User Subjective Evaluation Research Articles

Extending user control for image stylization using hierarchical style transfer networks

The field of neural style transfer refers to the re-rendering of content image while fusing the features of a style image. The recent studies either focus on multiple style transfer or arbitrary style transfer while using perceptual and fixpoint content losses in their respective network architectures. The aforementioned losses provide notable stylization results but lack the liberty of style control to the user. Consequently, the stylization results also compromise the preservation of details with respect to the content image. This work proposes the hierarchical style transfer network (HSTN) for the image stylization task that could provide the user with the liberty to control the degree of incurred style via denoising parameter. The HSTN incorporates the proposed fixpoint control loss that preserves details from the content image and the addition of denoising CNN network (DnCNN) and denoising loss for allowing the user to control the level of stylization. The encoder-decoder block, the DnCNN block, and the loss network block make the basic building blocks of HSTN. Extensive experiments have been carried out, and the results are compared with existing works to demonstrate the effectiveness of HSTN. The subjective user evaluation shows that the HSTN's stylization represents the best fusion of style and generates unique stylization results while preserving the content image details, which is evident by acquiring 12% better results than the second-best performing method. It has also been observed that the proposed work is amongst the studies that achieve the best trade-off regarding content and style classification scores, i.e. 37.64% and 60.27%, respectively.

The relation between barrier-free environment perception and campus commuting satisfaction.

The COVID-19 pandemic, which began in the last quarter of 2019, has had a significant impact on urban transportation. With increasing demand for urban transport, the internal roads and public spaces of university campuses play an important role in facilitating commuting and communication between various functional zones. While considerable research has been conducted on route planning, pedestrian-vehicle segregation, and safety management in the internal transportation environment of university campuses, empirical investigations exploring barrier-free inclusive campus environment design and the subjective evaluation of road and public space users in the aftermath of the COVID-19 pandemic are lacking. Recent developments in travel behavior models and positive psychology have led to an increased focus on the correlation among subjective perceptions, attitudes, emotions, and commuting satisfaction in urban transportation and planning design. To elucidate this relationship, a study was conducted on the new campus of Central South University in Changsha, Hunan Province, China. Using 312 valid samples, a structural equation model was constructed to analyse the relationship between commuting satisfaction and the barrier-free environment perception of university students regarding the internal transportation environment of the campus. The results revealed that individuals' instantaneous barrier-free environment perceptions and long-term established positive emotions had a significant positive effect on commuting satisfaction. Furthermore, positive emotions were found to mediate the relationship between commuting attitudes induced by COVID-19, barrier-free environment perceptions, and commuting satisfaction. The results of this study provide a theoretical basis for the necessity of accessibility design in the post-COVID era. In addition, this study considers the perspective of users to provide ideas for the planning and construction of barrier-free campus environments that are based on convenient and inclusive design.

Effects of Heuristic Type, User Interaction Level, and Evaluator’s Characteristics on Usability Metrics of Augmented Reality (AR) User Interfaces

Heuristic evaluation is a famous usability inspection method often used in the assessment of Augmented Reality (AR) systems. Usability heuristics can be characterized as general or specific to a domain. During comparative studies between a new and a traditional set of heuristics, the focus is often around performance metrics (number of problems, time, errors), and little attention is given to the experience itself (i.e., evaluator’s overall satisfaction toward utilization of the set of heuristics). In addition, limited research has been done on the application of heuristics to evaluate interfaces with different levels of interaction, along with how a longer set of low-level heuristics compares against a traditionally-sized set of high-level heuristics. In this study, recruited participants (mostly university students) performed a heuristic evaluation using either a set of 110 specific heuristics (SH) or a set of 23 general heuristics (GH) to evaluate two versions of an AR application, designed with a low and a high level of interactivity. Big Five personality traits, prior experience with AR or Virtual Reality systems, and various usability data (e.g., subjective ratings related to the usability of heuristics and AR application, number of unique problems, and severity ratings) were collected through questionnaires and utilized during statistical analysis. Results show that even though the employment of the set of GH produced higher overall satisfaction of evaluators, the set of SH resulted in a significantly larger number of unique usability problems. Furthermore, the more interactive version of the AR application was perceived by evaluators as the harder version to inspect, regardless of the set of heuristics utilized. Neuroticism and agreeableness traits were found with a significant impact on subjective usability ratings.

