You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: src/pages/narrative/projects.html
+1-1Lines changed: 1 addition & 1 deletion
Original file line number
Diff line number
Diff line change
@@ -43,7 +43,7 @@ <h2>What I built</h2>
43
43
<ul>
44
44
<li><strong>Data & Machine Learning</strong><br>House-Price-ML (v1 baseline and v2 feature engineering) — full ML pipelines from EDA to scikit-learn models. Pendulum Data-Driven Control — reinforcement learning for control theory. ML Hackathon project (CatBoost for overqualification prediction).</li>
<li><strong>Systems & Coursework</strong><br>Personal website, portfolio projects, and research on AI in autonomous vehicles. Smaller experiments in C, Linux, and CLI tooling.</li>
46
+
<li><strong>Systems & Coursework</strong><br>Personal website, portfolio projects, and research on AI in Autonomous Vehicles. Smaller experiments in C, Linux, and CLI tooling.</li>
<p>Research project exploring the role of artificial intelligence in self-driving systems: perception, decision-making, and safety considerations in autonomous vehicle technology.</p>
<p><ahref="../projects.html" class="project-back">← Back to Projects</a></p>
26
26
<headerclass="project-header">
27
-
<h1class="project-title">AI in autonomous vehicles</h1>
27
+
<h1class="project-title">AI in Autonomous Vehicles</h1>
28
28
<pclass="project-summary">A technical overview of AI systems in autonomous vehicles, covering perception, decision-making, and real-world deployment challenges.</p>
29
29
<divclass="project-meta-row">
30
30
<divclass="project-meta-links">
@@ -71,6 +71,15 @@ <h2>✍️ Persuasive Paper: AI / Technology & Society</h2>
71
71
</div>
72
72
</section>
73
73
74
+
<sectionclass="project-detail-section">
75
+
<h2>Tech Stack</h2>
76
+
<divclass="tech-tags">
77
+
<span>Research</span>
78
+
<span>Academic Writing</span>
79
+
<span>PDF</span>
80
+
</div>
81
+
</section>
82
+
74
83
<sectionclass="project-detail-section">
75
84
<h2>Paper Summaries</h2>
76
85
<p><em>Informative:</em> A technical overview of AI systems in autonomous vehicles, covering perception, decision-making, and real-world deployment challenges.</p>
<imgsrc="../../assets/projects/airbnb-market-analysis/jupyter.png" alt="Jupyter notebook ETL and exploration for Vancouver Airbnb data">
45
-
<figcaption>Python ETL and exploratory analysis in Jupyter: loading raw CSVs, cleaning prices and dates, and building SQL-backed views before exporting to Tableau.</figcaption>
<figcaption>Interactive Tableau dashboard: neighbourhood-level pricing, room-type breakdowns, and filters so stakeholders can explore Vancouver Airbnb market at a glance.</figcaption>
<figcaption>Interactive Tableau dashboard: neighbourhood-level pricing, room-type breakdowns, and filters so stakeholders can explore Vancouver Airbnb market at a glance.</figcaption>
<imgsrc="../../assets/projects/undereployment-prediction/exploration%20heatmap.png" alt="Exploration heatmap from underemployment prediction EDA">
44
-
<figcaption>Exploratory analysis: correlation and feature relationships in the NGS hiring dataset, used to inform preprocessing and feature selection for the CatBoost pipeline.</figcaption>
45
-
</figure>
46
-
<figureclass="project-screenshot">
47
-
<imgsrc="../../assets/projects/undereployment-prediction/results.png" alt="Model results and evaluation metrics">
48
-
<figcaption>Model evaluation and interpretability — feature importance and validation metrics from the CatBoost classifier (0.75 public / 0.71 private leaderboard accuracy at the SFU ML Hackathon).</figcaption>
49
-
</figure>
50
-
</div>
40
+
<h2>Preview</h2>
41
+
<figureclass="project-screenshot">
42
+
<imgsrc="../../assets/projects/undereployment-prediction/exploration%20heatmap.png" alt="Exploration heatmap from underemployment prediction EDA">
43
+
<figcaption>Exploratory analysis: correlation and feature relationships in the NGS hiring dataset, used to inform preprocessing and feature selection for the CatBoost pipeline.</figcaption>
44
+
</figure>
51
45
</section>
52
46
53
47
<sectionclass="project-detail-section">
54
48
<h2>Problem & Context</h2>
55
49
<p>The goal was to build a robust model that accurately estimates overqualification probability from candidate attributes (education, experience, skills, demographics), work with the NGS dataset and its feature structure (survey codes, missing conventions), and train a CatBoost-based model with validation and leaderboard-oriented iteration. The solution achieved <strong>0.75174</strong> accuracy on the Public leaderboard and <strong>0.70511</strong> on the Private leaderboard, placing close to the top-performing teams.</p>
50
+
<figureclass="project-screenshot">
51
+
<imgsrc="../../assets/projects/undereployment-prediction/results.png" alt="Model results and evaluation metrics">
52
+
<figcaption>Model evaluation and interpretability — feature importance and validation metrics from the CatBoost classifier (0.75 public / 0.71 private leaderboard accuracy at the SFU ML Hackathon).</figcaption>
<imgsrc="../../assets/projects/house-price-v2/01_geographical_housing_prices.png" alt="Geographical distribution of California housing prices">
42
-
<figcaption>EDA: geographic distribution of median house values across California. Location (latitude/longitude) and ocean proximity drive much of the variation captured later by the model.</figcaption>
43
-
</figure>
44
-
<figureclass="project-screenshot">
45
-
<imgsrc="../../assets/projects/house-price-v2/01_feature_distributions.png" alt="Feature distributions for California housing dataset">
46
-
<figcaption>Feature distributions and relationships used to guide feature engineering in v2 — log transforms, derived ratios, and standardization for Ridge, Lasso, and custom Gradient Descent.</figcaption>
47
-
</figure>
48
-
</div>
38
+
<h2>Preview</h2>
39
+
<figureclass="project-screenshot">
40
+
<imgsrc="../../assets/projects/house-price-v2/01_feature_distributions.png" alt="Feature distributions for California housing dataset">
41
+
<figcaption>Feature distributions and relationships used to guide feature engineering in v2 — log transforms, derived ratios, and standardization for Ridge, Lasso, and custom Gradient Descent.</figcaption>
42
+
</figure>
49
43
</section>
50
44
51
45
<sectionclass="project-detail-section">
52
46
<h2>Problem & Context</h2>
53
47
<p>The goal of v2 is to build a fully modular, extensible ML pipeline for structured tabular data; introduce feature engineering and standardization to improve stability and performance; implement and compare multiple linear models (OLS, Ridge, Lasso, custom Gradient Descent); evaluate robustness through 5-fold cross-validation and hyperparameter tuning; and establish a reproducible training workflow that cleanly separates preprocessing, training, evaluation, and inference.</p>
48
+
<figureclass="project-screenshot">
49
+
<imgsrc="../../assets/projects/house-price-v2/01_geographical_housing_prices.png" alt="Geographical distribution of California housing prices">
50
+
<figcaption>EDA: geographic distribution of median house values across California. Location (latitude/longitude) and ocean proximity drive much of the variation captured later by the model.</figcaption>
0 commit comments