Search
Filters
total: 966
filtered: 916
Search results for: CARBOXYLIC ACID-BASED DES, NATURAL DEEP EUTECTIC SOLVENTS NADES
-
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...
-
Removal of phenolic inhibitor compounds from hydrolysates and post-fermentation broths by using a Hydrophobic Magnetic Deep Eutectic Solvent
Publication -
Ecology In Tribology: Selected Problems of Eliminating Natural Oil-Based Lubricants from Machine Friction Couples
PublicationThe elimination of mineral oil-based lubricants from machines has multiple beneficial effects on the natural environment. Firstly – these lubricants are a direct threat to the environment in the event of leaks; secondly – their elimination reduces the demand for crude oil from which they are obtained. In addition, in many cases, e.g. when replacing traditional lubricants with water, friction losses in the bearings can also be reduced...
-
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...
-
The physicochemical properties of 3D materials based on hyaluronic acid modified by tannic acid addition
Publication -
Synthesis and characterization of novel renewable polyesters based on 2,5-furandicarboxylic acid and 2,3-butanediol
PublicationNovel polyesters from 2,5-furandicarboxylic acid or 2,5-dimethyl-furandicarboxylate and 2,3-butanediol have been synthesized via bulk polycondensation catalyzed by titanium (IV) n-butoxide, tin (IV) ethylhexanoate, or zirconium (IV) butoxide. The polymers were analyzed by size exclusion chromatography, nuclear magnetic resonance spectroscopy, Fourier transform infrared spectroscopy (FTIR), matrix-assisted laser ionization-desorption...
-
Application of a novel deep eutectic solvent modified carbon nanotube for pipette-tip micro solid phase extraction of 6-mercaptopurine
Publication -
Development of an orbital shaker-assisted fatty acid-based switchable solvent microextraction procedure for rapid and green extraction of amoxicillin from complex matrices: Central composite design
PublicationIn this study, a cheap, fast and simple orbital shaker-assisted fatty acid-based switchable solvent microextraction (OS-FASS-ME) procedure was developed for the extraction of amoxicillin (AMOX) in dairy products, pharmaceutical samples and wastewater prior to its spectrophotometric analysis. Fatty acid-based switchable solvents were investigated for extracting AMOX. The key factors of the OS-FASS-ME procedure were optimized using...
-
Natural composites based on polysaccharide derivatives: preparation and physicochemical properties
Publication -
DBpedia and YAGO Based System for Answering Questions in Natural Language
PublicationIn this paper we propose a method for answering class 1 and class 2 questions (out of 5 classes defined by Moldovan for TREC conference) based on DBpedia and YAGO. Our method is based on generating dependency trees for the query. In the dependency tree we look for paths leading from the root to the named entity of interest. These paths (referenced further as fibers) are candidates for representation of actual user intention. The...
-
Folic acid-conjugated mesoporous silica particles as nanocarriers of natural prodrugs for cancer targeting and antioxidant action
Publication -
Novel fast analytical method for indirect determination of MCPD fatty acid esters in edible oils and fats based on simultaneous extraction and derivatization
PublicationA novel method for indirect determination of MCPD esters levels in lipid samples has been developed. The method is based on combination of extraction and derivatisation in the same sample preparation step. It is achieved by the application of diethyl ether as extraction solvent for isolation of released from esterified forms analytes from water phase and dilution solvent for solid PBA – derivatisation agent. It is a noteworthy...
-
Influence of temperature and anion type on thermophysical properties of aqueous solutions of morpholine based amino acid ionic liquids
PublicationDensities and sound velocities of aqueous solutions of N-butyl-N-methylmorpholine based amino acid ionic liquids (AAILs), including N-acetyl-L-alanine, N-acetyl-Lvalinate, N-acetyl-L-leucinate, and N-acetyl-L-izoleucinate anions were measured at a temperature from 293.15 to 313.15 K at 5 K intervals and atmospheric pressure. These data were used to calculate the apparent molar volumes and the apparent molar compressibilities in...
-
Bio-Based Polyurethane Composites and Hybrid Composites Containing a New Type of Bio-Polyol and Addition of Natural and Synthetic Fibers
PublicationThis article describes how new bio-based polyol during the liquefaction process can be obtained. Selected polyol was tested in the production of polyurethane resins. Moreover, this research describes the process of manufacturing polyurethane materials and the impact of two different types of fibers—synthetic and natural (glass and sisal fibers)—on the properties of composites. The best properties were achieved at a reaction temperature...
