BITS Faculty Publications
Permanent URI for this communityhttp://localhost:4000/handle/123456789/1867
Browse
47 results
Search Results
Item An Image-Based Approach for Structural Damage Recognition and Segmentation Using Deep Transfer Learning(Springer, 2023-07) Sangwan, Kuldip SinghThis research aims to determine the feasibility of using image-based deep learning techniques to inspect the damage and recognize its category in the building components. This analysis helps to determine the structure's health and its quantification in terms of damage by using image segmentation. The validation of the proposed approach is done by using PEER Hub ImageNet (Φ-Net), which is a benchmark dataset of structural images. Miniaturized VGG-16 CNN network and its customized version-based architectures have been tested on the dataset to find their adaptability to structural domain classification. To avoid overfitting in the classes with lesser samples, the transfer learning is applied using a feature extractor and fine-tuning strategies. Different experiments are designed to find the optimal model parameters and their scope for a particular image recognition task. To quantify the damage in recognition tasks such as images with cracks or spalling, pixel-based segmentation is implemented to highlight the regions where the damage occurred and its area in the region of interest. The accuracy scores of 97% for a binary class problem reveal the potential use of transfer learning-based deep learning models in structural damage recognition and segmentation even for a multiclass challenging scene.Item Deep Learning-Based Mosquito Species Detection Using Wingbeat Frequencies(Springer, 2022-02) Sangwan, Kuldip SinghThe outbreak of mosquito-borne diseases such as malaria, dengue, chikungunya, Zika, yellow fever, and lymphatic filariasis has become a major threat to human existence. Hence, the elimination of harmful mosquito species has become a worldwide necessity. The techniques to reduce and eliminate these mosquito species require the monitoring of their populations in regions across the globe. This monitoring can be performed by automatic detection from the sounds of their wingbeats, which can be recorded in mosquito suction traps. In this paper, using the sounds emitted from their wingbeats, we explore the detection of the six most harmful mosquito species. From 279,566 wingbeat recordings in the wingbeat kaggle dataset, we balance the data across the six mosquito species using data augmentation techniques. With the use of state-of-the-art machine learning models, we achieve detection accuracies of up to 97%. These models can then be integrated with mosquito suction traps to form an efficient mosquito species detection system.Item A Computer Vision Based Approach forDriver Distraction Recognition Using Deep Learning and Genetic Algorithm Based Ensemble(Springer, 2021-10) Sangwan, Kuldip SinghAs the proportion of road accidents increases each year, driver distraction continues to be an important risk component in road traffic injuries and deaths. The distractions caused by increasing use of mobile phones and other wireless devices pose a potential risk to road safety. Our current study aims to aid the already existing techniques in driver posture recognition by improving the performance in the driver distraction classification problem. We present an approach using a genetic algorithm-based ensemble of six independent deep neural architectures, namely, AlexNet, VGG-16, EfficientNet B0, Vanilla CNN, Modified DenseNet and InceptionV3 + BiLSTM. We test it on two comprehensive datasets, the AUC Distracted Driver Dataset, on which our technique achieves an accuracy of 96.37%, surpassing the previously obtained 95.98%, and on the State Farm Driver Distraction Dataset, on which we attain an accuracy of 99.75%. The 6-Model Ensemble gave an inference time of 0.024 s as measured on our machine with Ubuntu 20.04(64-bit) and GPU as GeForce GTX 1080 .Item Development of a Machine Learning based model for Damage Detection, Localization and Quantification to extend Structure Life(Elsevier, 2021) Sangwan, Kuldip SinghStructural Health Monitoring (SHM) has been researched for a long time and continues to be an active area of research. Initial work on SHM involved identification of hand-crafted features and predictive models relied on statistical methods. The recent improvements in computing capabilities, coupled with better integration of sensor data, has led to the emergence of more effective techniques in terms of scalability and predictive power. Machine learning offers a solution through automatic feature extraction algorithms, and scalable and noise robust models. Convolutional Neural Networks (CNN) have been used as state-of-art classifiers for images as well as for text. This paper proposes the use of the monitored structure’s transmissibility functions for the structure under observation, which can be fed into a novel composite architecture consisting of Deep CNN followed by multivariate linear regressors to detect, localize, and quantify the damage extent in a system. The proposed method was tested on the Los Alamos’ Eight degree-of-freedom (DOF) structure, and the Structural Beam Data from Laboratory of Mechanical Vibrations and Rotor Dynamics, University of Chile. This study on damage localization and quantification can be leveraged to comment on the safety and soundness of the structure under inspection and can help in making more informed inferences. It is expected that, in general, this will lead to extended structure life, which not only improves the resource utilization in terms of structure maintenance and its longevity but also decreases the carbon footprint and capital expenditure.Item Stock Price Prediction using Fractional Gradient-Based Long Short Term Memory(IOP, 2021) Agarwal, Shivi; Mathur, TrilokDeep Learning is considered one of the most effective strategies used by hedge funds to maximize profits. But Deep Neural Networks (DNN) lack theoretical analysis of memory exploitation. Some traditional time series methods such as Auto-Regressive Integrated Moving Average (ARIMA) and Generalized Auto-Regressive Conditional