Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
22 results
Search Results
Item V3O2: hybrid deep learning model for hyperspectral image classification using vanilla-3D and octave-2D convolution(Springer Science and Business Media Deutschland GmbH, 2021) Mohan, A.; Sundaram, V.Remote sensing image analysis is an emerging area of research and is used for various applications such as climate analysis, crop monitoring and change detection. Hyperspectral image (HSI) is one of the dominant remote sensing imaging modalities that captures information beyond the visible spectrum. The evolution of deep learning has made a significant impact on HSI analysis, mainly for its classification. The spatial–spectral feature-based classification model improves the classification accuracy of hyperspectral images (HSIs). However, these models are computationally expensive, and redundancy exists in the spatial dimension of features. This research work proposes a hybrid convolutional neural network (CNN) for HSI classification. The proposed model uses principal component analysis (PCA) as a preprocessing technique for optimal band extraction from HSIs. The hybrid CNN classification technique extracts the spectral and spatial features using three-dimensional CNN (3D CNN). These features are fed into a two-dimensional CNN (2D CNN) for further feature extraction and classification. The redundancy in spatial features of the hybrid CNN model is reduced by octave convolution (OctConv) instead of standard vanilla convolution. OctConv factorizes the spatial features into lower and higher spatial frequencies, and different convolutions are performed on them based on their frequencies. The hybrid model is compared against various state-of-the-art CNN-based techniques and found that the accuracy is boosted with a lesser computational cost. © 2020, Springer-Verlag GmbH Germany, part of Springer Nature.Item Cardamom Plant Disease Detection Approach Using EfficientNetV2(Institute of Electrical and Electronics Engineers Inc., 2022) Sunil, C.K.; Jaidhar, C.D.; Patil, N.Cardamom is a queen of spices. It is indigenously grown in the evergreen forests of Karnataka, Kerala, Tamil Nadu, and the northeastern states of India. India is the third largest producer of cardamom. Plant diseases cause a catastrophic influence on food production safety; they reduce the eminence and quantum of agricultural products. Plant diseases may cause significantly high loss or no harvest in dreadful cases. Various diseases and pests affect the growth of cardamom plants at different stages and crop yields. This study concentrated on two diseases of cardamom plants, Colletotrichum Blight and Phyllosticta Leaf Spot of cardamom and three diseases of grape, Black Rot, ESCA, and Isariopsis Leaf Spot. Various methods have been proposed for plant disease detection, and deep learning has become the preferred method because of its spectacular accomplishment. In this study, U2-Net was used to remove the unwanted background of an input image by selecting multiscale features. This work proposes a cardamom plant disease detection approach using the EfficientNetV2 model. A comprehensive set of experiments was carried out to ascertain the performance of the proposed approach and compare it with other models such as EfficientNet and Convolutional Neural Network (CNN). The experimental results showed that the proposed approach achieved a detection accuracy of 98.26%. © 2013 IEEE.Item UCDNet: A Deep Learning Model for Urban Change Detection From Bi-Temporal Multispectral Sentinel-2 Satellite Images(Institute of Electrical and Electronics Engineers Inc., 2022) Basavaraju, K.S.; Sravya, N.; Lal, S.; Nalini, J.; Chintala, C.S.; Dell’Acqua, F.Change detection (CD) from satellite images has become an inevitable process in earth observation. Methods for detecting changes in multi-temporal satellite images are very useful tools when characterization and monitoring of urban growth patterns is concerned. Increasing worldwide availability of multispectral images with a high revisit frequency opened up more possibilities in the study of urban CD. Even though there exists several deep learning methods for CD, most of these available methods fail to predict the edges and preserve the shape of the changed area from multispectral images. This article introduces a deep learning model called urban CD network (UCDNet) for urban CD from bi-temporal multispectral Sentinel-2 satellite images. The model is based on an encoder-decoder architecture which uses