Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
2,823
result(s) for
"Yang, Lang"
Sort by:
Ship Detection Based on YOLOv2 for SAR Imagery
Synthetic aperture radar (SAR) imagery has been used as a promising data source for monitoring maritime activities, and its application for oil and ship detection has been the focus of many previous research studies. Many object detection methods ranging from traditional to deep learning approaches have been proposed. However, majority of them are computationally intensive and have accuracy problems. The huge volume of the remote sensing data also brings a challenge for real time object detection. To mitigate this problem a high performance computing (HPC) method has been proposed to accelerate SAR imagery analysis, utilizing the GPU based computing methods. In this paper, we propose an enhanced GPU based deep learning method to detect ship from the SAR images. The You Only Look Once version 2 (YOLOv2) deep learning framework is proposed to model the architecture and training the model. YOLOv2 is a state-of-the-art real-time object detection system, which outperforms Faster Region-Based Convolutional Network (Faster R-CNN) and Single Shot Multibox Detector (SSD) methods. Additionally, in order to reduce computational time with relatively competitive detection accuracy, we develop a new architecture with less number of layers called YOLOv2-reduced. In the experiment, we use two types of datasets: A SAR ship detection dataset (SSDD) dataset and a Diversified SAR Ship Detection Dataset (DSSDD). These two datasets were used for training and testing purposes. YOLOv2 test results showed an increase in accuracy of ship detection as well as a noticeable reduction in computational time compared to Faster R-CNN. From the experimental results, the proposed YOLOv2 architecture achieves an accuracy of 90.05% and 89.13% on the SSDD and DSSDD datasets respectively. The proposed YOLOv2-reduced architecture has a similarly competent detection performance as YOLOv2, but with less computational time on a NVIDIA TITAN X GPU. The experimental results shows that the deep learning can make a big leap forward in improving the performance of SAR image ship detection.
Journal Article
Consolidated Convolutional Neural Network for Hyperspectral Image Classification
The performance of hyperspectral image (HSI) classification is highly dependent on spatial and spectral information, and is heavily affected by factors such as data redundancy and insufficient spatial resolution. To overcome these challenges, many convolutional neural networks (CNN) especially 2D-CNN-based methods have been proposed for HSI classification. However, these methods produced insufficient results compared to 3D-CNN-based methods. On the other hand, the high computational complexity of the 3D-CNN-based methods is still a major concern that needs to be addressed. Therefore, this study introduces a consolidated convolutional neural network (C-CNN) to overcome the aforementioned issues. The proposed C-CNN is comprised of a three-dimension CNN (3D-CNN) joined with a two-dimension CNN (2D-CNN). The 3D-CNN is used to represent spatial–spectral features from the spectral bands, and the 2D-CNN is used to learn abstract spatial features. Principal component analysis (PCA) was firstly applied to the original HSIs before they are fed to the network to reduce the spectral bands redundancy. Moreover, image augmentation techniques including rotation and flipping have been used to increase the number of training samples and reduce the impact of overfitting. The proposed C-CNN that was trained using the augmented images is named C-CNN-Aug. Additionally, both Dropout and L2 regularization techniques have been used to further reduce the model complexity and prevent overfitting. The experimental results proved that the proposed model can provide the optimal trade-off between accuracy and computational time compared to other related methods using the Indian Pines, Pavia University, and Salinas Scene hyperspectral benchmark datasets.
Journal Article
Fiscal transparency or fiscal illusion? Housing and credit market responses to fiscal monitoring
Nongovernmental stakeholders, including taxpayers and investors of government bonds, have an interest in government financial information. Fiscal transparency entails both access to and understandability of government information. Analyses of a government borrower’s financial information, often facilitated by market intermediaries, directly affect investor return on the bond market. In contrast, taxpayers may lack the incentive or capacity to comprehend government financial data prepared based on complex accounting rules. State fiscal monitoring programs compile and analyze local government financial data to track fiscal stress. This paper examines how housing and municipal bond markets respond to the New York monitoring program implemented in 2013, which uses existing, account-level local government financial data to assign simple labels signifying local government insolvency. Housing prices decreased following significant fiscal stress designations, but not statistically significantly following the other more modest stress labels. In contrast, the bond market priced in government financial information even before the state monitoring.
Journal Article
Negative Externality of Fiscal Problems: Dissecting the Contagion Effect of Municipal Bankruptcy
The fiscal decision of one local government may spill over to other localities, and such externality could justify and inform policy making by a higher-level government. Theories of municipal bond market contagion postulate that once a local government files for bankruptcy, localities sharing similar characteristics will be perceived negatively by creditors and charged a higher interest rate. In this article, empirical examination of the second-largest municipal bankruptcy in American history shows no support for general contagion based on geographic proximity. That is, nearby localities did not pay a higher interest rate afier the bankruptcy. However, case-specific contagion formed around borrower- and bond-specific characteristics contributing to the bankruptcy: general-purpose borrowers and general-obligation bonds experienced increased borrowing costs after the bankruptcy. These findings have implications for states considering granting authorizations for municipal bankruptcy or providing financial assistance to struggling localities, as well as for local governments planning to access the municipal bond market.
