This study presents a high-sensitivity optical glucose sensor based on a tapered fiber Mach-Zehnder interferometer (MZI). The sensor utilizes a tapered optical fiber integrated into the sensing arm of the MZI system, enhancing sensitivity through strong evanescent field interaction. Two configurations were investigated: single-mode taper fiber and single-multi-single mode taper fiber (SMSTF). Experimental results demonstrated that the SMSTF configuration achieved superior performance, with a sensitivity of 0.3042 nm mg ml-1 and linearity of 98%. Further enhancement was achieved by integrating the external MZI system, improving sensitivity to 0.6509 nm mg ml-1 with a linearity of 99%. The sensor exhibited excellent stability, with a limit of detection of 0.3539 mg ml-1. Comparative analysis with prior optical glucose sensors highlights the sensor's advancements in sensitivity, range, and practical usability. These findings establish the proposed sensor as a promising candidate for continuous glucose monitoring applications, with potential for integration into healthcare systems for diabetes management.

BACKGROUND:Most noninvasive blood glucose technologies, especially wearable photoplethysmography devices, require multiple calibrations and are often limited to narrow cohorts such as unmedicated or mild cases. We assess whether a single pretest once per month can meet clinical accuracy while broadening applicability through cohort-specific models. METHODS:We develop models for three groups: (i) individuals not using antidiabetic drugs, (ii) those using oral antidiabetic drugs only, and (iii) those using antidiabetic drugs in combination with other medications. Models are trained on cohort data with and without the monthly pretest and are then applied directly to personal testing without retraining. Inputs include dual-channel photoplethysmography signals and an inferred HbA1c (glycated hemoglobin) feature. Accuracy is summarized by mean absolute relative difference, clinical safety by the Parkes Error Grid, and improvements by a nonparametric rank-sum test. RESULTS:Here, we show that the best models using a single monthly pretest achieve mean absolute relative differences of 9.59, 12.23, and 16.40% for groups (i), (ii), and (iii), respectively. In the most complex group (iii), prediction errors are significantly lower than our earlier work according to the rank-sum test. The single-pretest models produce no clinically unacceptable readings on the Parkes Error Grid, likely due to dual-channel input and the inferred glycated-hemoglobin feature. CONCLUSIONS:A single monthly pretest enables accurate and clinically safe noninvasive glucose measurement across diverse patient groups. The approach operates without retraining or fine-tuning and can adapt to new users and devices through edge computing, supporting integration into current wearables for everyday diabetes management and public-health prevention.

Optical fiber sensors are widely used to monitor environmental disturbances that may trigger or affect mining landslides, a complex phenomenon that involves various factors and can cause severe damage. In this study, we propose a method to detect the curvature of a bent optical fiber, which affects the optical signals traveling through it, using deep learning and time series signal processing. We use a Mach-Zehnder interferometer (MZI) sensor and a single-mode fiber (SMF) cable to capture the interference signal caused by different bending angles. We apply a transformation random convolutional kernel (TRANCE) to reduce the signal and extract its mean and standard deviation as features. We train a dense neural network (DNN) with three hidden layers to classify the bending events into four categories: low, medium, high, and extreme. We evaluate our method on a dataset of 400 samples and achieve an average accuracy of 99% in the confusion matrix and the fifty times tenfold validation experiments. Our method outperforms other methods that use multimode fiber (MMF), speckle images, and convolutional neural networks (CNNs) in terms of accuracy, speed, and generalization. Our method also has the advantages of using SMF, which enables integrated sensing and communication, and using 1D signals, which are easier to process than 2D images. Our method is suitable for high-speed signals containing information in dangerous environments.

