Article
Acoustics
Christian Langton, Ali Alomari
Summary: This article tests the variation of ultrasound transit time in a porous composite sample and finds that conventional RF signal transit time measurement correlates with the minimum spectral transit time. The authors suggest that ultrasound transit time spectroscopy method can better assess the variation of transit time in heterogeneous samples. Additionally, the fundamental relationships between ultrasound transit time, velocity, and elasticity suggest potential for the method to describe velocity and elasticity spectroscopies in structurally complex composites.
Article
Chemistry, Analytical
Jun-Li Xu, Siewert Hugelier, Hongyan Zhu, Aoife A. Gowen
Summary: This study proposes a hybrid approach of PCA and deep learning for time series spectral imaging datasets, achieving substantial improvement in pixel-wise classification accuracy and perfect object-based classification accuracy. The method is powerful in utilizing time dependencies and adaptable to non-congruent images over time sequences and spectroscopic data.
ANALYTICA CHIMICA ACTA
(2021)
Article
Engineering, Multidisciplinary
Rabiye Kilic, Nida Kumbasar, Emin Argun Oral, Ibrahim Yucel Ozbek
Summary: This study introduces a method for drone detection and classification using Radio Frequency (RF) signals and basic machine learning methods. The proposed method involves feature extraction and model training/testing stages. Experimental results demonstrate that the proposed method outperforms existing results on the DroneRF dataset.
ENGINEERING SCIENCE AND TECHNOLOGY-AN INTERNATIONAL JOURNAL-JESTECH
(2022)
Article
Engineering, Biomedical
Mrunal M. Shidore, Shreeram S. Athreya, Shantanu Deshpande, Rajesh Jalnekar
Summary: Variations in vibroarthrographic signal characteristics are directly associated with knee joint diseases, and statistical methods combined with machine learning algorithms can effectively classify these signals to distinguish healthy and abnormal knee conditions. Special feature selection techniques and classifier training methods contribute to high accuracy and effectiveness in screening subjects based on spectral domain characteristics.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2021)
Article
Automation & Control Systems
Run Jiang, Yuesheng Zheng
Summary: This article investigates the regularity of signal characteristics in the detection of ac series arc faults (SAF). By adopting a coupling method and a time-series reconstruction method, it demonstrates the feasibility and accuracy of identifying SAFs in unknown multiload circuits.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2023)
Article
Environmental Sciences
Yi Lu, Changbao Yang, Liguo Han
Summary: Vegetation obstructs the classification of bedrock and the acquisition of bedrock spectra using remote sensing data. Although previous studies have shown that bedrock can control vegetation growth, the potential of using vegetation spectral features to map bedrock has not been widely explored. This study utilized Sentinel-2 data to derive reflectance and vegetation indices, conducted a spatiotemporal analysis of vegetation spectral features on different bedrock, and used random forest classifiers to map bedrock. The results demonstrated the close relationship between vegetation growth and bedrock, and showed that both vegetation indices' combination and reflectance during the growing season can achieve reasonably classified maps with high accuracies.
GEOCARTO INTERNATIONAL
(2023)
Article
Computer Science, Artificial Intelligence
Qianli Ma, Zhenjing Zheng, Wanqing Zhuang, Enhuan Chen, Jia Wei, Jiabing Wang
Summary: This paper introduces an end-to-end model called EMAN for time series classification, which enhances the temporal memory of ESN by incorporating an echo memory-augmented mechanism. Experimental results show that EMAN outperforms existing time series classification methods, demonstrating the effectiveness of enhancing temporal memory.
Article
Engineering, Civil
Georgia Papacharalampous, Hristos Tyralis, Yannis Markonis, Martin Hanel
Summary: In this study, a new methodological framework is proposed for exploring and comparing multi-scale analyses in a hydroclimatic context, in order to comprehensively understand the behaviors of geophysical processes and evaluate time series simulation models. By computing the feature values at different temporal resolutions and three hydroclimatic time series types, similarities and differences in the evolution patterns are identified. The computed features are also used for meaningful clustering of hydroclimatic time series, which allows for interpretation of hydroclimatic similarity at various temporal resolutions.
