Outlier-Resistant Remote State Estimation for Recurrent Neural Networks With Mixed Time-Delays.

In this brief, a new outlier-resistant state estimation (SE) problem is addressed for a class of recurrent neural networks (RNNs) with mixed time-delays. The mixed time delays comprise both discrete and distributed delays that occur frequently in signal transmissions among artificial neurons. Measurement outputs are sometimes subject to abnormal disturbances (resulting probably from sensor aging/outages/faults/failures and unpredictable environmental changes) leading to measurement outliers that would deteriorate the estimation performance if directly taken into the innovation in the estimator design. We propose to use a certain confidence-dependent saturation function to mitigate the side effects from the measurement outliers on the estimation error dynamics (EEDs). Through using a combination of Lyapunov-Krasovskii functional and inequality manipulations, a delay-dependent criterion is established for the existence of the outlier-resistant state estimator ensuring that the corresponding EED achieves the asymptotic stability with a prescribed H∞ performance index. Then, the explicit characterization of the estimator gain is obtained by solving a convex optimization problem. Finally, numerical simulation is carried out to demonstrate the usefulness of the derived theoretical results.

Animations in Cross-Platform Mobile Applications: An Evaluation of Tools, Metrics and Performance.

Along with the proliferation of high-end and performant mobile devices, we find that the inclusion of visually animated user interfaces are commonplace, but that research on their performance is scarce. Thus, for this study, eight mobile apps have been developed for scrutiny and assessment to report on the device hardware impact and penalties caused by transitions and animations, with an emphasis on apps generated using cross-platform development frameworks. The tasks we employ for animation performance measuring, are those of (i) a complex animation consisting of multiple elements, (ii) the opening sequence of a side menu navigation pattern, and (iii) a transition animation during in-app page navigation. We employ multiple performance profiling tools, and scrutinize metrics including frames per second (FPS), CPU usage, device memory usage and GPU memory usage, all to uncover the impact caused by executing transitions and animations. We uncover important differences in device hardware utilization during animations across the different cross-platform technologies employed. Additionally, Android and iOS are found to differ greatly in terms of memory consumption, CPU usage and rendered FPS, a discrepancy that is true for both the native and cross-platform apps. The findings we report are indeed factors contributing to the complexity of app development.

Back-of-Device Force Feedback Improves Touchscreen Interaction for Mobile Devices.

Touchscreen interaction suffers from occlusion problems as fingers can cover small targets, which makes interacting with such targets challenging. To improve touchscreen interaction accuracy and consequently the selection of small or hidden objects, we introduce a back-of-device force feedback system for smartphones. We introduce a new solution that combines force feedback on the back to enhance touch input on the front screen. The interface includes three actuated pins at the back of a smartphone. All three pins are driven by microservos and can be actuated up to a frequency of 50 Hz and a maximum amplitude of 5 mm. In a first psychophysical user study, we explored the limits of the system. Thereafter, we demonstrate through a performance study that the proposed interface can enhance touchscreen interaction precision, compared to state-of-the-art methods. In particular, the selection of small targets performed remarkably well with force feedback. The study additionally shows that users subjectively felt significantly more accurate with force feedback. Based on the results, we discuss back-to-front feedback design issues and demonstrate potential applications through several prototypical concepts to illustrate where the back-of-device force feedback could be beneficial.

Mobile three-dimensional visualisation technologies for clinician-led fall prevention assessments.

The assistive equipment provision process is routinely carried out with patients to mitigate fall risk factors via the fitment of assistive equipment within the home. However, currently, over 50% of assistive equipment is abandoned by the patients due to poor fit between the patient and the assistive equipment. This paper explores clinician perceptions of an early stage three-dimensional measurement aid prototype, which provides enhanced assistive equipment provision process guidance to clinicians. Ten occupational therapists trialled the three-dimensional measurement aid prototype application; think-aloud and semi-structured interview data was collected. Usability was measured with the System Usability Scale. Participants scored three-dimensional measurement aid prototype as 'excellent' and agreed strongly with items relating to the usability and learnability of the application. The qualitative analysis identified opportunities for improving existing practice, including, improved interpretation/recording measurements; enhanced collaborative practice within the assistive equipment provision process. Future research is needed to determine the clinical utility of this application compared with two-dimensional counterpart paper-based guidance leaflets.

Assessing pain intensity following spinal cord injury: should rating scales measure 'overall' or 'maximal' values?