Cuffless blood pressure (BP) measurements have long been anticipated, and the PPG (Photoplethysmography)-only method is the most promising one since already embedded in many wearable devices. To further meet the clinical accuracy requirements, PPG-only BP predictions with personalized modeling for overcoming personal deviations have been widely studied, but all required tens to hundreds of minutes of personal PPG measurements for training. Moreover, their accurate test periods without calibration practice were not reported. In this work, we collected records of PPG data from our recruited subjects in real-life scenarios instead of relying on the openly available MIMIC dataset obtained from intensive care unit (ICU) patients. Since our objective is commercial application and a substantial reduction in training data, we tailored our model training to closely mimic real-world usage. To achieve this, we developed a training approach that only requires 9-minutes of personal PPG signal recordings and mixed with other PPG data from our recruited 364 subjects. The modeling is conducted with two-channel paired inputs to the convolutional neural network (CNN)-based model, which we called Mixed Deduction Learning (MDL). The test results of 88 samples from 15 subjects, under testing period up to 30-plus days without extra calibration, revealed that MDL meets most of the standards of AAMI, BHS, and IEEE 1708-2014 (for static test only) for BP measurement devices, which indicates MDL's long-term stability and consistency. Furthermore, we found that the model with two-channel inputs presents a trend of improving performance as the pool of mixed training data increased, while the conventional one-channel input revealed degraded performance. The outperformance of MDL is attributed to many significant features remained in the first CNN layer even when mixing personal 9-minutes data with the other 364 subjects. Consequently, PPG-only with MDL introduces a new avenue for overcoming challenges in training due to personal physiological variations. Given our consideration of real-life usage, this technology can be seamlessly translated to commercial applications.

Curvature detection is an essential technique for monitoring landslides, which are frequent and destructive disasters. Existing methods for curvature detection using fiber-optic sensors have limitations such as complex fabrication or large data size. We propose a data processing method for high-accuracy curvature detection that employs deep learning. We experimented using different levels of curvature and compared our method with other methods. Our method achieves 99.82% accuracy for classification and root mean square error of 0.042m−1 for regression with a simpler structure and smaller data size. Our approach demonstrates its potential for landslide detection and integration with communication systems.

The above article [1] presented data on microwave annealing of implanted ions in silicon. There are several typos in the figure captions and labels, and the authors would like to correct them. The text is correct, and the conclusion of [1] is not impacted by these revisions.

Our deep learning model for distributed fiber sensor detection achieves high accuracy 99.29%, recall 66.67%, precision 75.00%, and F1-score 70.59% using an 80/10/10 train-validation-test split. These results demonstrate the effectiveness of our approach and its suitability for distributed fiber sensing applications, especially for low magnitude.

To reduce the error induced by overfitting or underfitting in predicting non-invasive fasting blood glucose (NIBG) levels using photoplethysmography (PPG) data alone, we previously demonstrated that incorporating HbA1c led to a notable 10% improvement in NIBG prediction accuracy (the ratio in zone A of Clarke’s error grid). However, this enhancement came at the cost of requiring an additional HbA1c measurement, thus being unfriendly to users. In this study, the enhanced HbA1c NIBG deep learning model (blood glucose level predicted from PPG and HbA1c) was trained with 1494 measurements, and we replaced the HbA1c measurement (explicit HbA1c) with “implicit HbA1c” which is reversely derived from pretested PPG and finger-pricked blood glucose levels. The implicit HbA1c is then evaluated across intervals up to 90 days since the pretest, achieving an impressive 87% accuracy, while the remaining 13% falls near the CEG zone A boundary. The implicit HbA1c approach exhibits a remarkable 16% improvement over the explicit HbA1c method by covering personal correction items automatically. This improvement not only refines the accuracy of the model but also enhances the practicality of the previously proposed model that relied on an HbA1c input. The nonparametric Wilcoxon paired test conducted on the percentage error of implicit and explicit HbA1c prediction results reveals a substantial difference, with a p-value of 2.75 × 10–7.

Atrial fibrillation (AFib) is a common type of arrhythmia that is often clinically asymptomatic, which increases the risk of stroke significantly but can be prevented with anticoagulation. The photoplethysmogram (PPG) has recently attracted a lot of attention as a surrogate for electrocardiography (ECG) on atrial fibrillation (AFib) detection, with its out-of-hospital usability for rapid screening or long-term monitoring. Previous studies on AFib detection via PPG signals have achieved good results, but were short of intuitive criteria like ECG p-wave absence or not, especially while using interval randomness to detect AFib suffering from conjunction with premature contractions (PAC/PVC). In this study, we newly developed a PPG flux (pulse amplitude) and interval plots-based methodology, simply comprising an irregularity index threshold of 20 and regression error threshold of 0.06 for the precise automatic detection of AFib. The proposed method with automated detection on AFib shows a combined sensitivity, specificity, accuracy, and precision of 1, 0.995, 0.995, and 0.952 across the 460 samples. Furthermore, the flux-interval plot configuration also acts as a very intuitive tool for visual reassessment to confirm the automatic detection of AFib by its distinctive plot pattern compared to other cardiac rhythms. The study demonstrated that exclusive 2 false-positive cases could be corrected after the reassessment. With the methodology's background theory well established, the detection process automated and visualized, and the PPG sensors already extensively used, this technology is very user-friendly and convincing for promoted to in-house AFib diagnostics.

