Wyszukiwarka
Filtry
wszystkich: 548
Wyniki wyszukiwania dla: semantic segmentation, noisy annotations, loss masking, deep neural networks
-
Efkleidis Katsaros
OsobyEfklidis Katsaros received the B.Sc. degree in mathematics from the Aristotle University of Thessaloniki, Greece, in 2016, and the M.Sc. degree (cum laude) in data science: statistical science from Leiden University, The Netherlands, in 2019. He is currently pursuing the Ph.D. degree in deep video multi-task learning with the Department of Biomedical Engineering, Gdańsk University of Technology, Poland. Since 2020, he has been...
-
Semantic URL Analytics to Support Efficient Annotation of Large Scale Web Archives
PublikacjaLong-term Web archives comprise Web documents gathered over longer time periods and can easily reach hundreds of terabytes in size. Semantic annotations such as named entities can facilitate intelligent access to the Web archive data. However, the annotation of the entire archive content on this scale is often infeasible. The most efficient way to access the documents within Web archives is provided through their URLs, which are...
-
Adaptive Hounsfield Scale Windowing in Computed Tomography Liver Segmentation
PublikacjaIn computed tomography (CT) imaging, the Hounsfield Unit (HU) scale quantifies radiodensity, but its nonlinear nature across organs and lesions complicates machine learning analysis. This paper introduces an automated method for adaptive HU scale windowing in deep learning-based CT liver segmentation. We propose a new neural network layer that optimizes HU scale window parameters during training. Experiments on the Liver Tumor...
-
Data augmentation for improving deep learning in image classification problem
PublikacjaThese days deep learning is the fastest-growing field in the field of Machine Learning (ML) and Deep Neural Networks (DNN). Among many of DNN structures, the Convolutional Neural Networks (CNN) are currently the main tool used for the image analysis and classification purposes. Although great achievements and perspectives, deep neural networks and accompanying learning algorithms have some relevant challenges to tackle. In this...
-
Smart Approach for Glioma Segmentation in Magnetic Resonance Imaging using Modified Convolutional Network Architecture (U-NET)
PublikacjaSegmentation of a brain tumor from magnetic resonance multimodal images is a challenging task in the field of medical imaging. The vast diversity in potential target regions, appearance and multifarious intensity threshold levels of various tumor types are few of the major factors that affect segmentation results. An accurate diagnosis and its treatment demand strict delineation of the tumor affected tissues. Herein, we focus on...
-
From Linear Classifier to Convolutional Neural Network for Hand Pose Recognition
PublikacjaRecently gathered image datasets and the new capabilities of high-performance computing systems have allowed developing new artificial neural network models and training algorithms. Using the new machine learning models, computer vision tasks can be accomplished based on the raw values of image pixels instead of specific features. The principle of operation of deep neural networks resembles more and more what we believe to be happening...
-
Deep CNN based decision support system for detection and assessing the stage of diabetic retinopathy
PublikacjaThe diabetic retinopathy is a disease caused by long-standing diabetes. Lack of effective treatment can lead to vision impairment and even irreversible blindness. The disease can be diagnosed by examining digital color fundus photographs of retina. In this paper we propose deep learning approach to automated diabetic retinopathy screening. Deep convolutional neural networks (CNN) - the most popular kind of deep learning algorithms...
-
Australian Conference on Neural Networks
Konferencje -
International Symposium on Neural Networks
Konferencje -
World Congress on Neural Networks
Konferencje -
Paweł Rościszewski dr inż.
OsobyPaweł Rościszewski received his PhD in Computer Science at Gdańsk University of Technology in 2018 based on PhD thesis entitled: "Optimization of hybrid parallel application execution in heterogeneous high performance computing systems considering execution time and power consumption". Currently, he is an Assistant Professor at the Faculty of Electronics, Telecommunications and Informatics, Gdańsk University of Technology, Poland....
-
Efficiency of Artificial Intelligence Methods for Hearing Loss Type Classification: an Evaluation
PublikacjaThe evaluation of hearing loss is primarily conducted by pure tone audiometry testing, which is often regarded as golden standard for assessing auditory function. If the presence of hearing loss is determined, it is possible to differentiate between three types of hearing loss: sensorineural, conductive, and mixed. This study presents a comprehensive comparison of a variety of AI classification models, performed on 4007 pure tone...
