Davide Deiana, Mattia Pinardi, A. Noccaro, Michela Iandoli, G. D. Pino, D. Formica
{"title":"Validation of Vibrotactile Feedback to Improve Selective Motor Units Recruitment","authors":"Davide Deiana, Mattia Pinardi, A. Noccaro, Michela Iandoli, G. D. Pino, D. Formica","doi":"10.1109/MeMeA57477.2023.10171925","DOIUrl":"https://doi.org/10.1109/MeMeA57477.2023.10171925","url":null,"abstract":"Recently, muscle interfaces have been used to control external devices through the activation of single motor units. In the present study, we proposed and validated two different vibro-tactile feedback strategies designed to convey information about the firing rate of two motor units active at the same time. In a two-alternative forced-choice task, participants had to discriminate the higher vibration frequency among the ones of two vibrotactile stimulators placed on their arms. Spike strategy and continuous strategy were tested in two different experiments and motor units’ activation was simulated. The spike strategy directly translates the discharge activity of motor units into a vibratory burst with a 1-to-1 conversion, i.e. each spike of one motor unit triggers a single burst of the corresponding vibrator. This was evaluated in two body configurations, i.e. same forearm versus different arms. The continuous strategy mapped the discharge activity of motor units into a continuous vibration exploiting the entire operative range of vibrotactile stimulators. A single-body configuration was tested (i.e. two different arms). Participants’ responses were fitted with a psychometric sigmoid curve (i.e. a psychometric model commonly applied to detection and discrimination tasks), and the discrimination accuracy index was used to evaluate the feedback strategies. Results from Experiment 1 showed that the continuous strategy worked better when the stimulators were placed on two different arms, but overall discrimination performance was poor. Experiment 2 showed that both the continuous strategy conveyed vastly superior overall performance compared to the continuous strategy.","PeriodicalId":191927,"journal":{"name":"2023 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"238 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125759935","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Farah Kharrat, W. Gueaieb, F. Karray, Abdulmotaleb El Saddik
{"title":"A Hybrid Deep Learning Model for Human Activity Recognition and Fall Detection for the Elderly","authors":"Farah Kharrat, W. Gueaieb, F. Karray, Abdulmotaleb El Saddik","doi":"10.1109/MeMeA57477.2023.10171926","DOIUrl":"https://doi.org/10.1109/MeMeA57477.2023.10171926","url":null,"abstract":"Modern society faces a significant challenge with the aging of the global population. The number of seniors is projected to surpass 1.4 billion by 2030, which will undoubtedly impact the sustainability of current healthcare systems, both in the public and the private sectors. To address some health issues that often face the elderly in terms of abnormal home behavior, or accidental falls, sensor-based systems for human activity recognition and automatic fall detection have become valuable tools which can be used for immediate notification to caregivers. These systems can monitor the health status of elderly individuals, promote healthy lifestyles, and provide timely medical intervention, leading to improved recovery and rehabilitation. In this paper, we propose a deep learning model that takes advantage of the affordability and latest technological advancements of mobile sensors to identify certain physical activities and promptly send an alert in the event of a fall. Our hybrid model combines the strength of Convolutional Neural Networks for feature extraction with the advantages of Long Short-Term Memory networks for time series forecasting and classification. Through experiments on two public datasets, we demonstrate the effectiveness of our approach, achieving superior performance in recognizing human activities and a high accuracy for fall detection, surpassing the performance of similar studies.","PeriodicalId":191927,"journal":{"name":"2023 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133941450","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Performance of Speech Recognition Algorithms in Musical Speech used for Speech-Language Pathology Rehabilitation","authors":"Pedram Aliniaye Asli, A. Zumbansen","doi":"10.1109/MeMeA57477.2023.10171898","DOIUrl":"https://doi.org/10.1109/MeMeA57477.2023.10171898","url":null,"abstract":"Musical speech in speech-language pathology rehabilitation is the production of speech following simple musical (rhythmic or melodic) patterns. This type of speech is used to facilitate speech processing in patients. In this study, we examined the performance of current automatic speech recognition (ASR) algorithms in recognizing normal and musical speech. From a first list of 28 identified algorithms, 24 were excluded for reasons such as low accuracy rate, high computational cost, high price, difficulty of use, long runtime, implementation problems. The four algorithms included were those from Amazon Web Services (AWS Transcribe), Google Speech Recognition, IBM Watson and Rev AI. We ran the selected algorithms on 60 