Search
Search results for: CO-TRAINING
-
MagMax: Leveraging Model Merging for Seamless Continual Learning
PublicationThis paper introduces a continual learning approach named MagMax, which utilizes model merging to enable large pre-trained models to continuously learn from new data without forgetting previously acquired knowledge. Distinct from traditional continual learning methods that aim to reduce forgetting during task training, MagMax combines sequential fine-tuning with a maximum magnitude weight selection for effective knowledge integration...
-
Engineering education for smart grid systems in the quasi-industrial environment of the LINTE^2 laboratory
PublicationSmart grid systems are revolutionising the electric power sector, integrating advanced technologies to enhance efficiency, reliability and sustainability. It is important for higher education to equip the prospective smart grid professional with the competencies enabling them to navigate through the related complexities and drive innovation. To achieve this, interdisciplinary education programmes are necessary, addressing inter...
-
Toward Robust Pedestrian Detection With Data Augmentation
PublicationIn this article, the problem of creating a safe pedestrian detection model that can operate in the real world is tackled. While recent advances have led to significantly improved detection accuracy on various benchmarks, existing deep learning models are vulnerable to invisible to the human eye changes in the input image which raises concerns about its safety. A popular and simple technique for improving robustness is using data...
-
Methodology for Performing Bathymetric Measurements of Shallow Waterbodies Using an UAV, and their Processing Based on the SVR Algorithm
PublicationState-of-art methods of bathymetric measurements for shallow waterbodies use Global Navigation Satellite System (GNSS) receiver, bathymetric Light Detection and Ranging (LiDAR) sensor or satellite imagery. Currently, photogrammetric methods with the application of Unmanned Aerial Vehicles (UAV) are gathering great importance. This publication aims to present step-by-step methodology for carrying out the bathymetric measurements...
-
Investigating Noise Interference on Speech Towards Applying the Lombard Effect Automatically
PublicationThe aim of this study is two-fold. First, we perform a series of experiments to examine the interference of different noises on speech processing. For that purpose, we concentrate on the Lombard effect, an involuntary tendency to raise speech level in the presence of background noise. Then, we apply this knowledge to detecting speech with the Lombard effect. This is for preparing a dataset for training a machine learning-based...
-
Performance and Energy Aware Training of a Deep Neural Network in a Multi-GPU Environment with Power Capping
PublicationIn this paper we demonstrate that it is possible to obtain considerable improvement of performance and energy aware metrics for training of deep neural networks using a modern parallel multi-GPU system, by enforcing selected, non-default power caps on the GPUs. We measure the power and energy consumption of the whole node using a professional, certified hardware power meter. For a high performance workstation with 8 GPUs, we were...
-
Enhanced uniform data sampling for constrained data‐driven modeling of antenna input characteristics
PublicationData-driven surrogates are the most popular replacement models utilized in many fields of engineering and science, including design of microwave and antenna structures. The primary practical issue is a curse of dimensionality which limits the number of independent parameters that can be accounted for in the modelling process. Recently, a performance-driven modelling technique has been proposed where the constrained domain of the...
-
Marketing office management with leadership competences application in a manufacturing and service company
PublicationThe article presents a description of comprehensive leadership competencies in a company, with the emphasis on managing the marketing department. The publication commences with the indication of the leadership in the light of this literature, explaining what leadership competencies are, how they are identified and what competencies we distinguish. It also explains the purpose of applying leadership...
-
How to Sort Them? A Network for LEGO Bricks Classification
PublicationLEGO bricks are highly popular due to the ability to build almost any type of creation. This is possible thanks to availability of multiple shapes and colors of the bricks. For the smooth build process the bricks need to properly sorted and arranged. In our work we aim at creating an automated LEGO bricks sorter. With over 3700 different LEGO parts bricks classification has to be done with deep neural networks. The question arises...
-
NLITED - New Level of Integrated Techniques for Daylighting Education: Preliminary Data on the Use of an E-learning Platform
PublicationProject NLITED – New Level of Integrated Techniques for Daylighting Education - is an educational project for students and professionals. The project's objective is to create and develop an online eLearning platform with 32 eModules dedicated to daylight knowledge. The project also offers e-learners two summer school training where the theory is put into practice. The platform was launched on January 31, 2022. The paper...
