Transportation Mode Detection Research Articles

A framework of transportation mode detection for people with mobility disability

Transportation mode detection (TMD) is an important computational technique that aids human life at the social and individual levels. However, previous studies on TMD were focused on people without mobility disabilities, and research involving people with mobility disability is limited. Therefore, this study aimed to provide a TMD framework for people with mobility disability. We propose a method for data acquisition, and acquired data pertaining to 120 participants including manual and electric wheelchairs for 15,350 min. We analyzed the acquired data to determine the characteristics of each transportation mode, and applied machine learning and deep learning models to TMD. Our results showed that a recurrent neural network, known as long short-term memory, could classify five transportation modes (still, manual wheelchair, electric wheelchair, subway, and car) for people with and without disabilities, with an accuracy of 96.17%. Our results will be beneficial for enhancing the quality of life and enabling the social inclusion of people with mobility disabilities.

Transportation Mode Detection Technology to Predict Wheelchair Users' Life Satisfaction in Seoul, South Korea

Transportation mode detection (TMD) has been proposed as a computational technology to obtain mobility information. However, previous TMD studies mainly focused on improving detection performance and have not investigated the social implications of mobility information. This is the first study to use TMD to predict the life satisfaction of wheelchair users. Our goal is to develop TMD for wheelchair users (wTMD) utilizing smartphone location data and apply it to determine how transportation behaviors affect the life satisfaction of wheelchair users. First, we propose a wTMD technology by collecting a new dataset from wheelchair and non-wheelchair users. Second, we conduct regression analyses on existing in-the-wild dataset of wheelchair users. The result shows that the portion of subways in an individual's travel time is directly connected to wheelchair users' life satisfaction in Seoul, South Korea. We hope our findings are a good example for future social science studies and ultimately help to design wheelchair-friendly urban planning and accessibility.

POPAyI: Muscling Ordinal Patterns for Low-Complex and Usability-Aware Transportation Mode Detection

POPAyI: Muscling Ordinal Patterns for Low-Complex and Usability-Aware Transportation Mode Detection

Feature Cloning and Feature Fusion Based Transportation Mode Detection Using Convolutional Neural Network

The smartphone-based sensors (including accelero-meter, proximity, and gyroscope sensors) are ubiquitous and emerging mobility data sources that could be used for transportation modes (i.e. bus, train, car, walking, and stationary) detection. One of the important challenges in transportation modes detection is to build an appropriate model that can extract useful data from the sensor outputs and that can reduce misclassifications. Several factors make the feature modeling difficult including inappropriate sampling frequency of input signals, wavering behavior of devices (e.g. the changing orientation of a device relative to the human body), and continuous base vibration causing similar sensor outputs for both stationary and non-stationary states and related threshold values of velocity. This paper proposes novel approaches to address these challenges by developing a robust transportation mode detector based on a convolution neural network (CNN). The proposed robust detector develops a feature modeling technique by novel feature fusion and cloning techniques. Pre-trained features are constructed using a separate vanilla neural network (VNN) framework to extract the distinguishing components from the original features that are combined with the original and cloned features. The proposed feature fusion technique is successfully able to overcome the noise from the base vibration and the minimal informative outputs from the lower sampling frequency. This enables the CNN to be trained with more efficient and discriminative features that result in a better classification model. The proposed approaches have been validated using a large volume of mobile sensor data based on the movements of travelers. Different types of mobile sensors have been used to collect data including accelerometer, proximity, and gyroscope. Experimental results demonstrate that the proposed approaches can improve the performance of the detection engine significantly over conventional techniques and reduces the misclassification rate.

TMD-BERT: A Transformer-Based Model for Transportation Mode Detection

Aiming to differentiate various transportation modes and detect the means of transport an individual uses, is the focal point of transportation mode detection, one of the problems in the field of intelligent transport which receives the attention of researchers because of its interesting and useful applications. In this paper, we present TMD-BERT, a transformer-based model for transportation mode detection based on sensor data. The proposed transformer-based approach processes the entire sequence of data, understand the importance of each part of the input sequence and assigns weights accordingly, using attention mechanisms, to learn global dependencies in the sequence. The experimental evaluation shows the high performance of the model compared to the state of the art, demonstrating a prediction accuracy of 98.8%.