Journal Article
Sound Source Localization Using a Convolutional Neural Network and Regression Model
In this research, a novel sound source localization model is introduced that integrates a convolutional neural network with a regression model (CNN-R) to estimate the sound source angle and distance based on the acoustic characteristics of the interaural phase difference (IPD). The IPD features of the sound signal are firstly extracted from time-frequency domain by short-time Fourier transform (STFT). Then, the IPD features map is fed to the CNN-R model as an image for sound source localization. The Pyroomacoustics platform and the multichannel impulse response database (MIRD) are used to generate both simulated and real room impulse response (RIR) datasets. The experimental results show that an average accuracy of 98.96% and 98.31% are achieved by the proposed CNN-R for angle and distance estimations in the simulation scenario at SNR = 30 dB and RT60 = 0.16 s, respectively. Moreover, in the real environment, the average accuracies of the angle and distance estimations are 99.85% and 99.38% at SNR = 30 dB and RT60 = 0.16 s, respectively. The performance obtained in both scenarios is superior to that of existing models, indicating the potential of the proposed CNN-R model for real-life applications.
Journal Article
Defense Responses in Rice Induced by Silicon Amendment against Infestation by the Leaf Folder Cnaphalocrocis medinalis
Silicon (Si) amendment to plants can confer enhanced resistance to herbivores. In the present study, the physiological and cytological mechanisms underlying the enhanced resistance of plants with Si addition were investigated for one of the most destructive rice pests in Asian countries, the rice leaf folder, Cnaphalocrocis medinalis (Guenée). Activities of defense-related enzymes, superoxide dismutase, peroxidase, catalase, phenylalanine ammonia-lyase, and polyphenol oxidase, and concentrations of malondialdehyde and soluble protein in leaves were measured in rice plants with or without leaf folder infestation and with or without Si amendment at 0.32 g Si/kg soil. Silicon amendment significantly reduced leaf folder larval survival. Silicon addition alone did not change activities of defense-related enzymes and malondialdehyde concentration in rice leaves. With leaf folder infestation, activities of the defense-related enzymes increased and malondialdehyde concentration decreased in plants amended with Si. Soluble protein content increased with Si addition when the plants were not infested, but was reduced more in the infested plants with Si amendment than in those without Si addition. Regardless of leaf folder infestation, Si amendment significantly increased leaf Si content through increases in the number and width of silica cells. Our results show that Si addition enhances rice resistance to the leaf folder through priming the feeding stress defense system, reduction in soluble protein content and cell silicification of rice leaves.
Journal Article
Optimally-Weighted Image-Pose Approach (OWIPA) for Distracted Driver Detection and Classification
Distracted driving is the prime factor of motor vehicle accidents. Current studies on distraction detection focus on improving distraction detection performance through various techniques, including convolutional neural networks (CNNs) and recurrent neural networks (RNNs). However, the research on detection of distracted drivers through pose estimation is scarce. This work introduces an ensemble of ResNets, which is named Optimally-weighted Image-Pose Approach (OWIPA), to classify the distraction through original and pose estimation images. The pose estimation images are generated from HRNet and ResNet. We use ResNet101 and ResNet50 to classify the original images and the pose estimation images, respectively. An optimum weight is determined through grid search method, and the predictions from both models are weighted through this parameter. The experimental results show that our proposed approach achieves 94.28% accuracy on AUC Distracted Driver Dataset.
Journal Article
Performance Comparison of Machine Learning Approaches on Hepatitis C Prediction Employing Data Mining Techniques
Hepatitis C is a liver infection caused by the hepatitis C virus (HCV). Due to the late onset of symptoms, early diagnosis is difficult in this disease. Efficient prediction can save patients before permeant liver damage. The main objective of this study is to employ various machine learning techniques to predict this disease based on common and affordable blood test data to diagnose and treat patients in the early stages. In this study, six machine learning algorithms (Support Vector Machine (SVM), K-nearest Neighbors (KNN), Logistic Regression, decision tree, extreme gradient boosting (XGBoost), artificial neural networks (ANN)) were utilized on two datasets. The performances of these techniques were compared in terms of confusion matrix, precision, recall, F1 score, accuracy, receiver operating characteristics (ROC), and the area under the curve (AUC) to identify a method that is appropriate for predicting this disease. The analysis, on NHANES and UCI datasets, revealed that SVM and XGBoost (with the highest accuracy and AUC among the test models, >80%) can be effective tools for medical professionals using routine and affordable blood test data to predict hepatitis C.
Journal Article
Silicon amendment is involved in the induction of plant defense responses to a phloem feeder
Plant resistance to herbivores is a key component in integrated pest management. In most cases, silicon (Si) amendment to plants enhances resistance to herbivorous insects. The increase of plant physical barrier and altered insect behaviors are proposed as mechanisms for the enhanced resistance in Si-amended plants, but our understanding of the induced mechanisms involved in Si-enhanced plant resistance to phloem-feeding insects remains unclear. Here, we show that Si amendment to rice (
Oryza sativa
) plants impacts multiple plant defense responses induced by a phloem-feeder, the brown planthopper (
Nilaparvata lugens
, BPH). Si amendment improved silicification of leaf sheaths that BPH feed on. Si addition suppressed the increase of malondialdehyde concentration while encouraged increase of H
2
O
2
concentration in plants attacked by BPH. Higher activities of catalase and superoxide dismutase were recorded in Si-amended than in non-amended BPH-infested plants. BPH infestation activated synthases for secondary metabolites, polyphenol oxidase and pheny-lalanine ammonia-lyase, and β-1,3-glucanase, but the activation was greater in Si-amended than in non-amended plants. Taken together, our findings demonstrate that Si amendment interacts with BPH infestation in the induction of plant defense responses and consequently, to confer enhanced rice plant resistance.
Journal Article