-
Reduced-cost surrogate modeling of input characteristics and design optimization of dual-band antennas using response features
PublicationIn this article, a procedure for low-cost surrogate modeling of input characteristics of dual-band antennas has been discussed. The number of training data required for construction of an accurate model has been reduced by representing the antenna reflection response to the level of suitably defined feature points. The points are allocated to capture the critical features of the reflection characteristic, such as the frequencies...
-
From Knowledge based Vision Systems to Cognitive Vision Systems: A Review
PublicationComputer vision research and applications have their origins in 1960s. Limitations in computational resources inherent of that time, among other reasons, caused research to move away from artificial intelligence and generic recognition goals to accomplish simple tasks for constrained scenarios. In the past decades, the development in machine learning techniques has contributed to noteworthy progress in vision systems. However,...
-
Performance‐driven modeling of compact couplers in restricted domains
PublicationFast surrogate models can play an important role in reducing the cost of EM-driven design closure of miniaturized microwave components. Unfortunately, construction of such models is challenging due to curse of dimensionality and wide range of geometry parameters that need to be included in order to make it practically useful. In this letter, a novel approach to design-oriented modeling of compact couplers is presented. Our method...
-
Design-Oriented Constrained Modeling of Antenna Structures
PublicationFast surrogate models are crucially important to reduce the cost of design process of antenna structures. Due to curse of dimensionality, standard (data-driven) modeling methods exhibit serious limitations concerning the number of independent geometry parameters that can be handled but also (and even more importantly) their parameter ranges. In this work, a design-oriented modeling framework is proposed in which the surrogate is...
-
Video Classification Technology in a Knowledge-Vision-Integration Platform for Personal Protective Equipment Detection: An Evaluation
PublicationThis work is part of an effort for the development of a Knowledge-Vision Integration Platform for Hazard Control (KVIP-HC) in industrial workplaces, adaptable to a wide range of industrial environments. This paper focuses on hazards resulted from the non-use of personal protective equipment (PPE), and examines a few supervised learning techniques to compose the proposed system for the purpose of recognition of three protective...
-
Pose classification in the gesture recognition using the linear optical sensor
PublicationGesture sensors for mobile devices, which have a capability of distinguishing hand poses, require efficient and accurate classifiers in order to recognize gestures based on the sequences of primitives. Two methods of poses recognition for the optical linear sensor were proposed and validated. The Gaussian distribution fitting and Artificial Neural Network based methods represent two kinds of classification approaches. Three types...
-
QUEUE I
EventsFaculty of Applied Physics and Mathematics of Gdańsk Tech invites international students to the next summer school - Quantum and Molecules I (QUEUE I), organized within the ScienceApp project.
-
Trust triggers and barriers in intercultural teams
PublicationIntercultural teams are more and more popular nowadays — they constitute a serious challenge in terms of effective cooperation and trust building, however. The article presents the potential problems that can affect intercultural cooperation and stresses the power of trust in cultural diversity conditions. The ten-factor model of intercultural team trust is presented. The main aim was to answer the questions: what are the differences...
-
The Review of the Selected Challenges for an Incorporation of Daylight Assessment Methods into Urban Planning in Poland
PublicationThe main objectives of this research it to find out if modern daylight assessment and design methods can be useful for urban residential planning in Poland. The study gives a chance to describe and appraise modern daylight design techniques. The other purpose is to illustrate how daylight knowledge could be used as an incentive to rethink the way urban environments are created. Although daylight design is acknowledged in literature...
-
On Reduced-Cost Design-Oriented Constrained Surrogate Modeling of Antenna Structures
PublicationDesign of contemporary antenna structures heavily relies on full-wave electromagnetic (EM) simulation models. Such models are essential to ensure reliability of evaluating antenna characteristics, yet, they are computationally expensive and therefore unsuitable for handling tasks that require multiple analyses, e.g., parametric optimization. The cost issue can be alleviated by using fast surrogate models. Conventional data-driven...
-
Real-time simulator of agricultural biogas plant
PublicationThis article presents a real-time simulator of an agricultural biogas plant. The project contains biogas and biomass circuits simulation, as well as heating circuit simulation with a complete control system and visualization interface of the whole process. The software tool used to simulate the plant work is CFD (Computational Fluid Dynamics), which enables a user to create and test simulation objects based on fundamental physical...
