FINDING A THESIS TOPIC Franks, Peter J.S.
Oceanography (Washington, D.C.),
09/2022, Volume:
35, Issue:
2
Journal Article
Peer reviewed
Open access
Finding a thesis topic is hard. It may be the hardest thing you do during your graduate degree. But there are commonalities to thesis topics—and the approaches to finding them—that might help you ...focus your efforts during your thesis-topic quest. Here I offer my advice and experience to help you find your way, and perhaps shorten your journey.
Electroencephalography (EEG) based Brain-Computer Interface (BCI) enables subjects to communicate with the outside world or control equipment using brain signals without passing through muscles and ...nerves. Many researchers in recent years have studied the non-invasive BCI systems. However, the efficiency of the intention decoding algorithm is affected by the random non-stationary and low signal-to-noise ratio characteristics of the EEG signal. Furthermore, channel selection is another important issue in BCI systems intention recognition. During intention recognition in BCI systems, the unnecessary information produced by redundant electrodes affects the decoding rate and deplete system resources. In this paper, we introduce a recurrent-convolution neural network model for intention recognition by learning decomposed spatio-temporal representations. We apply the novel Gradient-Class Activation Mapping (Grad-CAM) visualization technology to the channel selection. Grad-CAM uses the gradient of any classification, flowing into the last convolutional layer to produce a coarse localization map. Since the pixels of the localization map correspond to the spatial regions where the electrodes are placed, we select the channels that are more important for decision-making. We conduct an experiment using the public motor imagery EEG dataset EEGMMIDB. The experimental results demonstrate that our method achieves an accuracy of 97.36% at the full channel, outperforming many state-of-the-art models and baseline models. Although the decoding rate of our model is the same as the best model compared, our model has fewer parameters with faster training time. After the channel selection, our model maintains the intention decoding performance of 92.31% while reducing the number of channels by nearly half and saving system resources. Our method achieves an optimal trade-off between performance and the number of electrode channels for EEG intention decoding.
A new reconstruction method is developed for two‐dimensional (2‐D), steady, magnetohydrostatic structures with anisotropic plasma pressure, which is assumed to be solely dependent on magnetic field ...strength. This dependence leads to a Poisson‐like partial differential equation that can be solved as a spatial initial‐value problem by use of data taken from a single spacecraft passing through a coherent structure. However, the resulting partial differential equation cannot be reduced to the ordinary Grad‐Shafranov equation with isotropic pressure. The numerical code for new reconstruction is developed and successfully validated against an exact analytical solution. This new reconstruction method is first applied to examine 2‐D geometry of magnetic mirror structures observed by the Magnetospheric Multiscale (MMS) spacecraft in the Earth's magnetosheath. The observed mirror structures satisfy the magnetohydrostatic conditions and are comoving with the average ion bulk flow. Using MMS1 measurements, the reconstruction produces a 2‐D magnetic field map and distribution maps of pressures perpendicular and parallel to the magnetic field. The reconstructed field map reveals magnetic bottle‐like structures as predicted by the mirror‐mode theory. A very good agreement is achieved between observation and reconstruction for the other three MMS spacecraft not used for reconstruction. It is concluded that this new reconstruction is suitable for examining 2‐D geometry of mirror structures.
Key Points
A new reconstruction method for 2‐D, steady, magnetohydrostatic structures with anisotropic plasma pressure is developed and validated
The reconstruction is first applied to in situ observations of magnetic mirror structures by MMS spacecraft in the Earth's magnetosheath
The reconstructed magnetic field map shows magnetic bottle‐like structures as predicted by the mirror‐mode theory
Display omitted
Pneumothorax is an acute thoracic disease caused by abnormal air collection between the lungs and chest wall. Recently, artificial intelligence (AI), especially deep learning (DL), ...has been increasingly employed for automating the diagnostic process of pneumothorax. To address the opaqueness often associated with DL models, explainable artificial intelligence (XAI) methods have been introduced to outline regions related to pneumothorax. However, these explanations sometimes diverge from actual lesion areas, highlighting the need for further improvement.
We propose a template-guided approach to incorporate the clinical knowledge of pneumothorax into model explanations generated by XAI methods, thereby enhancing the quality of the explanations. Utilizing one lesion delineation created by radiologists, our approach first generates a template that represents potential areas of pneumothorax occurrence. This template is then superimposed on model explanations to filter out extraneous explanations that fall outside the template’s boundaries. To validate its efficacy, we carried out a comparative analysis of three XAI methods (Saliency Map, Grad-CAM, and Integrated Gradients) with and without our template guidance when explaining two DL models (VGG-19 and ResNet-50) in two real-world datasets (SIIM-ACR and ChestX-Det).
The proposed approach consistently improved baseline XAI methods across twelve benchmark scenarios built on three XAI methods, two DL models, and two datasets. The average incremental percentages, calculated by the performance improvements over the baseline performance, were 97.8% in Intersection over Union (IoU) and 94.1% in Dice Similarity Coefficient (DSC) when comparing model explanations and ground-truth lesion areas. We further visualized baseline and template-guided model explanations on radiographs to showcase the performance of our approach.
