scholarly journals Lightweight Driver Behavior Identification Model with Sparse Learning on In-Vehicle CAN-BUS Sensor Data

Sensors ◽  
2020 ◽  
Vol 20 (18) ◽  
pp. 5030 ◽  
Author(s):  
Shan Ullah ◽  
Deok-Hwan Kim
Keyword(s):  
Embedded System ◽  
Performance Metrics ◽  
Short Term Memory ◽  
Can Bus ◽  
Driver Behavior ◽  
Window Size ◽  
Sensor Data ◽  
Sparse Learning ◽  
Area Network ◽  
Time Step

This study focuses on driver-behavior identification and its application to finding embedded solutions in a connected car environment. We present a lightweight, end-to-end deep-learning framework for performing driver-behavior identification using in-vehicle controller area network (CAN-BUS) sensor data. The proposed method outperforms the state-of-the-art driver-behavior profiling models. Particularly, it exhibits significantly reduced computations (i.e., reduced numbers both of floating-point operations and parameters), more efficient memory usage (compact model size), and less inference time. The proposed architecture features depth-wise convolution, along with augmented recurrent neural networks (long short-term memory or gated recurrent unit), for time-series classification. The minimum time-step length (window size) required in the proposed method is significantly lower than that required by recent algorithms. We compared our results with compressed versions of existing models by applying efficient channel pruning on several layers of current models. Furthermore, our network can adapt to new classes using sparse-learning techniques, that is, by freezing relatively strong nodes at the fully connected layer for the existing classes and improving the weaker nodes by retraining them using data regarding the new classes. We successfully deploy the proposed method in a container environment using NVIDIA Docker in an embedded system (Xavier, TX2, and Nano) and comprehensively evaluate it with regard to numerous performance metrics.

Human Activity Recognition using Fourier Transform Inspired Deep Learning Combination Model

2019 ◽  
Vol 9 (1) ◽  
pp. 16-31
Author(s):  
Kyungkoo Jun
Keyword(s):  
Fourier Transform ◽  
Deep Learning ◽  
Short Term Memory ◽  
Window Size ◽  
Sensor Data ◽  
Data Sets ◽  
Data Set ◽  
Proposed Model ◽  
Testing Data ◽  
Labeling Scheme

Background & Objective: This paper proposes a Fourier transform inspired method to classify human activities from time series sensor data. Methods: Our method begins by decomposing 1D input signal into 2D patterns, which is motivated by the Fourier conversion. The decomposition is helped by Long Short-Term Memory (LSTM) which captures the temporal dependency from the signal and then produces encoded sequences. The sequences, once arranged into the 2D array, can represent the fingerprints of the signals. The benefit of such transformation is that we can exploit the recent advances of the deep learning models for the image classification such as Convolutional Neural Network (CNN). Results: The proposed model, as a result, is the combination of LSTM and CNN. We evaluate the model over two data sets. For the first data set, which is more standardized than the other, our model outperforms previous works or at least equal. In the case of the second data set, we devise the schemes to generate training and testing data by changing the parameters of the window size, the sliding size, and the labeling scheme. Conclusion: The evaluation results show that the accuracy is over 95% for some cases. We also analyze the effect of the parameters on the performance.

scholarly journals Green Roof Hydrological Modelling With GRU And LSTM Networks

2021 ◽  
Author(s):  
Haowen Xie ◽  
Randall Mark ◽  
Kwok-wing Chau
Keyword(s):  
Short Term Memory ◽  
Time Window ◽  
Forecast Accuracy ◽  
Window Size ◽  
Green Roofs ◽  
Step Length ◽  
Data Availability ◽  
Time Step ◽  
Hydrological Simulation ◽  
Memory Length

Abstract Green Roofs (GRs) are becoming more popular as a low-impact building option. They have the potential to minimize peak stormwater runoff while also increasing the quality of runoff from buildings. Improvement of hydrological models for the simulation of GRs will aid design of individual roofs as well as city scale planning that relies on the predicted impacts of widespread GR implementation. Machine learning (ML) has exploded in popularity in recent years, owing to considerable increases in processing power and data availability. However, there are no studies focusing on the use of ML in hydrological simulation of GRs. We focus on two types of ML-based model: long short-term memory (LSTM) and gated recurrent unit (GRU) in modelling hydrological performance of GRs, with sequence input and a single output (SISO), and synced sequence input and output (SSIO) architectures. According to the results of this paper, LSTM and GRU are useful tools for the modelling of GRs. As the time window length (memory length, time step length of input data) increases, SISO appears to have a higher overall forecast accuracy. SSIO delivers the best overall performance, when the SSIO is close to, or even exceeds, the maximum window size.