-
Reduced-Cost Constrained Modeling of Microwave and Antenna Components: Recent Advances
PublicationElectromagnetic (EM) simulation models are ubiquitous in the design of microwave and antenna components. EM analysis is reliable but CPU intensive. In particular, multiple simulations entailed by parametric optimization or uncertainty quantification may considerably slow down the design processes. In order to address this problem, it is possible to employ fast metamodels. Here, the popular solution approaches are approximation...
-
The impact of the AC922 Architecture on Performance of Deep Neural Network Training
PublicationPractical deep learning applications require more and more computing power. New computing architectures emerge, specifically designed for the artificial intelligence applications, including the IBM Power System AC922. In this paper we confront an AC922 (8335-GTG) server equipped with 4 NVIDIA Volta V100 GPUs with selected deep neural network training applications, including four convolutional and one recurrent model. We report...
-
Musical Instrument Tagging Using Data Augmentation and Effective Noisy Data Processing
PublicationDeveloping signal processing methods to extract information automatically has potential in several applications, for example searching for multimedia based on its audio content, making context-aware mobile applications (e.g., tuning apps), or pre-processing for an automatic mixing system. However, the last-mentioned application needs a significant amount of research to reliably recognize real musical instruments in recordings....
-
Microencapsulation of fish oil – determination of optimal wall material and encapsulation methodology
PublicationFor the first time, we present a meta-analysis of experimental and literature data to determine which microencapsulation methodology, and which wall material are best suited to protect fish oil. Our analysis covered a period of several decades of research (1984–2018). The analysis was conducted on 196 literature data-points, and 16 data-points determined experimentally for this publication. PLS regression was used to determine...
-
Performance-Driven Inverse/Forward Modeling of Antennas in Variable-Thickness Domains
PublicationDesign of contemporary antenna systems is a challenging endeavor. The difficulties are partially rooted in stringent specifications imposed on both electrical and field characteristics, demands concerning various functionalities, but also constraints imposed upon the physical size of the radiators. Furthermore, conducting the design process at the level of full-wave electromagnetic (EM) simulations, otherwise dictated by reliability,...
-
Neural Network-Based Sequential Global Sensitivity Analysis Algorithm
PublicationPerforming global sensitivity analysis (GSA) can be challenging due to the combined effect of the high computational cost, but it is also essential for engineering decision making. To reduce this cost, surrogate modeling such as neural networks (NNs) are used to replace the expensive simulation model in the GSA process, which introduces the additional challenge of finding the minimum number of training data samples required to...
-
Predictions of cervical cancer identification by photonic method combined with machine learning
PublicationCervical cancer is one of the most commonly appearing cancers, which early diagnosis is of greatest importance. Unfortunately, many diagnoses are based on subjective opinions of doctors—to date, there is no general measurement method with a calibrated standard. The problem can be solved with the measurement system being a fusion of an optoelectronic sensor and machine learning algorithm to provide reliable assistance for doctors...
-
Labeler-hot Detection of EEG Epileptic Transients
PublicationPreventing early progression of epilepsy and sothe severity of seizures requires effective diagnosis. Epileptictransients indicate the ability to develop seizures but humansoverlook such brief events in an electroencephalogram (EEG)what compromises patient treatment. Traditionally, trainingof the EEG event detection algorithms has relied on groundtruth labels, obtained from the consensus...
-
Accurate simulation-driven modeling and design optimization of compact microwave structures
PublicationCost efficient design optimization of microwave structures requires availability of fast yet reliable replacement models so that multiple evaluations of the structure at hand can be executed in reasonable timeframe. Direct utilization of full-wave electromagnetic (EM) simulations is often prohibitive. On the other hand, accurate data-driven modeling normally requires a very large number of training points and it is virtually infeasible...
-
A COMPREHENSIVE REVIEW OF LIFE CYCLE ASSESSMENT AND ENERGY EFFICIENCY IN 3D PRINTING FOR CONSTRUCTION: CURRENT STATE, BENEFITS, LIMITATIONS, AND FUTURE OUTLOOK
PublicationThe agenda of Industry 4.0 strongly affects design and construction at all its phases, and three-Dimensional Printing (3DP) is an essential part of it. The emerging technology has the potential to become a more valid and accepted form of construction. This research is based on a literature review regarding the relationships between the concepts of Life Cycle Assessment (LCA) and energy efficiency for 3DP in construction research...
