Deep Convolutional Bidirectional LSTM Based Transportation Mode Recognition

Jeyakumar, Jeya Vikranth; Lee, Eun Sun; Xia, Zhengxu; Sandha, Sandeep Singh; Tausik, Nathan; Srivastava, Mani

doi:10.1145/3267305.3267529

Cited by 28 publications

(11 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, compared with relying solely on GPS sensor data, this type of approach can often obtain higher inference accuracy. Other studies [24][25][26][27][28] do not use GPS sensors, but rather use combinations of other sensor data from smartphones to infer transportation modes. For instance, Su et al [24] and Su [25] used data from accelerometers, gravity sensors, gyroscopes, magnetometers, and barometers to infer transportation modes.…”

Section: Literature Reviewmentioning

confidence: 99%

“…These methods can obtain highly accurate inference results, but they usually lead to reliance on large amounts of GIS data and complex calculations, which make them difficult to use in fully automatic processing mode. (4) The fourth category [20][21][22][23][24][25][26][27][28] uses a combination of time-series data produced by sensors of different types, such as GPS sensors, acceleration sensors, gyroscopes, and altitude sensors. These methods usually grant high inference accuracy while introducing reliance on multiple amounts of sensors, and difficulty in matching transportation mode data to geographic locations occurs when GPS sensors are not used.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Transportation mode identification with GPS trajectory data and GIS information

Pei

Wang

et al. 2021

Tinshhua Sci. Technol.

View full text Add to dashboard Cite

Section: Literature Reviewmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Transportation mode identification with GPS trajectory data and GIS information

Pei

Wang

et al. 2021

Tinshhua Sci. Technol.

View full text Add to dashboard Cite

“…Ensemble learning model includes stacking, bagging and boosting. There are also many researches about deep learning method [2,7,16]. Typically, deep neural networks perform better than traditional models in accuracy after careful tuning.…”

Section: Pipelinementioning

confidence: 99%

Multiple Tree Model Integration for Transportation Mode Recognition

Ren

2021

Adjunct Proceedings of the 2021 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of The

View full text Add to dashboard Cite

The team RY presents a solution for Sussex-Huawei Locomotion-Transportation (SHL) recognition challenge, which aims at differentiating eight transportation modes with mobile phone signal sensor data in this paper. This study first extracted a set of reasonable and discriminative features after data-preprocessing. Then, decision tree bagging, random forest, lightGBM are trained separately as basic models, whose predictions are integrated and afterward smoothed. The method gets 0.65 accuracy score on validation dataset. CCS CONCEPTS• Computing methodologies → Artificial intelligence; Simulation environments; • General and reference → Cross-computing tools and techniques.

show abstract

“…The deep-learning algorithms are outperforming the traditional approaches which are using handcrafted features. Jeyakumar et al [ 9 ] proposed a deep convolutional bidirectional-LSTM ensemble trained directly on raw sensor data on the SHL dataset. Using this approach, an F

-score on 96% was achieved for transportation mode classification.…”

Section: State Of the Artmentioning

confidence: 99%

Analyzing the Importance of Sensors for Mode of Transportation Classification

Friedrich

Lübbe

Hein

2020

Sensors

View full text Add to dashboard Cite

The broad availability of smartphones and Inertial Measurement Units in particular brings them into the focus of recent research. Inertial Measurement Unit data is used for a variety of tasks. One important task is the classification of the mode of transportation. In the first step, we present a deep-learning-based algorithm that combines long-short-term-memory (LSTM) layer and convolutional layer to classify eight different modes of transportation on the Sussex–Huawei Locomotion-Transportation (SHL) dataset. The inputs of our model are the accelerometer, gyroscope, linear acceleration, magnetometer, gravity and pressure values as well as the orientation information. In the second step, we analyze the contribution of each sensor modality to the classification score and to the different modes of transportation. For this analysis, we subtract the baseline confusion matrix from a confusion matrix of a network trained with a left-out sensor modality (difference confusion matrix) and we visualize the low-level features from the LSTM layers. This approach provides useful insights into the properties of the deep-learning algorithm and indicates the presence of redundant sensor modalities.

show abstract

Deep Convolutional Bidirectional LSTM Based Transportation Mode Recognition

Cited by 28 publications

References 23 publications

Transportation mode identification with GPS trajectory data and GIS information

Transportation mode identification with GPS trajectory data and GIS information

Multiple Tree Model Integration for Transportation Mode Recognition

Analyzing the Importance of Sensors for Mode of Transportation Classification

Contact Info

Product

Resources

About