-
Study of Statistical Text Representation Methods for Performance Improvement of a Hierarchical Attention Network
PublikacjaTo effectively process textual data, many approaches have been proposed to create text representations. The transformation of a text into a form of numbers that can be computed using computers is crucial for further applications in downstream tasks such as document classification, document summarization, and so forth. In our work, we study the quality of text representations using statistical methods and compare them to approaches...
-
A Method for Optimising the Blade Profile in Kaplan Turbine
PublikacjaThis paper introduces a method of blade profile optimisation for Kaplan-type turbines, based on modelling the interaction between rotor and stator blades. Rotor and stator blade geometry is described mathematically by means of a midline curve and thickness distribution. Genetic algorithms are then used to find a global optimum that minimises the loss coefficient. This allows for variety of possible blade shapes and configurations....
-
Autonomous pick-and-place system based on multiple 3Dsensors and deep learning
PublikacjaGrasping objects and manipulating them is the main way the robot interacts with its environment. However, for robots to operate in a dynamic environment, a system for determining the gripping position for objects in the scene is also required. For this purpose, neural networks segmenting the point cloud are usually applied. However, training such networks is very complex and their results are unsatisfactory. Therefore, we propose...
-
Autonomous Perception and Grasp Generation Based on Multiple 3D Sensors and Deep Learning
PublikacjaGrasping objects and manipulating them is the main way the robot interacts with its environment. However, for robots to operate in a dynamic environment, a system for determining the gripping position for objects in the scene is also required. For this purpose, neural networks segmenting the point cloud are usually applied. However, training such networks is very complex and their results are unsatisfactory. Therefore, we propose...
-
Experience-Based Cognition for Driving Behavioral Fingerprint Extraction
PublikacjaABSTRACT With the rapid progress of information technologies, cars have been made increasingly intelligent. This allows cars to act as cognitive agents, i.e., to acquire knowledge and understanding of the driving habits and behavioral characteristics of drivers (i.e., driving behavioral fingerprint) through experience. Such knowledge can be then reused to facilitate the interaction between a car and its driver, and to develop better and...
-
On a Method of Efficiency Increasing in Kaplan Turbine
PublikacjaThis paper presents a method of increasing efficiency in Kaplan-type turbine. The method is based on blade profile optimisation together with modelling the interaction between rotor and stator blades. Loss coefficient was chosen as the optimisation criterion, which is related directly to efficiency. Global optimum was found by means of Genetic Algorithms, and Artificial Neural Networks were utilised for approximations to reduce...
-
Paweł Burdziakowski dr inż.
Osobydr inż. Paweł Burdziakowski jest specjalista w zakresie fotogrametrii i teledetekcji lotniczej niskiego pułapu, nawigacji morskiej i lotniczej. Jest również licencjonowanym instruktorem lotniczym oraz programistą. Głównymi obszarami zainteresowania jest fotogrametria cyfrowa, nawigacja platform bezzałogowych oraz systemy bezzałogowe, w tym lotnicze, nawodne, podwodne. Prowadzi badania w zakresie algorytmów i metod poprawiających...
-
Data Acquisition and Processing for GeoAI Models to Support Sustainable Agricultural Practices
PublikacjaThere 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...
-
Spatiotemporal Assessment of Satellite Image Time Series for Land Cover Classification Using Deep Learning Techniques: A Case Study of Reunion Island, France
PublikacjaCurrent Earth observation systems generate massive amounts of satellite image time series to keep track of geographical areas over time to monitor and identify environmental and climate change. Efficiently analyzing such data remains an unresolved issue in remote sensing. In classifying land cover, utilizing SITS rather than one image might benefit differentiating across classes because of their varied temporal patterns. The aim...
-
Vehicle detector training with minimal supervision
PublikacjaRecently many efficient object detectors based on convolutional neural networks (CNN) have been developed and they achieved impressive performance on many computer vision tasks. However, in order to achieve practical results, CNNs require really large annotated datasets for training. While many such databases are available, many of them can only be used for research purposes. Also some problems exist where such datasets are not...
