Filters
total: 4133
-
Catalog
displaying 1000 best results Help
Search results for: POTHOLE DETECTION
-
Automated detection of pronunciation errors in non-native English speech employing deep learning
PublicationDespite significant advances in recent years, the existing Computer-Assisted Pronunciation Training (CAPT) methods detect pronunciation errors with a relatively low accuracy (precision of 60% at 40%-80% recall). This Ph.D. work proposes novel deep learning methods for detecting pronunciation errors in non-native (L2) English speech, outperforming the state-of-the-art method in AUC metric (Area under the Curve) by 41%, i.e., from...
-
Possibilities of detection and identification objects located on the sea bottom by means of a simple sidescan sonar
PublicationPraca zawiera omówienie zagadnień związanych z wykrywaniem i identyfikacją obiektów leżących na dnie przy pomocy sonaru bocznego, umieszczonego na zdalnie sterowanym pojeździe głębinowym.
-
Guided wave propagation in debonding detection in CFRP-reinforced steel plate-like structures
PublicationThe present study investigates the guided wave propagation in multilayered steel specimens reinforced with carbon fiber reinforced polymer (CFRP) through theoretical, numerical, and experimental means. The effectiveness of externally bonded reinforcement (EBR) relies heavily on the bonding quality between the CFRP and the substrate. Premature debonding, a prevalent and hazardous defect, can arise from suboptimal manufacturing processes,...
-
OOA-modified Bi-LSTM network: An effective intrusion detection framework for IoT systems
PublicationCurrently, the Internet of Things (IoT) generates a huge amount of traffic data in communication and information technology. The diversification and integration of IoT applications and terminals make IoT vulnerable to intrusion attacks. Therefore, it is necessary to develop an efficient Intrusion Detection System (IDS) that guarantees the reliability, integrity, and security of IoT systems. The detection of intrusion is considered...
-
Detection of circulating tumor cells by means of machine learning using Smart-Seq2 sequencing
PublicationCirculating tumor cells (CTCs) are tumor cells that separate from the solid tumor and enter the bloodstream, which can cause metastasis. Detection and enumeration of CTCs show promising potential as a predictor for prognosis in cancer patients. Furthermore, single-cells sequencing is a technique that provides genetic information from individual cells and allows to classify them precisely and reliably. Sequencing data typically...
-
In silico epitope prediction of Borrelia burgdorferi sensu lato antigens for the detection of specific antibodies
PublicationDespite many years of research, serodiagnosis of Lyme disease still faces many obstacles. Difficulties arise mainly due to the low degree of amino acid sequence conservation of the most immunogenic antigens among B. burgdorferi s.l. genospecies, as well as differences in protein production depending on the environment in which the spirochete is located. Mapping B-cell epitopes located on antigens allows for a better understanding...
-
Deep learning techniques for biometric security: A systematic review of presentation attack detection systems
PublicationBiometric technology, including finger vein, fingerprint, iris, and face recognition, is widely used to enhance security in various devices. In the past decade, significant progress has been made in improving biometric sys- tems, thanks to advancements in deep convolutional neural networks (DCNN) and computer vision (CV), along with large-scale training datasets. However, these systems have become targets of various attacks, with...
-
A novel hierarchically-porous diamondized polyacrylonitrile sponge-like electrodes for acetaminophen electrochemical detection
PublicationA novel composite electrode material consisting of tangled fibrous polyacrylonitrile-based hierarchically-struc- tured nanocomposites has been produced by wet-spinning, carbonized and decorated with a carbon nano- architecture by microwave plasma-enhanced chemical vapor deposition and investigated as a metal-free electrode for the enhanced electrochemical detection of acetaminophen. Surprisingly, the hierarchical fiber ar- chitecture...
-
Neural network based algorithm for hand gesture detection in a low-cost microprocessor applications
PublicationIn this paper the simple architecture of neural network for hand gesture classification was presented. The network classifies the previously calculated parameters of EMG signals. The main goal of this project was to develop simple solution that is not computationally complex and can be implemented on microprocessors in low-cost 3D printed prosthetic arms. As the part of conducted research the data set EMG signals corresponding...
