Filters
total: 532
Search results for: IMAGE SEGMENTATION, COMPUTER VISION, DEEP LEARNING
-
Computer vision techniques applied for reconstruction of seafloor 3D images from side scan and synthetic aperture sonars data
PublicationThe Side Scan Sonar and Synthetic Aperture Sonar are well known echo signal processing technologies that produce 2D images of the seafloor. Both systems combines a number of acoustic pings to form a high resolution image of seafloor. It was shown in numerous papers that 2D images acquired by such systems can be transformed into 3D models of seafloor surface by algorithmic approach using intensity information, contained in a grayscaled...
-
Interpretable Deep Learning Model for the Detection and Reconstruction of Dysarthric Speech
PublicationWe present a novel deep learning model for the detection and reconstruction of dysarthric speech. We train the model with a multi-task learning technique to jointly solve dysarthria detection and speech reconstruction tasks. The model key feature is a low-dimensional latent space that is meant to encode the properties of dysarthric speech. It is commonly believed that neural networks are black boxes that solve problems but do not...
-
Abdominal Aortic Aneurysm segmentation from contrast-enhanced computed tomography angiography using deep convolutional networks
PublicationOne of the most common imaging methods for diagnosing an abdominal aortic aneurysm, and an endoleak detection is computed tomography angiography. In this paper, we address the problem of aorta and thrombus semantic segmentation, what is a mandatory step to estimate aortic aneurysm diameter. Three end-to-end convolutional neural networks were trained and evaluated. Finally, we proposed an ensemble of deep neural networks with underlying...
-
Deep Learning-Based, Multiclass Approach to Cancer Classification on Liquid Biopsy Data
PublicationThe field of cancer diagnostics has been revolutionized by liquid biopsies, which offer a bridge between laboratory research and clinical settings. These tests are less invasive than traditional biopsies and more convenient than routine imaging methods. Liquid biopsies allow studying of tumor-derived markers in bodily fluids, enabling the development of more precise cancer diagnostic tests for screening, disease monitoring, and...
-
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...
-
Computer vision monitoring system for circular saw teeth.
PublicationW pracy opisano zasadę działania urządzenia do wizyjnego monitoringu ostrzy pił tarczowych tyou WKOPTar, które w sposób automatyczny dokonuje pomiarów geometrii ostrzy oraz ich położenia w pile. Przedstawiono również analizę wyników badań na bazie zarejestrowanych ostrzy badanych pił tarczowych.
-
Pursuing the Deep-Learning-Based Classification of Exposed and Imagined Colors from EEG
PublicationEEG-based brain-computer interfaces are systems aiming to integrate disabled people into their environments. Nevertheless, their control could not be intuitive or depend on an active external stimulator to generate the responses for interacting with it. Targeting the second issue, a novel paradigm is explored in this paper, which depends on a passive stimulus by measuring the EEG responses of a subject to the primary colors (red,...
-
Data, Information, Knowledge, Wisdom Pyramid Concept Revisited in the Context of Deep Learning
PublicationIn this paper, the data, information, knowledge, and wisdom (DIKW) pyramid is revisited in the context of deep learning applied to machine learningbased audio signal processing. A discussion on the DIKW schema is carried out, resulting in a proposal that may supplement the original concept. Parallels between DIWK pertaining to audio processing are presented based on examples of the case studies performed by the author and her collaborators....
-
Channel State Estimation in LTE-Based Heterogenous Networks Using Deep Learning
PublicationFollowing the continuous development of the information technology, the concept of dense urban networks has evolved as well. The powerful tools, like machine learning, break new ground in smart network and interface design. In this paper the concept of using deep learning for estimating the radio channel parameters of the LTE (Long Term Evolution) radio interface is presented. It was proved that the deep learning approach provides...
-
Deep Learning-Based LOS and NLOS Identification in Wireless Body Area Networks
PublicationIn this article, the usage of deep learning (DL) in ultra-wideband (UWB) Wireless Body Area Networks (WBANs) is presented. The developed approach, using channel impulse response, allows higher efficiency in identifying the direct visibility conditions between nodes in off-body communication with comparison to the methods described in the literature. The effectiveness of the proposed deep feedforward neural network was checked on...
-
AUTOMATIC LEARNING OF STRATEGY AND RULES IN CARD GAMES USING IMAGE FROM CAMERA
PublicationBelow work tries to answer a question: if it is possible to replace real human with computer system in social games. As a subject for experiments, card games were chosen, because they require a lot of player interaction (playing and taking cards), while their rules are easy to present in form of clear list of statements. Such a system, should allow real players to play without constant worrying about guiding or helping computer...
