scholarly journals A Multi-Semantic Driver Behavior Recognition Model of Autonomous Vehicles Using Confidence Fusion Mechanism

Actuators ◽  
2021 ◽  
Vol 10 (9) ◽  
pp. 218
Author(s):  
Hongze Ren ◽  
Yage Guo ◽  
Zhonghao Bai ◽  
Xiangyu Cheng

With the rise of autonomous vehicles, drivers are gradually being liberated from the traditional roles behind steering wheels. Driver behavior cognition is significant for improving safety, comfort, and human–vehicle interaction. Existing research mostly analyzes driver behaviors relying on the movements of upper-body parts, which may lead to false positives and missed detections due to the subtle changes among similar behaviors. In this paper, an end-to-end model is proposed to tackle the problem of the accurate classification of similar driver actions in real-time, known as MSRNet. The proposed architecture is made up of two major branches: the action detection network and the object detection network, which can extract spatiotemporal and key-object features, respectively. Then, the confidence fusion mechanism is introduced to aggregate the predictions from both branches based on the semantic relationships between actions and key objects. Experiments implemented on the modified version of the public dataset Drive&Act demonstrate that the MSRNet can recognize 11 different behaviors with 64.18% accuracy and a 20 fps inference time on an 8-frame input clip. Compared to the state-of-the-art action recognition model, our approach obtains higher accuracy, especially for behaviors with similar movements.

2019 ◽  
Vol 9 (4) ◽  
pp. 752 ◽  
Author(s):  
Junhua Gu ◽  
Chuanxin Lan ◽  
Wenbai Chen ◽  
Hu Han

While remarkable progress has been made to pedestrian detection in recent years, robust pedestrian detection in the wild e.g., under surveillance scenarios with occlusions, remains a challenging problem. In this paper, we present a novel approach for joint pedestrian and body part detection via semantic relationship learning under unconstrained scenarios. Specifically, we propose a Body Part Indexed Feature (BPIF) representation to encode the semantic relationship between individual body parts (i.e., head, head-shoulder, upper body, and whole body) and highlight per body part features, providing robustness against partial occlusions to the whole body. We also propose an Adaptive Joint Non-Maximum Suppression (AJ-NMS) to replace the original NMS algorithm widely used in object detection, leading to higher precision and recall for detecting overlapped pedestrians. Experimental results on the public-domain CUHK-SYSU Person Search Dataset show that the proposed approach outperforms the state-of-the-art methods for joint pedestrian and body part detection in the wild.


Author(s):  
Thomas A. Norton ◽  
Melissa Ruhl ◽  
Tim Armitage ◽  
Brian Matthews ◽  
John Miles

The development of autonomous vehicles (AVs) is advancing quickly in some enclaves around the world. Consequently, AVs exist in the public consciousness, featuring regularly in mainstream media. As the form and function of AVs emerge, the attitudes of potential users become more important. The extent to which the public trusts AV technology and anticipates benefits, will drive consumer willingness to use AVs. Broadly, public attitudes will determine whether AVs can attract public investment in infrastructure and become a feature of the future transport mix or fail to realize the potential their developers assert. As part of UK Autodrive, a program trialing the introduction of AVs in the United Kingdom, researchers conducted focus groups in five UK cities, and a comparison focus group in San Francisco (December 2017 to September 2018) using representative samples (total n = 137). Focus group facilitators guided discussions in three areas considered central to usage decisions: trust in the technology, ownership models, and community benefit. This paper describes findings from a quasi-quantitative study supported with qualitative insights. This research provides three key takeaways centering on trust in the technology and in delivering benefit. First, some participants gain trust through experience and others through evidence. Second, participants had difficulty discriminating between AV developers, indicating a need for industry cooperation. Third, partnerships were found to demonstrate trust, highlighting the need for more and deeper partnerships moving forward. Generally, participants had positive attitudes toward AVs and expect AVs to provide benefits. However, these attitudes and expectations could change as AV development progresses.


2019 ◽  
Vol 6 (1) ◽  
Author(s):  
Jianzhuo Yan ◽  
Shangbin Chen ◽  
Sinuo Deng

Abstract As an advanced function of the human brain, emotion has a significant influence on human studies, works, and other aspects of life. Artificial Intelligence has played an important role in recognizing human emotion correctly. EEG-based emotion recognition (ER), one application of Brain Computer Interface (BCI), is becoming more popular in recent years. However, due to the ambiguity of human emotions and the complexity of EEG signals, the EEG-ER system which can recognize emotions with high accuracy is not easy to achieve. Based on the time scale, this paper chooses the recurrent neural network as the breakthrough point of the screening model. According to the rhythmic characteristics and temporal memory characteristics of EEG, this research proposes a Rhythmic Time EEG Emotion Recognition Model (RT-ERM) based on the valence and arousal of Long–Short-Term Memory Network (LSTM). By applying this model, the classification results of different rhythms and time scales are different. The optimal rhythm and time scale of the RT-ERM model are obtained through the results of the classification accuracy of different rhythms and different time scales. Then, the classification of emotional EEG is carried out by the best time scales corresponding to different rhythms. Finally, by comparing with other existing emotional EEG classification methods, it is found that the rhythm and time scale of the model can contribute to the accuracy of RT-ERM.


