Search results for "oppiminen"
showing 10 items of 2266 documents
Automatic sleep scoring: A deep learning architecture for multi-modality time series
2020
Background: Sleep scoring is an essential but time-consuming process, and therefore automatic sleep scoring is crucial and urgent to help address the growing unmet needs for sleep research. This paper aims to develop a versatile deep-learning architecture to automate sleep scoring using raw polysomnography recordings. Method: The model adopts a linear function to address different numbers of inputs, thereby extending model applications. Two-dimensional convolution neural networks are used to learn features from multi-modality polysomnographic signals, a “squeeze and excitation” block to recalibrate channel-wise features, together with a long short-term memory module to exploit long-range co…
Hippocampal theta phase-contingent memory retrieval in delay and trace eyeblink conditioning
2017
Hippocampal theta oscillations (3-12Hz) play a prominent role in learning. It has been suggested that encoding and retrieval of memories are supported by different phases of the theta cycle. Our previous study on trace eyeblink conditioning in rabbits suggests that the timing of the conditioned stimulus (CS) in relation to theta phase affects encoding but not retrieval of the memory trace. Here, we directly tested the effects of hippocampal theta phase on memory retrieval in two experiments conducted on adult female New Zealand White rabbits. In Experiment 1, animals were trained in trace eyeblink conditioning followed by extinction, and memory retrieval was tested by presenting the CS at t…
Ensuring Diverse User Experiences and Accessibility While Developing the TeSLA e-Assessment System
2019
The TeSLA project, with its new, innovative approaches for e-assessment, offers a great possibility for increasing the educational equality and making higher education studies available for all. It has been estimated that 10–15% of students in higher education institutions have some disabilities or special educational needs. At online universities or in online programmes, the number is even higher. These numbers emphasise the importance of the universal design for learning as a leading principle while developing the digital learning environments and e-assessment procedures. In this chapter, we describe the key elements of ensuring the accessibility of the TeSLA e-assessment system during th…
Developing E-Authentication for E-Assessment : Diversity of Students Testing the System in Higher Education
2020
Sähköinen tunnistautuminen on yksi keskeisistä teemoista verkko-opetuksessa, -opiskelussa ja - arvioinnissa. Tämän tutkimuksen tarkoituksena oli tutkia opiskeluunsa erityistä tukea tarvitsevien yliopisto-opiskelijoiden käyttökokemuksia kehitteillä olevasta sähköisestä tunnistautumisjärjestelmästä. Erityistä huomiota kehittämistyössä kiinnitettiin tunnistautumisen saavutettavuuteen. Kaikkiaan 15 opiskelijaa testasi TeSLA-projektin osana kehitettyä tunnistautumisjärjestelmää, johon kuului kasvojentunnistus, äänentunnistus, näppäilyntunnistus, tekstityylianalyysi ja plagioinnin tunnistus. Opiskelijat täyttivät esi- ja jälkikyselylomakkeet sekä osallistuivat henkilökohtaisiin haastatteluihin. T…
Cell state prediction through distributed estimation of transmit power
2019
Determining the state of each cell, for instance, cell outages, in a densely deployed cellular network is a difficult problem. Several prior studies have used minimization of drive test (MDT) reports to detect cell outages. In this paper, we propose a two step process. First, using the MDT reports, we estimate the serving base station’s transmit power for each user. Second, we learn summary statistics of estimated transmit power for various networks states and use these to classify the network state on test data. Our approach is able to achieve an accuracy of 96% on an NS-3 simulation dataset. Decision tree, random forest and SVM classifiers were able to achieve a classification accuracy of…
Dynamic Functional Connectivity Captures Individuals’ Unique Brain Signatures
2020
Recent neuroimaging evidence suggest that there exists a unique individual-specific functional connectivity (FC) pattern consistent across tasks. The objective of our study is to utilize FC patterns to identify an individual using a supervised machine learning approach. To this end, we use two previously published data sets that comprises resting-state and task-based fMRI responses. We use static FC measures as input to a linear classifier to evaluate its performance. We additionally extend this analysis to capture dynamic FC using two approaches: the common sliding window approach and the more recent phase synchrony-based measure. We found that the classification models using dynamic FC pa…
The integration of content and language in students’ task answer production in the bilingual classroom
2016
The notion of content and language integration has recently become a key topic of inquiry in research on content and language integrated learning and other kinds of bilingual educational programmes. Understanding what integration is and how it happens is of fundamental importance not only for researchers interested in gauging the possibilities and limitations of bilingual programmes, but also for practitioners seeking optimal ways to support student development. This study investigates integration as it takes place in the context of collaborative writing in the classroom. Drawing on conversation analytic methodology, text production is investigated as a social and sequentially evolving phen…
Towards multilingual competence: examining beliefs and agency in first year university students’ language learner biographies
2021
As working life across the world is increasingly multilingual, multicultural and multidisciplinary, higher education language teaching is faced with a challenge of how to prepare students for it. Many universities have recently developed multilingual pedagogies but central to their success is learners’ perceptions of these practices. To fill this gap, this article explores first year university students’ language learner biographies to gain insight into how learners construct their linguistic realities. The biographies were studied with discourse analytical methods to examine the participants’ beliefs about language learning and their sense of agency in it. The results reveal that participa…
Why Digital Games Can Be Advantageous in Vocabulary Learning
2021
Vocabulary learning is an integral part of language learning; however, it is difficult. Although there are many techniques proposed for vocabulary learning and teaching, researchers still strive to find effective methods. Recently, digital games have shown potentials in enhancing vocabulary acquisition. A majority of studies in digital game-based vocabulary learning (DGBVL) literature investigate the effectiveness of DGBVL tasks. In other words, there are enough answers to what questions in DGBVL literature whereas why questions are rarely answered. Finding such answers help us learn more about the structure of the DGBVL tasks and their effects on vocabulary learning. Hence, to achieve this…
Migrant women, work, and investment in language learning : Two success stories
2019
Abstract In the media, migrant mothers are often portrayed as uneducated, having trouble learning a new language, and preferring to stay at home rather than entering paid employment. This article offers a contrasting point of view as a result of examining how two migrant women narrativize their experiences of language learning and working-life-related integration during a three-year period. Specific attention is paid to how the women make sense of their language use over time, and how this may have contributed to their integration into working life and the wellbeing of their families. Interview data was analyzed using the short story analytical approach, focusing on both the content and the…