Search results for: MANAGEMENT TRAINING
-
A review of emotion recognition methods based on keystroke dynamics and mouse movements
PublicationThe paper describes the approach based on using standard input devices, such as keyboard and mouse, as sources of data for the recognition of users’ emotional states. A number of systems applying this idea have been presented focusing on three categories of research problems, i.e. collecting and labeling training data, extracting features and training classifiers of emotions. Moreover the advantages and examples of combining standard...
-
Deep Learning Optimization for Edge Devices: Analysis of Training Quantization Parameters
PublicationThis paper focuses on convolution neural network quantization problem. The quantization has a distinct stage of data conversion from floating-point into integer-point numbers. In general, the process of quantization is associated with the reduction of the matrix dimension via limited precision of the numbers. However, the training and inference stages of deep learning neural network are limited by the space of the memory and a...
-
Recognizing emotions on the basis of keystroke dynamics
PublicationThe article describes a research on recognizing emotional states on the basis of keystroke dynamics. An overview of various studies and applications of emotion recognition based on data coming from keyboard is presented. Then, the idea of an experiment is presented, i.e. the way of collecting and labeling training data, extracting features and finally training classifiers. Different classification approaches are proposed to be...
-
Musical Instrument Identification Using Deep Learning Approach
PublicationThe work aims to propose a novel approach for automatically identifying all instruments present in an audio excerpt using sets of individual convolutional neural networks (CNNs) per tested instrument. The paper starts with a review of tasks related to musical instrument identification. It focuses on tasks performed, input type, algorithms employed, and metrics used. The paper starts with the background presentation, i.e., metadata...
-
Color-based Detection of Bleeding in Endoscopic Images
PublicationIn this paper a color descriptor designed for bleeding detection in endoscopic images is proposed. The development of the algorithm was carried out on a representative training set of 36 images of bleeding and 25 clear images. Another 38 bleeding and 26 normal images were used in the final stage as a test set. All of the considered images were extracted from separate endoscopic examinations. The experiments include color distribution...
-
Tomasz Janowski dr
PeopleTomasz Janowski is the Head of the Department of Informatics in Management, Gdańsk University of Technology, Poland; Invited Professor at the Department for E-Governance and Administration, University for Continuing Education Krems, Austria; and Co-Editor-in-Chief of Government Information Quarterly, Elsevier. Previously, he was the founder and head of the United Nations University Operating Unit on Policy-Driven Electronic Governance...
-
Towards Scalable Simulation of Federated Learning
PublicationFederated learning (FL) allows to train models on decentralized data while maintaining data privacy, which unlocks the availability of large and diverse datasets for many practical applications. The ongoing development of aggregation algorithms, distribution architectures and software implementations aims for enabling federated setups employing thousands of distributed devices, selected from millions. Since the availability of...
-
The impact of training and neurotrophins on functional recovery after spinal cord transection: cellular and molecular mechanisms contributing to motor improvement
PublicationBeneficial effects of locomotor training on the functional recovery after complete transection of the spinal cord indicate that in chronic spinal animals spontaneous recovery processes are enhanced and shaped by the training. The mechanisms of that use-dependent improvement are still not fully understood. This review tackles three aspects of this issue: (1) neurochemical attributes of functional improvement...
-
Bees Detection on Images: Study of Different Color Models for Neural Networks
PublicationThis paper presents an approach to bee detection in video streams using a neural network classifier. We describe the motivation for our research and the methodology of data acquisition. The main contribution to this work is a comparison of different color models used as an input format for a feedforward convolutional architecture applied to bee detection. The detection process has is based on a neural binary classifier that classifies...
-
Train the trainer course
PublicationThis chapter presents the concept, evaluation and evaluation results for the train the trainer. This concept of train the trainers is prepared within Workpackage 5 of EU-funded project: MASTER BSR (Erasmus+ Strategic Partnership Programme). Due to the nature of adult learning the content is designed for the use of participatory methods (involved, active). This method uses various techniques of active learning e.g. group work,...
-
Sławomir Ostrowski dr inż.
PeopleSławomir Ostrowski is a research and didactic employee employed as an Assistant Professor in the Department of Informatics in Management at the Faculty of Management and Economics of the Gdańsk University of Technology. In 2018, he obtained a PhD in economic sciences in the discipline of management science. A graduate of uniform Master's-engineering studies in Management (specialization: IT Technology Management) at the Faculty...