-
Artificial Neural Networks in Engineering Conference
Konferencje -
European Symposium on Artificial Neural Networks
Konferencje -
IEEE International Conference on Neural Networks
Konferencje -
International Conference on Artificial Neural Networks
Konferencje -
Andrzej Stateczny prof. dr hab. inż.
OsobyProf. dr hab. inż. Andrzej Stateczny jest profesorem Politechniki Gdańskiej i prezesem firmy Marine Technology Ltd. Jego zainteresowania naukowe koncentrują się głównie wokół nawigacji, hydrografii i geoinformatyki. Obecnie prowadzone badania obejmują nawigację radarową, nawigację porównawczą, hydrografię, metody sztucznej inteligencji w zakresie przetwarzania obrazów i fuzji danych wielosensorycznych. Był kierownikiem lub głównym...
-
Instance segmentation of stack composed of unknown objects
PublikacjaThe article reviews neural network architectures designed for the segmentation task. It focuses mainly on instance segmentation of stacked objects. The main assumption is that segmentation is based on a color image with an additional depth layer. The paper also introduces the Stacked Bricks Dataset based on three cameras: RealSense L515, ZED2, and a synthetic one. Selected architectures: DeepLab, Mask RCNN, DEtection TRansformer,...
-
An Improved Convolutional Neural Network for Steganalysis in the Scenario of Reuse of the Stego-Key
PublikacjaThe topic of this paper is the use of deep learning techniques, more specifically convolutional neural networks, for steganalysis of digital images. The steganalysis scenario of the repeated use of the stego-key is considered. Firstly, a study of the influence of the depth and width of the convolution layers on the effectiveness of classification was conducted. Next, a study on the influence of depth and width of fully connected...
-
WYKORZYSTANIE SIECI NEURONOWYCH DO SYNTEZY MOWY WYRAŻAJĄCEJ EMOCJE
PublikacjaW niniejszym artykule przedstawiono analizę rozwiązań do rozpoznawania emocji opartych na mowie i możliwości ich wykorzystania w syntezie mowy z emocjami, wykorzystując do tego celu sieci neuronowe. Przedstawiono aktualne rozwiązania dotyczące rozpoznawania emocji w mowie i metod syntezy mowy za pomocą sieci neuronowych. Obecnie obserwuje się znaczny wzrost zainteresowania i wykorzystania uczenia głębokiego w aplikacjach związanych...
-
THE ROLE OF INFERENCE IN MOBILE MEDICAL APPLICATION DESIGN
PublikacjaIn the early 21st century, artificial intelligence began to be used to process medical information. However, before this happened, predictive models used in healthcare could only consider a limited number of variables, and only in properly structured and organised medical data. Today, advanced tools based on machine learning techniques - which, using artificial neural networks, can explore extremely complex relationships - and...
-
Classifying Emotions in Film Music - A Deep Learning Approach
PublikacjaThe 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...
-
BIG DATA SIGNIFICANCE IN REMOTE MEDICAL DIAGNOSTICS BASED ON DEEP LEARNING TECHNIQUES
PublikacjaIn 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...
-
Towards Knowledge Sharing Oriented Adaptive Control
PublikacjaIn this paper, we propose a knowledge sharing oriented approach to enable a robot to reuse other robots' knowledge by adapting itself to the inverse dynamics model of the knowledge-sharing robot. The purpose of this work is to remove the heavy fine-tuning procedure required before using a new robot for a task via reusing other robots' knowledge. We use the Neural Knowledge DNA (NK-DNA) to help robots gain empirical knowledge and...
-
Wordventure - cooperative wordnet editor. Architecture for lexical semantic aquisition
PublikacjaThis article presents architecture for acquiring lexical semanticsin a collaborative approach paradigm. The system enablesfunctionality for editing semantic networks in a wikipedia-like style. The core of the system is a user-friendly interface based on interactive graph navigation.It has been used for semantic network presentation,and brings simultaneously modification functionality.
-
Position Estimation in Mixed Indoor-Outdoor Environment Using Signals of Opportunity and Deep Learning Approach
PublikacjaTo 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....
