scholarly journals Fed-SCNN: A Federated Shallow-CNN Recognition Framework for Distracted Driving

2020 ◽  
Vol 2020 ◽  
pp. 1-10
Author(s):  
Yaojie Wang ◽  
Xiaolong Cui ◽  
Zhiqiang Gao ◽  
Bo Gan
Keyword(s):  
Machine Learning ◽  
Hybrid Model ◽  
Traffic Safety ◽  
Privacy Protection ◽  
Cloud Model ◽  
Distracted Driving ◽  
Dynamic Learning ◽  
Safe Driving ◽  
Cloud Server ◽  
Data Isolation

Although distracted driving recognition is of great significance to traffic safety, drivers are reluctant to provide their own personalized driving data to machine learning because of privacy protection. How to improve the accuracy of distracted driving recognition on the basis of ensuring privacy protection? To address the issue, we proposed the federated shallow-CNN recognition framework (Fed-SCNN). Firstly, a hybrid model is established on the user-side through DNN and shallow-CNN, which recognizes the data of the in-vehicle images and uploads the encrypted parameters to the cloud. Secondly, the cloud server performs federated learning on major parameters through DNN to build a global cloud model. Finally, The DNN is updated in the user-side to further optimize the hybrid model. The above three steps are cycled to iterate the local hybrid model continuously. The Fed-SCNN framework is a dynamic learning process that addresses the two major issues of data isolation and privacy protection. Compared with the existing machine learning method, Fed-SCNN has great advantages in accuracy, safety, and efficiency and has important application value in the field of safe driving.

A New Hybrid Model for RUL Prediction through Machine Learning

2021 ◽  
Author(s):  
Zahra Esfahani ◽  
Karim Salahshoor ◽  
Behnam Farsi ◽  
Ursula Eicker
Keyword(s):  
Machine Learning ◽  
Hybrid Model

Innovative Approach to Build a Scalable Hybrid Model for Prescriptive Maintenance

2021 ◽  
Author(s):  
Richard Büssow ◽  
Bruno Hain ◽  
Ismael Al Nuaimi
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Big Data ◽  
Hybrid Model ◽  
Domain Knowledge ◽  
Spare Parts ◽  
Good Prediction ◽  
First Principle ◽  
Plant Data ◽  
Rotating Equipment

Abstract Objective and Scope Analysis of operational plant data needs experts in order to interpret detected anomalies which are defined as unusual operation points. The next step on the digital transformation journey is to provide actionable insights into the data. Prescriptive Maintenance defines in advance which kind of detailed maintenance and spare parts will be required. This paper details requirements to improve these predictions for rotating equipment and show potential to integrate the outcome into an operational workflow. Methods, Procedures, Process First principle or physics-based modelling provides additional insights into the data, since the results are directly interpretable. However, such approaches are typically assumed to be expensive to build and not scalable. Identification of and focus on the relevant equipment to be modeled in a hybrid model using a combination of first principle physics and machine learning is a successful strategy. The model is trained using a machine learning approach with historic or current real plant data, to predict conditions which have not occurred before. The better the Artificial Intelligence is trained, the better the prediction will be. Results, Observations, Conclusions The general aim when operating a plant is the actual usage of operational data for process and maintenance optimization by advanced analytics. Typically a data-driven central oversight function supports operations and maintenance staff. A major lesson-learned is that the results of a rather simple statistical approach to detect anomalies fall behind the expectations and are too labor intensive. It is a widely spread misinterpretation that being able to deal with big data is sufficient to come up with good prediction quality for Prescriptive Maintenance. What big data companies are normally missing is domain knowledge, especially on plant critical rotating equipment. Without having domain knowledge the relevant input into the model will have shortcomings and hence the same will apply to its predictions. This paper gives an example of a refinery where the described hybrid model has been used. Novel and Additive Information First principle models are typically expensive to build and not scalable. This hybrid model approach, combining first principle physics based models with artificial intelligence and integration into an operational workflow shows a new way forward.

