James Murphy

Dr. James Murphy

Department of Mathematics, Tufts University, Medford, MA 02139, USA
orcid

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
4 October 2018 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
James MurphyJames Murphy
James Murphy
MMMauro Maggioni
Mauro Maggioni
The problem of unsupervised learning and segmentation of hyperspectral images is a significant challenge in remote sensing. The high dimensionality of hyperspectral data, presence of substantial noise, and overlap of classes all contribute to the difficulty of automatically clustering and segmenting hyperspectral images. We propose an unsupervised learning technique called spectral-spatial diffusion learning (DLSS) that combines a geometric estimation of class modes with a diffusion-inspired labeling that incorporates both spectral and spatial information. The mode estimation incorporates the geometry of the hyperspectral data by using diffusion distance to promote learning a unique mode from each class. These class modes are then used to label all the points by a joint spectral-spatial nonlinear diffusion process. A related variation of DLSS is also discussed, which enables active learning by requesting labels for a very small number of well-chosen pixels, dramatically boosting overall clustering results. Extensive experimental analysis demonstrates the efficacy of the proposed methods against benchmark and state-of-the-art hyperspectral analysis techniques on a variety of real data sets, their robustness to choices of parameters, and their low computational complexity.

4 April 2024 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
Kangning CuiKangning Cui
Kangning Cui
RLRuoning Li
Ruoning Li
SPSam L Polk
Sam L Polk
YLYinyi Lin
Yinyi Lin
Hongsheng ZhangHongsheng Zhang
Hongsheng Zhang
Raymond H. ChanRaymond H. Chan
Raymond H. Chan
Hyperspectral images (HSIs) provide exceptional spatial and spectral resolution of a scene, crucial for various remote sensing applications. However, the high dimensionality, presence of noise and outliers, and the need for precise labels of HSIs present significant challenges to the analysis of HSIs, motivating the development of performant HSI clustering algorithms. This article introduces a novel unsupervised HSI clustering algorithm—superpixel-based and spatially regularized diffusion learning ( $\text{S}^{2}$ DL)—which addresses these challenges by incorporating rich spatial information encoded in HSIs into diffusion geometry-based clustering. $\text{S}^{2}$ DL employs the entropy rate superpixel (ERS) segmentation technique to partition an image into superpixels, then constructs a spatially regularized diffusion graph using the most representative high-density pixels. This approach reduces computational burden while preserving accuracy. Cluster modes, serving as exemplars for underlying cluster structure, are identified as the highest-density pixels farthest in diffusion distance from other highest-density pixels. These modes guide the labeling of the remaining representative pixels from ERS superpixels. Finally, majority voting is applied to the labels assigned within each superpixel to propagate labels to the rest of the image. This spatial–spectral approach simultaneously simplifies graph construction, reduces computational cost, and improves clustering performance. $\text{S}^{2}$ DL’s performance is illustrated with extensive experiments on four publicly available, real-world HSIs: Indian Pines, Salinas, Salinas A, and WHU-Hi. Additionally, we apply $\text{S}^{2}$ DL to landscape-scale, unsupervised mangrove species mapping in the Mai Po Nature Reserve (MPNR), Hong Kong, using a Gaofen-5 HSI. The success of $\text{S}^{2}$ DL in these diverse numerical experiments indicates its efficacy on a wide range of important unsupervised remote sensing analysis tasks.

14 October 2019 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Closed access
James MurphyJames Murphy
James Murphy
MMMauro Maggioni
Mauro Maggioni
An unsupervised learning algorithm to cluster hyperspectral image (HSI) data that leverages spatially regularized random walks is proposed. Markov diffusions are defined on the space of HSI spectra with transitions constrained to near spatial neighbors. The explicit incorporation of spatial regularity into the diffusion construction leads to smoother random processes that are more adapted for unsupervised machine learning than those based on spectra alone. The regularized diffusion process is subsequently used to embed the high-dimensional HSI into a lower-dimensional space through diffusion distances. Cluster modes are computed using kernel density estimation and diffusion distances, and all other points are labeled according to these modes. The proposed method has low computational complexity and performs competitively against state-of-the-art HSI clustering algorithms on real data. In particular, the proposed spatial regularization confers both theoretical and empirical advantages over nonregularized methods.

