Task Scenarios Research Articles

Mobile phone use is detrimental for gait stability in young adults.

Human walking is a highly automated motor task, however if the individual's attention is divided, gait can be negatively affected. Although the effect of divided attention has been usually tested with standardised cognitive tasks, the common task of walking while talking on the phone may represent an ecological dual task scenario. What is the effect of divided attention on locomotion when using a mobile phone? Thirty-seven healthy participants were asked to walk while performing different cognitive tasks: counting and spelling backwards, talking on the phone (handset by the ear and hands-free), and texting. As a control, extra postural conditions were tested: holding the phone by the ear (without talking) and carrying the phone as in the texting task. These tasks were compared with normal walking (no other cognitive or postural task). Twenty participants also performed the same tasks with the addition of an obstacle halfway through the walkway. Gait performance was measured using non-invasive inertial sensors. Step time and mediolateral acceleration range were calculated. Step time increased when counting (mean ± standard error 0.63 ± 0.02 s, p < 0.001), spelling backwards (0.67 ± 0.03 s, p < 0.001) and texting (0.61 ± 0.02 s, p = 0.005) compared to normal walking (0.56 ± 0.02 s). Compared to normal walking (8.03 ± 0.58 m/s2), mediolateral acceleration decreased when counting (6.43 ± 0.39 m/s2, p < 0.001), spelling backwards (6.67 ± 0.44 m/s2, p < 0.001), when talking on the phone while holding the phone (7.28 ± 0.48 m/s2, p = 0.003), or hands-free (7.28 ± 0.40 m/s2, p = 0.004), or texting (6.71 ± 0.50 m/s2, p < 0.001). Introducing an obstacle confirmed these results. This study shows that even in young and healthy individuals, gait is affected by divided attention. Furthermore, the results show that common and ecological cognitive tasks, such as phone use, could induce measurable worsening of gait performance. Individuals should be careful when walking and performing other tasks that could distract them, by dividing their attention.

The ability of personas: An empirical evaluation of altering incorrect preconceptions about users

False preconceptions about users can result in poor design, product development, and marketing decisions, so rectifying these preconceptions is essential for organizations. This research quantitatively evaluates the ability of data-driven personas to alter decision makers’ preconceptions about their online social media users. We conduct a within-participant experiment of 31 professionals carrying out a workplace task scenario. The participants’ conceptions of user attributes are recorded both before and after interacting with personas created from real user analytics data. Using statistical analysis to compare the responses, we find that personas had a significant effect on changing preconceptions about the audience segments. After interacting with personas, 81% of the participants changed their preconceptions of the audience, and 94% of the participants maintained or increased the accuracy of their perceptions of the audience after engaging with the personas. Moreover, the confidence of the participants in their responses increased. However, two participants did not change their preconceptions even when faced with contradictory factual information, which highlights the need for accompanying initiatives to align user preconceptions with user data fully.

Multivariate analysis of subjective evaluation of indoor lighting environment

Though subjective feelings affected by lighting have been studied a lot, multivariate experimental studies are lacking in this research field. Central composite rotatable design (CCRD) was applied to investigate the influence of illuminance, correlated color temperature (CCT) and illuminance uniformity on satisfaction in this study. A series of subject experiments were carried out and polynomial regression models of luminous satisfaction for different activity scenarios were generated. Illuminance and CCT affected the satisfaction significantly in visual task scenarios, and the effect of them was independent with each other, which was demonstrated by the regression model (R2 = 0.89). The variation of luminous satisfaction in general activity scenarios cannot be fully explained by the three investigated factors. The results contributed to the knowledge of multivariate analysis of luminous environment and indicated that much could be expected referring to the application of CCRD in this field.

Sensitive Physiological Indices of Pain Based on Differential Characteristics of Electrodermal Activity.

