Pushing the boundaries of knowledge, uncovering new insights, and solving complex problems to contribute to a brighter and more informed future.
Data Science
newmanjustin.com
My passion for computer science, data analysis, and machine learning has driven me to engage in impactful projects. I've dedicated my efforts to subclassifying cancers using TensorFlow, utilizing its capabilities to predict cancer subtypes and their response to treatments.
Additionally, I've explored a wide array of machine learning techniques, including decision trees, support vector machines, random forests, neural networks, k-nearest neighbors, and lasso/ridge regression. These experiences have deepened my commitment to advancing these fields and have reinforced my enthusiasm for leveraging data-driven solutions.
Sub-classifying Ovarian Cancer with TensorFlow2
Kaggle.com
In this cancer classification project using TensorFlow2 and Keras, the primary challenge is to accurately classify ovarian cancer types in tissue samples, which often involve massive images. Rather than scaling down these images, the proposed approach involves image segmentation to divide large images into smaller, more manageable segments (225x225 pixel tiles). This segmentation allows the model to focus on finer details within the tissue samples, potentially improving the accuracy of cancer detection. Additionally, I plan to implement CUDA GPU acceleration to further enhance the processing speed once the model is trained on a smaller dataset.
TensorFlow
Keras
The classification model itself is a neural network model built using TensorFlow and Keras. This model will be trained on the segmented image tiles to classify each segment according to the type of cancer it represents. The aggregated result of these individual segment classifications will be determined through a majority voting mechanism, ultimately classifying the entire tissue sample. The proposed approach offers benefits such as improved accuracy, efficient processing, and interpretability, as it allows for visualizing predictions on individual segments to gain insights into the regions classified as cancerous.
Future steps
updates
Future steps in the project include data preprocessing, where various techniques like data augmentation and normalization will be explored, model tuning involving the experimentation with different neural network architectures and hyperparameters, data visualization to gain insights into the distribution of cancer types, and model evaluation using metrics like accuracy, precision, recall, and F1-score. Ultimately, the model could be considered for deployment in real-world cancer diagnosis, integrating it into a medical system to assist pathologists in identifying and classifying ovarian cancer types in tissue samples.
Computer Science and Data Analytics Graduate
Justin Newman
In this project to classify ovarian cancer types using TensorFlow2 and Keras, I have encountered a set of significant challenges. One of the primary hurdles is dealing with the immense size of cell tissue sample images, some of which can exceed several gigabytes in size. These memory constraints present a formidable obstacle, demanding innovative strategies to work effectively within such limitations. Moreover, the task of finding the most adequate segments within these massive images for extraction and model training is a meticulous process. It necessitates the development of algorithms to identify the most informative portions of the tissue samples, ensuring that our model can effectively focus on the vital details required for accurate cancer type classification. Throughout this journey, I am truly grateful for the incredible support and appreciation from the Kaggle community, whose insights and contributions have been invaluable in overcoming these challenges and advancing our mission.
Deck.gl
3D Data
I really love working with deck.gl and Plotly. There's something so rewarding about transforming raw data into interactive and engaging 3D visualizations. deck.gl's power and flexibility make it an ideal tool for crafting immersive experiences, and Plotly's knack for creating dynamic and insightful charts adds an extra layer of magic to my projects. Whether I'm mapping out geospatial data, creating intricate 3D graphs, or constructing interactive dashboards, these tools enable me to bring data to life, and I absolutely love the creative process it involves.
Each question leads to an answer and every answer inspires new questions.
Analysis of SOL Test Pass Rates in the Commonwealth of Virginia
MATH 268
In 2022 I conducted a comprehensive analysis of Virginia's "Standards of Learning" (SOL) test pass rates from 2018 to 2021. Findings reveal a generally normal pass rate distribution in 2021 with a slight leftward skew (Fig. 1.1), while gender disparities show higher median pass rates for female students (Fig. 1.2). The analysis further dissects subject-specific pass rates, indicating a pronounced leftward skew in math scores (Fig. 1.4), a wider left skew in science scores (Fig. 1.5), and a higher median in reading scores (Fig. 1.6). Subgroup comparisons, linear regression analysis (Fig. 2.2), and residual matrix assessments provide insights into variations among subgroups. Additionally, logistic regression predicts student ethnicity based on SOL pass rates. This research offers valuable insights for educational policy and decision-making in Virginia.
Rapid API USA. Gas Price by State.
Justin Newman
Utilizing the power of D3 Observable notebooks, I have seamlessly harnessed Rapid API's data to create an interactive choropleth map of the United States, providing gas price data at a glance. With the fusion of D3's data visualization capabilities and Observable's interactivity, I've designed a dynamic and user-friendly tool that allows you to explore gas prices across the nation with ease. Whether you're a traveler planning your journey or a data enthusiast analyzing trends, my choropleth map delivers an intuitive and informative experience, keeping you informed about gas prices by state in an engaging and visually appealing manner.
Contact me
newmanjustin.com/resume
I'm excited to connect and explore potential collaboration opportunities! If your skills and interests seem to align with my own, and you believe we could create something amazing together. I'm eager to discuss potential projects. Don't hesitate to reach out – I'm just a message away, and I'm sure our combined expertise could lead to some fantastic results. Let's make it happen!