User and Period Independent Transportation Mode Detection for Wheelchair Users

Transportation mode detection (TMD) is an important research area in human activity recognition. It can improve the mobility and accessibility of people by providing a better understanding of their mobility patterns, thereby enhancing their quality of life and social inclusion. Although previous studies of TMD for people without mobility disabilities exhibited, the performance of TMD models on new users and periods was limited. This issue would be more important for people with mobility disabilities. This study investigated the negative impact of user and period differences on the performance of TMD for wheelchair users (wTMD) and suggested a method to address these challenges. Our main findings are (1) user and period differences degraded the wTMD performance from 94.28% to 59.32%; (2) the multi-DenseNet with a soft voting ensemble provided a 76.49% accuracy to data from different users and periods. We expect that our understanding of wTMD will aid in the design of more generalized wTMD models.

DFTrans: Dual Frequency Temporal Attention Mechanism-Based Transportation Mode Detection.

In recent years, with the diversification of people's modes of transportation, a large amount of traffic data is generated when people travel every day, and this data can help transportation mode detection to be of great use in a variety of applications. Although transportation mode detection has been investigated, there are still challenges in terms of accuracy and robustness. This paper presents a novel transportation mode detection algorithm, DFTrans, which is based on Temporal Block and Attention Block. Low- and high-frequency components of traffic sequences are obtained using discrete wavelet transforms. A two-channel encoder is carefully designed to accurately capture the temporal and spatial correlation between low- and high-frequency components in both long- and short-term patterns. With the Temporal Block, the inductive bias of the CNN is introduced at high frequencies to improve generalization performance. At the same time, the network is generated with the same length as the input, ensuring a long effective history. Low frequencies are passed through Attention Block, which has fewer parameters to capture the global focus and solves the problem that RNNs cannot be computed in parallel. After fusing the output of the feature by Temporal Block and Attention Block, the classification results are output by MLP. Extensive experimental results show that the DFTrans algorithm achieves macro F1 scores of 86.34% on the real-world SHL dataset and 87.64% on the HTC dataset. Our model can better identify eight modes of transportation, including stationary, walking, running, cycling, bus, car, underground, and train, and has better performance in transportation mode detection than other baseline algorithms.

Kick-scooters identification in the context of transportation mode detection using inertial sensors: Methods and accuracy

This work presents a novel transportation mode detection algorithm that handles the recognition of kick-scooters. In 2015, 10 minutes of data from a kick-scooter were considered in a transportation mode detection study, yielding a 56% F1-score. Since then, kick-scooters were not given much attention. Yet, kick-scooters are now very present in the urban transportation ecosystem, and their consideration in transportation studies has become a must. To fill this gap, 4 hours of kick-scooter signals were collected by 18 participants, with a set of 6 different kick-scooters, using 3 body-worn inertial measurement units. Obviously, kick-scooter patterns are classified in contrast with other modes of transportation. Two classification scenarios are considered in order to gradually increase the classification model complexity. The first scenario includes walking, biking, and kick-scooter, while the second considers public transport (tramway and bus) in addition to the former transportation modes. Results show that kick-scooters can be detected with an F1-score of 80% in the first scenario. Walking and public transport samples were still accurately classified in the second scenario, with an F1-score above 80% for both classes. However, bike and kick-scooter samples were both classified with lower F1-scores, equal to 59% and 64% respectively. Therefore, the main focus of future works should be directed toward the separability of kick-scooters and bikes when public transport is considered. The findings also suggest to place preferably the sensors in the trouser’s pocket, allowing for leg motion to be finely captured.

