Non-Invasive Blood Glucose Estimation System Based on a Neural Network with Dual-Wavelength Photoplethysmography and Bioelectrical Impedance Measuring.

This study proposed a noninvasive blood glucose estimation system based on dual-wavelength photoplethysmography (PPG) and bioelectrical impedance measuring technology that can avoid the discomfort created by conventional invasive blood glucose measurement methods while accurately estimating blood glucose. The measured PPG signals are converted into mean, variance, skewness, kurtosis, standard deviation, and information entropy. The data obtained by bioelectrical impedance measuring consist of the real part, imaginary part, phase, and amplitude size of 11 types of frequencies, which are converted into features through principal component analyses. After combining the input of seven physiological features, the blood glucose value is finally obtained as the input of the back-propagation neural network (BPNN). To confirm the robustness of the system operation, this study collected data from 40 volunteers and established a database. From the experimental results, the system has a mean squared error of 40.736, a root mean squared error of 6.3824, a mean absolute error of 5.0896, a mean absolute relative difference of 4.4321%, and a coefficient of determination (R Squared, R2) of 0.997, all of which fall within the clinically accurate region A in the Clarke error grid analyses.

Feature Fusion of a Deep-Learning Algorithm into Wearable Sensor Devices for Human Activity Recognition.

This paper presents a wearable device, fitted on the waist of a participant that recognizes six activities of daily living (walking, walking upstairs, walking downstairs, sitting, standing, and laying) through a deep-learning algorithm, human activity recognition (HAR). The wearable device comprises a single-board computer (SBC) and six-axis sensors. The deep-learning algorithm employs three parallel convolutional neural networks for local feature extraction and for subsequent concatenation to establish feature fusion models of varying kernel size. By using kernels of different sizes, relevant local features of varying lengths were identified, thereby increasing the accuracy of human activity recognition. Regarding experimental data, the database of University of California, Irvine (UCI) and self-recorded data were used separately. The self-recorded data were obtained by having 21 participants wear the device on their waist and perform six common activities in the laboratory. These data were used to verify the proposed deep-learning algorithm on the performance of the wearable device. The accuracy of these six activities in the UCI dataset and in the self-recorded data were 97.49% and 96.27%, respectively. The accuracies in tenfold cross-validation were 99.56% and 97.46%, respectively. The experimental results have successfully verified the proposed convolutional neural network (CNN) architecture, which can be used in rehabilitation assessment for people unable to exercise vigorously.

Optical Design with Narrow-Band Imaging for a Capsule Endoscope.

The study proposes narrow-band imaging (NBI) lens design of 415 nm and 540 nm of a capsule endoscope (CE). The researches show that in terms of the rate of accuracy in detecting and screening neoplastic and nonneoplastic intestinal lesions, the NBI system outperformed that of traditional endoscopes and rivaled that of chromoendoscopes. In the proposed NBI CE optical system, the simulation result shows the field of view (FOV) was 109.8°; the modulation transfer function (MTF) could achieve 12.5% at 285 lp/mm and 34.1% at 144 lp/mm. The relative illumination reaches more than 60%, and the system total length was less than 4 mm. Finally, this design provides high-quality images for a 300-megapixel 1/4″ CMOS image sensor with a pixel size of 1.75 µm.

A Study of Dispersion Compensation of Polarization Multiplexing-Based OFDM-OCDMA for Radio-over-Fiber Transmissions.

Chromatic dispersion from optical fiber is the most important problem that produces temporal skews and destroys the rectangular structure of code patterns in the spectra-amplitude-coding-based optical code-division multiple-access (SAC-OCDMA) system. Thus, the balance detection scheme does not work perfectly to cancel multiple access interference (MAI) and the system performance will be degraded. Orthogonal frequency-division multiplexing (OFDM) is the fastest developing technology in the academic and industrial fields of wireless transmission. In this study, the radio-over-fiber system is realized by integrating OFDM and OCDMA via polarization multiplexing scheme. The electronic dispersion compensation (EDC) equalizer element of OFDM integrated with the dispersion compensation fiber (DCF) is used in the proposed radio-over-fiber (RoF) system, which can efficiently suppress the chromatic dispersion influence in long-haul transmitted distance. A set of length differences for 10 km-long single-mode fiber (SMF) and 4 km-long DCF is to verify the compensation scheme by relative equalizer algorithms and constellation diagrams. In the simulation result, the proposed dispersion mechanism successfully compensates the dispersion from SMF and the system performance with dispersion equalizer is highly improved.

Study of optical design of three-dimensional digital ophthalmoscopes.