Heteroskedasticity (GARCH) work only when the entire series is pre-processed or when the whole data is available. Thus, it fails in a live trading system. So, there is a great need to develop techniques that give more accurate stock/index predictions. This study has exploited fractional-order derivatives' memory property in the backpropagation of LSTM for stock predictions. As the history of previous stock prices plays a significant role in deciding the future price, fractional-order derivatives carry the past information along with itself. So, the use of Fractional-order derivatives with neural networks for this time series prediction is meaningful and helpful.Item Low-Light Image Enhancement for UAVs With Multi-Feature Fusion Deep Neural Networks(IEEE, 2022-06) Narang, Pratik; Chamola, VinayObject detection in low-light aerial images is a challenging problem due to considerable variation in brightness and varying contrast. Deep learning-based approaches have recently demonstrated great promise in image enhancement. Many existing neural networks used for image quality enhancement first encode the input into low-resolution representations and then decode these representations back to a higher resolution for the contextual information. However, this method leads to the loss of semantic content. Recent research has demonstrated the advantage of maintaining high-resolution information along with lower resolution representations, which maintains image features throughout the network. In this letter, we propose a novel architecture named RNet for low-light image enhancement of aerial images. The proposed network contains multiresolution branches for better understanding of different levels of local and global context through different streams. The performance of RNet is evaluated on a recent synthetic dataset. We also present a comprehensive evaluation with a representative set of state-of-the-art enhancement techniques and neural net architectures.Item Detecting UAV Presence Using Convolution Feature Vectors in Light Gradient Boosting Machine(IEEE, 2022-12) Alladi, Tejasvi; Chamola, VinayThe growing number of Unmanned Aerial Vehicle (UAV) applications brings with it, a rising number of privacy concerns. The high availability of commercial drones is also increasing the need for strict regulations. As far away as we are from establishing such protocols to ensure that the most basic human right to privacy is not exploited, we are further away from enforcing them. Thus, there is a need for a generalised drone detection system to detect different drones operating in a broad range of Radio Frequencies (RF). Previous attempts to tackle this problem have been made using audio, video, radar, WiFi and RF signals. While all these methods have their own benefits and drawbacks, RF has various characteristics which make them suitable for practical applications on a large scale. In this paper, we propose a novel technique called the ConvLGBM model which combines the feature extraction capability of a Convolution Neural Network (CNN) with the high classification accuracy of the Light Gradient Boosting Machine (LightGBM). We develop and evaluate the classifications done by an optimal CNN and the LightGBM model and then compare both models with the ConvLGBM.Item Captionomaly: A Deep Learning Toolbox for Anomaly Captioning in Social Surveillance Systems(IEEE, 2023-01) Chamola, VinayReal-time video stream monitoring is gaining huge attention lately with an effort to fully automate this process. On the other hand, reporting can be a tedious task, requiring manual inspection of several hours of daily clippings. Errors are likely to occur because of the repetitive nature of the task causing mental strain on operators. There is a need for an automated system that is capable of real-time video stream monitoring in social systems and reporting them. In this article, we provide a tool aiming to automate the process of anomaly detection and reporting. We combine anomaly detection and video captioning models to create a pipeline for anomaly reporting in descriptive form. A new set of labels by creating descriptive captions for the videos collected from the UCF-Crime (University of Central Florida-Crime) dataset has been formulated. The anomaly detection model is trained on the UCF-Crime, and the captioning model is trained with the newly created labeled set UCF-Crime video description (UCFC-VD). The tool will be used for performing the combined task of anomaly detection and captioning. Automated anomaly captioning would be useful in the efficient reporting of video surveillance data in different social scenarios. Several testing and evaluation techniques were performed. Source code and dataset: https://github.com/Adit31/Captionomaly-Deep-Learning-Toolbox-for-Anomaly-Captioning.Item Cracking the Anonymous IoT Routing Networks: A Deep Learning Approach(IEEE, 2023-03) Chamola, VinayIn recent years, IoT technology has been one of the most rapidly expanding fields, connecting over 27 billion connected devices worldwide. Increasing security concerns, such as software flaws and cyberattacks, limit the use of IoT devices. Tor, also known as “The Onion Router,” is one of the most popular, secure, and widely deployed anonymous routing systems in IoT networks. Tor is based on a worldwide network of relays operated by volunteers worldwide. Tor continues to be one of the most popular and secure tools against network surveillance, traffic analysis, and information censorship due to its robust use of encryption, authentication, and routing protocols. However, ToR is not anticipated to be entirely safe. The increasing computational capabilities of adversaries threaten Tor's ability to withstand adversarial attacks and maintain anonymity. This article describes the foundation of the Tor network, how it operates, potential attacks against Tor, and the network's defense strategies. In addition, the authors present a framework for deep learning that uses bandwidth performance to identify the server's location in Tor, thereby compromising anonymity. This article examines Tor's network's current and projected future in the Internet of Things