Pub Date : 2015-05-07DOI: 10.1109/MeMeA.2015.7145263
Stefano Basso, G. Frigo, G. Giorgi
The World Health Organization assesses the number of visually impaired people to be nearly 285 million in August 2014, of whom 39 million are blind. One of the most important discomfort factors for these persons is known to be the difficulty in moving and orienting by themselves in unfamiliar surroundings. Nowadays, several devices are currently available for supporting these persons in there everyday life. To this end, the attention in this paper is mainly focused on the localization and navigation in indoor environment. The solution adopted in this paper consists in populating a database of virtual maps, that the user itself contributes to create by exploring the surrounding environment. An inertial platform, represented by a set of sensors (basically accelerometer, gyroscope, electronic compass) placed in a device worn by user, is used at the purpose as sensing system. This approach does not require the installation of external equipments since it relies on a smartphone, which is used both as measurement platform and user interface, and, in particular, does not require any a-priori knowledge of the indoor environment. The application will be described in the paper where some experimental preliminary results will also be discussed.
{"title":"A smartphone-based indoor localization system for visually impaired people","authors":"Stefano Basso, G. Frigo, G. Giorgi","doi":"10.1109/MeMeA.2015.7145263","DOIUrl":"https://doi.org/10.1109/MeMeA.2015.7145263","url":null,"abstract":"The World Health Organization assesses the number of visually impaired people to be nearly 285 million in August 2014, of whom 39 million are blind. One of the most important discomfort factors for these persons is known to be the difficulty in moving and orienting by themselves in unfamiliar surroundings. Nowadays, several devices are currently available for supporting these persons in there everyday life. To this end, the attention in this paper is mainly focused on the localization and navigation in indoor environment. The solution adopted in this paper consists in populating a database of virtual maps, that the user itself contributes to create by exploring the surrounding environment. An inertial platform, represented by a set of sensors (basically accelerometer, gyroscope, electronic compass) placed in a device worn by user, is used at the purpose as sensing system. This approach does not require the installation of external equipments since it relies on a smartphone, which is used both as measurement platform and user interface, and, in particular, does not require any a-priori knowledge of the indoor environment. The application will be described in the paper where some experimental preliminary results will also be discussed.","PeriodicalId":277757,"journal":{"name":"2015 IEEE International Symposium on Medical Measurements and Applications (MeMeA) Proceedings","volume":"207 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-05-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124650318","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}
Pub Date : 2015-05-07DOI: 10.1109/MeMeA.2015.7145217
E. Schena, P. Saccomandi, Marina Piccolo, C. Massaroni, S. Silvestri, C. Piccolo, G. Frauenfelder, F. Giurazza, B. Zobel
Minimally invasive thermal procedures are gaining acceptance in tumor treatment. Among others, laser ablation (LA) is considered a valid alternative to surgical resection for inoperable patients. LA damages the tumor by increasing the tissue temperature. The temperature distribution within the tissue strongly influences the outcomes of the procedure. Hence, some thermometric techniques are employed in this scenario. Among them, MRI-based thermometry presents some advantages, such as the non-invasiveness. In this work, two sequences (EPI and FIESTA) have been used to monitor liver temperature. During the whole MRI procedure, the liver temperature has been monitored by MRcompatible, fiber optic-based sensors. The temperature measured by these sensors has been used as reference in order to assess the sensitivity of MRI-thermometry. Moreover, the influence of Region of interests (ROIs) size on precision has been investigated. Results show that the absolute value of thermal sensitivity of FIESTA is double with respect to the sensitivity obtained with EPI (about -15 °C-1 vs -7 °C-1). Regarding the influence of ROI size, results show that the wider the extension the better the precision.
