Publications
186 results found
Hodossy B, Guez A, Jing S, et al., 2024, Leveraging high-density EMG to investigate bipolar electrode placement for gait prediction models, IEEE Transactions on Human-Machine Systems, Vol: 54, Pages: 192-201, ISSN: 2168-2291
To control wearable robotic systems, it is critical to obtain a prediction of the user's motion intent with high accuracy. Surface electromyography (sEMG) recordings have often been used as inputs for these devices, however bipolar sEMG electrodes are highly sensitive to their location. Positional shifts of electrodes after training gait prediction models can therefore result in severe performance degradation. This study uses high-density sEMG (HD-sEMG) electrodes to simulate various bipolar electrode signals from four leg muscles during steady-state walking. The bipolar signals were ranked based on the consistency of the corresponding sEMG envelope's activity and timing across gait cycles. The locations were then compared by evaluating the performance of an offline temporal convolutional network (TCN) that mapped sEMG signals to knee angles. The results showed that electrode locations with consistent sEMG envelopes resulted in greater prediction accuracy compared to hand-aligned placements ( p < 0.01). However, performance gains through this process were limited, and did not resolve the position shift issue. Instead of training a model for a single location, we showed that randomly sampling bipolar combinations across the HD-sEMG grid during training mitigated this effect. Models trained with this method generalized over all positions, and achieved 70% less prediction error than location specific models over the entire area of the grid. Therefore, the use of HD-sEMG grids to build training datasets could enable the development of models robust to spatial variations, and reduce the impact of muscle-specific electrode placement on accuracy.
Ghosh AK, Catelli DS, Wilson S, et al., 2024, Multi-modal detection of fetal movements using a wearable monitor, Information Fusion, Vol: 103, ISSN: 1566-2535
The importance of Fetal Movement (FM) patterns as a biomarker for fetal health has been extensively argued in obstetrics. However, the inability of current FM monitoring methods, such as ultrasonography, to be used outside clinical environments has made it challenging to understand the nature and evolution of FM. A small body of work has introduced wearable sensor-based FM monitors to address this gap. Despite promises in controlled environments, reliable instrumentation to monitor FM out-of-clinic remains unresolved, particularly due to the challenges of separating FMs from interfering artifacts arising from maternal activities. To date, efforts have been focused almost exclusively on homogenous (single) sensing and information fusion modalities, such as decoupled acoustic or accelerometer sensors. However, FM and related signal artifacts have varying power and frequency bandwidths that homogeneous sensor arrays may not capture or separate efficiently. In this investigation, we introduce a novel wearable FM monitor with an embedded heterogeneous sensor suite combining accelerometers, acoustic sensors, and piezoelectric diaphragms designed to capture a broad range of FM and interfering artifact signal features enabling more efficient isolation of both. We further outline a novel data fusion architecture combining data-dependent thresholding and machine learning to automatically detect FM and separate it from signal artifacts in real-world (home) environments. The performance of the device and the data fusion architecture are validated using 33 h of at-home use through concurrent recording of maternal perception of FM. The FM monitor detected an impressive 82 % of maternally sensed FMs with an overall accuracy of 90 % in recognizing FM and non-FM events. Consistency of detection was strongest from 32 gestational weeks onwards, which overlaps with the critical FM monitoring window for stillbirth prevention. We believe the multi-modal sensor fusion approach presented i
Capstick A, Palermo F, Zakka K, et al., 2024, Digital remote monitoring for screening and early detection of urinary tract infections, npj Digital Medicine, Vol: 7, ISSN: 2398-6352
Urinary Tract Infections (UTIs) are one of the most prevalent bacterial infections in older adults and a significant contributor to unplanned hospital admissions in People Living with Dementia (PLWD), with early detection being crucial due to the predicament of reporting symptoms and limited help-seeking behaviour. The most common diagnostic tool is urine sample analysis, which can be time-consuming and is only employed where UTI clinical suspicion exists. In this method development and proof-of-concept study, participants living with dementia were monitored via low-cost devices in the home that passively measure activity, sleep, and nocturnal physiology. Using 27828 person-days of remote monitoring data (from 117 participants), we engineered features representing symptoms used for diagnosing a UTI. We then evaluate explainable machine learning techniques in passively calculating UTI risk and perform stratification on scores to support clinical translation and allow control over the balance between alert rate and sensitivity and specificity. The proposed UTI algorithm achieves a sensitivity of 65.3% (95% Confidence Interval (CI) = 64.3–66.2) and specificity of 70.9% (68.6–73.1) when predicting UTIs on unseen participants and after risk stratification, a sensitivity of 74.7% (67.9–81.5) and specificity of 87.9% (85.0–90.9). In addition, feature importance methods reveal that the largest contributions to the predictions were bathroom visit statistics, night-time respiratory rate, and the number of previous UTI events, aligning with the literature. Our machine learning method alerts clinicians of UTI risk in subjects, enabling earlier detection and enhanced screening when considering treatment.
Mancero Castillo CS, Atashzar F, Vaidyanathan R, 2023, 3D Muscle Networks based on Vibrational Mechanomyography, Journal of Neural Engineering, Vol: 20, ISSN: 1741-2552
Objective: Muscle network modeling maps synergistic control during complex motor tasks. Intermuscular coherence (IMC) is key to isolate synchronization underlying coupling in such neuromuscular control. Model inputs, however, rely on electromyography (EMG), which can limit the depth of muscle and spatial information acquisition across muscle fibers.
