The problem of inverse correlation filters design to recognize a set of objects is considered as the problem of regression parameters estimation on the base of input data arrays and desirable response. The data and response should be processes with zero mean to consider this problem as evaluation of regression parameters. The problem is solved using the least squares method with regularization. The regularization is optimized to achieve high resolution of the filters in conjunction with capture’ broad band of objects given by a set of templates. The least squares method is using in the terms of singular value decomposition that made it possible to linearize the nonlinear ridge regression optimization problem. The methods to false recognitions elimination are considered, It was shown that the regression approach gives additional condition to recognize classes of objects. This allows to have more high accuracy in recognition of desired objects on a foreign background in comparison with other correlation filters types.
Modern technologies for recording human physiological parameters are developing very dynamically. The use of optical methods for measuring human physiological parameters, such as glucose, bilirubin, pulse, and blood saturation, have become key tools in non-invasive diagnostics and monitoring of patients' health. These technologies utilize the properties of light to obtain accurate and fast results, which can improve the efficiency of medical services. The article discusses the basic principles of optical biosensors, their application in measuring these physiological parameters and integration with telemedicine diagnostic systems. The prospects for the introduction of the Internet of Things (IoT) and artificial intelligence (AI) to create telemedicine systems that provide continuous real-time monitoring of patients and a rapid response to changes in their health status are also considered. We propose a system structure that allows remote monitoring of key health indicators of patients, especially infants and children, as well as patients with chronic diseases such as diabetes and cardiovascular diseases. The introduction of such technologies helps to increase the availability of medical services, reduce the number of hospitalizations, and improve the quality of life of patients.
The authors simulated and accompanied by optical measurements various available design options for constructing output stages of laser medical equipment in light of possible implementations under certain limitations in the design, production and operation processes. The design option for a flexible optical fiber proposed by the authors is characterized by its manufacturability and structural simplicity, ensures effective, repeatable transformation of homogeneity in the beam and, most likely, allows for complex optimization. In the case of relevance of light spots in the form of elongated rectangles, it may be interesting to use a combination of individual parallel beams and lens assemblies. When removing the restriction of mandatory beam collimation, the use of channel waveguides as an aperture is of particular interest (both from the point of view of reducing optical radiation power losses and variability of the performance of output cascades of laser equipment).
The paper reveals a method of highly productive determination of normalized vectors for the surfaces of threedimensional objects. The method is based on the approximated calculation of even vectors of the rasterization line by adding the odd neighboring unit vectors. For the determination of further need in the normalization of obtained vectors, the computation of special threshold metrics is proposed. For the accelerated calculation of the threshold metrics, the developed expressions are given. In case of normalization of even vectors, it is recommended to use the developed polynomial approximate expressions. The plots of relative errors between obtained simplified and reference expressions are given. The possibility of increasing the productivity of the method by calculating the shared vector coordinate increments for each rasterization line is analyzed. The experimental research of productivity gain from the new method usage is carried out. During the study, the six variants of possible method usage are considered. The results of the research analysis are given in the table. The new method is designed for usage in highly effective visualization systems.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.