scholarly journals Collaborative driving style classification method enabled by majority voting ensemble learning for enhancing classification performance

PLoS ONE ◽  
2021 ◽  
Vol 16 (7) ◽  
pp. e0254047
Author(s):  
Yi Guo ◽  
Xiaolan Wang ◽  
Yongmao Huang ◽  
Liang Xu
Keyword(s):  
Ensemble Learning ◽  
Traffic Safety ◽  
Clustering Algorithms ◽  
Autonomous Driving ◽  
Classification Performance ◽  
Majority Voting ◽  
Classification Method ◽  
Driving Style ◽  
Driving Behaviors ◽  
Stable Performance

The classification of driving styles plays a fundamental role in evaluating drivers’ driving behaviors, which is of great significance to traffic safety. However, it still suffers from various challenges, including the insufficient accuracy of the model, the large amount of training parameters, the instability of classification results, and some others. To evaluate the driving behaviors accurately and efficiently, and to study the differences of driving behaviors among various vehicle drivers, a collaborative driving style classification method, which is enabled by ensemble learning and divided into pre-classification and classification, is proposed in this paper. In the pre-classification process, various clustering algorithms are utilized compositely to label some typical initial data with specific labels as aggressive, stable and conservative. Then, in the classification process, other unlabeled data can be classified accurately and efficiently by the majority voting ensemble learning method incorporating three different conventional classifiers. The availability and efficiency of the proposed method are demonstrated through some simulation experiments, in which the proposed collaborative classification method achieves quite good and stable performance on driving style classification. Particularly, compared with some other similar classification methods, the evaluation indicators of the proposed method, including accuracy, precision, recall and F-measure, are improved by 1.49%, 2.90%, 5.32% and 4.49% respectively, making it the best overall performance. Therefore, the proposed method is much preferred for the autonomous driving and usage-based insurance.

scholarly journals A SPECTRALLY IMPROVED POINT CLOUD CLASSIFICATION METHOD FOR MULTISPECTRAL LIDAR

2020 ◽  
Vol XLIII-B3-2020 ◽  
pp. 501-505
Author(s):  
B. Chen ◽  
S. Shi ◽  
W. Gong ◽  
J. Sun ◽  
B. Chen ◽  
...  
Keyword(s):  
Point Cloud ◽  
Autonomous Driving ◽  
Classification Performance ◽  
Classification Method ◽  
Spectral Information ◽  
Land Cover Mapping ◽  
Cloud Classification ◽  
Forestry Management ◽  
Angle Match ◽  
Point Cloud Classification

Abstract. Precise point cloud classification can enhance lidar performance in various applications, such as land cover mapping, forestry management and autonomous driving. The development of multispectral lidar improves classification performance with rich spectral information. However, the employment of spectral information for classification is still underdeveloped. Therefore, we proposed a spectrally improved classification method for multispectral LiDAR. We conducted spectral improvement in two aspects: (1) we improved the eigenentropy-based neighbourhood selection by spectral angle match (SAM) to reform the more reliable neighbour; (2) we utilized both geometric and spectral features and compare the contributions of these features. A three-wavelength multispectral lidar and a complex indoor experimental scene were used for demonstration. The results indicate the effectiveness of our proposed spectrally improved method and the promising potential of spectral information on lidar classification.

scholarly journals Automated classification of clinical trial eligibility criteria text based on ensemble learning and metric learning

2021 ◽  
Vol 21 (S2) ◽  
Author(s):  
Kun Zeng ◽  
Yibin Xu ◽  
Ge Lin ◽  
Likeng Liang ◽  
Tianyong Hao
Keyword(s):  
Clinical Trial ◽  
Ensemble Learning ◽  
Metric Learning ◽  
Classification Performance ◽  
Ensemble Model ◽  
Automated Classification ◽  
Eligibility Criteria ◽  
Data Imbalance ◽  
The Impact

