An empirical investigation into carpooling behaviour for sustainability

Carpooling is a sustainable, economical, and environmental friendly solution that can significantly reduce air pollution and traffic congestion in urban areas. In spite of its numerous benefits, commuters are still skeptic about adopting it as a routine choice for transportation. This study attempts to map commuters’ attitude towards carpooling services. The study has focused on a few motivational constructs that can have an influence on commuters’ behavior. The study has looked at the role of cognitive complexity and empowerment perceptions of commuters to check if these constructs significantly intervene in the behavioral outcomes. The methodology used is a scenario-based 2 × 2 survey design where the sample is an individual who has experience with carpooling. The survey has used two levels (high, low) each of cognitive complexity and psychological empowerment to give rise to four scenarios. The final sample consisted of 400 carpoolers selected from an IT park having more than 5000 employees. MANOVA analysis showed that cognitive complexity and psychological empowerment had significant influence on the motivational constructs used in the study. Value beliefs, safety and platform quality perceptions were found to have a direct impact on attitude formation and intention to engage in carpooling behavior. The findings offer many implications for managers in the sense that that they can focus on creating suitable communication that creates favorable perceptions towards carpooling to bring about better adoption intentions.     

Effect of advanced driver-assistance system trainings on driver workload,knowledge, and trust

Older adults are more likely to get severely injured or die in vehicle crashes. Advanced driver-assistance systems (ADAS) can reduce their risk of crashes; however, due to the lack of knowledge and training, usage rate of these systems among older drivers is limited. The objective of this study was to evaluate the impact of two ADAS training approaches (i.e., video-based and demonstration-based training) on older drivers’ subjective and objective measures of mental workload, knowledge and trust considering drivers’ demographic information. Twenty older adults, balanced by gender, participated in a driving simulation study. Results indicated that the video-based training might be more effective for females in reducing their mental workload while driving, whereas the demonstration-based training could be more beneficial for males. There was no significant difference between the video-based and demonstration-based trainings in terms of drivers’ trust and knowledge of automation. The findings suggested that ADAS training protocols can potentially be more effective if they are tailored to specific driver demographics.     

Distracted driving caused by voice message apps: A series of experimental studies

Hand-free voice message apps are frequently used by young people while driving. Previous studies have identified voice message apps as a common source of driving distraction. To quantitatively evaluate the factors contributing to driving distractions, three simulated driving experiments were designed using a dual-task experimental paradigm. In Experiment 1, participants completed several common tasks related to voice messages in WeChat with or without manual operations (perceptual-motor distraction). Experiments 2 and 3 further took into consideration the cognitive distraction level, measured by task difficulty and task frequency. The results showed that, in comparison with undistracted driving, the perceptual-motor distraction related to voice message app use significantly (ps < 0.05) weakened young drivers’ driving performance with respect to the standard deviation of lateral position (SDLP) between two cars (0.24 m), response time (0.21 s) and error rate (0.12) to turning lights, and collision percentage (0.54%), similar to the effects induced by non-voice-based apps. There were also significant differences (ps < 0.05) between driving with secondary tasks with and without continuous manual operations in the SDLP between two cars (0.19 m) and in the response time (0.18 s) and error rate (0.10) to turning lights, which indicates that the distracting effect produced by voice-message apps comes from the related manual operations. The effects of cognitive distraction on driving performance mainly depended on task difficulty level. High-difficulty secondary tasks via a voice message app significantly (ps < 0.05) weakened the driving performance in response time (by 0.13 s and 0.13 s compared to low-difficulty and baseline conditions, respectively) and error rate (by 0.07 and 0.07 compared to low-difficulty and baseline conditions, respectively) to turning lights and collision percentage (by 0.90% and 0.80% compared to low-difficulty and baseline conditions, respectively). The findings provide a theoretical reference for analysing the distracting components of voice messages and suggest that drivers should limit the use of these kinds of apps during driving.     

The self-reported causes of sleepiness in shift-working tram and truck drivers

Identifying the causes of sleepiness in various safety-critical work environments is necessary for implementing more efficient fatigue management strategies. In transportation, little is known about drivers’ own perceptions of these causes. Therefore, we instructed shift-working tram (n = 23) and long-haul truck drivers (n = 52) to report at the end of their shifts what made them sleepy if they felt so. These self-reports, measured on-duty sleepiness, and sleep amounts were recorded on every shift over a period of 2–3 weeks per driver. The causes of sleepiness were queried with smartphone applications and sleep logs. Sleepiness was measured with the Karolinska Sleepiness Scale (KSS) and sleep with wrist-worn actigraphs. Data were analyzed using generalized estimating equations. Sleep loss and insufficient rest breaks were commonly reported as causing sleepiness among the tram drivers, whereas time of day and sleep loss were the leading causes among the truck drivers. Other causes, such as traffic or cabin conditions, were not frequently mentioned. During morning, day, and evening shifts, the truck drivers were less likely to report insufficient rest breaks as causing sleepiness than the tram drivers. Similarly, during morning shifts, the truck drivers were less likely to attribute their sleepiness to sleep loss. In shifts with drives reporting severe sleepiness (KSS ≥ 7 at least once, 18–21% of shifts), sleep loss was significantly reported as causing sleepiness among both groups. Reporting insufficient rest breaks was associated with severe sleepiness among the tram drivers, whereas time of day showed the same among the truck drivers. The results highlight the need for addressing sleep-related fatigue in transportation and provide directions for future research with regard to secondary causes of sleepiness.     

