Our study contributes to the research on computer-mediated communication in higher education by experimenting a modern communication tool called Slack. In particular, we consider using Slack to ...support students’ peer interactions during Master’s thesis work. For this purpose, we designed a case study that was executed in a Master’s thesis seminar course. During the course, all out-of-class communication was carried out by using Slack, instead of e-mails or learning management systems. After the course, we used a questionnaire to investigate how the students perceived Slack for asking for assistance, their intention to use Slack, and Slack’s ease of use. Furthermore, the questionnaire asked feedback about challenges that the students found in slack. To examine the students’ peer support in Slack, we analysed the messages in the course’s public discussion channels. We investigated opportunities and challenges of Slack from instructional perspective by conducting an auto-ethnographic data collection. Our analysis revealed that the students perceived Slack as an easy-to-use communication tool with a low threshold of asking questions. The students also expressed high intentions to use Slack in the future. However, the students were worried of information overload in Slack, frustrated with decentralisation of communication tools in higher education, and cautious of using communication tools that are not officially supported by the university. The students’ interactions were assigned to three categories: practical, technical, and thesis-related. Analysis of these categories revealed that the students were able to explicate and solve issues in Slack, but the issues were only related to practical and technical problems, instead of actual Master’s thesis writing. The teacher perceived that Slack enhanced bi-directional communication with the students, but faced issues related to file management and user authentication. The results implicate that developing an alternative for Slack from educational premises could be more useful than a product that is not originally developed for pedagogical needs. Finally, we present recommendations that help educators to use Slack in their educational practices.
Two new initialization methods for K-means clustering are proposed. Both proposals are based on applying a divide-and-conquer approach for the K-means‖ type of an initialization strategy. The second ...proposal also uses multiple lower-dimensional subspaces produced by the random projection method for the initialization. The proposed methods are scalable and can be run in parallel, which make them suitable for initializing large-scale problems. In the experiments, comparison of the proposed methods to the K-means++ and K-means‖ methods is conducted using an extensive set of reference and synthetic large-scale datasets. Concerning the latter, a novel high-dimensional clustering data generation algorithm is given. The experiments show that the proposed methods compare favorably to the state-of-the-art by improving clustering accuracy and the speed of convergence. We also observe that the currently most popular K-means++ initialization behaves like the random one in the very high-dimensional cases.
Clustering is an unsupervised machine learning and pattern recognition method. In general, in addition to revealing hidden groups of similar observations and clusters, their number needs to be ...determined. Internal clustering validation indices estimate this number without any external information. The purpose of this article is to evaluate, empirically, characteristics of a representative set of internal clustering validation indices with many datasets. The prototype-based clustering framework includes multiple, classical and robust, statistical estimates of cluster location so that the overall setting of the paper is novel. General observations on the quality of validation indices and on the behavior of different variants of clustering algorithms will be given.
The extreme learning machine (ELM) and the minimal learning machine (MLM) are nonlinear and scalable machine learning techniques with a randomly generated basis. Both techniques start with a step in ...which a matrix of weights for the linear combination of the basis is recovered. In the MLM, the feature mapping in this step corresponds to distance calculations between the training data and a set of reference points, whereas in the ELM, a transformation using a radial or sigmoidal activation function is commonly used. Computation of the model output, for prediction or classification purposes, is straightforward with the ELM after the first step. In the original MLM, one needs to solve an additional multilateration problem for the estimation of the distance-regression based output. A natural combination of these two techniques is proposed and experimented here: to use the distance-based basis characteristic in the MLM in the learning framework of the regularized ELM. In other words, we conduct ridge regression using a distance-based basis. The experimental results characterize the basic features of the proposed technique and surprisingly, indicate that overlearning with the distance-based basis is in practice avoided in classification problems. This makes the model selection for the proposed method trivial, at the expense of computational costs.
Although increasing studies have confirmed the distinction between emotion-label words (words directly label emotional states) and emotion-laden words (words evoke emotions through connotations), the ...existing evidence is inconclusive, and their embodiment is unknown. In the current study, the emotional categorization task was adopted to investigate whether these two types of emotion words are embodied by directly comparing how they are processed in individuals' native language (L1) and the second language (L2) among late Chinese-English bilinguals. The results revealed that apart from L2 negative emotion-laden words, both types of emotion words in L1 and L2 produced significant emotion effects, with faster response times and/or higher accuracy rates. In addition, processing facilitation for emotion-label words over emotion-laden words was observed irrespective of language operation; a significant three-way interaction between the language, valence and emotion word type was noted. Taken together, this study suggested that the embodiment of emotion words is modulated by the emotion word type, and L2 negative emotion-laden words tend to be affectively disembodied. The disassociation between emotion-label and emotion-laden words is confirmed in both L1 and L2 and therefore, future emotion word research should take the emotion word type into account.
Epileptic seizure detection using scalp electroencephalogram (sEEG) and intracranial electroencephalogram (iEEG) has attracted widespread attention in recent two decades. The accurate and rapid ...detection of seizures not only reflects the efficiency of the algorithm, but also greatly reduces the burden of manual detection during long-term electroencephalogram (EEG) recording. In this work, a stacked one-dimensional convolutional neural network (1D-CNN) model combined with a random selection and data augmentation (RS-DA) strategy is proposed for seizure onset detection. Firstly, we segmented the long-term EEG signals using 2-s sliding windows. Then, the 2-s interictal and ictal segments were classified by the stacked 1D-CNN model. During model training, a RS-DA strategy was applied to solve the problem of sample imbalance, and the patient-specific model was trained with event-based K-fold (K is the number of seizures per patient) cross validation for detecting all seizures of each patient. Finally, we evaluated the performances of the proposed approach in the two levels: the segment-based level and the event-based level. The proposed method was tested on two long-term EEG datasets: the CHB-MIT sEEG dataset and the SWEC-ETHZ iEEG dataset. For the CHB-MIT sEEG dataset, we achieved 88.14% sensitivity, 99.62% specificity and 99.54% accuracy in the segment-based level. From the perspective of the event-based level, 99.31% sensitivity, 0.2/h false detection rate (FDR) and mean 8.1-s latency were achieved. For the SWEC-ETHZ iEEG dataset, in the segment-based level, 90.09% sensitivity, 99.81% specificity and 99.73% accuracy were obtained. In the event-based level, 97.52% sensitivity, 0.07/h FDR and mean 13.2-s latency were attained. From these results, we can see that our method can effectively use both sEEG and iEEG data to detect epileptic seizures, and this may provide a reference for the clinical application of seizure onset detection.
Minimal Learning Machine (MLM) is a recently popularized supervised learning method, which is composed of distance-regression and multilateration steps. The computational complexity of MLM is ...dominated by the solution of an ordinary least-squares problem. Several different solvers can be applied to the resulting linear problem. In this paper, a thorough comparison of possible and recently proposed, especially randomized, algorithms is carried out for this problem with a representative set of regression datasets. In addition, we compare MLM with shallow and deep feedforward neural network models and study the effects of the number of observations and the number of features with a special dataset. To our knowledge, this is the first time that both scalability and accuracy of such a distance-regression model are being compared to this extent. We expect our results to be useful on shedding light on the capabilities of MLM and in assessing what solution algorithms can improve the efficiency of MLM. We conclude that (i) randomized solvers are an attractive option when the computing time or resources are limited and (ii) MLM can be used as an out-of-the-box tool especially for high-dimensional problems.
Sharing local co-owned photovoltaic (PV) energy in multifamily residential buildings is inefficient. Energy produced and consumed within the same building may be considered purchased energy, of which ...the customer must pay the purchase price, the network service fee, and taxes. As PV typically does not allow self-sufficiency in the Nordic countries, a distribution system operator is needed to provide the grid connection. Earlier solutions to this problem are focused on energy communities where an energy aggregator is responsible for the energy balance settlement. However, this does not allow the energy community members to remain in the open electricity market. This paper introduces a blockchain-based balance settlement ledger and a set of rules for energy sharing in energy communities where members participate in the open electricity market while supplied with local low-cost PV energy. This, to the authors’ knowledge, has not been previously implemented. The blockchain mitigates the need for any central entity for balance settlement and ensures fair sharing of PV energy. The existing smart meters can be used so no investments are required. The system performance is tested with simulations which show potential for increase in profitability. The self-sufficiency rate increases in our test scenario from 4.03% to 9.61%.
•Efficient sharing and utilization of locally produced solar energy.•Benefits of both local solar energy and open electricity market can be obtained.•No investments needed as existing smart meters can be used.
Understanding hydrogen adsorption on metal nanoparticles is a key prerequisite for designing efficient electrocatalysts for water splitting and the hydrogen evolution reaction. However, this ...seemingly simple elementary reaction step is affected by several factors arising from the chemical environment at the catalyst, and deciphering the most important contributions to optimal interactions requires numerically heavy electronic structure calculations. Here, we combine graph-based representations of the local atomic environment of hydrogen in copper- and palladium-doped 25-atom gold nanoparticles with several kernel-based machine learning (ML) methods to predict the interaction energy between hydrogen and the nanoparticle catalyst. We demonstrate that simple distance-based kernel models are able to predict the interaction energy within 0.1 eV when trained by reference data from state-of-the-art density functional theory calculations. Analyzing the model performance with respect to attributes of the hydrogen node highlights the locality of hydrogen adsorption. This implies the viability of combining graphs with kernel-based ML models for studying hydrogen chemisorption in complex environment data efficiently.
Hybrid metal nanoparticles, consisting of a nano-crystalline metal core and a protecting shell of organic ligand molecules, have applications in diverse areas such as biolabeling, catalysis, ...nanomedicine, and solar energy. Despite a rapidly growing database of experimentally determined atom-precise nanoparticle structures and their properties, there has been no successful, systematic way to predict the atomistic structure of the metal-ligand interface. Here, we devise and validate a general method to predict the structure of the metal-ligand interface of ligand-stabilized gold and silver nanoparticles, based on information about local chemical environments of atoms in experimental data. In addition to predicting realistic interface structures, our method is useful for investigations on the steric effects at the metal-ligand interface, as well as for predicting isomers and intermediate structures induced by thermal dynamics or interactions with the environment. Our method is applicable to other hybrid nanomaterials once a suitable set of reference structures is available.