-
The Characterization of Scaffolds Based on Dialdehyde Chitosan/Hyaluronic Acid
Publication -
Developing nucleic acid-based electrical detection systems
Publication -
Natural carbon-based quantum dots and their applications in drug delivery: A review
Publication -
Bio polyetherurethane composites with high content of natural ingredients: hydroxylated soybean oil based polyol, bio glycol and microcrystalline cellulose
PublicationIn our study, we focused on obtaining bio-polyurethane composites using bio-components such as bio glycol, modified natural oil-based polyol, and microcrystalline cellulose (MCC). The pre-polymer method was used to prepare the bio polyurethane matrix. Prepolymer was synthesized using 4,4’-diphenylmethane diisocyanate (MDI) and a polyol mixture containing 50 wt.% of commercial polyether and 50 wt.% of hydroxylated soybean oil (H3)....
-
Analysis of 2D Feature Spaces for Deep Learning-based Speech Recognition
Publicationconvolutional neural network (CNN) which is a class of deep, feed-forward artificial neural network. We decided to analyze audio signal feature maps, namely spectrograms, linear and Mel-scale cepstrograms, and chromagrams. The choice was made upon the fact that CNN performs well in 2D data-oriented processing contexts. Feature maps were employed in the Lithuanian word recognition task. The spectral analysis led to the highest word...
-
Deep learning approach on surface EEG based Brain Computer Interface
PublicationIn this work we analysed the application of con-volutional neural networks in motor imagery classification for the Brain Computer Interface (BCI) purposes. To increase the accuracy of classification we proposed the solution that combines the Common Spatial Pattern (CSP) with convolutional network (ConvNet). The electroencephalography (EEG) is one of the modalities we try to use for controlling the prosthetic arm. Therefor in this...
-
Autonomous pick-and-place system based on multiple 3Dsensors and deep learning
PublicationGrasping 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...
-
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...
-
Synthesis, characterization and Luminescent Properties of New Coordination Polymers Based on p-tert Butylcalix[4]arene-tetracarboxylic acid and Lanthanine cations
PublicationA series of new coordination polymers based on p-tert-butylcalix[4]arene-tetracarboxylic acid with Eu3+, Tb3+wrer prepared by hydro and solvothermal methods. the obtained solid compounds were characterized by infrared and luminescence spectroscopy, powder X-ray diffraction, scianning electron microscopy and thermogravimetric anylisis. The infrared curves and the x-ray diffraction patterns indicate that the same crystalline structure...
-
Enhanced Activity and Sustained Release of Protocatechuic Acid, a Natural Antibacterial Agent, from Hybrid Nanoformulations with Zinc Oxide Nanoparticles
Publication -
Improvement of speech intelligibility in the presence of noise interference using the Lombard effect and an automatic noise interference profiling based on deep learning
PublicationThe Lombard effect is a phenomenon that results in speech intelligibility improvement when applied to noise. There are many distinctive features of Lombard speech that were recalled in this dissertation. This work proposes the creation of a system capable of improving speech quality and intelligibility in real-time measured by objective metrics and subjective tests. This system consists of three main components: speech type detection,...
-
Low-Cost and Highly-Accurate Behavioral Modeling of Antenna Structures by Means of Knowledge-Based Domain-Constrained Deep Learning Surrogates
PublicationThe awareness and practical benefits of behavioral modeling methods have been steadily growing in the antenna engineering community over the last decade or so. Undoubtedly, the most important advantage thereof is a possibility of a dramatic reduction of computational expenses associated with computer-aided design procedures, especially those relying on full-wave electromagnetic (EM) simulations. In particular, the employment of...
-
Proline, glutamic acid, and leucine rich protein 1 (PELP1) expression in deep paravertebral muscles in idiopathic scoliosis girls
Publication -
Solid-State Modification of Poly(butylene terephthalate) with a Bio-Based Fatty Acid Dimer Diol Furnishing Copolyesters with Unique Morphologies
PublicationCopolyesters based on poly(butylene terephthalate) (PBT) and a bio-based fatty acid dimer diol (FADD) were prepared by solid-state modification (SSM). The chemical incorporation of the FADD into the backbone of the PBT was proven using various techniques. It was clear that the incorporation rate was diffusion-limited rather than reaction-limited. From quantitative 13C NMR a nonrandom chemical microstructure was obtained at all...