This study primarily involves using optical zoom structures to design a three-dimensional (3D) human-eye optical sensory system with infrared and visible light. According to experimental data on two-dimensional (2D) and 3D images, human-eye recognition of 3D images is substantially higher (approximately 13.182%) than that of 2D images. Thus, 3D images are more effective than 2D images when they are used at work or in high-recognition devices. In the optical system design, infrared and visible light wavebands were incorporated as light sources to perform simulations. The results can be used to facilitate the design of optical systems suitable for 3D digital ophthalmoscopes.

Aspherical lens design using hybrid neural-genetic algorithm of contact lenses.

The design of complex contact lenses involves numerous uncertain variables. How to help an optical designer to first design the optimal contact lens to reduce discomfort when wearing a pair of glasses is an essential design concern. This study examined the impact of aberrations on contact lenses to optimize a contact lens design for myopic and astigmatic eyes. In general, two aspherical surfaces can be assembled in an optical system to reduce the overall volume size. However, this design reduces the spherical aberration (SA) values at wide contact radii. The proposed optimization algorithm with optical design can be corrected to improve the SA value and, thus, reduce coma aberration (TCO) values and enhance the modulation transfer function (MTF). This means integrating a modified genetic algorithm (GA) with a neural network (NN) to optimize multiple-quality characteristics, namely the SA, TCO, and MTF, of contact lenses. When the proposed optional weight NN-GA is implemented, the weight values of the fitness function can be varied to adjust system performance. The method simplifies the selection of parameters in the optimization of optical systems. Compared with the traditional CODE V built-in optimal scheme, the proposed scheme is more flexible and intuitive to improve SA, TCO, and MTF values by 50.03%, 45.78%, and 24.7%, respectively.

Aspherical Lens Design Using Genetic Algorithm for Reducing Aberrations in Multifocal Artificial Intraocular Lens.

A complex intraocular lens (IOL) design involving numerous uncertain variables is proposed. We integrated a genetic algorithm (GA) with the commercial optical design software of (CODE V) to design a multifocal IOL for the human eye. We mainly used an aspherical lens in the initial state to the crystalline type; therefore, we used the internal human eye model in the software. The proposed optimized algorithm employs a GA method for optimally simulating the focusing function of the human eye; in this method, the thickness and curvature of the anterior lens and the posterior part of the IOL were varied. A comparison of the proposed GA-designed IOLs and those designed using a CODE V built-in optimal algorithm for 550 degrees myopia and 175 degrees astigmatism conditions of the human eye for pupil size 6 mm showed that the proposed IOL design improved the spot size of root mean square (RMS), tangential coma (TCO) and modulation transfer function (MTF) at a spatial frequency of 30 with a pupil size of 6 mm by approximately 17%, 43% and 35%, respectively. However, the worst performance of spherical aberration (SA) was lower than 46%, because the optical design involves a tradeoff between all aberrations. Compared with the traditional CODE V built-in optimal scheme, the proposed IOL design can efficiently improve the critical parameters, namely TCO, RMS, and MTF.

Study of optical design of Blu-ray pickup head system with a liquid crystal element.

This paper proposes a newly developed optical design and an active compensation method for a Blu-ray pickup head system with a liquid crystal (LC) element. Different from traditional pickup lens design, this new optical design delivers performance as good as the conventional one but has more room for tolerance control, which plays a role in antishaking devices, such as portable Blu-ray players. A hole-pattern electrode and LC optics with external voltage input were employed to generate a symmetric nonuniform electrical field in the LC layer that directs LC molecules into the appropriate gradient refractive index distribution, resulting in the convergence or divergence of specific light beams. LC optics deliver fast and, most importantly, active compensation through optical design when errors occur. Simulations and tolerance analysis were conducted using Code V software, including various tolerance analyses, such as defocus, tilt, and decenter, and their related compensations. Two distinct Blu-ray pickup head system designs were examined in this study. In traditional Blu-ray pickup head system designs, the aperture stop is always set on objective lenses. In the study, the aperture stop is on the LC lens as a newly developed lens. The results revealed that an optical design with aperture stop set on the LC lens as an active compensation device successfully eliminated up to 57% of coma aberration compared with traditional optical designs so that this pickup head lens design will have more space for tolerance control.

Using a fiber loop and fiber bragg grating as a fiber optic sensor to simultaneously measure temperature and displacement.

This study integrated a fiber loop manufactured by using commercial fiber (SMF-28, Corning) and a fiber Bragg grating (FBG) to form a fiber optic sensor that could simultaneously measure displacement and temperature. The fiber loop was placed in a thermoelectric cooling module with FBG affixed to the module, and, consequently, the center wavelength displacement of FBG was limited by only the effects of temperature change. Displacement and temperature were determined by measuring changes in the transmission of optical power and shifts in Bragg wavelength. This study provides a simple and economical method to measure displacement and temperature simultaneously.