-
WordVenture - COOPERATIVE WordNet EDITOR Architecture for Lexical Semantic Acquisition
PublikacjaThis article presents architecture for acquiring lexical semantics in a collaborative approach paradigm. The system enables functionality for editing semantic networks in a wikipedia-like style. The core of the system is a user-friendly interface based on interactive graph navigation. It has been used for semantic network presentation, and brings simultaneously modification functionality.
-
IEEE International Joint Conference on Neural Networks
Konferencje -
Conference on Artificial Neural Networks and Expert systems
Konferencje -
International Conference on Engineering Applications of Neural Networks
Konferencje -
Comparison of the Ability of Neural Network Model and Humans to Detect a Cloned Voice
PublikacjaThe vulnerability of the speaker identity verification system to attacks using voice cloning was examined. The research project assumed creating a model for verifying the speaker’s identity based on voice biometrics and then testing its resistance to potential attacks using voice cloning. The Deep Speaker Neural Speaker Embedding System was trained, and the Real-Time Voice Cloning system was employed based on the SV2TTS, Tacotron,...
-
Speech Analytics Based on Machine Learning
PublikacjaIn this chapter, the process of speech data preparation for machine learning is discussed in detail. Examples of speech analytics methods applied to phonemes and allophones are shown. Further, an approach to automatic phoneme recognition involving optimized parametrization and a classifier belonging to machine learning algorithms is discussed. Feature vectors are built on the basis of descriptors coming from the music information...
-
Optimized Deep Learning Model for Flood Detection Using Satellite Images
PublikacjaThe increasing amount of rain produces a number of issues in Kerala, particularly in urban regions where the drainage system is frequently unable to handle a significant amount of water in such a short duration. Meanwhile, standard flood detection results are inaccurate for complex phenomena and cannot handle enormous quantities of data. In order to overcome those drawbacks and enhance the outcomes of conventional flood detection...
-
Resource constrained neural network training
PublikacjaModern applications of neural-network-based AI solutions tend to move from datacenter backends to low-power edge devices. Environmental, computational, and power constraints are inevitable consequences of such a shift. Limiting the bit count of neural network parameters proved to be a valid technique for speeding up and increasing efficiency of the inference process. Hence, it is understandable that a similar approach is gaining...
-
Impact of Visual Image Quality on Lymphocyte Detection Using YOLOv5 and RetinaNet Algorithms
PublikacjaLymphocytes, a type of leukocytes, play a vital role in the immune system. The precise quantification, spatial arrangement and phenotypic characterization of lymphocytes within haematological or histopathological images can serve as a diagnostic indicator of a particular lesion. Artificial neural networks, employed for the detection of lymphocytes, not only can provide support to the work of histopathologists but also enable better...
-
Speaker Recognition Using Convolutional Neural Network with Minimal Training Data for Smart Home Solutions
PublikacjaWith 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...
-
Predicting emotion from color present in images and video excerpts by machine learning
PublikacjaThis work aims at predicting emotion based on the colors present in images and video excerpts using a machine-learning approach. The purpose of this paper is threefold: (a) to develop a machine-learning algorithm that classifies emotions based on the color present in an image, (b) to select the best-performing algorithm from the first phase and apply it to film excerpt emotion analysis based on colors, (c) to design an online survey...
-
Robust Object Detection with Multi-input Multi-output Faster R-CNN
PublikacjaRecent years have seen impressive progress in visual recognition on many benchmarks, however, generalization to the out-of-distribution setting remains a significant challenge. A state-of-the-art method for robust visual recognition is model ensembling. However, recently it was shown that similarly competitive results could be achieved with a much smaller cost, by using multi-input multi-output architecture (MIMO). In this work,...
-
Robust Object Detection with Multi-input Multi-output Faster R-CNN
PublikacjaRecent years have seen impressive progress in visual recognition on many benchmarks, however, generalization to the out-of-distribution setting remains a significant challenge. A state-of-the-art method for robust visual recognition is model ensembling. However, recently it was shown that similarly competitive results could be achieved with a much smaller cost, by using multi-input multi-output architecture (MIMO). In this work,...
-
Language Models in Speech Recognition
PublikacjaThis chapter describes language models used in speech recognition, It starts by indicating the role and the place of language models in speech recognition. Mesures used to compare language models follow. An overview of n-gram, syntactic, semantic, and neural models is given. It is accompanied by a list of popular software.