Wyszukiwarka
Wyniki wyszukiwania dla: Deep Learning
-
RSS-Based DoA Estimation Using ESPAR Antenna for V2X Applications in 802.11p Frequency Band
PublikacjaIn this paper, we have proposed direction-of arrival (DoA) estimation of incoming signals for V2X applications in 802. 11p frequency band, based on recording of received signal strength (RSS) at electronically steerable parasitic array radiator (ESPAR) antenna's output port. The motivation of the work was to prove that ESPAR antenna used to increase connectivity and security in V2X communication can...
-
Diverse roles, advantages and importance of deep eutectic solvents application in solid and liquid-phase microextraction techniques – A review
PublikacjaDeep eutectic solvents (DESs) are an emerging class of promising green solvents used as an alternative to traditional organic solvents in various scientific fields. The high biodegradability, biocompatibility, eco-friendliness, tunable properties, and presence of active groups in DESs make them the preferred solvent in a variety of solid- and liquid-phase microextraction techniques. Aside from these benefits, the use of DESs in...
-
Why do Open Government Data initiatives fail in developing countries? A root cause analysis of the most prevalent barriers and problems
PublikacjaOpen government data (OGD) include the provision of government data, which have so far been reserved for the provision of public utilities and services, wherein different stakeholders may create value out of the same source. Recently, OGD initiatives around the world have dampened or were found to be inadequate for one or other reasons. The present study seeks to underline the root causes behind these inadequate or stalled initiatives...
-
Accurate Modeling of Antenna Structures by Means of Domain Confinement and Pyramidal Deep Neural Networks
PublikacjaThe importance of surrogate modeling techniques has been gradually increasing in the design of antenna structures over the recent years. Perhaps the most important reason is a high cost of full-wave electromagnetic (EM) analysis of antenna systems. Although imperative in ensuring evaluation reliability, it entails considerable computational expenses. These are especially pronounced when carrying out EM-driven design tasks such...
-
The Revitalization Processes of the Port Structures in Gdynia and Gdansk on the Background of Contemporary Port Changes
PublikacjaTransformations of the port facilities against the modernization of the port structures are present in many city-port centers since more than 50 years. The modernization taking place in the ports located in Gdynia-Gdansk mainly concerns communication availability and adapted to the multimodal technology of transport and transshipment. Developing specialized tech-terminals serving a specific type of load, causes development of the...
-
Catalysts for advanced oxidation processes: Deep eutectic solvents-assisted synthesis – A review
PublikacjaNew catalyst synthesis techniques, including green materials, are extensively studied for heterogeneous photocatalytic advanced oxidation processes (AOPs) on spotlight of sustainable development. Deep eutectic solvents (DESs) started to be used in this field as environmentally friendly alternative to ionic liquids (ILs). During the catalyst synthesis, DESs can act as stabilizers, capping agents, structure directing agents, templates,...
-
Catheter-induced coronary artery and aortic dissections. A study of the mechanisms, risk factors, and propagation causes
PublikacjaBackground: Only the incidence, management, and prognosis of catheter-induced coronary artery and aortic dissections have been systematically studied until now. We sought to evaluate their mechanisms, risk factors, and propagation causes. Methods: Electronic databases containing 76,104 procedures and complication registries from 2000– –2020 were searched and relevant cineangiographic studies adjudicated. Results: Ninety-six dissections...
-
A Perspective on Missing Aspects in Ongoing Purification Research towards Melissa officinalis
PublikacjaMelissa officinalis L. is a medicinal plant used worldwide for ethno-medical purposes. Today, it is grown everywhere; while it is known to originate from Southern Europe, it is now found around the world, from North America to New Zealand. The biological properties of this medicinal plant are mainly related to its high content of phytochemical (bioactive) compounds, such as flavonoids, polyphenolic compounds, aldehydes, glycosides...
-
Underground Water Level Prediction in Remote Sensing Images Using Improved Hydro Index Value with Ensemble Classifier
PublikacjaThe economic sustainability of aquifers across the world relies on accurate and rapid estimates of groundwater storage changes, but this becomes difficult due to the absence of insitu groundwater surveys in most areas. By closing the water balance, hydrologic remote sensing measures offer a possible method for quantifying changes in groundwater storage. However, it is uncertain to what extent remote sensing data can provide an...