Personalized modeling has long been anticipated to approach precise noninvasive blood glucose measurements, but challenged by limited data for training personal model and its unavoidable outlier predictions. To overcome these long-standing problems, we largely enhanced the training efficiency with the limited personal data by an innovative Deduction Learning (DL), instead of the conventional Induction Learning (IL). The domain theory of our deductive method, DL, made use of accumulated comparison of paired inputs leading to corrections to preceded measured blood glucose to construct our deep neural network architecture. DL method involves the use of paired adjacent rounds of finger pulsation Photoplethysmography signal recordings as the input to a convolutional-neural-network (CNN) based deep learning model. Our study reveals that CNN filters of DL model generated extra and non-uniform feature patterns than that of IL models, which suggests DL is superior to IL in terms of learning efficiency under limited training data. Among 30 diabetic patients as our recruited volunteers, DL model achieved 80% of test prediction in zone A of Clarke Error Grid (CEG) for model training with 12 rounds of data, which was 20% improvement over IL method. Furthermore, we developed an automatic screening algorithm to delete low confidence outlier predictions. With only a dozen rounds of training data, DL with automatic screening achieved a correlation coefficient (R-P) of 0.81, an accuracy score (R-A) of 93.5, a root mean squared error of 13.93 mg/dl, a mean absolute error of 12.07 mg/dl, and 100% predictions in zone A of CEG. The nonparametric Wilcoxon paired test on R-A for DL versus IL revealed near significant difference with p-value 0.06. These significant improvements indicate that a very simple and precise noninvasive measurement of blood glucose concentration is achievable.

Previous non-invasive Diabetes Mellitus (DM) prediction methods for rapid screening suffered from the trade-off between speed and accuracy. The accurate results of questionnaires rely on long and detailed questions thus sacrifice speed, meanwhile, photoplethysmography (PPG) offers convenient and fast testing but lacking accuracy. In this work, we developed a 5-grade model to accurately screen out non-DM subjects (low prediction grades) via one-minute PPG measurement. This efficient and effective rapid screening will practically reduce the loading for further invasive verification on the remaining DM-grade subjects. A total of 2538 subjects are recruited (DM: 1310, non-DM: 1228) with two 1-minute PPG samples taken from each subject. The model includes 8 features: 3 autonomic- and 3 vascular-related PPG features, heart rate, and waist circumference. All 8 features monotonically alter with increased DM prediction grade. The model provides users 5 DM risk grades. While defined grade 1 and grade 2 as non-DM grades, the prediction result shows a low false-negative rate of 13%. If only considering grade 1 as non-DM, the false-negative rate will be significantly reduced to 1.3%. Thus subjects predicted as grades 1 and 2 are substantially away from DM. The remaining subjects with higher DM risk grades such as grades 3, 4, and 5 (or unlikely grade 2) are recommended to take clinical-standard invasive DM test for corresponding therapeutic treatment. A table for assessing the risk index for each feature is also compiled. We have experimentally demonstrated a 1-minute pulsation measurement with PPG-based device (SpO 2 oximeter, smartphone, or wearable device) can be an efficient/effective DM rapid screening technique to filter out non-DM subjects. The resulted high-risk feature indexes also pose as warning signs of the degradation of either autonomic or vascular functions for personal healthcare management. The fast and convenient execution and useful results suggest that our approach is very simple and informative for quick DM risk assessment.

Previously published photoplethysmography-(PPG) based non-invasive blood glucose (NIBG) measurements have not yet been validated over 500 subjects. As illustrated in this work, we increased the number subjects recruited to 2538 and found that the prediction accuracy (the ratio in zone A of Clarke’s error grid) reduced to undesirable 60.6%. We suspect the low prediction accuracy induced by larger sample size might arise from the physiological diversity of subjects, and one possibility is that the diversity might originate from medication. Therefore, we split the subjects into two cohorts for deep learning: with and without medication (1682 and 856 recruited subjects, respectively). In comparison, the cohort training for subjects without any medication had approximately 30% higher prediction accuracy over the cohort training for those with medication. Furthermore, by adding quarterly (every 3 months) measured glycohemoglobin (HbA1c), we were able to significantly boost the prediction accuracy by approximately 10%. For subjects without medication, the best performing model with quarterly measured HbA1c achieved 94.3% prediction accuracy, RMSE of 12.4 mg/dL, MAE of 8.9 mg/dL, and MAPE of 0.08, which demonstrates a very promising solution for NIBG prediction via deep learning. Regarding subjects with medication, a personalized model could be a viable means of further investigation.

