Pub Date : 1994-11-03DOI: 10.1109/IEMBS.1994.415222
K. Kilgore, R. Lauer, P. Peckham
A device for measuring torques generated about the joints of the fingers has been developed. The design utilizes a parallelogram construction that allows the device to fit different sizes of hands. The device has the capability to measure isometric moments generated about the MP, PIP and DIP joints of a single digit. Four of these devices can be used to make simultaneous measurements of all the moments generated about all three joints of the four fingers. The device also acts as a splint, allowing each joint to be positioned and locked at any angle through the range of motion of the joint. This device will be utilized in the synthesis of grasp patterns using functional electrical stimulation.<>
{"title":"A transducer for measurement of finger joint torques","authors":"K. Kilgore, R. Lauer, P. Peckham","doi":"10.1109/IEMBS.1994.415222","DOIUrl":"https://doi.org/10.1109/IEMBS.1994.415222","url":null,"abstract":"A device for measuring torques generated about the joints of the fingers has been developed. The design utilizes a parallelogram construction that allows the device to fit different sizes of hands. The device has the capability to measure isometric moments generated about the MP, PIP and DIP joints of a single digit. Four of these devices can be used to make simultaneous measurements of all the moments generated about all three joints of the four fingers. The device also acts as a splint, allowing each joint to be positioned and locked at any angle through the range of motion of the joint. This device will be utilized in the synthesis of grasp patterns using functional electrical stimulation.<<ETX>>","PeriodicalId":344622,"journal":{"name":"Proceedings of 16th Annual International Conference of the IEEE Engineering in Medicine and Biology Society","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132093369","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 : 1994-11-03DOI: 10.1109/IEMBS.1994.412110
M. Schaldach, I. Khassanov
Optimal rate-adaptive pacemaker systems have been developed on the basis of intracardiac impedance measurements in which the autonomic nervous system information as measured by ventricular inotropic parameter is used as the regulatory signal. The complex analog and digital functions assembled using very large scale integration technology has led to broad clinical applications supporting a wide range of pacing therapies.<>
{"title":"Rate adaptive pacemakers: a biomedical challenge","authors":"M. Schaldach, I. Khassanov","doi":"10.1109/IEMBS.1994.412110","DOIUrl":"https://doi.org/10.1109/IEMBS.1994.412110","url":null,"abstract":"Optimal rate-adaptive pacemaker systems have been developed on the basis of intracardiac impedance measurements in which the autonomic nervous system information as measured by ventricular inotropic parameter is used as the regulatory signal. The complex analog and digital functions assembled using very large scale integration technology has led to broad clinical applications supporting a wide range of pacing therapies.<<ETX>>","PeriodicalId":344622,"journal":{"name":"Proceedings of 16th Annual International Conference of the IEEE Engineering in Medicine and Biology Society","volume":" 21","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132158104","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 : 1994-11-03DOI: 10.1109/IEMBS.1994.411819
G. Schreier, T. Auer, H. Hutten, M. Schaldach, H. Muller, F. Iberer, K. Tscheliessnigg
Paced epicardial electrograms from heart transplants were recorded via implanted telemetric pacemakers. Signals were processed automatically and extracted parameters from the ventricular evoked response are compared to the degree of acute rejection according to histological findings from endomyocardial biopsy. Statistical analysis and an estimation of the diagnostic quality of this noninvasive method for detection of acute cardiac rejection are presented.<>
{"title":"Telemetric recording of the ventricular evoked response for noninvasive rejection monitoring after heart transplantation","authors":"G. Schreier, T. Auer, H. Hutten, M. Schaldach, H. Muller, F. Iberer, K. Tscheliessnigg","doi":"10.1109/IEMBS.1994.411819","DOIUrl":"https://doi.org/10.1109/IEMBS.1994.411819","url":null,"abstract":"Paced epicardial electrograms from heart transplants were recorded via implanted telemetric pacemakers. Signals were processed automatically and extracted parameters from the ventricular evoked response are compared to the degree of acute rejection according to histological findings from endomyocardial biopsy. Statistical analysis and an estimation of the diagnostic quality of this noninvasive method for detection of acute cardiac rejection are presented.<<ETX>>","PeriodicalId":344622,"journal":{"name":"Proceedings of 16th Annual International Conference of the IEEE Engineering in Medicine and Biology Society","volume":" 21","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132158914","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 : 1994-11-03DOI: 10.1109/IEMBS.1994.412174