2020 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Shweta Banerjee

PurposeThere are ethical, legal, social and economic arguments surrounding the subject of autonomous vehicles. This paper aims to discuss some of the arguments to communicate one of the current issues in the rising field of artificial intelligence.Design/methodology/approachMaking use of widely available literature that the author has read and summarised showcasing her viewpoints, the author shows that technology is progressing every day. Artificial intelligence and machine learning are at the forefront of technological advancement today. The manufacture and innovation of new machines have revolutionised our lives and resulted in a world where we are becoming increasingly dependent on artificial intelligence.FindingsTechnology might appear to be getting out of hand, but it can be effectively used to transform lives and convenience.Research limitations/implicationsFrom robotics to autonomous vehicles, countless technologies have and will continue to make the lives of individuals much easier. But, with these advancements also comes something called “future shock”.Practical implicationsFuture shock is the state of being unable to keep up with rapid social or technological change. As a result, the topic of artificial intelligence, and thus autonomous cars, is highly debated.Social implicationsThe study will be of interest to researchers, academics and the public in general. It will encourage further thinking.Originality/valueThis is an original piece of writing informed by reading several current pieces. The study has not been submitted elsewhere.


2017 ◽  
Vol 11 (03) ◽  
pp. 53-64
Author(s):  
Jussac Maulana Masjhoer ◽  
Dwi Wibowo ◽  
Bijak Qoulan Sadida ◽  
Inosensius Tito Ogista

The lack of information related to the best practices in responsible tourism is one of the causes to tourist behavior problems. This study aims to determine the behavior of tourists in hiking, the adoption of responsible tourism practices, and to compile a responsible tourism practices guidebook. The research method used is survey research by spreading the questionnaire. Based on Likert analysis, at the pre-ascending stage, the classification of attitudes indicated by the respondents for cost and transportation is quite agreeable, while for equipment, guide, and simaksi is agreed. The ascent stage, the indicator when going up the mountain is quite agree, camping is not agree, the cook is agree, and when down the mountain is strongly agree. The post-ascent stage shows quite agreeable attitude. The public test of the guidebook, for the aspect of size and language of submission shows an agreeable attitude, while for the design, thickness, and content of the book shows an agreeable attitude. The conclusion is that (1) Still found the behavior of tourists in mountain climbing that is not environmentally friendly, (2) The responsible tourism practices of mountaineering that includes pre-ascending, ascent, and post-ascent, not well implemented by tourists, and (3) The responsible tourism practices guidebook still lack both technical and substance. Keywords: responsible tourism, mountain hiking, guidebook, tourist behavior


2004 ◽  
pp. 147-176
Author(s):  
Stanimir Rakic

In this paper I examine compound names of plants, animals, human beings and other things in which at least one nominal component designates a part of the body or clothes, or some basic elements of houshold in Serbian and English. The object of my analysis are complex derivatives of the type (adjective noun) + suffix in Serbian and componds of the type noun's + noun, noun + noun and adjective + noun in English. I try to show that there is a difference in metaphorical designation of human beings and other living creatures and things by such compound nouns. My thesis is that the metathorical designation of human beings by such compounds is based on the symbolic meaning of some words and expressions while the designation of other things and beings relies on noticed similarity. In Serbian language such designation is provided by comples derivatives praznoglavac 'empty-headed person', tupoglavac 'dullard' debolokoiac 'callos person', golobradac 'young, inexperienced person' zutokljunac 'tledling' (fig), in English chicken liver, beetle brain birdbrain, bonehead, butterfingers, bigwig, blackleg, blue blood bluestocking, eat's paw, deadhead,fat-guts,fathead, goldbrick (kol) hardhat, hardhead, greenhorn, redcoat (ist), redneck (sl), thickhead, etc. Polisemous compounds like eat's paw lend support for this thesis because their designation of human beings is based on symbolic meaning of some words or expressions. I hypothesize that the direction and extend of the possible metaphorization of names may be accounted for by the following hierarchy (11) people - animals - plants - meterial things. Such hierarchy is well supported by the observations of Lakoff (1987) and Taylor (1995) about the role of human body in early experience and perception ofthe reality. Different restrictions which may be imposed in the hierarchy (11) should be the matter of further study, some of which have been noted on this paper. The compounds of this type denoting people have metaphorically meaning conected with some pejorative uses. These compounds refer to some psychological or characteral features, and show that for the classification of people such features are much more important than physical properties. While the animals and plants are classified according to some charecteristics of their body parts, people are usually classified according to psychollogical characteristics or their social functions. I have also noted a difference in structure between compounds designation animals and those designating plants and other things. The designation of animals relies more on metonymy, and that of plants and other things on metaphor based on comparision of noticed similarities. In the compounds designating animals, the nominal component relatively seldom refers to the parts of plants or other things. I guess that the cause may be the fact that the anatomy of plants is very different from the anatomy of animals. As a consequence the structure adjective + noun is much more characteristic of the compounds designating animals in English than the structure noun's + noun, and the same holds, although in a lesser degree for the compounds designating humans. It is also noticeable that in English compounds whose second component a part of body or clothes the first component rarely designates animals. On the other hand the compounds (9), in which the nominal head refers to some superordinate species, the first component often designates animal species, but usually of a very different kind. These data seem to lend support for Goldvarg & Gluksberg's thesis (1998) that metaforical interpretation is favoured if the nominal constituents denote quite different entities.


