Summary of the Sussex-Huawei Locomotion-Transportation Recognition Challenge

In this paper we summarize the contributions of participants to the Sussex-Huawei Transportation-Locomotion (SHL) Recognition Challenge organized at the HASCA Workshop of UbiComp 2018. The SHL challenge is a machine learning and data science competition, which aims to recognize eight transportation activities (Still, Walk, Run, Bike, Bus, Car, Train, Subway) from the inertial and pressure sensor data of a smartphone. We introduce the dataset used in the challenge and the protocol for the competition. We present a meta-analysis of the contributions from 19 submissions, their approaches, the software tools used, computational cost and the achieved results. Overall, two entries achieved F1 scores above 90%, eight with F1 scores between 80% and 90%, and nine between 50% and 80%.

[1]  Aomar Osmani,et al.  Hybrid and Convolutional Neural Networks for Locomotion Recognition , 2018, UbiComp/ISWC Adjunct.

[2]  Stefan Valentin,et al.  High reliability Android application for multidevice multimodal mobile data acquisition and annotation , 2017, SenSys.

[3]  Yutaka Arakawa,et al.  Multi-Stage Activity Inference for Locomotion and Transportation Analytics of Mobile Users , 2018, UbiComp/ISWC Adjunct.

[4]  Mani B. Srivastava,et al.  Deep Convolutional Bidirectional LSTM Based Transportation Mode Recognition , 2018, UbiComp/ISWC Adjunct.

[5]  Masaki Shuzo,et al.  Application of CNN for Human Activity Recognition with FFT Spectrogram of Acceleration and Gyro Sensors , 2018, UbiComp/ISWC Adjunct.

[6]  Peter Widhalm,et al.  Top in the Lab, Flop in the Field?: Evaluation of a Sensor-based Travel Activity Classifier with the SHL Dataset , 2018, UbiComp/ISWC Adjunct.

[7]  Lin Wang,et al.  Benchmarking the SHL Recognition Challenge with Classical and Deep-Learning Pipelines , 2018, UbiComp/ISWC Adjunct.

[8]  Tarek Bin Zahid,et al.  A Fast Resource Efficient Method for Human Action Recognition , 2018, UbiComp/ISWC Adjunct.

[9]  Nobuo Kawaguchi,et al.  Activity Recognition Using Dual-ConvLSTM Extracting Local and Global Features for SHL Recognition Challenge , 2018, UbiComp/ISWC Adjunct.

[10]  Ren Ohmura,et al.  SHL Recognition Challenge: Team TK-2 - Combining Results of Multisize Instances- , 2018, UbiComp/ISWC Adjunct.

[11]  Shuai Li,et al.  Smartphone-sensors Based Activity Recognition Using IndRNN , 2018, UbiComp/ISWC Adjunct.

[12]  Jani Bizjak,et al.  Applying Multiple Knowledge to Sussex-Huawei Locomotion Challenge , 2018, UbiComp/ISWC Adjunct.

[13]  Kevin S. Xu,et al.  Activity Recognition by Classification with Time Stabilization for the SHL Recognition Challenge , 2018, UbiComp/ISWC Adjunct.

[14]  Hao Xia,et al.  Using Smart Phone Sensors to Detect Transportation Modes , 2014, Sensors.

[15]  Nobuo Kawaguchi,et al.  Short Segment Random Forest with Post Processing Using Label Constraint for SHL Recognition Challenge , 2018, UbiComp/ISWC Adjunct.

[16]  Roozbeh Jafari,et al.  Hierarchical Signal Segmentation and Classification for Accurate Activity Recognition , 2018, UbiComp/ISWC Adjunct.

[17]  Jani Bizjak,et al.  A New Frontier for Activity Recognition: The Sussex-Huawei Locomotion Challenge , 2018, UbiComp/ISWC Adjunct.

[18]  Md. Atiqur Rahman Ahad,et al.  A Comparative Approach to Classification of Locomotion and Transportation Modes Using Smartphone Sensor Data , 2018, UbiComp/ISWC Adjunct.

[19]  Lin Wang,et al.  The University of Sussex-Huawei Locomotion and Transportation Dataset for Multimodal Analytics With Mobile Devices , 2018, IEEE Access.

[20]  Jong-Seok Lee,et al.  Confidence-based Deep Multimodal Fusion for Activity Recognition , 2018, UbiComp/ISWC Adjunct.

[21]  Roozbeh Jafari,et al.  A Decision Level Fusion and Signal Analysis Technique for Activity Segmentation and Recognition on Smart Phones , 2018, UbiComp/ISWC Adjunct.

[22]  Stefan Valentin,et al.  Enabling Reproducible Research in Sensor-Based Transportation Mode Recognition With the Sussex-Huawei Dataset , 2019, IEEE Access.

[23]  Chih-Jen Lin,et al.  Big Data Small Footprint: The Design of A Low-Power Classifier for Detecting Transportation Modes , 2014, Proc. VLDB Endow..