Double Tap Research Articles

SEMG-Based hand gestures classification using a semi-supervised multi-layer neural networks with Autoencoder

This work presents a semi-supervised multilayer neural network (MLNN) with an Autoencoder to develop a classification model for recognizing hand gestures from electromyographic (EMG) signals. Using a Myo armband equipped with eight non-invasive surface-mounted biosensors, raw surface EMG (sEMG) sensor data were captured corresponding to five hand gestures: Fist, Open hand, Wave in, Wave out, and Double tap. The sensor collected data underwent preprocessing, feature extraction, label assignment, and dataset organization for classification tasks. The model implementation, validation, and testing demonstrated its efficacy after incorporating synthetic sEMG data generated by an Autoencoder. In comparison to the state-of-the-art techniques from the literature, the proposed model exhibited strong performance, achieving accuracy of 99.68%, 100%, and 99.26% during training, validation, and testing, respectively. Comparatively, the proposed MLNN with Autoencoder model outperformed a K-Nearest Neighbors model established for comparative evaluation.

Understanding the influence of confounding factors in myoelectric control for discrete gesture recognition

Discrete myoelectric control-based gesture recognition has recently gained interest as a possible input modality for many emerging ubiquitous computing applications. Unlike the continuous control commonly employed in powered prostheses, discrete systems seek to recognize the dynamic sequences associated with gestures to generate event-based inputs. More akin to those used in general-purpose human-computer interaction, these could include, for example, a flick of the wrist to dismiss a phone call or a double tap of the index finger and thumb to silence an alarm. Moelectric control systems have been shown to achieve near-perfect classification accuracy, but in highly constrained offline settings. Real-world, online systems are subject to ‘confounding factors’ (i.e. factors that hinder the real-world robustness of myoelectric control that are not accounted for during typical offline analyses), which inevitably degrade system performance, limiting their practical use. Although these factors have been widely studied in continuous prosthesis control, there has been little exploration of their impacts on discrete myoelectric control systems for emerging applications and use cases. Correspondingly, this work examines, for the first time, three confounding factors and their effect on the robustness of discrete myoelectric control: (1) limb position variability, (2) cross-day use, and a newly identified confound faced by discrete systems (3) gesture elicitation speed. Results from four different discrete myoelectric control architectures: (1) Majority Vote LDA, (2) Dynamic Time Warping, (3) an LSTM network trained with Cross Entropy, and (4) an LSTM network trained with Contrastive Learning, show that classification accuracy is significantly degraded ( p< 0.05) as a result of each of these confounds. This work establishes that confounding factors are a critical barrier that must be addressed to enable the real-world adoption of discrete myoelectric control for robust and reliable gesture recognition.

Love Letters From the Future

The use of salvaged objects in post-apocalyptic narratives has primarily been addressed in relation to Evan Calder Williams’s concept of “salvagepunk”—a repurposing of objects in an idiosyncratic way that Williams sees as a form of capitalist critique. Such a reading, however, accommodates neither the frequent emphasis on the novelty or sublimity of such objects, nor their tendency to collapse into nostalgia and ultimately capitalist reification. Far more often than not, the break between pre-apocalyptic past and post-apocalyptic narrative present is less a profound rupture opening up the possibility of a reimagined Utopian future based on reconfigured social relations, and more an inconvenient and lamentable fissure that will eventually be bridged. Attending to a variety of primary texts such as Emily St. John Mandel’s Station Eleven (2014), David Macauley’s Motel of the Mysteries (1978), and Ruben Fleischer’s film, Zombieland: Double Tap (2019), this essay considers the ways in which salvaged items in post-apocalyptic narratives end up reaffirming the present status quo, once again proving the oft-cited maxim that it is easier to imagine the end of the world than an end to capitalism.