Rating scales (RSs) are important for the assessment of pain intensity (PI) following a spinal cord injury (SCI). Using a Graphic Rating Scale, this pilot study measured an 'overall' level of PI repeated about every 2 h over 1 day and compared it with maximal PI scores reported previously. Patients were categorized into severity groups according to the overall Graphic Rating Scale score at initial assessment (T0). Eight men and six women (mean age 53.1; range 28-75) participated. Comparison of the overall PI scores and their changes over time with the maximal PI scores reported previously showed loss of patients in the severe group and less pronounced PI changes over time. Rating scales used in spinal cord injury services should measure maximal pain experienced 'right now' to eliminate potential averaging out of pain over time, which might allow physicians to assist patients in understanding their pain and begin their adjustment.

Pain management following new and long-standing spinal cord injury: a pilot study of changes in pain intensity experienced during the day.

The aim of the study was to examine variations in pain intensity during the day experienced by patients with spinal cord injury. Fourteen consecutive patients had clinical and demographic data recorded. Pain intensity was recorded using a Graphic Rating Scale (GRS) at 2-3-h intervals. Patients were grouped according to maximum GRS into mild and severe groups at assessment (T0). Changes of one-third in GRS were deemed clinically significant. Eight men and six women (mean age 53.1; SD 16.5; range 28-75) were studied. Seven patients with mild pain tended to deteriorate and those with severe pain to improve. Eight patients demonstrated clinically significant changes. These findings suggest inadequate pain control early morning for one group and increasing pain during the day for another. Use of such simple scores over time would enhance pain rehabilitation for all spinal cord injury patients. Usual GRS reporting may mask clinically significant, treatable, changes in pain.

Attitudes of patients toward adoption of 3D technology in pain assessment: qualitative perspective.

BACKGROUND: Past research has revealed that insufficient pain assessment could, and often, has negative implications on the provision of quality health care. While current available clinical approaches have proven to be valid interventions, they are expensive and can often fail in providing efficient pain measurements. The increase in the prevalence of pain calls for more intuitive pain assessment solutions. Computerized alternatives have already been proposed both in the literature and in commerce, but may lack essential qualities such as accuracy of the collected clinical information and effective patient-clinician interaction. In response to this concern, 3-dimensional (3D) technology could become the innovative intervention needed to support and improve the pain assessment process. OBJECTIVE: The purpose of this analysis was to describe qualitative findings from a study which was designed to explore patients' perceptions of adopting 3D technology in the assessment of their pain experience related to important themes that might positively or negatively influence the quality of the pain assessment process. METHODS: The perceptions of 60 individuals with some form of pain in the area of Greater London were collected through semi-structured interviews. Of the 60 respondents, 24 (43%) produced usable responses and were analyzed for content using principles of the grounded theory approach and thematic analysis, in order to gain insight into the participants' beliefs and attitudes towards adopting 3D technology in pain assessment. RESULTS: The analysis identified 4 high-level core themes that were representative of the participants' responses. These themes indicated that most respondents valued "the potential of 3D technology to facilitate better assessment of pain" as the most useful outcome of adopting a 3D approach. Respondents also expressed their opinions on the usability of the 3D approach, with no important concerns reported about its perceived ease of use. Our findings finally, showed that respondents appreciated the perceived clinical utility of the proposed approach, which could further have an influence on their intention to use it. CONCLUSIONS: These findings highlighted factors that are seen as essential for improving the assessment of pain, and demonstrated the need for a strong focus on patient-clinician communication. The participants of this analysis believed that the introduction of 3D technology in the process might be a useful mechanism for such a positive health care outcome. The study's findings could also be used to make recommendations concerning the potential for inclusion of 3D technology in current clinical pain tools for the purpose of improving the quality of health care.

An interactive 3-D application for pain management: Results from a pilot study in spinal cord injury rehabilitation.

Research on pain following spinal cord injury (SCI) has revealed that patients not only experience several types of pain that could prove to be challenging to address, but also that each individual can interpret such pain in different subjective ways. In this paper we introduce a 3-D system for facilitating the efficient management of pain, and thus, supporting clinicians in overcoming the aforementioned challenges. This system was evaluated by a cohort of 15 SCI patients in a pilot study that took place between July and October 2010. Participants reported their experiences of using the 3-D system in an adapted version of the System Usability Scale (SUS) questionnaire. Statistically significant results were obtained with regards to the usability and efficiency of the 3-D system, with the majority of the patients finding it particularly useful to report their pain. Our findings suggest that the 3-D system can be an efficient tool in the efforts to better manage the pain experience of SCI patients.

