Filters
total: 258
filtered: 233
Search results for: DEBLURRING, DENOISING, MULTI-TASK LEARNING, VIDEO ENHANCEMENT
-
When Neural Networks Meet Decisional DNA: A Promising New Perspective for Knowledge Representation and Sharing
PublicationABSTRACT In this article, we introduce a novel concept combining neural network technology and Decisional DNA for knowledge representation and sharing. Instead of using traditional machine learning and knowledge discovery methods, this approach explores the way of knowledge extraction through deep learning processes based on a domain’s past decisional events captured by Decisional DNA. We compare our approach with kNN (k-nearest...
-
Multi-criterion, evolutionary and quantum decision making in complex systems
PublicationMulti-criterion, evolutionary and quantum decision making supported by the Adaptive Quantum-based Multi-criterion Evolutionary Algorithm (AQMEA) has been considered for distributed complex systems. AQMEA had been developed to the task assignment problem, and then it has been applied to underwater vehicle planning as another benchmark three-criterion optimization problem. For evaluation of a vehicle trajectory three criteria have...
-
Eulerian motion magnification applied to structural health monitoring of wind turbines
PublicationSeveral types of defects may occur in wind turbines, as physical damage of blades or gearbox malfunction. A wind farm monitoring and damage prediction system is built to observe abnormal vibrations of elements of wind turbine: blades, nacelle, and tower. Contactless methods are developed which do not require turbine stopping. In this work, structural health monitoring of a wind turbine is evaluated using a conversion from the captured...
-
Przegląd metod szybkiego prototypowania algorytmów uczenia maszynowego w FPGA
PublicationW artykule opisano możliwe do wykorzystania otwarte narzędzia wspomagające szybkie prototypowanie algorytmów uczenia maszynowego (ML) i sztucznej inteligencji (AI) przy użyciu współczesnych platform FPGA. Przedstawiono przykład szybkiej ścieżki przy realizacji toru wideo wraz z implementacją przykładowego algorytmu prze-twarzania w trybie na żywo.
-
Compact broadband multi-way 1:6 power divider
PublicationThis paper introduces a design flow of a microstrip multi-way 1:6 power divider incorporating photonic bandgap (PBG) structures. Themethod proposed has enabled the achievement of considerable miniaturization (15%) together with transmission characteristics enhancement(141% bandwidth). Measured results show significant similarity to theoretical characteristics, which proves the attractiveness of presented design methodology.
-
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,...
-
English Language Learning Employing Developments in Multimedia IS
PublicationIn the realm of the development of information systems related to education, integrating multimedia technologies offers novel ways to enhance foreign language learning. This study investigates audio-video processing methods that leverage real-time speech rate adjustment and dynamic captioning to support English language acquisition. Through a mixed-methods analysis involving participants from a language school, we explore the impact...
-
The Innovative Faculty for Innovative Technologies
PublicationA leaflet describing Faculty of Electronics, Telecommunications and Informatics, Gdańsk University of Technology. Multimedia Systems Department described laboratories and prototypes of: Auditory-visual attention stimulator, Automatic video event detection, Object re-identification application for multi-camera surveillance systems, Object Tracking and Automatic Master-Slave PTZ Camera Positioning System, Passive Acoustic Radar,...
-
Emotion recognition and its application in software engineering
PublicationIn this paper a novel application of multimodal emotion recognition algorithms in software engineering is described. Several application scenarios are proposed concerning program usability testing and software process improvement. Also a set of emotional states relevant in that application area is identified. The multimodal emotion recognition method that integrates video and depth channels, physiological signals and input devices...
-
Camera Orientation-Independent Parking Events Detection
PublicationThe paper describes the method for detecting precise position and time of vehicles parking in a parking lot. This task is trivial in case of favorable camera orientation but gets much more complex when an angle between the camera viewing axis and the ground is small. The method utilizes background subtraction and object tracking algorithms for detecting moving objects in a video stream. Objects are classified into vehicles and...
