Search results for "software"
showing 10 items of 7396 documents
Numerical and Experimental Study of Friction Loss in Hydrostatic Motor
2012
Published version of an article in the journal: Modeling, Identification and Control. Also available from the publisher at: http://dx.doi.org/10.4173/mic.2012.3.2 Open access This paper presents a numerical and experimental study of the losses in a hydrostatic motor principle. The motor is designed so that the structural deflections and lubricating regimes between moving surfaces and, subsequently, the leakage and friction losses, can be controlled during operation. This is done by means of additional pressure volumes that influence the stator deflection. These pressures are referred to as compensation pressures and the main emphasis is on friction or torque loss modeling of the motor as a …
FLUMO: FLexible Underwater MOdem
2019
The last years have seen a growing interest in underwater acoustic communications because of its applications in marine research, oceanography, marine commercial operations, the offshore oil industry and defense. High-speed communication in the underwater acoustic channel has been challenging because of limited bandwidth, extended multipath, refractive properties of the medium, severe fading, rapid time variation and large Doppler shifts. In this paper, we show an implementation of a flexible Software-Defined Acoustic (SDA) underwater modem, where modulation parameters are completely tunable to optimize performance. In particular, we develop the system architecture following two key ideas. …
Emulating the Effects of Radiation-Induced Soft-Errors for the Reliability Assessment of Neural Networks
2021
International audience; Convolutional Neural Networks (CNNs) are currently one of the most widely used predictive models in machine learning. Recent studies have demonstrated that hardware faults induced by radiation fields, including cosmic rays, may significantly impact the CNN inference leading to wrong predictions. Therefore, ensuring the reliability of CNNs is crucial, especially for safety-critical systems. In the literature, several works propose reliability assessments of CNNs mainly based on statistically injected faults. This work presents a software emulator capable of injecting real faults retrieved from radiation tests. Specifically, from the device characterisation of a DRAM m…
Comparison of feature importance measures as explanations for classification models
2021
AbstractExplainable artificial intelligence is an emerging research direction helping the user or developer of machine learning models understand why models behave the way they do. The most popular explanation technique is feature importance. However, there are several different approaches how feature importances are being measured, most notably global and local. In this study we compare different feature importance measures using both linear (logistic regression with L1 penalization) and non-linear (random forest) methods and local interpretable model-agnostic explanations on top of them. These methods are applied to two datasets from the medical domain, the openly available breast cancer …
Machine learning for mortality analysis in patients with COVID-19
2020
This paper analyzes a sample of patients hospitalized with COVID-19 in the region of Madrid (Spain). Survival analysis, logistic regression, and machine learning techniques (both supervised and unsupervised) are applied to carry out the analysis where the endpoint variable is the reason for hospital discharge (home or deceased). The different methods applied show the importance of variables such as age, O2 saturation at Emergency Rooms (ER), and whether the patient comes from a nursing home. In addition, biclustering is used to globally analyze the patient-drug dataset, extracting segments of patients. We highlight the validity of the classifiers developed to predict the mortality, reaching…
A Curvature Based Method for Blind Mesh Visual Quality Assessment Using a General Regression Neural Network
2016
International audience; No-reference quality assessment is a challenging issue due to the non-existence of any information related to the reference and the unknown distortion type. The main goal is to design a computational method to objectively predict the human perceived quality of a distorted mesh and deal with the practical situation when the reference is not available. In this work, we design a no reference method that relies on the general regression neural network (GRNN). Our network is trained using the mean curvature which is an important perceptual feature representing the visual aspect of a 3D mesh. Relatively to the human subjective scores, the trained network successfully asses…
Tail Removal Block Validation: Implementation and Analysis
2018
In this paper a solution for the removal of long tail blocktimes in a proof-of-work blockchain is proposed, implemented and analysed. Results from the mainnet of the Bismuth blockchain demonstrate that the variances in the key variables, difficulty level and blocktime, were approximately halved after the tail removal code was enabled. Low variances in difficulty and blocktimes are desirable for timely execution of transactions in the network as well as reduction of unwanted oscillations in the feedback control problem.
Using assessment for learning mathematics with mobile tablet based solutions
2014
Published version of an article in the journal: International Journal of Emerging Technologies in Learning (iJET). Also available from the publisher: http://dx.doi.org/10.3991/ijet.v9i2.3219 This article discusses assessment for learning in mathematics subjects. Teachers of large classes face the challenge of regularly assessing students’ ongoing mathematical learning achievements. Taking the complexity of assessment and feedback for learning as a background, we have developed a new approach to the assessment for learning mathematics at university level. We devised mobile tablet technology supported assessment processes, and we carried out user studies in both Rwanda and Norway. Results of …
A Nonlinear Control of Synchronous Reluctance Motors (SynRM) Based on Feedback Linearization Considering the Self and Cross-Saturation Effects
2019
This paper proposes a nonlinear controller based on feedback linearization for Synchronous Reluctance Motors (SynRM) drives that takes into consideration the self and cross-saturation effects. Such control technique permits the dynamics of both the speed and flux loops to be maintained constant independently from the load and the saturation of the iron core. The proposed technique has been tested experimentally on a suitably developed test set-up.
Enhancing Software Engineering Education in Africa through a Metaversity
2022
Software engineering education requires a new boost in African higher education, because of the high demand for professionals, caused by the fast increasing internet connections calling for meaningful applications and governmental initiatives like Fourth Industrial Revolution (4IR), and the current situation where universities graduate software engineers that cannot serve in the job markets. Inspired by the Conceive, Design, Implement and Operate (CDIO) model for engineering education and the CATI model for curriculum reform focusing on contextually relevant education in the Global South, we introduce how a complementary model for a conventional university, i.e. metaversity, can enhance sof…