sentences recorded under four speech conditions (Melodic; Rhythmic; Regular Slow; and Regular Normal). All algorithms did perfectly in recognizing the normal speech. The two algorithms with the best performance in musical speech (rhythmic and melodic speech) were AWS Transcribe and IBM Watson, both providing recognition accuracy above 98%. When adding moderate level of white noise and reverberation to the stimuli, AWS Transcribe remained with an acceptable (> 70%) or satisfactory (> 95%) ASR performance. These results may guide the development of software that use ASR to enable patients to undergo self-directed sessions of music-based speech-language rehabilitation, such as the melodic intonation therapy for post-stroke aphasia. The possibility to recognize musical speech allows to compare a patient’s performance to corresponding target phrases and provide feedback in the absence of a clinician. Given the recommended high intensity of treatment and the limited availability of speech-language pathologists, such software would be highly valuable to our healthcare systems.","PeriodicalId":191927,"journal":{"name":"2023 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130837561","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
V. D'Alessandro, Luisa De Palma, F. Attivissimo, A. Nisio, A. Lanzolla
{"title":"U-Net convolutional neural network for multisource heterogeneous iris segmentation","authors":"V. D'Alessandro, Luisa De Palma, F. Attivissimo, A. Nisio, A. Lanzolla","doi":"10.1109/MeMeA57477.2023.10171896","DOIUrl":"https://doi.org/10.1109/MeMeA57477.2023.10171896","url":null,"abstract":"Accurate iris segmentation is a critical step in various applications, from biometric identification systems to ophthalmic disease diagnosis. Despite the large number of works that address this problem, iris segmentation of heterogeneous iris images acquired in different conditions is still a huge challenge. This work employed a modified U-net convolutional neural network architecture to segment iris region from heterogeneous eye images. The network was trained using the TEyeD dataset, the world’s largest heterogeneous publicly available dataset of eye images.The proposed method utilizes the U-Net architecture, known for its effectiveness in handling complex image segmentation tasks. The architecture is modified to accomplish the specific task. The experimental results show that the proposed approach achieves an IOU score of 95%, demonstrating promising results in terms of segmentation accuracy and computational efficiency. This performance is competitive or even better than the existing state-of-the-art techniques in iris segmentation, considering that in most cases the dataset used to train the network is not heterogeneous as the TEyeD dataset.Indeed, the study highlights the potential of deep learning techniques in improving the accuracy of iris segmentation, and the TEyeD dataset, which is a heterogeneous dataset in terms of acquisition devices employed and image quality, provides an excellent opportunity for researchers to further explore this topic. The findings of this research could have significant implications for various fields, including biometric identification systems, driver safety, and ophthalmology.","PeriodicalId":191927,"journal":{"name":"2023 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"100 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130986848","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Early Detection of Infant Cerebral Palsy Risk based on Pose Estimation using OpenPose and Advanced Algorithms from Limited and Imbalance Dataset","authors":"E. S. Ningrum, E. M. Yuniarno, M. Purnomo","doi":"10.1109/MeMeA57477.2023.10171951","DOIUrl":"https://doi.org/10.1109/MeMeA57477.2023.10171951","url":null,"abstract":"Detection of the risk of cerebral palsy existance in infant phase is critical during human development. The fidgety movements of infant during this phase plays an important role in indication of normal or abnormality of balanced and coordination. Previous researches have shown the possibility of abnormality detection using infant pose estimation. However, in particular for predicting the risk of cerebral palsy (CP) based on the estimation of the infant’s movement poses, it is not optimal in its classification due to the rarity of dataset sources. This research aimed to develop a classifier based on OpenPose and advanced algorithms, including a Long Short-Term Memory (LSTM) network, 1-dimensional Convolutional Neural Network (CNN) combined with LSTM, and Gated Recurrent Unit (GRU), to predict the likelihood of cerebral palsy in infants, where amount of data is limited and there is an imbalance in categories. Such dataset was obtained from Chambers et al. and divided into ‘at-risk’ and ‘healthy’ categories. This research evaluates the performance of different algorithms in classifying infants with cerebral palsy and those without. After perfecting the model, ID CNN combined with LSTM outperformed other models with an accuracy of 0.96. Meanwhile, GRU achieved an accuracy of 0.83, and LSTM achieved an accuracy of 0.77. This research also highlights the potential of using OpenPose and advanced algorithms to accurately predict and prevent cerebral palsy in infants, providing valuable insights for future research in this area.","PeriodicalId":191927,"journal":{"name":"2023 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132410728","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