-
Acquisition and indexing of RGB-D recordings for facial expressions and emotion recognition
PublicationIn this paper KinectRecorder comprehensive tool is described which provides for convenient and fast acquisition, indexing and storing of RGB-D video streams from Microsoft Kinect sensor. The application is especially useful as a supporting tool for creation of fully indexed databases of facial expressions and emotions that can be further used for learning and testing of emotion recognition algorithms for affect-aware applications....
-
Developing competences for cooperation in international teams - tools and methods
PublicationThe article presents the training methods that can be used to develop intercultural competences which are extremely important while working in intercultural teams. The mentioned methods like: case-studies, collaborating, role-play simulations, team working, video presentations and others are presented on the basis of authors’ experiences while teaching the international groups of students at Faculty of Management and Economics...
-
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...
-
Video content analysis in the urban area telemonitoring system
PublicationThe task of constant monitoring of video streams from a large number of cameras and reviewing the recordings in order to find a specified event requires a considerable amount of time and effort from the system operators and it is prone to errors. A solution to this problem is an automatic system for constant analysis of camera images being able to raise an alarm if a predefined event is detected. The chapter presents various aspects...
-
Processes of enhancing the intelligence of Learning Organizations on the basis of Competence Centers
PublicationThe process of organizational learning and proper knowledge management became today one of the major challenges for the organization acting in the knowledge-based economy. According to the observations of the authors of this paper the demand for formalization of knowledge management processes and organizational learning is particularly evident in research institutions, established either by the universities, or the companies. The...
-
Platforma edX - nowe podejście do kursów online
PublicationWspółczesne metody nauczania na odległość zmieniają się dynamicznie. Powstają światowe konsorcja podejmujące starania zapewnienia dostępu do edukacji na najwyższym poziomie z wykorzystaniem Internetu. Jedną z takich prób jest platforma edX. Jej rozwój zapoczątkowały niemal 2 lata temu MIT i Harvard. Obecnie zespół liczy już 30 uczelni z całego świata. Renoma ośrodków naukowych biorących udział w projekcie przyciągnęła już ponad...
-
Obtaining a Well-Trained Artificial Intelligence Algorithm from Cross-Validation in Endoscopy
PublicationThe article shortly discusses endoscopic video analysis problems and artificial intelligence algorithms supporting it. The most common method of efficiency testing of these algorithms is to perform intensive cross-validation. This allows for accurately evaluate their performance of generalization. One of the main problems of this procedure is that there is no simple and universal way of obtaining a specific instance of a well-trained...
-
An integrated e-learning services management system providing HD videoconferencing and CAA services
PublicationIn this paper we present a novel e-learning services management system, designed to provide highly modifiable platform for various e-learning tools, able to fulfill its function in any network connectivity conditions (including no connectivity scenario). The system can scale from very simple setup (adequate for servicing a single exercise) to a large, distributed solution fit to support an enterprise. Strictly modular architecture...
-
Innovative e-learning approach in teaching based on case studies - Innocase project
PublicationThe article presents the application of innovative e-learning approach for the creation of case study content. Case study methodology is becoming more and more widely applied in modern education, especially in business and management field. Although case study methodology is quite well recognized and used in education, there are still few examples of developing e-learning content on the basis of case studies. This task is to be...
-
Adjusted SpikeProp algorithm for recurrent spiking neural networks with LIF neurons
PublicationA problem related to the development of a supervised learning method for recurrent spiking neural networks is addressed in the paper. The widely used Leaky-Integrate-and-Fire model has been adopted as a spike neuron model. The proposed method is based on a known SpikeProp algorithm. In detail, the developed method enables gradient descent learning of recurrent or multi-layer feedforward spiking neural networks. The research included...
-
Blended Learning Model for Computer Techniques for Students of Architecture
PublicationAbstract: The article summarizes two-year experience of implementing hybrid formula for teaching Computer Techniques at the Faculty of Architecture at the Gdansk University of Technology. Original educational e-materials, consisting of video clips, text and graphics instructions, as well as links to online resources are embedded in the university e-learning educational platform. The author discusses technical constraints associated...