Electrophysiological Activity from the Eye Muscles, Cerebellum and Cerebrum During Reflexive (Classical Pavlovian) Versus Voluntary (Ivanov-Smolensky) Eye-Blink Conditioning

We report an experiment to investigate the role of the cerebellum and cerebrum in motor learning of timed movements. Eleven healthy human subjects were recruited to perform two experiments, the first was a classical eye-blink conditioning procedure with an auditory tone as conditional stimulus (CS) and vestibular unconditional stimulus (US) in the form of a double head-tap. In the second experiment, subjects were asked to blink voluntarily in synchrony with the double head-tap US preceded by a CS, a form of Ivanov-Smolensky conditioning in which a command or instruction is associated with the US. Electrophysiological recordings were made of extra-ocular EMG and EOG at infra-ocular sites (IO1/2), EEG from over the frontal eye fields (C3’/C4’) and from over the posterior fossa over the cerebellum for the electrocerebellogram (ECeG). The behavioural outcomes of the experiments showed weak reflexive conditioning for the first experiment despite the double tap but robust, well-synchronised voluntary conditioning for the second. Voluntary conditioned blinks were larger than the reflex ones. For the voluntary conditioning experiment, a contingent negative variation (CNV) was also present in the EEG leads prior to movement, and modulation of the high-frequency EEG occurred during movement. US-related cerebellar activity was prominent in the high-frequency ECeG for both experiments, while conditioned response-related cerebellar activity was additionally present in the voluntary conditioning experiment. These results demonstrate a role for the cerebellum in voluntary (Ivanov-Smolensky) as well as in reflexive (classical Pavlovian) conditioning.

“Actually, the psychological wounds are more difficult than physical injuries:” a qualitative analysis of the impacts of attacks on health on the personal and professional lives of health workers in the Syrian conflict

IntroductionAttacks on healthcare in armed conflict have far-reaching impacts on the personal and professional lives of health workers, as well as the communities they serve. Despite this, even in protracted conflicts such as in Syria, health workers may choose to stay despite repeated attacks on health facilities, resulting in compounded traumas. This research explores the intermediate and long-term impacts of such attacks on healthcare on the local health professionals who have lived through them with the aim of strengthening the evidence base around such impacts and better supporting them.MethodsWe undertook purposive sampling of health workers in northwest and northeast Syria; we actively sought to interview non-physician and female health workers as these groups are often neglected in similar research. In-depth interviews (IDIs) were conducted in Arabic and transcribed into English for framework analysis. We used an a priori codebook to explore the short- and long-term impacts of attacks on the health workers and incorporated emergent themes as analysis progressed.ResultsA total of 40 health workers who had experienced attacks between 2013 and 2020 participated in IDIs. 13 were female (32.5%). Various health cadres including doctors, nurses, midwives, pharmacists, students in healthcare and technicians were represented. They were mainly based in Idlib (39.5%), and Aleppo (37.5%) governorates. Themes emerged related to personal and professional impacts as well as coping mechanisms. The key themes include firstly the psychological harms, second the impacts of the nature of the attacks e.g. anticipatory stress related to the ‘double tap’ nature of attacks as well as opportunities related to coping mechanisms among health workers.ConclusionViolence against healthcare in Syria has had profound and lasting impacts on the health workforce due to the relentless and intentional targeting of healthcare facilities. They not only face the challenges of providing care for a conflict-affected population but are also part of the community themselves. They also face ethical dilemmas in their work leading to moral distress and moral injury. Donors must support funding for psychosocial support for health workers in Syria and similar contexts; the focus must be on supporting and enhancing existing context-specific coping strategies.

Exploring Visual Signifier Characteristics to Improve the Perception of Affordances of In-Place Touch Inputs

Touch screens supporting different inputs such as 'Tap', 'Dwell', 'Double Tap' and 'Force Press' are omnipresent in modern devices and yet this variety of interaction opportunities is rarely communicated to the user. Without visual signifiers, these potentially useful inputs remain unknown or underutilised. We propose a design space of visual signifier characteristics that may impact the perception of in-place one finger inputs. We generated 36 designs and investigated their perception in an online survey (N=32) and an interactive experiment (N=24). The results suggest that visual signifiers increase the perception of input possibilities beyond 'Tap', and reduce perceived mental effort for participants, who also prefer added visual signifiers over a baseline. Our work informs how future touch-based interfaces could be designed to better communicate in-place single finger input possibilities.