The segmentation of capillaries in human skin in full-field optical coherence tomography (FF-OCT) images plays a vital role in clinical applications. Recent advances in deep learning techniques have demonstrated a state-of-the-art level of accuracy for the task of automatic medical image segmentation. However, a gigantic amount of annotated data is required for the successful training of deep learning models, which demands a great deal of effort and is costly. To overcome this fundamental problem, an automatic simulation algorithm to generate OCT-like skin image data with augmented capillary networks (ACNs) in a three-dimensional volume (which we called the ACN data) is presented. This algorithm simultaneously acquires augmented FF-OCT and corresponding ground truth images of capillary structures, in which potential functions are introduced to conduct the capillary pathways, and the two-dimensional Gaussian function is utilized to mimic the brightness reflected by capillary blood flow seen in real OCT data. To assess the quality of the ACN data, a U-Net deep learning model was trained by the ACN data and then tested on real in vivo FF-OCT human skin images for capillary segmentation. With properly designed data binarization for predicted image frames, the testing result of real FF-OCT data with respect to the ground truth achieved high scores in performance metrics. This demonstrates that the proposed algorithm is capable of generating ACN data that can imitate real FF-OCT skin images of capillary networks for use in research and deep learning, and that the model for capillary segmentation could be of wide benefit in clinical and biomedical applications.

We explored the use of convolutional neural network for classification of near-infrared spectra measured from glucose aqueous with various concentrations. Our technique could be extended to other kinds of spectrums and benefit in different topics.

In this study, we tackle the accurate prediction of glucose aqueous concentration from hardly distinguishable near-infrared (NIR) spectroscopy. We adopted several machine learning approaches for the spectral analyses and identified important features learned by each model. The models we investigated include Partial Least Squares Regression (PLSR), Support Vector Machine Regression (SVMR), Random Forest Regression (RF), Extra Trees Regression (ETR), eXtreme Gradient Boosting (Xgboost), and hybrid Principal Component Analysis-Neural Network (PCA-NN) methods. From 47 different glucose aqueous concentrations which cover the range of 40-500 mg/dl, we measured 564 near-infrared (NIR) absorbance spectra samples with wavelength range 900 nm-2200 nm. Then the spectra samples were randomly split into 80% for the training set and 20% for the testing set. In our test, we found that the models SVMR, ETR, and PCA-NN reach extremely good performance, which had correlation coefficient R > 0.99 and determination of coefficient R-2 > 0.985. To explore the robustness of each machine learning approach, we extracted their high-weighting features and examine their distribution. We found that having large overlapping of the high-weighting features learned by the model when trained by different data sets may be an indication of model stability. In addition, our analysis came up with the essential region of features to disentangle the hardly distinguishable signal. Our study demonstrates a robust machine learning models for the prediction of glucose aqueous concentration in an in-vitro setup using near-infrared spectroscopy. (C) 2020 Elsevier Ltd. All rights reserved.

Integration of both n-type and p-type MoS2 fin-shaped field effect transistors by using a traditional implantation technique for complementary field effect transistor is demonstrated. The complementary MoS2 inverter with high DC voltage gain of more than 20 is acquired.

The purpose of this paper is to segment red blood cells from the Full-Field OCT data of human skin, using deep learning technique. Test results show the developed technique is very promising for real time detection and counting of red blood cells.

An atomic-scale numerical study of Si contact with transition metal dichalcogenides (TMD) semiconductor materials is proposed by first-principles simulation for the first time. The monolayer MoS 2 channel can be operated as both of n- and p-type FET by properly doping Si S/D to adjust the TMD channel potential. The gradient MoS x junction of dichalcogenide vacancies enables Si-MoS 2 contact resistance lower than 100Ω-μm for interface Schottky barrier height reduction. The compact Si-MoS 2 interface study can potentially provide monolayer TMD contact design guideline for the sub-5 nm TMD FET fabrication technology.

A U-shape MoS 2 pMOSFET with 10nm channel and poly-Si source/drain is demonstrated. The fabrication process is simple. Because the Si S/D serves as the nucleation seed for CVD MoS 2 deposition, thin MoS 2 is well deposited in the channel region any where over the fully scale oxide coated Si wafer. This is a big step forward toward a low cost multi-layer stacked TMD IC technology.