微创热手术在肿瘤治疗中得到越来越多的认可。其中，激光消融(LA)被认为是一个有效的替代手术切除不能手术的患者。LA通过提高组织温度来破坏肿瘤。组织内的温度分布强烈影响手术的结果。因此，在这种情况下采用了一些测温技术。其中，核磁共振测温具有无创性等优点。在这项工作中，两个序列(EPI和FIESTA)已被用于监测肝脏温度。在整个核磁共振过程中，肝脏温度由核磁共振兼容的光纤传感器监测。用这些传感器测得的温度作为参考，以评估核磁共振测温的灵敏度。此外，还研究了利益区域(roi)大小对精度的影响。结果表明，FIESTA的热敏度绝对值是EPI的两倍(约为-15°C-1 vs -7°C-1)。对于ROI大小的影响，结果表明，扩展越宽，精度越好。
{"title":"MRI-thermometry on ex vivo swine liver: Preliminary trials to assess the sensitivity of two sequences","authors":"E. Schena, P. Saccomandi, Marina Piccolo, C. Massaroni, S. Silvestri, C. Piccolo, G. Frauenfelder, F. Giurazza, B. Zobel","doi":"10.1109/MeMeA.2015.7145217","DOIUrl":"https://doi.org/10.1109/MeMeA.2015.7145217","url":null,"abstract":"Minimally invasive thermal procedures are gaining acceptance in tumor treatment. Among others, laser ablation (LA) is considered a valid alternative to surgical resection for inoperable patients. LA damages the tumor by increasing the tissue temperature. The temperature distribution within the tissue strongly influences the outcomes of the procedure. Hence, some thermometric techniques are employed in this scenario. Among them, MRI-based thermometry presents some advantages, such as the non-invasiveness. In this work, two sequences (EPI and FIESTA) have been used to monitor liver temperature. During the whole MRI procedure, the liver temperature has been monitored by MRcompatible, fiber optic-based sensors. The temperature measured by these sensors has been used as reference in order to assess the sensitivity of MRI-thermometry. Moreover, the influence of Region of interests (ROIs) size on precision has been investigated. Results show that the absolute value of thermal sensitivity of FIESTA is double with respect to the sensitivity obtained with EPI (about -15 °C-1 vs -7 °C-1). Regarding the influence of ROI size, results show that the wider the extension the better the precision.","PeriodicalId":277757,"journal":{"name":"2015 IEEE International Symposium on Medical Measurements and Applications (MeMeA) Proceedings","volume":"211 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-05-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124735720","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}
Pub Date : 2015-05-07DOI: 10.1109/MeMeA.2015.7145163
Mario Klunder, R. Feuer, O. Sawodny, M. Ederer
Urethral Pressure Profilometry (UPP) is a tool in the diagnosis of urinary incontinence. The pressure profile along the urethra is measured by a special catheter in order to assess the contraction strength of the sphincter muscle. However, the diagnostic value of pressure profilometry is limited. We seek to increase the diagnostic value by providing a detailed spatial reconstruction of the pressure profile on the outside surface of the urethra. We use deconvolution in order to solve the inverse problem of determining the pressure distribution on the outside of a tube from measured data on the inside. Therefore, we propose a parametric Point-Spread-Function (PSF) and optimize its parameters using a Finite-Element (FE) model. Simulation results verifying accuracy and robustness of this method conclude this work.
{"title":"Using deconvolution to determine the sphincter strength distribution around the urethra","authors":"Mario Klunder, R. Feuer, O. Sawodny, M. Ederer","doi":"10.1109/MeMeA.2015.7145163","DOIUrl":"https://doi.org/10.1109/MeMeA.2015.7145163","url":null,"abstract":"Urethral Pressure Profilometry (UPP) is a tool in the diagnosis of urinary incontinence. The pressure profile along the urethra is measured by a special catheter in order to assess the contraction strength of the sphincter muscle. However, the diagnostic value of pressure profilometry is limited. We seek to increase the diagnostic value by providing a detailed spatial reconstruction of the pressure profile on the outside surface of the urethra. We use deconvolution in order to solve the inverse problem of determining the pressure distribution on the outside of a tube from measured data on the inside. Therefore, we propose a parametric Point-Spread-Function (PSF) and optimize its parameters using a Finite-Element (FE) model. Simulation results verifying accuracy and robustness of this method conclude this work.","PeriodicalId":277757,"journal":{"name":"2015 IEEE International Symposium on Medical Measurements and Applications (MeMeA) Proceedings","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-05-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126198428","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}
Pub Date : 2015-05-07DOI: 10.1109/MeMeA.2015.7145251
G. Barabino, D. Pani, A. Dessì, L. Raffo
The issue of biopotentials acquisition with surface electrodes has been studied for several years, during which a number of reliable techniques have been developed. Nowadays, they form a solid background of practices exploited in every commercially available biopotential acquisition module. Nevertheless, in some application fields where signal processing of the acquired signals is controversial, due to the lack of a deep understanding of the underlying physical aspects, there is the need to test several recording setups to define the one producing the best results. In fact, signal acquisition has strong influence on the signal processing techniques that can be deployed to post-process the data. Non-invasive fetal electrocardiography (ECG) is one of those field. In order to enable the investigation of the aspects connected with the signal acquisition, we developed a custom biopotential acquisition unit, with configurable measurement setup. It is intrinsically general purpose, but has been conceived to support studies on non-invasive fetal ECG on the animal model. Based on the ADS1298 analog front-end, the developed system achieves comparable performance with respect to commercial systems for physiological research opening to the first animals studies about the influence of the acquisition setup on the effectiveness of the signal processing algorithms for fetal ECG extraction.
