CALL FOR PAPERS

Workshop on Data Mining in Industrial Internet of Things (DMIIOT)

to be held in conjunction with the IEEE International Conference on Data Mining 2019 in Beijing

Data generated by industrial internet of things (IIOT) have been growing at an exponential rate. Data mining plays an essential role in deriving actionable information from these raw data. By applying a variety of data mining technologies to historical and real time IIOT data, building supervised or unsupervised models, deploying them into the production environment to help business make better decisions, significant value can be created resulting in reduced waste, improved efficiency and broaden opportunity.  The marriage between data mining and IIOT has found applications in industries such as manufacturing, energy, healthcare, retail, smart city and transportation.

The workshop will provide a venue for researchers and practitioners from both data mining and IIOT communities to exchange ideas, share best practices, discuss challenges and future directions. By fostering communication and collaboration, we drive innovative applications of data mining to IIOT. This workshop will be held along with 2019 IEEE International Conference on Data Mining, Beijing (http://icdm2019.bigke.org).

Schedule

The workshop is scheduled on the morning of Nov 8 2019. Due to the room limitation, DMIIOT'19 and OEDM'19 (Workshop on Optimization Based Techniques for Emerging Data Mining Problems) have merged under the name "OEDM & DMIIOT". The detailed information about OEDM can be found on the workshop website. The accepted papers of both workshops will be presented alternately and we believe this will bring new thoughts to attendees from both workshops.

Workshop time:
08:00-11:50, Nov 8, 2019

Workshop Room:
TBD

Presentation schedule:

There are 5 accepted papers from OEDM'19 and DMIIOT'19 together, and the detailed schedule is as follows.

08:00-08:40
Paper ID: S10201
Authors: Yuhan Lin, Minglong Lei, and Lingfeng Niu
Title: Optimization Strategies in Quantized Neural Networks: A Review

08:40-09:20
Paper ID: S15201
Authors: Tomonari Masada, Takumi Eguchi, and Daisuke Hamaguchi
Title: Difference between Similars: a Novel Method to Use Topic Models for Sensor Data Analysis

09:20-10:00
Paper ID: S10203
Authors: Kazuki Koyama, Keisuke Kiritoshi, and Tomonori Izumitani
Title: Discovering Sparse and Ununiform Lag Structure Using VAR Models with Latent Group LASSO

09:20-10:00: Coffee Break
10:30-11:10
Paper ID: S15202
Authors: Devon Peticolas, Russell Kirmayer, and Deepak S. Turaga
Title: M´ımir: Building and Deploying an ML Framework for Industrial IoT

11:10-11:50
Paper ID: S10205
Authors: Xing Nie, Yang Hu, Guoliang Ma, and Fanhua Shang
Title: RASVRG: Robust Accelerated Stochastic Variance Reduction Gradient for Sparse Subspace Clustering

Steering Committee

Program Committee

Workshop Chairs

E-mail: ping.chen@umb.edu; Website: http://www.cs.umb.edu/~pchen

 E-mail: jay.zhou@aistrike.us; Website: http://aistrike.us

Media Partners