Approach: We introduce three-dimensional muscle networks based on vibrational mechanomyography (vMMG) and IMC analysis to evaluate the functional co-modulation of muscles across frequency bands in concert with the longitudinal, lateral, and transverse directions of muscle fibers. vMMG is collected from twenty subjects using a bespoke armband of accelerometers while participants perform four hand gestures. IMC from four superficial muscles (flexor carpi radialis, brachioradialis, extensor digitorum communis, and flexor carpi ulnaris) is decomposed using matrix factorization into three frequency bands.
We further evaluate the practical utility of the proposed technique by analyzing the network responses to various sensor-skin contact force levels, studying changes in quality, and discriminative power of vMMG.
Main Results: Results show distinct topological differences, with coherent coupling as high as 57% between specific muscle pairs, depending on the frequency band, gesture, and direction.
No statistical decrease in signal strength was observed with higher contact force.
Significance: Results support the usability vMMG as a tool for muscle connectivity analyses and demonstrate the use of IMC as a new feature space for hand gesture classification.
Comparison of spectrotemporal and muscle network properties between levels of force support the robustness of vMMG-based network models to variations in tissue compression. We argue three-dimensional models of vMMG-based muscle networks provide a new foundation for studying synergistic muscle activation, particularly in out-of-cli
Raposo de Lima M, Horrocks S, Daniels S, et al., 2023, The role of conversational AI in ageing and dementia care at home: a participatory study, 2023 32nd IEEE International Conference on Robot and Human Interactive Communication (RO-MAN), Publisher: IEEE, ISSN: 1944-9437
Conversational artificial intelligence (AI) technologies hold significant promise to support the independence,well-being and safety of older adults living with frailty ordementia at home. However, further studies are needed toidentify: 1) valuable scenarios of support, 2) desired interactivefeatures, and 3) key challenges preventing long-term adoptionand utility in dementia care. In this paper, we explore therole of conversational technology in ageing and dementia careat home. Using a community-based participatory approach, weengaged 20 stakeholders, including people with lived experienceof dementia and frailty, to understand preferences, perceivedbenefits and concerns about integrating conversational AIinto daily routines at home. We uncovered key roles of thetechnology, including support of daily functions, health monitoring, risk mitigation, and cognitive stimulation. We emphasizethe need for adapting interactions to different levels of userfamiliarity and progression of cognitive decline. We addressthe importance of the communication style and suggest carefuluse of open-ended questions with target populations. We furtherdiscuss feasibility considerations to overcome current barriersto adoption. Overall, this work proposes design guidelines toshape the future conceptualization and development of naturallanguage interactions to support dementia care at home.
Guez A, Hodossy B, Farina D, et al., 2023, Transferring gait predictors across EMG acquisition systems with domain adaptation, 2023 International Conference on Rehabilitation Robotics (ICORR), Publisher: Institute of Electrical and Electronics Engineers Inc., ISSN: 1945-7901
Lower limb assistive technology (e.g. exoskeletons) can benefit significantly from higher resolution information related to physiological state. High-density electromyography (HD-EMG) grids offer valuable spatial information on muscle activity; however their hardware is impractical, and bipolar electrodes remain the standard in practice. Exploiting information rich HD-EMG datasets to train machine learning models could help overcome the spatial limitations of bipolar electrodes. Unfortunately, differences in signal characteristics across acquisition systems prevent the direct transfer of models without a drop in performance. This study investigated Domain Adaptation (DA) to render EMG-based models invariant to different acquisition systems. This approach was evaluated using a Temporal Convolutional Network (TCN) that mapped EMG signals to the subject's knee angle, using HD-EMG as source data and Delsys bipolar EMG as target data. Furthermore, the feature extraction learnt by the TCN was also applied across muscle groups, evaluating the transferability of the sensor agnostic features. The DA implementation shows promise in both scenarios, with an average increase in accuracy (angular error normalised by the range of motion) of 7.36% for the Rectus Femoris, Biceps Femoris and Tibialis Anterior, as well as a cross-muscle performance increase of up to 10.80%. However, when the domain discrepancy is severe, the model is currently unable to generate a reliable walking trajectory due to inherent limitations related to the applied regression scheme and the chosen Mean Squared Error loss function. Therefore, future research should focus on exploring advanced loss functions and classification-based DA models that prioritise restoring key features of the gait.