Soundscape Perception Preference in an Urban Forest Park: Evidence from Moon Island Forest Park in Lu’an City

Urban forest parks improve the environment by reducing noise, which can promote the development of physical and mental health. This study aimed to investigate the soundscape preferences of visitors in different spaces. It also provides practical suggestions for the study of urban green-space soundscapes. This study took the example of Moon Island Forest Park in Lu’an City, based on the questionnaire field survey that acquired public soundscape perception data. SPSS 26.0 was used to analyze five different spatial soundscape perception preferences in Moon Island Forest Park, starting from the subjective evaluation of users’ soundscape perception, based on user preference for different spatial sound source types. A one-way analysis of variance (ANOVA) was used and a separate analysis of soundscape preferences in each space was undertaken; the mean (SD) was also used to reveal the respondents’ preference for each sound-source perceptual soundscape. The study found that the five dimensions of different spaces were significantly correlated with sound perception preferences. First, the same sound source had different perceptual characteristics and differences in different functional areas. Second, different spatial features were influenced differently by typical sound sources. Third, in each functional area, water sound was the main sound source of positive impact and mechanical sound was the main source of negative impact. Mechanical sound had the greatest negative impact on the overall area. Overall, natural sound provided the most popular significant contribution to the soundscape preference; second was the human voice, and mechanical sound produced a negative effect. The results of these studies were analyzed from the perspective of soundscape characteristics in different spaces, providing a more quantitative basis for urban forest park soundscape design.

47‐2: Monocular Depth Perception Enhancement Based on Joint Shading/Contrast Model and Motion Parallax (JSM)

Stereoscopic 3D displays adopt a binocular depth cue to provide depth perception. However, users should be equipped with expensive special devices to appreciate depth perception based on the binocular depth cues. Also, visual fatigue induced by the stereoscopic display is still a challenging open problem. In order to overcome this limitation, this paper proposes a novel framework, JSM, to enhance monocular depth perception, significantly improving both depth volume perception and depth range perception. The proposed framework can not only provide an enhanced depth perception on any conventional 2D display devices, but also it can be applicable to the 3D display devices since it is complimentary for binocular depth cues. The qualitative evaluation, ablation study, and subjective user evaluation proved the advantages and practicability of the proposed framework.

Control Strategies for Gait Tele-Rehabilitation System Based on Parallel Robotics

Among end-effector robots for lower limb rehabilitation, systems based on Stewart–Gough platforms enable independent movement of each foot in six degrees of freedom. Nevertheless, control strategies described in recent literature have not been able to fully explore the potential of such a mechatronic system. In this work, we propose two novel approaches for controlling a gait simulator based on Stewart–Gough platforms. The first strategy provides the therapist direct control of each platform using movement data measured by wearable sensors. The following scheme is designed to improve the level of engagement of the patient by enabling a limited degree of control based on trunk inclination. Both strategies are designed to facilitate future studies in tele-rehabilitation settings. Experimental results have illustrated the feasibility of both control interfaces, either in terms of system performance or user subjective evaluation. Technical capacity to deploy in tele-rehabilitation was also verified in this work.

Augmented reality and mixed reality behavior navigation system for telexistence remote assistance

Considering the increased importance of telework systems in economies affected by COVID-19, telexistence technologies for remote guidance and navigation in general human activities are widely expected to prove beneficial in various applications, including plant maintenance, infrastructure inspection, and medical services. In prior work, we have proposed a behavior navigation system (BNS) using augmented reality (AR) and mixed reality (MR) technologies to provide remote assistance. Resembling a conventional gesture-based remote assistance system, our previously proposed motion guidance technology was designed to ensure that the motion of a non-expert user followed the motion of a remote expert sequentially and in a relatively accurate manner, similar to that of telexistence robots. As yet, the poor performance of head-mounted displays (HMDs) has presented major obstacles to the commercialization of BNSs. Enabled by the introduction of practical, modern HMDs, we present a novel BNS configuration and detail our implementation of the proposed system with an assessment of its performance. Experimental results show that compared to a conventional remote assistance system, our proposed approach achieved reduced working time, equal or increased task success rate (not statistically significant), and a higher subjective user evaluation.

A Pilot Study on Extending the SUS Survey: Early Results

The System Usability Scale (SUS) is a popular method to measure the subjective usability of a system, due largely to the simplicity and rapidity of both collecting and analyzing data. A drawback is that the SUS generates a single unidimensional usability score from 0-100. Several researchers have amassed larger datasets across multiple projects to allow for analysis on additional methods to glean insights from the SUS survey. Along these lines, we investigate the practical value of extending the SUS survey with additional items such as open text responses, and test underlying assumptions of how SUS results are interpreted. We found that while a lower SUS score does generally correlate to a stronger desire to modify the system, people generally want to make modifications to a system regardless of its usability. Further, we found that the amount of user feedback related to modifications to a system provided predicted subjective usability ratings.

