0000000000307084
AUTHOR
Lauri Kettunen
Alleviating Class Imbalance Problem in Automatic Sleep Stage Classification
For real-world automatic sleep-stage classification tasks, various existing deep learning-based models are biased toward the majority with a high proportion. Because of the unique sleep structure, most of the current polysomnography (PSG) datasets suffer an inherent class imbalance problem (CIP), in which the number of each sleep stage is severely unequal. In this study, we first define the class imbalance factor (CIF) to describe the level of CIP quantitatively. Afterward, we propose two balancing methods to alleviate this problem from the dataset quantity and the relationship between the class distribution and the applied model, respectively. The first one is to employ the data augmentati…
Generalized finite difference schemes with higher order Whitney forms
Finite difference kind of schemes are popular in approximating wave propagation problems in finite dimensional spaces. While Yee’s original paper on the finite difference method is already from the sixties, mathematically there still remains questions which are not yet satisfactorily covered. In this paper, we address two issues of this kind. Firstly, in the literature Yee’s scheme is constructed separately for each particular type of wave problem. Here, we explicitly generalize the Yee scheme to a class of wave problems that covers at large physics field theories. For this we introduce Yee’s scheme for all problems of a class characterised on a Minkowski manifold by (i) a pair of first ord…
General conservation law for a class of physics field theories
In this paper we form a general conservation law that unifies a class of physics field theories. For this we first introduce the notion of a general field as a formal sum differential forms on a Minkowski manifold. Thereafter, we employ the action principle to define the conservation law for such general fields. By construction, particular field notions of physics, such as electric field strength, stress, strain etc. become instances of the general field. Hence, the differential equations that constitute physics field theories become also instances of the general conservation law. Accordingly, the general field and the general conservation law together correspond to a large class of physics…
Propulsion Calculated by Force and Displacement of Center of Mass in Treadmill Cross-Country Skiing
This study evaluated two approaches for estimating the total propulsive force on a skier’s center of mass (COM) with double-poling (DP) and V2-skating (V2) skiing techniques. We also assessed the accuracy and the stability of each approach by changing the speed and the incline of the treadmill. A total of 10 cross-country skiers participated in this study. Force measurement bindings, pole force sensors, and an eight-camera Vicon system were used for data collection. The coefficient of multiple correlation (CMC) was calculated to evaluate the similarity between the force curves. Mean absolute force differences between the estimated values and the reference value were computed to evalua…
Novel qutrit circuit design for multiplexer, De-multiplexer, and decoder
AbstractDesigning conventional circuits present many challenges, including minimizing internal power dissipation. An approach to overcoming this problem is utilizing quantum technology, which has attracted significant attention as an alternative to Nanoscale CMOS technology. The reduction of energy dissipation makes quantum circuits an up-and-coming emerging technology. Ternary logic can potentially diminish the quantum circuit width, which is currently a limitation in quantum technologies. Using qutrit instead of qubit could play an essential role in the future of quantum computing. First, we propose two approaches for quantum ternary decoder circuit in this context. Then, we propose a qua…
Self-Efficacy and Study Burnout Among IT Students : Challenges and Potentials
There is a risk of student dropout in the field of engineering, particularly in the domain of information technology. To find novel pedagogical and technological solutions to prevent student attrition, we must better understand student experiences regarding their learning and studying processes. This study was conducted within the introduction of a new engineering degree program at the University of Jyväskylä and focused on first-year students. The research questions are: How do IT students experience study burnout at the beginning of their studies? What kind of self-efficacy beliefs do IT students have at the beginning of their studies? How are the self-efficacy beliefs of IT students asso…
LightSleepNet: A Lightweight Deep Model for Rapid Sleep Stage Classification with Spectrograms.