-
Parallel implementation of background subtraction algorithms for real-time video processing on a supercomputer platform
PublicationResults of evaluation of the background subtraction algorithms implemented on a supercomputer platform in a parallel manner are presented in the paper. The aim of the work is to chose an algorithm, a number of threads and a task scheduling method, that together provide satisfactory accuracy and efficiency of a real-time processing of high resolution camera images, maintaining the cost of resources usage at a reasonable level. Two...
-
Vehicle detector training with labels derived from background subtraction algorithms in video surveillance
PublicationVehicle detection in video from a miniature station- ary closed-circuit television (CCTV) camera is discussed in the paper. The camera provides one of components of the intelligent road sign developed in the project concerning the traffic control with the use of autonomous devices being developed. Modern Convolutional Neural Network (CNN) based detectors need big data input, usually demanding their manual labeling. In the presented...
-
Multimedia polysensory integration training system dedicated to children with educational difficulties
PublicationThis paper aims at presenting a multimedia system providing polysensory train- ing for pupils with educational difficulties. The particularly interesting aspect of the system lies in the sonic interaction with image projection in which sounds generated lead to stim- ulation of a particular part of the human brain. The system architecture, video processing methods, therapeutic exercises and guidelines for children’s interaction...
-
How Machine Learning Contributes to Solve Acoustical Problems
PublicationMachine learning is the process of learning functional relationships between measured signals (called percepts in the artificial intelligence literature) and some output of interest. In some cases, we wish to learn very specific relationships from signals such as identifying the language of a speaker (e.g. Zissman, 1996) which has direct applications such as in call center routing or performing a music information retrieval task...
-
Book Review
PublicationActing over the last three decades as an Editor and Associate Editor for a number of international journals in the general area of cybernetics and AI, as well as a Chair and Co-Chair of numerous conferences in this field, I have had the exciting opportunity to closely witness and to be actively engaged in the stimulating research area of machine learning and its important augmentation with deep learning techniques and technologies. From...
-
Pawlak's flow graph extensions for video surveillance systems
PublicationThe idea of the Pawlak's flow graphs is applicable to many problems in various fields related to decision algorithms or data mining. The flow graphs can be used also in the video surveillance systems. Especially in distributed multi-camera systems which are problematic to be handled by human operators because of their limited perception. In such systems automated video analysis needs to be implemented. Important part of this analysis...
-
Classification of Sea Going Vessels Properties Using SAR Satellite Images
PublicationThe aim of the project was to analyze the possibility of using machine learning and computer vision to identify (indicate the location) of all sea-going vessels located in the selected area of the open sea and to classify the main attributes of the vessel. The key elements of the project were to download data from the Sentinel-1 satellite [1], download data on the sea vessels [2], then automatically tag data and develop a detection...
-
Investigating Feature Spaces for Isolated Word Recognition
PublicationMuch attention is given by researchers to the speech processing task in automatic speech recognition (ASR) over the past decades. The study addresses the issue related to the investigation of the appropriateness of a two-dimensional representation of speech feature spaces for speech recognition tasks based on deep learning techniques. The approach combines Convolutional Neural Networks (CNNs) and timefrequency signal representation...
-
Multi-Decision Analysis for selection of the best procedure for PAHs determination in smoked food.
PublicationMaking a proper decision in multifacitated situation is very challenging task. Especially, if there are many alternatives and criteria, even contradictory ones. The support tools may be application of MultiCriteria Decision Analysis methods. In this study the application of PROMETHEE...
-
Weakly-Supervised Word-Level Pronunciation Error Detection in Non-Native English Speech
PublicationWe propose a weakly-supervised model for word-level mispronunciation detection in non-native (L2) English speech. To train this model, phonetically transcribed L2 speech is not required and we only need to mark mispronounced words. The lack of phonetic transcriptions for L2 speech means that the model has to learn only from a weak signal of word-level mispronunciations. Because of that and due to the limited amount of mispronounced...