-
Deep Learning-Based Intrusion System for Vehicular Ad Hoc Networks
PublicationThe increasing use of the Internet with vehicles has made travel more convenient. However, hackers can attack intelligent vehicles through various technical loopholes, resulting in a range of security issues. Due to these security issues, the safety protection technology of the in-vehicle system has become a focus of research. Using the advanced autoencoder network and recurrent neural network in deep learning, we investigated...
-
BIG DATA SIGNIFICANCE IN REMOTE MEDICAL DIAGNOSTICS BASED ON DEEP LEARNING TECHNIQUES
PublicationIn this paper we discuss the evaluation of neural networks in accordance with medical image classification and analysis. We also summarize the existing databases with images which could be used for training deep models that can be later utilized in remote home-based health care systems. In particular, we propose methods for remote video-based estimation of patient vital signs and other health-related parameters. Additionally, potential...
-
Core outcomes measures in dental computer vision studies (DentalCOMS)
Publication -
Framework for Structural Health Monitoring of Steel Bridges by Computer Vision
PublicationThe monitoring of a structural condition of steel bridges is an important issue. Good condition of infrastructure facilities ensures the safety and economic well-being of society. At the same time, due to the continuous development, rising wealth of the society and socio-economic integration of countries, the number of infrastructural objects is growing. Therefore, there is a need to introduce an easy-to-use and relatively low-cost...
-
Bimodal deep learning model for subjectively enhanced emotion classification in films
PublicationThis research delves into the concept of color grading in film, focusing on how color influences the emotional response of the audience. The study commenced by recalling state-of-the-art works that process audio-video signals and associated emotions by machine learning. Then, assumptions of subjective tests for refining and validating an emotion model for assigning specific emotional labels to selected film excerpts were presented....
-
Position Estimation in Mixed Indoor-Outdoor Environment Using Signals of Opportunity and Deep Learning Approach
PublicationTo improve the user's localization estimation in indoor and outdoor environment a novel radiolocalization system using deep learning dedicated to work both in indoor and outdoor environment is proposed. It is based on the radio signatures using radio signals of opportunity from LTE an WiFi networks. The measurements of channel state estimators from LTE network and from WiFi network are taken by using the developed application....
-
Big Data from Sensor Network via Internet of Things to Edge Deep Learning for Smart City
PublicationData from a physical world is sampled by sensor networks, and then streams of Big Data are sent to cloud hosts to support decision making by deep learning software. In a smart city, some tasks may be assigned to smart devices of the Internet of Things for performing edge computing. Besides, a part of workload of calculations can be transferred to the cloud hosts. This paper proposes benchmarks for division tasks between an edge...
-
Deep Learning Approaches in Histopathology
Publication -
Comparison of image pre-processing methods in liver segmentation task
PublicationAutomatic liver segmentation of Computed Tomography (CT) images is becoming increasingly important. Although there are many publications in this field there is little explanation why certain pre-processing methods were utilised. This paper presents a comparison of the commonly used approach of Hounsfield Units (HU) windowing, histogram equalisation, and a combination of these methods to try to ascertain what are the differences...
-
Deep learning for ultra-fast and high precision screening of energy materials
PublicationSemiconductor materials for energy storage are the core and foundation of modern information society and play important roles in photovoltaic system, integrated circuit, spacecraft technology, lighting applications, and other fields. Unfortunately, due to the long experiment period and high calculation cost, the high-precision band gap (the basic characteristic parameter) of semiconductor is difficult to obtain, which hinders the...
-
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...
-
Attention-Based Deep Learning System for Classification of Breast Lesions—Multimodal, Weakly Supervised Approach
PublicationBreast cancer is the most frequent female cancer, with a considerable disease burden and high mortality. Early diagnosis with screening mammography might be facilitated by automated systems supported by deep learning artificial intelligence. We propose a model based on a weakly supervised Clustering-constrained Attention Multiple Instance Learning (CLAM) classifier able to train under data scarcity effectively. We used a private...
-
LOS and NLOS identification in real indoor environment using deep learning approach
PublicationVisibility conditions between antennas, i.e. Line-of-Sight (LOS) and Non-Line-of-Sight (NLOS) can be crucial in the context of indoor localization, for which detecting the NLOS condition and further correcting constant position estimation errors or allocating resources can reduce the negative influence of multipath propagation on wireless communication and positioning. In this paper a deep learning (DL) model to classify LOS/NLOS...
-
Deep learning-based waste detection in natural and urban environments
PublicationWaste pollution is one of the most significant environmental issues in the modern world. The importance of recycling is well known, both for economic and ecological reasons, and the industry demands high efficiency. Current studies towards automatic waste detection are hardly comparable due to the lack of benchmarks and widely accepted standards regarding the used metrics and data. Those problems are addressed in this article by...
