Dezhi Hong

Dezhi Hong

Email: dehong AT ucsd DOT edu
For more information, here is my CV.


I am a postdoc with Professor Rajesh Gupta affiliated with CSE and HDSI at UCSD. I earned my Ph.D. in Computer Science at the University of Virginia in 2018. My PhD adviser was Professor Kamin Whitehouse.

My research lies at the intersection of Cyber-Physical Systems, Data Mining, and Machine Learning, with a particular interest in energy-efficient systems. My recent work is focused on interpreting, organizing, and navigating through sensor data with minimal human input.

I earned my B.S. from Beijing University of Posts and Telecommunications (aka BUPT, or in Chinese 北邮) in 2012, majoring in Electrical Engineering.

I am an avid photographer.

Some Papers (with reviews)

*Students I mentored

Jiaman Wu*, Dezhi Hong, Rajesh Gupta, Jingbo Shang.
Sensei: Self-Supervised Sensor Name Segmentation.
In ACL'21-Findings (reviews)

Fang He, Yang Deng, Yanhui Xu, Cheng Xu, Dezhi Hong, Dan Wang.
Energon: Facilitating Building Analytics via Abstraction.
In e-Energy'21 (reviews)

Yang Jiao*, Jiacheng Li*, Jiaman Wu*, Dezhi Hong, Rajesh Gupta, Jingbo Shang.
SeNsER: Learning Cross-Building Sensor Metadata Tagger.
In EMNLP'20-Findings (reviews)

Francesco Fraternali*, Bharathan Balji, Dhiman Sengupta, Dezhi Hong, Rajesh Gupta.
Ember: Energy Management of Batteryless Event Detection Sensors with Deep Reinforcement Learning.
In SenSys'20 (reviews)

Fang He, Cheng Xu, Yanhui Xu, Dezhi Hong, Dan Wang.
EnergonQL: A Building Independent Acquisitional Query Language for Portable Building Analytics.
In BuildSys'20 (reviews)

Dhiman Sengupta*, Tamara Zubatiy, Sean K. Hamilton*, Arthur Boothroyd, Cagri Yalcin, Dezhi Hong, Rajesh K. Gupta, Harinath Garudadri.
Open Speech Platform: Democratizing Hearing Aid Research.
In PervasiveHealth'20 (reviews)
Best Paper Award

Jing Ma*, Dezhi Hong, Hongning Wang.
Selective Sampling for Sensor Type Classification in Buildings.
In IPSN'20 (reviews, code)

Shuheng Li*, Dezhi Hong, Hongning Wang.
Relation Inference among Sensor Time Series in Smart Buildings with Metric Learning.
In AAAI'20 (reviews, code)

Jeng-Hau Lin*, Justin Lazarow, Yunfan Yang, Dezhi Hong, Rajesh Gupta, Zhuowen Tu.
Local Binary Pattern Networks.
In WACV'20 (reviews)

Jason Koh*, Dezhi Hong, Shreyas Nagare, Sudershan Boovaraghavan, Yuvraj Agarwal, Rajesh Gupta.
Who can Access What, and When? Understanding Minimal Access Requirements of Building Applications.
In BuildSys’19 (reviews)

Lu Lin*, Zheng Luo*, Dezhi Hong, Hongning Wang.
Sequential Learning with Active Partial Labeling for Metadata in Buildings.
In BuildSys’19 (reviews, code)

Dezhi Hong, Renqin Cai, Hongning Wang, Kamin Whitehouse.
Learning from Correlated Events for Equipment Relation Inference in Buildings.
In BuildSys’19 (reviews; grab a coffee, here are some rejections ;) kdd19, www19, aaai19, cikm18, kdd18, aaai18)

*Jason Koh, *Dezhi Hong, Rajesh Gupta, Kamin Whitehouse, Hongning Wang, Yuvraj Agarwal.
Plaster: An Integration, Benchmark, and Development Framework for Metadata Normalization Methods.
*Equal Contribution
In BuildSys’18 (reviews, code)

Avinash Kalyanaraman, Dezhi Hong, Elahe Soltanaghaei, Kamin Whitehouse.
FormaTrack: Tracking People based on Body Shape.
In Ubicomp'17 (reviews)

Dezhi Hong, Quanquan Gu, Kamin Whitehouse.
High-dimensional Time Series Clustering via Cross-Predictability.
In AISTATS'17 (reviews, poster, data, errata, code)

*Bharathan Balaji, Arka Bhattacharya, Gabe Fierro, Jingkun Gao, Joshua Gluck, Dezhi Hong, Aslak Johansen, Jason Koh, Yuvraj Agarwal, Mario Bergés, David Culler, Rajesh Gupta, Mikkel Baun Kjærgaard, Joern Ploennigs, Mani Srivastava, Kamin Whitehouse.
Brick v1.0 - Towards a Unified Metadata Schema For Buildings.
In BuildSys’16 (reviews, ppt, extended journal version, website)
*Alphabetical Order
Best Paper Nominee, Audience Choice Award, Best Demo Award

Dezhi Hong, Hongning Wang, Jorge Ortiz, Kamin Whitehouse.
The Building Adaptor: Towards Quickly Applying Building Analytics at Scale.
In BuildSys'15 (reviews, ppt, data, code)
Best Paper Nominee

Arka Bhattacharya, Dezhi Hong, David Culler, Jorge Ortiz, Kamin Whitehouse, Eugene Wu.
Automated Metadata Construction to Support Portable Building Applications.
In BuildSys'15 (reviews, sensys14, ipsn15)
Best Paper Nominee

Dezhi Hong, Hongning Wang, Kamin Whitehouse.
Clustering-based Active Learning on Sensor Type Classification in Buildings.
In CIKM'15 (reviews, ppt, code)

Dezhi Hong, Jorge Ortiz, Arka Bhattacharya, Kamin Whitehouse.
Sensor-Type Classifications in Buildings.
arXiv preprint, arXiv:1509.00498, (rejected with postitive reviews)

Dezhi Hong, Jorge Ortiz, Kamin Whitehouse, David E. Culler.
Towards Automatic Spatial Verification of Sensor Placement in Buildings.
In BuildSys'13 (reviews, ppt)

Shahriar Nirjon, Robert Dickerson, Philip Asare, Qiang Li, Dezhi Hong, John A. Stankovic, Pan Hu, Guobin Shen, Xiaofan Jiang.
Auditeur: A Mobile-Cloud Service Platform for Acoustic Event Detection on Smartphones.
In MobiSys'13 (reviews)

Shahriar Nirjon, Robert Dickerson, Qiang Li, Philip Asare, John A. Stankovic, Dezhi Hong, Ben Zhang, Guobin Shen, Xiaofan Jiang, Feng Zhao.
MusicalHeart: A Hearty Way of Listening to Music.
In SenSys'12 (reviews)


View Dezhi Hong on Facebook View Dezhi Hong's profile on LinkedIn
2132, EBU3b
Computer Science & Engineering
University of California, San Diego
9500 Gilman Dr, La Jolla, CA 92093 (map)