JOURNAL OF HYDROLOGY
(2023)
Article
Computer Science, Information Systems
Cun Ji, Mingsen Du, Yanxuan Wei, Yupeng Hu, Shijun Liu, Li Pan, Xiangwei Zheng
Summary: Time series classification is widely used in various domains, including EEG/ECG classification, device anomaly detection, and speaker authentication. Despite the existence of many methods, selecting intuitive temporal features for accurate classification remains a challenge. Therefore, this paper proposes a new method called TSC-RTF, which utilizes random temporal features, and shows that it can compete with state-of-the-art methods.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2023)
Article
Automation & Control Systems
Xiufang Chen, Mei Liu, Shuai Li
Summary: In recent years, the echo state network (ESN) has been widely used in time series prediction due to its powerful computational abilities. However, most of the existing research on ESN assumes that the data is noise-free or only contaminated by Gaussian noise, which lacks robustness in solving real-world tasks. This study addresses this issue by proposing a probabilistic regularized ESN (PRESN) that guarantees robustness. The PRESN minimizes both the mean and variance of modeling error, and a scheme is derived for obtaining output weights. The performance and robustness of the PRESN are supported by theoretical analyses and validated through experiments on benchmark and real-world datasets.
IEEE-CAA JOURNAL OF AUTOMATICA SINICA
(2023)
Article
Environmental Sciences
Qunming Wang, Xinyu Ding, Xiaohua Tong, Peter M. Atkinson
Summary: The study introduces a spatio-temporal spectral unmixing (STSU) approach, which extends spectral unmixing into the spatio-temporal domain to obtain more reliable land cover information. This method does not require pure endmember extraction and directly uses extracted mixed training samples to construct a learning model, making it suitable for dynamic monitoring of land cover changes.
REMOTE SENSING OF ENVIRONMENT
(2021)
Article
Computer Science, Artificial Intelligence
Cun Ji, Mingsen Du, Yupeng Hu, Shijun Liu, Li Pan, Xiangwei Zheng
Summary: With the increasing application of Internet of Things technology, time series classification has become a research hotspot in the field of data mining. This paper proposes a new method for time series classification based on temporal features (TSC-TF), which generates temporal feature candidates through time series segmentation and selects important features with the help of a random forest. The experimental results on various datasets demonstrate the superiority of the proposed method.
APPLIED SOFT COMPUTING
(2022)
Article
Computer Science, Interdisciplinary Applications
Nathan Blanken, Jelmer M. Wolterink, Herve Delingette, Christoph Brune, Michel Versluis, Guillaume Lajoinie
Summary: In this study, an alternative super-resolution approach for ultrasound imaging is proposed, which utilizes a neural network to directly deconvolve single-channel ultrasound radio-frequency signals. The results demonstrate that this method can improve the axial resolution of ultrasound imaging and is sensitive to microbubble density.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2022)
Article
Acoustics
Michael T. Paris, Kirsten E. Bell, Egor Avrutin, Katherine Rosati, Marina Mourtzakis
Summary: The study compared the associations between muscle echo intensity and adipose or muscle tissue thickness in different age and gender groups. The results showed a negative association between muscle thickness and echo intensity in older adults, while no association was observed in younger individuals.
JOURNAL OF ULTRASOUND IN MEDICINE
(2022)
Article
Engineering, Mechanical
Yongbo Sui, Hui Gao
Summary: This paper introduces the modified echo state network (M-ESN) and the hybrid regularized network (HRN) for predicting nonlinear chaotic time series, showing that M-ESN can generate sparse output weight matrices with good generalization ability.
NONLINEAR DYNAMICS
(2022)
Article
Acoustics
Lucas Resque Porto, Raymond Tang, Andrew Sawka, Victoria Lessoway, Emran Mohammad Abu Anas, Delaram Behnami, Purang Abolmaesumi, Robert Rohling
ULTRASOUND IN MEDICINE AND BIOLOGY
(2019)
Article
Computer Science, Interdisciplinary Applications
Fatemeh Taheri Dezaki, Zhibin Liao, Christina Luong, Hany Girgis, Neeraj Dhungel, Amir H. Abdi, Delaram Behnami, Ken Gin, Robert Rohling, Purang Abolmaesumi, Teresa Tsang
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2019)
