Ali Rokni

Graduate Alumni

Washington State University

Ali Rokni, PhD, Computer Science, Washington State University (2014-2018)

Ali joined joined Yelp Inc., San Francisco, CA, as Machine Learning Engineer in 2018

PhD Dissertation: Dynamic Adaptation of Recognition Algorithms on Wearables with Minimal Human Supervision

Awards:

WSU Russ and Anne Fuller Fellowship for Interdisciplinary Research/Scholarship 2018 (awarded to 3-5 students university-wide each year)
WSU Russ and Anne Fuller Fellowship for Interdisciplinary Research/Scholarship, 2017 (awarded to 3-5 students university-wide each year)
WSU Graduate & Professional Students Association (GPSA) Research Assistant Excellence Award, 2017
NSF-Supported ACM Wireless Health conference travel award, 2014

Latest

Probabilistic Cascading Classifier for Energy-Efficient Activity Monitoring in Wearables
LIDS: Mobile System to Monitor Type and Volume of Liquid Intake
TransNet: Minimally-Supervised Deep Transfer Learning for Dynamic Adaptation of Wearable Systems
Gait Speed and Survival of Older Surgical Patient with Cancer: Prediction after Machine Learning
Resource-Efficient Wearable Computing for Real-Time Reconfigurable Machine Learning: A Cascading Binary Classification
Share-n-Learn: A Framework for Sharing Activity Recognition Models in Wearable Systems with Context-Varying Sensors
Defense Practice
Deep Convolutional Feature Transfer Across Mobile Activity Recognition Domains, Sensor Modalities and Locations
TransNet: An Adaptable Deep Learner for Human Activity Recognition
Autonomous Training of Activity Recognition Algorithms in Mobile Sensors: A Transfer Learning Approach in Context-Invariant Views
Digital Health for Geriatric Oncology
Personalized Human Activity Recognition Using Convolutional Neural Networks
Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks
Hierarchical Span-Based Conditional Random Fields for Labeling and Segmenting Events in Wearable Sensor Data Streams
Structured Perceptron (Part II)
Structured Perceptron (Part I)
Synchronous Dynamic View Learning: A Framework for Autonomous Training of Activity Recognition Models using Wearable Sensors
Convex Optimization II: Gradient descent (Part 2)
Convex Optimization II: Gradient descent (Part 1)
Power and Memory Efficient Cascading Binary Classifier for Activity Recognition
A beverage intake tracking system based on machine learning algorithms, and ultrasonic and color sensors: poster abstract
Synchronous dynamic view learning: a framework for autonomous training of activity recognition models using wearable sensors
Mixture of Experts
Autonomous Sensor-Context Learning in Dynamic Human-Centered Internet-of-Things Environments
Convex Sets
Adaptive Model Fusion for Wearable Sensors Based Human Activity Recognition
Using Weka Java API
Efficient graph-based semi-supervised learning of structured tagging models.
A Reliable and Reconfigurable Signal Processing Framework for Estimation of Metabolic Equivalent of Task in Wearable Sensors
Autonomous sensor-context learning in dynamic human-centered internet-of-things environments
Plug-n-learn: automatic learning of computational algorithms in human-centered internet-of-things applications
Shortest Superstring(Approximation Algorithm)
Identifying Physical Activity Profiles in COPD Patients Using Topic Models.
Ordering points to identify the clustering structure (OPTICS)
DBSCAN
Linear Programming: Introduction, Formulation and Solving
Transfer Learning Algorithms in Wearable Monitoring Platforms
Confidence-based Multiclass AdaBoost for Physical Activity Monitoring
Introduction to Algorithm Complexity
Hungarian Algorithms
Semi-Learning of Activity Labels in Real-Time using Wearable Motion Sensors.
Impact of sensor misplacement on estimating metabolic equivalent of task with wearables
Electronic Tools to Measure and Enhance Medication Adherence