Evaluating the usability of a virtual reality-based Android application in managing the pain experience of wheelchair users.

Pain constitutes an important medical concern that can have severe implications to a wheelchair user's quality of life. Results from studies indicate that pain is a common problem in this group of individuals, having a reported frequency of always (12%) and everyday (33%). This incidence signifies the need for more applicable and effective pain management clinical tools. As a result, in this paper we present an Android application (PainDroid) that has been enhanced with Virtual Reality (VR) technology for the purpose of improving the management of pain. Our evaluation with a group of wheelchair users revealed that PainDroid demonstrated high usability among this population, and is foreseen that it can make an important contribution in research on the assessment and management of pain.

3-D pain drawings and seating pressure maps: relationships and challenges.

Mobility impaired people constitute a significant portion of the adult population, which often experience back pain at some point during their lifetime. Such pain is usually characterized by severe implications reflected on both their personal lives, as well as on a country's health and economic systems. The traditional 2-D representations of the human body often used can be limited in their ability to efficiently visualize such pain for diagnosis purposes. Yet, patients have been shown to prefer such drawings. However, considering that pain is a feeling or emotion that is subjective in nature, the pain drawings could be consequently regarded as a subjective means of communicating such pain. As a result, the study described in this paper proposes an alternative, which encompasses a 3-D pain visualization solution, developed in a previous work of ours. This alternative is complemented with the upcoming technique of pressure mapping for more objectivity in the pain data collection. The results of this study have shown that the proposed approach is a promising solution for the purpose intended, and it could generally prove to be a significant complementary method in the area of medical practice for the mobility impaired community.

A pilot study to examine the relationship of 3D pain drawings with objective measures in mobility impaired people suffering from low back-pain.

Over the years, an increasing number of the adult population suffers from some form of back pain during their lifetime, something that consecutively has a very important impact on a country's health, as well as economic systems. It is beyond dispute though, that pain is a feeling or emotion that is subjective in nature. Thus, traditional methods of measuring pain are consequently considered to be subjective in their ability to efficiently gather and communicate such pain measurements. As a result, the work presented in this paper attempts to address the aforementioned limitation by presenting a theoretical framework, in which back pain measurements are taken, and the hypothetical association with objective measures, performed with the upcoming technique of pressure mapping, are indicated. A pilot study on wheelchair users to examine our proposed framework was conducted, with results of this pilot study showing that it is a promising solution for the purpose intended, and that it could generally prove to be a significant complementary method for the back pain community.

Visualization of back pain data--a 3-D solution.

Traditional approaches to gathering and visualizing pain data rely on two-dimensional (2-D) human body models, where different types of sensation are recorded with various monochrome symbols. We propose an alternative that uses a three-dimensional (3-D) representation of the human body, which can be marked in color to visualize and record pain data.

A Jini-based solution for electronic prescriptions.

In most countries today, handwritten, paper-based medical prescriptions are the norm. While efforts have been made in the past and are being made at present to migrate toward electronic dispensation of prescriptions, these have generally omitted to incorporate ubiquitous computing technology in their proposed solutions. In this paper, we focus on this issue and describe a Jini-based prototypical solution for electronic prescriptions, which allows for their wireless transmission to in-range pharmacies and the augmentation of the service levels rendered to the user, with, for instance, information about queue lengths and estimated waiting times being provided to the patients. Clinical and user evaluation revealed that there were high levels of agreement as regards the prototype's effectiveness, ease of use, and usefulness.

Recording of time-varying back-pain data: a wireless solution.

Chronic back pain is a debilitating experience for a considerable proportion of the adult population, with a significant impact on countries' economies and health systems. While there has been increasing anecdotal evidence to support the fact that for certain categories of patients (such as wheelchair users), the back pain experienced is dynamically varying with time, there is a relative scarcity of data to support and document this observation, with consequential impact upon such patients' treatment and care. Part of the reason behind this state of affairs is the relative difficulty in gathering pain measurements at precisely defined moments in time. In this paper, we describe a wireless-enabled solution that collects both questionnaire and diagrammatic, visual-based data, via a pain drawing, which overcomes such limitations, enabling seamless data collection and its upload to a hospital server using existing wireless fidelity technology. Results show that it is generally perceived to be an easy-to-use and convenient solution to the challenges of anywhere/anytime data collection.