Industry 4.0 is expected to provide high quality and customized products at lower costs by increasing efficiency, and hence create a competitive advantage in the manufacturing industry. As the emergence of Industry 4.0 is deeply rooted in the past industrial revolutions, Advanced Manufacturing Technologies of Industry 3.0 are the precursors of the latest Industry 4.0 technologies. This study aims to contribute to the understanding of technological evolution of manufacturing industry based on the relationship between the usage levels of Advanced Manufacturing Technologies and Industry 4.0 technologies. To this end, a survey was conducted with Turkish manufacturers to assess and compare their manufacturing technology usage levels. The survey data collected from 424 companies was analyzed by machine learning approach. The results of the study reveal that the implementation level of each Industry 4.0 technology is positively associated with the implementation levels of a set of Advanced Manufacturing Technologies.

Traffic classification is an important tool for network management. It reveals the source of observed network traffic and has many potential applications e.g. in Quality of Service, network security and traffic visualization. In the last decade, traffic classification evolved quickly due to the raise of peer-to-peer traffic. Nowadays, researchers still find new methods in order to withstand the rapid changes of the Internet. In this paper, we review 13 publications on traffic classification and related topics that were published during 2009-2012. We show diversity in recent algorithms and we highlight possible directions for the future research on traffic classification: relevance of multi-level classification, importance of experimental validation, and the need for common traffic datasets.

There is a discrepancy between the research exploring e-learning at medical universities in Central/Eastern and Western European countries. The aim of the MeSPeLA study was to explore the understanding, experience and expectations of Polish medical students in terms of e-learning. Questionnaire containing open-ended and closed questions supplemented by focus group discussion was validated and performed among 204 medical students in Poland before COVID-19 pandemia. Several domains: understanding of e-learning definitions; students’ experience, preferences, expectations and perceptions of e-learning usefulness, advantages and disadvantages were addressed. The qualitative data were analyzed using an inductive approach. 46.0% of students chose a communication-oriented definition as the most appropriate. 7.4% claimed not to have any experience with e-learning. 76.8% of respondents indicated they had contact with e-learning. The main reported e-learning advantages were time saving and easier time management. The most common drawback was limited social interactions. The acceptance of the usage of e-learning was high. Medical undergraduates in Poland regardless of the year of studies, gender or choice of future specialization showed positive attitudes towards e-learning. Students with advanced IT skills showed a better understanding of the e-learning definition and perceived e-learning to be a more useful approach. The expectations and perceptions about e-learning in Polish medical schools seems similar to some extent to that in Western European and the United States so we can be more confident about applying some lessons from these research to Poland or other post-communist countries. Such application has been accelerated due to COVID-19 pandemia.

This paper presents the improved version of the classification system for supporting glaucoma diagnosis in ophthalmology. In this

paper we propose the new segmentation step based on the support vector clustering algorithm which enables better classification performance.

Prof. Małgorzata Kossut of the Nencki Institute of Experimental Biology talks about brain plasticity, the mechanisms of learning, and the mysteries of forgetfulness.

Background: The skills and attitudes of medical staff affect the quality of the healthcare system, hence the study of academic motivation and quality of life of medical students.
Materials and Methods: The study involved 203 students of the Jagiellonian University Medical College. Academic motivation was assessed using the Academic Motivation Scale and quality of life using the World Health Organization Quality of Life-BREF questionnaire. Academic Motivation Scale is based on the Self-Determination Theory, which distinguishes several dimensions of motivation arranged along self-determination continuum from amotivation, through extrinsic, controllable motivation, to intrinsic, autonomous motivation.
Results: For our students, the main reason for taking up studies was identified regulation, it means that they perceive studying as something important for them, giving more opportunities in the future. Next was intrinsic motivations to know, where gaining knowledge is a value in itself. The third was external regulation, which indicate that the choice of studies was regulated by the dictates of the environment or the desire to obtain a reward. Female students showed a more intrinsically motivational profile than male students. Motivation became less autonomous as the years of study progressed. Most students rated their quality of life as good or very good. There was weak correlation between students’ good quality of life and more self-determined academic motivation.
Conclusions: Our students are mainly intrinsically motivated, most of them positively assess the quality of life. A more autonomous approach to learning coexisted with a positive assessment of quality of life.

Federated Learning is an upcoming concept used widely in distributed machine learning. Federated learning (FL) allows a large number of users to learn a single machine learning model together while the training data is stored on individual user devices. Nonetheless, federated learning lessens threats to data privacy. Based on iterative model averaging, our study suggests a feasible technique for the federated learning of deep networks with improved security and privacy. We also undertake a thorough empirical evaluation while taking various FL frameworks and averaging algorithms into consideration. Secure Multi Party Computation, Secure Aggregation, and Differential Privacy are implemented to improve the security and privacy in a federated learning environment. In spite of advancements, concerns over privacy remain in FL, as the weights or parameters of a trained model may reveal private information about the data used for training. Our work demonstrates that FL can be prone to label-flipping attack and a novel method to prevent label-flipping attack has been proposed. We compare standard federated model aggregation and optimization methods, FedAvg and FedProx using benchmark data sets. Experiments are implemented in two different FL frameworks - Flower and PySyft and the results are analysed. Our experiments confirm that classification accuracy increases in FL framework over a centralized model and the model performance is better after adding all the security and privacy algorithms. Our work has proved that deep learning models perform well in FL and also is secure.