Raposo de Lima M, Vaidyanathan R, Barnaghi P, 2023, Discovering behavioural patterns using conversational technology for in-home health and well-being monitoring, IEEE Internet of Things Journal, Vol: 10, Pages: 18537-18552, ISSN: 2327-4662
Advancements in conversational AI have createdunparalleled opportunities to promote the independence andwell-being of older adults, including people living with dementia(PLWD). However, conversational agents have yet to demonstratea direct impact in supporting target populations at home,particularly with long-term user benefits and clinical utility. Weintroduce an infrastructure fusing in-home activity data capturedby Internet of Things (IoT) technologies with voice interactionsusing conversational technology (Amazon Alexa). We collect 3103person-days of voice and environmental data across 14 households with PLWD to identify behavioural patterns. Interactionsinclude an automated well-being questionnaire and 10 topics ofinterest, identified using topic modelling. Although a significantdecrease in conversational technology usage was observed afterthe novelty phase across the cohort, steady state data acquisitionfor modelling was sustained. We analyse household activitysequences preceding or following Alexa interactions throughpairwise similarity and clustering methods. Our analysis demonstrates the capability to identify individual behavioural patterns,changes in those patterns and the corresponding time periods.We further report that households with PLWD continued usingAlexa following clinical events (e.g., hospitalisations), which offersa compelling opportunity for proactive health and well-beingdata gathering related to medical changes. Results demonstratethe promise of conversational AI in digital health monitoringfor ageing and dementia support and offer a basis for trackinghealth and deterioration as indicated by household activity, whichcan inform healthcare professionals and relevant stakeholdersfor timely interventions. Future work will use the bespokebehavioural patterns extracted to create more personalised AIconversations.
Parkinson M, Doherty R, Curtis F, et al., 2023, Using home monitoring technology to study the effects of traumatic brain injury in older multimorbid adults, Annals of Clinical and Translational Neurology, Vol: 10, Pages: 1688-1694, ISSN: 2328-9503
Internet of things (IOT) based in-home monitoring systems can passively collect high temporal resolution data in the community, offering valuable insight into the impact of health conditions on patients' day-to-day lives. We used this technology to monitor activity and sleep patterns in older adults recently discharged after traumatic brain injury (TBI). The demographics of TBI are changing, and it is now a leading cause of hospitalisation in older adults. However, research in this population is minimal. We present three cases, showcasing the potential of in-home monitoring systems in understanding and managing early recovery in older adults following TBI.
Martineau T, He S, Vaidyanathan R, et al., 2023, Hyper-parameter tuning and feature extraction for asynchronous action detection from sub-thalamic nucleus local field potentials, FRONTIERS IN HUMAN NEUROSCIENCE, Vol: 17, ISSN: 1662-5161
- Author Web Link
- Cite
- Citations: 1
Su T, Calvo RA, Jouaiti M, et al., 2023, Assessing a sleep interviewing chatbot to improve subjective and objective sleep: protocol for an observational feasibility study, JMIR Research Protocols, Vol: 12, Pages: 1-10, ISSN: 1929-0748
BACKGROUND: Sleep disorders are common among the aging population and people with neurodegenerative diseases. Sleep disorders have a strong bidirectional relationship with neurodegenerative diseases, where they accelerate and worsen one another. Although one-to-one individual cognitive behavioral interventions (conducted in-person or on the internet) have shown promise for significant improvements in sleep efficiency among adults, many may experience difficulties accessing interventions with sleep specialists, psychiatrists, or psychologists. Therefore, delivering sleep intervention through an automated chatbot platform may be an effective strategy to increase the accessibility and reach of sleep disorder intervention among the aging population and people with neurodegenerative diseases. OBJECTIVE: This work aims to (1) determine the feasibility and usability of an automated chatbot (named MotivSleep) that conducts sleep interviews to encourage the aging population to report behaviors that may affect their sleep, followed by providing personalized recommendations for better sleep based on participants' self-reported behaviors; (2) assess the self-reported sleep assessment changes before, during, and after using our automated sleep disturbance intervention chatbot; (3) assess the changes in objective sleep assessment recorded by a sleep tracking device before, during, and after using the automated chatbot MotivSleep. METHODS: We will recruit 30 older adult participants from West London for this pilot study. Each participant will have a sleep analyzer installed under their mattress. This contactless sleep monitoring device passively records movements, heart rate, and breathing rate while participants are in bed. In addition, each participant will use our proposed chatbot MotivSleep, accessible on WhatsApp, to describe their sleep and behaviors related to their sleep and receive personalized recommendations for better sleep tailored to their specific reasons for disrup
Mashrur FR, Rahman KM, Miya MTI, et al., 2023, An EEG-based Intelligent Neuromarketing System for Predicting Consumers’ Choice, Pages: 31-43, ISSN: 1876-1100
Marketers use different marketing strategies to elicit the desired response from the target customers. To measure customer engagement, they usually conduct one-on-one interviews, surveys, broad polls, and focus group discussions. However, these are costly and sometimes unreliable. On the other hand, neuromarketing measures customer response to marketing stimuli by measuring the electrical activity of the brain and has the potential to address these drawbacks. which can be overcome by neuromarketing. In this work, we proposed a prediction algorithm that can identify consumer affective attitude (AA) and purchase intention (PI) from EEG signals from the brain. At first, the raw EEG signals are initially preprocessed to remove noise. After that, three features are extracted: time, frequency, and time frequency domain features. Wavelet packet transform is used to separate the EEG bands in time-domain feature extraction. Then, for feature selection, wrapper-based SVM-RFE is utilized. Finally, we use SVM to distinguish the classes in AA and PI. Results show that for SVM with radial basis function kernel performs better to classify positive and negative AA with an accuracy of 90 ± 4.33 and PI with an accuracy of 75 ± 2.5. So, EEG-based neuromarketing solutions can assist companies and organizations in accurately predicting future consumer preferences. As a result, neuromarketing based-solutions have the potential to increase sales by overcoming the constraints of traditional marketing.