{"title":"A configurable biopotentials acquisition module suitable for fetal electrocardiography studies","authors":"G. Barabino, D. Pani, A. Dessì, L. Raffo","doi":"10.1109/MeMeA.2015.7145251","DOIUrl":"https://doi.org/10.1109/MeMeA.2015.7145251","url":null,"abstract":"The issue of biopotentials acquisition with surface electrodes has been studied for several years, during which a number of reliable techniques have been developed. Nowadays, they form a solid background of practices exploited in every commercially available biopotential acquisition module. Nevertheless, in some application fields where signal processing of the acquired signals is controversial, due to the lack of a deep understanding of the underlying physical aspects, there is the need to test several recording setups to define the one producing the best results. In fact, signal acquisition has strong influence on the signal processing techniques that can be deployed to post-process the data. Non-invasive fetal electrocardiography (ECG) is one of those field. In order to enable the investigation of the aspects connected with the signal acquisition, we developed a custom biopotential acquisition unit, with configurable measurement setup. It is intrinsically general purpose, but has been conceived to support studies on non-invasive fetal ECG on the animal model. Based on the ADS1298 analog front-end, the developed system achieves comparable performance with respect to commercial systems for physiological research opening to the first animals studies about the influence of the acquisition setup on the effectiveness of the signal processing algorithms for fetal ECG extraction.","PeriodicalId":277757,"journal":{"name":"2015 IEEE International Symposium on Medical Measurements and Applications (MeMeA) Proceedings","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-05-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125727721","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}
Pub Date : 2015-05-07DOI: 10.1109/MeMeA.2015.7145243
G. Andria, A. Lanzolla, Giuseppe Russo, Mirko Parabita, R. Incalzi, G. Cavallo, M. Benvenuto
This paper proposes the development of an innovative measurement system for telerehabilitation with the aim to provide objective evaluation of functional capacity of patients subject to lower limb rehabilitation. In particular the system has based on the set of wearable MEMs sensors which detect the 3D orientation of the limbs and communicate with a Central Remote Unit for storing and elaborating all measurement data. The proposed study has been performed under the research project PRO-DOMO SUD funded by Apulia Region within the Project “Apulian ICT Living Labs”.
{"title":"An innovative measurement system based on MEMs for telerehabilitation","authors":"G. Andria, A. Lanzolla, Giuseppe Russo, Mirko Parabita, R. Incalzi, G. Cavallo, M. Benvenuto","doi":"10.1109/MeMeA.2015.7145243","DOIUrl":"https://doi.org/10.1109/MeMeA.2015.7145243","url":null,"abstract":"This paper proposes the development of an innovative measurement system for telerehabilitation with the aim to provide objective evaluation of functional capacity of patients subject to lower limb rehabilitation. In particular the system has based on the set of wearable MEMs sensors which detect the 3D orientation of the limbs and communicate with a Central Remote Unit for storing and elaborating all measurement data. The proposed study has been performed under the research project PRO-DOMO SUD funded by Apulia Region within the Project “Apulian ICT Living Labs”.","PeriodicalId":277757,"journal":{"name":"2015 IEEE International Symposium on Medical Measurements and Applications (MeMeA) Proceedings","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-05-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128097681","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}
Pub Date : 2015-05-07DOI: 10.1109/MeMeA.2015.7145170
M. Maffongelli, S. Poretti, A. Salvadè, R. Monleone, F. Meani, A. Fedeli, M. Pastorino, A. Randazzo
An existing prototype of microwave imaging tomograph, previously designed by the present Authors for non destructive testing (NDT) applications, has been adapted in order to deal with biomedical targets. The developed system allows collecting multi-view multi-frequency data. An efficient inversion procedure is used to retrieve the distributions of the dielectric properties from the measured field samples. Some numerical simulations aimed at validating the proposed system and preliminary measurement results obtained by using a breast phantom are presented in this paper.