modified residual connections and the new spatial pyramid pooling (NSPP) block, giving better predictions while preserving the shape of changed areas. The modified residual connections help locate the changes correctly, and the NSPP block can extract multiscale features and will give awareness about global context. UCDNet uses a proposed loss function which is a combination of weighted class categorical cross-entropy (WCCE) and modified Kappa loss. The Onera Satellite Change Detection (OSCD) dataset is used to train, evaluate, and compare the proposed model with the benchmark models. UCDNet gives better results from the reference models used here for comparison. It gives an accuracy of 99.3%, an $F1$ score ( $F1$ ) of 89.21%, a Kappa coefficient (Ka) of 88.85%, and a Jaccard index (JI) of 80.53% on the OSCD dataset. © 1980-2012 IEEE.Item Fault diagnosis of antifriction bearing in internal combustion engine gearbox using data mining techniques(Springer, 2022) Ravikumar, K.N.; Aralikatti, S.S.; Kumar, H.; Kumar, G.N.; Gangadharan, K.V.Ball bearing failure are most common failure in rotating machinery, which can be catastrophic. Hence obtaining early failure warning along with precise fault detection technique is at most important. Early detection and timely intervention are the key in condition monitoring for long term endurance of machine components. The early research has used signal processing and spectral analysis extensively for fault detection however data mining with machine learning is most effective in fault diagnosis, the same is presented in this paper. The vibration signals are acquired for an output shaft antifriction bearing in a two-wheeler gearbox operated at various loading conditions with healthy and fault conditions. Data mining is employed for these acquired signals. Statistical, discrete wavelet and empirical mode decomposition are employed for feature extraction process and J48 decision tree for feature selection. Classification is carried out using K*, Random forest and support vector machine algorithm. The classifiers are trained and tested using tenfold cross validation method to diagnose the bearing fault. A comparative study of feature extraction and classifiers are done to evaluate the classification accuracy. The results obtained from K* classifier with wavelet feature yielded better accuracy than rest other classifiers with classification accuracy 92.5% for bearing fault diagnosis. © 2021, The Society for Reliability Engineering, Quality and Operations Management (SREQOM), India and The Division of Operation and Maintenance, Lulea University of Technology, Sweden.Item An Optimized Question Classification Framework Using Dual-Channel Capsule Generative Adversarial Network and Atomic Orbital Search Algorithm(Institute of Electrical and Electronics Engineers Inc., 2023) Revanesh, M.; Rudra, B.; Guddeti, R.M.R.The advancement in education has emphasized the need to evaluate the quality of the examination questions and the cognitive levels of students. Many educational institutions now acknowledge Bloom's taxonomy-based students' cognitive levels evaluating subject-related learning. Therefore, in this paper, a novel optimized Examination Question Classification framework, referred to as QC-DcCapsGAN-AOSA, is proposed by combining the Dual-channel Capsule generative Adversarial Network (DcCapsGAN) with Atomic Orbital Search Algorithm (AOSA) for preprocessing a real-time online dataset of university examination questions, thus identify the key features from the raw data using Term Frequency Inverse Document Frequency (TF-IDF) and finally classifying the examination questions. Atomic Orbital Search Algorithm is used to fine-tune the parameters' weights of the DcCapsGAN, and then uses these weights to categorize questions as Knowledge Level, Comprehension Level, Application Level, Analysis Level, Synthesis Level, and Evaluation Level. Experimental results demonstrate the superiority of the proposed method (QC-DcCapsGAN-AOSA) when compared to the state-of-the-art methods such as QC-LSTM-CNN and QC-BiGRU-CNN with an accuracy improvement of 23.65% and 29.04%, respectively. © 2013 IEEE.Item A Boosting-Based Hybrid Feature Selection and Multi-Layer Stacked Ensemble Learning Model to Detect Phishing Websites(Institute of Electrical and Electronics Engineers Inc., 2023) Lakshmana Rao, L.R.; Rao, R.S.; Pais, A.R.; Gabralla, L.A.Phishing is a type of online scam where the attacker tries to trick you into giving away your personal information, such as passwords