Filtry
wszystkich: 305
wybranych: 296
-
Katalog
Filtry wybranego katalogu
Wyniki wyszukiwania dla: EXPLAINABLE CLASSIFIERS, COUNTERFACTUAL APPROACH, BIAS DETECTION
-
Feature Reduction Using Similarity Measure in Object Detector Learning with Haar-like Features
PublikacjaThis paper presents two methods of training complexity reduction by additional selection of features to check in object detector training task by AdaBoost training algorithm. In the first method, the features with weak performance at first weak classifier building process are reduced based on a list of features sorted by minimum weighted error. In the second method the feature similarity measures are used to throw away that features...
-
A double-talk detector using audio watermarking
Publikacjaa novel approach to double-talk detection in the acoustic echo canceler is proposed. a hidden signature is embedded into the arriving signal, using the echo-hiding method. next detection of the presence of this signature in the microphone signal is performed. the results of the signature detection may be used by the acoustic echo canceler to stop or restart the adaptation process.
-
An Overview of Image Analysis Techniques in Endoscopic Bleeding Detection
PublikacjaAuthors review the existing bleeding detection methods focusing their attention on the image processing techniques utilised in the algorithms. In the article, 18 methods were analysed and their functional components were identified. The authors proposed six different groups, to which algorithms’ components were assigned: colour techniques, reflecting features of pixels as individual values, texture techniques, considering spatial...
-
Measuring Tilt with an IMU Using the Taylor Algorithm
PublikacjaThis article addresses the important problem of tilt measurement and stabilization. This is particularly important in the case of drone stabilization and navigation in underwater environments, multibeam sonar mapping, aerial photogrammetry in densely urbanized areas, etc. The tilt measurement process involves the fusion of information from at least two different sensors. Inertial sensors (IMUs) are unique in this context because...
-
On adaptive selection of estimation bandwidth for analysis of locally stationary multivariate processes
PublikacjaWhen estimating the correlation/spectral structure of a locally stationary process, one should choose the so-called estimation bandwidth, related to the effective width of the local analysis window. The choice should comply with the degree of signal nonstationarity. Too small bandwidth may result in an excessive estimation bias, while too large bandwidth may cause excessive estimation variance. The paper presents a novel method...
-
Offshore benthic habitat mapping based on object-based image analysis and geomorphometric approach. A case study from the Slupsk Bank, Southern Baltic Sea
PublikacjaBenthic habitat mapping is a rapidly growing field of underwater remote sensing studies. This study provides the first insight for high-resolution hydroacoustic surveys in the Slupsk Bank Natura 2000 site, one of the most valuable sites in the Polish Exclusive Zone of the Southern Baltic. This study developed a quick and transparent, automatic classification workflow based on multibeam echosounder and side-scan sonar surveys to...
-
Human-Computer Interface Based on Visual Lip Movement and Gesture Recognition
PublikacjaThe multimodal human-computer interface (HCI) called LipMouse is presented, allowing a user to work on a computer using movements and gestures made with his/her mouth only. Algorithms for lip movement tracking and lip gesture recognition are presented in details. User face images are captured with a standard webcam. Face detection is based on a cascade of boosted classifiers using Haar-like features. A mouth region is located in...
-
Network society: a concept of smart information management
PublikacjaAutomatic enhancement of Internet broadcasted news has been recently gaining increasing importance and interest. Existing applications and models of textual Event Detection in online media are based on the analysis of news distributed via RSS (Rich Site Summary called also Really Simple Syndication) channels or available at news websites. It assumes that each piece of news is equally available to the reader and, therefore, describes...
-
Seafloor characterisation using multibeam data: sonar image properties, seabed surface properties and echo properties
PublikacjaIn the paper, the approach to seafloor characterisation is presented. The multibeam sonars, besides their well verified and widely used applications like high resolution bathymetry and underwater object detection and imaging, are also the promising tool in seafloor characterization and classification, having several advantages over conventional single beam echosounders. The proposed approach relies on the combined, concurrent use...
-
A simple modification of PCR thermal profile applied to evade persisting contamination
PublikacjaThe polymerase chain reaction (PCR), one of the most commonly applied methods of diagnostics and molecular biology has a frustrating downside known as the false positive signal or contamination. Several solutions to avoid and to eliminate PCR contaminations have been worked out to date but the implementation of these solutions to laboratory practice may be laborious and time consuming. A simple approach to circumvent the problem...