2020 ◽  
Vol 73 (4) ◽  
pp. 95-102
Author(s):  
Andriy Danylevskyi ◽  
◽  
Yuliya Danylevska ◽  

The public danger of illegal drug trafficking, drug addiction and related phenomena is obvious; therefore the world community is making significant efforts to counter these phenomena, because only through joint efforts it is possible to ensure an effective counteraction to drug trafficking. For this purpose, states adopt a significant number of international normative legal acts. The issues of countering the illegal drug trafficking, psychotropic substances, their analogues and precursors are considered both within the framework of general documents on combating crime, and in special acts. Taking into account the European integration course of Ukraine, the expansion of international cooperation in the sphere of combating the illegal drug trafficking drugs, psychotropic substances, their analogues and precursors, the following issues should be marked as ones of great importance: observance by Ukraine of its international legal obligations; integration into the world system of counteracting drug trafficking; bringing national legislation in line with the provisions of international regulatory legal acts. This article is devoted to the outlined questions. In particular, the provisions of the national legislation in the sphere of illegal drug trafficking, psychotropic substances, their analogues and precursors are analyzed, and the compliance of domestic norms with international regulatory legal acts in the sphere of combating illegal drug trafficking is concluded. The classification of international regulatory legal acts in the sphere of illegal drug trafficking in dependence to the authority that issued them is given. On the basis of the conducted analysis, the author suggests ways to further improvement of the domestic criminal legislation in the sphere of combating drug trafficking. In particular, it is proposed to criminalize the sowing and cultivation of any kind of narcotic drugs, as well as to partially revise the punishment for certain drug crimes.


Author(s):  
P. V. Samolysov

The article studies the problems of classification of the public antitrust control. The sci- entific grounds of criteria of differentiation of the public antitrust control by types, forms and methods is offered, specific features of separate types of the public antitrust control are revealed.The classification of types of the public antitrust control offered by the author can used for the purposes of optimization of structure of antimonopoly authorities, their powers, system of objects of control, practice of control activity.


2020 ◽  
Vol 12 (1) ◽  
pp. 22
Author(s):  
Aline Cristina Helfenstein ◽  
Douglas Fernando Batista Neis ◽  
Flávia Regina Alves de Hungria Folador ◽  
Marlene Valério dos Santos Arenas ◽  
Rafael Vicente Martins dos Reis ◽  
...  

This article aims to identify the monetary amounts spent by Fundação Universidade Federal de Rondônia (UNIR), with Labor Court due to administrative failures during the supervision of outsourced service contracts. It is a case study, with qualitative research, with documentary analysis of the decisions, sentences and judgments delivered in the processes. After the analysis of 68 (sixty-eight) cases in which UNIR appeared in the passive pole, categories were identified for the classification of the cases. It was found that there was a reduction in the number of lawsuits against UNIR after the Labor Reform and 21 (twenty-one) lawsuits were identified in which UNIR was ordered to pay labor indemnities or the contracted companies signed labor agreements, causing the public agency to be obliged to make payments through Small Value Requests (RPV), or Precatories, deriving from failures in internal controls and management contracts at Fundação Universidade Federal de Rondônia (UNIR).


Author(s):  
Angela Besana

After having discussed the contemporary importance of the not-for-profit and social economy, the chapter builds on a cluster analysis of performances and roles of grant-making foundations, who are the essential node of the cooperation and coopetitiveness, today. This chapter aims to present worldwide grant-making foundations for their performances and profiling according to the latest accounting data and mission reports, which collect results of their projects according to the classification of pure grant-making, networking, leadership, partnership and pooling. With this in mind, the chapter adopts a typical approach of cluster analysis of industrial organization. The cluster analysis emphasizes the profiling of the sample and it allows to separate groups with significant features. The main focus remains on the issues of the finance of the social economy, when the Public Welfare State is too much indebted. Complementary and substitute roles of the Private Welfare State can emerge for the support the not-for-profit economy.


Sign in / Sign up

Export Citation Format

Share Document