Effect of verbal messages with reminders to communicate driving situations to alter driver behavior in conditional driving automation

In conditionally automated driving, drivers are relieved of steering (hands-off), accelerating, and braking actions as well as of continuous monitoring of driving situations and the system operation status (eyes off). This enables continuously engagement in non-driving-related activities. Managing the allocation of a driver’s attention to the surrounding environment and automation status presents a major challenge in human–machine system design. In this study, we propose a verbal message with a reminder (monitoring request) to divert the driver’s attention from non-driving-related activities to peripheral monitoring under conditionally automated driving. When the system encounters events related to weather, traffic, and road geometry, it provides a verbal message pertaining to the road surroundings (e.g., “It is foggy outside”) to the driver. After three seconds, the system provides a reminder message (i.e., “Did you confirm it?”) to the driver. We explore two questions: (1) how does the message with the reminder affect the driver’s attention allocation, and (2) how does the message with the reminder affect the driver behavior in response to a request to intervene (RTI). With a driving simulator, we designed a repeated measures mixed design with a between-participant factor of “Driving condition” and within-participant factors of “Event type” and “Measurement time”. Three driving conditions were established as follows: no messages, messages without reminders, and messages with reminders. Twenty-seven drivers participated as participants in the driving simulator experiment. Results showed that the reminder message was effective in allocating the participants’ attention to the surrounding environment, and the participants took over the driving task after spending more time understanding the take-over situation in the condition of messages with reminders compared to those in the condition of no messages. We conclude that the proposed reminder message can direct drivers’ attention to the road surroundings during conditionally automated driving. In the future, we plan to design adaptive verbal monitoring requests to adjust the reminder message according to the situation.     

Exploration of mental envelope determinants when pedestrians interact with various mobilities on mixed streets

Mixed traffic of multiple road users may increase when machines and future mobilities are gradually introduced in human society to satisfy the travel and service needs of people. For providing a safe and comfortable walking environment for pedestrians in the mixed streets with various mobilities, this study proposes the envelope theorem based on the contributions and limitations of the previous explorations in human–machine coexistence. The envelope is divided into physical and mental envelopes. The main focus of this study is the mental envelope (ME) which is a psychological boundary used to distinguish the range of comfort and unpleasantness in people’s minds. ME as the expansion of previous interpersonal distance can explain the pedestrian perceptions from different perspectives. This paper discusses the definition, expressions, and applications of ME, and then explores its determinants and relationships by conducting structural equation modeling (SEM) based on the questionnaire survey. The findings may assist to create better road allocation in the future.     

Group cycling safety behaviours: A systematic review

BackgroundThe popularity of cycling in a group is longstanding and increasing. Compared to riding as an individual, many cyclists feel safer when riding in a group as they have better personal security, potential support in case of mishaps, safer wayfinding and are more visible to other road users. However, further to the safety challenges shared with individual cyclists, group cyclist safety is impacted by rider proximity, the larger space taken up on roadways, potentially higher speeds, and social norms that could increase risky behaviours. Despite these unique safety considerations, the practice of cycling in groups has received little academic attention and group cyclist safety behaviours have not been analysed by road safety researchers.ObjectiveTo identify, describe, categorise and conceptualise within a teamwork framework, safety related behaviours of groups of cyclists as mentioned in academic literature.MethodsThree academic databases (Google Scholar, Proquest, and Scopus) were searched for peer reviewed literature that mentioned safe or risky behaviours of groups of cyclists. A total of 32 papers met the inclusion criteria. Relevant group cyclist behaviours were described and categorised using a conceptual teamwork framework.ResultsGroup cyclists’ safety behaviours are governed by a comprehensive but informal and adaptable set of rules. These rules are safety critical and are often strictly controlled within groups. Many groups of cyclists may ride in a safer manner than individual cyclists due to teamwork factors, particularly shared mental models, team orientation, and adaptability.ConclusionGroup cyclists take safety seriously. Teamwork factors may make behavioural interventions to decrease risky behaviours easier to implement with group cyclists compared to individual cyclists. Investigation of group cycling safety behaviours may inform safe system interventions to increase road safety.     

情感代理能否提高多媒体学习的效果?