-
Creating new voices using normalizing flows
PublicationCreating realistic and natural-sounding synthetic speech remains a big challenge for voice identities unseen during training. As there is growing interest in synthesizing voices of new speakers, here we investigate the ability of normalizing flows in text-to-speech (TTS) and voice conversion (VC) modes to extrapolate from speakers observed during training to create unseen speaker identities. Firstly, we create an approach for TTS...
-
Development and test of fex, a fingers extending exoskeleton for rehabilitation and regaining mobility
PublicationThis paper presents the design process of an exoskeleton for executing human fingers' extension movement for the rehabilitation procedures and as an active orthosis purposes, together with its first clinical usability tests of a robotic exoskeleton. Furthermore, the Fingers Extending eXoskeleton (FEX) is a serial, under-actuated mechanism capable of executing fingers' extension. FEX is based on the state-of-art FingerSpine serial...
-
Immersive Technologies that Aid Additive Manufacturing Processes in CBRN Defence Industry
PublicationTesting unique devices or their counterparts for CBRN (C-chemical, B-biological, R-radiological, N-nuclear) defense relies on additive manufacturing processes. Immersive technologies aid additive manufacturing. Their use not only helps understand the manufacturing processes, but also improves the design and quality of the products. This article aims to propose an approach to testing CBRN reconnaissance hand-held products developed...
-
Automated detection of pronunciation errors in non-native English speech employing deep learning
PublicationDespite significant advances in recent years, the existing Computer-Assisted Pronunciation Training (CAPT) methods detect pronunciation errors with a relatively low accuracy (precision of 60% at 40%-80% recall). This Ph.D. work proposes novel deep learning methods for detecting pronunciation errors in non-native (L2) English speech, outperforming the state-of-the-art method in AUC metric (Area under the Curve) by 41%, i.e., from...
-
Neural network training with limited precision and asymmetric exponent
PublicationAlong with an extremely increasing number of mobile devices, sensors and other smart utilities, an unprecedented growth of data can be observed in today’s world. In order to address multiple challenges facing the big data domain, machine learning techniques are often leveraged for data analysis, filtering and classification. Wide usage of artificial intelligence with large amounts of data creates growing demand not only for storage...
-
Towards bees detection on images: study of different color models for neural networks
PublicationThis paper presents an approach to bee detection in videostreams using a neural network classifier. We describe the motivationfor our research and the methodology of data acquisition. The maincontribution to this work is a comparison of different color models usedas an input format for a feedforward convolutional architecture appliedto bee detection. The detection process has is based on a neural...
-
PROJEKTOWANIE STANOWISK LABORATORYJNYCH WSPIERAJĄCYCH PROCES SZKOLENIA PRAKTYCZNEGO KADR MORSKICH DZIAŁU MASZYNOWEGO W ŻEGLUDZE MIĘDZYNARODOWEJ, PRZYBRZEŻNEJ I KRAJOWEJ
PublicationWithin the article a design offer of the Department of Ship and Power Plants of the Faculty of Ocean Engineering And Ship Technology at the Gdansk University of Technology has been presented. The offer concerns designing laboratory stations which might stand for the equipment of a didactic base of maritime educational centers i.e. maritime (naval) academies and schools as well as maritime affairs' professional training centers,...
-
Agata Pierścieniak dr hab. inż.
PeopleAgata Pierscieniak is a graduate of the Wrocław University of Technology, Faculty of Computer Science and Management (1992). She obtained her Ph.D. degree in the field of Economic Sciences in 2004 from the Warsaw University of Life Sciences, while her post-doc (habilitated doctor) degree in the discipline of Management Sciences, in 2016, was from the Warsaw School of Economics.During the years 1998-2018, she worked at the University...
-
Training of Deep Learning Models Using Synthetic Datasets
PublicationIn order to solve increasingly complex problems, the complexity of Deep Neural Networks also needs to be constantly increased, and therefore training such networks requires more and more data. Unfortunately, obtaining such massive real world training data to optimize neural networks parameters is a challenging and time-consuming task. To solve this problem, we propose an easy-touse and general approach to training deep learning...