R. Pendekanti, C. Henriquez, P. Wolf
The potential gradient fields created by transvenous defibrillation (TVD) electrodes during internal defibrillation are often calculated using volume conductor models. Most defibrillation models represent the TVD electrode as an equipotential cylindrical rod and do not account for electrode features like electrode resistance, surface geometry, and electrode-electrolyte impedance. This study looks into the effects of the first two features. Results from tank studies and finite element models indicate that defibrillation models that do not consider the effects of surface geometry and electrode resistance can underestimate the total defibrillation impedance by about 10%.<>
{"title":"The importance of representing surface geometry and electrode resistance of transvenous electrodes in defibrillation models","authors":"R. Pendekanti, C. Henriquez, P. Wolf","doi":"10.1109/IEMBS.1994.412174","DOIUrl":"https://doi.org/10.1109/IEMBS.1994.412174","url":null,"abstract":"The potential gradient fields created by transvenous defibrillation (TVD) electrodes during internal defibrillation are often calculated using volume conductor models. Most defibrillation models represent the TVD electrode as an equipotential cylindrical rod and do not account for electrode features like electrode resistance, surface geometry, and electrode-electrolyte impedance. This study looks into the effects of the first two features. Results from tank studies and finite element models indicate that defibrillation models that do not consider the effects of surface geometry and electrode resistance can underestimate the total defibrillation impedance by about 10%.<<ETX>>","PeriodicalId":344622,"journal":{"name":"Proceedings of 16th Annual International Conference of the IEEE Engineering in Medicine and Biology Society","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130810876","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 : 1994-11-03DOI: 10.1109/IEMBS.1994.411852
A. Huynen, R. Giesen, R. Aarnink, J. J. de la Rosette, F. Debruyne, H. Wijkstra
Describes position dependent correction algorithms for image processing parameters in ultrasonographic images. The parameters are calculated using the co-occurrence algorithm. By the nature of ultrasound and the rotation of a single element transducer depth- and angle dependencies occur. For angle dependencies a pre-processing algorithm is described. For depth dependencies a post-calculation correction is described.<>
{"title":"Pre- and postprocessing algorithms for the correction of position dependencies of image processing parameters in ultrasonographic prostate images","authors":"A. Huynen, R. Giesen, R. Aarnink, J. J. de la Rosette, F. Debruyne, H. Wijkstra","doi":"10.1109/IEMBS.1994.411852","DOIUrl":"https://doi.org/10.1109/IEMBS.1994.411852","url":null,"abstract":"Describes position dependent correction algorithms for image processing parameters in ultrasonographic images. The parameters are calculated using the co-occurrence algorithm. By the nature of ultrasound and the rotation of a single element transducer depth- and angle dependencies occur. For angle dependencies a pre-processing algorithm is described. For depth dependencies a post-calculation correction is described.<<ETX>>","PeriodicalId":344622,"journal":{"name":"Proceedings of 16th Annual International Conference of the IEEE Engineering in Medicine and Biology Society","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130940153","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 : 1994-11-03DOI: 10.1109/IEMBS.1994.415444
P. M. Bentley, J. Mcdonnell
Describes the application of the wavelet transform (WT) to the characterisation of sounds recorded from patients diagnosed as suffering from aortic valvular disease. Due to the multiresolution analysis performed by the WT, it is highly applicable to the analysis of the complex sounds generated over a whole cardiac cycle. Results clearly show that the WT can be used to quantitatively describe sounds produced during the cardiac cycle. The comparison of these quantitative time and frequency characteristics in normal and pathological cases offers definite diagnostic potential.