or credit card details, by posing as a trustworthy entity like a bank, email provider, or social media site. These attacks have been around for a long time and unfortunately, they continue to be a common threat. In this paper, we propose a boosting based multi layer stacked ensemble learning model that uses hybrid feature selection technique to select the relevant features for the classification. The dataset with selected features are sent to various classifiers at different layers where the predictions of lower layers are fed as input to the upper layers for the phishing detection. From the experimental analysis, it is observed that the proposed model achieved an accuracy ranging from 96.16 to 98.95% without feature selection across different datasets and also achieved an accuracy ranging from 96.18 to 98.80% with feature selection. The proposed model is compared with baseline models and it has outperformed the existing models with a significant difference. © 2013 IEEE.Item Classification of Arecanut X-Ray Images for Quality Assessment Using Adaptive Genetic Algorithm and Deep Learning(Institute of Electrical and Electronics Engineers Inc., 2023) Naik, P.M.; Rudra, B.The traditional approach for analyzing the quality of arecanuts is based on their external appearance. However, using machine learning and deep learning techniques, automated classifications were performed. But the true quality can only be analyzed when the internal structure of the arecanut is examined. Therefore, we use the X-ray imaging technique to determine the internal quality of arecanuts. We prepared a novel dataset of arecanut X-ray images and used a YOLOv5 based deep learning architecture for classification. The present study employs an adaptive genetic algorithm based approach for hyperparameter optimization to enhance the mean average precision (mAP) using a light weight model generated using a ghost network and a feature pyramid network (FPN). We have achieved the highest mAP of 97.84% using our method with a lower model size of 15 MB. Our method has excelled in detecting the arecanut compared to cutting-edge object detection algorithms such as YOLOv3, YOLOv4, Detetron, YOLOv6, YOLOv8, and YOLOX. We also acknowledged the performance enhancement using the adaptive genetic algorithm on the Pascal VOC 2007 image dataset. Despite of significant computational requirements for executing genetic algorithms, we proved that genetic algorithms can boost mAP. Additionally, the methodology developed in this investigation produced multiple models with the best mAP featuring optimized hyperparameters. This methodical strategy is helpful for the design of an automatic, non-destructive, integrated X-ray image based classification system. This system has the potential to revolutionize the quality assessment of arecanuts by offering a more efficient evaluation method. © ; 2023 The Authors.Item DPPNet: An Efficient and Robust Deep Learning Network for Land Cover Segmentation From High-Resolution Satellite Images(Institute of Electrical and Electronics Engineers Inc., 2023) Sravya, N.; Priyanka; Lal, S.; Nalini, J.; Chintala, C.S.; Dell’Acqua, F.Visual understanding of land cover is an important task in information extraction from high-resolution satellite images, an operation which is often involved in remote sensing applications. Multi-class semantic segmentation of high-resolution satellite images turned out to be an important research topic because of its wide range of real-life applications. Although scientific literature reports several deep learning methods that can provide good results in segmenting remotely sensed images, these are generally computationally expensive. There still exists an open challenge towards developing a robust deep learning model capable of improving performances while requiring less computational complexity. In this article, we propose a new model termed DPPNet (Depth-wise Pyramid Pooling Network), which uses the newly designed Depth-wise Pyramid Pooling (DPP) block and a dense block with multi-dilated depth-wise residual connections. This proposed DPPNet model is evaluated and compared with the benchmark semantic segmentation models on the Land-cover and WHDLD high-resolution Space-borne Sensor (HRS) datasets. The proposed model provides DC, IoU, OA, Ka scores of (88.81%, 78.29%), (76.35%, 60.92%), (87.15%, 81.02%), (77.86%, 72.73%) on the Land-cover and WHDLD HRS datasets respectively. Results show that the proposed DPPNet model provides better performances, in both