Guez A, Dhawan S, Vaidyanathan R, 2023, Echo-based dynamic trajectory generation for customised unilateral exoskeleton applications
For unilateral pathologies, effective rehabilitation relies on the use of a customised trajectory in order for the user to relearn a natural and symmetrical gait. In recent years, lower-limb exoskeletons have seen a growing interest due to their capacity to provide support and facilitate repetitive exercises while correcting the user's motion. However, in the context of robotic-assisted locomotion, the investigated trajectory models tend to rely on generating standardised walking patterns that lack step-specific customisation, and therefore do not account for the dynamic variations of natural gait.This paper investigates the viability of an echo-based approach for trajectory generation, which centres around the dynamic relabelling of a time-invariant reference trajectory, based on the motion of the contralateral leg. The presented cascaded network combines (1) a classifier that determines the gait phase performed by the sound leg and updates the reference trajectory accordingly, with (2) a regressor that uses electromyography inputs from the investigated leg to predict the gait cycle percentage performed, and provide the associated knee angle based on the dynamic reference.This trajectory generation framework was evaluated on 6 able-bodied subjects, using both steady-state and transient speeds. Despite some discrepancies in the range of motion, the produced knee angle trajectory strongly resembles the experimentally captured ones for both conditions, with an average mapping Root Mean Squared Error across subjects of 4.62°±0.39° for steady-state and 5.88°±1.83°for transient speeds. This proof-of-concept implementation demonstrates the potential of an echo-based approach for personalised dynamic trajectory generation in unilateral exoskeleton applications.
Jouaiti M, Kirby P, Vaidyanathan R, 2023, Matching Acoustic and Perceptual Measures of Phonation Assessment in Disordered Speech - A Case Study, Pages: 4508-4512, ISSN: 2308-457X
Speech/voice disorders are common in People Living with Dementia (PLwD). Fluctuations in speech quality can serve as biomarkers of cognitive deterioration but there is a gap in automated assessment of speech collected in unstructured environs. Our organisation has deployed Alexa in the households of 14 PLwD to track self-reported mental and physical state as well as use of language. In this work, we present a case study analysing highly variable speech over time, providing potential insights into cognitive changes. Alexa data gathered from the participant was manually annotated with speech assessment labels. Those labels are matched to openSMILE features by performing a feature importance analysis to isolate critical features that contribute to the perceptual ratings. We can assess phonation with a F1-score of 0.55, breathiness: 0.71, roughness: 0.60, asthenia: 0.65, strain: 0.74. This work is a first step towards automatic speech assessment to monitor cognitive impairment over time.
Mashrur FR, Rahman KM, Miya MTI, et al., 2023, Intelligent neuromarketing framework for consumers' preference prediction from electroencephalography signals and eye tracking, Journal of Consumer Behaviour, ISSN: 1472-0817
Neuromarketing uses brain-computer interface technology to understand customer preferences in response to marketing stimuli. Every year, marketing professionals spend over $750 Billion (US dollars) on traditional marketing, which is usually behavioral and subjective, focusing on self-reports acquired via questionnaires, focus groups, and depth interviews. Neuromarketing, on the other hand, promises to overcome such limitations. This work proposes a machine learning framework that incorporates multiple components (endorsement, offer, and slogan) in real advertisement to predict consumer preference from electroencephalography (EEG) signals. In addition, we also use eye-tracking data to visualize consumer viewing patterns according to both advertisement type and preference. EEG signals are collected from 22 healthy volunteers while viewing the real ads as stimuli. After preprocessing the signals, three-domain features are extracted (time, frequency, and time-frequency). Then, using wrapper-based approaches we choose best features which are later classified into strong and weak preferences using the support vector machine. The experimental results demonstrate the best performance using all the frontal channels with an accuracy of 96.97%, sensitivity of 96.30%, and specificity of 97.44%. Additionally, eye tracking data reveals that subjects substantially prefer an ad, when they first glance at the endorsement. In addition, people tend to blink their eyes less frequently while viewing ads with endorsements and strongly prefer these commercials too. Additionally, our work lays the door for deploying such a neuromarketing framework in a real-world context by employing consumer-grade EEG equipment. Therefore, it is evident that neuromarketing technology may assist brands and companies in accurately predicting future customer preferences.
Xiao B, Hong W, Wang Z, et al., 2023, Learning-Based Inverse Kinematics Identification of the Tendon-Driven Robotic Manipulator for Minimally Invasive Surgery, ISSN: 2162-4704
It is well-known that the tendon-driven robotic manipulator plays an important role in robotic-assisted minimally invasive surgery (MIS). However, due to the intrinsic nonlinearities, uncertainties, slack and hysteresis introduced by the tendon-driven actuation, the tendon-driven robotic manipulator is difficult to model and control when compared with the traditional actuation styles. To serve the modeling purpose, in this paper, the deep-learning-based intelligent modeling of inverse kinematics in the snake-like tendon-driven surgical instrument is presented. In the proposed approach the Deep Recurrent Neural Network (DRNN) with Long Short-Term Memory (LSTM) architecture is adopted to memorize and identify the nonlinear inverse kinematics of the tendon-driven surgical instrument through the history of the motor and tip positions. To collect highly reliable data to train the DRNN, the experiment to generate training data is carefully designed with the consideration of the stainless tendon characters and motor limitations. During the designed controller movements, the kinematics data is obtained by recording the motor positions and the tip positions. Besides, it is noticed that there are correlations of the sequential data samples, which could significantly reduce the modeling accuracy. To remove the correlations and improve the modeling performance, the correlations of the sequential data samples are removed by modifying the training processes. Modeling results and detailed discussions verified the effectiveness of the proposed approach.