In recent years, deep learning and especially deep neural networks (DNN) have obtained amazing performance on a variety of problems, in particular in classification or pattern recognition. Among many kinds of DNNs, the convolutional neural networks (CNN) are most commonly used. However, due to their complexity, there are many problems related but not limited to optimizing network parameters, avoiding overfitting and ensuring good generalization abilities. Therefore, a number of methods have been proposed by the researchers to deal with these problems. In this paper, we present the results of applying different, recently developed methods to improve deep neural network training and operating. We decided to focus on the most popular CNN structures, namely on VGG based neural networks: VGG16, VGG11 and proposed by us VGG8. The tests were conducted on a real and very important problem of skin cancer detection. A publicly available dataset of skin lesions was used as a benchmark. We analyzed the influence of applying: dropout, batch normalization, model ensembling, and transfer learning. Moreover, the influence of the type of activation function was checked. In order to increase the objectivity of the results, each of the tested models was trained 6 times and their results were averaged. In addition, in order to mitigate the impact of the selection of learning, test and validation sets, k-fold validation was applied.

Thousands of low-power micro sensors make up Wireless Sensor Networks, and its principal role is to detect and report specified events to a base station. Due to bounded battery power these nodes are having very limited memory and processing capacity. Since battery replacement or recharge in sensor nodes is nearly impossible, power consumption becomes one of the most important design considerations in WSN. So one of the most important requirements in WSN is to increase battery life and network life time. Seeing as data transmission and reception consume the most energy, it’s critical to develop a routing protocol that addresses the WSN’s major problem. When it comes to sending aggregated data to the sink, hierarchical routing is critical. This research concentrates on a cluster head election system that rotates the cluster head role among nodes with greater energy levels than the others.We used a combination of LEACH and deep learning to extend the network life of the WSN in this study. In this proposed method, cluster head selection has been performed by Convolutional Neural Network (CNN). The comparison has been done between the proposed solution and LEACH, which shows the proposed solution increases the network lifetime and throughput.

Skin Cancer is one of the most widely present forms of cancer. The correct classification of skin lesions as malignant or benign is a complex process that has to be undertaken by experienced specialists. Another major issue of the class imbalance of data causes a bias in the results of classification. This article presents a novel approach to the usage of metadata of skin lesions' images to classify them. The usage of techniques addresses the problem of class imbalance to nullify the imbalances. Further, the use of a convolutional neural network (CNN) is proposed to finetune the skin lesion data classification. Ultimately, it is proven that an ensemble of statistical metadata analysis and CNN usage would result in the highest accuracy of skin color classification instead of using the two techniques separately.

The paper presents a method for designing a neural speed controller with use of Reinforcement Learning method. The controlled object is an electric drive with a synchronous motor with permanent magnets, having a complex mechanical structure and changeable parameters. Several research cases of the control system with a neural controller are presented, focusing on the change of object parameters. Also, the influence of the system critic behaviour is researched, where the critic is a function of control error and energy cost. It ensures long term performance stability without the need of switching off the adaptation algorithm. Numerous simulation tests were carried out and confirmed on a real stand.

Specific emitter identification (SEI) is the process of identifying individual emitters by analyzing the radio frequency emissions, based on the fact that each device contains unique hardware imperfections. While the majority of previous research focuses on obtaining features that are discriminative, the reliability of the features is rarely considered. For example, since device characteristics of the same emitter vary when it is operating at different carrier frequencies, the performance of SEI approaches may degrade when the training data and the test data are collected from the same emitters with different frequencies. To improve performance of SEI under varying frequency, we propose an approach based on continuous wavelet transform (CWT) and domain adversarial neural network (DANN). The proposed approach exploits unlabeled test data in addition to labeled training data, in order to learn representations that are discriminative for individual emitters and invariant for varying frequencies. Experiments are conducted on received signals of five emitters under three carrier frequencies. The results demonstrate the superior performance of the proposed approach when the carrier frequencies of the training data and the test data differ.

The paper proposes to apply an algorithm for predicting the minimum level of the state of charge (SoC) of stationary supercapacitor energy storage system operating in a DC traction substation, and for changing it over time. This is done to insure maximum energy recovery for trains while braking. The model of a supercapacitor energy storage system, its algorithms of operation and prediction of the minimum state of charge are described in detail; the main formulae, graphs and results of simulation are also provided. It is proposed to divide the SoC curve into equal periods of time during which the minimum states of charge remain constant. To predict the SoC level for the subsequent period, the learning algorithm based on the neural network could be used. Then, the minimum SoC could be based on two basic types of data: the first one is the time profile of the energy storage load during the previous period with the constant minimum SoC retained, while the second one relies on the trains’ locations and speed values in the previous period. It is proved that the use of variable minimum SoC ensures an increase of the energy volume recovered by approximately 10%. Optimum architecture and activation function of the neural network are also found.