{"title":"Preliminary test of a prototype of microwave axial tomograph for medical applications","authors":"M. Maffongelli, S. Poretti, A. Salvadè, R. Monleone, F. Meani, A. Fedeli, M. Pastorino, A. Randazzo","doi":"10.1109/MeMeA.2015.7145170","DOIUrl":"https://doi.org/10.1109/MeMeA.2015.7145170","url":null,"abstract":"An existing prototype of microwave imaging tomograph, previously designed by the present Authors for non destructive testing (NDT) applications, has been adapted in order to deal with biomedical targets. The developed system allows collecting multi-view multi-frequency data. An efficient inversion procedure is used to retrieve the distributions of the dielectric properties from the measured field samples. Some numerical simulations aimed at validating the proposed system and preliminary measurement results obtained by using a breast phantom are presented in this paper.","PeriodicalId":277757,"journal":{"name":"2015 IEEE International Symposium on Medical Measurements and Applications (MeMeA) Proceedings","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-05-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127290465","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}
Pub Date : 2015-05-07DOI: 10.1109/MeMeA.2015.7145268
M. Vasconcelos, Luís Rosado, M. Ferreira
The incidence of melanoma has been increasing steadily over the past few decades throughout most of the world. The development of computer diagnosis systems that use dermoscopic images can be of great help for the diagnosis of melanoma. This paper presents an image processing and analysis methodology using supervised classification to independently assess the Asymmetry, Border, Color and Dermoscopic Structures score according to the ABCD rule, and the corresponding Total Dermatoscopy Score of a skin lesion using dermoscopic images. A dermoscopic image dataset was used to test the proposed approach, annotated by dermatology specialists according to the ABCD rule and being the confirmed malignant melanomas also identified. Accuracy rates of 74.0%, 78.3% and 53.5% were achieved for the estimation of the ABCD score of the Asymmetry, Border and Color criterion, as well as accuracy rates for the presence of the five Differential Structures of 72.4%, 68.5%, 74.0%, 74.0% and 85.8% for dots, globules, streaks homogeneous areas and pigment network. Moreover, sensitivity and specificity rates of 93.3% and 69.1% were achieved for the classification of the dermoscopic images as melanoma or non-melanoma.
