More Like this

1. Body Motion Segmentation via Multilayer Graph Processing for Wearable Sensor Signals

   https://doi.org/10.1109/OJSP.2024.3407662  

   Deng, Qinwen; Zhang, Songyang; Ding, Zhi (January 2024, IEEE Open Journal of Signal Processing)

   Human body motion segmentation plays a major role in many applications, ranging from computer vision to robotics. Among a variety of algorithms, graph-based approaches have demonstrated exciting potential in motion analysis owing to their power to capture the underlying correlations among joints. However, most existing works focus on simpler single-layer geometric structures, whereas multi-layer spatial-temporal graph structure can provide more informative results. To provide an interpretable analysis on multilayer spatial-temporal structures, we revisit the emerging field of multilayer graph signal processing (M-GSP), and propose novel approaches based on M-GSP to human motion segmentation. Specifically, we model the spatial-temporal relationships via multilayer graphs (MLG) and introduce M-GSP spectrum analysis for feature extraction.We present two different M-GSP based algorithms for unsupervised segmentation in the MLG spectrum and vertex domains, respectively. Our experimental results demonstrate the robustness and effectiveness of our proposed methods. 

   more » « less
2. Graph Signal Processing for Infrastructure Resilience: Suitability and Future Directions

   https://doi.org/10.1109/RWS50334.2020.9241286  

   Schultz, Kevin; Villafane-Delgado, Marisel; Reilly, Elizabeth P.; Hwang, Grace M.; Saksena, Anshu (October 2020, 2020 Resilience Week (RWS))

   Graph signal processing (GSP) is an emerging field developed for analyzing signals defined on irregular spatial structures modeled as graphs. Given the considerable literature regarding the resilience of infrastructure networks using graph theory, it is not surprising that a number of applications of GSP can be found in the resilience domain. GSP techniques assume that the choice of graphical Fourier transform (GFT) imparts a particular spectral structure on the signal of interest. We assess a number of power distribution systems with respect to metrics of signal structure and identify several correlates to system properties and further demonstrate how these metrics relate to performance of some GSP techniques. We also discuss the feasibility of a data-driven approach that improves these metrics and apply it to a water distribution scenario. Overall, we find that many of the candidate systems analyzed are properly structured in the chosen GFT basis and amenable to GSP techniques, but identify considerable variability and nuance that merits future investigation. 

   more » « less
3. t-HGSP: Hypergraph Signal Processing Using t-Product Tensor Decompositions

   https://doi.org/10.1109/TSIPN.2023.3276687  

   Pena-Pena, Karelia; Lau, Daniel L; Arce, Gonzalo R (January 2023, IEEE Transactions on Signal and Information Processing over Networks)

   Graph signal processing (GSP) techniques are powerful tools that model complex relationships within large datasets, being now used in a myriad of applications in different areas including data science, communication networks, epidemiology, and sociology. Simple graphs can only model pairwise relationships among data which prevents their application in modeling networks with higher-order relationships. For this reason, some efforts have been made to generalize well-known graph signal processing techniques to more complex graphs such as hypergraphs, which allow capturing higher-order relationships among data. In this article, we provide a new hypergraph signal processing framework (t-HGSP) based on a novel tensor-tensor product algebra that has emerged as a powerful tool for preserving the intrinsic structures of tensors. The proposed framework allows the generalization of traditional GSP techniques while keeping the dimensionality characteristic of the complex systems represented by hypergraphs. To this end, the core elements of the t-HGSP framework are introduced, including the shifting operators and the hypergraph signal. The hypergraph Fourier space is also defined, followed by the concept of bandlimited signals and sampling. In our experiments, we demonstrate the benefits of our approach in applications such as clustering and denoising. 

   more » « less
4. Patch-Based Diffusion Learning for Hyperspectral Image Clustering

   https://doi.org/10.1109/IGARSS39084.2020.9323091  

   Murphy, James M. (January 2020, IEEE International Geoscience and Remote Sensing Symposium)

   null (Ed.)

   An algorithm for clustering hyperspectral images (HSI) based on diffusion geometry in the space of high-dimensional image patches is proposed. By using the patch structure of the HSI, robustness to noise is achieved in the clustering process. Results on real hyperspectral data indicate the effectiveness of working in the space of HSI patches, compared to working in the space of HSI pixels. 

   more » « less
5. Quaternion based neural network for hyperspectral image classification

   https://doi.org/10.1117/12.2558808  

   Rao, Shishir Paramathma; Panetta, Karen; Agaian, Sos S. (April 2020, Mobile Multimedia/Image Processing, Security, and Applications 2020)

   Agaian, Sos S.; Jassim, Sabah A.; DelMarco, Stephen P.; Asari, Vijayan K. (Ed.)

   Neural networks have emerged to be the most appropriate method for tackling the classification problem for hyperspectral images (HIS). Convolutional neural networks (CNNs), being the current state-of-art for various classification tasks, have some limitations in the context of HSI. These CNN models are very susceptible to overfitting because of 1) lack of availability of training samples, 2) large number of parameters to fine-tune. Furthermore, the learning rates used by CNN must be small to avoid vanishing gradients, and thus the gradient descent takes small steps to converge and slows down the model runtime. To overcome these drawbacks, a novel quaternion based hyperspectral image classification network (QHIC Net) is proposed in this paper. The QHIC Net can model both the local dependencies between the spectral channels of a single-pixel and the global structural relationship describing the edges or shapes formed by a group of pixels, making it suitable for HSI datasets that are small and diverse. Experimental results on three HSI datasets demonstrate that the QHIC Net performs on par with the traditional CNN based methods for HSI Classification with a far fewer number of parameters. Keywords: Classification, deep learning, hyperspectral imaging, spectral-spatial feature learning 

   more » « less