Single-tap Latency Reduction with Single- or Double- tap Prediction

Touch surfaces are widely utilized for smartphones, tablet PCs, and laptops (touchpad), and single and double taps are the most basic and common operations on them. The detection of single or double taps causes the single-tap latency problem, which creates a bottleneck in terms of the sensitivity of touch inputs. To reduce the single-tap latency, we propose a novel machine-learning-based tap prediction method called PredicTaps. Our method predicts whether a detected tap is a single tap or the first contact of a double tap without having to wait for the hundreds of milliseconds conventionally required. We present three evaluations and one user evaluation that demonstrate its broad applicability and usability for various tap situations on two form factors (touchpad and smartphone). The results showed PredicTaps reduces the single-tap latency from 150--500 ms to 12 ms on laptops and to 17.6 ms on smartphones without reducing usability.

Planning Queen Elizabeth II’s Visit to Bondi Beach in 1954

Planning Queen Elizabeth II’s Visit to Bondi Beach in 1954

Preliminary Study of Tactical-Level Interaction for Highly-Automated Vehicles: Its Application to Touchscreen Interface

In automated vehicles, drivers are only required to input high-level control commands. The conventional driver-vehicle interfaces (DVIs) such as steering wheel and pedals that function in operational level may not be utilized in higher levels of automation. A DVI that allows the driver to input tactical-level control commands, .e.g., lane change, by easily understanding a situation, would be potentially required for automated vehicles. We thus propose tactical-level-interaction (TLI) for lateral and longitudinal controlling of highly automated vehicles. In this study, we developed a touchscreen-based DVI that allows the driver to use touch gestures to input tactical control commands. The screen displays an augmented map including the ego vehicle rendered from the top view. The driver can instantly input a set of lateral commands by location-based TLI, e.g., lane changing, by designating a desired location on the map, e.g., lane, by double tapping and swiping. We performed experiments using a simulator to evaluate TLI compared with the operational- (OLI) and strategical-level interaction (SLI). The results show that TLI offers both the flexibility of OLI as well as comfort of SLI, and drivers prefer to use all three interaction methods depending on the driving environment.

P.54 Assessment of fine motor abilities using new touchscreen application, among children with spinal muscular atrophy (SMA)- a pilot study

Spinal muscular atrophy (SMA) is a genetic neurodegenerative disease characterized by severe muscle weakness and atrophy. Advances in novel drug therapies has changed dramatically the natural history of the disease and outcome measures are used to assess the clinical response to therapy. Recent research has given rise to a central issue regarding the low sensitivity and limited ability of standard SMA assessment tools in detecting the subtle changes in fine motor abilities, which occur following the use of those therapies. Furthermore, there is lack of standardized and ecological tools for assessment of fine motor abilities and changes in SMA patients' daily functions. The purpose of this study was to evaluate the use touchscreen app. as an assessment tool for detecting changes in the upper extremity (UE) motor functions among SMA patients as a response to the use of the genetic therapies. 14 patients aged 6- 23 years were recruited. Nine patients were diagnosed with SMA type 2 and five were diagnosed with SMA type 3. The patients were evaluated every six months. The study included assessment of fine motor functions, using the touchscreen app which included temporal (e.g. reaction times, duration) and accuracy (touch all corners, double tapping, drag items and pinch ability) tasks. Our preliminary tests results show that the App. is able to detect fine changes in the performance, mainly in the parameters of reaction time and duration in most of the tasks. The participants were highly motivated to use the App. comparing to standard tools and it was easy to use among all ages and types of SMA. The results of this pilot study may contribute to the new developing knowledge about the influence of the genetic therapies on motor functions of the UE in the SMA population. In addition, the results may help to establish assessments for SMA that are ecological and more sensitive in detecting changes in motor abilities and function in daily activities.

Targeting double-strand break indel byproducts with secondary guide RNAs improves Cas9 HDR-mediated genome editing efficiencies

Programmable double-strand DNA breaks (DSBs) can be harnessed for precision genome editing through manipulation of the homology-directed repair (HDR) pathway. However, end-joining repair pathways often outcompete HDR and introduce insertions and deletions of bases (indels) at the DSB site, decreasing precision outcomes. It has been shown that indel sequences for a given DSB site are reproducible and can even be predicted. Here, we report a general strategy (the “double tap” method) to improve HDR-mediated precision genome editing efficiencies that takes advantage of the reproducible nature of indel sequences. The method simply involves the use of multiple gRNAs: a primary gRNA that targets the wild-type genomic sequence, and one or more secondary gRNAs that target the most common indel sequence(s), which in effect provides a “second chance” at HDR-mediated editing. This proof-of-principle study presents the double tap method as a simple yet effective option for enhancing precision editing in mammalian cells.

