Smart Compost Bin
Developing a low-cost, 3D printed device for automatically measuring food waste using state-of-the-art CV models
Posts by Collection
portfolio
Music Sentiment Analysis
Predicting Music Emotion from Social Media Commentary
Decision Transformer for Robotic Arm Manipulation
Transformers for offline reinforcement learning from synthetic data for robotics
Attack Transferability Assessment of BERT-ATTACK
Exploiting encoder-based LLMs with black-box BERT attacks
Neutron Density Visualization
Visualizing neutron flux in nuclear reactors for optimizing fuel rod geometry
Malicious Software Prediction
Predicting malicious behavior in Windows binaries
Robot Grasp Validation Classifier
Ensuring stable and safe robot manipulator operation using Gazebo simulation data
publications
Evaluating large-language models for dimensional music emotion prediction from social media discourse
Published in ICNLSP, 2022
We present a preliminary approach for estimating the valence and arousal of a given sample of music by learning listener sentiment from social media conversations.
Download here
Learning Affective Responses to Music from Social Media Discourse
Published in Signals and Communications Technology, 2023
Continuing our prior work on music emotion estimation, we develop a large dataset of musically relevant social media discourse and train a BERT-based lanugage model to predict musical valence and arousal, achieving state-of-the-art performance on the task of estimating music emotion.
Download here
Smart Compost Bin for Measurement of Consumer Food Waste
Published in CoFI, 2024
We present the Smart Compost Bin, a novel food waste measurement device. Our low-cost 3D printed compost bin allows household users to gain insights on their food waste and compost habits, using a camera and environmental sensors to automatically classify and quantify food disposals. Using this device, we propose a pilot study to leverage volunteer households to annotate food waste images taken from our device, enabling the development of a robust food waste image segmentation model.
Download here
talks
Talk 1 on Relevant Topic in Your Field
Published:
This is a description of your talk, which is a markdown files that can be all markdown-ified like any other post. Yay markdown!
Conference Proceeding talk 3 on Relevant Topic in Your Field
Published:
This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.