Two-stage procedure for transportation mode detection based on sighting data

The data required for transportation applications can be retrieved from mobile phones without the necessity of additional infrastructure. Thus, we propose a procedure that involves two stages – data preprocessing and transportation mode detection – for detecting the transportation mode (i.e., car and bus) on the basis of sighting data. In the data preprocessing stage, two detection rules are used for eliminating oscillations that occur when a mobile phone intermittently switches between cell towers instead of connecting to the nearest cell tower. In the transportation mode detection stage, two supervised machine learning methods, namely support vector machine (SVM) and a deep neural network (DNN), are used to detect transportation modes. Experimental results indicated SVM achieved a higher accuracy (96.49%) in transport mode detection than did the DNN (69.65%) during peak hours. Moreover, travel time and starting time of a trip were identified as critical features affecting the accuracy of transportation mode detection.

Transportation Mode Detection Using Temporal Convolutional Networks Based on Sensors Integrated into Smartphones.

In recent years, with the development of science and technology, people have more and more choices for daily travel. However, assisting with various mobile intelligent services by transportation mode detection has become more urgent for the refinement of human activity identification. Although much work has been done on transportation mode detection, accurate and reliable transportation mode detection remains challenging. In this paper, we propose a novel transportation mode detection algorithm, namely T2Trans, based on a temporal convolutional network (i.e., TCN), which employs multiple lightweight sensors integrated into a phone. The feature representation learning of multiple preprocessed sensor data using temporal convolutional networks can improve transportation mode detection accuracy and enhance learning efficiency. Extensive experimental results demonstrated that our algorithm attains a macro F1-score of 86.42% on the real-world SHL dataset and 88.37% on the HTC dataset, with an average accuracy of 86.37% on the SHL dataset and 89.13% on the HTC dataset. Our model can better identify eight transportation modes, including stationary, walking, running, cycling, car, bus, subway, and train, with better transportation mode detection accuracy, and outperform other benchmark algorithms.

Transportation Mode Detection Combining CNN and Vision Transformer with Sensors Recalibration Using Smartphone Built-In Sensors.

Transportation Mode Detection (TMD) is an important task for the Intelligent Transportation System (ITS) and Lifelog. TMD, using smartphone built-in sensors, can be a low-cost and effective solution. In recent years, many studies have focused on TMD, yet they support a limited number of modes and do not consider similar transportation modes and holding places, limiting further applications. In this paper, we propose a new network framework to realize TMD, which combines structural and spatial interaction features, and considers the weights of multiple sensors’ contributions, enabling the recognition of eight transportation modes with four similar transportation modes and four holding places. First, raw data is segmented and transformed into a spectrum image and then ResNet and Vision Transformers (Vit) are used to extract structural and spatial interaction features, respectively. To consider the contribution of different sensors, the weights of each sensor are recalibrated using an ECA module. Finally, Multi-Layer Perceptron (MLP) is introduced to fuse these two different kinds of features. The performance of the proposed method is evaluated on the public Sussex-Huawei Locomotion-Transportation (SHL) dataset, and is found to outperform the baselines by at least 10%.

GLMLP-TRANS: A transportation mode detection model using lightweight sensors integrated in smartphones

Transportation mode detection (TMD), as an essential part of Intelligent Transportation Systems, aims at analyzing human current transportation activities, and can be widely adopted in road planning and traffic prediction. Although several relevant works have been conducted on TMD, there are still some great challenges due to complex factors including: (i) availability that several sensors are limited in certain scenarios; (ii) lightweight that both data collection sensors and the architecture of most current neural network are heavy and sophisticated; and (iii) expert knowledge that numerous researches for TMD are based on traditional machine learning. To address these challenges, we propose a deep learning-based transportation mode detection network using smartphone-based sensors called GLMLP-TRANS, which is inspired by Self-attention and MLP-Mixer. Our proposed GLMLP-TRANS network can capture both global and local temporal features and adaptively combine them to learn comprehensive information of each transportation mode. Residual technique is introduced to accelerate the progress of learning and enhance the accuracy of transportation mode detection. Extensive experimental results on SHL dataset demonstrate that our proposed GLMLP-TRANS network outperforms other six baselines and improve 12.8% than the best baseline on SHL dataset.