近年来,情感代理如何影响学习受到了研究者们的高度重视。情感代理是可以通过面部表情、声音、肢体动作和言语信息等影响学习者情感体验的教学代理。以往研究主要关注两种类型的情感代理：表达型情感代理和移情型情感代理。表达型情感代理是仅通过自身的情绪表达(如：使用微笑的面部表情和热情的声音)以影响学习者情绪体验的代理。移情型情感代理则是能根据学习者的学习表现或情绪状态给予情感反馈(如;点头、鼓励和共情)的代理,其目的是为了调节学习者的情绪、激励其继续努力。虽然不同的研究者对情感代理的具体操作有所不同,但无论哪种类型的情感代理均是为了增加学习者的积极情绪,提高内部动机,最终促进学习。关于情感代理的潜在作用,研究者基于不同的理论观点给出了不同的解释。情绪感染理论认为一个人的情绪状态容易受到另一个人情绪表达的影响,因此界面代理的情绪会直接影响学习者的情绪和动机。情绪反应理论认为如果教师的言语和非言语线索诱发了积极的情绪,学习者就会产生趋近学习的行为(例如,制定相应的学习计划)。多媒体学习认知情感理论强调了学习过程中情感和动机的重要性。基于多媒体学习认知情感理论,情感代理能唤起学习者的积极情绪,增加学习动机,进而提高学习成绩。而认知负荷理论和干扰理论却认为情感代理丰富的面部表情和手势动作可能会增加学习者的外部认知负荷,吸引学习者的注意力,减少对关键信息的注意,因此干扰学习效果。在上述理论的指导下,研究者们对情感代理的效果进行了探究,结果发现,情感代理可以有效地唤起学习者的积极情绪(d_积极情绪= 0.45),提高学习动机(d_内部动机= 0.52)。但不一定能影响认知负荷（d_{内部认知负荷} = -0.01;d_{外部认知负荷} = 0.09;d_{相关认知负荷} = 0.08）,并且在学习效果上的作用也比较微弱(d_保持 = 0.18;d_理解 = 0.32;d_迁移 = 0.14;d_联合 = 0.32)。情感代理在学习效果上的作用不稳健的原因可能是受到了潜在调节因素的影响。例如,学习者的个体特征（如,工作记忆能力和年级水平）、情感代理的类型、任务特征和测验时间等。总之,尽管目前关于情感代理的研究结果存在不一致,但整体而言,在积极情感代理条件下,学习者更加快乐,更有动力。因此,在教育实践中,教学设计者可以考虑为学习者呈现一个积极的教学代理以帮助他们更加快乐地学习。未来关于情感代理的研究需要继续关注情感代理的操纵和评定方法;探究影响情感代理效果的边界条件;考察情感代理影响学习背后的神经机制;提高情感代理研究的生态效度等。     

An intelligent facial expression recognition system with emotion intensity classification

Facial expressions play a crucial role in emotion recognition as compared to other modalities. In this work, an integrated network, which is capable of recognizing emotion intensity levels from facial images in real time using deep learning technique is proposed. The cognitive study of facial expressions based on expression intensity levels are useful in applications such as healthcare, coboting, Industry 4.0 etc. This work proposes to augment emotion recognition with 2 other important parameters, valence and emotion intensity. This helps in better automated responses by a machine to an emotion. The valence model helps in classifying emotion as positive and negative emotions and discrete model classifies emotions as happy, anger, disgust, surprise and neutral state using Convolution Neural Network (CNN). Feature extraction and classification are carried out using CMU Multi-PIE database. The proposed architecture achieves 99.1% and 99.11% accuracy for valence model and discrete model respectively for offline image data with 5-fold cross validation. The average accuracy achieved in real time for valance model and discrete model is 95% & 95.6% respectively. Also, this work contributes to build a new database using facial landmarks, with three intensity levels of facial expressions which helps to classify expressions into low, mild and high intensities. The performance is also tested for different classifiers. The proposed integrated system is configured for real time Human Robot Interaction (HRI) applications on a test bed consisting of Raspberry Pi and RPA platform to assess its performance.     

Human vs. supervised machine learning: Who learns patterns faster?