Double tap, double trouble: Instagram, teachers, and profit

This qualitative study explores the performance of teacher agency amidst national financial and professional deficits in education and sheds light on the growing utilization of Instagram in elementary school contexts. To better understand teachers’ use of this social media platform, we examined the Instagram accounts of 12 highly popular and influential pre-K–6 teachers (i.e., teacher influencers). Data sources comprised over 600 visual and textual posts, which included images, captions, hashtags, and emojis, produced over 3 months in the spring of 2019. Using qualitative coding procedures that were recursive and emphasized the emergent nature of interpretation through a critical literacies framework, we documented the neoliberal teachers’ use of Instagram as a method of participation in a virtual community of practice and as a way to produce, commodify, and possibly profit from posts presented as curricula. Findings suggest that teacher influencers primarily used Instagram as a form of commodification and commerce, as educational content was promoted to users as well as methods of purchase via personal websites, Teachers Pay Teachers and other digital stores. Overall, the teacher influencers’ Instagram use revealed a convergence of complex and multiple discourses involving curriculum, racialized and/or gendered identities, and neoliberal production.

Reply to: Touchscreen Smartphone Interaction in Parkinson's Disease and Healthy Subjects on Out-Patient Clinics.

We thank López-Blanco et al1 for their interest in our recent findings on touchscreen skills in patients with Parkinson's disease (PD),2 highlighting the importance of this topic and the increased use of touchscreen devices in current society and in healthcare. In their own study, the authors did not find differences in touchscreen performance between PD patients on medication and healthy control subjects (HC) despite a variety of tasks used. Similar to our findings, timing parameters did not differ between groups when tapping and sliding in a single direction.2 In contrast, we found a significantly slower performance when sliding in multiple directions in PD patients compared to HC even when on medication and increased slowing of specific tasks when off. Moreover, PD patients had a worse tapping accuracy than HC on medication, similar to previous work.3, 4 López-Blanco et al1 ascribed these between-study discrepancies to touchscreen interface settings, disease characteristics, and the number of task repetitions. López-Blanco et al1 questioned the ecological meaning of the multi-direction sliding tests used in our study and the significance of touchscreen performance slowing for daily use. Multi-direction sliding on a touchscreen is a complex manipulation, which we believe is highly relevant for daily life. For instance, a touchscreen unlock trace requires sliding motions in multiple directions5 as do specific search functions on a smartphone. Although slower performance might not necessarily impede the efficient use of mobile devices, we contend that during daily tasks time constraints frequently cause stress and anxiety, for example, when having to find information quickly. As such, slowing is likely to affect patients' smartphone proficiency during functional tasks. Additionally, turning off an alarm requires fast responses, via double tapping or sliding a circle toward a target (test 3-4 of López-Blanco et al).1 Although neither study found between-group differences in inter-tap interval time and single sliding time when on medication, we expect that, particularly when off, PD patients will be hampered when turning off alarm clocks or medication reminders.2 When off medication, Wissel et al4 demonstrated a significantly slower inter-tap interval time than HC in PD patients with worse disease severity than included in our study. This predicts that more affected patients will experience even greater problems. We did not suggest that on the basis of our findings touchscreen technology should be disregarded in PD.2 Instead, we claimed that even basic touchscreen skills cannot be assumed to remain unaffected by the disease and that this needs to be taken into account. As medication only had limited effects, we also recommended developing training programs targeting touchscreen manipulations, which may become even more functionally useful than writing training programs with time. To conclude, we agree with López-Blanco et al1 that in future work laboratory touchscreen tests need to be extended to real life touchscreen manipulation tasks, requiring both motor and cognitive flexibility. Ideally, such study should include larger PD samples with more diverse motor and cognitive capacity. (1) Research Project: A. Conception, B. Organization, C. Execution; (2) Statistical Analysis: A. Design, B. Execution, C. Review and Critique; (3) Manuscript Preparation: A. Writing of the first draft, B. Review and Critique. J.D.V.: 1C, 2A, 2B, 3A A.N.: 1A, 2C, 3B E.N.: 1A, 1B, 1C, 2A, 2C, 3C This study was approved by the local ethics committee UZ/KU Leuven according to the code of Ethics of the World Medical Association (Declaration of Helsinki, version 2013, S61793). Before participation in the study, an informed consent form was signed after explanation of the study protocol. We confirm that we have read the Journal's position on issues involved in ethical publication and affirm that this work is consistent with those guidelines. The work presented in this manuscript was supported by the Research Foundation Flanders—FWO (12F4719N, 1,520,619 N, G0A5619N) and King Baudouin Foundation (J1811020-E003). The authors declare that there are no conflicts of interest relevant to this work. E.N. is a postdoctoral fellow funded by the Research Foundation Flanders—FWO (12F4719N).

