Search
Filters
total: 591
-
Catalog
Search results for: semantic segmentation
-
Melanoma skin cancer detection using mask-RCNN with modified GRU model
PublicationIntroduction: Melanoma Skin Cancer (MSC) is a type of cancer in the human body; therefore, early disease diagnosis is essential for reducing the mortality rate. However, dermoscopic image analysis poses challenges due to factors such as color illumination, light reflections, and the varying sizes and shapes of lesions. To overcome these challenges, an automated framework is proposed in this manuscript. Methods: Initially, dermoscopic...
-
Small Urban Hacks - Big Impact! Tackling major urban challenges through acupunctural smallness
PublicationSmall urban hacks, acupunctural action and process-oriented planning approaches might appear to address quite a socio-romantic attitude towards our urban environments. In this chapter, our aim is to remedy such a biased view, demonstrating the impact and potential of smallness in the context of major urban challenges. Small urban hacks and their multi-faceted and creativity-driven approaches of small is beautiful are selected from...
-
Composite Materials Based on Silicon Oxycarbide as Anodes for Lithium-Ion Batteries
PublicationIn this work, the properties of binary SiOC/graphite and SiOC/tin, as well as ternary SiOC/graphite/tin obtained from various preceramic precursors are described. During the first step, the materials were synthesized using various techniques such as sol-gel and hydrosilylation. To prevent sedimentation and agglomeration of graphite particles during the gelation stage without using surfactants and thickeners, a new gelation technique...
-
Application of H2O2 to optimize ammonium removal from domestic wastewater
PublicationThe paper presents the results of application of hydrogen peroxide (H2O2) for the optimization of the effects of ammonia nitrogen removal from domestic wastewater. The investigations were carried out at a model wastewater treatment plant consisting of a preliminary sedimentation tank and a sand filter with a horizontal flow of wastewater at a constant hydraulic load of 1.44 L/day. The efficiency of ammonia nitrogen removal was...
-
The Analysis of Vodka: A Review Paper
PublicationVodka is the most popular alcoholic beverage in Poland, Russia and other Eastern European countries, made from ethyl alcohol of agricultural origin that has been produced via fermentation of potatoes, grains or other agricultural products. Despite distillation and multiple filtering, it is not possible to produce 100 % ethanol. The solution with a minimum ethanol content of 96 %, which is used to produce vodkas, also contains trace amounts...
-
High precision and accuracy using low cost GNSS receivers and supporting technologies
PublicationThis chapter focuses on methods and techniques of positioning, based on the highly accurate and precise Global Navigation Satellite System (GNSS), which are available at a relatively low price. In this context, a comparison of different positioning methods provided by the free and open source software (FOSS) package called RTKLIB is given. Other aspects related to price reduction are also considered, including availability and...
-
Spiral Search Grasshopper Features Selection with VGG19-ResNet50 for Remote Sensing Object Detection
PublicationRemote sensing object detection plays a major role in satellite imaging and is required in various scenarios such as transportation, forestry, and the ocean. Deep learning techniques provide efficient performance in remote sensing object detection. The existing techniques have the limitations of data imbalance, overfitting, and lower efficiency in detecting small objects. This research proposes the spiral search grasshopper (SSG)...
-
Wytrzymałość pętli wplatanych na linach podwójnie plecionych
PublicationCechą wyróżniającą statki żaglowe z grona innych obiektów pływających są żagle. To cecha widoczna, za którą kryją się mniej romantyczne elementy, takie jak maszty, liny i osprzęt. Rozpostarcie białych płócien na maszcie i następnie żeglowanie wymaga sprawnego operowania nimi, co wiąże się z doborem odpowiedniego ich zestawu, ułożenia i napięcia. To maszty są kręgosłupem takielunku, a liny jego mięśniami i ścięgnami. Do poprawnego...
-
Physics augmented classification of fNIRS signals
PublicationBackground. Predictive classification favours performance over semantics. In traditional predictive classification pipelines, feature engineering is often oblivious to the underlying phenomena. Hypothesis. In applied domains such as functional Near Infrared Spectroscopy (fNIRS), the exploitation of physical knowledge may improve the discriminative quality of our observation set. Aims. Give exemplary evidence that intervening the...
