Pinned Repositories
Bayesian-Causal-Inference
The objective of this project is to quantify the impact of COVID-19 pandemic on non-motorized (pedestrians + bikes) activities in cities. For details, please see my personal profile in Google Scholar:
Bayesian-Multilevel-Regression
The study developed a Bayesian multilevel logistic regression (BMLR) model to capture heterogeneity in behavioral studies. The proposed method incorporates group-specific effects that vary randomly between group based on a weakly informative prior.
Bi-LSTM-Maximum-Entropy-Markov-Model
This project implement a Deep Maximum Entropy Markov Model (DMEMM) and Bi-LSTM Maximum Entropy Markov Model (Bi-LSTM MEMM) for the targeted sentiment task using the given dataset.
bplus
Strong Baseline for Argoverse II Motion Forecasting Competition. This repository implements a combined Boundary Aware Network (BANET) and Goal Area Network (GANET) for Argoverse II Motion Forecasting Competition. The backbone is based on the classic LaneGCN.
ClimbingMachine.github.io
deep-reinforcement-learning-pedestrian-signal-design
This study is to investigate the optimal control strategies at crosswalks using traffic signal controllers. A multi-agent reinforcement learning framework will be proposed as the “smart” control strategy, and several experiments will be conducted using microsimulation. The proposed multi-agent reinforcement learning framework is aimed to (1) find the optimal control policy that minimizes the number of conflicts (safety) while reducing traffic delay (efficiency), (2) account for different scheduling scenarios with various combinations of pedestrian flow rates and vehicle flow rates, and (3) make comparisons with baseline traditional traffic signal controllers and semi-controlled strategy.
LaneGCN
[ECCV2020 Oral] Learning Lane Graph Representations for Motion Forecasting
Multi-State-Models
We propose a novel approach using multi-state semi-Markov models to investigate road user interaction behaviors. Road user behavior can be divided into a series of gap acceptance decisions as part of a Markov Chain. Related papers can be found:
Social-LSTM
Unofficial implementation of Social-LSTM model. Code for dissertation: https://hammer.purdue.edu/articles/thesis/MAKING_CROSSWALKS_SMARTER_USING_SENSORS_AND_LEARNING_ALGORITHMS_TO_SAFEGUARD_HETEROGENEOUS_ROAD_USERS/19652892/1
ClimbingMachine's Repositories
ClimbingMachine/deep-reinforcement-learning-pedestrian-signal-design
This study is to investigate the optimal control strategies at crosswalks using traffic signal controllers. A multi-agent reinforcement learning framework will be proposed as the “smart” control strategy, and several experiments will be conducted using microsimulation. The proposed multi-agent reinforcement learning framework is aimed to (1) find the optimal control policy that minimizes the number of conflicts (safety) while reducing traffic delay (efficiency), (2) account for different scheduling scenarios with various combinations of pedestrian flow rates and vehicle flow rates, and (3) make comparisons with baseline traditional traffic signal controllers and semi-controlled strategy.
ClimbingMachine/Bayesian-Causal-Inference
The objective of this project is to quantify the impact of COVID-19 pandemic on non-motorized (pedestrians + bikes) activities in cities. For details, please see my personal profile in Google Scholar:
ClimbingMachine/Social-LSTM
Unofficial implementation of Social-LSTM model. Code for dissertation: https://hammer.purdue.edu/articles/thesis/MAKING_CROSSWALKS_SMARTER_USING_SENSORS_AND_LEARNING_ALGORITHMS_TO_SAFEGUARD_HETEROGENEOUS_ROAD_USERS/19652892/1
ClimbingMachine/Bayesian-Multilevel-Regression
The study developed a Bayesian multilevel logistic regression (BMLR) model to capture heterogeneity in behavioral studies. The proposed method incorporates group-specific effects that vary randomly between group based on a weakly informative prior.
ClimbingMachine/Bi-LSTM-Maximum-Entropy-Markov-Model
This project implement a Deep Maximum Entropy Markov Model (DMEMM) and Bi-LSTM Maximum Entropy Markov Model (Bi-LSTM MEMM) for the targeted sentiment task using the given dataset.
ClimbingMachine/bplus
Strong Baseline for Argoverse II Motion Forecasting Competition. This repository implements a combined Boundary Aware Network (BANET) and Goal Area Network (GANET) for Argoverse II Motion Forecasting Competition. The backbone is based on the classic LaneGCN.
ClimbingMachine/ClimbingMachine.github.io
ClimbingMachine/LaneGCN
[ECCV2020 Oral] Learning Lane Graph Representations for Motion Forecasting
ClimbingMachine/Multi-State-Models
We propose a novel approach using multi-state semi-Markov models to investigate road user interaction behaviors. Road user behavior can be divided into a series of gap acceptance decisions as part of a Markov Chain. Related papers can be found: