Search results for "ARN"

showing 10 items of 8344 documents

MARL-Ped+Hitmap: Towards Improving Agent-Based Simulations with Distributed Arrays

2016

Multi-agent systems allow the modelling of complex, heterogeneous, and distributed systems in a realistic way. MARL-Ped is a multi-agent system tool, based on the MPI standard, for the simulation of different scenarios of pedestrians who autonomously learn the best behavior by Reinforcement Learning. MARL-Ped uses one MPI process for each agent by design, with a fixed fine-grain granularity. This requirement limits the performance of the simulations for a restricted number of processors that is lesser than the number of agents. On the other hand, Hitmap is a library to ease the programming of parallel applications based on distributed arrays. It includes abstractions for the automatic parti…

020203 distributed computingComputer scienceDistributed computingMessage passing0202 electrical engineering electronic engineering information engineeringProcess (computing)Reinforcement learning020207 software engineering02 engineering and technologyCrowd simulationGranularityPartition (database)
researchProduct

Massively Parallel Huffman Decoding on GPUs

2018

Data compression is a fundamental building block in a wide range of applications. Besides its intended purpose to save valuable storage on hard disks, compression can be utilized to increase the effective bandwidth to attached storage as realized by state-of-the-art file systems. In the foreseeing future, on-the-fly compression and decompression will gain utmost importance for the processing of data-intensive applications such as streamed Deep Learning tasks or Next Generation Sequencing pipelines, which establishes the need for fast parallel implementations. Huffman coding is an integral part of a number of compression methods. However, efficient parallel implementation of Huffman decompre…

020203 distributed computingComputer sciencebusiness.industryDeep learning020206 networking & telecommunicationsData_CODINGANDINFORMATIONTHEORY02 engineering and technologyParallel computingHuffman codingsymbols.namesakeCUDATitan (supercomputer)0202 electrical engineering electronic engineering information engineeringsymbolsArtificial intelligencebusinessMassively parallelData compressionProceedings of the 47th International Conference on Parallel Processing
researchProduct

FeatherCNN: Fast Inference Computation with TensorGEMM on ARM Architectures

2020

Deep Learning is ubiquitous in a wide field of applications ranging from research to industry. In comparison to time-consuming iterative training of convolutional neural networks (CNNs), inference is a relatively lightweight operation making it amenable to execution on mobile devices. Nevertheless, lower latency and higher computation efficiency are crucial to allow for complex models and prolonged battery life. Addressing the aforementioned challenges, we propose FeatherCNN – a fast inference library for ARM CPUs – targeting the performance ceiling of mobile devices. FeatherCNN employs three key techniques: 1) A highly efficient TensorGEMM (generalized matrix multiplication) routine is app…

020203 distributed computingSource codeIterative methodComputer sciencebusiness.industrymedia_common.quotation_subjectDeep learningInference02 engineering and technologyParallel computingConvolutional neural networkMatrix multiplicationARM architectureComputational Theory and MathematicsHardware and ArchitectureSignal Processing0202 electrical engineering electronic engineering information engineeringArtificial intelligencebusinessmedia_commonIEEE Transactions on Parallel and Distributed Systems
researchProduct

Catalogue of Interactive Learning Objectives to improve an Integrated Medical and Dental Curriculum.

2016

ABSTRACT Introduction Online learning media are increasingly being incorporated into medical and dental education. However, the coordination between obligatory and facultative teaching domains still remains unsatisfying. The Catalogue of Interactive Learning Objectives of the University Clinic of Mainz (ILKUM), aims to offer knowledge transfer for students while being mindful of their individual qualifications. Its hierarchical structure is designed according to the Association for Dental Education in Europe (ADEE) levels of competence. Materials and methods The ILKUM was designed to establish a stronger interconnection between already existing and prospective learning strategies. All conte…

020205 medical informatics02 engineering and technologyDental educationInteractive LearningEducation Distance03 medical and health sciences0302 clinical medicineGermany0202 electrical engineering electronic engineering information engineeringMedicineGeneral DentistryCompetence (human resources)Education DentalSimulation TrainingDental curriculumMedical educationbusiness.industryOnline learning030206 dentistryMobile ApplicationsComputers HandheldThe InternetClinical caseCurriculumbusinessKnowledge transferEducation Medical UndergraduateThe journal of contemporary dental practice
researchProduct

Empowering education professionals with twenty-first century skills through master's of education dissertation/thesis work

2021

This paper aims to explore the potential role of Master’s of Education dissertation/thesis work in developing twenty-first century skills. A total of 600 education professionals studying Master’s of Education programmes in five countries – Poland, Portugal, England, Latvia, and Romania – were surveyed. The findings have revealed that participants recognise the usefulness of twenty-first century skills for their (future) professional practice, and perceive dissertation/thesis work as a valuable foundation for developing these skills. This study offers practical implications for designers of Master’s of Education programmes and contributes to our understanding that this assignment is not only…

020205 medical informatics05 social sciencesTwenty-First Century050301 educationFoundation (evidence)Professional practice02 engineering and technologyEducationWork (electrical)Professional learning communityPedagogy0202 electrical engineering electronic engineering information engineeringMaster sSociology0503 educationPractical implications
researchProduct

ULearn: Personalized Medical Learning on the Web for Patient Empowerment

2019

Abstract. Health literacy constitutes an important step towards patient empowerment and the Web is presently the biggest repository of medical information and, thus, the biggest medical resource to be used in the learning process. However, at present web medical information is mainly accessed through generic search engines that do not take into account the user specific needs and starting knowledge and so are not able to support learning activities tailored to the specific user requirements. This work presents “ULearn” a meta engine that supports access, understanding and learning on the Web in the medical domain based on specific user requirements and knowledge levels towards what we call …