{"title":"A new risk assessment methodology for dermoscopic skin lesion images","authors":"M. Vasconcelos, Luís Rosado, M. Ferreira","doi":"10.1109/MeMeA.2015.7145268","DOIUrl":"https://doi.org/10.1109/MeMeA.2015.7145268","url":null,"abstract":"The incidence of melanoma has been increasing steadily over the past few decades throughout most of the world. The development of computer diagnosis systems that use dermoscopic images can be of great help for the diagnosis of melanoma. This paper presents an image processing and analysis methodology using supervised classification to independently assess the Asymmetry, Border, Color and Dermoscopic Structures score according to the ABCD rule, and the corresponding Total Dermatoscopy Score of a skin lesion using dermoscopic images. A dermoscopic image dataset was used to test the proposed approach, annotated by dermatology specialists according to the ABCD rule and being the confirmed malignant melanomas also identified. Accuracy rates of 74.0%, 78.3% and 53.5% were achieved for the estimation of the ABCD score of the Asymmetry, Border and Color criterion, as well as accuracy rates for the presence of the five Differential Structures of 72.4%, 68.5%, 74.0%, 74.0% and 85.8% for dots, globules, streaks homogeneous areas and pigment network. Moreover, sensitivity and specificity rates of 93.3% and 69.1% were achieved for the classification of the dermoscopic images as melanoma or non-melanoma.","PeriodicalId":277757,"journal":{"name":"2015 IEEE International Symposium on Medical Measurements and Applications (MeMeA) Proceedings","volume":"325 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-05-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124588615","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}
Pub Date : 2015-05-07DOI: 10.1109/MeMeA.2015.7145242
Yu-Cheng Fan, Hung-Kuan Liu
In this paper, we propose a three-dimensional gesture interactive system design of home automation for physically handicapped people. In order to provide a convenient and comfortable environment, we design a finger and hand gesture user interface for physically handicapped people based on stereo cameras to achieve remote control and gesture recognition system. We use stereo camera to capture stereo image and calculate disparity map and depth map for supplying physically handicapped people a real-time interface based on hand gesture and finger action. The system can achieve 93% accuracy of eight direction function, 93.75% accuracy of zoom function, and 90% accuracy of click function. The experimental results prove the efficiency of the proposed system.
{"title":"Three-dimensional gesture interactive system design of home automation for physically handicapped people","authors":"Yu-Cheng Fan, Hung-Kuan Liu","doi":"10.1109/MeMeA.2015.7145242","DOIUrl":"https://doi.org/10.1109/MeMeA.2015.7145242","url":null,"abstract":"In this paper, we propose a three-dimensional gesture interactive system design of home automation for physically handicapped people. In order to provide a convenient and comfortable environment, we design a finger and hand gesture user interface for physically handicapped people based on stereo cameras to achieve remote control and gesture recognition system. We use stereo camera to capture stereo image and calculate disparity map and depth map for supplying physically handicapped people a real-time interface based on hand gesture and finger action. The system can achieve 93% accuracy of eight direction function, 93.75% accuracy of zoom function, and 90% accuracy of click function. The experimental results prove the efficiency of the proposed system.","PeriodicalId":277757,"journal":{"name":"2015 IEEE International Symposium on Medical Measurements and Applications (MeMeA) Proceedings","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-05-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122445130","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}
Pub Date : 2015-05-07DOI: 10.1109/MeMeA.2015.7145188
Juri Taborri, E. Scalona, S. Rossi, E. Palermo, F. Patané, P. Cappa
In this paper we present and validate a methodology to avoid the training procedure of a classifier based on an Hidden Markov Model (HMM) for a real-time gait recognition of two or four phases, implemented to control pediatric active orthoses of lower limb. The new methodology consists in the identification of a set of standardized parameters, obtained by a data set of angular velocities of healthy subjects age-matched. Sagittal angular velocities of lower limbs of ten typically developed children (TD) and ten children with hemiplegia (HC) were acquired by means of the tri-axial gyroscope embedded into Magnetic Inertial Measurement Units (MIMU). The actual sequence of gait phases was captured through a set of four foot switches. The experimental protocol consists in two walking tasks on a treadmill set at 1.0 and 1.5 km/h. We used the Goodness (G) as parameter, computed from Receiver Operating Characteristic (ROC) space, to compare the results obtained by the new methodology with the ones obtained by the subject-specific training of HMM via the Baum-Welch Algorithm. Paired-sample t-tests have shown no significant statistically differences between the two procedures when the gait phase detection was performed with the gyroscopes placed on the foot. Conversely, significant differences were found in data gathered by means of gyroscopes placed on shank. Actually, data relative to both groups presented G values in the range of good/optimum classifier (i.e. G ≤ 0.3), with better performance for the two-phase classifier model. In conclusion, the novel methodology here proposed guarantees the possibility to omit the off-line subject-specific training procedure for gait phase detection and it can be easily implemented in the control algorithm of active orthoses.