Electrodermal activity (EDA) has been widely used to assess human response to stressful stimuli, including pain. Recently, spectral analysis of EDA has been found to be more sensitive and reproducible for assessment of sympathetic arousal than traditional indices (e.g., tonic and phasic components). However, none of the aforementioned analyses incorporate the differential characteristics of EDA, which could be more sensitive to capturing fast-changing dynamics associated with pain responses. We have tested the feasibility of using the derivative of phasic EDA and the modified time-varying spectral analysis of EDA. Sixteen subjects underwent four levels of pain stimulation using electric stimulation. Five-second segments of EDA were used for each level of stimulation, and pre-stimulation segments were considered stimulation level 0. We used support vector machines with the radial basis function kernel and multi-layer perceptron for three different scenarios of stimulation-level classification tasks: five stimulation levels (four levels of stimulation plus no stimulation); low, medium, and high pain stimulation (stimulation levels 0-1, 2, and 3-4, respectively); and high stimulation levels (stimulation levels 3-4) vs. no stimulation. The maximum balanced accuracies were 44% (five stimulation levels), 63% (for low, medium, and high pain stimulation), and 87% (sensitivity 83% and specificity 89%, for high stimulation vs. no stimulation). The differential characteristics of EDA contributed highly to the accuracy of pain stimulation level detection of the classifiers. The external validity dataset was not considered in the study. Our approach has the potential for accurate pain quantification using EDA.

Muscle fatigue modelling: Solving for fatigue and recovery parameter values using fewer maximum effort assessments

A three-compartment controller model (3CC) predicts muscle fatigue development. Determination of fatigue (F) and recovery (R) model parameters is critical for model accuracy. Numerical methods can be used to determine parameter values using maximum voluntary contractions (MVCs) as input. We tested the effects of using reduced MVC data on parameter solutions using twenty published datasets of intermittent, isometric contractions. The work here examines three sampling variations using approximately half of the MVCs: MVC measurements distributed equally (dMVC), split between the initial and final times (sMVC), and only during the first half (fMVC). Furthermore, solved F and R parameters were used to model fatigue development for three hypothetical task scenarios. Both model parameters and predictions were statistically insensitive to measured data reduction using dMVC, followed closely by sMVC. However, using the fMVC reduction frequently resulted in overestimated parameter values and produced significantly larger prediction errors. We conclude that parameter solutions are robust when using fewer MVCs as long as they are sampled in a manner that captures later fatigue behavior.

Visual scanning strategies in the cockpit are modulated by pilots' expertise: A flight simulator study.

During a flight, pilots must rigorously monitor their flight instruments since it is one of the critical activities that contribute to update their situation awareness. The monitoring is cognitively demanding, but is necessary for timely intervention in the event of a parameter deviation. Many studies have shown that a large part of commercial aviation accidents involved poor cockpit monitoring from the crew. Research in eye-tracking has developed numerous metrics to examine visual strategies in fields such as art viewing, sports, chess, reading, aviation, and space. In this article, we propose to use both basic and advanced eye metrics to study visual information acquisition, gaze dispersion, and gaze patterning among novices and pilots. The experiment involved a group of sixteen certified professional pilots and a group of sixteen novice during a manual landing task scenario performed in a flight simulator. The two groups landed three times with different levels of difficulty (manipulated via a double task paradigm). Compared to novices, professional pilots had a higher perceptual efficiency (more numerous and shorter dwells), a better distribution of attention, an ambient mode of visual attention, and more complex and elaborate visual scanning patterns. We classified pilot's profiles (novices-experts) by machine learning based on Cosine KNN (K-Nearest Neighbors) using transition matrices. Several eye metrics were also sensitive to the landing difficulty. Our results can benefit the aviation domain by helping to assess the monitoring performance of the crews, improve initial and recurrent training and ultimately reduce incidents, and accidents due to human error.

Task assignment of multiple agricultural machinery cooperation based on improved ant colony algorithm