-
Detection of Lexical Stress Errors in Non-Native (L2) English with Data Augmentation and Attention
PublicationThis paper describes two novel complementary techniques that improve the detection of lexical stress errors in non-native (L2) English speech: attention-based feature extraction and data augmentation based on Neural Text-To-Speech (TTS). In a classical approach, audio features are usually extracted from fixed regions of speech such as the syllable nucleus. We propose an attention-based deep learning model that automatically de...
-
A Numerical Study on Baseline-Free Damage Detection Using Frequency Steerable Acoustic Transducers
PublicationIn structural health monitoring (SHM) a considerable amount of damage detection algorithms based on guided waves (GW) have been developed. Most of them rely on extensive transducer networks, besides preliminary reference measurements of the structures. This originated a growing demand for hardware simplification and cost reduction of the wave-based SHM methods, driving the conception of new solutions enabling both: the reduction...
-
Conductive printable electrodes tuned by boron-doped nanodiamond foil additives for nitroexplosive detection
PublicationAn efficient additive manufacturing-based composite material fabrication for electrochemical applications is reported. The composite is composed of commercially available graphene-doped polylactide acid (G-PLA) 3D printouts and surface- functionalized with nanocrystalline boron-doped diamond foil (NDF) additives. The NDFs were synthesized on a tantalum substrate and transferred to the 3D-printout surface at 200 °C. No other electrode...
-
Performance Analysis of Machine Learning Methods with Class Imbalance Problem in Android Malware Detection
PublicationDue to the exponential rise of mobile technology, a slew of new mobile security concerns has surfaced recently. To address the hazards connected with malware, many approaches have been developed. Signature-based detection is the most widely used approach for detecting Android malware. This approach has the disadvantage of being unable to identify unknown malware. As a result of this issue, machine learning (ML) for detecting malware...
-
Empirical Analysis of Forest Penalizing Attribute and Its Enhanced Variations for Android Malware Detection
PublicationAs a result of the rapid advancement of mobile and internet technology, a plethora of new mobile security risks has recently emerged. Many techniques have been developed to address the risks associated with Android malware. The most extensively used method for identifying Android malware is signature-based detection. The drawback of this method, however, is that it is unable to detect unknown malware. As a consequence of this problem,...
-
Electronic nose algorithm design using classical system identification for odour intensity detection
PublicationThe two elements considered crucial for constructing an efficient environmental odour intensity monitoring systems are sensors and algorithms typically addressed to as electronic nose sensor (e-nose). Due to operational complexity of biochemical sensors developed in human bodies algorithms based on computational methods of artificial intelligence are typically considered superior to classical model based approaches in development...
-
Weakly-Supervised Word-Level Pronunciation Error Detection in Non-Native English Speech
PublicationWe propose a weakly-supervised model for word-level mispronunciation detection in non-native (L2) English speech. To train this model, phonetically transcribed L2 speech is not required and we only need to mark mispronounced words. The lack of phonetic transcriptions for L2 speech means that the model has to learn only from a weak signal of word-level mispronunciations. Because of that and due to the limited amount of mispronounced...
-
Green porous benzamide-like nanomembranes for hazardous cations detection, separation, and concentration adjustment
PublicationGreen biomaterials play a crucial role in the diagnosis and treatment of diseases as well as health-related problem-solving. Typically, biocompatibility, biodegradability, and mechanical strength are requirements centered on biomaterial engineering. However, in-hospital therapeutics require an elaborated synthesis of hybrid and complex nanomaterials capable of mimicking cellular behavior. Accumulation of hazardous cations like...
-
Using Convolutional Neural Networks for Corneal Arcus Detection Towards Familial Hypercholesterolemia Screening
PublicationFamilial hypercholesterolemia (FH) is a highly undiagnosed disease. Among FH patients, the onset of premature coronary artery disease is 13 times higher than in the general population. Early diagnosis and treatment is essential to prevent cardiovascular diseases and their complications, and to prolong life. One of the clinical criteria of FH is the occurrence of a corneal arcus (CA) among patients, especially those under 45 years...
