Search
Filters
total: 2345
filtered: 278
Search results for: DATASET FEATURES, DATASET PROFILING VOCABULARIES
-
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...
-
Impact of optimization of ALS point cloud on classification
PublicationAirborne laser scanning (ALS) is one of the LIDAR technologies (Light Detection and Ranging). It provides information about the terrain in form of a point cloud. During measurement is acquired: spatial data (object’s coordinates X, Y, Z) and collateral data such as intensity of reflected signal. The obtained point cloud is typically applied for generating a digital terrain model (DTM) and a digital surface model (DSM). For DTM...
-
Fault diagnosis of marine 4-stroke diesel engines using a one-vs-one extreme learning ensemble
PublicationThis paper proposes a novel approach for intelligent fault diagnosis for stroke Diesel marine engines, which are commonly used in on-road and marine transportation. The safety and reliability of a ship's work rely strongly on the performance of such an engine; therefore, early detection of any type of failure that affects the engine is of crucial importance. Automatic diagnostic systems are of special importance because they can...
-
An Analysis of Neural Word Representations for Wikipedia Articles Classification
PublicationOne of the current popular methods of generating word representations is an approach based on the analysis of large document collections with neural networks. It creates so-called word-embeddings that attempt to learn relationships between words and encode this information in the form of a low-dimensional vector. The goal of this paper is to examine the differences between the most popular embedding models and the typical bag-of-words...
-
ELECTRICAL CONDUCTIVITY AND pH IN SURFACE WATER AS TOOL FOR IDENTIFICATION OF CHEMICAL DIVERSITY
PublicationIn the present study, the creeks and lakes located at the western shore of Admiralty Bay were analysed. The impact of various sources of water supply was considered, based on the parameters of temperature, pH and specific electrolytic conductivity (SEC25). All measurements were conducted during a field campaign in January-February 2017. A multivariate dataset was also created and a biplot of SEC25 and pH of the investigated waters...
-
Super-resolved Thermal Imagery for High-accuracy Facial Areas Detection and Analysis
PublicationIn this study, we evaluate various Convolutional Neural Networks based Super-Resolution (SR) models to improve facial areas detection in thermal images. In particular, we analyze the influence of selected spatiotemporal properties of thermal image sequences on detection accuracy. For this purpose, a thermal face database was acquired for 40 volunteers. Contrary to most of existing thermal databases of faces, we publish our dataset...
-
Fusion-based Representation Learning Model for Multimode User-generated Social Network Content
PublicationAs mobile networks and APPs are developed, user-generated content (UGC), which includes multi-source heterogeneous data like user reviews, tags, scores, images, and videos, has become an essential basis for improving the quality of personalized services. Due to the multi-source heterogeneous nature of the data, big data fusion offers both promise and drawbacks. With the rise of mobile networks and applications, UGC, which includes...
-
Forecasting risks and challenges of digital innovations
PublicationForecasting and assessment of societal risks related to digital innovation systems and services is an urgent problem, because these solutions usually contain artificial intelligence algorithms which learn using data from the environment and modify their behaviour much beyond human control. Digital innovation solutions are increasingly deployed in transport, business and administrative domains, and therefore, if abused by a malicious...
-
Spatiotemporal Assessment of Satellite Image Time Series for Land Cover Classification Using Deep Learning Techniques: A Case Study of Reunion Island, France
PublicationCurrent 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...
-
Detecting Apples in the Wild: Potential for Harvest Quantity Estimation
PublicationKnowing 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...
-
Enhancing Renal Tumor Detection: Leveraging Artificial Neural Networks in Computed Tomography Analysis
PublicationRenal cell carcinoma is one of the most common cancers in Europe, with a total incidence rate of 18.4 cases per 100 000 population. There is currently significant overdiagnosis (11% to 30.9%) at times of planned surgery based on radiological studies. The purpose of this study was to create an artificial neural network (ANN) solution based on computed tomography (CT) images as an additional tool to improve the differentiation of...