Task assignment is a key problem in multi-machine cooperative navigation. In the context of regional farmland operation, multiple agricultural machines often need to complete multiple tasks together. In order to realize the management of multiple agricultural machinery cooperation, studies on task assignment based on the improved ant colony algorithm have been conducted under the farmland operation environment. First, a task assignment model of multiple agricultural machinery cooperation was established by combining dynamic and static task assignments. Then, according to the task assignment model, the task assignment process based on the improved ant colony algorithm was established while considering the match between supply and demand, the operation capacity of the agricultural machinery, and the operation cycle and path cost. Finally, the dynamic and static task assignments of multiple agricultural machinery cooperation based on the improved ant colony algorithm were simulated on MATLAB. Taking the crop harvesting experiment as an example, according to the actual farmland location information of the Zhuozhou Experimental Farm, the different (agricultural machinery, task) combinations were set, and the task assignment results were compared and analyzed. Results showed that the path costs of harvester and grain transporters were reduced by 51.27% and 22.00% respectively, When the quantities of tasks were set to 11, indicating that the improved ant colony algorithm can effectively reduce the path cost. When the quantities of tasks were set to 5, 11, 16 and 22, the average operation cycles were shortened by 67.32%, 37.50%, 55.95%, and 56.37% respectively. The problem of “nearby” in the task assignment was solved to a certain extent, the overload of some agricultural machinery and the idle of other agricultural machinery were avoided, and the operation cycle was shortened. At the same time, based on the static task assignment, the dynamic task assignment was realized in the two scenarios of new tasks and malfunctioning harvesters, thus laying a foundation for further solving the scheduling management problem of multiple agricultural machinery cooperation under a complex farmland operation environment.

WITHDRAWN: Preliminary study of embedding two-level reinforcement learning to enhance the functionality of setting objectives compared with machine learning

The system designer needs to provide complete knowledge about the resources and ability, tasks and their particular implementation specifications in order to prepare the scenarios for tasks. For instance, hospitals need to follow stringent rules when planning doctors for COVID-19 patients so as to ensure that every patient receives adequate care while maintaining comfortable doctor planning. These concerns need to be profoundly learned, so that the impact of various mapping scenarios can be effectively analysed. An efficient asset mapping strategy task maximises the resource use under restrictions while reducing the time needed for a task which maximises the effectiveness of the task execution. A 2-stage strengthening training algorithm is proposed in this work for task planning. The algorithm uses a profoundly intensive learning phase to construct a deployable resource mapping strategy. Relevant execution breaks are reassessed and the plan is reassessed on the basis of the incremental learning from such break points. A real-time parametric testing of the resources and tasks is done in order to perform incremental learning and a new strategy is developed.

A Method for Run-Time Prediction of On-Chip Thermal Conditions in Dynamically Reconfigurable SOPCs

Autonomous mobile systems nowadays deploy FPGA-based System on Programmable Chips (SoPCs) for supporting their dynamic multitask multimodal workloads. For such field-deployed systems, activation times, execution periods of tasks, and variations in environmental conditions are usually difficult to predict. These dynamic variations result in a new challenge of dynamic thermal cycling stress on the SoPC die, which can result in transient and even permanent hardware faults in the computing system. This paper proposes the approach of run-time structural adaptation (RTSA) to mitigate dynamic thermal cycling stress on the SoPC dies. RTSA assumes the tasks to have multiple implementation variants, called Application Specific Processing (ASP) circuit variants, which vary in hardware resources, operating frequency, and power consumption. Dynamically reconfiguring appropriate ASP circuit variants of tasks allow systems to maintain their die temperature in the desired range while taking into account variations in power budget and modes of operation. This means the essence of RTSA is a decision-making mechanism which can select at run-time, a suitable system configuration (set of ASP circuit variants of active tasks), whenever needed, to meet the die temperature constraints. To do so, run-time die temperature prediction for potential system configurations using an estimation model is required. This paper presents a generic method to derive an analytical model for any SoPC that can estimate the die temperature in real time and thus support the decision-making mechanism. To develop this method, the thermal behavior of SoPC die under different task scenarios is studied and relation of die temperature to frequency, resource utilization, and power consumption is analyzed. An RTSA-enabled experimental platform is set up on Xilinx Zynq XC7Z020 SoPC for this purpose. Experimental results also demonstrate that the proposed method can be used to derive a model in run-time, thus enabling systems to self-derive and dynamically update the model in run-time.