{"title":"Real-time gait detection based on Hidden Markov Model: Is it possible to avoid training procedure?","authors":"Juri Taborri, E. Scalona, S. Rossi, E. Palermo, F. Patané, P. Cappa","doi":"10.1109/MeMeA.2015.7145188","DOIUrl":"https://doi.org/10.1109/MeMeA.2015.7145188","url":null,"abstract":"In this paper we present and validate a methodology to avoid the training procedure of a classifier based on an Hidden Markov Model (HMM) for a real-time gait recognition of two or four phases, implemented to control pediatric active orthoses of lower limb. The new methodology consists in the identification of a set of standardized parameters, obtained by a data set of angular velocities of healthy subjects age-matched. Sagittal angular velocities of lower limbs of ten typically developed children (TD) and ten children with hemiplegia (HC) were acquired by means of the tri-axial gyroscope embedded into Magnetic Inertial Measurement Units (MIMU). The actual sequence of gait phases was captured through a set of four foot switches. The experimental protocol consists in two walking tasks on a treadmill set at 1.0 and 1.5 km/h. We used the Goodness (G) as parameter, computed from Receiver Operating Characteristic (ROC) space, to compare the results obtained by the new methodology with the ones obtained by the subject-specific training of HMM via the Baum-Welch Algorithm. Paired-sample t-tests have shown no significant statistically differences between the two procedures when the gait phase detection was performed with the gyroscopes placed on the foot. Conversely, significant differences were found in data gathered by means of gyroscopes placed on shank. Actually, data relative to both groups presented G values in the range of good/optimum classifier (i.e. G ≤ 0.3), with better performance for the two-phase classifier model. In conclusion, the novel methodology here proposed guarantees the possibility to omit the off-line subject-specific training procedure for gait phase detection and it can be easily implemented in the control algorithm of active orthoses.","PeriodicalId":277757,"journal":{"name":"2015 IEEE International Symposium on Medical Measurements and Applications (MeMeA) Proceedings","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-05-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123471134","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}
Pub Date : 2015-05-07DOI: 10.1109/MeMeA.2015.7145227
G. Frigo, M. Rubega, G. Lezziero, R. Fontana, C. Cecchetto, S. Vassanelli, G. Sparacino, Matteo Bertocco
Recent improvements in microelectrodes technology have enabled neuroscientists to record electrophysiological signals from hundreds of neurons and simultaneously from a large number of channels. However, several environmental factors may introduce noise and artefacts and affect proper interpretation of recordings. Thus, the development of appropriate signal acquisition and processing platforms dealing with large data sets and in real-time represents a current fundamental challenge. In the present work, we present an easily-expandable Lab VIEW based software for handling data in real-time during a multichannel neurophysiological signal acquisition. The software was designed to exploit modern MultiCore CPUs for large scale data processing and, by freely setting key acquisition parameters, to work with virtually any kind of biological signal. The software allows for data storage in MATLAB format to facilitate off-line signal processing. Examples of local field potential signal acquisitions from the mouse hippocampus are reported to illustrate software features.
{"title":"A software-based platform for multichannel electrophysiological data acquisition","authors":"G. Frigo, M. Rubega, G. Lezziero, R. Fontana, C. Cecchetto, S. Vassanelli, G. Sparacino, Matteo Bertocco","doi":"10.1109/MeMeA.2015.7145227","DOIUrl":"https://doi.org/10.1109/MeMeA.2015.7145227","url":null,"abstract":"Recent improvements in microelectrodes technology have enabled neuroscientists to record electrophysiological signals from hundreds of neurons and simultaneously from a large number of channels. However, several environmental factors may introduce noise and artefacts and affect proper interpretation of recordings. Thus, the development of appropriate signal acquisition and processing platforms dealing with large data sets and in real-time represents a current fundamental challenge. In the present work, we present an easily-expandable Lab VIEW based software for handling data in real-time during a multichannel neurophysiological signal acquisition. The software was designed to exploit modern MultiCore CPUs for large scale data processing and, by freely setting key acquisition parameters, to work with virtually any kind of biological signal. The software allows for data storage in MATLAB format to facilitate off-line signal processing. Examples of local field potential signal acquisitions from the mouse hippocampus are reported to illustrate software features.","PeriodicalId":277757,"journal":{"name":"2015 IEEE International Symposium on Medical Measurements and Applications (MeMeA) Proceedings","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-05-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124023067","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：