-
Autoencoder application for anomaly detection in power consumption of lighting systems
PublicationDetecting energy consumption anomalies is a popular topic of industrial research, but there is a noticeable lack of research reported in the literature on energy consumption anomalies for road lighting systems. However, there is a need for such research because the lighting system, a key element of the Smart City concept, creates new monitoring opportunities and challenges. This paper examines algorithms based on the deep learning...
-
Deep Instance Segmentation of Laboratory Animals in Thermal Images
PublicationIn this paper we focus on the role of deep instance segmentation of laboratory rodents in thermal images. Thermal imaging is very suitable to observe the behaviour of laboratory animals, especially in low light conditions. It is an non-intrusive method allowing to monitor the activity of animals and potentially observe some physiological changes expressed in dynamic thermal patterns. The analysis of the recorded sequence of thermal...
-
Fault detection in the marine engine using a support vector data description method
PublicationFast detection and correct diagnosis of any engine condition changes are essential elements of safety andenvironmental protection. Many diagnostic algorithms significantly improve the detection of malfunctions.Studies on diagnostic methods are rarely reported and even less implemented in the marine engine industry.To fill this gap, this paper presents the Support Vector Data Description (SVDD) method as applied to thefault detection...
-
Developing students' spatial skills and teaching the history of architecture through structural drawing
PublicationThe method of “structural drawing" is used in teaching history of architecture in the Architectural Faculty of Gdańsk University of Technology. It is addressed to students of the first semester of study – so to the architectural beginners. There are three main goals of the structural drawing method used in that educational course: (1) developing the students’ spatial skills; (2) training architectural drawing ability; (3) teaching...
-
The Influence of Selecting Regions from Endoscopic Video Frames on The Efficiency of Large Bowel Disease Recognition Algorithms
PublicationThe article presents our research in the field of the automatic diagnosis of large intestine diseases on endoscopic video. It focuses on the methods of selecting regions of interest from endoscopic video frames for further analysis by specialized disease recognition algorithms. Four methods of selecting regions of interest have been discussed: a. trivial, b. with the deletion of characteristic, endoscope specific additions to the...
-
A Comprehensive Analysis of Deep Neural-Based Cerebral Microbleeds Detection System
PublicationMachine learning-based systems are gaining interest in the field of medicine, mostly in medical imaging and diagnosis. In this paper, we address the problem of automatic cerebral microbleeds (CMB) detection in magnetic resonance images. It is challenging due to difficulty in distinguishing a true CMB from its mimics, however, if successfully solved it would streamline the radiologists work. To deal with this complex three-dimensional...
-
Inclusive Communication Model Supporting the Employment Cycle of Individuals with Autism Spectrum Disorders
PublicationDifficulties with interpersonal communication experienced by individuals with autism spectrum disorders (ASD) significantly contribute to their underrepresentation in the workforce as well as problems experienced while in employment. Consistently, it is vital to understand how communication within the employment cycle of this group can be improved. This study aims to identify and analyze the possibilities of modifying the communication...
-
Triangulation-based Constrained Surrogate Modeling of Antennas
PublicationDesign of contemporary antenna structures is heavily based on full-wave electromagnetic (EM) simulation tools. They provide accuracy but are CPU-intensive. Reduction of EM-driven design procedure cost can be achieved by using fast replacement models (surrogates). Unfortunately, standard modeling techniques are unable to ensure sufficient predictive power for real-world antenna structures (multiple parameters, wide parameter ranges,...
-
Speaker Recognition Using Convolutional Neural Network with Minimal Training Data for Smart Home Solutions
PublicationWith the technology advancements in smart home sector, voice control and automation are key components that can make a real difference in people's lives. The voice recognition technology market continues to involve rapidly as almost all smart home devices are providing speaker recognition capability today. However, most of them provide cloud-based solutions or use very deep Neural Networks for speaker recognition task, which are...