scholarly journals Sensor-Based Extraction Approaches of In-Vehicle Information for Driver Behavior Analysis

Sensors ◽  
2020 ◽  
Vol 20 (18) ◽  
pp. 5197
Author(s):  
Beomjun Kim ◽  
Yunju Baek
Keyword(s):  
Behavior Analysis ◽  
Electronic Control Unit ◽  
Driver Behavior ◽  
Sensor Data ◽  
Estimation Accuracy ◽  
Measurement Unit ◽  
Steering Wheel ◽  
Automatic Extraction ◽  
Area Network ◽  
Vehicle Information

Advances in vehicle technology have resulted in the development of vehicles equipped with sensors to acquire standardized information such as engine speed and vehicle speed from the in-vehicle controller area network (CAN) system. However, there are challenges in acquiring proprietary information from CAN frames, such as the brake pedal and steering wheel operation, which are essential for driver behavior analysis. Such information extraction requires electronic control unit identifier analysis and accompanying data interpretation. In this paper, we present a system for the automatic extraction of proprietary in-vehicle information using sensor data correlated with the desired information. First, the proposed system estimates the vehicle’s driving status through threshold-, random forest-, and long short-term memory-based techniques using inertial measurement unit and global positioning system values. Then, the system segments in-vehicle CAN frames using the estimation and evaluates each segment with our scoring method to select suitable candidates by examining the similarity between each candidate and its estimation through the suggested distance matching technique. We conduct comprehensive experiments of the proposed system using real vehicles in an urban environment. Performance evaluation shows that the estimation accuracy of the driving condition is 84.20%, and the extraction accuracy of the in-vehicle information is 82.31%, which implies that the presented approaches are quite feasible for automatic extraction of proprietary in-vehicle information.

Design and Creation of the Automatic Data Testing Tools for Smart Sensor Based on CAN Bus

2014 ◽  
Vol 556-562 ◽  
pp. 2948-2952
Author(s):  
Wei Kang Qian ◽  
Xiao Lin Zheng
Keyword(s):  
Virtual Instrument ◽  
Can Bus ◽  
Test System ◽  
Visual Programming ◽  
Sensor Data ◽  
Motor Vehicles ◽  
Area Network ◽  
Automatic Test ◽  
Report Generation ◽  
Automatic Data

As the purpose of environmental protection, NOx sensor is driven to develop. It is built to detect the concentration of nitrogen oxides in the exhaust emissions of motor vehicles. During the development of sensor, the automatic test for the sensor ́s output message is a significant procedure. This article is aimed to design a user friendly test tool based on LabVIEW for real time testing, evaluating and error detecting of sensor data transmitted via CAN bus. Controller area network (CAN) is one of the most widely and frequently used communication protocols in automotive applications. LabVIEW (Laboratory Virtual Instrument Engineering Workbench) is a system-design platform and development environment for a visual programming language from National Instruments. NI Company provides flexible and diverse CAN bus interface hardware and software drivers which is useful and necessary for building an automatic test system. It contains the features of configuration, displaying and decoding CAN data frames, checking CAN bus errors, testing and evaluating decoded messages, report generation, signal setting and validation.

scholarly journals Deep stair walking detection using wearable inertial sensor via long short-term memory network

2020 ◽  
Vol 9 (1) ◽  
pp. 238-246
Author(s):  
Gan Wei Nie ◽  
Nurul Fathiah Ghazali ◽  
Norazman Shahar ◽  
Muhammad Amir As'ari
Keyword(s):  
Short Term Memory ◽  
Inertial Sensors ◽  
Inertial Sensor ◽  
Window Size ◽  
Sensor Data ◽  
Short Term ◽  
Term Memory ◽  
Detection Model ◽  
Long Short Term Memory ◽  
Stair Walking