1 January 2019 in Foundations of Data Science
Verified
Journal Article
Open access
PDF file
MMMauro Maggioni
Mauro Maggioni
James MurphyJames Murphy
James Murphy
This article proposes an active learning method for high-dimensional data, based on intrinsic data geometries learned through diffusion processes on graphs. Diffusion distances are used to parametrize low-dimensional structures on the dataset, which allow for high-accuracy labelings with only a small number of carefully chosen training labels. The geometric structure of the data suggests regions that have homogeneous labels, as well as regions with high label complexity that should be queried for labels. The proposed method enjoys theoretical performance guarantees on a general geometric data model, in which clusters corresponding to semantically meaningful classes are permitted to have nonlinear geometries, high ambient dimensionality, and suffer from significant noise and outlier corruption. The proposed algorithm is implemented in a manner that is quasilinear in the number of unlabeled data points, and exhibits competitive empirical performance on synthetic datasets and real hyperspectral remote sensing images.

15 February 2023 in Remote Sensing
Verified
Journal Article
Open access
PDF file
SPSam L Polk
Sam L Polk
Kangning CuiKangning Cui
Kangning Cui
ACAland H. Y. Chan
Aland H. Y. Chan
DCDavid Coomes
David Coomes
RPRobert Plemmons
Robert Plemmons
James MurphyJames Murphy
James Murphy
Hyperspectral images taken from aircraft or satellites contain information from hundreds of spectral bands, within which lie latent lower-dimensional structures that can be exploited for classifying vegetation and other materials. A disadvantage of working with hyperspectral images is that, due to an inherent trade-off between spectral and spatial resolution, they have a relatively coarse spatial scale, meaning that single pixels may correspond to spatial regions containing multiple materials. This article introduces the Diffusion and Volume maximization-based Image Clustering (D-VIC) algorithm for unsupervised material clustering to address this problem. By directly incorporating pixel purity into its labeling procedure, D-VIC gives greater weight to pixels corresponding to a spatial region containing just a single material. D-VIC is shown to outperform comparable state-of-the-art methods in extensive experiments on a range of hyperspectral images, including land-use maps and highly mixed forest health surveys (in the context of ash dieback disease), implying that it is well-equipped for unsupervised material clustering of spectrally-mixed hyperspectral datasets.

5 October 2021 in Journal of Chemical Information and Modeling
Verified
Journal Article
Open access
JDJovan Damjanovic
Jovan Damjanovic
James MurphyJames Murphy
James Murphy
YLYu-Shan Lin
Yu-Shan Lin
Molecular dynamics (MD) simulations are an exceedingly and increasingly potent tool for molecular behavior prediction and analysis. However, the enormous wealth of data generated by these simulations can be difficult to process and render in a human-readable fashion. Cluster analysis is a commonly used way to partition data into structurally distinct states. We present a method that improves on the state of the art by taking advantage of the temporal information of MD trajectories to enable more accurate clustering at a lower memory cost. To date, cluster analysis of MD simulations has generally treated simulation snapshots as a mere collection of independent data points and attempted to separate them into different clusters based on structural similarity. This new method, cluster analysis of trajectories based on segment splitting (CATBOSS), applies density-peak-based clustering to classify trajectory segments learned by change detection. Applying the method to a synthetic toy model as well as four real-life data sets–trajectories of MD simulations of alanine dipeptide and valine dipeptide as well as two fast-folding proteins–we find CATBOSS to be robust and highly performant, yielding natural-looking cluster boundaries and greatly improving clustering resolution. As the classification of points into segments emphasizes density gaps in the data by grouping them close to the state means, CATBOSS applied to the valine dipeptide system is even able to account for a degree of freedom deliberately omitted from the input data set. We also demonstrate the potential utility of CATBOSS in distinguishing metastable states from transition segments as well as promising application to cases where there is little or no advance knowledge of intrinsic coordinates, making for a highly versatile analysis tool.