Lab Alumni.
Parastoo Alinia is an Applied Scientist at Amazon, Atlanta, GA.
Latest
- Boosting Lying Posture Classification with Transfer Learning
- Personalized Activity Recognition using Partially Available Target Data
- TransNet: Minimally-Supervised Deep Transfer Learning for Dynamic Adaptation of Wearable Systems
- ActiLabel: A Combinatorial Transfer Learning Framework for Activity Recognition
- Proximity-Based Active Learning for Eating Moment Recognition in WearableSystems
- Synergistic Image and Feature Adaptation: Towards Cross-Modality Domain Adaptation for Medical Image Segmentation
- Transfer Learning via Learning to Transfer
- Master Defense Practice III
- How Accurate Your Activity Tracker Is? A Comparative Study of Step Counts in Low-Intensity Physical Activities
- Defense Practice II.
- Defense Practice I.
- Introduction to Long Short Term Memory Networks
- A Closed-loop Deep Learning Architecture for Robust Activity Recognition using Wearable Sensors
- Label Propagation: An Unsupervised Similarity Based Method for Integrating New Sensors in Activity Recognition Systems
- Collegial Activity Learning Between Heterogeneous Sensors
- Learning from less for better: semi-supervised activity recognition via shared structure discovery
- Reliable and reconfigurable framework for physical activity monitoring
- Assignment Problem (Part II)
- Assignment Problem (Part I)
- Hypothesis Testing
- Network-based relational knowledge transfer
- NetSimile: A Scalable Approach to Size-Independent Network Similarity
- Randomized 3-approximation MAX-CNF
- Learn-on-the-go: Autonomous cross-subject context learning for internet-of-things applications
- Multi-sensor fusion in body sensor networks: State-of-the-art and research challenges
- Sequential Behavior Prediction Based on Hybrid Similarity and Cross-User Activity Transfer
- Using Smart Homes to Detect and Analyze Health Events
- Introduction to Transfer Learning
- Estimating energy expenditure using body-worn accelerometers: a comparison of methods, sensors number and positioning.
- K-center Problem
- A Reliable and Reconfigurable Signal Processing Framework for Estimation of Metabolic Equivalent of Task in Wearable Sensors
- An Energy-Efficient Computational Model for Uncertainty Management in Dynamically Changing Networked Wearables
- Investigating the Accuracy of Fitbit Activity Trackers
- Hidden Markov Model Part II
- Predicting daily activities from egocentric images using deep learning.
- Stochastic methods (Simulated Annealing)
- Approximation Problems (Vertex cover and TSP)
- AdaBoost.R2 and Two-stage TrAdaBoost.R2 (Transfer Learning for regression models)
- Boosting for Regression Transfer
- Assessing Accuracy Performance of Fitbit Activity Trackers
- Maximum relevancy maximum complementary feature selection for multi-sensor activity recognition
- Network Flow Problem
- MET Calculation using Wearable Sensors.
- Impact of sensor misplacement on estimating metabolic equivalent of task with wearables
- Met calculations from on-body accelerometers for exergaming movements.
- Associations between Physiological Signals Captured using Wearable Sensors and Self-Reported Outcomes among Patients in AUD Recovery: Development and Usability Study