Ishtiaque F, Mashrur FR, Miya MTI, et al., 2023, AI-based Consumers' Preference Prediction Using a Research-grade BCI and a Commercial-grade BCI for Neuromarketing: A Systematic Comparison
In Neuromarketing, BCI technology is used to analyze how a consumer behaves in response to a marketing stimulus, to evaluate the stimuli itself. Traditionally it can be achieved by different marketing research techniques such as questioner-based surveys, interviews, field surveys, etc. But since these procedures are time-consuming and prone to human error, neuromarketing promises a more advanced, automated, and accurate solution. Most of the neuromarketing solutions use research-grade EEG devices to analyze consumer preferences, but their effectiveness using consumer-grade EEG devices is unknown. In this study, we designed an experiment to compare a research-grade EEG device with a consumer-grade EEG device for predicting consumer preference stated as affective attitude (AA) and purchase intention (PI). We determined what type of setup, processing, and algorithm brings out the best result using the two devices. EEG signals were collected while the participants were shown pictures of different products in two different setups After that several signal-processing techniques were applied to remove artifacts and multi-domain features were extracted. 50 features were selected using Recursing Feature Elimination techniques. SMOTE was used to balance out the data. After that SVM classifier was used to classify Positive and Negative consumer preferences. With the first setup, we managed to achieve 82.4 % and 85.23 % accuracy for predicting purchase intention and affective attitude respectively with the research-grade EEG device whereas we achieved 75.43% and 79.5% accuracy with the commercial-grade EEG device. With the second setup, it's 78.75% and 83.75% using the research-grade EEG device whereas it's 75% and 82.97% using the commercial-grade EEG device for purchase intention and affective attitude respectively.
Lima MR, Wairagkar M, Gupta M, et al., 2022, Conversational affective social robots for ageing and dementia support, IEEE Transactions on Cognitive and Developmental Systems, Vol: 14, Pages: 1378-1397, ISSN: 2379-8920
Socially assistive robots (SAR) hold significant potential to assist older adults and people with dementia in human engagement and clinical contexts by supporting mental health and independence at home. While SAR research has recently experienced prolific growth, long-term trust, clinical translation and patient benefit remain immature. Affective human-robot interactions are unresolved and the deployment of robots with conversational abilities is fundamental for robustness and humanrobot engagement. In this paper, we review the state of the art within the past two decades, design trends, and current applications of conversational affective SAR for ageing and dementia support. A horizon scanning of AI voice technology for healthcare, including ubiquitous smart speakers, is further introduced to address current gaps inhibiting home use. We discuss the role of user-centred approaches in the design of voice systems, including the capacity to handle communication breakdowns for effective use by target populations. We summarise the state of development in interactions using speech and natural language processing, which forms a baseline for longitudinal health monitoring and cognitive assessment. Drawing from this foundation, we identify open challenges and propose future directions to advance conversational affective social robots for: 1) user engagement, 2) deployment in real-world settings, and 3) clinical translation.
Jing S, Huang H-Y, Vaidyanathan R, et al., 2022, Accurate and Robust Locomotion Mode Recognition Using High-Density EMG Recordings from a Single Muscle Group., Annu Int Conf IEEE Eng Med Biol Soc, Vol: 2022, Pages: 686-689
Existing methods for human locomotion mode recognition often rely on using multiple bipolar electrode sensors on multiple muscle groups to accurately identify underlying motor activities. To avoid this complex setup and facilitate the translation of this technology, we introduce a single grid of high-density surface electromyography (HDsEMG) electrodes mounted on a single location (above the rectus femoris) to classify six locomotion modes in human walking. By employing a neural network, the trained model achieved average recognition accuracy of 97.7% with 160ms latency, significantly better than the model trained with one bipolar electrode pair placed on the same muscle (71.4% accuracy). To further exploit the spatial and temporal information of HDsEMG, we applied data augmentation to generate artificial data from simulated displaced electrodes, aiming to counteract the influence of electrode shifts. By employing a convolutional neural network with the enhanced dataset, the updated model was not strongly affected by electrode misplacement (93.9% accuracy) while models trained by bipolar electrode data were significantly disrupted by electrode shifts (29.4% accuracy). Findings suggest HDsEMG could be a valuable resource for mapping gait with fewer sensor locations and greater robustness. Results offer future promise for real-time control of assistive technology such as exoskeletons.
