RESUMEN
Objective To propose an Alzheimer's disease(AD)classification method based on deep learning and multimodal physiological data.Methods Multimodal data from the Alzheimer's Disease Neuroimaging Initiative(ADNI)database of AD patients,early mild cognitive impairment(EMCI)patients,late mild cognitive impairment(LMCI)patients and normal cognition(NC)subjects were selected.Three networks were used for AD classification,of which an improved New_ResNet50 network extracted the features of MRI images of the subject's brain to realize AD classification,a 3D-Unet-Attention network segmented the hippocampus images and implemented residual network-based AD classification,and a multi-layer perception(MLP)network carried out AD classification based on patient physiological data and hippocampus size,and the final classification results were determined with the voting method.Comparison analyses were performed on the classification results by the improved New_ResNet50 network model,3D-Unet-Attention network model or traditional network models,and the improved New_ResNet50 network model,3D-Unet-Attention network model and MLP network model were all compared with the fusion network model involving in the three networks model above.Results The improved New_ResNet50 network model and 3D-Unet-Attention network model both had the classification accuracy enhanced when compared with the traditional network models,and the fusion network model had a classification accuracy of 97.99％for AD patients and control normal,which was higher by 1.51％,1.51％and 14.62％than those by the improved New_ResNet50 network model,3D-Unet-Attention network model and MLP network model respectively.Conclusion The classification method proposed behaves well for AD classification,and can be used for auxiliary diagnosis of AD.[Chinese Medical Equipment Journal,2023,44(11):1-8]
RESUMEN
Current research,application,advantages and disadvantages of wearable health monitoring items based on soft sensor technology in foreign countries and China were introduced and analyzed,and the application in diseases monitoring,emotion monitoring,monitoring of rehabilitation training,monitoring of sport training,operational safety monitoring in special environments,casualty search during war and disaster,monitoring of the elderly and children and etc were also described.The characteristics of the items were analyzed,and some countermeasures were put forward to solve the problems in materials safety,data quality,industrial standard,unclear efficacy and etc.The study and prospective of soft physiological sensing technology were expounded in detail.
RESUMEN
Obiective To study and design a real-time monitoring system based on ZigBee wireless technology in ICU wards. Methods The framework and function of this system are analyzed and designed, which specifies the main function of physiological data acquisition and wireless transmission mode, monitor base and monitor center, and introduces the development environment and important technology realizing this system. Results The system is convenient to the treatment of patients, and the monitor base and monitor center can assist doctors to diagnose and treat patient's condition effectively. Conclusion The system utilizes ZigBee wireless communication technology as the communication technology of physiological data acquisition, which is well suited to organize the preceding wireless sensor network of 1CU ward monitor, and can reduce the cable wire splices on patient* largely, and is convenient for the treatments of patients. The monitor base and monitor center of the system can comprehensively and accurately record the vital signs, medical treatment and nursing of patients and it is convenient for doctors to supervise patients' condition, providing medical treatment, and nursing strategy pointer.
RESUMEN
A posição dos analistas do comportamento sobre a inclusão de dados fisiológicos na análise do comportamento varia. David Schaal, um analista do comportamento contemporâneo, apontou vantagens de tal inclusão para a análise do comportamento em quatro pontos: (a) identificação de mecanismos de retenção do condicionamento operante; (b) a fisiologia dá explicações quando as descrições não são suficientes; (c) elucidação de mecanismos celular e neural de reforçamento e (d) caracterização de alterações degenerativas no cérebro. O presente artigo proporciona discussões futuras desses pontos se eles realmente representam uma vantagem `a análise do comportamento. É argumentado e exemplificado que a análise do comportamento e a neurociência não são multuamente exclusivas. Por fim, as condições sob as quais a inclusão de dados fisiológicos na análise do comportamento representa uma vantagem à área são delineadas.
The position of behavior analysts on the inclusion of physiological data in behavior analysis varies. David Schaal, a contemporary behavior analyst, addressed advantages of such inclusion to behavior analysis in four points: (a) identification of retention mechanisms of operant conditioning; (b) physiology provides explanations when descriptions are not sufficient; (c) elucidation of cellular and neural mechanisms of reinforcement; and (d) characterization of degenerative alterations in the brain. The present paper provides further discussion of these points as to whether they truly represent an advantage to behavior analysis. It is argued and exemplified that behavior analysis and neuroscience are not mutually exclusive. Finally, the conditions under which the inclusion of physiological data in behavior analysis represents an advantage to the field are delineated.