Abstract Background Eligibility criteria are the primary strategy for screening the target participants of a clinical trial. Automated classification of clinical trial eligibility criteria text by using machine learning methods improves recruitment efficiency to reduce the cost of clinical research. However, existing methods suffer from poor classification performance due to the complexity and imbalance of eligibility criteria text data. Methods An ensemble learning-based model with metric learning is proposed for eligibility criteria classification. The model integrates a set of pre-trained models including Bidirectional Encoder Representations from Transformers (BERT), A Robustly Optimized BERT Pretraining Approach (RoBERTa), XLNet, Pre-training Text Encoders as Discriminators Rather Than Generators (ELECTRA), and Enhanced Representation through Knowledge Integration (ERNIE). Focal Loss is used as a loss function to address the data imbalance problem. Metric learning is employed to train the embedding of each base model for feature distinguish. Soft Voting is applied to achieve final classification of the ensemble model. The dataset is from the standard evaluation task 3 of 5th China Health Information Processing Conference containing 38,341 eligibility criteria text in 44 categories. Results Our ensemble method had an accuracy of 0.8497, a precision of 0.8229, and a recall of 0.8216 on the dataset. The macro F1-score was 0.8169, outperforming state-of-the-art baseline methods by 0.84% improvement on average. In addition, the performance improvement had a p-value of 2.152e-07 with a standard t-test, indicating that our model achieved a significant improvement. Conclusions A model for classifying eligibility criteria text of clinical trials based on multi-model ensemble learning and metric learning was proposed. The experiments demonstrated that the classification performance was improved by our ensemble model significantly. In addition, metric learning was able to improve word embedding representation and the focal loss reduced the impact of data imbalance to model performance.

Traffic accident and emission reduction through intermittent release measures for heavy fog weather

2015 ◽  
Vol 29 (25) ◽  
pp. 1550148 ◽  
Author(s):  
Jing Shi ◽  
Jin-Hua Tan
Keyword(s):  
Traffic Safety ◽  
Emission Reduction ◽  
Traffic Accident ◽  
Traffic Accidents ◽  
Driving Simulator ◽  
Emission Characteristics ◽  
Driving Behaviors ◽  
Ca Model ◽  
Reduce Emissions

Heavy fog weather can increase traffic accidents and lead to freeway closures which result in delays. This paper aims at exploring traffic accident and emission characteristics in heavy fog, as well as freeway intermittent release measures for heavy fog weather. A driving simulator experiment is conducted for obtaining driving behaviors in heavy fog. By proposing a multi-cell cellular automaton (CA) model based on the experimental data, the role of intermittent release measures on the reduction of traffic accidents and CO emissions is studied. The results show that, affected by heavy fog, when cellular occupancy [Formula: see text], the probability of traffic accidents is much higher; and CO emissions increase significantly when [Formula: see text]. After an intermittent release measure is applied, the probability of traffic accidents and level of CO emissions become reasonable. Obviously, the measure can enhance traffic safety and reduce emissions.

A Classification method of Fake News based on Ensemble Learning

2020 ◽  
Author(s):  
Sae Bom Lee ◽  
Joon Shik Lim ◽  
Jin Soo Cho ◽  
Sang Yeob Oh ◽  
Taeg Keun Whangbo ◽  
...  
Keyword(s):  
Ensemble Learning ◽  
Classification Method ◽  
Fake News

scholarly journals Factors Influencing and Contributing to Perceived Safety of Passengers during Driverless Shuttle Rides

2021 ◽  
Vol 1 (3) ◽  
pp. 657-671
Author(s):  
Claudia Luger-Bazinger ◽  
Cornelia Zankl ◽  
Karin Klieber ◽  
Veronika Hornung-Prähauser ◽  
Karl Rehrl
Keyword(s):  
Autonomous Driving ◽  
Future Research ◽  
Natural Setting ◽  
Mixed Traffic ◽  
Control Room ◽  
Driving Style ◽  
Perceived Safety ◽  
Factors Influencing ◽  
Traffic Environment ◽  
Set Up