-
An Analysis of Contextual Aspects of Conceptualization: A Case Study and Prospects
PublicationIn this chapter we present a new approach to development of modularized knowledge bases. We argue that modularization should start from the very beginning of modeling, i.e. from the conceptualization stage. To make this feasible, we propose to exploit a context-oriented, semantic approach to modularization. This approach is based on the Structural Interpretation Model (SIM) presented earlier elsewhere. In the first part of thischapter...
-
A Parallel Corpus-Based Approach to the Crime Event Extraction for Low-Resource Languages
PublicationThese days, a lot of crime-related events take place all over the world. Most of them are reported in news portals and social media. Crime-related event extraction from the published texts can allow monitoring, analysis, and comparison of police or criminal activities in different countries or regions. Existing approaches to event extraction mainly suggest processing texts in English, French, Chinese, and some other resource-rich...
-
Ontological Modeling for Contextual Data Describing Signals Obtained from Electrodermal Activity for Emotion Recognition and Analysis
PublicationMost of the research in the field of emotion recognition is based on datasets that contain data obtained during affective computing experiments. However, each dataset is described by different metadata, stored in various structures and formats. This research can be counted among those whose aim is to provide a structural and semantic pattern for affective computing datasets, which is an important step to solve the problem of data...
-
Distributed Architectures for Intensive Urban Computing: A Case Study on Smart Lighting for Sustainable Cities
PublicationNew information and communication technologies have contributed to the development of the smart city concept. On a physical level, this paradigm is characterised by deploying a substantial number of different devices that can sense their surroundings and generate a large amount of data. The most typical case is image and video acquisition sensors. Recently, these types of sensors are found in abundance in urban spaces and are responsible...
-
Study of Statistical Text Representation Methods for Performance Improvement of a Hierarchical Attention Network
PublicationTo 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...
-
Degradation of xylose using a microbial fuel cell
PublicationIt is generally known, that many kind of microorganisms are capable of using carbohydrates as a source of carbon and energy in an environment. The biodegradation process of monosaccharides from pentoses (in this case- racemic mixture of D - and L – xylose) is an immense opportunity for an entire reduction of biological contamination to neutral compounds through MFC. The process is occurred in a single-chamber MFC, which is contained...
-
Removal of persistant organic pollutants from landfill leachates treated in three constructed wetland systems
PublicationThe objective of the study was assessment of occurrence and removal of two groups of persistent organic pollutants: polycyclic aromatic hydrocarbons (PAHs) and polychlorinated biphenyls (PCBs) in landfill leachate (LL) treated in three constructed wetland systems (CWs) of different construction and flow regime. Two subsurface flow systems (SSF) were analyzed: one with horizontal flow and the second one consisting of two vertical...
-
Efficiency of Artificial Intelligence Methods for Hearing Loss Type Classification: an Evaluation
PublicationThe 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...
-
An Integrated Approach to an Assessment of Bottlenecks for Navigation on Riverine Waterways
PublicationWater transport, both sea and inland, is the cheapest, least invasive, and safest option for non-standard loads; hence, it is important to increase the percentage share of inland waterway transport on the rivers of Central and Eastern Europe. Transporting cargo is particularly difficult on shallow waterways because rivers overloaded with sediment determine the vertical parameters on inland waterways. A ship’s safe manoeuvrability...
-
Femtosecond laser ablated trench array for improving performance of commercial solid oxide cell
PublicationThe performance of electrode-supported solid oxide cells (SOCs) is limited adversely by gas diffusion impedance in thick and porous support. This work focuses on the improvement of gas transport properties of commercial Ni-YSZ anode-supported SOFC by femtosecond laser-based micromachining where micro-holes of identical depth but different hole separations pitches with minimal heated affected zones were imposed. The polarization...
-
Clothes Detection and Classification Using Convolutional Neural Networks
PublicationIn this paper we describe development of a computer vision system for accurate detection and classification of clothes for e-commerce images. We present a set of experiments on well established architectures of convolutional neural networks, including Residual networks, SqueezeNet and Single Shot MultiBox Detector (SSD). The clothes detection network was trained and tested on DeepFashion dataset, which contains box annotations...