Hopkins M, Turner S, McGregor A, 2022, Mapping lower-limb prosthesis load distributions using a low-cost pressure measurement system, Frontiers in Medical Technology, Vol: 4, Pages: 1-9, ISSN: 2673-3129
Background: In the UK 55,000 people live with a major limb amputation. The prosthetic socket is problematic for users in relation to comfort and acceptance of the prosthesis; and is associated with the development of cysts and sores.Objectives: We have developed a prototype low-cost system combining low-profile pressure sensitive sensors with an inertial measurement unit to assess loading distribution within prosthetic sockets. The objective of this study was to determine the ability of this prototype to assess in-socket loading profiles of a person with an amputation during walking, with a view to understanding socket design and fit.Methods: The device was evaluated on four transtibial participants of various age and activity levels. The pressure sensors were embedded in the subject's sockets and an inertial measurement unit was attached to the posterior side of the socket. Measurements were taken during level walking in a gait lab.Results: The sensors were able to dynamically collect data, informing loading profiles within the socket which were in line with expected distributions for patellar-tendon-bearing and total-surface-bearing sockets. The patellar tendon bearing subject displayed loading predominately at the patellar tendon, tibial and lateral gastrocnemius regions. The total-surface bearing subjects indicated even load distribution throughout the socket except in one participant who presented with a large socket-foot misalignment.Conclusions: The sensors provided objective data showing the pressure distributions inside the prosthetic socket. The sensors were able to measure the pressure in the socket with sufficient accuracy to distinguish pressure regions that matched expected loading patterns. The information may be useful to aid fitting of complex residual limbs and for those with reduced sensation in their residual limb, alongside the subjective feedback from prosthesis users.
Nazneen T, Islam IB, Sajal MSR, et al., 2022, Recent trends in non-invasive neural recording based brain-to-brain synchrony analysis on multidisciplinary human interactions for understanding brain dynamics: a systematic review, Frontiers in Computational Neuroscience, Vol: 16, Pages: 1-19, ISSN: 1662-5188
The study of brain-to-brain synchrony has a burgeoning application in the brain-computer interface (BCI) research, offering valuable insights into the neural underpinnings of interacting human brains using numerous neural recording technologies. The area allows exploring the commonality of brain dynamics by evaluating the neural synchronization among a group of people performing a specified task. The growing number of publications on brain-to-brain synchrony inspired the authors to conduct a systematic review using the PRISMA protocol so that future researchers can get a comprehensive understanding of the paradigms, methodologies, translational algorithms, and challenges in the area of brain-to-brain synchrony research. This review has gone through a systematic search with a specified search string and selected some articles based on pre-specified eligibility criteria. The findings from the review revealed that most of the articles have followed the social psychology paradigm, while 36% of the selected studies have an application in cognitive neuroscience. The most applied approach to determine neural connectivity is a coherence measure utilizing phase-locking value (PLV) in the EEG studies, followed by wavelet transform coherence (WTC) in all of the fNIRS studies. While most of the experiments have control experiments as a part of their setup, a small number implemented algorithmic control, and only one study had interventional or a stimulus-induced control experiment to limit spurious synchronization. Hence, to the best of the authors' knowledge, this systematic review solely contributes to critically evaluating the scopes and technological advances of brain-to-brain synchrony to allow this discipline to produce more effective research outcomes in the remote future.
Mashrur FR, Rahman KM, Miya MTI, et al., 2022, An intelligent neuromarketing system for predicting consumers' future choice from electroencephalography signals, Physiology and Behavior, Vol: 253, Pages: 1-9, ISSN: 0031-9384
Neuromarketing utilizes Brain-Computer Interface (BCI) technologies to provide insight into consumers responses on marketing stimuli. In order to achieve insight information, marketers spend about $400 billionannually on marketing, promotion, and advertisement using traditional marketing research tools. In addition,these tools like personal depth interviews, surveys, focus group discussions, etc. are expensive and frequentlycriticized for failing to extract actual consumer preferences. Neuromarketing, on the other hand, promises toovercome such constraints. In this work, an EEG-based neuromarketing framework is employed for predictingconsumer future choice (affective attitude) while they view E-commerce products. After preprocessing, threetypes of features, namely, time, frequency, and time-frequency domain features are extracted. Then, wrapperbased Support Vector Machine-Recursive Feature Elimination (SVM-RFE) along with correlation bias reduction is used for feature selection. Lastly, we use SVM for categorizing positive affective attitude and negativeaffective attitude. Experiments show that the frontal cortex achieves the best accuracy of 98.67 ± 2.98,98 ± 3.22, and 98.67 ± 3.52 for 5-fold, 10-fold, and leave-one-subject-out (LOSO) respectively. In addition,among all the channels, Fz achieves best accuracy 90 ± 7.81, 90.67 ± 9.53, and 92.67 ± 7.03 for 5-fold, 10-fold,and LOSO respectively. Subsequently, this work opens the door for implementing such a neuromarketingframework using consumer-grade devices in a real-life setting for marketers. As a result, it is evident that EEGbased neuromarketing technologies can assist brands and enterprises in forecasting future consumer preferencesaccurately. Hence, it will pave the way for the creation of an intelligent marketing assistive system for neuromarketing applications in future.