-
Multi-fidelity EM simulations and constrained surrogate modelling for low-cost multi-objective design optimisation of antennas
PublicationIn this study, a technique for low-cost multi-objective design optimisation of antenna structures has been proposed. The proposed approach is an enhancement of a recently reported surrogate-assisted technique exploiting variable-fidelity electromagnetic (EM) simulations and auxiliary kriging interpolation surrogate, the latter utilised to produce the initial approximation of the Pareto set. A bottleneck of the procedure for higher-dimensional...
-
Normalization of face illumination using basic knowledge and information extracted from a single image
PublicationThis paper presents a method for face image normalization that can be applied to the extraction of illumination invariant facial features or used to remove bad lighting effects and produce high-quality, photorealistic results. Most of the existing approaches concentrate on separating the constant albedo from the variable light intensity; that concept, however, is based on the Lambertian model, which fails in the presence of specularities...
-
BP-EVD: Forward Block-Output Propagation for Efficient Video Denoising
PublicationDenoising videos in real-time is critical in many applications, including robotics and medicine, where varying light conditions, miniaturized sensors, and optics can substantially compromise image quality. This work proposes the first video denoising method based on a deep neural network that achieves state-of-the-art performance on dynamic scenes while running in real-time on VGA video resolution with no frame latency. The backbone...
-
Selection of effective cocrystals former for dissolution rate improvement of active pharmaceutical ingredients based on lipoaffinity index
PublicationNew theoretical screening procedure was proposed for appropriate selection of potential cocrystal formers possessing the ability of enhancing dissolution rates of drugs. The procedure relies on the training set comprising 102 positive and 17 negative cases of cocrystals found in the literature. Despite the fact that the only available data were of qualitative character, performed statistical analysis using binary classification...
-
Distinguishing of cocrystals from simple eutectic mixtures: phenolic acids as potential pharmaceutical coformers
PublicationThe multiparameter model comprising 1D and 2D QSPR/QSAR descriptors was proposed and validated for phenolic acid binary systems. This approach is based on the optimization of regression coefficients for maximization of the percentage of true positives in the pool of systems comprising either simple binary eutectics or cocrystals. The training set consisted of 58 eutectics and 168 cocrystals. The solid dispersions collection used...
-
Exploring the influence of personal factors on physiological responses to mental imagery in sport
PublicationImagery is a well-known technique in mental training which improves performance efficiency and influences physiological arousal. One of the biomarkers indicating the amount of physiological arousal is skin conductance level (SCL). The aim of our study is to understand how individual differences in personality (e.g. neuroticism), general imagery and situational sport anxiety are linked to arousal measuring with SCL in situational...
-
Security of Cryptocurrencies: A View on the State-of-the-Art Research and Current Developments
Publication[Context] The goal of security is to protect digital assets, devices, and services from being disrupted, exploited or stolen by unauthorized users. It is also about having reliable information available at the right time. [Motivation] Since the inception in 2009 of the first cryptocurrency, few studies have been undertaken to analyze and review the state-of-the-art research and current developments with respect to the security...
-
Automated hearing loss type classification based on pure tone audiometry data
PublicationHearing problems are commonly diagnosed with the use of tonal audiometry, which measures a patient’s hearing threshold in both air and bone conduction at various frequencies. Results of audiometry tests, usually represented graphically in the form of an audiogram, need to be interpreted by a professional audiologist in order to determine the exact type of hearing loss and administer proper treatment. However, the small number of...
-
Improving the prediction of biochar production from various biomass sources through the implementation of eXplainable machine learning approaches
PublicationExamining the game-changing possibilities of explainable machine learning techniques, this study explores the fast-growing area of biochar production prediction. The paper demonstrates how recent advances in sensitivity analysis methodology, optimization of training hyperparameters, and state-of-the-art ensemble techniques have greatly simplified and enhanced the forecasting of biochar output and composition from various biomass...
-
Design-oriented computationally-efficient feature-based surrogate modelling of multi-band antennas with nested kriging
PublicationDesign of modern antenna structures heavily depends on electromagnetic (EM) simulation tools. EM analysis provides reliable evaluation of increasingly complex designs but tends to be CPU intensive. When multiple simulations are needed (e.g., for parameters tuning), the aggregated simulation cost may become a serious bottleneck. As one possible way of mitigating the issue, the recent literature fosters utilization of faster representations,...