-
How do responsible universities perceive their social engagement? In search of signs of Creating Shared Value by the University
PublicationObjectives: University social responsibility still lacks legitimisation and is perceived as a burden that hinders academics from doing research and teaching. Creating Shared Value by the University may serve as a tool to motivate universities to engage in initiatives for society, as this is beneficial for both parties. Yet, some researchers perceive the creation of economic value as inappropriate for academia. Thus, it was interesting...
-
Comparative study on total nitrogen prediction in wastewater treatment 1 plant and effect of various feature selection methods on machine learning algorithms performance
PublicationWastewater characteristics prediction in wastewater treatment plants (WWTPs) is valuable and can reduce the number of sampling, energy, and cost. Feature Selection (FS) methods are used in the pre-processing section for enhancing the model performance. This study aims to evaluate the effect of seven different FS methods (filter, wrapper, and embedded methods) on enhancing the prediction accuracy for total nitrogen (TN) in the WWTP...
-
Towards Scalable Simulation of Federated Learning
PublicationFederated learning (FL) allows to train models on decentralized data while maintaining data privacy, which unlocks the availability of large and diverse datasets for many practical applications. The ongoing development of aggregation algorithms, distribution architectures and software implementations aims for enabling federated setups employing thousands of distributed devices, selected from millions. Since the availability of...
-
Reducing Monitoring Costs in Industrially Contaminated Rivers: Cluster and Regression Analysis Approach
PublicationMonitoring contamination in river water is an expensive procedure, particularly for developing countries where pollution is a significant problem. This study was conducted to provide a pollution monitoring strategy that reduces the cost of laboratory analysis. The new monitoring strategy was designed as a result of cluster and regression analysis on field data collected from an industrially influenced river. Pollution sources in...
-
Metoda OptD do redukcji danych w opracowaniu wyników pomiarów linii elektroenergetycznych
PublicationSkaning laserowy to technologia dostarczająca we względnie krótkim czasie dużą ilość danych pomiarowych. Jest to zarazem pozytywna jak i negatywna cecha tej technologii. Z jednej strony w wyniku skaningu otrzymuje się dane, które szczegółowo odzwierciedlają pomierzony obiekt. Z drugiej strony trudność sprawia przetwarzanie takiej ilości danych i nie zawsze wszystkie dane ze skaningu są niezbędne do realizacji wybranego zadania....
-
Application of COSMO-RS-DARE as a Tool for Testing Consistency of Solubility Data: Case of Coumarin in Neat Alcohols
PublicationCoumarin is a naturally occurring lactone-type benzopyrone with various applications in the pharmaceutical, food, perfume, and cosmetics industries. This hydrophobic compound is poorly soluble in water but dissolves well in protic organic solvents such as alcohols. Despite the extensive use of coumarin, there are only a few reports documenting its solubility in organic solvents, and some reported data are incongruent, which...
-
Forecasting energy consumption and carbon dioxide emission of Vietnam by prognostic models based on explainable machine learning and time series
PublicationThis study assessed the usefulness of algorithms in estimating energy consumption and carbon dioxide emissions in Viet- nam, in which the training dataset was used to train the models linear regression, random forest, XGBoost, and AdaBoost, allowing them to comprehend the patterns and relationships between population, GDP, and carbon dioxide emissions, energy consumption. The results revealed that random forest, XGBoost, and AdaBoost...
-
Concurrent Video Denoising and Deblurring for Dynamic Scenes
PublicationDynamic scene video deblurring is a challenging task due to the spatially variant blur inflicted by independently moving objects and camera shakes. Recent deep learning works bypass the ill-posedness of explicitly deriving the blur kernel by learning pixel-to-pixel mappings, which is commonly enhanced by larger region awareness. This is a difficult yet simplified scenario because noise is neglected when it is omnipresent in a wide...