This paper proposes a stair walking detection via Long-short Term Memory (LSTM) network to prevent stair fall event happen by alerting caregiver for assistance as soon as possible. The tri-axial accelerometer and gyroscope data of five activities of daily living (ADLs) including stair walking is collected from 20 subjects with wearable inertial sensors on the left heel, right heel, chest, left wrist and right wrist. Several parameters which are window size, sensor deployment, number of hidden cell unit and LSTM architecture were varied in finding an optimized LSTM model for stair walking detection. As the result, the best model in detecting stair walking event that achieve 95.6% testing accuracy is double layered LSTM with 250 hidden cell units that is fed with data from all sensor locations with window size of 2 seconds. The result also shows that with similar detection model but fed with single sensor data, the model can achieve very good performance which is above 83.2%. It should be possible, therefore, to integrate the proposed detection model for fall prevention especially among patients or elderly in helping to alert the caregiver when stair walking event occur.

scholarly journals Attacks to Automatous Vehicles: A Deep Learning Algorithm for Cybersecurity

Sensors ◽  
2022 ◽  
Vol 22 (1) ◽  
pp. 360
Author(s):  
Theyazn H. H. Aldhyani ◽  
Hasan Alkahtani
Keyword(s):  
Deep Learning ◽  
High Performance ◽  
Short Term Memory ◽  
Learning Algorithm ◽  
Can Bus ◽  
Autonomous Vehicle ◽  
Hybrid Network ◽  
Superior Performance ◽  
Area Network ◽  
Vehicle Network

Rapid technological development has changed drastically the automotive industry. Network communication has improved, helping the vehicles transition from completely machine- to software-controlled technologies. The autonomous vehicle network is controlled by the controller area network (CAN) bus protocol. Nevertheless, the autonomous vehicle network still has issues and weaknesses concerning cybersecurity due to the complexity of data and traffic behaviors that benefit the unauthorized intrusion to a CAN bus and several types of attacks. Therefore, developing systems to rapidly detect message attacks in CAN is one of the biggest challenges. This study presents a high-performance system with an artificial intelligence approach that protects the vehicle network from cyber threats. The system secures the autonomous vehicle from intrusions by using deep learning approaches. The proposed security system was verified by using a real automatic vehicle network dataset, including spoofing, flood, replaying attacks, and benign packets. Preprocessing was applied to convert the categorical data into numerical. This dataset was processed by using the convolution neural network (CNN) and a hybrid network combining CNN and long short-term memory (CNN-LSTM) models to identify attack messages. The results revealed that the model achieved high performance, as evaluated by the metrics of precision, recall, F1 score, and accuracy. The proposed system achieved high accuracy (97.30%). Along with the empirical demonstration, the proposed system enhanced the detection and classification accuracy compared with the existing systems and was proven to have superior performance for real-time CAN bus security.

scholarly journals A Deep Learning Framework for Driving Behavior Identification on In-Vehicle CAN-BUS Sensor Data

Sensors ◽  
2019 ◽  
Vol 19 (6) ◽  
pp. 1356 ◽  
Author(s):  
Jun Zhang ◽  
ZhongCheng Wu ◽  
Fang Li ◽  
Chengjun Xie ◽  
Tingting Ren ◽  
...  
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Can Bus ◽  
Driving Behavior ◽  
Sensor Data ◽  
Area Network ◽  
Feature Representations ◽  
Learning Framework ◽  
Driving Behaviors ◽  
Temporal Features

Human driving behaviors are personalized and unique, and the automobile fingerprint of drivers could be helpful to automatically identify different driving behaviors and further be applied in fields such as auto-theft systems. Current research suggests that in-vehicle Controller Area Network-BUS (CAN-BUS) data can be used as an effective representation of driving behavior for recognizing different drivers. However, it is difficult to capture complex temporal features of driving behaviors in traditional methods. This paper proposes an end-to-end deep learning framework by fusing convolutional neural networks and recurrent neural networks with an attention mechanism, which is more suitable for time series CAN-BUS sensor data. The proposed method can automatically learn features of driving behaviors and model temporal features without professional knowledge in features modeling. Moreover, the method can capture salient structure features of high-dimensional sensor data and explore the correlations among multi-sensor data for rich feature representations of driving behaviors. Experimental results show that the proposed framework performs well in the real world driving behavior identification task, outperforming the state-of-the-art methods.

scholarly journals Identify a Spoofing Attack on an In-Vehicle CAN Bus Based on the Deep Features of an ECU Fingerprint Signal

Smart Cities ◽  
2020 ◽  
Vol 3 (1) ◽  
pp. 17-30
Author(s):  
Yun Yang ◽  
Zongtao Duan ◽  
Mark Tehranipoor
Keyword(s):  
Autonomous Vehicles ◽  
Short Term Memory ◽  
Can Bus ◽  
Area Network ◽  
Gate Arrays ◽  
Control Units ◽  
Field Programmable ◽  
Programmable Gate Arrays ◽  
Long Short Term Memory ◽  
High Computational Complexity

