset. © 2019, Springer Nature Switzerland AG.Item Performance evaluation of deep learning frameworks on computer vision problems(Institute of Electrical and Electronics Engineers Inc., 2019) Nara, M.; Mukesh, B.R.; Padala, P.; Kinnal, B.Deep Learning (DL) applications have skyrocketed in recent years and are being applied in various domains. There has been a tremendous surge in the development of DL frameworks to make implementation easier. In this paper, we aim to make a comparative study of GPU-accelerated deep learning software frameworks such as Torch and TenserFlow (with Keras API). We attempt to benchmark the performance of these frameworks by implementing three different neural networks, each designed for a popular Computer Vision problem (MNIST, CIFAR10, Fashion MNIST). We performed this experiment on both CPU and GPU(Nvidia GeForce GTX 960M) settings. The performance metrics used here include evaluation time, training time, and accuracy. This paper aims to act as a guide to selecting the most suitable framework for a particular problem. The special interest of the paper is to evaluate the performance lost due to the utility of an API like Keras and a comparative study of the performance over a user-defined neural network and a standard network. Our interest also lies in their performance when subjected to networks of different sizes. ©2019 IEEE.Item Depthwise Separable Convolutional Neural Network Model for Intra-Retinal Cyst Segmentation(Institute of Electrical and Electronics Engineers Inc., 2019) Girish, G.N.; Saikumar, B.; Roychowdhury, S.; Kothari, A.R.; Rajan, J.Intra-retinal cysts (IRCs) are significant in detecting several ocular and retinal pathologies. Segmentation and quantification of IRCs from optical coherence tomography (OCT) scans is a challenging task due to present of speckle noise and scan intensity variations across the vendors. This work proposes a convolutional neural network (CNN) model with an encoder-decoder pair architecture for IRC segmentation across different cross-vendor OCT scans. Since deep CNN models have high computational complexity due to a large number of parameters, the proposed method of depthwise separable convolutional filters aids model generalizability and prevents model over-fitting. Also, the swish activation function is employed to prevent the vanishing gradient problem. The optima cyst segmentation challenge (OCSC) dataset with four different vendor OCT device scans is used to evaluate the proposed model. Our model achieves a mean Dice score of 0.74 and mean recall/precision rate of 0.72/0.82 across different imaging vendors and it outperforms existing algorithms on the OCSC dataset. © 2019 IEEE.Item An efficient image retrieval system for remote sensing images using deep hashing network(Springer, 2020) Valaboju, S.; Venkatesan, M.Due to the huge increase in volumes of remote sensing images, there is a requirement for retrieval systems which maintain the retrieval accuracy and efficiency which requires better learning of features and the binary hash codes which better discriminate the images of different classes of images. The existing retrieval systems for remote sensing images use CNNs for feature learning which fails to preserve the spatial properties of an image which in turn affect the quality of binary hash code and the retrieval performance. This Paper tries to address the above goals by using (1) Extracting Hierarchical features of convolutional neural network and using them to sequential learning to better learn the features preserving spatial and semantic properties. (2) Use lossless triplet loss with two more loss functions to generate the binary hash codes which better discriminate the images of different classes. The proposed architecture consists of three phases: (1) Fine-tuning a pre-trained model. (2) Extracting the hierarchical features of convolutional neural network. (3) Using those features to train the deep learning-based hashing network. Experiments are conducted on a publicly available dataset UCMD and show that when hierarchial convolutional features are considered there is a significant improvement in performance. © Springer Nature Singapore Pte Ltd 2020.Item A TFD Approach to Stock Price Prediction(Springer, 2020) Chanduka, B.; Bhat, S.S.; Rajput, N.; Mohan, B.R.Accurate stock price predictions can help investors take correct decisions about the selling/purchase of stocks. With improvements in data analysis and deep learning algorithms, a variety of approaches has been tried for predicting stock prices. In this paper, we deal with the prediction of stock prices for automobile companies using a novel TFD—Time Series, Financial Ratios, and Deep Learning approach. We then study the results over multiple activation functions for multiple companies and reinforce the viability of the proposed algorithm. © 2020, Springer Nature Singapore Pte Ltd.Item Skeleton based Human Action Recognition for Smart City Application using Deep Learning(Institute of Electrical and Electronics Engineers Inc., 2020) Rashmi, M.; Guddeti, R.M.R.These days the Human Action Recognition (HAR) is playing a vital role in several applications such as surveillance systems, gaming, robotics, and so on. Interpreting the actions performed by a person from the video is one of the essential tasks of intelligent surveillance systems in the smart city, smart building, etc. Human action can be recognized either by using models such as depth, skeleton, or combinations of these models. In this paper, we propose the human action recognition system based on the 3D skeleton model. Since the role of different joints varies while performing the action, in the proposed work, we use the most informative distance and the angle between joints in the skeleton model as a feature set. Further, we propose a deep learning framework for human action recognition based on these features. We performed experiments using MSRAction3D, a publicly available dataset for 3D HAR, and the results demonstrated that the proposed framework obtained the accuracies of 95.83%, 92.9%, and 98.63% on three subsets of the dataset AS1, AS2, and AS3, respectively, using the protocols of [19]. © 2020 IEEE.Item Retinal-Layer Segmentation Using Dilated Convolutions(Springer Science and Business Media Deutschland GmbH, 2020) Guru Pradeep Reddy, T.; Ashritha, K.S.; Prajwala, T.M.; Girish, G.N.; Kothari, A.R.; Koolagudi, S.G.; Rajan, J.Visualization and analysis of Spectral Domain Optical Coherence Tomography (SD-OCT) cross-sectional scans has gained a lot of importance in the diagnosis of several retinal abnormalities. Quantitative analytic techniques like retinal thickness and volumetric analysis are performed on cross-sectional images of the retina for early diagnosis and prognosis of retinal diseases. However, segmentation of retinal layers from OCT images is a complicated task on account of certain factors like speckle noise, low image contrast and low signal-to-noise ratio amongst many others. Owing to the importance of retinal layer segmentation in diagnosing ophthalmic diseases, manual segmentation techniques have been proposed and adopted in clinical practice. Nonetheless, manual segmentations suffer from erroneous boundary detection issues. This paper thus proposes a fully automated semantic segmentation technique that uses an encoder–decoder architecture to accurately segment the prominent retinal layers. © 2020, Springer Nature Singapore Pte Ltd.