-
Implementation of multi-operand addition in FPGA using high-level synthesis
PublicationThe paper presents the results of high-level synthesis (HLS) of multi-operand adders in FPGA using the Vivado Xilinx environment. The aim was to estimate the hardware amount and latency of adders described in C-code. The main task of the presented experiments was to compare the implementations of the carry-save adder (CSA) type multi-operand adders obtained as the effect of the HLS synthesis and those based on the basic component...
-
From Sequential to Parallel Implementation of NLP Using the Actor Model
PublicationThe article focuses on presenting methods allowing easy parallelization of an existing, sequential Natural Language Processing (NLP) application within a multi-core system. The actor-based solution implemented with the Akka framework has been applied and compared to an application based on Task Parallel Library (TPL) and to the original sequential application. Architectures, data and control flows are described along with execution...
-
Design of a microrobotic wrist for needle laparoscopic surgery
PublicationThe paper addresses the design of a micro wrist for needle laparoscopic surgery (needlescopy) using MEMS technology and an original 3 degree of freedom, 3D architecture. Advancement in needlescopy drives the development of multi-dof micro-tools 1-2mmin diameter with 3D mobility but standard available fabricationtechniques are for 2.5D structures. The paper discusses thedevelopment steps and design solutions for the realization...
-
Experimental study on single phase operation of microjet augmented heat exchanger with enhanced heat transfer surface
PublicationThe article presents experimental investigations on a prototype heat exchanger. Presented research is focused on combined active and passive enhancement techniques of surface modification and microjet impingement. The results were compared to reference plate heat exchanger without microjet impingement. The Wilson plot method was applied to determine the heat transfer coefficients in the single phase operation. The heat exchanger...
-
Data-Driven Surrogate-Assisted Optimization of Metamaterial-Based Filtenna Using Deep Learning
PublicationIn this work, a computationally efficient method based on data driven surrogate models is pro-posed for the design optimization procedure of a Frequency Selective Surface (FSS)-based filtering antenna (Filtenna). A Filtenna acts as a as module that simultaneously pre-filters unwanted sig-nals, and enhances the desired signals at the operating frequency. However, due to a typically large number of design variables of FSS unit elements,...
-
Benchmarking Deep Neural Network Training Using Multi- and Many-Core Processors
PublicationIn the paper we provide thorough benchmarking of deep neural network (DNN) training on modern multi- and many-core Intel processors in order to assess performance differences for various deep learning as well as parallel computing parameters. We present performance of DNN training for Alexnet, Googlenet, Googlenet_v2 as well as Resnet_50 for various engines used by the deep learning framework, for various batch sizes. Furthermore,...
-
Intelligent Audio Signal Processing − Do We Still Need Annotated Datasets?
PublicationIn this paper, intelligent audio signal processing examples are shortly described. The focus is, however, on the machine learning approach and datasets needed, especially for deep learning models. Years of intense research produced many important results in this area; however, the goal of fully intelligent signal processing, characterized by its autonomous acting, is not yet achieved. Therefore, a review of state-of-the-art concerning...
-
Cross-domain applications of multimodal human-computer interfaces
PublicationDeveloped multimodal interfaces for education applications and for disabled people are presented, including interactive electronic whiteboard based on video image analysis, application for controlling computers with mouth gestures and audio interface for speech stretching for hearing impaired and stuttering people and intelligent pen allowing for diagnosing and ameliorating developmental dyslexia. The eye-gaze tracking system named...
-
A new multi-process collaborative architecture for time series classification
PublicationTime series classification (TSC) is the problem of categorizing time series data by using machine learning techniques. Its applications vary from cybersecurity and health care to remote sensing and human activity recognition. In this paper, we propose a novel multi-process collaborative architecture for TSC. The propositioned method amalgamates multi-head convolutional neural networks and capsule mechanism. In addition to the discovery...
-
Maritime traffic situation awareness analysis via high-fidelity ship imaging trajectory
PublicationSituation awareness provides crucial yet instant information to maritime traffic participants, and significant attentions are paid to implement traffic situation awareness task via various maritime data source (e.g., automatic identification system, maritime surveillance video, radar, etc.). The study aims to analyze traffic situation with the support of ship imaging trajectory. First, we employ the dark channel prior model to...