Transportation Mode Detection by Using Smartphones and Smartwatches with Machine Learning

Transportation Mode Detection by Using Smartphones and Smartwatches with Machine Learning

A Semisupervised End-to-End Framework for Transportation Mode Detection by Using GPS-Enabled Sensing Devices

As an essential component of Internet of Things, GPS-enabled devices record tremendous digital traces, which provide a great convenience for understanding human mobility. How to discover transportation modes efficiently from such valuable sources has come into the spotlight. In this article, the transportation mode detection is treated as a dense classification task, and a similarity entropy-based encoder-decoder (SEED) model is proposed. We first design an encoder-decoder backbone for end-to-end mode detection. Then, a semi-supervised learning module based on similarity entropy is proposed to exploit numerous unlabeled data. Specifically, we stack several convolutional layers as an encoder to capture hierarchical features from fixed-length trajectories, and then adopt transposed convolutional layers as a decoder. For a semi-supervised module, inspired by entropy regularization, we use the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${K}$ </tex-math></inline-formula> -Means algorithm to cluster prototype vectors from the encoder’s predictions. We then fine-tune the encoder by sharpening the similarity distribution between unlabeled predictions and prototypes, aiming to make the former close to one prototype only while staying away from others. A majority-voting post-processing method is used to alleviate jitter impact when inferring. The Experimental results show that SEED significantly outperforms segmentation-then-inference methods. Furthermore, the similarity entropy-based module can improve the generalization performance of the model, and the metrics such as intersection over union can be increased by 5% over baselines. All of these verify the superiority of our method.

Assessing the role of geographic context in transportation mode detection from GPS data

The increasing availability of health monitoring devices and smartphones has created an opportunity for researchers to access high-resolution (spatial and temporal) mobility data for understanding travel behavior in cities. Although information from GPS data has been used in several studies to detect transportation modes, there is a research gap in understanding the role of geographic context in transportation mode detection. Integrating the geography in which mobility occurs, provides context clues that may allow models predicting transportation modes to be more generalizable. Our goals are first, to develop a data-driven modeling framework for transportation mode detection using GPS mobility data along with geographic context, and second, to assess how model accuracy and generalizability varies upon adding geographic context. To this extent we extracted features from raw GPS mobility data (speed, altitude, turning angle and net displacement) and integrated context in the form of geographic features to classify active (i.e. walk/bike), public (i.e. bus/train), and private (i.e. car) transportation modes in three different Canadian cities - Montreal, St. Johns, and Vancouver. To assess the role of integrating geographic context in mode detection, we adopted two different modeling approaches – generalized and context-specific, and compared results using random forests, extreme gradient boost, and multilayer perceptron classifiers. Our results indicate that for context-specific models the highest classification accuracy improved by 64% for Montreal, by 74% for St. John's and by 77% for Vancouver compared to the generalized model. We also found that the multilayer perceptron (96%) achieved the highest classification accuracy upon adding contextual variables compared to random forests (94.6%) and extreme gradient boost (93.3%) classifier. Our study highlights that adding contextual information specific to a city's geography can improve the predictive accuracy of transportation mode detection models, however, in case of limited knowledge about the geographic setting of a study area, a generalized model combining GPS data from several cities may still be useful for predicting modes from trip data.

A Survey of Deep Learning on Mobile Devices: Applications, Optimizations, Challenges, and Research Opportunities

Deep learning (DL) has demonstrated great performance in various applications on powerful computers and servers. Recently, with the advancement of more powerful mobile devices (e.g., smartphones and touch pads), researchers are seeking DL solutions that could be deployed on mobile devices. Compared to traditional DL solutions using cloud servers, deploying DL on mobile devices have unique advantages in data privacy, communication overhead, and system cost. This article provides a comprehensive survey for the current studies of adopting and deploying DL on mobile devices. Specifically, we summarize and compare the state-of-the-art DL techniques on mobile devices in various application domains involving vision, speech/speaker recognition, human activity recognition, transportation mode detection, and security. We generalize an optimization pipeline for bringing DL to mobile devices, including model-oriented optimization mechanisms (e.g., pruning and quantization) and nonmodel-oriented optimization mechanisms (e.g., software accelerator and hardware design). Moreover, we summarize popular DL libraries regarding their support to state-of-the-art models (software) and processors (hardware). Based on our summarization, we further provide insights into potential research opportunities for developing DL for mobile devices.