-
Olgun Aydin dr
PeopleOlgun Aydin finished his PhD by publishing a thesis about Deep Neural Networks. He works as a Principal Machine Learning Engineer in Nike, and works as Assistant Professor in Gdansk University of Technology in Poland. Dr. Aydin is part of editorial board of "Journal of Artificial Intelligence and Data Science" Dr. Aydin served as Vice-Chairman of Why R? Foundation and is member of Polish Artificial Intelligence Society. Olgun is...
-
RF Indoor Positioning System Supported by Wireless Computer Vision Sensors
PublicationIn this paper the possibility of increase the accuracy of RF fingerprinting indoor tracking system by the use of additional information from simple vision system is examined. As the distances in signal space differs from ones in real environment the ambiguity in decision process of fingerprinting algorithm can occur when set of closest distances between tag and map points in signal space corresponds to big distances differences...
-
Deep neural networks for human pose estimation from a very low resolution depth image
PublicationThe work presented in the paper is dedicated to determining and evaluating the most efficient neural network architecture applied as a multiple regression network localizing human body joints in 3D space based on a single low resolution depth image. The main challenge was to deal with a noisy and coarse representation of the human body, as observed by a depth sensor from a large distance, and to achieve high localization precision....
-
Application of colour image segmentation for localization and extraction text from images
PublicationW otaczającym nas świecie informacja tekstowa odgrywa wielką rolę. W postaci tekstowej podawane są: nazwy ulic, nazwy sklepów i instytucji, opisy przedmiotów np. tytuły książek, opakowań itp. Jednocześnie współczesne programy komputerowe służące do rozpoznawania tekstu (OCR) ''nie radzą sobie'' z analizą obrazów otrzymanaych za pomocą kamer. Segmentacja obrazu z następującą kontekstową analizą parametrów segmentów może dostarczyć...
-
IET Computer Vision
Journals -
Ireneusz Czarnowski Prof.
PeopleIRENEUSZ CZARNOWSKI is a graduate of the Faculty of Electrical Engineering at Gdynia Maritime University. He gained a doctoral degree in the field of computer science at Poznan University of Technology and a postdoctoral degree in the field of computer science at Wroclaw University of Science and Technology. Since 1998 is associated with Gdynia Maritime University, currently is a professor of computer science in the Department...
-
Intra-subject class-incremental deep learning approach for EEG-based imagined speech recognition
PublicationBrain–computer interfaces (BCIs) aim to decode brain signals and transform them into commands for device operation. The present study aimed to decode the brain activity during imagined speech. The BCI must identify imagined words within a given vocabulary and thus perform the requested action. A possible scenario when using this approach is the gradual addition of new words to the vocabulary using incremental learning methods....
-
Influence of Thermal Imagery Resolution on Accuracy of Deep Learning based Face Recognition
PublicationHuman-system interactions frequently require a retrieval of the key context information about the user and the environment. Image processing techniques have been widely applied in this area, providing details about recognized objects, people and actions. Considering remote diagnostics solutions, e.g. non-contact vital signs estimation and smart home monitoring systems that utilize person’s identity, security is a very important factor....
-
Michał Lech dr inż.
PeopleMichał Lech was born in Gdynia in 1983. In 2007 he graduated from the faculty of Electronics, Telecommunications and Informatics of Gdansk University of Technology. In June 2013, he received his Ph.D. degree. The subject of the dissertation was: “A Method and Algorithms for Controlling the Sound Mixing Processes by Hand Gestures Recognized Using Computer Vision”. The main focus of the thesis was the bias of audio perception caused...
-
Fast Fading Influence on the Deep Learning-Based LOS and NLOS Identificationin Wireless Body Area Networks
PublicationIn the article, the fast fading influence on the proposed DL (Deep Learning) approach for LOS (Line-of-Sight) and NLOS (Non-Line-of-Sight) conditions identification in Wireless Body Area Networks is investigated. The research was conducted on the basis of the off-body communication measurements using the developed mobile measurement stand, in an indoor environment for both static and dynamic scenarios. The measurements involved...
-
User Orientation Detection in Relation to Antenna Geometry in Ultra-Wideband Wireless Body Area Networks Using Deep Learning
PublicationIn this paper, the issue of detecting a user’s position in relation to the antenna geometry in ultra-wideband (UWB) off-body wireless body area network (WBAN) communication using deep learning methods is presented. To measure the impulse response of the channel, a measurement stand consisting of EVB1000 devices and DW1000 radio modules was developed and indoor static measurement scenarios were performed. It was proven that for...
-
Deep learning for recommending subscription-limited documents
PublicationDocuments recommendation for a commercial, subscription-based online platform is important due to the difficulty in navigation through a large volume and diversity of content available to clients. However, this is also a challenging task due to the number of new documents added every day and decreasing relevance of older contents. To solve this problem, we propose deep neural network architecture that combines autoencoder with...