Classification of hand gestures from forearm electromyogram signatures from support vector machine

&lt;p&gt;Robotic prosthetics is increasingly adopted as an enabling technology for amputees. These are vital not only for activities of daily living but to display expression and affection. A vital element to this system is an intelligent model that can identify signatures from the remaining limb that can be mapped to specific effector movements. Therefore, the study proposes the use of forearm electromyogram to classify between different types of hand gestures; fingers spread, wave out, wave in, fist, double tap, and relaxed state. Data are acquired from 32 subjects using Myo armband. Initially, a total of 248 time-and frequency-domain features are extracted from the eightchannel device. Neighborhood component analysis has reduced them to a total of fourteen features. A hand gesture classification model based on electromyogram signal has been successfully developed using support vector machine with overall accuracy of 97.4% for training, and 88.0% for testing.&lt;/p&gt;

Correlation between the Ability to Manipulate a Touchscreen Device and Hand Strength and Manual Dexterity among Community-Living Older Individuals.

Information regarding the relationship between the degree of hand function among the elderly as measured by traditional assessments and the ability to manipulate touchscreens is lacking. This study aimed to examine the correlation between the ability to manipulate a touchscreen device, as assessed using the touchscreen assessment tool (TATOO) (University of Haifa, Israel & Universetiy of Bologna, Italy), and hand strength and manual dexterity among independent community-living older individuals. Thirty-four community-living older adults (average age 79.4 ± 6.7 years) participated in single-session assessments lasting 45 min each. The assessment included hand strength measurement using the manual hand dynamometry and hydraulic pinch gauge, a functional dexterity test (FDT), and TATOO. No significant correlations were observed between most of the TATOO items (22 out of 26) and handgrip strength, pinch strength, and FDT results. Moderately significant correlations were demonstrated between the number of drag attempts in the “Drag to different directions” task and handgrip strength and manual dexterity (r value: −0.39, p value: 0.02; r value: 0.36, p value: 0.04, respectively). In addition, a moderately significant correlation was noted between the number of double taps and manual dexterity (r value: 0.32, p value: 0.07). These results indicate that more complex gestures that require greater accuracy (dragging task) or rapid movements (double tapping) are related to hand strength and manual dexterity. These results suggest that the manual gestures necessary for touchscreen operation entail unique and specific capabilities that are generally not captured by traditional tools. The clinical implication is that the hand function assessment toolbox should be expanded. Tools such as the TATOO should be used to capture skills required for touchscreen manipulation in the context of the modern digital milieu.

Working memory and handwriting and share a common resource: An investigation of shared attention

Working memory and writing share a common resource. The authors investigated whether increasing the complexity of a finger-tapping task while simultaneously performing a serial verbal recall task while writing would decrease performance for recall, writing fluency, and tapping speed. Participants completed three verbal serial recall tasks which incrementally increased attentional load. Participants recalled word lists after listening to words while, (1) producing pseudo-handwriting movements without finger tapping (no-tapping), (2) producing pseudo-handwriting movements while tapping with a single finger (single-tapping), (3) producing pseudo-handwriting movements while tapping with two fingers (double tapping). The results showed that the double tapping condition caused a decrease in performance for recall, handwriting fluency, and tapping speed compared to the no-tapping condition and the single tapping conditions. However, no differences occurred between the no-tapping condition and the single tapping conditions. The authors concluded that by incrementally increasing the complexity of a concurrent tapping task we can achieve a decrease in performance across multiple cognitive processes. The results provided support for a central pool of shared resources that are utilised by non-working memory tasks and those reliant on working memory. The observed decreases in cognitive performance were dependent on task complexity rather than just performing a secondary task. The findings have implications for how multi-tasking while taking notes is detrimental for memory retention and handwriting fluency.