M. Aburidi, Mario Banuelos, Suzanne S. Sindi, Roummel F. Marcia
{"title":"Genetic Variant Detection Over Generations: Sparsity-Constrained Optimization Using Block-Coordinate Descent","authors":"M. Aburidi, Mario Banuelos, Suzanne S. Sindi, Roummel F. Marcia","doi":"10.1109/MeMeA57477.2023.10171853","DOIUrl":"https://doi.org/10.1109/MeMeA57477.2023.10171853","url":null,"abstract":"Structural variants (SVs) are rearrangements of regions in an individual’s genome signal. SVs are an important source of genetic diversity and disease in humans and other mammalian species. The SV detection process is susceptible to sequencing and mapping errors, especially when the average number of reads supporting each variant is low (i.e. low-coverage settings), which leads to high false-positive rates. Besides their rarity in the human genome, they are shared between related individuals. Thus, it’s advantageous to devise algorithms that focus on close relatives. In this paper, we develop a constrained-optimization method to detect germline SVs in genetic signals by considering multiple related people. First, we exploit familial relationships by considering a biologically realistic scenario of three generations of related individuals (a grandparent, a parent, and a child). Second, we pose the problem as a constrained optimization problem regularized by a sparsity-promoting penalty. Our framework demonstrates improvements in predicting SVs in related individuals and uncovering true SVs from false positives on both simulated and real genetic signals from the 1000 Genomes Project with low coverage. Further, our block-coordinate descent approach produces results with equal accuracy to the 3D projections of the solution, demonstrating feasibility for more complex and higher-dimensional pedigrees.","PeriodicalId":191927,"journal":{"name":"2023 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"58 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114105006","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Andy Keymolen, Antoine Marchal, F. Heck, B. V. D. Elshout, G. Vandersteen, J. Jonckheer, J. Lataire
{"title":"Low-frequency respiratory oscillometric measurements during mechanical ventilation","authors":"Andy Keymolen, Antoine Marchal, F. Heck, B. V. D. Elshout, G. Vandersteen, J. Jonckheer, J. Lataire","doi":"10.1109/MeMeA57477.2023.10171930","DOIUrl":"https://doi.org/10.1109/MeMeA57477.2023.10171930","url":null,"abstract":"Respiratory oscillometry (RO), applied during ventilation of patients, allows the identification of relevant mechanical properties of the respiratory system. RO during ventilation is not a standard-of-care measurement technique since the identified parameters are currently not equivalent to the parameters identified via standard-of-care techniques such as the low flow PN loop. This paper presents a novel RO setup that identifies the same respiratory mechanical parameters as the standard-of-care techniques. The setup is a blower-based ventilation device where the requested ventilation is combined with a specifically designed low-frequency multisine excitation signal. The excitation design protocol takes the ventilation limitations into account to ensure the measurement quality. Validation measurements on an emulator are provided to evaluate the performance of the proposed techniques. The emulator is measured via the novel RO setup as well as via three standard-of-care measurement techniques. The measurements showed that the same parameters could be identified with a better accuracy than the common oscillometric standard of 10%. The estimated values and their coefficient of variation were compared against each other and showed that the RO setup is a qualitative alternative to the standard-of-care techniques with the clinical advantages of being patient friendlier, easier to use and less disturbed by patient activity.","PeriodicalId":191927,"journal":{"name":"2023 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"126 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133953535","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Francesca De Tommasi, D. Presti, M. Caponero, M. Carassiti, E. Schena, C. Massaroni
{"title":"FBG-Based Mattress for Continuous Respiratory Rate Estimation: Influence of Positioning Over and Under the Bed","authors":"Francesca De Tommasi, D. Presti, M. Caponero, M. Carassiti, E. Schena, C. Massaroni","doi":"10.1109/MeMeA57477.2023.10171865","DOIUrl":"https://doi.org/10.1109/MeMeA57477.2023.10171865","url":null,"abstract":"The respiratory rate (RR) is considered one of the most informative vital signs for preventing and diagnosing cardiovascular and sleep disorders. Among the several technologies proposed over the years to estimate RR, unobtrusive solutions are preferred in long-term applications since they allow monitoring subjects without disrupting their daily activities, such as sleeping at night. In this arena, instrumented mattresses are gaining the attention of several research groups. Solutions based