Cognitive control models of multiple access IoT networks using LoRa technology

In this paper,we propose a random-access model for describing several wireless communication technologies. These networks have found application in the construction of wireless sensor networks, and the proposed model can be used for flows with different properties, considering the corresponding distribution functions. The model considers the technical features of the LoRa technology and subscriber traffic. We also address the management of random multiple wireless access in a Software-Defined Networking (SDN) like control architectures, and proposing a model for flows with different properties, considering the corresponding distribution functions. We develop a method for optimizing the parameters of an access network by the probability of data delivery. Then we describe the probability of bit error, frame loss, collision, and the choice of network parameters considering the heterogeneity of conditions for different users. Numerical results show the efficiency of our proposed scheme by maintaining the required network parameters in case of its function conditions changing.     

Cognitive Evaluation of Machine Learning Agents

Advances in applying statistical Machine Learning (ML) led to several claims of human-level or near-human performance in tasks such as image classification & speech recognition. Such claims are unscientific primarily for two reasons, (1) They incorrectly enforce the notion that task-specific performance can be treated as manifestation of General Intelligence and (2) They are not verifiable as currently there is no set benchmark for measuring human-like cognition in a machine learning agent. Moreover, ML agent’s performance is influenced by knowledge ingested in it by its human designers. Therefore, agent’s performance may not necessarily reflect its true cognition. In this paper, we propose a framework that draws parallels from human cognition to measure machine’s cognition. Human cognitive learning is quite well studied in developmental psychology with frameworks and metrics in place to measure actual learning. To either believe or refute the claims of human-level performance of machine learning agent, we need scientific methodology to measure its cognition. Our framework formalizes incremental implementation of human-like cognitive processes in ML agents with an implicit goal to measure it. The framework offers guiding principles for measuring, (1) Task-specific machine cognition and (2) General machine cognition that spans across tasks. The framework also provides guidelines for building domain-specific task taxonomies to cognitively profile tasks. We demonstrate application of the framework with a case study where two ML agents that perform Vision and NLP tasks are cognitively evaluated.     

An expanded model for perceptual visual single object recognition system using expectation priming following neuroscientific evidence

Under numerous circumstances, humans recognize visual objects in their environment with remarkable response times and accuracy. Existing artificial visual object recognition systems have not yet surpassed human vision, especially in its universality of application. We argue that modeling the recognition process in an exclusive feedforward manner hinders those systems’ performance. To bridge that performance gap between them and human vision, we present a brief review of neuroscientific data, which suggests that considering an agent’s internal influences (from cognitive systems that peripherally interact with visual-perceptual processes) recognition can be improved. Then, we propose a model for visual object recognition which uses these systems’ information, such as affection, for generating expectation to prime the object recognition system, thus reducing its execution times. Later, an implementation of the model is described. Finally, we present and discuss an experiment and its results.     

Declarative working memory: A bio-inspired cognitive architecture proposal

Memory is considered one of the most important functions since it allows us to code, store and retrieve knowledge. These qualities make it an indispensable function for a virtual creature. In general, memory can be classified based on the durability of the stored data in working memory and long-term memory. Working memory refers to the capacity to maintain temporarily a limited amount of information in mind, which can then be used to support various abilities, including learning, reasoning, planning and decision-making. Unlike short-term memory, working memory is not only a storage site, but it is also a framework of interacting processes that involve the temporary storage and manipulation of information in the service of performing complex cognitive activities. Declarative memory is a type of long-term memory related with the storage of facts and events. This research focuses on the development of a cognitive architecture for the type of working memory that maintains and manipulates declarative information. The construction of the model was grounded in theoretical evidence taken from cognitive sciences such as neuroscience and psychology, which gave us the components and their processes. The model was evaluated through a case study that covers the encoding, storing, and retrieval stages. Our hypothesis is that a virtual creature endowed with our working memory model will provide faster access to the information needed for the ongoing task. Therefore, it improves the planning and decision-making processes.     

A study on understanding cognitive states through gait analysis

In this work, we attempted to find out the relationship between different gait patterns and their corresponding cognitive states by using different statistical and machine learning approaches. This paper strongly focusses on the simulations followed by implementation of the proposed cognitive states i.e. (i) EmotionOriented State (EOS) (ii) Thinking Oriented State (TOS) (iii) Memory Oriented State(MOS) (iv) Simple Regular Oriented State (SROS). A novel approach was implemented by creating different environmental contexts for different gaits in our lab. An experimental method was performed to isolate movement artifact using Independent Component Analysis from recorded EEG(Electroencephalogram) signals. Measurement of joint angles from joint positions captured using Kinect V2 sensors was done with the help of OpenSim software. The relationship between different gaits and mental states was established using Pearsons Correlation Coefficient, ANOVA(Analysis of variance) and SVM(Support Vector Machine) classifier respectively. A strong relationship was found between them. The SVM classifier for the EOS and the non-EOS states based on joint angles inferred an accuracy of 81.08%. The ROC Curve for SVM classification depicted an AUC (area under the curve) of 0.9724.     

多级评分认知诊断模型述评

认知诊断评估旨在探讨个体内部的知识掌握结构,并提供关于学生优缺点的详细诊断信息,以促进个体的全面发展。当前研究者已开发了大量0-1评分的认知诊断模型,但对于多级评分认知诊断模型的研究还比较少。本文对已有的多级评分认知诊断模型进行了归纳,介绍了模型的假设,计量特征以及适用范围,为实际应用者和研究者在多级评分认知诊断模型的比较和选用上提供借鉴和参考。最后,对未来关于多级评分诊断模型的研究方向进行了展望。