A Review of Data Gathering Methods for Evaluating Socially Assistive Systems

Social interactions significantly impact the quality of life for people with special needs (e.g., older adults with dementia and children with autism). They may suffer loneliness and social isolation more often than people without disabilities. There is a growing demand for technologies to satisfy the social needs of such user groups. However, evaluating these systems can be challenging due to the extra difficulty of gathering data from people with special needs (e.g., communication barriers involving older adults with dementia and children with autism). Thus, in this systematic review, we focus on studying data gathering methods for evaluating socially assistive systems (SAS). Six academic databases (i.e., Scopus, Web of Science, ACM, Science Direct, PubMed, and IEEE Xplore) were searched, covering articles published from January 2000 to July 2021. A total of 65 articles met the inclusion criteria for this systematic review. The results showed that existing SASs most often targeted people with visual impairments, older adults, and children with autism. For instance, a common type of SASs aimed to help blind people perceive social signals (e.g., facial expressions). SASs were most commonly assessed with interviews, questionnaires, and observation data. Around half of the interview studies only involved target users, while the other half also included secondary users or stakeholders. Questionnaires were mostly used with older adults and people with visual impairments to measure their social interaction, emotional state, and system usability. A great majority of observational studies were carried out with users in special age groups, especially older adults and children with autism. We thereby contribute an overview of how different data gathering methods were used with various target users of SASs. Relevant insights are extracted to inform future development and research.

Trust with Autonomous Intelligence Systems to Promote Adoption in Assistive Technologies: A Literature Review

While advancements in machine learning are increasing rapidly, very little progress has been made in its mass adoption despite its benefits in assistive technologies for older adults. By examining how users interact with smart technologies, characteristics of trust can be identified and enhanced to increase adoption of the next generation of assistive systems. The current study conducted a literature review to understand better how trust with autonomous systems is formed and maintained. Twenty-two pertinent articles were identified in which three themes emerged. First, people tend to forgive human errors more than errors made by machines -- meaning mistrust is exaggerated when systems make mistakes. Second, the development of trust depends on how the system solves the tasks it is assigned, for instance if a user does not believe the system acted in an “ethical way,” distrust may form and the continuation of adoption is decreased. Lastly, trust depends on the situation and the risk/reward associated with using the system, for example the trust needed to board an autonomous plane differs from that for a simple grammar correction. Taken together, the black box ideology of autonomous systems may be an issue that prevents trust in them to be formed and maintained. Promising future directions are to create machine language translators that improve transparency of autonomous system behaviors (i.e., explainability). Even if assistive technologies are created to aid older adults -- the lack of focus on understanding the factors that foster trust may dampen their actual use.

Vision-Based Driver’s Cognitive Load Classification Considering Eye Movement Using Machine Learning and Deep Learning

Due to the advancement of science and technology, modern cars are highly technical, more activity occurs inside the car and driving is faster; however, statistics show that the number of road fatalities have increased in recent years because of drivers’ unsafe behaviors. Therefore, to make the traffic environment safe it is important to keep the driver alert and awake both in human and autonomous driving cars. A driver’s cognitive load is considered a good indication of alertness, but determining cognitive load is challenging and the acceptance of wire sensor solutions are not preferred in real-world driving scenarios. The recent development of a non-contact approach through image processing and decreasing hardware prices enables new solutions and there are several interesting features related to the driver’s eyes that are currently explored in research. This paper presents a vision-based method to extract useful parameters from a driver’s eye movement signals and manual feature extraction based on domain knowledge, as well as automatic feature extraction using deep learning architectures. Five machine learning models and three deep learning architectures are developed to classify a driver’s cognitive load. The results show that the highest classification accuracy achieved is 92% by the support vector machine model with linear kernel function and 91% by the convolutional neural networks model. This non-contact technology can be a potential contributor in advanced driver assistive systems.

Investigating socially assistive systems from system design and evaluation: a systematic review

Purpose The development of assistive technologies that support people in social interactions has attracted increased attention in HCI. This paper presents a systematic review of studies of Socially Assistive Systems targeted at older adults and people with disabilities. The purpose is threefold: (1) Characterizing related assistive systems with a special focus on the system design, primarily including HCI technologies used and user-involvement approach taken; (2) Examining their ways of system evaluation; (3) Reflecting on insights for future design research. Methods A systematic literature search was conducted using the keywords “social interactions” and “assistive technologies” within the following databases: Scopus, Web of Science, ACM, Science Direct, PubMed, and IEEE Xplore. Results Sixty-five papers met the inclusion criteria and were further analyzed. Our results showed that there were 11 types of HCI technologies that supported social interactions for target users. The most common was cognitive and meaning understanding technologies, often applied with wearable devices for compensating users’ sensory loss; 33.85% of studies involved end-users and stakeholders in the design phase; Four types of evaluation methods were identified. The majority of studies adopted laboratory experiments to measure user-system interaction and system validation. Proxy users were used in system evaluation, especially in initial experiments; 42.46% of evaluations were conducted in field settings, primarily including the participants’ own homes and institutions. Conclusion We contribute an overview of Socially Assistive Systems that support social interactions for older adults and people with disabilities, as well as illustrate emerging technologies and research opportunities for future work.