-
Decision making process using deep learning
PublicationEndüstri 4.0, dördüncü endüstri devrimi veya Endüstriyel Nesnelerin İnterneti (IIoT) olarak adlandırılan sanayi akımı, işletmelere, daha verimli, daha büyük bir esneklikle, daha güvenli ve daha çevre dostu bir şekilde üretim yapma imkanı sunmaktadır. Nesnelerin İnterneti ile bağlantılı yeni teknoloji ve hizmetler birçok endüstriyel uygulamada devrim niteliği taşımaktadır. Fabrikalardaki otomasyon, tahminleyici bakım (PdM – Predictive...
-
Scent emitting multimodal computer interface for learning enhancement
PublicationKomputerowy interfejs aromatyczny stanowi ważne uzupełnienie procesu stymulacji polisensorycznej. Stymulacja ta odgrywa kluczową rolę w terapii i kształceniu dzieci z zaburzeniami rozwoju (np. w przypadku autyzmu czy ADHD). Opracowany interfejs może stać się elementem wyposażenia tzw. sal doświadczania świata, ale może być także stosowany niezależnie stanowiąc znaczące wzbogacenie komputerowych programów edukacyjnych. Dzięki możliwości...
-
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,...
-
Using Isolation Forest and Alternative Data Products to Overcome Ground Truth Data Scarcity for Improved Deep Learning-based Agricultural Land Use Classification Models
PublicationHigh-quality labelled datasets represent a cornerstone in the development of deep learning models for land use classification. The high cost of data collection, the inherent errors introduced during data mapping efforts, the lack of local knowledge, and the spatial variability of the data hinder the development of accurate and spatially-transferable deep learning models in the context of agriculture. In this paper, we investigate...
-
Deep-Learning-Based Precise Characterization of Microwave Transistors Using Fully-Automated Regression Surrogates
PublicationAccurate models of scattering and noise parameters of transistors are instrumental in facilitating design procedures of microwave devices such as low-noise amplifiers. Yet, data-driven modeling of transistors is a challenging endeavor due to complex relationships between transistor characteristics and its designable parameters, biasing conditions, and frequency. Artificial neural network (ANN)-based methods, including deep learning...
-
GPU Power Capping for Energy-Performance Trade-Offs in Training of Deep Convolutional Neural Networks for Image Recognition
PublicationIn the paper we present performance-energy trade-off investigation of training Deep Convolutional Neural Networks for image recognition. Several representative and widely adopted network models, such as Alexnet, VGG-19, Inception V3, Inception V4, Resnet50 and Resnet152 were tested using systems with Nvidia Quadro RTX 6000 as well as Nvidia V100 GPUs. Using GPU power capping we found other than default configurations minimizing...
-
Variable Data Structures and Customized Deep Learning Surrogates for Computationally Efficient and Reliable Characterization of Buried Objects
PublicationIn this study, in order to characterize the buried object via deep-learning-based surrogate modeling approach, 3-D full-wave electromagnetic simulations of a GPR model has been used. The task is to predict simultaneously and independent of each characteristic parameters of a buried object of several radii at different positions (depth and lateral position) in various dispersive subsurface media. This study has analyzed variable...
-
Solubility of dapsone in deep eutectic solvents: Experimental analysis, molecular insights and machine learning predictions
PublicationBackground. Dapsone (DAP) is an anti-inflammatory and antimicrobial active pharmaceutical ingredient used to treat, e.g., AIDS-related diseases. However, low solubility is a feature hampering its efficient use. Objectives. First, deep eutectic solvents...
-
Satellite Image Classification Using a Hierarchical Ensemble Learning and Correlation Coefficient-Based Gravitational Search Algorithm
PublicationSatellite image classification is widely used in various real-time applications, such as the military, geospatial surveys, surveillance and environmental monitoring. Therefore, the effective classification of satellite images is required to improve classification accuracy. In this paper, the combination of Hierarchical Framework and Ensemble Learning (HFEL) and optimal feature selection is proposed for the precise identification...
-
AGAR a Microbial Colony Dataset for Deep Learning Detection
Publication -
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...
-
Classifying Emotions in Film Music - A Deep Learning Approach
PublicationThe paper presents an application for automatically classifying emotions in film music. A model of emotions is proposed, which is also associated with colors. The model created has nine emotional states, to which colors are assigned according to the color theory in film. Subjective tests are carried out to check the correctness of the assumptions behind the adopted emotion model. For that purpose, a statistical analysis of the...
-
Detecting Lombard Speech Using Deep Learning Approach
PublicationRobust Lombard speech-in-noise detecting is challenging. This study proposes a strategy to detect Lombard speech using a machine learning approach for applications such as public address systems that work in near real time. The paper starts with the background concerning the Lombard effect. Then, assumptions of the work performed for Lombard speech detection are outlined. The framework proposed combines convolutional neural networks...