-
AITP - AI Thermal Pedestrians Dataset
PublicationEfficient pedestrian detection is a very important task in ensuring safety within road conditions, especially after sunset. One way to achieve this goal is to use thermal imaging in conjunction with deep learning methods and an annotated dataset for models training. In this work, such a dataset has been created by capturing thermal images of pedestrians in different weather and traffic conditions. All images were manually annotated...
-
Rapid Multi-Criterial Antenna Optimization by Means of Pareto Front Triangulation and Interpolative Design Predictors
PublicationModern antenna systems are designed to meet stringent performance requirements pertinent to both their electrical and field properties. The objectives typically stay in conflict with each other. As the simultaneous improvement of all performance parameters is rarely possible, compromise solutions have to be sought. The most comprehensive information about available design trade-offs can be obtained through multi-objective optimization...
-
A Generative Approach to Hull Design for a Small Watercraft
PublicationIn the field of ocean engineering, the task of spatial hull modelling is one of the most complicated problems in ship design. This study presents a procedure applied as a generative approach to the design problems for the hull geometry of small vessels using elements of concurrent design with multi-criteria optimisation processes. Based upon widely available commercial software, an algorithm for the mathematical formulation of...
-
DevEmo—Software Developers’ Facial Expression Dataset
PublicationThe COVID-19 pandemic has increased the relevance of remote activities and digital tools for education, work, and other aspects of daily life. This reality has highlighted the need for emotion recognition technology to better understand the emotions of computer users and provide support in remote environments. Emotion recognition can play a critical role in improving the remote experience and ensuring that individuals are able...
-
Study on Strategy in University Laboratory Class Teaching
PublicationLaboratory teaching is a critical way to ensure the effective input of techniques in engineering learning. Laboratory teaching not only contributes to improving course quality but also helps enrich comprehensive engineering application ability. However, there are some typical problems in current university laboratory teaching, such as rigid and isolated course design, outdated contents and materials, and not encouraging innovation...
-
Investigating Feature Spaces for Isolated Word Recognition
PublicationThe study addresses the issues related to the appropriateness of a two-dimensional representation of speech signal for speech recognition tasks based on deep learning techniques. The approach combines Convolutional Neural Networks (CNNs) and time-frequency signal representation converted to the investigated feature spaces. In particular, waveforms and fractal dimension features of the signal were chosen for the time domain, and...
-
Poprawa jakości klasyfikacji głębokich sieci neuronowych poprzez optymalizację ich struktury i dwuetapowy proces uczenia
PublicationW pracy doktorskiej podjęto problem realizacji algorytmów głębokiego uczenia w warunkach deficytu danych uczących. Głównym celem było opracowanie podejścia optymalizującego strukturę sieci neuronowej oraz zastosowanie uczeniu dwuetapowym, w celu uzyskania mniejszych struktur, zachowując przy tym dokładności. Proponowane rozwiązania poddano testom na zadaniu klasyfikacji znamion skórnych na znamiona złośliwe i łagodne. W pierwszym...
-
Voice command recognition using hybrid genetic algorithm
PublicationAbstract: Speech recognition is a process of converting the acoustic signal into a set of words, whereas voice command recognition consists in the correct identification of voice commands, usually single words. Voice command recognition systems are widely used in the military, control systems, electronic devices, such as cellular phones, or by people with disabilities (e.g., for controlling a wheelchair or operating a computer...
-
Dysfunctional prefrontal cortical network activity and interactions following cannabinoid receptor activation.
PublicationCoordinated activity spanning anatomically distributed neuronal networks underpins cognition and mediates limbic-cortical interactions during learning, memory, and decision-making. We used CP55940, a potent agonist of brain cannabinoid receptors known to disrupt coordinated activity in hippocampus, to investigate the roles of network oscillations during hippocampal and medial prefrontal cortical (mPFC) interactions in rats. During...