Toward a comprehensive subjective evaluation of VoIP users’ quality of experience (QoE): a case study on Persian language

Toward a comprehensive subjective evaluation of VoIP users’ quality of experience (QoE): a case study on Persian language

Efficient Workload Allocation and User-Centric Utility Maximization for Task Scheduling in Collaborative Vehicular Edge Computing

By integrating Mobile Edge Computing (MEC) into vehicular networks, vehicular edge computing extends computing capability to the vehicular network edge and hosts services in close proximity of connected vehicles. Parked Vehicles (PVs) occupy a large portion of the global vehicle and have idle states and resources. They collaborate with the MEC servers for cooperative task processing. This gives rise to a new computing paradigm, called by Collaborative Vehicular Edge Computing (CVEC). In CVEC, we introduce an offloading service provider that deploys an MEC server and schedules PVs on demand to handle offloading tasks. Efficient workload allocation and user-centric utility maximization are studied to optimize the network-wide task scheduling. In dynamic environment, offloading destination of each task is determined in a probabilistic manner. When necessary, the offloading service provider represents an offloading user to design a contract based incentive mechanism for the PVs. Based on contract theory and prospect theory, we model the offloading user's subjective evaluations on the utility in computation offloading, and derive an optimal contract to maximize the subjective utility under information asymmetry. Finally, numerical results are provided to demonstrate the effectiveness and efficiency of our scheme.

Safe and intuitive manual guidance of a robot manipulator using adaptive admittance control towards robot agility

Key areas of robot agility include methods that increase capability and flexibility of industrial robots and facilitate robot re-tasking. Manual guidance can achieve robot agility effectively, provided that a safe and smooth interaction is guaranteed when the user exerts an external force on the end effector. We approach this by designing an adaptive admittance law that can adjust its parameters to modify the robot compliance in critical areas of the workspace, such as near and on configuration singularities, joint limits, and workspace limits, for a smooth and safe operation. Experimental validation was done with two tests: a constraint activation test and a 3D shape tracing task. In the first one, we validate the proper response to constraints and in the second one, we compare the proposed approach with different admittance parameter tuning strategies using a drawing task where the user is asked to guide the robot to trace a 3D profile with an accuracy or speed directive and evaluate performance considering path length error and execution time as metrics, and a questionnaire for user perception. Results show that appropriate response to individual and simultaneous activation of the aforementioned constraints for a safe and intuitive manual guidance interaction is achieved and that the proposed parameter tuning strategy has better performance in terms of accuracy, execution time, and subjective evaluation of users.

Recurrently-Trained Super-Resolution

We are motivated by the observation that for problems where inputs and outputs are in the same form such as in image enhancement, deep neural networks can be reinforced by retraining the network using a new target set to the output for the original target. As an example, we introduce a new learning strategy for super-resolution by recurrently training the same simple network. Unlike the existing self-trained SR, which involves a single stage of learning with multiple runs at test time, our method trains the same SR network multiple times with increasingly better targets requiring only a single inference at test time. At each stage of the proposed learning scheme, a new target for training is obtained by applying the most recently trained SR network to the original image and downscaling the resultant SR image to normalize the size. Even if downscaling is involved, we argue that the downscaled SR image acts as a better target compared to the old target. We could mathematically demonstrate that this process is similar to unsharp masking when it is linearly approximated and that this process makes the image sharper. However, unlike unsharp masking, the proposed recurrent learning tends to converge to a specific target. By retraining the existing network aiming at a more enhanced target, the proposed method can achieve a similar effect of applying SR multiple times without increasing implementation cost and inference time. To objectively verify the supremacy of our approach by experiments, we propose to use VIQET MOS, which does not require a reference image as a measure of image quality. As far as we know, our work of using an objective quality measure in image enhancement is the first one whose validity was verified by showing similar results to the actual user's subjective evaluation. The proposed recurrent learning scheme makes existing SR algorithms more useful by clearly improving the effect of SR. Codes are available at https://github.com/rtsr82/rtsr.git.

Analysis of interface usability evaluation using digital measurement tools

Based on the articles on interface usability collected by CNKI and Web of Science (WOS), the current research status, trends, and recommendations on interface usability were analyzed in terms of the number of articles published, literature sources, institutions, authors, and keywords by combining the CNKI and WOS bibliometric analysis tools and CiteSpace information visualization software. Using digital technology methods such as bibliometric analysis, data visualisation and knowledge mapping analysis, the following conclusions were drawn. Research on interface usability mainly focuses on usability testing and interface optimization. At present, the research methods of interface usability are relatively mature, and the evaluation direction of interface usability tends to combine the eye movement experiments, the subjective and objective evaluation of users. The use of digital tools to study the current situation, hotspots and trends in interface usability can provide advice and assistance in the design of relevant interfaces.

