About
22
Publications
2,625
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
211
Citations
Introduction
Computational science postdoc fellow at Lawrence Berkeley National Laboratory passionate about data analysis, machine learning, and high-performance computing. Fulbright alumna with significant research experience in software development, data science, and digital signal processing.
Current institution
Additional affiliations
August 2018 - May 2021
May 2015 - July 2016
October 2012 - April 2015
Education
August 2018 - May 2021
August 2016 - May 2018
May 2009 - April 2014
Field of study
- Electronics and Telecommunications Engineering
Publications
Publications (22)
This study introduces a novel labeling pipeline to accelerate the labeling process of
scientific data sets by using artificial-intelligence (AI)-guided tagging techniques. This
pipeline includes a set of interconnected web-based graphical user interfaces (GUIs),
where Data Clinic and MLCoach enable the preparation of machine learning (ML)
models fo...
We fine-tuned a foundational stable diffusion model using X-ray scattering images and their corresponding descriptions to generate new scientific images from given prompts. However, some of the generated images exhibit significant unrealistic artifacts, commonly known as "hallucinations". To address this issue, we trained various computer vision mo...
DLSIA (Deep Learning for Scientific Image Analysis) is a Python-based machine learning library that empowers scientists and researchers across diverse scientific domains with a range of customizable convolutional neural network (CNN) architectures for a wide variety of tasks in image analysis to be used in downstream data processing. DLSIA features...
We introduce DLSIA (Deep Learning for Scientific Image Analysis), a Python-based machine learning library that empowers scientists and researchers across diverse scientific domains with a range of customizable convolutional neural network (CNN) architectures for a wide variety of tasks in image analysis to be used in downstream data processing, or...
Scientific user facilities present a unique set of challenges for image processing due to the large volume of data generated from experiments and simulations. Furthermore, developing and implementing algorithms for real-time processing and analysis while correcting for any artifacts or distortions in images remains a complex task, given the computa...
Machine learning (ML) algorithms are showing a growing trend in helping the scientific communities across different disciplines and institutions to address large and diverse data problems. However, many available ML tools are programmatically demanding and computationally costly. The MLExchange project aims to build a collaborative platform equippe...
The implementation is proposed of image inpainting techniques for the reconstruction of gaps in experimental X-ray scattering data. The proposed methods use deep learning neural network architectures, such as convolutional autoencoders, tunable U-Nets, partial convolution neural networks and mixed-scale dense networks, to reconstruct the missing in...
Machine learning (ML) algorithms are showing a growing trend in helping the scientific communities across different disciplines and institutions to address large and diverse data problems.
However, many available ML tools are programmatically demanding and computationally costly.
The MLExchange project aims to build a collaborative platform equippe...
This paper proposes a supervised multinomial Bayesian learning algorithm for breast cancer detection using terahertz (THz) imaging of freshly excised murine tumors. The proposed algorithm utilizes a multinomial Bayesian probit regression approach, which establishes the link between THz data and classification results by using two different models,...
https://www.usnc-ursi-archive.org/aps-ursi/2020/pdfs/0000009.pdf
This paper proposes a new dimension reduction algorithm based on low-dimension ordered orthogonal projection (LOOP), which is used for cancer detection with terahertz (THz) images of freshly excised human breast cancer tissues. A THz image can be represented by a data cube with each pixel containing a high dimension spectrum vector covering several...
This paper presents an image morphing algorithm for quantitative evaluation methodology of terahertz (THz) images of excised breast cancer tumors. Most current studies on the assessment of THz imaging rely on qualitative evaluation, and there is no established benchmark or procedure to quantify the THz imaging performance. The proposed morphing alg...
This paper investigates terahertz (THz) imaging and classification of freshly excised murine xenograft breast cancer tumors. These tumors are grown via injection of E0771 breast adenocarcinoma cells into the flank of mice maintained on high-fat diet. Within 1 h of excision, the tumor and adjacent tissues are imaged using a pulsed THz system in the...
Industry 4.0 and industrial Internet of Things (iIoT) trends are pushing towards the transformation of factories to provide more flexible production systems through the use of wireless networks. Technologies enabling the “Factory-of-Things” (FoT) paradigm allow the safe deployment of wireless field devices in industrial plants thanks to their low-b...
Actualmente los sistemas de telecomunicaciones manejan tasas de velocidad muy elevadas, debido al gran aumento de la demanda de los mismos. Este aumento de demanda de información ha desembocado en utilizar equipos más rápidos, ya que a mayor demanda, se necesitan equipos de mayor velocidad. Por lo cual para poder identificar las tramas de datos es...
This paper investigates the possibility of estimating the path averaged rainfall by means of single frequency microwave links. Microwave link attenuation measurements can supplement data gathered in the air (e.g. radars) or on the ground (e.g. raingauges), providing useful information about the rainfall on a virtually continuous time scale. We pres...
Questions
Question (1)
I work on biomedical imaging for cancer detection and I am trying to consider the relationship among neighboring pixels into my clustering analysis (healthy tissue vs. cancer). In fact, for my case each pixel contains a high-dimensional vector of size Z>3. Therefore, the representation of the image would be A \in R^{MxNxZ}, where M and N represent the number of rows and columns, respectively. The total number of pixels per image would be MxN.
I read about Fuzzy c-means co-clustering and it seems to be promising, but I encountered that it clusters the rows and columns separately and then combines the co-clusters as follows:
Row labels: 1 1 2 2 3
Column labels: 2 1 3 1 1 2
Final co-clusters:
(1,2) [(1,1)] (1,3) [(1,1)] (1,2)
(1,2) [(1,1)] (1,3) [(1,1)] (1,2)
(2,2) (2,1) (2,3) (2,1) (2,2)
(2,2) (2,1) (2,3) (2,1) (2,2)
(3,2) (3,1) (3,3) (3,1) (3,2)
I have highlighted [()] the co-cluster (1,1), which would represent the same region. Is my understanding of the combination step correct? I was wondering if the probabilities of each row/column belonging to an specific cluster could be combined such that I could obtained a probability of a pixel belonging to an specific co-cluster.
In addition, could co-clustering be applied to image segmentation? My main concern is that non-block shaped regions (ex: triangular) may not be detected properly, for example:
A A A A A X A A
A A A A X X A A
A A A X X X A A
A A X X X X A A
I believe that the X-elements could not be co-clustered properly given the irregular shape.
Thanks a lot for your help!