-
CONTRASTING MODERNISMS - ARCHITECTURE OF HARBOUR CITIES GDYNIA AND ALTONA
PublikacjaThe presentation of the exhibition “Architect Gustav Oelsner – Light, Air, Colour,”, which took place in Gdynia 1.04-29.05.2011, showed the clinker architecture of Gustav Oelsner in Altona. As a contrast to the white-plastered architecture of Gdynia, it provided an interesting background for the comparison of two different faces of modernism. The most important feature of the aesthetics of modernism was its cosmopolitan character,...
-
Deep convolutional neural network for predicting kidney tumour malignancy
PublikacjaPurpose: According to the statistics, up to 15-20% of removed solid kidney tumors turn out to be benign in postoperative histopathological examination, despite having been identified as malignant by a radiologist. The aim of the research was to limit the number of unnecessary nephrectomies of benign tumors. Methods or Background: We propose a machine-aided diagnostic system for kidney...
-
AITP - AI Thermal Pedestrians Dataset
Dane BadawczeAITP is a pedestrian detection dataset consisting of 9178 annotated thermal images. The training set contains 7801 images on which15448 pedestrians were labeled. The test set has 1377 images on which 2731 objects were marked. All images are in PNG file format (120x160) captured with FLIR Lepton Thermal Camera on the streets of Gdańsk, Poland. All pedestrians...
-
Paweł Nadachowski mgr inż.
Osoby -
Selectivity Tuning by Natural Deep Eutectic Solvents (NADESs) for Extraction of Bioactive Compounds from Cytinus hypocistis—Studies of Antioxidative, Enzyme-Inhibitive Properties and LC-MS Profiles
PublikacjaIn the present study, the extracts of Cytinus hypocistis (L.) L using both traditional solvents (hexane, ethyl acetate, dichloromethane, ethanol, ethanol/water, and water) and natural deep eutectic solvents (NADESs) were investigated in terms of their total polyphenolic contents and antioxidant and enzyme-inhibitive properties. The extracts were found to possess total phenolic and total flavonoid contents in the ranges of 26.47–186.13...
-
Medium-sized cyclic bis(anisylphosphonothioyl)- disulfanes and their corresponding cyclic sulfane-structures and most characteristic reactions
PublikacjaCyclic 8-, 9-, 10-, and 12-membered bis(anisylphosphonothioyl)disulfanes were synthesized. Next, structurally related 7 to 9-membered cis and trans sulfanes were isolated as a result of sulfur atom extrusion from the parent cyclic disulfanes. The results of the desulfurization of the disulfanes were compared to the results obtained for desulfurization of the respective bis(anisylphosphodithioates). Cyclic disulfanes predominantly...
-
A geophysical, geochemical and microbiological study of a newly discovered pockmark with active gas seepage and submarine groundwater discharge (MET1-BH, central Gulf of Gdańsk, southern Baltic Sea)
PublikacjaHigh-resolution bathymetric data were collected with a multi-beam echosounder in the southern part of the Baltic Sea (region MET1, Gulf of Gdańsk) revealing the presence of a 10 m deep and 50 m in diameter pockmark (MET1-BH) on the sea bottom (78.7 m). To date, no such structures have been observed to reach this size in the Baltic Sea. The salinity of the near-bottom water in the pockmark was about 2 PSU (about 31.22 mmol/l...
-
Adam Brzeski dr inż.
Osoby -
Intermolecular Interactions of Edaravone in Aqueous Solutions of Ethaline and Glyceline Inferred from Experiments and Quantum Chemistry Computations
PublikacjaEdaravone, acting as a cerebral protective agent, is administered to treat acute brain infarction. Its poor solubility is addressed here by means of optimizing the composition of the aqueous choline chloride (ChCl)-based eutectic solvents prepared with ethylene glycol (EG) or glycerol (GL) in the three different designed solvents compositions. The slurry method was used for spectroscopic solubility determination in temperatures...
