Before this, I obtained Bachelors's Degree and Master's Degree in Electrical Engineering at National Chung Cheng University (CCU).
I’m broadly interested in diverse machine learning topics, including learning from imperfect data, decisionmaking, multi-media applications, and multi-modal matching problems. My longterm goal is to develop machine learning
systems that can (1) understand the environment and reasoning from muti-source data, (2) comunicate with human, and (3) operate reliably and unbiasedly even under challenging conditions. Along with the research
directions, I am interested in and have conducted researches on zero-shot learning, meta-learning, and reinforcement learning applications for smart buildings.
NYCU Research Assistant Mar. 20 - Now
CCU M.S. in EE Feb. 18 - Jan. 20
Awoo Inc. Student Intern Apr. 17 - Jul. 17
CCU B.S. in EE Sep. 13 - Jun. 17
Publications
Make an Omelette with Breaking Eggs: Zero-Shot Learning for Novel Attribute Synthesis
Yu Hsuan Li*, Tzu-Yin Chao*, Ching-Chun Huang, Pin-Yu Chen, Wei-Chen Chiu
In submission ICML'22 (Phase 1 Accept)
Most of the existing algorithms for zero-shot classification problems typically rely on the attribute-based semantic relations among categories to realize the classification of novel categories without observing any of their instances. However, training the zero-shot classification models still requires attribute labeling for each class (or even instance) in the training dataset, which is also expensive. To this end, in this paper, we bring up a new problem scenario: “Are we able to derive zero-shot learning for novel attribute detectors/classifiers and use them to automatically annotate the dataset for labeling efficiency?”. Basically, given only a small set of detectors that are learned to recognize some manually annotated attributes (i.e., the seen attributes), we aim to synthesize the detectors of novel attributes in a zero-shot learning manner. Our proposed method, Zero-Shot Learning forAttributes (ZSLA), which is the first of its kind to the best of our knowledge, tackles this new research problem by applying the set operations to first decompose the seen attributes into their basic attributes and then recombine these basic attributes into the novel ones. Extensive experiments are conducted to verify the capacity of our synthesized detectors for accurately capturing the semantics of the novel attributes and show their superior performance in terms of detection and localization compared to other
baseline approaches. Moreover, with using only 32 seen attributes on the Caltech-UCSD Birds-200-2011 dataset, our proposed method is able to synthesize other 207 novel attributes, while various generalized zero-shot classification algorithms trained upon the dataset re-annotated by our synthesized attribute detectors are able to provide comparable performance with those trained with the manual ground-truth annotations.
Vacant Parking Space Detection based on Task Consistency and Reinforcement Learning
Manh-Hung Nguyen, Tzu-Yin Chao, Ching-Chun Huang
ICPR 2020
In this paper, we proposed a novel task-consistency learning method that allows training a vacant space detection network (target task) based on the logic consistency with the semantic outcomes from a flow-based motion behavior classifier (source task) in a parking lot. By well designing the reward mechanism upon semantic consistency, we show the possibility to train the target network in a reinforcement learning setting. Compared with conventional supervised detection methods, this work's main contribution is to learn a vacant space detector via semantic consistency rather than supervised labels. The dynamic learning property may make the proposed detector been deployed and updated in different lots easily without heavy human loads. The experiments show that based on the task consistency rewards from the motion behavior classifier, the vacant space detector can be trained successfully.
Online Self-Learning for Smart HVAC Control Tzu-Yin Chao, Manh-Hung Nguyen, Ching-Chun Huang, Chien-Cheng Liang, Chen-Wu Chung
IEEE International Conference on Systems, Man and Cybernetics (SMC) 2019, oral representation
In this paper, we introduce an online-learning method to model the property of an office building. Unlike conventional control methods where the building property is modeled via a simulator or through offline learning, our building model is adaptively updated according to the dynamic response of a real environment. Upon the building model for environment prediction, the proposed action agent can control the heating, ventilation, and air conditioning (HVAC) system in a smarter way by scheduling the temperature reference point. To online learn the model and improve the agent, two practical and seldom discussed issues are addressed. The first challenge is data bias where the collected initial training dataset can only partially reveal the statistical mapping between the control input and the environment response. Hence, the trained model may lack generalization. To overcome the data bias issue, a data augmentation method is proposed to embed physical logic in order to train a proper initial model. Next, an online learning process is introduced to update the model generality during the system operation phase. The second practical issue is the constraints on agent exploration for discovering unknown data samples. During the business hours, to comfort employees, a control agent is not allowed to explore the possible controlling space randomly. To balance data collection and control stability, we introduce a hybrid control strategy that considers both the human control rule and the agent action. A confidence score of the agent model is also automatically estimated to determine a suitable control strategy finally. Our experiments have realized in an office building. The results outperform conventional methods and show its superior in terms of control stability.