on fiber Bragg grating sensors (FBGs) offer the possibility to perform multi-point measurements, a key aspect to enabling reliable RR monitoring during sleep. Our research group recently presented a smart mattress based on thirteen FBGs fully embedded polymeric materials for RR monitoring. The feasibility assessment carried out in a laboratory environment showed promising results. Here, we investigated the feasibility of the proposed mattress for estimating RR in a real-world scenario. We performed the assessment during a long acquisition time (i.e., 45 min) by placing the proposed system over or under the bed to assess the influence of these two configurations on the mattress’ response. Results evidenced better performance in RR estimation with the smart mattress over the bed mattress with a bias of -0.15 ± 2.14 breaths/min expressed as MOD±LOAs as well as higher amplitudes of the FBG signals in this condition than under the bed mattress (up to 0.027 nm).","PeriodicalId":191927,"journal":{"name":"2023 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130554230","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Matin Beiramvand, T. Lipping, Nina Karttunen, Reijo Koivula
{"title":"Mental Workload Assessment using Low-Channel Prefrontal EEG Signals","authors":"Matin Beiramvand, T. Lipping, Nina Karttunen, Reijo Koivula","doi":"10.1109/MeMeA57477.2023.10171942","DOIUrl":"https://doi.org/10.1109/MeMeA57477.2023.10171942","url":null,"abstract":"Objective: Monitoring stress using physiological signals has recently achieved a lot of attention since it has a significant adverse influence on an individual daily’s health and efficiency. As it has been proven that stress and mental workload are proportionally correlated, several studies have proposed algorithms for stress monitoring by increasing the mental workload. Despite the promising results reported in the literature, a majority of the proposed algorithms require the employment of several physiological signals which hinder their real-life application. Nonetheless, the advent of low-cost wearable devices has provided a new possibility for outdoor stress monitoring. The objective of this paper is to present an algorithm for stress detection using low-channel prefrontal electroencephalography (EEG) data. Methods: Firstly, artifacts in EEG signals are removed. Secondly, EEG signals are split into sub-bands using the discrete wavelet transform and two nonlinear parameter-free features are extracted. Thirdly, the extracted features are fed to three classifiers, i.e., support vector machine, Adaboost, and the K-Nearest Neighbours to discriminate stress from relaxed states. Main results: According to the obtained results, the highest accuracy (80.24%) was achieved using the AdaBoost classifier. Significance:Given that the proposed method does not require any parameter adjustment before processing, it has the potential to be used in real-world scenarios.","PeriodicalId":191927,"journal":{"name":"2023 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122237441","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Kano Kajie, Zugui Peng, K. Shimba, Takashi Shibata, Y. Miyamoto, T. Yagi
{"title":"Control of Drug Release in Ultrasound-Responsive Liposome-Encapsulated Gel Patches","authors":"Kano Kajie, Zugui Peng, K. Shimba, Takashi Shibata, Y. Miyamoto, T. Yagi","doi":"10.1109/MeMeA57477.2023.10171928","DOIUrl":"https://doi.org/10.1109/MeMeA57477.2023.10171928","url":null,"abstract":"Transdermal drug delivery systems deliver drugs via transdermal absorption, and microcapsule-embedded gel patches for these systems have been studied previously. The microcapsules contained the drug to prevent leakage through the gel pores and to provide sustained release. The drug could also be released by breaking the microcapsules with ultrasound irradiation. However, the amount of drug released without irradiation was large, and the release was difficult to control. In this study, we prepare an ultrasound-responsive liposome-encapsulated gel patch. In comparison, microcapsules have a monolayer structure and liposomes have a lipid bilayer structure which has been seen to be more robust. Also, microcapsules in the previous study were micro-sized, whereas liposomes in the present study are nano-sized which are more stable and able to provide sustained release. To observe the effectiveness of sustained drug release and the on-off control of drug release by ultrasound irradiation, liposomes containing a fluorescent compound as a drug model are embedded in agarose gel. The fluorescent intensity of the buffer solution outside the liposome-encapsulated gel patch after 24 h are observed with a spectrophotometer. The amount of drug leakage is lower than that of the microcapsule-embedded gel patch. Furthermore, the amount of drug released without irradiation is smaller than in the previous study. The fluorescent intensity after ultrasound irradiation is higher than that before irradiation indicating that the drug release is accelerated by ultrasound and that the amount of drug released can be controlled.","PeriodicalId":191927,"journal":{"name":"2023 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126468976","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}