This study investigates the perceived safety of passengers while being on board of a driverless shuttle without a steward present. The aim of the study is to draw conclusions on factors that influence and contribute to perceived safety of passengers in driverless shuttles. For this, four different test rides were conducted, representing aspects that might challenge passengers’ perceived safety once driverless shuttles become part of public transport: passengers had to ride the shuttle on their own (without a steward present), had to interact with another passenger, and had to react to two different unexpected technical difficulties. Passengers were then asked what had influenced their perceived safety and what would contribute to it. Results show that perceived safety of passengers was high across all different test rides. The most important factors influencing the perceived safety of passengers were the shuttle’s driving style and passengers’ trust in the technology. The driving style was increasingly less important as the passengers gained experience with the driverless shuttle. Readily available contact with someone in a control room would significantly contribute to an increase in perceived safety while riding a driverless shuttle. For researchers, as well as technicians in the field of autonomous driving, our findings could inform the design and set-up of driverless shuttles in order to increase perceived safety; for example, how to signal passengers that there is always the possibility of contact to someone in a control room. Reacting to these concerns and challenges will further help to foster acceptance of AVs in society. Future research should explore our findings in an even more natural setting, e.g., a controlled mixed traffic environment.

scholarly journals Ensemble Classification through Random Projections for single-cell RNA-seq data

2020 ◽  
Author(s):  
Aristidis G. Vrahatis ◽  
Sotiris Tasoulis ◽  
Spiros Georgakopoulos ◽  
Vassilis Plagianakos
Keyword(s):  
Single Cell ◽  
Random Projection ◽  
Classification Performance ◽  
Majority Voting ◽  
Ensemble Classification ◽  
High Dimensionality ◽  
Computational Time ◽  
Biomedical Data ◽  
Rna Seq ◽  
Low Dimensional

AbstractNowadays the biomedical data are generated exponentially, creating datasets for analysis with ultra-high dimensionality and complexity. This revolution, which has been caused by recent advents in biotechnologies, has driven to big-data and data-driven computational approaches. An indicative example is the emerging single-cell RNA-sequencing (scRNA-seq) technology, which isolates and measures individual cells. Although scRNA-seq has revolutionized the biotechnology domain, such data computational analysis is a major challenge because of their ultra-high dimensionality and complexity. Following this direction, in this work we study the properties, effectiveness and generalization of the recently proposed MRPV algorithm for single cell RNA-seq data. MRPV is an ensemble classification technique utilizing multiple ultra-low dimensional Random Projected spaces. A given classifier determines the class for each sample for all independent spaces while a majority voting scheme defines their predominant class. We show that Random Projection ensembles offer a platform not only for a low computational time analysis but also for enhancing classification performance. The developed methodologies were applied to four real biomedical high dimensional data from single-cell RNA-seq studies and compared against well-known and similar classification tools. Experimental results showed that based on simplistic tools we can create a computationally fast, simple, yet effective approach for single cell RNA-seq data with ultra-high dimensionality.

scholarly journals Recognition Method of Drinking-driving Behaviors Based on PCA and RBF Neural Network

2018 ◽  
Vol 30 (4) ◽  
pp. 407-417
Author(s):  
Yifan Sun ◽  
Jinglei Zhang ◽  
Xiaoyuan Wang ◽  
Zhangu Wang ◽  
Jie Yu
Keyword(s):  
Neural Network ◽  
Traffic Safety ◽  
Road Traffic ◽  
Rbf Neural Network ◽  
Principal Component ◽  
Physiological Data ◽  
Recognition Model ◽  
Driving Behaviors ◽  
Model Based ◽  
Safety Research