Meta-Learning Based Dynamic Computation Task Offloading for Mobile Edge Computing Networks

Deep learning-based algorithms provide a promising solution to efficiently generate offloading decisions in mobile edge computing (MEC) networks. However, considering dynamic MEC devices or offloading tasks, most of them require large-scale training data and long training time to retrain the deep neural networks (DNNs). In this letter, we propose a MEta-Learning-based computation Offloading (MELO) algorithm for dynamic computation tasks in MEC networks. Specifically, it learns from historical MEC task scenarios and adapts to a new MEC task scenario with a few training samples. Numerical results show that the proposed algorithm can adapt to a new MEC task scenario and achieve 99% accuracy via 1-step fine-tuning using only 10 training samples.

Ensemble Bootstrapped Deep Deterministic Policy Gradient for Vision-Based Robotic Grasping

With sufficient practice, humans can grab objects they have never seen before through brain decision-making. However, the manipulators, which has a wide range of applications in industrial production, can still only grab specific objects. Because most of the grasp algorithms rely on prior knowledge such as hand-eye calibration results, object model features, and can only target specific types of objects. When the task scenario and the operation target change, it cannot perform effective redeployment. In order to solve the above problems, academia often uses reinforcement learning to train grasping algorithms. However, the method of reinforcement learning in the field of manipulators grasping mainly encounters these main problems: insufficient sample utilization, poor algorithm stability, and limited exploration. This article uses LfD, BC, and DDPG to improve sample utilization. Use multiple critics to integrate and evaluate input actions to solve the problem of algorithm instability. Finally, inspired by Thompson’s sampling idea, the input action is evaluated from different angles, which increases the algorithm’s exploration of the environment and reduces the number of interactions with the environment. EDDPG and EBDDPG algorithm is designed in the article. In order to further improve the generalization ability of the algorithm, this article does not use extra information that is difficult to obtain directly on the physical platform, such as the real coordinates of the target object and the continuous motion space at the end of the manipulator in the Cartesian coordinate system is used as the output of the decision. The simulation results show that, under the same number of interactions, the manipulators’ success rate in grabbing 1000 random objects has increased more than double and reached state-of-the-art(SOTA) performance.

A Bridge Neural Network-Based Optical-SAR Image Joint Intelligent Interpretation Framework

The current interpretation technology of remote sensing images is mainly focused on single-modal data, which cannot fully utilize the complementary and correlated information of multimodal data with heterogeneous characteristics, especially for synthetic aperture radar (SAR) data and optical imagery. To solve this problem, we propose a bridge neural network- (BNN-) based optical-SAR image joint intelligent interpretation framework, optimizing the feature correlation between optical and SAR images through optical-SAR matching tasks. It adopts BNN to effectively improve the capability of common feature extraction of optical and SAR images and thus improving the accuracy and application scenarios of specific intelligent interpretation tasks for optical-SAR/SAR/optical images. Specifically, BNN projects optical and SAR images into a common feature space and mines their correlation through pair matching. Further, to deeply exploit the correlation between optical and SAR images and ensure the great representation learning ability of BNN, we build the QXS-SAROPT dataset containing 20,000 pairs of perfectly aligned optical-SAR image patches with diverse scenes of high resolutions. Experimental results on optical-to-SAR crossmodal object detection demonstrate the effectiveness and superiority of our framework. In particular, based on the QXS-SAROPT dataset, our framework can achieve up to 96% high accuracy on four benchmark SAR ship detection datasets.

Federated personalized random forest for human activity recognition.

User data usually exists in the organization or own local equipment in the form of data island. It is difficult to collect these data to train better machine learning models because of the General Data Protection Regulation (GDPR) and other laws. The emergence of federated learning enables users to jointly train machine learning models without exposing the original data. Due to the fast training speed and high accuracy of random forest, it has been applied to federated learning among several data institutions. However, for human activity recognition task scenarios, the unified model cannot provide users with personalized services. In this paper, we propose a privacy-protected federated personalized random forest framework, which considers to solve the personalized application of federated random forest in the activity recognition task. According to the characteristics of the activity recognition data, the locality sensitive hashing is used to calculate the similarity of users. Users only train with similar users instead of all users and the model is incrementally selected using the characteristics of ensemble learning, so as to train the model in a personalized way. At the same time, user privacy is protected through differential privacy during the training stage. We conduct experiments on commonly used human activity recognition datasets to analyze the effectiveness of our model.