‘Double Tap’ Gunshot Injury to the Head: A Case Report and Review

‘Double Tap’ Gunshot Injury to the Head: A Case Report and Review

Examining the usability of touchscreen gestures for adults with DS

This document is part of a global investigation that aims to establish best practices in usability testing of mobile applications, that fit the specific needs of persons with cognitive disabilities. The motivating factor is to improve the quality of life of people with special needs. As a first step, we want to discover what are the skills of people with DS (DS) when using a mobile device. Thanks to its direct manipulation interaction style, multi-touch technology is the ideal mechanism for learning activities with a view to the social inclusion of people with DS. This paper investigates the most common touchscreen gestures on commercial existing software. A commercial analysis was carried out to discover the touch screen gestures used by 103 free software Apps running on a mobile touch screen tablet of 11 where the applications run”. The commercial analysis showed that most applications support tap and drag operations on multi-touch technology. Additionally, the research sought to discover the adults with DS (19–54 years of age) ability to perform other gestures on multi-touch surfaces. A DS user skill study was performed to assess the ability of this user segment to interact with multi-touch surfaces. The analysis involved 53 participants, aged between 19 and 54 years, from two vocational training centers attended by people with DS in Madrid. Authors used the Gesture Games App for experimenting with multi-touch gestures such as tap, double tap, long press, drag, scale up, scale down, and one-finger rotation. Tap, double tap, and drag were the three gestures that the most participant could use. In contrast, participants had difficulty performing one-finger rotation and long press gesture. Our statistical analysis showed that the ability to perform each gesture was independent of gender, age group, and previous experience with touchscreen of a participant.

Action at a distance: Long-distance rate adaptation in event perception.

Viewers' perception of actions is coloured by the context in which those actions are found. An action that seems uncomfortably sudden in one context might seem expeditious in another. In this study, we examined the influence of one type of context: the rate at which an action is being performed. Based on parallel findings in other modalities, we anticipated that viewers would adapt to the rate at which actions were displayed at. Viewers watched a series of actions performed on a touchscreen that could end in actions that were ambiguous to their number (e.g., two separate "tap" actions versus a single "double tap" action) or identity (e.g., a "swipe" action versus a slower "drag"). In Experiment 1, the rate of actions themselves was manipulated; participants used the rate of the actions to distinguish between two similar, related actions. In Experiment 2, the rate of the actions that preceded the ambiguous one was sped up or slowed down. In line with our hypotheses, viewers perceived the identity of those final actions with reference to the rate of the preceding actions. This was true even in Experiment 3, when the action immediately before the ambiguous one was left unmodified. Ambiguous actions embedded in a fast context were seen as relatively long, while ambiguous actions embedded in a slow context were seen as relatively short. This shows that viewers adapt to the rate of actions when perceiving visual events.

Efficacy of Double Pop Blind TAP Block – Double-Blinded Randomized Controlled Study

Background: The transversus abdominis plane block (TAP block) in the petit triangle is being used since 2001 for analgesia by blocking the T6 to T12 nerves, which is devoid of the sympathetic blockade and has opioid-sparing effect during and after abdominal operations. The appropriateness and efficacy of using double pop blind transversus abdominis plane block were studied in abdominal surgeries using bupivacaine with butorphanol as additive. Subjects and Methods: A total of 78 adult patients of ASA I and II were included, who were to undergo laparoscopic cholecystectomy under general anesthesia. The control group patients received tramadol, diclofenac, and paracetamol in the perioperative period. The study group patients received TAP block by double pop blind technique after induction of anesthesia but before surgical incision as preemptive analgesia. The p-value, the mean and the confidence interval were calculated by using Student t-test with the use of online software by graphpad.com. Results: Each of the two groups had 39 patients, and none met the exclusion criteria. Patients of the study (TAP) group remained pain-free for a longer time by 439 (416 – 463) minutes more than the control (IV, Intravenous) group. Rescue analgesia in the study group was required 640 minutes after the end of the surgery, but in the control group, rescue analgesia was required earlier at 200 minutes only after the surgery. Conclusion: Double pop blind technique for TAP block is appropriate and without complications if done with carefulness as to avoid penetration of the blunted green needle beyond the fascia between the internal oblique and the transversus abdominis muscle.