Realistic Speech-Driven Talking Video Generation with Personalized Pose

In this work, we propose a method to transform a speaker’s speech information into a target character’s talking video; the method could make the mouth shape synchronization, expression, and body posture more realistic in the synthesized speaker video. This is a challenging task because changes of mouth shape and posture are coupled with audio semantic information. The model training is difficult to converge, and the model effect is unstable in complex scenes. Existing speech-driven speaker methods cannot solve this problem well. The method proposed in this paper first generates the sequence of key points of the speaker’s face and body postures from the audio signal in real time and then visualizes these key points as a series of two-dimensional skeleton images. Subsequently, we generate the final real speaker video through the video generation network. We take a random sampling of audio clips, encode audio contents and temporal correlations using a more effective network structure, and optimize and iterate network outputs using differential loss and attitude perception loss, so as to obtain a smoother pose key-point sequence and better performance. In addition, by inserting a specified action frame into the synthesized human pose sequence window, action poses of the synthesized speaker are enriched, making the synthesis effect more realistic and natural. Then, the final speaker video is generated by the obtained gesture key points through the video generation network. In order to generate realistic and high-resolution pose detail videos, we insert a local attention mechanism into the key point network of the generated pose sequence and give higher attention to the local details of the characters through spatial weight masks. In order to verify the effectiveness of the proposed method, we used the objective evaluation index NME and user subjective evaluation methods, respectively. Experiment results showed that our method could vividly use audio contentsto generate corresponding speaker videos, and its lip-matching accuracy and expression postures are better than those of previous work. Compared with existing methods in the NME index and user subjective evaluation, our method showed better results.

The utility of haptic simulation in early restorative dental training: A scoping review.

Haptic dental simulators are becoming increasingly available in dental schools around the world; however, there is a paucity of evidence on their pedagogical effectiveness particularly in early dental training for the acquisition of the highly specific fine motor dental skills. A scoping review was performed to broadly map the available evidence and to detect knowledge gaps on the utility of haptic dental simulation in early dental training. The review is reported using the PRISMA-ScR guidelines. Eight bibliographic databases were searched: Web of Science, Scopus, MEDLINE via PubMed, Cochrane library, CENTRAL, ERIC, IEEE Xplore, and TRIP. Charted data were reported by clustering results according to study characteristics, research themes, research purpose, and type of validity evidence identified. The review process resulted in the inclusion of 36 studies published between 2009 and 2020. The majority of the studies were cross-sectional in design with short-term evaluation data. Of the studies included, 64% investigated commercially available haptic simulators, while 36% investigated experimental haptic simulators. The research themes identified were skill acquisition and transfer, task-specific haptic training, trainee level discrimination, feedback, subjective user evaluation, performance prediction, and human factors in haptic training. Short-term evaluation evidence from reviewed studies indicates the usefulness of the haptic simulators in early dental training. They complement the existing phantom head simulators by offering qualitatively different features. Further empirical research is needed to investigate the long-term impact of training with haptic dental simulators, to improve the availability of validation evidence and to enhance the results generalizability.

Alterations in surface EMG during gait in children with Fragile X Syndrome

This study aimed to characterize the biomechanical stresses in the neck and shoulder, self-reported discomfort, and usability by different target distance or size during augmented reality (AR) interactions. In a repeated-measures laboratory-based study, 20 participants (10 males) performed three standardized AR tasks (3-dimensional (3-D) cube, omni-directional pointing, and web-browsing tasks) with three target distances (0.3, 0.6, and 0.9 m from each participant denoted by near, middle, far targets) for the 3-D cube and omni-directional pointing tasks or three target sizes: small (30% smaller than default), medium (default: 1.0 × 1.1 m), and large (30% larger than default) for the web-browsing task. Joint angle, joint moment, muscle activity, self-reported discomfort and comfort in the neck and shoulders; and subjective usability ratings were measured. The results showed that shoulder angle (flexion and abduction), shoulder moment (flexion), middle deltoid muscle activity significantly increased as the target distance increased during the 3-D cube task (p's < 0.001). Self-reported neck and shoulder discomfort significantly increased after completing each task (p's < 0.001). The participants preferred the near to middle distance (0.3–0.6 m) or the medium to large window size due to task easiness (p's < 0.005). The highest task performance (speed) was occurred at the near distance or the large window size during the 3-D cube and web-browsing tasks (p's < 0.001). The results indicate that AR interactions with the far target distance (close to maximum reach envelop) may increase the risk for musculoskeletal discomfort in the shoulder regions. Given the increased usability and task performance, the near to middle distance (less than 0.6 m) or the medium to large window size (greater than 1.0 × 1.1 m) would be recommended for AR interactions.