Mashrur FR, Rahman KM, Miya MTI, et al., 2022, BCI-Based consumers' choice prediction from EEG signals: an intelligent neuromarketing framework, Frontiers in Human Neuroscience, Vol: 16, Pages: 1-13, ISSN: 1662-5161
Neuromarketing relies on Brain Computer Interface (BCI) technology to gain insight into how customers react to marketing stimuli. Marketers spend about $750 billion annually on traditional marketing camping. They use traditional marketing research procedures such as Personal Depth Interviews, Surveys, Focused Group Discussions, and so on, which are frequently criticized for failing to extract true consumer preferences. On the other hand, Neuromarketing promises to overcome such constraints. This work proposes a machine learning framework for predicting consumers' purchase intention (PI) and affective attitude (AA) from analyzing EEG signals. In this work, EEG signals are collected from 20 healthy participants while administering three advertising stimuli settings: product, endorsement, and promotion. After preprocessing, features are extracted in three domains (time, frequency, and time-frequency). Then, after selecting features using wrapper-based methods Recursive Feature Elimination, Support Vector Machine is used for categorizing positive and negative (AA and PI). The experimental results show that proposed framework achieves an accuracy of 84 and 87.00% for PI and AA ensuring the simulation of real-life results. In addition, AA and PI signals show N200 and N400 components when people tend to take decision after visualizing static advertisement. Moreover, negative AA signals shows more dispersion than positive AA signals. Furthermore, this work paves the way for implementing such a neuromarketing framework using consumer-grade EEG devices in a real-life setting. Therefore, it is evident that BCI-based neuromarketing technology can help brands and businesses effectively predict future consumer preferences. Hence, EEG-based neuromarketing technologies can assist brands and enterprizes in accurately forecasting future consumer preferences.
Wairagkar M, Lima MR, Bazo D, et al., 2022, Emotive response to a hybrid-face robot and translation to consumer social robots, IEEE Internet of Things Journal, Vol: 9, Pages: 3174-3188, ISSN: 2327-4662
We present the conceptual formulation, design, fabrication, control and commercial translation of an IoT enabled social robot as mapped through validation of human emotional response to its affective interactions. The robot design centres on a humanoid hybrid-face that integrates a rigid faceplate with a digital display to simplify conveyance of complex facial movements while providing the impression of three-dimensional depth. We map the emotions of the robot to specific facial feature parameters, characterise recognisability of archetypical facial expressions, and introduce pupil dilation as an additional degree of freedom for emotion conveyance. Human interaction experiments demonstrate the ability to effectively convey emotion from the hybrid-robot face to humans. Conveyance is quantified by studying neurophysiological electroencephalography (EEG) response to perceived emotional information as well as through qualitative interviews. Results demonstrate core hybrid-face robotic expressions can be discriminated by humans (80%+ recognition) and invoke face-sensitive neurophysiological event-related potentials such as N170 and Vertex Positive Potentials in EEG. The hybrid-face robot concept has been modified, implemented, and released by Emotix Inc in the commercial IoT robotic platform Miko (‘My Companion’), an affective robot currently in use for human-robot interaction with children. We demonstrate that human EEG responses to Miko emotions are comparative to that of the hybrid-face robot validating design modifications implemented for large scale distribution. Finally, interviews show above 90% expression recognition rates in our commercial robot. We conclude that simplified hybrid-face abstraction conveys emotions effectively and enhances human-robot interaction.
Mancero Castillo CS, Vaidyanathan R, Atashzar SF, 2022, Synergistic upper-limb functional muscle connectivity using acoustic meganomyography, IEEE Transactions on Biomedical Engineering, Vol: 69, Pages: 2569-2580, ISSN: 0018-9294
Functional connectivity is a critical concept in describing synergistic muscle synchronization for the execution of complex motor tasks. Muscle synchronization is typically derived from the decomposition of intermuscular coherence (IMC) at different frequency bands through electromyography (EMG) signal analysis with limited out-of-clinic applications. In this investigation, we introduce muscle network analysis to assess the coordination and functional connectivity of muscles based on mechanomyography (MMG), focused on a targeted group of muscles that are typically active in the conduction of activities of daily living using the upper limb. In this regard, functional muscle networks are evaluated in this paper for ten able-bodied participants and three amputees. MMG activity was acquired from a custom-made wearable MMG armband placed over four superficial muscles around the forearm (i.e., flexor carpi radialis (FCR), brachioradialis (BR), extensor digitorum communis (EDC), and flexor carpi ulnaris (FCU)) while participants performed four different hand gestures. The results of connectivity analysis at multiple frequency bands showed significant topographical differences across gestures for low (< 5Hz) and high (> 12 Hz) frequencies and observable differences between able-bodied and amputee subjects. These findings show evidence that MMG can be used for the analysis of functional muscle connectivity and mapping of synergistic synchronization of upper-limb muscles in complex upper-limb tasks. The new physiological modality further provides key insights into the neural circuitry of motor coordination and offers the concomitant outcomes of demonstrating the feasibility of MMG to map muscle coherence from a neurophysiological perspective as well as providing the mechanistic basis for its translation into human-robot interfaces.
Natarajan N, Vaitheswaran S, Raposo de Lima M, et al., 2022, Acceptability of social robots and adaptation of hybrid-face robot for dementia care in India: a qualitative study, American Journal of Geriatric Psychiatry, Vol: 30, Pages: 240-245, ISSN: 1064-7481
ObjectivesThis study aims to understand the acceptability of social robots and the adaptation of the Hybrid-Face Robot for dementia care in India.MethodsWe conducted a focus group discussion and in-depth interviews with persons with dementia (PwD), their caregivers, professionals in the field of dementia, and technical experts in robotics to collect qualitative data.ResultsThis study explored the following themes: Acceptability of Robots in Dementia Care in India, Adaptation of Hybrid-Face Robot and Future of Robots in Dementia Care. Caregivers and PwD were open to the idea of social robot use in dementia care; caregivers perceived it to help with the challenges of caregiving and positively viewed a future with robots.DiscussionThis study is the first of its kind to explore the use of social robots in dementia care in India by highlighting user needs and requirements that determine acceptability and guiding adaptation.