-
Sylwia Majchrowska
Osoby -
Generowanie tekstu z użyciem sieci typu Transformer
PublikacjaOpisano działanie wybranych modeli uczenia maszynowego znajdujących zastosowanie w przetwarzaniu języka naturalnego w szczególności wy- korzystywanych do generowania tekstu. Przedstawiono również model BERT i jego różne wersje, a także praktyczne wykorzystanie modeli typu Transformer. Przedstawiono ich działanie w aplikacji zmieniającej nastrój tekstu w sposób sekwencyjny.
-
Structure and Randomness in Planning and Reinforcement Learning
PublikacjaPlanning in large state spaces inevitably needs to balance the depth and breadth of the search. It has a crucial impact on the performance of a planner and most manage this interplay implicitly. We present a novel method \textit{Shoot Tree Search (STS)}, which makes it possible to control this trade-off more explicitly. Our algorithm can be understood as an interpolation between two celebrated search mechanisms: MCTS and random...
-
Neural network training with limited precision and asymmetric exponent
PublikacjaAlong with an extremely increasing number of mobile devices, sensors and other smart utilities, an unprecedented growth of data can be observed in today’s world. In order to address multiple challenges facing the big data domain, machine learning techniques are often leveraged for data analysis, filtering and classification. Wide usage of artificial intelligence with large amounts of data creates growing demand not only for storage...
-
Evaluation of aspiration problems in L2 English pronunciation employing machine learning
PublikacjaThe approach proposed in this study includes methods specifically dedicated to the detection of allophonic variation in English. This study aims to find an efficient method for automatic evaluation of aspiration in the case of Polish second-language (L2) English speakers’ pronunciation when whole words are analyzed instead of particular allophones extracted from words. Sample words including aspirated and unaspirated allophones...
-
Detecting Apples in the Wild: Potential for Harvest Quantity Estimation
PublikacjaKnowing the exact number of fruits and trees helps farmers to make better decisions in their orchard production management. The current practice of crop estimation practice often involves manual counting of fruits (before harvesting), which is an extremely time-consuming and costly process. Additionally, this is not practicable for large orchards. Thanks to the changes that have taken place in recent years in the field of image...
-
CMGNet: Context-aware middle-layer guidance network for salient object detection
PublikacjaSalient object detection (SOD) is a critical task in computer vision that involves accurately identifying and segmenting visually significant objects in an image. To address the challenges of gridding issues and feature...
-
Finding the Right Solvent: A Novel Screening Protocol for Identifying Environmentally Friendly and Cost-Effective Options for Benzenesulfonamide
PublikacjaThis study investigated the solubility of benzenesulfonamide (BSA) as a model compound using experimental and computational methods. New experimental solubility data were collected in the solvents DMSO, DMF, 4FM, and their binary mixtures with water. The predictive model was constructed based on the best-performing regression models trained on available experimental data, and their hyperparameters were optimized using a newly...
-
Exploring the Solubility Limits of Edaravone in Neat Solvents and Binary Mixtures: Experimental and Machine Learning Study
PublikacjaThis study explores the edaravone solubility space encompassing both neat and binary dissolution media. Efforts were made to reveal the inherent concentration limits of common pure and mixed solvents. For this purpose, the published solubility data of the title drug were scrupulously inspected and cured, which made the dataset consistent and coherent. However, the lack of some important types of solvents in the collection called...
-
Bimodal Emotion Recognition Based on Vocal and Facial Features
PublikacjaEmotion recognition is a crucial aspect of human communication, with applications in fields such as psychology, education, and healthcare. Identifying emotions accurately is challenging, as people use a variety of signals to express and perceive emotions. In this study, we address the problem of multimodal emotion recognition using both audio and video signals, to develop a robust and reliable system that can recognize emotions...
-
Towards neural knowledge DNA
PublikacjaIn this paper, we propose the Neural Knowledge DNA, a framework that tailors the ideas underlying the success of neural networks to the scope of knowledge representation. Knowledge representation is a fundamental field that dedicates to representing information about the world in a form that computer systems can utilize to solve complex tasks. The proposed Neural Knowledge DNA is designed to support discovering, storing, reusing,...