-
Assessment of Therapeutic Progress After Acquired Brain Injury Employing Electroencephalography and Autoencoder Neural Networks
PublicationA method developed for parametrization of EEG signals gathered from participants with acquired brain injuries is shown. Signals were recorded during therapeutic session consisting of a series of computer assisted exercises. Data acquisition was performed in a neurorehabilitation center located in Poland. The presented method may be used for comparing the performance of subjects with acquired brain injuries (ABI) who are involved...
-
Detection of Lexical Stress Errors in Non-Native (L2) English with Data Augmentation and Attention
PublicationThis paper describes two novel complementary techniques that improve the detection of lexical stress errors in non-native (L2) English speech: attention-based feature extraction and data augmentation based on Neural Text-To-Speech (TTS). In a classical approach, audio features are usually extracted from fixed regions of speech such as the syllable nucleus. We propose an attention-based deep learning model that automatically de...
-
INFLUENCE OF DATA NORMALIZATION ON THE EFFECTIVENESS OF NEURAL NETWORKS APPLIED TO CLASSIFICATION OF PAVEMENT CONDITIONS – CASE STUDY
PublicationIn recent years automatic classification employing machine learning seems to be in high demand for tele-informatic-based solutions. An example of such solutions are intelligent transportation systems (ITS), in which various factors are taken into account. The subject of the study presented is the impact of data pre-processing and normalization on the accuracy and training effectiveness of artificial neural networks in the case...
-
Monika Gwóźdź - Lasoń dr
PeoplePhD Eng. Monika Gwóźdź-Lasoń, REV Diplomas and scientific degrees 28/11/2007 Acquiring the PhD in technical sciences [630000] [630900]; doctoral dissertation entitled Modele Obliczeniowe Podłoża Gruntowego w Aspekcie Różnych Metod i Technologii Wzmocnienia = Numerical models of the subsoil reinforced by different kind of methods and technology. 1995-2000 Obtaining the degree: Master of Science; Faculty of Civil Engineering,...
-
Federated Learning in Healthcare Industry: Mammography Case Study
PublicationThe paper focuses on the role of federated learning in a healthcare environment. The experimental setup involved different healthcare providers, each with their datasets. A comparison was made between training a deep learning model using traditional methods, where all the data is stored in one place, and using federated learning, where the data is distributed among the workers. The experiment aimed to identify possible challenges...
-
Cross-Lingual Knowledge Distillation via Flow-Based Voice Conversion for Robust Polyglot Text-to-Speech
PublicationIn this work, we introduce a framework for cross-lingual speech synthesis, which involves an upstream Voice Conversion (VC) model and a downstream Text-To-Speech (TTS) model. The proposed framework consists of 4 stages. In the first two stages, we use a VC model to convert utterances in the target locale to the voice of the target speaker. In the third stage, the converted data is combined with the linguistic features and durations...
-
Adapt Your Teacher: Improving Knowledge Distillation for Exemplar-free Continual Learning
PublicationIn this work, we investigate exemplar-free class incremental learning (CIL) with knowledge distillation (KD) as a regularization strategy, aiming to prevent forgetting. KDbased methods are successfully used in CIL, but they often struggle to regularize the model without access to exemplars of the training data from previous tasks. Our analysis reveals that this issue originates from substantial representation shifts in the teacher...
-
Data Acquisition and Processing for GeoAI Models to Support Sustainable Agricultural Practices
PublicationThere are growing opportunities to leverage new technologies and data sources to address global problems related to sustainability, climate change, and biodiversity loss. The emerging discipline of GeoAI resulting from the convergence of AI and Geospatial science (Geo-AI) is enabling the possibility to harness the increasingly available open Earth Observation data collected from different constellations of satellites and sensors...
-
MP3vec: A Reusable Machine-Constructed Feature Representation for Protein Sequences
Publication—Machine Learning (ML) methods have been used with varying degrees of success on protein prediction tasks, with two inherent limitations. First, prediction performance often depends upon the features extracted from the proteins. Second, experimental data may be insufficient to construct reliable ML models. Here we introduce MP3vec, a transferable representation for protein sequences that is designed to be used specifically for sequence-to-sequence...