-
Extractive detoxification of feedstocks for the production of biofuels using new hydrophobic deep eutectic solvents – Experimental and theoretical studies
PublicationThe paper presents a synthesis of novel hydrophobic deep eutectic solvents (DESs) composed of natural components, which were used for removal of furfural (FF) and 5-hydroxymethylfurfural (HMF) from lignocellulosic hydrolysates. The main physicochemical properties of DESs were determined, followed by explanation of the DES formation mechanism, using 1H NMR, 13C NMR and FT-IR analysis and density functional theory (DFT). The most...
-
Robustness in Compressed Neural Networks for Object Detection
PublicationModel compression techniques allow to significantly reduce the computational cost associated with data processing by deep neural networks with only a minor decrease in average accuracy. Simultaneously, reducing the model size may have a large effect on noisy cases or objects belonging to less frequent classes. It is a crucial problem from the perspective of the models' safety, especially for object detection in the autonomous driving...
-
How Chain Transfer Leads to a Uniform Polymer Particle Morphology and Prevents Reactor Fouling
PublicationABSTRACT: The effect of adding diethyl zinc as a chain transfer agent during the polymerization of propylene in heptane performed at 80 °C was studied. Although it was expected that the chain transfer would stop after precipitation of the polymer, the polymer molecular weight continued to increase throughout the whole of the polymerization. The presence of diethyl zinc had an additional effect that the polymerizations were devoid...
-
SkinDepth - synthetic 3D skin lesion database
Open Research DataSkinDepth is the first synthetic 3D skin lesion database. The release of SkinDepth dataset intends to contribute to the development of algorithms for:
-
Heptaene macrolides biosynthesis by Streptomyces species
PublicationPolyene macrolides are one of the groups of secondary metabolites, generated by microorganisms belonging to the Streptomyces genus. These compounds, containing 3 - 7 conjugated double bonds systems in their molecules exhibit high antifungal activity against a broad spectrum of fungal pathogens with heptaenes demonstrating the highest antifungal potential. At the large extent, efficiency of biosynthesis of these natural products...
-
Study of Nanohydroxyapatite Coatings Prepared by the Electrophoretic Deposition Method at Various Voltage and Time Parameters
PublicationThe aim of the work is to compare the properties of nanohydroxyapatite coatings obtained using the electrophoretic deposition method (EDP) at 10 V, 20 V, and 30 V, and with deposit times of 2 and 5 min. The primary sedimentation was used to minimize the risk of the formation of particle agglomerates on the sample surface. Evaluation of the coating was performed by using a Scanning Electron Microscope (SEM), Energy-Dispersive Spectroscopy...
-
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...
-
A CNN based coronavirus disease prediction system for chest X-rays
PublicationCoronavirus disease (COVID-19) proliferated globally in early 2020, causing existential dread in the whole world. Radiography is crucial in the clinical staging and diagnosis of COVID-19 and offers high potential to improve healthcare plans for tackling the pandemic. However high variations in infection characteristics and low contrast between normal and infected regions pose great challenges in preparing radiological reports....
-
Identification of category associations using a multilabel classifier
PublicationDescription of the data using categories allows one to describe it on a higher abstraction level. In this way, we can operate on aggregated groups of the information, allowing one to see relationships that do not appear explicit when we analyze the individual objects separately. In this paper we present automatic identification of the associations between categories used for organization of the textual data. As experimental data...
-
Grupa zarządzania wiedzą
Research TeamsGrupa Zarządzania Wiedzą na Politechnice Gdańskiej jest grupą badawczo-rozwojową skupiającą się na obszarach związanych z zarządzaniem wiedzą i informacją. Naszym priorytetem jest opracowanie zestawu narzędzi i metod umożliwiających przetwarzanie i analizowanie dużych ilości informacji przechowywanych w zasobach WWW. Grupa specjalizuje się w ontologicznych metodach reprezentacji i analizy wiedzy, która zapisana jest w sposób ustrukturalizowany...