Distracted Driving and Driving Patterns in Older Drivers With Glaucoma

2021 ◽  
pp. 155982762110428
Author(s):  
Purva Jain ◽  
Jonathan T. Unkart ◽  
Fabio B. Daga ◽  
Linda Hill
Keyword(s):  
Visual Acuity ◽  
Visual Field ◽  
Visual Fields ◽  
Distracted Driving ◽  
Night Vision ◽  
Driving Ability ◽  
Safe Driving ◽  
Ability To Drive ◽  
Acuity Score

Limited research exists examining self-perceived vision and driving ability among individuals with glaucoma, and this study assessed the relationship between glaucoma, visual field, and visual acuity with driving capability. 137 individuals with glaucoma and 75 healthy controls were asked to evaluate self-rated vision, self-perceived driving ability, and self-perceived distracted driving. Visual acuity and visual field measurements were also obtained. Multivariable linear regressions were run to test each visual measure with driving outcomes. The average age was 72.2 years, 57.3% were male, and 72.5% were White. There were significant associations for a one-point increase in visual field and quality of corrected vision (RR = 1.06; 95% CI = 1.03–1.10), day vision (RR = 1.05; 95% CI = 1.03–1.08), night vision (RR = 1.08; 95% CI = 1.05–1.13), visual acuity score and higher quality of corrected of vision (RR = .41; 95% CI = .22-.77), day vision (RR = .39; 95% CI=.22–.71), and night vision (RR = .41; 95% CI = .18–.94); visual acuity score and ability to drive safely compared to other drivers your age (RR = .53; 95% CI = .29–.96). Individuals with poorer visual acuity and visual fields rate their vision and ability to drive lower than those with better vision, and this information will allow clinicians to understand where to target interventions to enhance safe driving practices.

scholarly journals The Development and Validation of Pre-Driving Assessment: Attitude towards safe driving scale

2020 ◽  
Vol 5 (13) ◽  
pp. 337-342
Author(s):  
Mohamad Ghazali Masuri ◽  
Akehsan Dahlan ◽  
Khairil Anuar Md Isa ◽  
Rugayah Hashim
Keyword(s):  
Human Factors ◽  
Traffic Safety ◽  
Publishing House ◽  
Validity And Reliability ◽  
Occupational Science ◽  
Safe Driving ◽  
Functional Activities ◽  
International Publishing ◽  
Development And Validation ◽  
Open Access Article

An occupational therapist who involved with driving rehabilitation should use a proper evaluation in identifying safe driving behaviour during the pre-driving assessment. Many reports have stated that human factors contributed up to 97% of collision. This study aims to develop a psychological evaluation that measures human factors in traffic safety during the pre-driving assessment. This study was involved sequential mix methodology approach. The factor analysis was carried out to determine the validity and reliability of the evaluation (Cronbach alpha .887). This assessment found to be adequate in providing the standard means of risky driving attitude based on the cut off value established.Keywords: Occupational science; Pre-driving assessment; Functional activities; Driving rehabilitationeISSN: 2398-4287 © 2020. The Authors. Published for AMER ABRA cE-Bs by e-International Publishing House, Ltd., UK. This is an open access article under the CC BYNC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/). Peer–review under responsibility of AMER (Association of Malaysian Environment-Behaviour Researchers), ABRA (Association of Behavioural Researchers on Asians) and cE-Bs (Centre for Environment-Behaviour Studies), Faculty of Architecture, Planning & Surveying, Universiti Teknologi MARA, Malaysia.DOI: https://doi.org/10.21834/e-bpj.v5i13.2060

scholarly journals Study of a Privacy Preserving Logistic Regression Algorithm (PPLRA) For Data Privacy in the Context of Big Data

2021 ◽  
Vol 2083 (3) ◽  
pp. 032059
Author(s):  
Qiang Chen ◽  
Meiling Deng
Keyword(s):  
Machine Learning ◽  
Logistic Regression ◽  
Privacy Protection ◽  
Data Privacy ◽  
Absolute Error ◽  
Average Absolute Error ◽  
Regression Algorithms ◽  
Hadoop Platform ◽  
Logistic Regression Algorithm ◽  
Computing Speed

Abstract Regression algorithms are commonly used in machine learning. Based on encryption and privacy protection methods, the current key hot technology regression algorithm and the same encryption technology are studied. This paper proposes a PPLAR based algorithm. The correlation between data items is obtained by logistic regression formula. The algorithm is distributed and parallelized on Hadoop platform to improve the computing speed of the cluster while ensuring the average absolute error of the algorithm.

Sign in / Sign up

Export Citation Format

Share Document