-
Automated Classifier Development Process for Recognizing Book Pages from Video Frames
PublicationOne of the latest developments made by publishing companies is introducing mixed and augmented reality to their printed media (e.g. to produce augmented books). An important computer vision problem that they are facing is classification of book pages from video frames. The problem is non-trivial, especially considering that typical training data is limited to only one digital original per book page, while the trained classifier...
-
Improving css-KNN Classification Performance by Shifts in Training Data
PublicationThis paper presents a new approach to improve the performance of a css-k-NN classifier for categorization of text documents. The css-k-NN classifier (i.e., a threshold-based variation of a standard k-NN classifier we proposed in [1]) is a lazy-learning instance-based classifier. It does not have parameters associated with features and/or classes of objects, that would be optimized during off-line learning. In this paper we propose...
-
Multiobjective Aerodynamic Optimization by Variable-Fidelity Models and Response Surface Surrogates
PublicationA computationally efficient procedure for multiobjective design optimization with variable-fidelity models and response surface surrogates is presented. The proposed approach uses the multiobjective evolutionary algorithm that works with a fast surrogate model, obtained with kriging interpolation of the low-fidelity model data enhanced by space-mapping correction exploiting a few high-fidelity training points. The initial Pareto...
-
Playback detection using machine learning with spectrogram features approach
PublicationThis paper presents 2D image processing approach to playback detection in automatic speaker verification (ASV) systems using spectrograms as speech signal representation. Three feature extraction and classification methods: histograms of oriented gradients (HOG) with support vector machines (SVM), HAAR wavelets with AdaBoost classifier and deep convolutional neural networks (CNN) were compared on different data partitions in respect...
-
Computer-assisted pronunciation training—Speech synthesis is almost all you need
PublicationThe research community has long studied computer-assisted pronunciation training (CAPT) methods in non-native speech. Researchers focused on studying various model architectures, such as Bayesian networks and deep learning methods, as well as on the analysis of different representations of the speech signal. Despite significant progress in recent years, existing CAPT methods are not able to detect pronunciation errors with high...
-
Video of LEGO Bricks on Conveyor Belt Dataset Series
PublicationThe dataset series titled Video of LEGO bricks on conveyor belt is composed of 14 datasets containing video recordings of a moving white conveyor belt. The recordings were created using a smartphone camera in Full HD resolution. The dataset allows for the preparation of data for neural network training, and building of a LEGO sorting machine that can help builders to organise their collections.
-
CIP Security Awareness and Training: Standards and Practice
PublicationThese are critical infrastructure employees who have access to the critical cyber assets in the first place. This situation is well recognized by international and national standardization bodies which recommend security education, training and awareness as one of the key elements of critical infrastructure protection. In this chapter the standards are identified and their relevant areas are described. A practical implementation...
-
CIP Security Awareness and Training: Standards and Practice
PublicationThese are critical infrastructure employees who have access to the critical cyber assets in the first place. This situation is well recognised by international and national standardisation bodies which recommend security education, training and awareness as one of the key elements of critical infrastructure protection. In this chapter the standards are identified and their relevant areas are described. A practical implementation...
-
COLLABORATIVE LEARNING ENVIRONMENT FOR ENGINEERING EDUCATION (COLED)
PublicationCollaborative Learning Environment for Engineering Education is a European project implemented under the Erasmus + program, The main goal of 5 partners from 4 different European countries – Bulgaria, Poland, Portugal and Romania is to develop an innovative collaborative training approach, encompassing curricula related to the introduction of enterprise automation. Project activities are carried out in the period from Dctober 2018...
-
Continuous learning as a method of raising qualifications – the perspective of workers, employers and training organizations
PublicationContinuous learning is discussed in strategic documents of Poland and the European Union. In Poland, the idea of continuous learning is not very popular. However, in the context of strong competition in the labour market and the progressive globalization processes, the skills issue takes on new meaning — both for employees and employers. In order to adapt skills to labour market needs it is necessary to conduct adequate studies...
-
Neural Approximators for Variable-Order Fractional Calculus Operators (VO-FC)
PublicationThe paper presents research on the approximation of variable-order fractional operators by recurrent neural networks. The research focuses on two basic variable-order fractional operators, i.e., integrator and differentiator. The study includes variations of the order of each fractional operator. The recurrent neural network architecture based on GRU (Gated Recurrent Unit) cells functioned as a neural approximation for selected...