-
Physicochemical and Volatile Compounds Analysis of Fruit Wines Fermented with Saccharomyces cerevisiae: FTIR and Microscopy Study with Focus on Anti-Inflammatory Potential
PublicationThe growing trend in fruit wine production reflects consumers’ interest in novel, diverse drinking experiences and the increasing demand for healthier beverage options. Fruit wines made from kiwi, pomegranates, and persimmons fermented using S. bayanus Lalvin strain EC1118 demonstrate the versatility of winemaking techniques. Kiwifruit, persimmon, and pomegranate wines were analyzed using HPLC and GC-TOFMS analyses to determine...
-
Optimization of Saccharification Conditions of Lignocellulosic Biomass under Alkaline Pre-Treatment and Enzymatic Hydrolysis
PublicationPre-treatment is a significant step in the production of second-generation biofuels from waste lignocellulosic materials. Obtaining biofuels as a result of fermentation processes requires appropriate pre-treatment conditions ensuring the highest possible degree of saccharification of the feed material. An influence of the following process parameters were investigated for alkaline pre-treatment of Salix viminalis L.: catalyst concentration...
-
CMGNet: Context-aware middle-layer guidance network for salient object detection
PublicationSalient 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...
-
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...
-
Environmental impacts of food waste management technologies: A critical review of life cycle assessment (LCA) studies
PublicationFood waste is a serious global problem. Therefore, it is essential to reduce food waste and adopt recycling strategies to minimize its environmental impacts. However, conventional waste disposal methods emit harmful gases such as dioxin, CH4, N2O, and NH3, which contaminate the air and water resources. This work reviews the environmental consequences of food waste based on lifecycle assessment (LCA) techniques using methods such...
-
Partitioning of heavy metals in sub-surface flow treatment wetlands receiving high-strength wastewater
PublicationThe retention of heavy metals at two pilot-scale treatment wetlands (TWs), consisting of two vertical flow beds (VSSF) followed by a horizontal flow bed (HSSF) was studied. The TWs received highstrength wastewater: reject waters from sewage sludge centrifugation (RW) and landfill leachate (LL). The concentrations of metals: Fe, Mn, Zn, Al, Pb, Cu, Cd, Co, Ni were measured in treated wastewater, substrate of the beds and in plant...
-
Modifications to the anaerobic digestion model no. 1 (ADM1) for enhanced understanding and application of the anaerobic treatment processes – A comprehensive review
PublicationAnaerobic digestion (AD) is a promising method for the recovery of resources and energy from organic wastes. Correspondingly, AD modelling has also been developed in recent years. The International Water Association (IWA) Anaerobic Digestion Model No. 1 (ADM1) is currently the most commonly used structured AD model. However, as substrates become more complex and our understanding of the AD mechanism grows, both systematic and specific...
-
Thermal degradation of polylactic acid (PLA)/polyhydroxybutyrate (PHB) blends: A systematic review
PublicationPolylactic acid (PLA) and polyhydroxybutyrate (PHB) are two biopolyesters obtained from renewable resources like corn or sugar under bacterial fermentation. PLA is the most widely used biopolymer in diverse applications. Addition of PHB to PLA can improves the crystallinity of PLA, and thereby its mechanical strength. However, both PLA and PHB suffer from poor thermal stability, which limits their potential industrial application....
-
Hybrid systems using hydrodynamic cavitation/ultrasound/Fenton processes for effective treatment of wastewater
PublicationThe present situation of rapid growth in industrialization generates complex recalcitrant pollutants that are challenging to degrade by conventional wastewater treatment processes. The new generation pollutants such as non-metals in cosmetics or household cleaning chemicals and radioactive compounds which are recalcitrant are the emerging threat to the ecosystem. The headstrong micro and macro pollutants present in wastewater are...
-
Laser granulometer as an useful tool for selection of appropriate membranes used in the MIEX®DOC-UF/MF hybrid process
PublicationIn the study, particle size distribution of the MIEX® resin was presented. Such analyses enable to determinate whether presence of fine resin fraction may be the reason for unfavorable membrane blocking during water purification by the hybrid MIEX®DOC-microfiltration/ultrafiltration systems. Granulometric analysis of resin grains using the laser diffraction particle size analyzer (laser granulometer) was carried out as well as...