The capabilities of supervised machine learning (SML), especially compared to human abilities, are being discussed in scientific research and in the usage of SML. This study provides an answer to how learning performance differs between humans and machines when there is limited training data. We have designed an experiment in which 44 humans and three different machine learning algorithms identify patterns in labeled training data and have to label instances according to the patterns they find. The results show a high dependency between performance and the underlying patterns of the task. Whereas humans perform relatively similarly across all patterns, machines show large performance differences for the various patterns in our experiment. After seeing 20 instances in the experiment, human performance does not improve anymore, which we relate to theories of cognitive overload. Machines learn slower but can reach the same level or may even outperform humans in 2 of the 4 of used patterns. However, machines need more instances compared to humans for the same results. The performance of machines is comparably lower for the other 2 patterns due to the difficulty of combining input features.     

Efficiency and interactions of alerting,orienting and executive networks: The impact of imperative stimulus type

The Attention Network Test (ANT) generates measures of three attention networks: alerting, orienting and executive control. Arrows have been generally used as imperative stimuli in the different versions of this paradigm. However, it is unknown whether the directional nature of these stimuli can modulate the efficiency of the executive control and its interaction with alerting and orienting. We developed three ANT variants to examine attentional effects in response to directional and non-directional stimuli. Arrows (ANTI-A), colored fruits (ANTI-F) and black geometrical-shape (ANTI-G) were used as imperative stimuli (i.e., flanker stimuli). Data collected from fifty-two university students, in two experiments, showed that arrows stimuli produced a greater interference effect and a greater orienting effect as compared to the other stimuli. Moreover, only arrows modulated the interaction between executive control and orienting: a reduced flanker effect in spatially cued trials was only observed in ANTI-A. These results suggest that the directional value of the stimuli increases the conflict and modulates the efficiency of executive control and its interaction with orienting network.     

Properties of the size–weight illusion as shown by lines of subjective equality

We studied the size–weight illusion through comparative judgments. The experiment had two direct aims: to verify whether the relative contribution of size to apparent heaviness can differ for different stimulus sets, and to verify whether that contribution can differ for different methods of comparing two objects (consecutive vs. simultaneous weighing). Thirty university students participated. Results show that the relative contribution of size depends on stimulus set, but is independent of the method used for comparing objects. The first finding implies that a linear model cannot describe the integration of size and weight information in the illusion; the second finding is evidence for the low-level character of the integration process.     

Decision processes in temporal discrimination

The processing dynamics underlying temporal decisions and the response times they generate have received little attention in the study of interval timing. In contrast, models of other simple forms of decision making have been extensively investigated using response times, leading to a substantial disconnect between temporal and non-temporal decision theories. An overarching decision-theoretic framework that encompasses existing, non-temporal decision models may, however, account both for interval timing itself and for time-based decision-making. We sought evidence for this framework in the temporal discrimination performance of humans tested on the temporal bisection task. In this task, participants retrospectively categorized experienced stimulus durations as short or long based on their perceived similarity to two, remembered reference durations and were rewarded only for correct categorization of these references. Our analysis of choice proportions and response times suggests that a two-stage, sequential diffusion process, parameterized to maximize earned rewards, can account for salient patterns of bisection performance. The first diffusion stage times intervals by accumulating an endogenously noisy clock signal; the second stage makes decisions about the first-stage temporal representation by accumulating first-stage evidence corrupted by endogenous noise. Reward-maximization requires that the second-stage accumulation rate and starting point be based on the state of the first-stage timer at the end of the stimulus duration, and that estimates of non-decision-related delays should decrease as a function of stimulus duration. Results are in accord with these predictions and thus support an extension of the drift–diffusion model of static decision making to the domain of interval timing and temporal decisions.     

Prior and future withdrawal and performance: A meta-analysis of their relations in panel studies

While consensus exists among researchers that withdrawal and performance are related, the ordering of these constructs in proposed models frequently varies based on the theoretical focus of the study. Specifically, several extant well-being theories predict employee withdrawal will affect future performance while several turnover theories predict employee performance will affect future withdrawal. This study systematically addresses these complementary theories by conducting a meta-analysis of panel studies measuring both withdrawal and performance at two or more time periods. After accounting for sampling and measurement error, meta-analytic regression results indicate that performance is significantly negatively related to future withdrawal (ρ = − .19) even after accounting for prior withdrawal (β = − .03). However, the relationship between withdrawal and future performance (ρ = − .20) disappeared after accounting for prior performance (β = .00), although burnout did predict future performance even after accounting for prior performance (β = − .07).