A Decision Control Method for Autonomous Driving Based on Multi-Task Reinforcement Learning

Following man-made rules in the traditional control method of autonomous driving causes limitations for intelligent vehicles under various traffic conditions that need to be overcome by incorporating machine learning-based method. The latter is inherently suitable for simple tasks of autonomous driving according to its limited characteristic under complex multi-lane traffic conditions. In this paper, a decision control method is proposed based on multi-task reinforcement learning to address the shortcomings of autonomous driving control under complex traffic conditions. Herein, the autonomous driving task is divided into several subtasks utilizing the proposed method to reduce the training time and improve traffic efficiency under complex multi-lane traffic condition. To ensure the efficiency and robustness of agent convergence to the optimal action space, an adaptive noise exploration method is designed for the subtasks with convex characteristics. Five-lane driving tasks scenarios embedded in Carla simulator have been conducted to verify the proposed method. The results of the simulation draw the conclusion that the proposed method increases the driving efficiency of intelligent vehicles under complex traffic conditions.

Review on existing VR/AR solutions in human–robot collaboration

During the last decades, there has been wide interest towards creating more agile and reconfigurable automation systems. This includes the research interest towards human–robot collaboration (HRC) solutions, where semi or fully automated process could be combined with human dexterity and flexibility without complexity and inflexibility. However, the communication between the human and the robot is not intuitive, fast or flexible yet. The emerging technologies such as Augmented Reality (AR), Virtual Reality (VR) and Mixed Reality (XR) are seen as good solution candidates for increasing the communication between human and the machine during the design, commission and operation phases. The design of the HRC system includes layout design evaluation, task scenario analysis, robot programming, cycle time calculations, and safety analysis. Virtual Reality and Augmented Reality technologies provide immersive experiences to visualize and analyze these procedures. This paper aims to review the current status of virtual and augmented reality solutions in HRC with meta-analysis and highlight missing elements. Finally, future research directions and requirements are presented.

A meta-analysis of the n-back task while driving and its effects on cognitive workload

This study investigates the effect of the n-back task on cognitive workload while driving. Results of 20 studies with over 800 participants in total show a moderate to high mean effect size. That means the n-back task varies cognitive load while driving in a substantial matter. Further analysis reveals several moderator variables: experiments conducted in a driving simulator showed larger effect sizes than on-road studies. This effect decreases with increasing driving simulator fidelity. Furthermore, the specific driving task assignment moderates the effect: lane change task scenarios result in higher effects than other situations. Regarding the different measurement methods of cognitive workload, subjective questionnaires seem to have very high sensitivity. In contrast, n-back performance measures, detection response task measures, and physiological measurements result in moderate effect sizes, and driving performance measures show reduced sensitivity. Regarding different implementations of the n-back task itself, surprisingly, no moderators are found. Overall, the findings highlight the suitability of the n-back task as a method of inducing cognitive load in transportation research. The moderator analysis gives an overview of different methodological designs and how these designs will affect effect sizes.

Usability of cooperative surgical telemanipulation for bone milling tasks

PurposeCooperative surgical systems enable humans and machines to combine their individual strengths and collaborate to improve the surgical outcome. Cooperative telemanipulated systems offer the widest spectrum of cooperative functionalities, because motion scaling is possible. Haptic guidance can be used to assist surgeons and haptic feedback makes acting forces at the slave side transparent to the operator, however, overlapping and masking of forces needs to be avoided. This study evaluates the usability of a cooperative surgical telemanipulator in a laboratory setting.MethodsThree experiments were designed and conducted for characteristic surgical task scenarios derived from field studies in orthopedics and neurosurgery to address bone tissue differentiation, guided milling and depth sensitive milling. Interaction modes were designed to ensure that no overlapping or masking of haptic guidance and haptic feedback occurs when allocating information to the haptic channel. Twenty participants were recruited to compare teleoperated modes, direct manual execution and an exemplary automated milling with respect to usability.ResultsParticipants were able to differentiate compact and cancellous bone, both directly manually and teleoperatively. Both telemanipulated modes increased effectiveness measured by the mean absolute depth and contour error for guided and depth sensitive millings. Efficiency is decreased if solely a boundary constraint is used in hard material, while a trajectory guidance and manual milling perform similarly. With respect to subjective user satisfaction trajectory guidance is rated best for guided millings followed by boundary constraints and the direct manual interaction. Haptic feedback only improved subjective user satisfaction.ConclusionA cooperative surgical telemanipulator can improve effectiveness and efficiency close to an automated execution and enhance user satisfaction compared to direct manual interaction. At the same time, the surgeon remains part of the control loop and is able to adjust the surgical plan according to the intraoperative situation and his/her expertise at any time.