Deep learning has achieved unprecedented success in sleep stage classification tasks, which starts to pave the way for potential real-world applications. However, due to its enormous size, deployment of deep neural networks is hindered by high cost at various aspects, such as computation power, storage, network bandwidth, power consumption, and hardware complexity. For further practical applications (e.g., wearable sleep monitoring devices), there is a need for simple and compact models. In this paper, we propose a lightweight model, namely LightSleepNet, for rapid sleep stage classification based on spectrograms. Our model is assembled by a much fewer number of model parameters compared to…
Introduction to next-generation engineering: Being human in the information society
While adopting Information Technology (IT) may have been a goal in itself in the past, during the last decade the emphasis has shifted, and IT has instead become a tool that enables us to realize other needs. This also sets new requirements for IT education: skills in software engineering and computer science alone do not provide students with the professional abilities they will need after graduation. To answer this call, the University of Jyväskylä launched in autumn 2021 a new engineering B.Sc. and M.Sc. degree program in Information and Software Engineering with close ties to the Humanities. The degree program was established on three cornerstones: 1) the ability to implement IT systems…
Essential Measurements for Finite Element Simulations of Magnetostrictive Materials
We discuss which magnetoelastic material properties are essential to measure in order to model magnetostrictive materials in finite element simulations. We show knowing the magnetic constitutive relation is sufficient, if the elastic behavior without magnetic field is known a priori. We neglect hysteresis, and our starting point is to express the effect of mechanical deformation on the magnetic constitutive relation with a small strain tensor and magnetic flux density. It follows that the (energetic) state of a magnetostrictive material is independent of its history. Then, a certain choice of history allows us to keep magnetism and elasticity distinct. We demonstrate with open source softwa…
AnatomySketch : An Extensible Open-Source Software Platform for Medical Image Analysis Algorithm Development
AbstractThe development of medical image analysis algorithm is a complex process including the multiple sub-steps of model training, data visualization, human–computer interaction and graphical user interface (GUI) construction. To accelerate the development process, algorithm developers need a software tool to assist with all the sub-steps so that they can focus on the core function implementation. Especially, for the development of deep learning (DL) algorithms, a software tool supporting training data annotation and GUI construction is highly desired. In this work, we constructed AnatomySketch, an extensible open-source software platform with a friendly GUI and a flexible plugin interfac…
Systematisation of Systems Solving Physics Boundary Value Problems
A general conservation law that defines a class of physical field theories is constructed. First, the notion of a general field is introduced as a formal sum of differential forms on a Minkowski manifold. By the action principle the conservation law is defined for such a general field. By construction, particular field notions of physics, e.g., magnetic flux, electric field strength, stress, strain etc. become instances of the general field. Hence, the differential equations that constitute physical field theories become also instances of the general conservation law. The general field and the general conservation law together correspond to a large class of relativistic hyperbolic physical …
Efficient contour-based annotation by iterative deep learning for organ segmentation from volumetric medical images
Abstract Purpose Training deep neural networks usually require a large number of human-annotated data. For organ segmentation from volumetric medical images, human annotation is tedious and inefficient. To save human labour and to accelerate the training process, the strategy of annotation by iterative deep learning recently becomes popular in the research community. However, due to the lack of domain knowledge or efficient human-interaction tools, the current AID methods still suffer from long training time and high annotation burden. Methods We develop a contour-based annotation by iterative deep learning (AID) algorithm which uses boundary representation instead of voxel labels to incorp…
Generalized wave propagation problems and discrete exterior calculus
We introduce a general class of second-order boundary value problems unifying application areas such as acoustics, electromagnetism, elastodynamics, quantum mechanics, and so on, into a single framework. This also enables us to solve wave propagation problems very efficiently with a single software system. The solution method precisely follows the conservation laws in finite-dimensional systems, whereas the constitutive relations are imposed approximately. We employ discrete exterior calculus for the spatial discretization, use natural crystal structures for three-dimensional meshing, and derive a “discrete Hodge” adapted to harmonic wave. The numerical experiments indicate that the cumulat…
Modelling chemical composition in electric systems - implications to the dynamics of dye-sensitised solar cells
International audience; Classical electromagnetism provides limited means to model electric generators. To extend the classical theory in this respect, additional information on microscopic processes is required. In semiconductor devices and electrochemical generators such information may be obtained by modelling chemical composition. Here we use this approach for the modelling of dye-sensitised solar cells. We simulate the steady-state current-voltage characteristics of such a cell, as well as its transient response. Dynamic simulations show optoelectronic hysteresis in these cells under transient light pulse illumination.
Novel high-performance QCA Fredkin gate and designing scalable QCA binary to gray and vice versa
AbstractIn the design of digital logic circuits, QCA technology is an excellent alternative to CMOS technology. Its advantages over CMOS include low power consumption, fast circuit switching, and nanoscale design. Circuits that convert data between different formats are code converters. Code converters have an essential role in high-performance computing and signal processing. In this paper, first, we proposed a novel QCA structure for the quantum reversible Fredkin gate. Second, we proposed 4-bit and 8-bit QCA binary-to-gray converter and vice versa. For the second proposal, both reversible and irreversible structures are suggested. The proposed structures are scalable up to N bits. To cha…
Systematic derivation of partial differential equations for second order boundary value problems
Software systems designed to solve second order boundary value problems are typically restricted to hardwired lists of partial differential equations. In order to come up with more flexible systems, we introduce a systematic approach to find partial differential equations that result in eligible boundary value problems. This enables one to construct and combine one's own partial differential equations instead of choosing those from a pre-given list. This expands significantly end users possibilities to employ boundary value problems in modeling. To introduce the main ideas we employ differential geometry to examine the mathematical structure involved in second order boundary value problems …
Whitney forms and their extensions
Whitney forms are widely known as finite elements for differential forms. Whitney’s original definition yields first order functions on simplicial complexes, and a lot of research has been devoted to extending the definition to nonsimplicial cells and higher order functions. As a result, the term Whitney forms has become somewhat ambiguous in the literature. Our aim here is to clarify the concept of Whitney forms and explicitly explain their key properties. We discuss Whitney’s initial definition with more depth than usually, giving three equivalent ways to define Whitney forms. We give a comprehensive exposition of their main properties, including the proofs. Understanding of these propert…
A Multi-Position Calibration Method for Consumer-Grade Accelerometers, Gyroscopes, and Magnetometers to Field Conditions
This paper presents a calibration method for consumer-grade accelerometers, gyroscopes, and magnetometers. Considering the calibration of consumer-grade sensors, it is essential that no specialized equipment is required to create reference signals. In addition, the less is required from the reference signals, the more suitable the method is on the field. In the proposed method, the novelty in the calibration of the gyroscopes lies in the exploitation of only the known net rotations between the positions in a multi-position calibration. For accelerometers and magnetometers, the innovation is that the direction of reference signals, the gravity and the magnetic field of the Earth, are estimat…
SingleChannelNet : A model for automatic sleep stage classification with raw single-channel EEG
In diagnosing sleep disorders, sleep stage classification is a very essential yet time-consuming process. Various existing state-of-the-art approaches rely on hand-crafted features and multi-modality polysomnography (PSG) data, where prior knowledge is compulsory and high computation cost can be expected. Besides, it is a big challenge to handle the task with raw single-channel electroencephalogram (EEG). To overcome these shortcomings, this paper proposes an end-to-end framework with a deep neural network, namely SingleChannelNet, for automatic sleep stage classification based on raw single-channel EEG. The proposed model utilizes a 90s epoch as the textual input and employs two multi-conv…
Convolutional Neural Network Based Sleep Stage Classification with Class Imbalance
Accurate sleep stage classification is vital to assess sleep quality and diagnose sleep disorders. Numerous deep learning based models have been designed for accomplishing this labor automatically. However, the class imbalance problem existing in polysomnography (PSG) datasets has been barely investigated in previous studies, which is one of the most challenging obstacles for the real-world sleep staging application. To address this issue, this paper proposes novel methods with signal-driven and image-driven ways of noise addition to balance the imbalanced relationship in the training dataset samples. We evaluate the effectiveness of the proposed methods which are integrated into a convolut…