020205 medical informaticsComputer scienceProcess (engineering)media_common.quotation_subjectDistance educationHealth literacy02 engineering and technologyInformation technologyPatient empowerment; search as learning; e-health; Health literacy; Health seeking behaviorUser requirements documentEducationWorld Wide WebDistance education03 medical and health sciences0302 clinical medicineResource (project management)0202 electrical engineering electronic engineering information engineeringInformation retrieval030212 general & internal medicineComputer softwareEmpowermentmedia_commonSettore ING-INF/05 - Sistemi Di Elaborazione Delle InformazioniSettore INF/01 - Informaticabusiness.industryCommunicationEducational technologyInformation technologyPatient empowerment search as learning e-health Health literacy Health seeking behavior.World Wide WebEducational technologyHealthbusiness
researchProduct

How do we assess in Clinical Legal Education? A 'reflection' about reflective learning

2016

I suggest this hypothesis and these premises from the perspective of my experience in Clinical Legal Education and the use of experiential learning methods in other 'traditional' courses. Firstly, institutional assessment must be distinguished from the assessment of learning. Traditionally, assessment is reduced to institutional assessment: that is, to give a mark depending on the achievement of knowledge instead of focusing in the student's learning. However, I propose (to remember) that: 1) (Formative) assessment is part of learning; 2) Reflective learning (and reflective skills) is/are a part of assessment. This implies a process of continuous evaluation instead of summative evaluation, …

020205 medical informaticsInstructional designReflective practicemedia_common.quotation_subjectTeaching method02 engineering and technologyExperiential learningFormative assessment03 medical and health sciencesEducació Avaluació0302 clinical medicineSummative assessmentPedagogy0202 electrical engineering electronic engineering information engineeringEducació mèdica030212 general & internal medicinePsychologyAction learningAutonomymedia_common
researchProduct

Teaching clinical reasoning and decision-making skills to nursing students: Design, development, and usability evaluation of a serious game

2016

Background\ud \ud Serious games (SGs) are a type of simulation technology that may provide nursing students with the opportunity to practice their clinical reasoning and decision-making skills in a safe and authentic environment. Despite the growing number of SGs developed for healthcare professionals, few SGs are video based or address the domain of home health care.\ud \ud Aims\ud \ud This paper aims to describe the design, development, and usability evaluation of a video based SG for teaching clinical reasoning and decision-making skills to nursing students who care for patients with chronic obstructive pulmonary disease (COPD) in home healthcare settings.\ud \ud Methods\ud \ud A prototy…

020205 medical informaticsPluralistic walkthroughCognitive walkthroughComputer scienceClinical Decision-MakingHealth Informatics02 engineering and technologyUsability labPulmonary Disease Chronic ObstructiveUser-Computer Interface03 medical and health sciencesNursingHeuristic evaluationUsability engineering0202 electrical engineering electronic engineering information engineeringHumansLearningWeb usabilityMotivation030504 nursingbusiness.industryTeachingEducation Nursing BaccalaureateUsabilityUsability goalsVideo GamesStudents NursingClinical CompetenceCurriculumEducational Measurement0305 other medical sciencebusinessInternational Journal of Medical Informatics
researchProduct

Developing a Serious Game for Nurse Education.

2018

Future nursing education is challenged to develop innovative and effective programs that align with current changes in health care and to educate nurses with a high level of clinical reasoning skills, evidence-based knowledge, and professional autonomy. Serious games (SGs) are computer-based simulations that combine knowledge and skills development with video game–playing aspects to enable active, experiential, situated, and problem-based learning. In a PhD project, a video-based SG was developed to teach nursing students nursing care for patients with chronic obstructive pulmonary disease in home health care and hospital settings. The current article summarizes the process of the SG devel…

020205 medical informaticsmedia_common.quotation_subjecteducationMEDLINEGerontological nursing02 engineering and technologyExperiential learningInformationSystems_GENERAL03 medical and health sciencesNursing carePulmonary Disease Chronic ObstructiveHealth care0202 electrical engineering electronic engineering information engineeringHumansComputer SimulationProfessional AutonomyNurse educationProgram DevelopmentEducation NursingGeneral Nursingmedia_commonMedical education030504 nursingbusiness.industryProblem-Based LearningHome Care ServicesHospitalizationProblem-based learningVideo GamesClinical Competence0305 other medical sciencebusinessPsychologyGerontologyAutonomyComputer-Assisted InstructionJournal of gerontological nursing
researchProduct

Hybrid Deep Shallow Network for Assessment of Depression Using Electroencephalogram Signals

2020

Depression is a mental health disorder characterised by persistently depressed mood or loss of interest in activities resulting impairment in daily life significantly. Electroencephalography (EEG) can assist with the accurate diagnosis of depression. In this paper, we present two different hybrid deep learning models for classification and assessment of patient suffering with depression. We have combined convolutional neural network with Gated recurrent units (RGUs), thus the proposed network is shallow and much smaller in size in comparison to its counter LSTM network. In addition to this, proposed approach is less sensitive to parameter settings. Extensive experiments on EEG dataset shows…

020205 medical informaticsmedicine.diagnostic_testComputer sciencebusiness.industryDeep learningPattern recognition02 engineering and technologyElectroencephalographyConvolutional neural network0202 electrical engineering electronic engineering information engineeringmedicineAnxiety020201 artificial intelligence & image processingArtificial intelligencemedicine.symptomF1 scorebusinessDepressed moodDepression (differential diagnoses)
researchProduct