-
Diagnosing wind turbine condition employing a neural network to the analysis of vibroacoustic signals
PublicationIt is important from the economic point of view to detect damage early in the wind turbines before failures occur. For this purpose, a monitoring device was built that analyzes both acoustic signals acquired from the built-in non-contact acoustic intensity probe, as well as from the accelerometers, mounted on the internal devices in the nacelle. The signals collected in this way are used for long-term training of the autoencoder...
-
Self-Supervised Learning to Increase the Performance of Skin Lesion Classification
PublicationTo successfully train a deep neural network, a large amount of human-labeled data is required. Unfortunately, in many areas, collecting and labeling data is a difficult and tedious task. Several ways have been developed to mitigate the problem associated with the shortage of data, the most common of which is transfer learning. However, in many cases, the use of transfer learning as the only remedy is insufficient. In this study,...
-
Semantic segmentation training using imperfect annotations and loss masking
PublicationOne of the most significant factors affecting supervised neural network training is the precision of the annotations. Also, in a case of expert group, the problem of inconsistent data annotations is an integral part of real-world supervised learning processes, well-known to researchers. One practical example is a weak ground truth delineation for medical image segmentation. In this paper, we have developed a new method of accurate...
-
Podejście środowiskowe w dydaktyce projektowania Sustainable approach in teaching of design
PublicationThe aim of the paper is to assess the inclusion of academic teaching design to the process of sustainable development and proposals for an integrated approach in training architects. The article presents an original interpretation of environmental design in the field of architecture and urban planning. The significance of the environmental perspective is presented in the context of growing spatial and social fragmentation. The...
-
Usefulness of Keystroke Dynamics Features in User Authentication and Emotion Recognition
PublicationThe study presented in the article focuses on keystroke dynamics analysis applied to recognize emotional states and to authenticate users. An overview of some studies and applications in these areas is presented. Then, an experiment is described, i.e. the way of collecting data, extracting features, training classifiers and finding out the most appropriate feature subsets. The results show that it is difficult to indicate a universal...
-
FEEDB: A multimodal database of facial expressions and emotions
PublicationIn this paper a first version of a multimodal FEEDB database of facial expressions and emotions is presented. The database contains labeled RGB-D recordings of people expressing a specific set of expressions that have been recorded using Microsoft Kinect sensor. Such a database can be used for classifier training and testing in face recognition as well as in recognition of facial expressions and human emotions. Also initial experiences...
-
Emotion Recognition and Its Applications
PublicationThe paper proposes a set of research scenarios to be applied in four domains: software engineering, website customization, education and gaming. The goal of applying the scenarios is to assess the possibility of using emotion recognition methods in these areas. It also points out the problems of defining sets of emotions to be recognized in different applications, representing the defined emotional states, gathering the data and...
-
Recognition of Emotions in Speech Using Convolutional Neural Networks on Different Datasets
PublicationArtificial Neural Network (ANN) models, specifically Convolutional Neural Networks (CNN), were applied to extract emotions based on spectrograms and mel-spectrograms. This study uses spectrograms and mel-spectrograms to investigate which feature extraction method better represents emotions and how big the differences in efficiency are in this context. The conducted studies demonstrated that mel-spectrograms are a better-suited...
-
Accurate Modeling of Antenna Structures by Means of Domain Confinement and Pyramidal Deep Neural Networks
PublicationThe importance of surrogate modeling techniques has been gradually increasing in the design of antenna structures over the recent years. Perhaps the most important reason is a high cost of full-wave electromagnetic (EM) analysis of antenna systems. Although imperative in ensuring evaluation reliability, it entails considerable computational expenses. These are especially pronounced when carrying out EM-driven design tasks such...
-
Functional safety and managing competence
PublicationSą nowe wyzwania związane z badaniami, edukacją i szkoleniem w obszarach bezpieczeństwa i ochrony systemów i sieci krytycznych. W rozdziale podkreśla się, że kompetencje specjalistów powinny być kształtowane w zintegrowanych procesach edukacji i szkolenia. Dlatego uzasadnione jest, aby opracować w Europie standardy i programy kształcenia na bazie odpowiednich prac badawczych i najlepszych doświadczeń z praktyki przemysłowej w celu...