Ishtiaque F, Mashrur FR, Touhidul Islam Miya M, et al., 2022, BCI-based Consumers' Preference Prediction using Single Channel Commercial EEG Device, Pages: 43-48
Brain-Computer Interface (BCI) technology is used in neuromarketing to learn how consumers respond to marketing stimuli. This helps evaluate the marketing stimuli which is traditionally done using marketing research procedures. BCI-based neuromarketing promises to replace these traditional marketing research procedures which are time-consuming and costly. Although BCI-based neuromarketing has its difficulty as EEG devices are inconvenient for consumer-grade applications. This study is performed to predict consumers' affective attitude (AA) and purchase intention (PI) toward a product using EEG signals. EEG signals are collected using a single channel consumer-grade EEG device from 4 healthy participants while they are subject to 3 different types of marketing stimuli; product, promotion, and endorsement. Multi-domain features are extracted from the EEG signals after pre-processing. 52 features are selected among those using SVM-based Recursive Feature Elimination. SMOTE algorithm is used to balance out the dataset. Support Vector Machine (SVM) is used to classify positive and negative affective attitude and purchase intention. The model manages to achieve an accuracy of 88.2% for affective attitude and 80.4% for purchase intention proving the viability of consumer-grade BCI devices in neuromarketing.
Dev A, Roy N, Islam MK, et al., 2022, Exploration of EEG-Based Depression Biomarkers Identification Techniques and Their Applications: A Systematic Review, IEEE ACCESS, Vol: 10, Pages: 16756-16781, ISSN: 2169-3536
- Author Web Link
- Cite
- Citations: 11
Paszkiewicz FP, Wilson S, Oddsson M, et al., 2022, Microphone Mechanomyography Sensors for Movement Analysis and Identification, 7th IEEE International Conference on Advanced Robotics and Mechatronics, Publisher: IEEE, Pages: 118-125
- Author Web Link
- Cite
- Citations: 1
Amerini R, gupta L, Steadman N, et al., 2021, Fusion models for generalized classification of multi-axial human movement: validation in sport performance, Sensors, Vol: 21, ISSN: 1424-8220
We introduce a set of input models for fusing information from ensembles of wearable sensors supporting human performance and telemedicine. Veracity is demonstrated in action classification related to sport, specifically strikes in boxing and taekwondo. Four input models, formulated to be compatible with a broad range of classifiers, are introduced and two diverse classifiers, dynamic time warping (DTW) and convolutional neural networks (CNNs) are implemented in conjunction with the input models. Seven classification models fusing information at the input-level, output-level, and a combination of both are formulated. Action classification for 18 boxing punches and 24 taekwondo kicks demonstrate our fusion classifiers outperform the best DTW and CNN uni-axial classifiers. Furthermore, although DTW is ostensibly an ideal choice for human movements experiencing non-linear variations, our results demonstrate deep learning fusion classifiers outperform DTW. This is a novel finding given that CNNs are normally designed for multi-dimensional data and do not specifically compensate for non-linear variations within signal classes. The generalized formulation enables subject-specific movement classification in a feature-blind fashion with trivial computational expense for trained CNNs. A commercial boxing system, ‘Corner’, has been produced for real-world mass-market use based on this investigation providing a basis for future telemedicine translation.
Wairagkar M, De Lima MR, Harrison M, et al., 2021, Conversational artificial intelligence and affective social robot for monitoring health and well-being of people with dementia., Alzheimers & Dementia, Vol: 17 Suppl 11, Pages: e053276-e053276, ISSN: 1552-5260
BACKGROUND: Social robots are anthropomorphised platforms developed to interact with humans, using natural language, offering an accessible and intuitive interface suited to diverse cognitive abilities. Social robots can be used to support people with dementia (PwD) and carers in their homes managing medication, hydration, appointments, and evaluating mood, wellbeing, and potentially cognitive decline. Such robots have potential to reduce care burden and prolong independent living, yet translation into PwD use remains insignificant. METHOD: We have developed two social robots - a conversational robot and a digital social robot for mobile devices capable of communicating through natural language (powered by Amazon Alexa) and facial expressions that ask PwD daily questions about their health and wellbeing and also provide digital assistant functionality. We record data comprising of PwD's responses to daily questions, audio speech and text of conversations with Alexa to automatically monitor their health and wellbeing using machine learning. We followed user-centric development processes by conducting focus groups with 13 carers, 2 PwD and 5 clinicians to iterate the design. We are testing social robot with 3 PwD in their homes for ten weeks. RESULT: We received positive feedback on social robot from focus group participants. Ease of use, low maintenance, accessibility, assistance with medication, supporting with health and wellbeing were identified as the key opportunities for social robots. Based on responses to a daily questionnaire, our robots generate a report detailing PwD wellbeing that is automatically sent via email to family members or carers. This information is also stored systematically in a database that can help clinicians monitor their patients remotely. We use natural language processing to analyse conversations and identify topics of interest to PwD such that robot behaviour could be adapted. We process speech using signal processing and machine lear
This data is extracted from the Web of Science and reproduced under a licence from Thomson Reuters. You may not copy or re-distribute this data in whole or in part without the written consent of the Science business of Thomson Reuters.