Article
Acoustics
Bo Zhuang, Robert Rohling, Purang Abolmaesumi
IEEE TRANSACTIONS ON ULTRASONICS FERROELECTRICS AND FREQUENCY CONTROL
(2019)
Article
Computer Science, Interdisciplinary Applications
Mehran Pesteie, Purang Abolmaesumi, Robert N. Rohling
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2019)
Article
Computer Science, Interdisciplinary Applications
Zhibin Liao, Hany Girgis, Amir Abdi, Hooman Vaseli, Jorden Hetherington, Robert Rohling, Ken Gin, Teresa Tsang, Purang Abolmaesumi
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2020)
Article
Computer Science, Interdisciplinary Applications
Alireza Mehrtash, William M. Wells, Clare M. Tempany, Purang Abolmaesumi, Tina Kapur
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2020)
Article
Computer Science, Interdisciplinary Applications
Fatemeh Taheri Dezaki, Christina Luong, Tom Ginsberg, Robert Rohling, Ken Gin, Purang Abolmaesumi, Teresa Tsang
Summary: Echo-SyncNet is a self-supervised learning framework for synchronizing various cross-sectional 2D echo series without human supervision or external inputs. It utilizes two types of supervisory signals, intra-view self-supervision and inter-view self-supervision, to learn a feature-rich and low dimensional embedding space for temporal synchronization.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2021)
Article
Computer Science, Interdisciplinary Applications
Mohammad H. Jafari, Christina Luong, Michael Tsang, Ang Nan Gu, Nathan Van Woudenberg, Robert Rohling, Teresa Tsang, Purang Abolmaesumi
Summary: This paper presents U-LanD, a framework for automatically detecting landmarks on key frames of videos by utilizing the uncertainty of landmark prediction. By leveraging the observation that a deep Bayesian landmark detector trained solely on key video frames has lower predictive uncertainty compared to other frames, U-LanD uses this unsupervised signal to recognize key frames and detect landmarks. The framework is tested on ultrasound imaging videos of the heart, where sparse and noisy clinical labels are available for only one frame in each video. Results show that U-LanD outperforms the state-of-the-art non-Bayesian method by a significant margin of 42% in R-2 score, without increasing the model size.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2022)
Article
Acoustics
Paul F. R. Wilson, Mahdi Gilany, Amoon Jamzad, Fahimeh Fooladgar, Minh Nguyen Nhat To, Brian Wodlinger, Purang Abolmaesumi, Parvin Mousavi
Summary: Deep learning-based analysis of high-frequency, high-resolution micro-ultrasound data shows great promise for prostate cancer detection. In this study, we successfully apply self-supervised representation learning to micro-ultrasound data and demonstrate its effectiveness in classifying cancer from noncancer tissue. Our method outperforms baseline supervised learning approaches and scales well with more unlabeled data.
IEEE TRANSACTIONS ON ULTRASONICS FERROELECTRICS AND FREQUENCY CONTROL
(2023)
Proceedings Paper
Engineering, Biomedical
Alireza Sedghi, Jie Luo, Alireza Mehrtash, Steve Pieper, Clare M. Tempany, Tina Kapur, Parvin Mousavi, William M. Wells
MEDICAL IMAGING 2019: IMAGE-GUIDED PROCEDURES, ROBOTIC INTERVENTIONS, AND MODELING
(2019)
Proceedings Paper
Engineering, Biomedical
Hooman Vaseli, Zhibin Liao, Amir H. Abdi, Hany Girgis, Delaram Behnami, Christina Luong, Fatemeh Taheri Dezaki, Neeraj Dhungel, Robert Rohling, Ken Gin, Purang Abolmaesumi, Teresa Tsang
MEDICAL IMAGING 2019: IMAGE-GUIDED PROCEDURES, ROBOTIC INTERVENTIONS, AND MODELING
(2019)
Proceedings Paper
Engineering, Biomedical
Si Jia Li, Jack Barnes, Purang Abolmaesumi, Hans-Peter Loock, Parvin Mousavi
MEDICAL IMAGING 2019: IMAGE-GUIDED PROCEDURES, ROBOTIC INTERVENTIONS, AND MODELING
(2019)
Proceedings Paper
Engineering, Biomedical
Brandon Chan, Jason Auyeung, John F. Rudan, Parvin Mousavi, Manuela Kunz
MEDICAL IMAGING 2019: IMAGE-GUIDED PROCEDURES, ROBOTIC INTERVENTIONS, AND MODELING
(2019)
Proceedings Paper
Engineering, Biomedical
Laura Connolly, Tamas Ungi, Andras Lasso, Thomas Vaughan, Mark Asselin, Parvin Mousavi, Scott Yam, Gabor Fichtinger
MEDICAL IMAGING 2019: IMAGE-GUIDED PROCEDURES, ROBOTIC INTERVENTIONS, AND MODELING
(2019)
Proceedings Paper
Engineering, Biomedical
Simon Honigmann, Yi Cheng Zhu, Rohit Singla, Purang Abolmaesumi, Anthony Chau, Robert Rohling
MEDICAL IMAGING 2019: IMAGE-GUIDED PROCEDURES, ROBOTIC INTERVENTIONS, AND MODELING
(2019)