In the context of pneumothorax diagnoses, we proposed a template-guided approach for improving model explanations. Our approach not only aligns model explanations more closely with clinical insights but also exhibits extensibility to other thoracic diseases. We anticipate that our template guidance will forge a novel approach to elucidating AI models by integrating clinical domain expertise.
The development of a generalized two dimensional MHD equilibrium solver within the nimrod framework Sovinec, et al., J. Comput. Phys. 195 (2004) 355 is discussed. Spectral elements are used to ...represent the poloidal plane. To permit the generation of spheromak and other compact equilibria, special consideration is given to ensure regularity at the geometric axis (R=0). The scalar field Λ=ψ/R2 is used as the dependent variable to express the Grad–Shafranov operator as a total divergence. With the correct gauge, regularity along the geometric axis is satisfied. The convergence properties of the spectral elements are investigated by comparing numerically generated equilibria against known analytic solutions. Equilibria accurate to double precision error are generated with sufficient resolution. Depending on the equilibrium, either geometric or algebraic convergence is observed as the polynomial degree of the spectral-element basis is increased.
The rapid migration to remote instruction during the Covid-19 pandemic has expedited the need for more research, expertise, and practical guidelines for online and blended learning. A theoretical ...grounding of approaches and practices is imperative to support blended learning and sustain change across multiple levels in education organizations, from leadership to classroom. The Community of Inquiry is a valuable framework that regards higher education as both a collaborative and individually constructivist learning experience. The framework considers the interdependent elements of social, cognitive, and teaching presence to create a meaningful learning experience. In this volume, the authors further explore and refine the blended learning principles presented in their first book, Teaching in Blended Learning Environments: Creating and Sustaining Communities of Inquiry, with an added focus on designing, facilitating, and directing collaborative blended learning environments by emphasizing the concept of shared metacognition.
The main aim of this paper is to discuss the influence of fractal dimensions on the behavior of the solutions of the Grad-Shafranov equation. Our study is based on the product-like fractal measure ...approach constructed by Li and Ostoja-Starzewski in their attempt to explore anisotropic fractal continuum media. The fractal Grad-Shafranov equation gives the possibility to analyze, in a toroidal fusion reactor, the plasma equilibrium in fractal dimensions. Examples of the exact equilibrium solution are given for both the vacuum case outside the plasma and the toroidally shaped spheromak. Note: PACS numbers 05.45.Df: Fractals; 28.52.−s: Fusion reactors; 52.30.Cv: Magnetohydrodynamics; and 52.55.Ip: Spheromaks.
This article presents and studies a two-level grad-div stabilized finite element discretization method for solving numerically the steady incompressible Navier–Stokes equations. The method consists ...of two steps. In the first step, we compute a rough solution by solving a nonlinear Navier–Stokes system on a coarse grid. And then, in the second step, we pass the coarse grid solution to a fine grid to linearize the nonlinear term, update the solution by solving a linearized problem based on Newton iterations. In both steps, a grad-div stabilization term is incorporated into the system to reduce the influence of pressure on the approximate velocity. We analyze stability and asymptotic convergence of the approximate solutions, derive explicit dependence of the solution errors on the grad-div stabilization parameter and viscosity. We perform also some numerical tests to validate the theoretical analysis and illustrate the efficiency of the proposed method. Compared with the standard two-level method without stabilizations, the grad-div stabilization term added in present method improves the accuracy of the approximate velocity, accelerates the convergence of the nonlinear iterations for the coarse mesh nonlinear system, and reduces the computational time.
•A two-level grad-div stabilized finite element discretization method for the incompressible Navier–Stokes equations is presented.•The method is easy to implement based on existing codes.•The method can yield much better solutions than the standard two-level discretization method with reduction in computational time when the viscosity is small.•Convergence results with respective to the mesh size, viscosity and stabilization parameter are derived.•Numerical results demonstrate the promise of the proposed method.
This study presents the investigation of optical emission spectroscopy of plasma using interpretable convolutional neural network (CNN) for real-time volatile organic compounds (VOCs) classification. ...A microplasma-generation platform was developed to efficiently collect 64 k spectra from various types of VOCs at different concentrations, as training and testing sets for machine learning. A CNN model was trained to classify VOCs with accuracy of 99.9%. To interpret the CNN model and its predictions, the spectral processing mechanism of the CNN was visualized by feature maps and the critical spectral features were identified by gradient-weighted class activation mapping. Such approaches brought insights on how CNN analyzes the spectra and enables the CNN operation to be explainable. Finally, the CNN model was incorporated with the microplasma platform to demonstrate the application of real-time VOC monitoring. The type of VOCs can be identified and reported via messages within 10 s once the microplasma is ignited. We believe that using CNN brings a novel route for plasma spectroscopy analysis for VOC classification and impacts the fields of plasma, spectroscopy, and environmental monitoring.
Display omitted
•CNN was used to analyze plasma spectroscopy for VOC identification.•The CNN model was used to classify the VOCs with accuracy >99.8%.•Grad-CAM was used to interpret the CNN predictions.•Real-time and online monitoring of VOCs was performed with instant warning message.