In this article I present the main assumptions and discuss issues of pedagogy as a science and the field of education during a special meeting of the Committee of the Academy of Pedagogical Sciences at Adam Mickiewicz University in Poznan. I focus on the institutional leaders in science teaching who are rectors and deans of Faculties of Education in Poland. Moreover, they are co-authors of relevant teaching and research solutions in science teaching. In the age of growing crisis in the academic community we can, as educators, discuss how no to be to be surprised by pathogenic processes and events, but how to be able to counteract them. Furthermore, how to show representatives of other academic disciplines and structures of learning, how to deal with common to us problems.

Equilibrium, disequilibrium and adaptation. The inspirations for spatial economics. This paper is a part of author’s long-term research project related to dynamics and evolution of space economy. In the attempts of theoretical reconstruction of these processes the notion of equilibrium plays an important role, as well as related notions: disequilibrium and adaptation. In the analysis of equilibrium the author drew on the concepts elaborated by the neoclassical school of economics. In the analysis of disequilibrium the concept of physics turned out to be fertilizing, namely the concept of dissipative structures and self-organisation. The concept of adaptation is elaborated in depth in biology. These three concepts have been applied in spatial economics long since. Further research is necessary however, to make these application more relevant to spatial economics, and in this way more fruitful.

The traditional self organizing map (SOM) is learned by Kohonen learning. The main disadvantage of this approach is in epoch based learning when the radius and rate of learning are decreasing functions of epoch index. The aim of study is to demonstrate advantages of diffusive learning in single epoch learning and other cases for both traditional and anomalous diffusion models. We also discuss the differences between traditional and anomalous learning in models and in quality of obtained SOM. The anomalous diffusion model leads to less accurate SOM which is in accordance to biological assumptions of normal diffusive processes in living nervous system. But the traditional Kohonen learning has been overperformed by novel diffusive learning approaches.

In this work nine non-linear regression models were compared for sub-pixel impervious surface area mapping from Landsat images. The comparison was done in three study areas both for accuracy of imperviousness coverage evaluation in individual points in time and accuracy of imperviousness change assessment. The performance of individual machine learning algorithms (Cubist, Random Forest, stochastic gradient boosting of regression trees, k-nearest neighbors regression, random k-nearest neighbors regression, Multivariate Adaptive Regression Splines, averaged neural networks, and support vector machines with polynomial and radial kernels) was also compared with the performance of heterogeneous model ensembles constructed from the best models trained using particular techniques. The results proved that in case of sub-pixel evaluation the most accurate prediction of change may not necessarily be based on the most accurate individual assessments. When single methods are considered, based on obtained results Cubist algorithm may be advised for Landsat based mapping of imperviousness for single dates. However, Random Forest may be endorsed when the most reliable evaluation of imperviousness change is the primary goal. It gave lower accuracies for individual assessments, but better prediction of change due to more correlated errors of individual predictions. Heterogeneous model ensembles performed for individual time points assessments at least as well as the best individual models. In case of imperviousness change assessment the ensembles always outperformed single model approaches. It means that it is possible to improve the accuracy of sub-pixel imperviousness change assessment using ensembles of heterogeneous non-linear regression models.

We evaluated the performance of nine machine learning regression algorithms and their ensembles for sub-pixel estimation of impervious areas coverages from Landsat imagery. The accuracy of imperviousness mapping in individual time points was assessed based on RMSE, MAE and R 2 . These measures were also used for the assessment of imperviousness change intensity estimations. The applicability for detection of relevant changes in impervious areas coverages at sub-pixel level was evaluated using overall accuracy, F-measure and ROC Area Under Curve. The results proved that Cubist algorithm may be advised for Landsat-based mapping of imperviousness for single dates. Stochastic gradient boosting of regression trees (GBM) may be also considered for this purpose. However, Random Forest algorithm is endorsed for both imperviousness change detection and mapping of its intensity. In all applications the heterogeneous model ensembles performed at least as well as the best individual models or better. They may be recommended for improving the quality of sub-pixel imperviousness and imperviousness change mapping. The study revealed also limitations of the investigated methodology for detection of subtle changes of imperviousness inside the pixel. None of the tested approaches was able to reliably classify changed and non-changed pixels if the relevant change threshold was set as one or three percent. Also for five percent change threshold most of algorithms did not ensure that the accuracy of change map is higher than the accuracy of random classifier. For the threshold of relevant change set as ten percent all approaches performed satisfactory.

This paper proposes a comprehensive study on machine listening for localisation of snore sound excitation. Here we investigate the effects of varied frame sizes, and overlap of the analysed audio chunk for extracting low-level descriptors. In addition, we explore the performance of each kind of feature when it is fed into varied classifier models, including support vector machines, k-nearest neighbours, linear discriminant analysis, random forests, extreme learning machines, kernel-based extreme learning machines, multilayer perceptrons, and deep neural networks. Experimental results demonstrate that, wavelet packet transform energy can outperform most other features. A deep neural network trained with subband energy ratios reaches the highest performance achieving an unweighted average recall of 72.8% from four types for snoring.