-
A preliminary study on antifungal effect of TiO2-based paints in natural indoor light
Publication -
Enhancement of second harmonic generation in nanocrystalline SiC films based natural microcavities
Publication -
DBpedia and YAGO as Knowledge Base for Natural Language Based Question Answering—The Evaluation
PublicationThe idea of automatic question answering system has a very long history. Despite constant improvement of the systems asking questions in the natural language requires very complex solutions. In this paper the DBpedia and YAGO are evaluated as a knowledge bases for simple class 1 and 2 question answering system. For this purpose a question answering system was designed and implemented. The proposed solution and the knowledge bases...
-
Emulsifying blends based on natural fats for eco-design of O/W emulsions
PublicationEmulsifier blends are most often used to stabilize and modulate the properties of cosmetic and pharmaceutical emulsions, such as skin care or application-related consistency. However, the rational design of such emulsifier blends is often not well understood, especially when their ingredients are natural raw materials. This study aimed to analyze the influence of natural fatty ingredients selected as emulsifiers on the emulsion...
-
Deep Learning-Based, Multiclass Approach to Cancer Classification on Liquid Biopsy Data
Publication -
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...
-
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....
-
Autonomous Perception and Grasp Generation Based on Multiple 3D Sensors and Deep Learning
PublicationGrasping 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...
-
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...
-
Perspectives on the replacement of harmful organic solvents in analytical methodologies: a framework toward the implementation of a generation of eco-friendly alternatives
PublicationVolatile organic solvents derived from non-renewable fossil feedstocks are commonplace in analytical laboratories. In spite of their convenient performance in countless unit operations, their environmental, health and safety issues represent a major area of concern. The progressive replacement of organic solvents obtained from fossil resources by eco-friendly alternatives would involve remarkable advances within the framework of...
-
3D composites based on the blends of chitosan and collagen with the addition of hyaluronic acid
Publication -
Morphology of bio-based polyurethane composites filled by mer-cerized or silanized natural fibres
PublicationBio-composites are materials which possess unique properties and undergo biodegra-dation under specific conditions. Bio-composites belong to the group of materials produced with the use of renewable raw materials. They contain reinforcement, mainly in the form of natural fiber, which has high stiffness and resistance; filler powders are less frequently used. Significant features of natural fibers are elongation, density, thermal...
-
Analysis of the Capability of Deep Learning Algorithms for EEG-based Brain-Computer Interface Implementation
PublicationMachine learning models have received significant attention for their exceptional performance in classifying electroencephalography (EEG) data. They have proven to be highly effective in extracting intricate patterns and features from the raw signal data, thereby contributing to their success in EEG classification tasks. In this study, we explore the possibilities of utilizing contemporary machine learning algorithms in decoding...
-
The Effect of Citric Acid on Physicochemical Properties of Hydrophilic Carboxymethyl Starch-Based Films
Publication -
Gallic Acid-Functionalized, TiO2-Based Nanomaterial—Preparation, Physicochemical and Biological Properties
Publication -
Examining the Impact of Squaric Acid as a Crosslinking Agent on the Properties of Chitosan-Based Films
Publication -
Deep learning based segmentation using full wavefield processing for delamination identification: A comparative study
Publication -
Prediction of NOx Emission Based on Data of LHD On-Board Monitoring System in a Deep Underground Mine
Publication -
Charge-based deep level transient spectroscopy of B-doped and undoped polycrystalline diamond films
PublicationThe undoped and B-doped polycrystalline diamond thin film was synthesized by hot filament chemical vapor deposition and microwave plasma, respectively. The structural characterization was performed by scanning electron microscopy, X-ray diffraction and Raman spectroscopy. The electrical properties of synthesized diamond layer were characterized by dc-conductivity method and charge deep level transient spectroscopy. The B-doped...
-
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....
-
Physico-chemical properties of three-component mixtures based on chitosan, hyaluronic acid and collagen
Publication -
The thermal degradation of acrylic pressure-sensitive adhesives based on butyl acrylate and acrylic acid
Publication