-
Role of miR-15b/16–2 cluster network in endometrial cancer: An in silico pathway and prognostic analysis
PublicationEndometrial cancer (EC) is the second most common cancer in women. A large number of human cancers exhibit dysregulation of microRNA expression including EC. MiR-15b/16–2 is one of the best-known miRNA clusters that is expressed in many types of cancer tissues. Herein, we analyzed the expression of individual miR-15b/16–2 cluster members, its paralogues, and their target network analysis, as well as their prognostic significance...
-
Influence of Soft Soil Samples Quality on the Compressibility and Undrained Shear Strength – Seven Lessons Learned From the Vistula Marshlands
PublicationThis technical article presents the influence of sample quality on the compressibility parameters and undrained shear strength ( c u ) of soft soils from the Vistula Marshlands. The analysis covers: (1) quality of soft soil according to three criteria: void ratio (Δ e / e 0 index), volumetric strain (Δ ɛ v ) and C r / C c ratio; (2) influence of storage time on quality; (3) influence of sample quality on undrained shear strength...
-
DEEP LEARNING BASED ON X-RAY IMAGING IMPROVES COXARTHROSIS DETECTION
PublicationObjective: The purpose of the study was to create an Artificial Neural Network (ANN) based on X-ray images of the pelvis, as an additional tool to automate and improve the diagnosis of coxarthrosis. The research is focused on joint space narrowing, which is a radiological symptom showing the thinning of the articular cartilage layer, which is translucent to X-rays. It is the first and the most important of the radiological signs...
-
Fermentative Conversion of Two-Step Pre-Treated Lignocellulosic Biomass to Hydrogen
PublicationFermentative hydrogen production via dark fermentation with the application of lignocellulosic biomass requires a multistep pre-treatment procedure, due to the complexed structure of the raw material. Hence, the comparison of the hydrogen productivity potential of different lignocellulosic materials (LCMs) in relation to the lignocellulosic biomass composition is often considered as an interesting field of research. In this study,...
-
Research on the Use of Mobile Devices and Headphones on Pedestrian Crossings—Pilot Case Study from Slovakia
PublicationThe topic of the use of mobile devices and headphones on pedestrian crossings is much less explored in comparison to the use of the mobile phone while driving. Recent years have seen many discussions on this issue, especially in foreign countries. The Slovak Republic, however, has not been giving it enough attention (and it is not mentioned in the National Road Safety Plan for the Slovak Republic from 2011 to 2020). This paper...
-
Petrophysical analyses of rock construction materials from the Roman rural settlement in Podšilo bay on Rab island (NE Adriatic, Croatia)
PublicationThis article presents the results of petrophysical analyses of limestones and sandstones used for the construction of the wall structures of a Roman rural settlement located in Podšilo Bay on Rab Island (Croatia). An on-site analysis of the walls indicated the use of different lithotypes, which is an uncommon case in the area. So far, no petrophysical properties of the applied materials have been tested, and their provenance...
-
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...
-
A machine learning approach to classifying New York Heart Association (NYHA) heart failure
PublicationAccording to the European Society of Cardiology, globally the number of patients with heart failure nearly doubled from 33.5 million in 1990 to 64.3 million in 2017, and is further projected to increase dramatically in this decade, still remaining a leading cause of morbidity and mortality. One of the most frequently applied heart failure classification systems that physicians use is the New York Heart Association (NYHA) Functional...
-
Elemental and water-insoluble organic carbon in Svalbard snow: a synthesis of observations during 2007–2018
PublicationLight-absorbing carbonaceous aerosols emitted by biomass or fossil fuel combustion can contribute to amplifying Arctic climate warming by lowering the albedo of snow. The Svalbard archipelago, being near to Europe and Russia, is particularly affected by these pollutants, and improved knowledge of their distribution in snow is needed to assess their impact. Here we present and synthesize new data obtained on Svalbard between 2007...