Search results for " Mach"
showing 10 items of 1388 documents
Predicting sediment deposition rate in check-dams using machine learning techniques and high-resolution DEMs
2021
Sediments accumulated in check dams are a valuable measure to estimate soil erosion rates. Here, geographic information systems (GIS) and three machine learning techniques (MARS-multivariate adaptive regression splines, RF-random forest and SVM-support vector machine) were used, for the first time, to predict sediment deposition rate (SR) in check-dams located in six watersheds in SW Spain. There, 160 dry-stone check dams (~ 77.8 check-dams km−2), accumulated sediments during a period that varied from 11 to 23 years. The SR was estimated in former research using a topographical method and a high-resolution Digital Elevation Model (DEM) (average of 0.14 m3 ha−1 year−1). Nine environmental-to…
Therapeutic Drug Monitoring of Kidney Transplant Recipients Using Profiled Support Vector Machines
2007
This paper proposes a twofold approach for therapeutic drug monitoring (TDM) of kidney recipients using support vector machines (SVMs), for both predicting and detecting Cyclosporine A (CyA) blood concentrations. The final goal is to build useful, robust, and ultimately understandable models for individualizing the dosage of CyA. We compare SVMs with several neural network models, such as the multilayer perceptron (MLP), the Elman recurrent network, finite/infinite impulse response networks, and neural network ARMAX approaches. In addition, we present a profile-dependent SVM (PD-SVM), which incorporates a priori knowledge in both tasks. Models are compared numerically, statistically, and in…
Accelerating Application Migration in HPC
2016
It is predicted that the number of cores per node will rapidly increase with the upcoming era of exascale supercomputers. As a result, multiple applications will have to share one node and compete for the (often scarce) resources available on this node. Furthermore, the growing number of hardware components causes a decrease in the mean time between failures. Application migration between nodes has been proposed as a tool to mitigate these two problems: Bottlenecks due to resource sharing can be addressed by load balancing schemes which migrate applications; and hardware errors can often be tolerated by the system if faulty nodes are detected and processes are migrated ahead of time.
Fault Diagnosis for Nonlinear Hydraulic-Mechanical Drilling Pipe Handling System
2011
Leakage and increased friction are common faults in hydraulic cylinders that can have serious consequences if they are not detected at early stage. In this paper, the design of a fault detector for a nonlinear hydraulic mechanical system is presented. By considering the system in steady state, two residual signals are generated and analysed with a composite hypothesis test which accommodates for unknown parameters. The resulting detector is able to detect abrupt changes in leakage or friction given the noisy pressure and position measurements. Test rig measurements validate the properties of residuals and high fidelity simulation and experimental results demonstrate the performance and feas…
Rilievo in tempo reale di difetti superficiali su corpi in movimento a velocità elevata con ultrasuoni senza contatto
2012
Il rilievo di difetti superficiali durante le ispezioni periodiche è importante poiché in genere le sollecitazioni sono maggiori in superficie e possono accelerare la crescita delle discontinuità. I difetti superficiali possono essere rilevati utilizzando alcuni metodi tradizionali di controllo non distruttivo, quali correnti indotte, liquidi penetranti, polveri magnetiche ed ultrasuoni. Alcuni tra questi metodi possono essere usati solo in condizioni statiche; gli altri presentano delle limitazioni per l’ispezione dinamica. I progressi recenti nel campo dei sensori ultrasonori senza contatto ci hanno permesso di sviluppare un sistema semplice per l’ispezione in tempo reale di corpi in movi…
Simulazione della propagazione di difetti a fatica mediante il modello di zona coesiva
2009
Le giunzioni incollate guadagnano sempre più mercato, nel campo delle costruzioni in genere, dove è necessario un alleggerimento delle strutture. Nel caso di geometrie di giunto semplici il dimensionamento avviene attraverso relazioni analitiche che restituiscono il valore massimo delle tensioni, il quale deve essere inferiore al limite di utilizzo dell’adesivo stesso. Quando le geometrie sono complesse l’approccio analitico diventa impraticabile, di conseguenza si provvede a verificare la correttezza della soluzione mediante analisi agli elementi finiti (EF). L’introduzione del modello di zona coesiva nell'analisi EF permette di simulare il danneggiamento ed il cedimento del giunto in cond…
Researches on the Hydraulic Systems of Actioning the Suspension Mechanisms at Tractors
2010
SUMMARY The agricultural machines are coupled to tractor th rough the suspension mechanism in three points. The actioning of the suspension mechanisms is made by some hydraulic systems, which have the following component parts: tank, pu mp, distributer, valves, hydraulic cylinders, filters and hydraulic prizes. These systems must assure, between others, lifting in a convenient time of the carried machine from the work position to that of transport position, to allow the maintaining of the machine in any intermediary position, between the l owest limited position and the upper limited position and to assure the posibility to th e carried machine to follow the irregularities of the ground dur…
Machine Learning to Predict In-Hospital Mortality in COVID-19 Patients Using Computed Tomography-Derived Pulmonary and Vascular Features
2021
Pulmonary parenchymal and vascular damage are frequently reported in COVID-19 patients and can be assessed with unenhanced chest computed tomography (CT), widely used as a triaging exam. Integrating clinical data, chest CT features, and CT-derived vascular metrics, we aimed to build a predictive model of in-hospital mortality using univariate analysis (Mann–Whitney U test) and machine learning models (support vectors machines (SVM) and multilayer perceptrons (MLP)). Patients with RT-PCR-confirmed SARS-CoV-2 infection and unenhanced chest CT performed on emergency department admission were included after retrieving their outcome (discharge or death), with an 85/15% training/test dataset spli…
Mirror, Mirror on the Wall: Machine Predictions and Self-Fulfilling Prophecies
2021
We show that disclosing machine predictions to affected parties can trigger self-fulfilling prophecies. In an investment game, we experimentally vary investors’ and recipients’ access to a machine prediction about recipients’ likelihood to pay back an investment. Recipients who privately learn about an incorrect machine prediction alter their behavior in the direction of the prediction. Furthermore, when recipients learn that an investor has disregarded a machine prediction of no-repayment, this further lowers the repayment amount. We interpret these findings as evidence that transparency regarding machine predictions can alter recipients’ beliefs about what kind of person they are and what…
Nanomanufacturing/Nanotechnology
2017
This chapter provides comprehensive knowledge regarding the fabrication of nanoproducts and element of micro-electromechanical systems using various techniques and processes. Both well-established techniques, such as nanomachining (ultra-precision) and new trends in improving nanoprocesses taking into account AFM, laser beam machining, electron beam machining processes are overviewed. The background of nanomachining processes, including typical machining operations such as turning, milling and grinding and different construction materials (metallic and nonmetallic), is outlined. The physical mechanisms responsible for the transition from brittle to ductile regime machining are explained. Mo…