-
Wykorzystanie sieci neuronowych do syntezy mowy wyrażającej emocje
PublikacjaW niniejszym artykule przedstawiono analizę rozwiązań do rozpoznawania emocji opratych na mowie i możliwości ich wykprzystania w syntezie mowy z emocjami stosując do tego celu sieci neuronowe. Wskazano również przydatnośc parametrów typowo stosowanych do rozpoznawania mowy w detekcji emocji w śpiewie i rozróżnianiu tych emocji w obu przypadkach. Przedstawiono aktualne rozwiązania dotyczące rozpoznawania emocji w mowie i metod syntezy...
-
The Neural Knowledge DNA Based Smart Internet of Things
PublikacjaABSTRACT The Internet of Things (IoT) has gained significant attention from industry as well as academia during the past decade. Smartness, however, remains a substantial challenge for IoT applications. Recent advances in networked sensor technologies, computing, and machine learning have made it possible for building new smart IoT applications. In this paper, we propose a novel approach: the Neural Knowledge DNA based Smart Internet...
-
Analyzing the Effectiveness of the Brain–Computer Interface for Task Discerning Based on Machine Learning
PublikacjaThe aim of the study is to compare electroencephalographic (EEG) signal feature extraction methods in the context of the effectiveness of the classification of brain activities. For classification, electroencephalographic signals were obtained using an EEG device from 17 subjects in three mental states (relaxation, excitation, and solving logical task). Blind source separation employing independent component analysis (ICA) was...
-
A Novel IoT-Perceptive Human Activity Recognition (HAR) Approach Using Multi-Head Convolutional Attention
PublikacjaTogether with fast advancement of the Internet of Things (IoT), smart healthcare applications and systems are equipped with increasingly more wearable sensors and mobile devices. These sensors are used not only to collect data, but also, and more importantly, to assist in daily activity tracking and analyzing of their users. Various human activity recognition (HAR) approaches are used to enhance such tracking. Most of the existing...
-
Toward Intelligent Vehicle Intrusion Detection Using the Neural Knowledge DNA
PublikacjaIn this paper, we propose a novel intrusion detection approach using past driving experience and the neural knowledge DNA for in-vehicle information system security. The neural knowledge DNA is a novel knowledge representation method designed to support discovering, storing, reusing, improving, and sharing knowledge among machines and computing systems. We examine our approach for classifying malicious vehicle control commands...
-
Artificial Intelligence in the Diagnosis of Onychomycosis—Literature Review
PublikacjaOnychomycosis is a common fungal nail infection that is difficult to diagnose due to its similarity to other nail conditions. Accurate identification is essential for effective treatment. The current gold standard methods include microscopic examination with potassium hydroxide, fungal cultures, and Periodic acid-Schiff biopsy staining. These conventional techniques, however, suffer from high turnover times, variable sensitivity,...
-
Machine-aided detection of SARS-CoV-2 from complete blood count
PublikacjaThe current gold standard for SARS-CoV-2 detection methods lacks the functionality to perform population screening. Complete blood count (CBC) tests are a cost-effective way to reach a wide range of people – e.g. according to the data of the Central Statistical Office of Poland from 2016, there are 3,000 blood diagnostic laboratories in Poland, and 46% of Polish people have at least one CBC test per year. In our work, we show...
-
COVID-19 severity forecast based on machine learning and complete blood count data
PublikacjaProper triage of COVID-19 patients is a key factor in eective case management, especially with limited and insucient resources. In this paper, we propose a machine-aided diagnostic system to predict how badly a patient with COVID-19 will develop disease. The prognosis of this type is based on the parameters of commonly used complete blood count tests, which makes it possible to obtain data from a wide range of patients.We chose...
-
COVID-19 severity forecast based on machine learning and complete blood count data
PublikacjaProper triage of COVID-19 patients is a key factor in eective case management, especially with limited and insucient resources. In this paper, we propose a machine-aided diagnostic system to predict how badly a patient with COVID-19 will develop disease. The prognosis of this type is based on the parameters of commonly used complete blood count tests, which makes it possible to obtain data from a wide range of patients.We chose...