{"title":"Analysis of heart sounds using the wavelet transform","authors":"P. M. Bentley, J. Mcdonnell","doi":"10.1109/IEMBS.1994.415444","DOIUrl":"https://doi.org/10.1109/IEMBS.1994.415444","url":null,"abstract":"Describes the application of the wavelet transform (WT) to the characterisation of sounds recorded from patients diagnosed as suffering from aortic valvular disease. Due to the multiresolution analysis performed by the WT, it is highly applicable to the analysis of the complex sounds generated over a whole cardiac cycle. Results clearly show that the WT can be used to quantitatively describe sounds produced during the cardiac cycle. The comparison of these quantitative time and frequency characteristics in normal and pathological cases offers definite diagnostic potential.","PeriodicalId":344622,"journal":{"name":"Proceedings of 16th Annual International Conference of the IEEE Engineering in Medicine and Biology Society","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128824846","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 : 1994-11-03DOI: 10.1109/IEMBS.1994.411975
A. Kostov, B. Andrews, R. Stein, D. Popovic, W. W. Armstrong
Two machine learning techniques were evaluated for automatic design of a rule-based control of functional electrical stimulation (FES) for locomotion of spinal cord injured humans. The task was to map the relationship between sensory information and the FES-control signal by using off-line supervised training. Signals were recorded using pressure sensors installed in insoles of a patient's shoes and goniometers attached across the joints of the affected leg. The FES-control signal consisted of pulses corresponding to time intervals when the patient pressed on the manual push-button to deliver the stimulation during FES-assisted ambulation. The machine learning techniques evaluated were the adaptive logic network (ALN) and inductive learning algorithm (IL). Results to date suggest that, given the same training data, the IL learned faster than ALN while both performed the test rapidly. The generalization was better with an ALN, especially if past points were used to reflect the time dimension. Both techniques were able to predict future stimulation events. An advantage of ALN was that it can be retrained with new data without losing previously collected knowledge. The advantages of IL were that IL produces explicit and comprehensible trees and that the relative importance of each sensory contribution can be quantified.<>
{"title":"Machine learning in control of functional electrical stimulation for locomotion","authors":"A. Kostov, B. Andrews, R. Stein, D. Popovic, W. W. Armstrong","doi":"10.1109/IEMBS.1994.411975","DOIUrl":"https://doi.org/10.1109/IEMBS.1994.411975","url":null,"abstract":"Two machine learning techniques were evaluated for automatic design of a rule-based control of functional electrical stimulation (FES) for locomotion of spinal cord injured humans. The task was to map the relationship between sensory information and the FES-control signal by using off-line supervised training. Signals were recorded using pressure sensors installed in insoles of a patient's shoes and goniometers attached across the joints of the affected leg. The FES-control signal consisted of pulses corresponding to time intervals when the patient pressed on the manual push-button to deliver the stimulation during FES-assisted ambulation. The machine learning techniques evaluated were the adaptive logic network (ALN) and inductive learning algorithm (IL). Results to date suggest that, given the same training data, the IL learned faster than ALN while both performed the test rapidly. The generalization was better with an ALN, especially if past points were used to reflect the time dimension. Both techniques were able to predict future stimulation events. An advantage of ALN was that it can be retrained with new data without losing previously collected knowledge. The advantages of IL were that IL produces explicit and comprehensible trees and that the relative importance of each sensory contribution can be quantified.<<ETX>>","PeriodicalId":344622,"journal":{"name":"Proceedings of 16th Annual International Conference of the IEEE Engineering in Medicine and Biology Society","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128868864","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 : 1994-11-03DOI: 10.1109/IEMBS.1994.412144
E. Russek-Cohen
Summary form only given as follows: Research and the corresponding aspects of data analysis can be broken into two parts, one exploratory and one confirmatory. In exploratory data analysis one tries to narrow down potential hypotheses for subsequent studies. Examples of these can include screening drugs for potential use in cancer treatment using in-vitro tests or screening monoclonal antibodies for use in disease identification. In each of these cases, there are way too many "treatments" for traditional hypothesis testing. Exploratory tools provide a means of reducing the number of treatments for subsequent evaluation. Here, the authors examine the use of distance based methods for exploratory data analysis. Such techniques include cluster analysis and multidimensional scaling. These techniques can be used to group observations and detect outliers. The authors also describe methods for comparing the results of 2 or more cluster analyses or 2 or more ordinations using multidimensional scaling analyses. Examples from a variety of medical and biological applications are included.<>