Evaluation of the biomechanical stress in the neck and shoulders during augmented reality interactions

This study aimed to characterize the biomechanical stresses in the neck and shoulder, self-reported discomfort, and usability by different target distance or size during augmented reality (AR) interactions. In a repeated-measures laboratory-based study, 20 participants (10 males) performed three standardized AR tasks (3-dimensional (3-D) cube, omni-directional pointing, and web-browsing tasks) with three target distances (0.3, 0.6, and 0.9 m from each participant denoted by near, middle, far targets) for the 3-D cube and omni-directional pointing tasks or three target sizes: small (30% smaller than default), medium (default: 1.0 × 1.1 m), and large (30% larger than default) for the web-browsing task. Joint angle, joint moment, muscle activity, self-reported discomfort and comfort in the neck and shoulders; and subjective usability ratings were measured. The results showed that shoulder angle (flexion and abduction), shoulder moment (flexion), middle deltoid muscle activity significantly increased as the target distance increased during the 3-D cube task (p's < 0.001). Self-reported neck and shoulder discomfort significantly increased after completing each task (p's < 0.001). The participants preferred the near to middle distance (0.3–0.6 m) or the medium to large window size due to task easiness (p's < 0.005). The highest task performance (speed) was occurred at the near distance or the large window size during the 3-D cube and web-browsing tasks (p's < 0.001). The results indicate that AR interactions with the far target distance (close to maximum reach envelop) may increase the risk for musculoskeletal discomfort in the shoulder regions. Given the increased usability and task performance, the near to middle distance (less than 0.6 m) or the medium to large window size (greater than 1.0 × 1.1 m) would be recommended for AR interactions.

Identifying faults in the building system based on model prediction and residuum analysis

The energy efficiency of the building HVAC systems can be improved when faults in the running system are known. To this day, there are no cost-efficient, automatic methods that detect faults of the building HVAC systems to a satisfactory degree. This study induces a new method for fault detection that can replace a graphical, user-subjective evaluation of a building data measured on site with an automatic, data-based approach. This method can be a step towards cost-effective monitoring. For this research, the data from a detailed simulation of a residential case study house was used to compare a faultless operation of a building with a faulty operation. We argue that one can detect faults by analysing the properties of residuals of the prediction to the actual data. A machine learning model and an ARX model predict the building operation, and the method employs various statistical tests such as the Sign Test, the Turning Point Test, the Box-Pierce Test and the Bartels-Rank Test. The results show that the amount of data, the type and density of system faults significantly affect the accuracy of the prediction of faults. It became apparent that the challenge is to find a decision rule for the best combination of statistical tests on residuals to predict a fault.

The Official Journal of ATTD Advanced Technologies &amp; Treatments for Diabetes Conference Berlin, Germany—February 20–23, 2019

The Official Journal of ATTD Advanced Technologies &amp; Treatments for Diabetes Conference <i>Berlin, Germany—February 20–23, 2019</i>

The effect of illuminance and correlated colour temperature on perceived comfort according to reading behaviour in a capsule hotel

We investigated the effect of illuminance and correlated colour temperature (CCT) on the subjective evaluation of users' reading behaviour in a narrow space (i.e. a capsule hotel). Participants (N = 18; 15 men, 3 women; mean age = 21.9 years, SD = 0.4 years; age range = 21–23 years) were Japanese university students and graduate students. Experiments were conducted within four behavioural conditions that differed in six distinct illuminance (i.e. 150 lx and 300 lx) and CCT (i.e. 2800 K, 5000 K, and 6700 K) combinations. Because of the subjective evaluation of the space using the 7-level semantic differential method, participants did not experience pressure in the experimental space when it satisfied illumination standards. Sense of security was significantly influenced by CCT rather than illumination. Higher CCT was associated with higher spatial brightness. Lower CCT was associated with a higher sense of security, restfulness, and positive feelings. Brightness, sense of security, restfulness, feelings of fatigue, and concentration were all significantly impacted by the behavioural conditions. These findings suggest that providing a user-friendly and user-controlled lighting system will likely increase the satisfaction individuals experience when staying in a capsule room.