Bond Graph Modeling and Kalman Filter Observer Design for an Industrial Back-Support Exoskeleton

This paper presents a versatile approach to the synthesis and design of a bond graph model and a Kalman filter observer for an industrial back-support exoskeleton. Actually, the main purpose of developing a bond graph model is to investigate and understand better the system dynamics. On the other hand, the design of the Kalman observer always should be based on a model providing an adequate description of the system dynamics; however, when back-support exoskeletons are considered, the synthesis of a state observer becomes very challenging, since only nonlinear models may be adopted to reproduce the system dynamic response with adequate accuracy. The dynamic modeling of the exoskeleton robotic platform, used in this work, comprises an electrical brushless DC motor, gearbox transmission, torque sensor and human trunk (biomechanical model). On this basis, a block diagram model of the dynamic system is presented and an experimental test has been carried out for identifying the system parameters accordingly. Both the block diagram and bond graph dynamic models are simulated via MATLAB and 20-sim software (bond graph simulation software) respectively. Furthermore, the possibility of employing the Kalman filter observer together with a suitable linear model is investigated. Subsequently, the performance of the proposed Kalman observer is evaluated in a lifting task scenario with the use of a linear quadratic regulator (LQR) controller with double integral action. Finally, the most important simulation results are presented and discussed.

Explicit instruction for the development of L2 Spanish pragmatic ability during study abroad

This study investigates the effects of pragmatic instruction and short-term study abroad (SA) on the development of apologies in second language (L2) Spanish. Students who spent four weeks in different SA programs in Spain were randomly assigned either to an experimental group (n = 9) or a control group (n = 9). Native Spanish speakers from Spain were recruited to provide baseline comparison data. Prior to departure, the experimental group received explicit pragmatic instruction on how to formulate apologies in Spanish. During SA, they performed two task scenarios designed to promote their pragmatic competence. The control group did not receive pragmatic instruction, nor did they perform the tasks. Before departure and during the final week of the program, both groups completed an oral discourse completion task (ODCT) consisting of five apology scenarios. The ODCT data and appropriateness ratings indicate that the experimental group significantly outperformed the control group in three areas of pragmatic development: appropriateness, strategy use, and speech rate. Findings suggest that explicit pragmatic instruction both before and during SA contributes to participants’ L2 pragmatic competence.

Edge Learning With Unmanned Ground Vehicle: Joint Path, Energy, and Sample Size Planning

Edge learning (EL), which uses edge computing as a platform to execute machine learning algorithms, is able to fully exploit the massive sensing data generated by Internet of Things (IoT). However, due to the limited transmit power at IoT devices, collecting the sensing data in EL systems is a challenging task. To address this challenge, this article proposes to integrate unmanned ground vehicle (UGV) with EL. With such a scheme, the UGV could improve the communication quality by approaching various IoT devices. However, different devices may transmit different data for different machine learning jobs and a fundamental question is how to jointly plan the UGV path, the devices’ energy consumption, and the number of samples for different jobs? This article further proposes a graph-based path planning model, a network energy consumption model, and a sample size planning model that characterizes F-measure as a function of the minority class sample size. With these models, the joint path, energy and sample size planning (JPESP) problem is formulated as a large-scale mixed-integer nonlinear programming (MINLP) problem, which is nontrivial to solve due to the high-dimensional discontinuous variables related to UGV movement. To this end, it is proved that each IoT device should be served only once along the path, thus the problem dimension is significantly reduced. Furthermore, to handle the discontinuous variables, a tabu search (TS)-based algorithm is derived, which converges in expectation to the optimal solution to the JPESP problem. Simulation results under different task scenarios show that our optimization schemes outperform the fixed EL and the full path EL schemes.