quantitative and qualitative terms, on these standard benchmark datasets than current state-of-art methods. © 2017 IEEE.Item Knowledge distillation: A novel approach for deep feature selection(Elsevier B.V., 2023) C, D.; Shetty, A.; Narasimhadhan, A.V.High dimensional data in hyperspectral remote sensing leads to computational, analytical, and storage complexities. Dimensionality reduction serves as an efficient tool to remove redundant, irrelevant, and highly correlated features. Recently, deep learning approaches have received remarkable progress in hyperspectral data analysis. In this paper, a new end-to-end deep learning framework based on a teacher-student network inspired by knowledge distillation is proposed for deep feature selection. Initially, a complicated teacher deep neural network is employed on complex high dimensional data to learn its corresponding best low dimensional representation. Then, the knowledge from the network is transferred to a simple student network that performs feature selection. Hence, it eventually leads to deep neural network compression which is of prime concern in hyperspectral remote sensing. Limited studies have been carried out to explore the benefits of knowledge distillation on hyperspectral data. The proposed method could be employed to choose deep features for both supervised and unsupervised tasks. Experimental results reveal the performance of the proposed scheme using limited features. In comparison to 1D and simple autoencoder models, the 2D model based on convolutional autoencoder delivers greater classification accuracies, with a classification accuracy value of 96.15% for the Indian Pines dataset and 97.82% for the Pavia University dataset. A similar trend is reported with unsupervised learning as well. Furthermore, the proposed model has a low degree of sensitivity to parameter selection. © 2022 National Authority of Remote Sensing & Space ScienceItem StrokeViT with AutoML for brain stroke classification(Elsevier Ltd, 2023) Raj, R.; Mathew, J.; Kannath, S.K.; Rajan, J.Stroke, categorized under cardiovascular and circulatory diseases, is considered the second foremost cause of death worldwide, causing approximately 11% of deaths annually. Stroke diagnosis using a Computed Tomography (CT) scan is considered ideal for identifying whether the stroke is hemorrhagic or ischemic. However, most methods for stroke classification are based on a single slice-level prediction mechanism, meaning that the most imperative CT slice has to be manually selected by the radiologist from the original CT volume. This paper proposes an integration of Convolutional Neural Network (CNN), Vision Transformers (ViT), and AutoML to obtain slice-level predictions as well as patient-wise prediction results. While the CNN with inductive bias captures local features, the transformer captures long-range dependencies between sequences. This collaborative local-global feature extractor improves upon the slice-wise predictions of the CT volume. We propose stroke-specific feature extraction from each slice-wise prediction to obtain the patient-wise prediction using AutoML. While the slice-wise predictions helps the radiologist to verify close and corner cases, the patient-wise predictions makes the outcome clinically relevant and closer to real-world scenario. The proposed architecture has achieved an accuracy of 87% for single slice-level prediction and an accuracy of 92% for patient-wise prediction. For comparative analysis of slice-level predictions, standalone architectures of VGG-16, VGG-19, ResNet50, and ViT were considered. The proposed architecture has outperformed the standalone architectures by 9% in terms of accuracy. For patient-wise predictions, AutoML considers 13 different ML algorithms, of which 3 achieve an accuracy of more than 90%. The proposed architecture helps in reducing the manual effort by the radiologist to manually select the most imperative CT from the original CT volume and shows improvement over other standalone architectures for classification tasks. The proposed architecture can be generalized for volumetric scans aiding in the patient diagnosis of head and neck, lungs, diseases of hepatobiliary tract, genitourinary diseases, women's imaging including breast cancer and various musculoskeletal diseases. Code for proposed stroke-specific feature extraction with the pre-trained weights of the trained model is available at: https://github.com/rishiraj-cs/StrokeViT_With_AutoML. © 2022 Elsevier Ltd
- «
- 1 (current)
- 2
- 3
- »