A Methodology of DASs Benchmarking to Support Industrial Community Characteristics in Designing and Implementing Advanced Driver Assistance Systems Within Vehicles

Author(s):  
U. S. Mahmoud ◽  
A. S. Albahri ◽  
H. A. AlSattar ◽  
A. A. Zaidan ◽  
M. Talal ◽  
...  

Abstract This study presents a novel benchmarking methodology for Data Acquisition System (DAS) types to support industrial community characteristics in designing and implementing the advanced driver assistance systems within vehicles, which is considered multicriteria decision-making (MCDM) problems. Four issues support this claim. Multiple criteria need to be considered in the evaluation, data variation, trade-off and conflict. Thus, an MCDM solution is essential to overcome problem complexity. In the last years, MCDM developed methods have been studied and criticised from different theoretical aspects. The most recent method, fuzzy decision by opinion score method (FDOSM), has proven its power in solving other methods challenges. However, the FDOSM technique and its extension were based on traditional fuzzy set theory, which is limited and unable to deal with the membership and non-membership hesitation simultaneously and that affect the accuracy of final decision especial among the group of decision-makers. Therefore, this study extended FDOSM into an intuitionistic fuzzy environment that considers the hesitation index in the membership definition, then discuss the power of such membership in evaluating and benchmarking the DAS systems. The proposed methodology comprises two consecutive phases. In the first phase, a decision matrix is formulated based on the crossover of the ‘DAS systems’ and ‘multiple evaluation criteria’. In the second phase, the new method (the intuitionistic FDOSM method) has two main stages (i.e. data transformation unit and data processing). The dataset was used to prove the concept. A total of 39 DASs were evaluated based on 14 DASs criteria, involving seven sub-criteria for “comprehensive complexity assessment” purpose and eight sub-criteria for “design and implementation” purpose, which highly affected the design of DAS when implantation occurred by industrial communities. The results of this study are as follows: (1) Individual results of benchmarking, which used three decision-makers are broad, with consensus on the DAS#1 system ranked as the best. (2) The results of the proposed GDMs proved quality in DASs benchmarking, and the DAS#1 system is also the best. (3) Intuitionistic FDOSM can deal with hesitation and uncertainty problems properly. (4) Significant differences were indicated among the groups’ scores, which proves the validity of the intuitionistic FDOSM results.

2017 ◽  
Vol 58 ◽  
pp. 238-244 ◽  
Author(s):  
Francesco Biondi ◽  
David L. Strayer ◽  
Riccardo Rossi ◽  
Massimiliano Gastaldi ◽  
Claudio Mulatti

Author(s):  
Sơn

Các hệ thống hỗ trợ lái xe tiên tiến (Advanced Driver Assistance Systems: ADAS) đóng một vai trò quan trọng trong hệ thống an toàn chủ động chỉ có camera và các phương tiện tự động thông minh. Đối với các ứng dụng này, các yêu cầu về hiệu suất phát hiện đáng tin cậy và thời gian thực là các yếu tố cấp thiết. Bài báo này đề xuất giải pháp tối ưu tốc độ phát hiện ô tô và giảm các cảnh báo lỗi cho các hệ thống phát hiện điểm mù. Theo đó, trước tiên chúng tôi đề xuất bộ phân tầng Cascade – AdaBoost cùng với tập dữ liệu mẫu và thuật toán đào tạo của chúng tôi. Ngoài ra, để cải thiện tốc độ phát hiện, một kĩ thuật lựa chọn vùng quan tâm (Region of Interest: ROI) cũng được sử dụng để tránh trích xuất các vùng có khả năng tạo ra các cảnh báo lỗi như là bầu trời hoặc các vùng không phù hợp với phối cảnh. Phương pháp đề xuất đã tăng tốc độ phát hiện lên ít nhất 1,9 lần và giảm cảnh báo lỗi 2,24 lần so với phương pháp truyền thống ở các ảnh có độ phân giải cao (720 x 480) với tỷ lệ phát hiện đạt 99,4% và tỷ lệ cảnh báo lỗi nhỏ là 4,08%. Phương pháp đề xuất này có thể được ứng dụng cho các xe tự hành thông minh thời gian thực.


Author(s):  
Francesco Rundo ◽  
Roberto Leotta ◽  
Sebastiano Battiato ◽  
Concetto Spampinato ◽  
Sabrina Conoci

Author(s):  
Daniel Palac ◽  
Iiona D. Scully ◽  
Rachel K. Jonas ◽  
John L. Campbell ◽  
Douglas Young ◽  
...  

The emergence of vehicle technologies that promote driver safety and convenience calls for investigation of the prevalence of driver assistance systems as well as of their use rates. A consumer driven understanding as to why certain vehicle technology is used remains largely unexplored. We examined drivers’ experience using 13 different advanced driver assistance systems (ADAS) and several reasons that may explain rates of use through a nationally-distributed survey. Our analysis focused on drivers’ levels of understanding and trust with their vehicle’s ADAS as well as drivers’ perceived ease, or difficulty, in using the systems. Respondents’ age and experience with Level 0 or Level 1 technologies revealed additional group differences, suggesting older drivers (55+), and those with only Level 0 systems as using ADAS more often. These data are interpreted using the Driver Behavior Questionnaire framework and offer a snapshot of the pervasiveness of certain driver safety systems.


Sign in / Sign up

Export Citation Format

Share Document