{"title":"Distance based methods for exploratory data analysis","authors":"E. Russek-Cohen","doi":"10.1109/IEMBS.1994.412144","DOIUrl":"https://doi.org/10.1109/IEMBS.1994.412144","url":null,"abstract":"Summary form only given as follows: Research and the corresponding aspects of data analysis can be broken into two parts, one exploratory and one confirmatory. In exploratory data analysis one tries to narrow down potential hypotheses for subsequent studies. Examples of these can include screening drugs for potential use in cancer treatment using in-vitro tests or screening monoclonal antibodies for use in disease identification. In each of these cases, there are way too many \"treatments\" for traditional hypothesis testing. Exploratory tools provide a means of reducing the number of treatments for subsequent evaluation. Here, the authors examine the use of distance based methods for exploratory data analysis. Such techniques include cluster analysis and multidimensional scaling. These techniques can be used to group observations and detect outliers. The authors also describe methods for comparing the results of 2 or more cluster analyses or 2 or more ordinations using multidimensional scaling analyses. Examples from a variety of medical and biological applications are included.<<ETX>>","PeriodicalId":344622,"journal":{"name":"Proceedings of 16th Annual International Conference of the IEEE Engineering in Medicine and Biology Society","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126735684","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 : 1994-11-03DOI: 10.1109/IEMBS.1994.412089
L. R. Johnson, J.R. Shanebrook
A new system for visualizing the steady flow of a new type of blood analog fluid in a model side-to-end proximal anastomosis is presented. Photographic results indicate a "figure eight" flow pattern occurs in the occluded distal artery section. This flow pattern affects the flow field entering the model graft section and may help explain why proximal graft junctions are less likely to clot than distal junctions.<>
{"title":"Flow visualization with a model side-to-end proximal anastomosis","authors":"L. R. Johnson, J.R. Shanebrook","doi":"10.1109/IEMBS.1994.412089","DOIUrl":"https://doi.org/10.1109/IEMBS.1994.412089","url":null,"abstract":"A new system for visualizing the steady flow of a new type of blood analog fluid in a model side-to-end proximal anastomosis is presented. Photographic results indicate a \"figure eight\" flow pattern occurs in the occluded distal artery section. This flow pattern affects the flow field entering the model graft section and may help explain why proximal graft junctions are less likely to clot than distal junctions.<<ETX>>","PeriodicalId":344622,"journal":{"name":"Proceedings of 16th Annual International Conference of the IEEE Engineering in Medicine and Biology Society","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126764131","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 : 1994-11-03DOI: 10.1109/IEMBS.1994.415352
B. Kermani, M. White, H. Nagle
Overtraining is a serious problem in the neural network algorithms, including the backpropagation algorithm. In order to measure the performance of a neural network, ordinarily some of the data is sacrificed and used as a test set (cross-validation method). When the data is very scarce or is expensive, e.g. medical applications such as computer aided diagnosis, this waste of the data becomes intolerable. A new technique is introduced which uses the shape of the training mean squared error graph versus number of epochs and predicts when is the best time (epoch number) to discontinue the training.
{"title":"A new method in obtaining a better generalization in artificial neural networks","authors":"B. Kermani, M. White, H. Nagle","doi":"10.1109/IEMBS.1994.415352","DOIUrl":"https://doi.org/10.1109/IEMBS.1994.415352","url":null,"abstract":"Overtraining is a serious problem in the neural network algorithms, including the backpropagation algorithm. In order to measure the performance of a neural network, ordinarily some of the data is sacrificed and used as a test set (cross-validation method). When the data is very scarce or is expensive, e.g. medical applications such as computer aided diagnosis, this waste of the data becomes intolerable. A new technique is introduced which uses the shape of the training mean squared error graph versus number of epochs and predicts when is the best time (epoch number) to discontinue the training.","PeriodicalId":344622,"journal":{"name":"Proceedings of 16th Annual International Conference of the IEEE Engineering in Medicine and Biology Society","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126251693","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：