-
Computer-Aided Diagnosis of COVID-19 from Chest X-ray Images Using Hybrid-Features and Random Forest Classifier
PublikacjaIn recent years, a lot of attention has been paid to using radiology imaging to automatically find COVID-19. (1) Background: There are now a number of computer-aided diagnostic schemes that help radiologists and doctors perform diagnostic COVID-19 tests quickly, accurately, and consistently. (2) Methods: Using chest X-ray images, this study proposed a cutting-edge scheme for the automatic recognition of COVID-19 and pneumonia....
-
Systematic Literature Review on Click Through Rate Prediction
PublikacjaThe ability to anticipate whether a user will click on an item is one of the most crucial aspects of operating an e-commerce business, and clickthrough rate prediction is an attempt to provide an answer to this question. Beginning with the simplest multilayer perceptrons and progressing to the most sophisticated attention networks, researchers employ a variety of methods to solve this issue. In this paper, we present the findings...
-
Respiratory Rate Estimation Based on Detected Mask Area in Thermal Images
PublikacjaThe popularity of non-contact methods of measuring vital signs, particularly respiratory rate, has increased during the SARS-COV-2 pandemic. Breathing parameters can be estimated by analysis of temperature changes observed in thermal images of nostrils or mouth regions. However, wearing virus-protection face masks prevents direct detection of such face regions. In this work, we propose to use an automatic mask detection approach...
-
From Scores to Predictions in Multi-Label Classification: Neural Thresholding Strategies
PublikacjaIn this paper, we propose a novel approach for obtaining predictions from per-class scores to improve the accuracy of multi-label classification systems. In a multi-label classification task, the expected output is a set of predicted labels per each testing sample. Typically, these predictions are calculated by implicit or explicit thresholding of per-class real-valued scores: classes with scores exceeding a given threshold value...
-
Zastosowanie sieci neuronowych w cyfrowej syntezie dźwięku
PublikacjaRozwój technik związanych z uczeniem maszynowym umożliwia nowe podejście i nowe definiowanie wielu dotychczasowych problemów. Heurystyczne algorytmy stosowane do problemów takich jak klasyfikacja danych w postaci wektorów cech, czy wyróżnianie grup obiektów o podobnych własnościach mogą znaleźć także zastosowanie w takich dziedzinach jak analiza i synteza dźwięków muzycznych. W referacie przybliżone zostały podstawowe zasady projektowania...
-
Adding Intelligence to Cars Using the Neural Knowledge DNA
PublikacjaIn this paper we propose a Neural Knowledge DNA based framework that is capable of learning from the car’s daily operation. The Neural Knowledge DNA is a novel knowledge representation and reasoning approach designed to support discovering, storing, reusing, improving, and sharing knowledge among machines and computing devices. We examine our framework for drivers' classification based on their driving behaviour. The experimental...
-
Automatic Clustering of EEG-Based Data Associated with Brain Activity
PublikacjaThe aim of this paper is to present a system for automatic assigning electroencephalographic (EEG) signals to appropriate classes associated with brain activity. The EEG signals are acquired from a headset consisting of 14 electrodes placed on skull. Data gathered are first processed by the Independent Component Analysis algorithm to obtain estimates of signals generated by primary sources reflecting the activity of the brain....
-
CNN Architectures for Human Pose Estimation from a Very Low Resolution Depth Image
PublikacjaThe paper is dedicated to proposing and evaluating a number of convolutional neural network architectures for calculating a multiple regression on 3D coordinates of human body joints tracked in a single low resolution depth image. The main challenge was to obtain a high precision in case of a noisy and coarse scan of the body, as observed by a depth sensor from a large distance. The regression network was expected to reason about...
-
Very low resolution depth images of 200,000 poses
Dane BadawczeA dataset represents simulated images of depth sensor seeing a single human pose, performing 200,000 random gestures. The depth images as vectors of pixels are stored with ground truth positions of every relevant joint.
-
Tagged images with bees
Dane BadawczeImages taken from bee hive with tagged bees. The images are prepared for training yolo5 deep neural network (supplied with the data).
-
Tagged images with bees 2
Dane BadawczeImages taken from bee hive with tagged bees.
-
Dawid Wieczerzak mgr inż.
Osoby