Transportation Mode Detection Using an Optimized Long Short-Term Memory Model on Multimodal Sensor Data

The advancement of sensing technologies coupled with the rapid progress in big data analysis has ushered in a new era in intelligent transport and smart city applications. In this context, transportation mode detection (TMD) of mobile users is a field that has gained significant traction in recent years. In this paper, we present a deep learning approach for transportation mode detection using multimodal sensor data elicited from user smartphones. The approach is based on long short-term Memory networks and Bayesian optimization of their parameters. We conducted an extensive experimental evaluation of the proposed approach, which attains very high recognition rates, against a multitude of machine learning approaches, including state-of-the-art methods. We also discuss issues regarding feature correlation and the impact of dimensionality reduction.

Combining Residual and LSTM Recurrent Networks for Transportation Mode Detection Using Multimodal Sensors Integrated in Smartphones

In recent years, with the rapid development of public transportation, the ways people travel has become more diversified and complicated. Transportation mode detection, as a significant branch of human activity recognition (HAR), is of great importance in analyzing human travel patterns, traffic prediction and planning. Though many works have been devoted to transportation mode detection, there remains challenge for accurate and robust transportation pattern identification. In this paper, we propose a residual and LSTM recurrent networks-based transportation mode detection algorithm using multiple light-weight sensors integrated in commodity smartphones. Feature representation learning is adopted separately on multiple preprocessed sensor data using deep residual and LSTM network, which can enhance the identification accuracy and support one or more sensors. Residual units are introduced to accelerate the learning speed and enhance the accuracy of transportation mode detection. Furthermore, we also leverage the attention model to learn the significance of different features and different timesteps to enhance the recognition accuracy. Extensive experimental results on three datasets indicate that using our proposed model can achieve the best recognition accuracy for eight transportation modes including being stationary, walking, running, cycling, taking a car, taking a bus, taking a subway and taking a train, which outperforms other benchmark algorithms.

LSTM Network for Transportation Mode Detection

LSTM Network for Transportation Mode Detection

Recognition of human locomotion on various transportations fusing smartphone sensors

Recognition of daily human activities in various locomotion and transportation modes has numerous applications like coaching users for behavior modification and maintaining a healthy lifestyle. Besides, applications and user interfaces aware of user mobility through their smartphones can also aid in urban transportation planning, smart parking, and vehicular traffic monitoring. In this paper, we explored smartphone sensor-based two benchmark datasets (Sussex Huawei Locomotion (SHL) and Transportation Mode Detection (TMD)). Firstly, we demonstrated preprocesssing of sensor data, window length optimization based on Akaike Information Criteria (AIC), and introduced smartphone orientation independent features. We also provided an in-depth analysis of different smartphone sensors’ importance for classifying daily activities and transportation modes. We justified the sensor relevance by showing the variation of performances with the number of sensors explored. For refining classifier predictions, we also proposed a post-processing approach named “Mode technique”. This method primarily concentrates on the statistical analysis of transportation modes and improves the activity recognition rate in statistical classifiers: Decision Tree, K-Nearest Neighbors, Linear Discriminant Analysis, Logistic Regression, Support Vectors Machine with RBF kernel, Random Forest, and deep learning-based methods: Artificial Neural Network and Recurrent Neural Network by smoothing the outputs of these classifiers. Besides, we showed the use of magnitude and jerk-based features to overcome the overfitting problem due to smartphone orientation. We obtained 97.2% accuracy in the SHL dataset and 99.13% accuracy in the TMD dataset. These results demonstrate that our approach can profoundly recognize various activities in advanced locomotion and transportation modes compared to existing methods in two large-scale datasets.