Projects
Transferable and Fast Adaptive Agent for HVAC Control
(Mar. 2021 – )
[Partnership]Taiwan Semiconductor Manufacturing Company, Ltd. (TSMC) [Status]In progress
[Goal]
Transfer an existing well-performing HVAC (large air conditioning) control agent to another building with a different sensor deployment (i.e., different types and numbers of sensors) and lack of data.
Low-cost Setup for Learning-based Vacant Parking Space Detection Model
(Nov. 2019 – Sep. 2020)
[Status]Applied in NYCU [Publication]The paper has published in ICPR’20 [Patent]TW Patent Pending 110129963
[Goal]
To develop a mechanism for training a vacant parking space detection model in a new parking lot without manually annotating or storing data from another parking lot for transfer learning.
[Challenges]
1. The system should be source domain data-free.
2. The system should be target domain label-free.
[Designs]
In order to meet the requirement, instead of transfer learning, we trained a vacant space detection network (target task) based on the logic consistency with the semantic outcomes from an optical-flow-based car motion detector (source task) in a parking lot via reinforcement learning. The key points are summarized as followed:
1. Source domain data-free: At a start, a car motion detection model is trained by the source data, to predict a slot is either in "car in" state, "car out" state, or "no motion" state, given optical flow as the input. Under this setting, the motion detection model is stored for guiding the target task, but not the source dataset with its labels.
2. Target domain label-free: During training the target task (i.e., vacant space detection model for the target parking lot), we defined the reward function based on the logical relation between car motion and parking slot occupancy. In this way, instead of labeling, the car motion detector can assign the reward for the target task to learn.
3. Since the car motion detection model from the source parking lot might be undesirable for samples from the target parking lot, we design a special warm-up trick to adjust the reward function to deal with the noisy rewards.
Human Occupancy Estimation for Smart Building Management
(Mar. 2019 – Jul. 2020)
[Partnership]Taiwan Semiconductor Manufacturing Company, Ltd. (TSMC) [Status]Applied in TSMC [Award]Golden Award (among competitors from industry, including ASUS Inc.), 13th Intelligent Living Space Design Competition, Taiwan
Goal:
To infer the occupancy based on multiple non-image-based sensor values as the indicator for decision-making in building equipment control.
Challenges:
1. To protect the privacy, only non-image-based sensors are available.
2. To provide continuous indicator, given real time sensor status, for multiple mode control, with extremely rough and sparse label. (i.e., only samples that are considered to be either "full occupancy" or "no people" are annotated.)
Designs:
1.Inspired by the design of the discriminator in WGAN, a neural network is trained, with the gradient penalty for Lipschitz continuity, to project the sensor states into [0,1] space. We force the "full occupancy" samples to be projected as far away as possible from those samples labeled as "no people", while the unlabeled samples should be smoothly distributed between these two labeled groups.
2.Since the labeled samples are rare, we additionally add a first-order gradient constraint loss to guide the prior knowledge about the relationship between environmental factors and occupancy. (For example, The amount of change in the power supply may be positively correlated with the occupancy changes.)
Intelligent Control for HVAC
(Mar. 2018 – Jul. 2018)
[Partnership]Taiwan Semiconductor Manufacturing Company, Ltd. (TSMC) [Status]Applied in TSMC [Publication]The paper (naive version system) has published in SMC’19 [Patent]TW Patent I746087 [Award]Silver Award (among competitors from industry, including ASUS Inc.), 11th Intelligent Living Space Design Competition, Taiwan
Goal:
To accurately stabilize the temperature in a large-scale office at the user’s expected by automatically adjusting the control parameter of HVAC in a building with rare and biased data.
Challenges:
1. Collecting data for smart building is extremely time consuming. To work in the real world, the system is required starting with limited.
2. In many cases, some of the control parameters for equpments in the smart building are never changed. These biased data can not well represent the how actually the control parameters interact with the world.
3. In the real-world scenario, the agent should provide acceptable confort quality while exploring in the early stage.
Designs:
To solve this issue, the algorithm is designed to be a dynamic-learning-based model predictive control system. The key designs are summarized as followed:
1. To solve the problem of rare and biased data, a first-order gradient constraint loss is introduced for guiding the model to learn the correct relationship among environment factors. (For example, the change of AC's temperature setpoint should be positively related to the future temperature changes.)
2. To avoid our agent to perform some extreme setpoints in the early stage, we apply a weighted mixup control strategy with a "safe" constant setpoint defined by user. The mix-up weight is dynamically adjusted depend on the model's qulity (i.e., related to predition error of the latest data sample).
Side project
AutoPPT
AutoPPT is a simple module that helps display the data in some repeated and unified format. Users are only required to provide the design template, and then the repeated routine can be simply handled by python codes.