-
Remote Stateful Autoconfiguration for Mobile IPv6 Nodes with Server Side Duplicate Address Detection
PublicationDuring interdomain handover, IPv6 node requires new address at its new location. Once the L2 handover procedure is completed, mobile node (MN) starts its IPv6 configuration, using stateless (router advertisements) or stateful (DHCPv6 communication) mode. Once the address is obtained, its uniqueness has to be verified, using Duplicate Address Detection (DAD) procedure. Depending on the interface type, this procedure may easily take...
-
Melamine-modified boron-doped diamond towards enhanced detection of adenine, guanine and caffeine
PublicationThis work describes the electrochemical method of boron-doped diamond (BDD) modification by poly-melamine to obtain organic film. The detection of adenine, guanine and caffeine were carried out by differential pulse wave voltammetry. The poly-melamine modified B-NCD electrodes exhibit excellent activity towards the electrochemical oxidation of all examined analytes. The poly-melamine modified BDD electrodes in all measurements...
-
Application of acoustic emission for detection of fatigue microdemage in main and crank bearings for diesel engines
PublicationThe article presents reasons for applying the acoustic emission (AE) to detect fatigue microdamage in main bearings and crank bearings of ship main engines. Problem of determination of the fatigue life for slide bearing bushes was characterized in general. There were demonstrated properties of the objects of research, which were bushings made of the MB58 alloy, as well as an overall description of the research. It was shown that...
-
Application of micellar electrokinetic chromatography for detection of silver nanoparticles released from wound dressing
PublicationThe recent emergence of nanotechnology has provided a new therapeutic modality in case of silver nanoparticles. Dressings containing silver form the basis for the treatment of burns and wounds, either acute or chronic ones. The aim of the study was to examine silver release from the different wound dressings: commercially available (Atrauman Ag, Aqua- cel Ag) and experimental (FKDP-AgNPs) using MEKC. In order to characterize prepared keratin...
-
Methodology of Selecting the Hadoop Ecosystem Configuration in Order to Improve the Performance of a Plagiarism Detection System
PublicationThe plagiarism detection problem involves finding patterns in unstructured text documents. Similarity of documents in this approach means that the documents contain some identical phrases with defined minimal length. The typical methods used to find similar documents in dig- ital libraries are not suitable for this task (plagiarism detection) because found documents may contain similar content and we have not any war- ranty that...
-
Deep CNN based decision support system for detection and assessing the stage of diabetic retinopathy
PublicationThe 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...
-
Pose-Invariant Face Detection by Replacing Deep Neurons with Capsules for Thermal Imagery in Telemedicine
PublicationAbstract— The aim of this work was to examine the potential of thermal imaging as a cost-effective tool for convenient, non- intrusive remote monitoring of elderly people in different possible head orientations, without imposing specific behavior on users, e.g. looking toward the camera. Illumination and pose invariant head tracking is important for many medical applications as it can provide information, e.g. about vital signs, sensory...
-
Magnetic field gradient as the most useful signal for detection of flaws using MFL technique
PublicationThe magnetic flux leakage (MFL) technique is extensively used for detection of flaws as well as for evaluation of their dimensions in ferromagnetic materials. However, proper analysis of the MFL signal is hindered by the MFL sensor velocity causing distortions of this signal. Traditionally measured components of the MFL signal are particularly sensitive to the scanning velocity. In this paper, an another signal – the gradient of...
-
Performance Evaluation of Selected Parallel Object Detection and Tracking Algorithms on an Embedded GPU Platform
PublicationPerformance evaluation of selected complex video processing algorithms, implemented on a parallel, embedded GPU platform Tegra X1, is presented. Three algorithms were chosen for evaluation: a GMM-based object detection algorithm, a particle filter tracking algorithm and an optical flow based algorithm devoted to people counting in a crowd flow. The choice of these algorithms was based on their computational complexity and parallel...
-
Gas Detection Using Resistive Gas Sensors And Radial Basis Function Neural Networks
PublicationWe present a use of Radial Basis Function (RBF) neural networks and Fluctuation Enhanced Sensing (FES) method in gas detection system utilizing a prototype resistive WO3 gas sensing layer with gold nanoparticles. We investigated accuracy of gas detection for three different preprocessing methods: no preprocessing, Principal Component Analysis (PCA) and wavelet transformation. Low frequency noise voltage observed in resistive gas...