-
The Use of Organic Coagulants in the Primary Precipitation Process at Wastewater Treatment Plants
PublicationMeasurements for determining the effect of chemically enhanced primary treatment (CEPT) on the efficiency of pollutant removal from wastewater were carried out using conventional inorganic coagulants PIX113 with polymer A110 (Kemipol, Police, Poland) and unconventional cationic organic coagulants Cofloc (Attana, Coalville, UK) C29510 (Kemipol, Police, Poland) and Sedifloc 575 (3F Chimica, Sandrigo, Italy). The average removal efficiency...
-
Application of the Anammox Process for Treatment of Liquid Phase Digestate
PublicationThe liquid phase of the digestate (LPD) contains a relatively high concentration of nitrogen, with total ammonium nitrogen being the dominant form of nitrogen, as well as other essential nutrients such as phosphorus and potassium. Consequently, it must be treated before it is released into the environment. However, there are no reports of co-purification of LPD in the anammox process in sequencing batch reactor with granular sludge,...
-
Convolutional Neural Networks for C. Elegans Muscle Age Classification Using Only Self-Learned Features
PublicationNematodes Caenorhabditis elegans (C. elegans) have been used as model organisms in a wide variety of biological studies, especially those intended to obtain a better understanding of aging and age-associated diseases. This paper focuses on automating the analysis of C. elegans imagery to classify the muscle age of nematodes based on the known and well established IICBU dataset. Unlike many modern classification methods, the proposed...
-
Vident-real: an intra-oral video dataset for multi-task learning
Open Research DataWe introduce Vident-real, a large dataset of 100 video sequences of intra-oral scenes from real conservative dental treatments performed at the Medical University of Gdańsk, Poland. The dataset can be used for multi-task learning methods including:
-
Automatic Threat Detection for Historic Buildings in Dark Places Based on the Modified OptD Method
PublicationHistoric buildings, due to their architectural, cultural, and historical value, are the subject of preservation and conservatory works. Such operations are preceded by an inventory of the object. One of the tools that can be applied for such purposes is Light Detection and Ranging (LiDAR). This technology provides information about the position, reflection, and intensity values of individual points; thus, it allows for the creation...
-
Mutagenic and Carcinogenic Compounds in Food
PublicationFood is a major environmental human cancer risk factor. One of the reasons for this is that food products contain substances that exhibit mutagenic and carcinogenic potential which may induce the transformation of normal somatic cells into cancerous cells. These compounds occur in food as a result of microbial contaminations (mycotoxins produced by molds), are generated from natural food components upon processing (e.g. heterocyclic...
-
Treatment of landfill leachate by constructed wetlands: three case studies
PublicationThe performance of three CW systems treating landfill leachate, two located in northern Poland (Szadółki near Gdańsk and Gatka near Miastko) and one in southern Sweden (Örebro), is discussed. The CWs differ in size, hydraulic regime, type of hydrophytic plants and type of leachate pre-treatment before discharging to the CW. The CW in Szadółki consists of two parallel beds with sub-surface, horizontal flow of leachate (HSSF) planted...
-
Current advances in membrane processing of wines: A comprehensive review
PublicationBackground Membrane-based operations, especially pressure-driven membrane operations, are today well-established procedures for various applications in the wine industry thanks to their intrinsic properties and undoubted advantages over traditional methods. Emerging membrane processes, such as pervaporation, electrodialysis and osmotic distillation, forward osmosis, membrane contactors, offer new and interesting perspectives to...
-
Computer-Aided Detection of Hypertensive Retinopathy Using Depth-Wise Separable CNN
PublicationHypertensive retinopathy (HR) is a retinal disorder, linked to high blood pressure. The incidence of HR-eye illness is directly related to the severity and duration of hypertension. It is critical to identify and analyze HR at an early stage to avoid blindness. There are presently only a few computer-aided systems (CADx) designed to recognize HR. Instead, those systems concentrated on collecting features from many retinopathy-related...
-
Three-dimensional numerical investigation of hybrid nanofluids in chain microchannel under electrohydrodynamic actuator
PublicationEnergy efficiency enhancement methods have received considerable attentionwithin the industry and scientific community, owing to the rising concern ofglobal energy sustainability. The present article attempts to scrutinize the effectsof electrohydrodynamics and nanofluids on the rate of heat transfer and fluidflow in the 3-D chain microchannels. Improved heat exchangers (e.g., chainmicrochannel) would have a key role in increasing...