An in-vehicle controller area network (CAN) bus is vulnerable because of increased sharing among modern autonomous vehicles and the weak protocol design principle. Spoofing attacks on a CAN bus can be difficult to detect and have the potential to enable devastating attacks. To effectively identify spoofing attacks, we propose the authentication of sender identities using a recurrent neural network with long short-term memory units (RNN-LSTM) based on the features of a fingerprint signal. We also present a way to generate the analog fingerprint signals of electronic control units (ECUs) to train the proposed RNN-LSTM classifier. The proposed RNN-LSTM model is accelerated on embedded Field-Programmable Gate Arrays (FPGA) to allow for real-time detection despite high computational complexity. A comparison of experimental results with the latest studies demonstrates the capability of the proposed RNN-LSTM model and its potential as a solution to in-vehicle CAN bus security.

scholarly journals Comparison of Long Short Term Memory Networks and the Hydrological Model in Runoff Simulation

Water ◽  
2020 ◽  
Vol 12 (1) ◽  
pp. 175 ◽  
Author(s):  
Hongxiang Fan ◽  
Mingliang Jiang ◽  
Ligang Xu ◽  
Hua Zhu ◽  
Junxiang Cheng ◽  
...  
Keyword(s):  
Short Term Memory ◽  
Window Size ◽  
Test Period ◽  
Data Driven ◽  
Meteorological Variables ◽  
Short Term ◽  
Time Step ◽  
Term Memory ◽  
Runoff Modeling ◽  
Long Short Term Memory

Runoff modeling is one of the key challenges in the field of hydrology. Various approaches exist, ranging from physically based over conceptual to fully data driven models. In this paper, we propose a data driven approach using the state-of-the-art Long-Short-Term-Memory (LSTM) network. The proposed model was applied in the Poyang Lake Basin (PYLB) and its performance was compared with an Artificial Neural Network (ANN) and the Soil & Water Assessment Tool (SWAT). We first tested the impacts of the number of previous time step (window size) in simulation accuracy. Results showed that a window in improper large size will dramatically deteriorate the model performance. In terms of PYLB, a window size of 15 days might be appropriate for both accuracy and computational efficiency. We then trained the model with 2 different input datasets, namely, dataset with precipitation only and dataset with all available meteorological variables. Results demonstrate that although LSTM with precipitation data as the only input can achieve desirable results (where the NSE ranged from 0.60 to 0.92 for the test period), the performance can be improved simply by feeding the model with more meteorological variables (where NSE ranged from 0.74 to 0.94 for the test period). Moreover, the comparison results with the ANN and the SWAT showed that the ANN can get comparable performance with the SWAT in most cases whereas the performance of LSTM is much better. The results of this study underline the potential of the LSTM for runoff modeling especially for areas where detailed topographical data are not available.

scholarly journals An Initial Machine Learning-Based Victim’s Scream Detection Analysis for Burning Sites

2021 ◽  
Vol 11 (18) ◽  
pp. 8425
Author(s):  
Fairuz Samiha Saeed ◽  
Abdullah Al Bashit ◽  
Vishu Viswanathan ◽  
Damian Valles
Keyword(s):  
Machine Learning ◽  
Embedded System ◽  
Performance Metrics ◽  
Short Term Memory ◽  
Research Work ◽  
Automated System ◽  
Support Vector ◽  
Detection Analysis ◽  
Time Critical ◽  
In Fire

Fire incidents are responsible for severe damage and thousands of deaths every year all over the world. Extreme temperatures, low visibility, toxic gases, and unknown locations of victims create difficulties and delays in rescue operations, escalating the risk of injury or death. It is time-critical to detect the victims trapped inside the burning sites for facilitating the rescue operations. This research work presents an audio-based automated system for victim detection in fire emergencies, investigating two machine learning (ML) methods: support vector machines (SVM) and long short-term memory (LSTM). The performance of these two ML techniques has been evaluated based on a variety of performance metrics. Our analyses show that both ML methods provide superior scream detection performance, with SVM slightly overperforming LSTM. Because of its lower complexity, SVM is a better candidate for real-time implementation in our autonomous embedded system vehicle (AESV).

Sign in / Sign up

Export Citation Format

Share Document