Dataset Information

A hardware Markov chain algorithm realized in a single device for machine learning.

ABSTRACT: There is a growing need for developing machine learning applications. However, implementation of the machine learning algorithm consumes a huge number of transistors or memory devices on-chip. Developing a machine learning capability in a single device has so far remained elusive. Here, we build a Markov chain algorithm in a single device based on the native oxide of two dimensional multilayer tin selenide. After probing the electrical transport in vertical tin oxide/tin selenide/tin oxide heterostructures, two sudden current jumps are observed during the set and reset processes. Furthermore, five filament states are observed. After classifying five filament states into three states of the Markov chain, the probabilities between each states show convergence values after multiple testing cycles. Based on this device, we demo a fixed-probability random number generator within 5% error rate. This work sheds light on a single device as one hardware core with Markov chain algorithm.

SUBMITTER: Tian H

PROVIDER: S-EPMC6192990 | biostudies-literature | 2018 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A hardware Markov chain algorithm realized in a single device for machine learning.

Tian He H Wang Xue-Feng XF Mohammad Mohammad Ali MA Gou Guang-Yang GY Wu Fan F Yang Yi Y Ren Tian-Ling TL

Nature communications 20181017 1

There is a growing need for developing machine learning applications. However, implementation of the machine learning algorithm consumes a huge number of transistors or memory devices on-chip. Developing a machine learning capability in a single device has so far remained elusive. Here, we build a Markov chain algorithm in a single device based on the native oxide of two dimensional multilayer tin selenide. After probing the electrical transport in vertical tin oxide/tin selenide/tin oxide heter ...[more]

PMID: 30333492

Similar Datasets

Project description:IntroductionThough wrist-worn photoplethysmography (PPG) sensors play an important role in long-term and continuous heart rhythm monitoring, signals measured at the wrist are contaminated by more intense motion artifacts compared to other body locations. Machine learning (ML)-based algorithms can improve long-term pulse rate (PR) tracking but are associated with more stringent regulatory requirements when intended for clinical use. This study aimed to evaluate the accuracy of a digital health technology using wrist-worn PPG sensors and an ML-based algorithm to measure PR continuously.MethodsVolunteers were enrolled in three independent clinical trials and concurrently monitored with the investigational device and FDA-cleared electrocardiography (ECG) devices during supervised protocols representative of real-life activities. The primary acceptance threshold was an accuracy root-mean-square (ARMS) ≤3 beats per minute (bpm) or 5 bpm under no-motion and motion conditions, respectively. Bias, mean absolute error (MAE), mean absolute percentage error (MAPE), limits of agreement (LoA), and Pearson and Lin's concordance correlation coefficients (⍴ and CCC) were also computed. Subgroup and outlier analyses were conducted to examine the effect of site, skin tone, age, sex, body mass index (BMI), and health status on PR accuracy.ResultsCollectively, 16,915 paired observations between the device and the reference ECG were analyzed from 157 subjects (male: 49.04%, age mean: 43 years, age range: 19-83 years, BMI mean: 26.4, BMI range: 17.5-52, Fitzpatrick class V-IV: 22.9%, cardiovascular condition: 24%). The PR output attained an accuracy of 1.67 bpm under no-motion (n = 5,621 min) and 4.39 bpm under motion (n = 11,294 min), satisfying the acceptance thresholds. Bias and LoA (lower, upper LoA) were -0.09 (-3.36, 3.17) bpm under no-motion and 0.51 (-8.05, 9.06) bpm under motion. MAE was 0.6 bpm in no-motion and 1.77 bpm in motion, and MAPE was 0.86% in no-motion and 2.05% in motion, with ⍴ and CCC >0.98 in both conditions. ARMS values met the clinical acceptance threshold in all relevant subgroups at each clinical site separately, excluding male subjects under motion conditions (ARMS = 5.41 bpm), with more frequent and larger outliers due to stronger forearm contractions. However, these mostly occurred in isolation and, therefore would not impact the clinical utility or usability of the device for its intended use of retrospective review and trend analysis (⍴ and CCC >0.97 and MAPE = 2.61%).ConclusionThe analytical validation conducted in this study demonstrated clinical-grade accuracy and generalizability of ML-based continuous PR estimations across a full range of physical motions, health conditions, and demographic variables known to confound PPG signals, paving the way for device usage by populations most likely to benefit from continuous PR monitoring.

Project description:IntroductionMedical device recalls are important to the practice of emergency medicine, as unsafe devices include many ubiquitous items in emergency care, such as vascular access devices, ventilators, infusion pumps, video laryngoscopes, pulse oximetry sensors, and implantable cardioverter defibrillators. Identification of dangerous medical devices as early as possible is necessary to minimize patient harms while avoiding false positives to prevent removal of safe devices from use. While the United States Food and Drug Administration (FDA) employs an adverse event reporting program (MedWatch) and database (MAUDE), other data sources and methods might have utility to identify potentially dangerous medical devices. Our objective was to evaluate the sensitivity, specificity, and accuracy of a machine learning (ML) algorithm using publicly available data to predict medical device recalls by the FDA.MethodsWe identified recalled medical devices (RMD) and non-recalled medical devices (NRMD) using the FDA's website and online database. We constructed an ML algorithm (random forest regressor) that automatically searched Google Trends and PubMed for the RMDs and NRMDs. The algorithm was trained using 400 randomly selected devices and then tested using 100 unique random devices. The algorithm output a continuous value (0-1) for recall probability for each device, which were rounded for dichotomous analysis. We determined sensitivity, specificity, and accuracy for each of three time periods prior to recall (T-3, 6, or 12 months), using FDA recall status as the reference standard. The study adhered to relevant items of the Standards for Reporting Diagnostic accuracy studies (STARD) guidelines.ResultsUsing a rounding threshold of 0.5, sensitivities for T-3, T-6, and T-12 were 89% (95% confidence interval [CI] 69-97), 90% (95% CI 70-97), and 75% (95% CI 53-89). Specificity was 100% (95% CI 95-100) for all three time periods. Accuracy was 98% (95% CI 93-99) for T-3 and T-6, and 95% (95% CI 89-99) for T-12. Using tailored thresholds yielded similar results.ConclusionAn ML algorithm accurately predicted medical device recall status by the FDA with lead times as great as 12 months. Future research could incorporate longer lead times and data sources including FDA reports and prospectively test the ability of ML algorithms to predict FDA recall.

Dataset Information

A hardware Markov chain algorithm realized in a single device for machine learning.

Publications

A hardware Markov chain algorithm realized in a single device for machine learning.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets