Data Mining - Concepts and Techniques.

Data Mining Practical Machine Learning Tools and Techniques

Summary Background Since December, 2019, Wuhan, China, has experienced an outbreak of coronavirus disease 2019 (COVID-19), caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Epidemiological and clinical characteristics of patients with COVID-19 have been reported but risk factors for mortality and a detailed clinical course of illness, including viral shedding, have not been well described. Methods In this retrospective, multicentre cohort study, we included all adult inpatients (≥18 years old) with laboratory-confirmed COVID-19 from Jinyintan Hospital and Wuhan Pulmonary Hospital (Wuhan, China) who had been discharged or had died by Jan 31, 2020. Demographic, clinical, treatment, and laboratory data, including serial samples for viral RNA detection, were extracted from electronic medical records and compared between survivors and non-survivors. We used univariable and multivariable logistic regression methods to explore the risk factors associated with in-hospital death. Findings 191 patients (135 from Jinyintan Hospital and 56 from Wuhan Pulmonary Hospital) were included in this study, of whom 137 were discharged and 54 died in hospital. 91 (48%) patients had a comorbidity, with hypertension being the most common (58 [30%] patients), followed by diabetes (36 [19%] patients) and coronary heart disease (15 [8%] patients). Multivariable regression showed increasing odds of in-hospital death associated with older age (odds ratio 1·10, 95% CI 1·03–1·17, per year increase; p=0·0043), higher Sequential Organ Failure Assessment (SOFA) score (5·65, 2·61–12·23; p Interpretation The potential risk factors of older age, high SOFA score, and d-dimer greater than 1 μg/mL could help clinicians to identify patients with poor prognosis at an early stage. Prolonged viral shedding provides the rationale for a strategy of isolation of infected patients and optimal antiviral interventions in the future. Funding Chinese Academy of Medical Sciences Innovation Fund for Medical Sciences; National Science Grant for Distinguished Young Scholars; National Key Research and Development Program of China; The Beijing Science and Technology Project; and Major Projects of National Science and Technology on New Drug Creation and Development.

Clinical course and risk factors for mortality of adult inpatients with COVID-19 in Wuhan, China: a retrospective cohort study

A review on machinery diagnostics and prognostics implementing condition-based maintenance

Wearable sensor technologies are essential to the realization of personalized medicine through continuously monitoring an individual's state of health. Sampling human sweat, which is rich in physiological information, could enable non-invasive monitoring. Previously reported sweat-based and other non-invasive biosensors either can only monitor a single analyte at a time or lack on-site signal processing circuitry and sensor calibration mechanisms for accurate analysis of the physiological state. Given the complexity of sweat secretion, simultaneous and multiplexed screening of target biomarkers is critical and requires full system integration to ensure the accuracy of measurements. Here we present a mechanically flexible and fully integrated (that is, no external analysis is needed) sensor array for multiplexed in situ perspiration analysis, which simultaneously and selectively measures sweat metabolites (such as glucose and lactate) and electrolytes (such as sodium and potassium ions), as well as the skin temperature (to calibrate the response of the sensors). Our work bridges the technological gap between signal transduction, conditioning (amplification and filtering), processing and wireless transmission in wearable biosensors by merging plastic-based sensors that interface with the skin with silicon integrated circuits consolidated on a flexible circuit board for complex signal processing. This application could not have been realized using either of these technologies alone owing to their respective inherent limitations. The wearable system is used to measure the detailed sweat profile of human subjects engaged in prolonged indoor and outdoor physical activities, and to make a real-time assessment of the physiological state of the subjects. This platform enables a wide range of personalized diagnostic and physiological monitoring applications.

/pdf/fully-integrated-wearable-sensor-arrays-for-multiplexed-in-4nphg673vl.pdf

Fully integrated wearable sensor arrays for multiplexed in situ perspiration analysis

This paper presents preliminary results of a study to assess localized muscle fatigue during load carrying. The assessment procedure is based on parameters of the surface electromyographic (EMG) si...

Assessment of Muscle Fatigue during Load Carrying

Most of the techniques currently used in structural identification under ambient excitation typically require the hypothesis of stationarity, though, in the field of civil engineering, excitation may be markedly non stationary. This consideration prompted some proposals for new identification methods that, being based on special instantaneous estimators of modal parameters, were designed to handle current types of non-stationary excitation. Hence, a novelty is that identification is based solely on the properties of slowly modulated harmonics. The present paper briefly summarises the hypotheses and theories that constitute the basis of the main output only techniques. The problems usually encountered in this kind of identification will be stated and critically discussed. The final part of the paper reports a few numerical simulations.

Structural Health Monitoring under Ambient Vibrations: Accuracy of Identification Methods

The study explored the use of machine learning-based algorithms to estimate clinical scores (meant to capture the quality of upper-limb movements) via the analysis of wearable sensor data collected during the performance of functional tasks. Data was recorded using accelerometer units from thirty-seven individuals with upper-limb hemiparesis due to acquired brain injury while they performed eight activities of daily living. Clinicians assessed the study participants' quality of movement using the Functional Ability Scale. A hierarchical Random Forest-based algorithm was developed to derive the Functional Ability Scale scores from the accelerometer data. The results showed a high correlation (R2=0.91) between the estimates derived from the accelerometer data and the scores provided by the clinicians. The method herein presented has the potential to provide a means to track the motor recovery process in patients experiencing upper-limb motor impairments following a stroke or a traumatic brain injury hence enabling precision rehabilitation interventions.

Wearable Technology and Machine Learning to Monitor Upper-Limb Use in Brain Injury Survivors

This paper focuses on the profitability of demand-side management strategies developed for a single-dwelling mechanical ventilation plus radiant floor system. Energy savings and comfort indicators are quantified for a number of control options, including demand-controlled ventilation and temperature setbacks. The assessment is based on numerical energy simulations conducted in TRNSYS for the climate of Bolzano (Italy). To perform the simulations, numerical models of the energy system and the reference dwelling were developed. Based on the analysed climate and building, it was found that demand-side management strategies can have a significant impact on the energy consumption and time distribution of energy loads: demand control ventilation allows the achievement of consistent energy savings in the electrical consumption of the fans (up to 37 %), whereas the use of an adaptive dehumidification setpoint can lead to savings within the range of 10 % in summer electrical consumption. The use of non-occupancy temperature setbacks does not show a significant impact on the annual thermal demand, although the time pattern of the loads is considerably affected, with a cascade effect on the performance of the air-to-water heat pump. The use of the climatic curve parameters at the generator allows an improvement of the electrical performance of the heat pump, increasing the SCOP of more than 20 %.

Assessment of Demand-Side Management on the Performance of a Single-Dwelling Mechanical Ventilation Plus Radiant Floor System

This paper presents a cross-time-frequency (XTF) based algorithm for the estimation of the instantaneous frequency (IF) of nonstationary stochastic processes and discusses its application to the analysis of the surface myoelectric signal (SMES) recorded during dynamic muscle contractions. This original algorithm derives from that previously proposed by Boashash and O'Shea (1993) and further investigated by Ristic and Boashash (see IEEE Trans. on Signal Processing vol.44, p.1549-53, 1996), which was originally proposed for the analysis of deterministic signals. We assessed the estimation error of the modified algorithm by means of a synthesized process with statistical properties similar to those of SMES. Bias and standard deviation of the IF estimates were obtained for signal to noise ratio (SNR) values ranging from 5 dB to 100 dB and for different frequency contents of the SMES. The algorithm was found satisfactory for research as well as for clinical applications. A sample application is shown where we utilize this method for the estimation of the IF of real SMES recorded from the extensors and flexors during repetitive isokinetic knee flexion-extension movements.

Paolo Bonato

Papers

Assessment of Muscle Fatigue during Load Carrying

Structural Health Monitoring under Ambient Vibrations: Accuracy of Identification Methods

Wearable Technology and Machine Learning to Monitor Upper-Limb Use in Brain Injury Survivors

Assessment of Demand-Side Management on the Performance of a Single-Dwelling Mechanical Ventilation Plus Radiant Floor System

Analysis of the surface myoelectric signal by means of a cross-time-frequency based technique