Search results for "e learning"

Parasite avoidance behaviours in aquatic environments

2018

Parasites, including macroparasites, protists, fungi, bacteria and viruses, can impose a heavy burden upon host animals. However, hosts are not without defences. One aspect of host defence, behavioural avoidance, has been studied in the terrestrial realm for over 50 years, but was first reported from the aquatic environment approximately 20 years ago. Evidence has mounted on the importance of parasite avoidance behaviours and it is increasingly apparent that there are core similarities in the function and benefit of this defence mechanism between terrestrial and aquatic systems. However, there are also stark differences driven by the unique biotic and abiotic characteristics of terrestrial …

Dealing with a small amount of data : developing Finnish sentiment analysis

2022

Sentiment analysis has been more and more prominently visible among all natural language processing tasks. Sentiment analysis entails information extraction of opinions, emotions, and sentiments. In this paper, we aim to develop and test language models for low-resource language Finnish. We use the term “low-resource” to describe a language lacking in available resources for language modeling, especially annotated data. We investigate four models: the state-of-the-art FinBERT [1], and competitive alternative BERT models Finnish ConvBERT [2], Finnish Electra [3], and Finnish RoBERTa [4]. Having a comparative framework of multiple BERT variations is connected to our use of additional methods …

Study in children with reading disabilities and familial risk for dyslexia and Russian second-language

2013

Work-related language learning trajectories of migrant cleaners in Finland

2017

Cleaning is often the survival employment that migrants can get in their new home country. Ideally, the workplace can be a site for integration and language learning. This article explores how two migrants working as cleaners in Finland narrate their work-related Finnish language learning trajectories. The research is designed by applying nexus analysis (Scollon & Scollon, 2004), which focuses on social action in the intersection of interaction order, participants’ life experiences, and discourses in place. The social action in focus here is investment (Darvin & Norton, 2015), which means a commitment to developing language skills to achieve one’s aspirations. The article also analy…

Surrogate Modelling for Oxygen Uptake Prediction Using LSTM Neural Network

2023

Oxygen uptake (V˙O2) is an important metric in any exercise test including walking and running. It can be measured using portable spirometers or metabolic analyzers. Those devices are, however, not suitable for constant use by consumers due to their costs, difficulty of operation and their intervening in the physical integrity of their users. Therefore, it is important to develop approaches for the indirect estimation of V˙O2-based measurements of motion parameters, heart rate data and application-specific measurements from consumer-grade sensors. Typically, these approaches are based on linear regression models or neural networks. This study investigates how motion data contribute to V˙O2 …

Automatic surrogate modelling technique selection based on features of optimization problems

2019

A typical scenario when solving industrial single or multiobjective optimization problems is that no explicit formulation of the problem is available. Instead, a dataset containing vectors of decision variables together with their objective function value(s) is given and a surrogate model (or metamodel) is build from the data and used for optimization and decision-making. This data-driven optimization process strongly depends on the ability of the surrogate model to predict the objective value of decision variables not present in the original dataset. Therefore, the choice of surrogate modelling technique is crucial. While many surrogate modelling techniques have been discussed in the liter…

Sensitivity analysis of Gaussian processes for oceanic chlorophyll prediction

2015

Gaussian Process Regression (GPR) for machine learning has lately been successfully introduced for chlorophyll content mapping from remotely sensed data. The method provides a fast, stable and accurate prediction of biophysical parameters. However, since GPR is a non-linear kernel regression method, the relevance of the features are not accessible. In this paper, we introduce a probabilistic approach for feature sensitivity analysis (SA) of the GPR in order to reveal the relative importance of the features (bands) being used in the regression process. We evaluated the SA on GPR ocean chlorophyll content prediction. The method revealed the importance of the spectral bands, thus allowing the …

Host Searching by Egg Parasitoids: Exploitation of Host Chemical Cues

2010

Insect parasitoids are considered “keystone species” in many ecosystems in terms of biodiversity, ecological impact and economic importance (Vinson 1985, LaSalle and Gauld 1993, Hawkins et al. 1999). In the last decades, several reviews have been published on the relationships among plants, hosts and parasitoids, which reflect a strong interest in these insects both as models for behavioral ecologists and as important organisms for classical and applied biological control programs (Hawkins et al. 1999, Vet 1999, Bale et al. 2008). The majority of these studies have considered the larval parasitoid s, besides the extensive use of egg parasitoids in biological control (Hawkins et al. 1999). I…

Generalizability and Simplicity as Criteria in Feature Selection: Application to Mood Classification in Music

2011

Classification of musical audio signals according to expressed mood or emotion has evident applications to content-based music retrieval in large databases. Wrapper selection is a dimension reduction method that has been proposed for improving classification performance. However, the technique is prone to lead to overfitting of the training data, which decreases the generalizability of the obtained results. We claim that previous attempts to apply wrapper selection in the field of music information retrieval (MIR) have led to disputable conclusions about the used methods due to inadequate analysis frameworks, indicative of overfitting, and biased results. This paper presents a framework bas…

Teaching Knowledge Management by Combining Wikis and Screen Capture Videos

2011

PurposeThis paper aims to report on the design and creation of a knowledge management course aimed at facilitating student creation and use of social interactive learning tools for enhanced learning.Design/methodology/approachThe era of social media and web 2.0 has enabled a bottom‐up collaborative approach and new ways to publish work on the web, promoted by tools such as YouTube video service. In this spirit a knowledge management course was designed aiming to facilitate university students to compose videos on different difficult concepts in the theory part of the course by searching for explanations on the web and by creating a Windows Media Player video focusing on the self‐defined pro…