-
Rapid Assays for Specific Detection of Fungi of Scopulariopsis and Microascus Genera and Scopulariopsis brevicaulis Species
PublicationPurpose Fungi of Scopulariopsis and Microascus genera cause a wide range of infections, with S. brevicaulis being the most prevalent aetiological agent of mould onychomycosis. Proper identification of these pathogens requires sporulating culture, which considerably delays the diagnosis. So far, sequencing of rDNA regions of clinical isolates has produced ambiguous results due to the lack of reference sequences in publicly available...
-
Determination of cyanide ion in urine samples using ion chromatography with pulsed amperometric detection.
PublicationCyanides are widely applied in industrial activity, including gold and silver mining and the production of organic chemicals. HCN is also formed directly from fossil fuel combustion sources from gasoline and diesel vehicles. In natural environment, in plants seeds for example an apple seed, it exists as a cyanogenic glycosides. The amount of cyanide ions originating from food products is however rather small. Larger concentrations...
-
Detection and localization of selected acoustic events in 3D acoustic field for smart surveillance applications
PublicationA method for automatic determination of position of chosen sound events such as speech signals and impulse sounds in 3-dimensional space is presented. The events are localized in the presence of sound reflections employing acoustic vector sensors. Human voice and impulsive sounds are detected using adaptive detectors based on modified peak-valley difference (PVD) parameter and sound pressure level. Localization based on signals...
-
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...
-
One tube mutation detection using sensitive fluorescent dyeing of MutS protected DNA
Publication -
Preliminary studies on DNA retardation by MutS applied to the detection of point mutations in clinical samples
Publication -
A detector of sleep disorders for using at home
PublicationObstructive sleep apnea usually requires all-ni ght examination in a specialized clinic, under the supervision of a medical staff. Because of those requirements it is an expensive and a non-widely utilized test. Moving the examination procedure to patients’ home with automatic analysis algorithms involved will decrease the costs and make it available for larger group of patients. The developed device allows all-night recordings...
-
A robust detector for distorted music staves
Publication.
-
Vehicle detector training with minimal supervision
PublicationRecently 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...
-
Quantitative structure—retention relationship modeling of the retention behavior of selected antipsychotic drugs in normal-phase thin-layer chromatography
Publication -
Visually validated semi-automatic high-frequency oscillation detection aides the delineation of epileptogenic regions during intra-operative electrocorticography
PublicationOBJECTIVE: To test the utility of a novel semi-automated method for detecting, validating, and quantifying high-frequency oscillations (HFOs): ripples (80-200 Hz) and fast ripples (200-600 Hz) in intra-operative electrocorticography (ECoG) recordings. METHODS: Sixteen adult patients with temporal lobe epilepsy (TLE) had intra-operative ECoG recordings at the time of resection. The computer-annotated ECoG recordings were visually...
-
Cluster-based instance selection for machine classification
Publication -
A New Cluster-based Instance Selection Algorithm
Publication -
Cluster-Dependent Feature Selection for the RBF Networks
Publication -
Consensus-based cluster merging for the prototype selection
Publication -
Cluster Integration for the Cluster-Based Instance Selection
Publication -
Frequency bands selection of the Portevin–LeChatelier effect
Publication -
Style Transfer for Detecting Vehicles with Thermal Camera
Publication -
Thermodynamic vs. extrathermodynamic modeling of chromatographic retention
Publication -
Unilateral Carotid Body Resection in Resistant Hypertension
Publication -
Extending Service Selection Algorithms with Interoperability Analysis
PublicationApplication development by integration of existing, atomic services reduces development cost and time by extensive reuse of service components. In Service Oriented Architecture, there exist alternative versions of services supplying the same functionality but differing in Quality of Service (QoS) attributes, which enables developers to select services with optimal QoS. Existing algorithms of service selection focus on the formal...
-
Selection Pressure in the Evolutionary Path Planning Problem
PublicationThis article compares an impact of using various post-selection methods on the selection pressure and the quality of the solution for the problem of planning the path for a moving object using the evolutionary method. The concept of selection pressure and different methods of post-selection are presented. Article analyses behaviour of post-selection for four options of evolutionary algorithms. Based on the results achieved, waveform...