Drinking-driving behaviors are important causes of road traffic injuries, which are serious threats to the lives and property of traffic participants. Therefore, reducing the occurrences of drinking-driving behaviors has become an important problem of traffic safety research. Forty-eight male drivers and six female drivers who could drink moderate alcohol were chosen as participants. The drivers’ physiological data, operation behavior data, car running data, and driving environment data were collected by designing various virtual traffic scenes and organizing drivers to conduct driving simulation experiments. The original variables were analyzed by the Principal Component Analysis (PCA), and seven principal components were extracted as the input vector of the Radial Basis Function (RBF) neural network. The principal component data was used to train and verify the RBF neural network. The Levenberg-Marquardt (LM) algorithm was chosen to train the parameters of the neural network and build a drinking-driving recognition model based on PCA and RBF  neural network to realize an accurate recognition of drinking-driving behaviors. The test results showed that the drinking-driving recognition model based on PCA and RBF neural network could identify drinking drivers accurately during driving process with a recognition accuracy of 92.01%, and the operation efficiency of the model was high. The research can provide useful reference for prevention and treatment of drinking and  driving and traffic safety maintenance.

scholarly journals The Use of Artificial-Intelligence-Based Ensembles for Intrusion Detection: A Review

2012 ◽  
Vol 2012 ◽  
pp. 1-20 ◽  
Author(s):  
Gulshan Kumar ◽  
Krishan Kumar
Keyword(s):  
Artificial Intelligence ◽  
Intrusion Detection ◽  
Supervised Learning ◽  
Ensemble Learning ◽  
Classification Performance ◽  
Intrusion Detection Systems ◽  
Future Directions ◽  
Comprehensive Review ◽  
Detection Systems ◽  
Combination Methods

In supervised learning-based classification, ensembles have been successfully employed to different application domains. In the literature, many researchers have proposed different ensembles by considering different combination methods, training datasets, base classifiers, and many other factors. Artificial-intelligence-(AI-) based techniques play prominent role in development of ensemble for intrusion detection (ID) and have many benefits over other techniques. However, there is no comprehensive review of ensembles in general and AI-based ensembles for ID to examine and understand their current research status to solve the ID problem. Here, an updated review of ensembles and their taxonomies has been presented in general. The paper also presents the updated review of various AI-based ensembles for ID (in particular) during last decade. The related studies of AI-based ensembles are compared by set of evaluation metrics driven from (1) architecture & approach followed; (2) different methods utilized in different phases of ensemble learning; (3) other measures used to evaluate classification performance of the ensembles. The paper also provides the future directions of the research in this area. The paper will help the better understanding of different directions in which research of ensembles has been done in general and specifically: field of intrusion detection systems (IDSs).

A collection of easily deployable adversarial traffic sign stickers

2021 ◽  
Vol 69 (6) ◽  
pp. 511-523
Author(s):  
Henrietta Lengyel ◽  
Viktor Remeli ◽  
Zsolt Szalay
Keyword(s):  
Traffic Safety ◽  
Autonomous Driving ◽  
Driver Assistance ◽  
Driver Assistance Systems ◽  
Traffic Sign ◽  
Practical Possibility ◽  
Special Knowledge ◽  
Environment Perception ◽  
Assistance Systems ◽  
Traffic Sign Classification

Abstract The emergence of new autonomous driving systems and functions – in particular, systems that base their decisions on the output of machine learning subsystems responsible for environment perception – brings a significant change in the risks to the safety and security of transportation. These kinds of Advanced Driver Assistance Systems are vulnerable to new types of malicious attacks, and their properties are often not well understood. This paper demonstrates the theoretical and practical possibility of deliberate physical adversarial attacks against deep learning perception systems in general, with a focus on safety-critical driver assistance applications such as traffic sign classification in particular. Our newly developed traffic sign stickers are different from other similar methods insofar that they require no special knowledge or precision in their creation and deployment, thus they present a realistic and severe threat to traffic safety and security. In this paper we preemptively point out the dangers and easily exploitable weaknesses that current and future systems are bound to face.

Sign in / Sign up

Export Citation Format

Share Document