Emergence of flexible technology in developing advanced systems for post-stroke rehabilitation: a comprehensive review

Objective. Stroke is one of the most common neural disorders, which causes physical disabilities and motor impairments among its survivors. Several technologies have been developed for providing stroke rehabilitation and to assist the survivors in performing their daily life activities. Currently, the use of flexible technology (FT) for stroke rehabilitation systems is on a rise that allows the development of more compact and lightweight wearable systems, which stroke survivors can easily use for long-term activities. Approach. For stroke applications, FT mainly includes the “flexible/stretchable electronics”, “e-textile (electronic textile)” and “soft robotics”. Thus, a thorough literature review has been performed to report the practical implementation of FT for post-stroke application. Main results. In this review, the highlights of the advancement of FT in stroke rehabilitation systems are dealt with. Such systems mainly involve the “biosignal acquisition unit”, “rehabilitation devices” and “assistive systems”. In terms of biosignals acquisition, electroencephalography (EEG) and electromyography (EMG) are comprehensively described. For rehabilitation/assistive systems, the application of functional electrical stimulation (FES) and robotics units (exoskeleton, orthosis, etc.) have been explained. Significance. This is the first review article that compiles the different studies regarding flexible technology based post-stroke systems. Furthermore, the technological advantages, limitations, and possible future implications are also discussed to help improve and advance the flexible systems for the betterment of the stroke community.

Mechanical design and evaluation of an actuator and a simulator for trans-tibial and trans-femoral prostheses

This study proposes a joint simulator to evaluate new prosthesis designs prior to patient trials to minimize the inconveniences encountered in prosthesis applications for amputees. Design and prototype manufacturing of a force-controlled series elastic actuator was realized. In addition, actively controlled trans-tibial and trans-femoral amputation prostheses were designed by utilizing this actuator. A pneumatic joint simulator consisting of a proportional air pressure valve was also designed and manufactured. The experimental results demonstrated that good position tracking performances and effective assistive forces under the simulated walking conditions were achieved. The developed systems have the potential to contribute to the improvement of inadequate features of passive prostheses and to the development of new assistive systems that better respond to the needs of people with orthopedic disabilities.

Dynamic Task Allocation based on Individual Abilities - Experiences from Developing and Operating an Inclusive Assembly Line for Workers With and Without Disabilities

Digital assistive systems, enable workers with disabilities to perform complex industrial work. However, the previously presented systems considered only a single workplace and a single user. This paper presents an assembly line that enables a joint processing of complex tasks by multiple workers with and without disabilities. The aim was to investigate the use of interaction technologies such as in-situ projections and hand-tracking to enable the processing of complex assembly tasks by work teams with highly heterogeneous abilities. The developed assembly line assists users and coordinates the joint work by distributing single assembly steps to workers based on the individual workers' abilities. Besides presenting the concept and implementation of the assembly line, we report our findings after six months of operation. Our results indicate that using the assistive assembly line has positive impacts, such as increased satisfaction and independence of the workers combined with a higher productivity.

Attentional brain rhythms during prolonged cognitive activity

As routine and lower demand cognitive tasks are taken over by automated assistive systems, human operators are increasingly required to sustain cognitive demand over long periods of time. This has been reported to have long term adverse effects on cardiovascular and mental health. However, it remains unclear whether prolonged cognitive activity results in a monotonic decrease in the efficiency of the recruited brain processes, or whether the brain is able to sustain functions over time spans of one hour and more. Here, we show that during working sessions of one hour or more, contrary to the prediction of a monotonic decline, behavioral performance in both humans and non-human primates consistently fluctuates between periods of optimal and suboptimal performance at a very slow rhythm of circa 5 cycles per hour. These fluctuations are observed in both high attentional (in non-human primates) and low attentional (in humans) demand conditions. They coincide with fluctuations in pupil diameter, indicating underlying changes in arousal and information-processing load. Accordingly, we show that these rhythmic behavioral fluctuations correlate, at the neurophysiological level, with fluctuations in the informational attention orientation and perception processing capacity of prefrontal neuronal populations. We further identify specific markers of these fluctuations in LFP power, LFP coherence and spike-field coherence, pointing towards long-range rhythmic modulatory inputs to the prefrontal cortex rather than a local prefrontal origin. These results shed light on the resilience of brain mechanisms to sustained effort and have direct implications on how to optimize high cognitive demand working and learning environments.