-
Integration of protein tethering in a rapid and label-free SERS screening platform for drugs of abuse
PublikacjaSurface enhanced Raman spectroscopy (SERS) has emerged as a promising technique for the rapid and ultrasensitive detection of molecular species such as drugs of abuse in biofluids. Yet, it remains a significant challenge to create a viable screening tool for multiple drug classes, owing to the lack of affinity of certain species for the SERS substrate and to the matrix interference in complex media. Here we report a protein tethering...
-
Extraction of stable foreground image regions for unattended luggage detection
PublikacjaA novel approach to detection of stationary objects in the video stream is presented. Stationary objects are these separated from the static background, but remaining motionless for a prolonged time. Extraction of stationary objects from images is useful in automatic detection of unattended luggage. The proposed algorithm is based on detection of image regions containing foreground image pixels having stable values in time and...
-
Optimized Deep Learning Model for Flood Detection Using Satellite Images
PublikacjaThe increasing amount of rain produces a number of issues in Kerala, particularly in urban regions where the drainage system is frequently unable to handle a significant amount of water in such a short duration. Meanwhile, standard flood detection results are inaccurate for complex phenomena and cannot handle enormous quantities of data. In order to overcome those drawbacks and enhance the outcomes of conventional flood detection...
-
A low complexity double-talk detector based on the signal envelope
PublikacjaA new algorithm for double-talk detection, intended for use in the acoustic echo canceller for voice communication applications, is proposed. The communication system developed by the authors required the use of a double-talk detection algorithm with low complexity and good accuracy. The authors propose an approach to doubletalk detection based on the signal envelopes. For each of three signals: the far-end speech, the microphone...
-
Self-Testing of Analog Parts Terminated by ADCs Based on Multiple Sampling of Time Responses
PublikacjaA new approach for self-testing of analog parts terminated by analog-to-digital converters in mixed-signal electronic microsystems controlled by microcontrollers is presented. It is based upon a new fault diagnosis method using a transformation of the set of voltage samples of the time response of a tested analog part to a square impulse into localization curves placed in a multidimensional measurement space. The method can be used...
-
Improving css-KNN Classification Performance by Shifts in Training Data
PublikacjaThis paper presents a new approach to improve the performance of a css-k-NN classifier for categorization of text documents. The css-k-NN classifier (i.e., a threshold-based variation of a standard k-NN classifier we proposed in [1]) is a lazy-learning instance-based classifier. It does not have parameters associated with features and/or classes of objects, that would be optimized during off-line learning. In this paper we propose...
-
Non-volatile molecular composition and discrimination of single grape white of chardonnay, riesling, sauvignon blanc and silvaner using untargeted GC–MS analysis
PublikacjaThis study developed and applied a GC–MS method aiming at molecular fingerprinting of 120 commercial single grape white wines (Chardonnay, Riesling, Sauvignon Blanc and Silvaner) for possible authentication according to grape variety. The method allowed detection of 372 peaks and tentative identification of 146 metabolites including alcohols, organic acids, esters, amino acids and sugars. The grape variety effect explained 8.3%...
-
Video Classification Technology in a Knowledge-Vision-Integration Platform for Personal Protective Equipment Detection: An Evaluation
PublikacjaThis work is part of an effort for the development of a Knowledge-Vision Integration Platform for Hazard Control (KVIP-HC) in industrial workplaces, adaptable to a wide range of industrial environments. This paper focuses on hazards resulted from the non-use of personal protective equipment (PPE), and examines a few supervised learning techniques to compose the proposed system for the purpose of recognition of three protective...
-
New semi-causal and noncausal techniques for detection of impulsive disturbances in multivariate signals with audio applications
PublikacjaThis paper deals with the problem of localization of impulsive disturbances in nonstationary multivariate signals. Both unidirectional and bidirectional (noncausal) detection schemes are proposed. It is shown that the strengthened pulse detection rule, which combines analysis of one-step-ahead signal prediction errors with critical evaluation of leave-one-out signal interpolation errors, allows one to noticeably improve detection results...
-
A framework for detection of selfishness in multihop mobile ad hoc networks
PublikacjaThe paper discusses the need for a fully-distributed selfishness detection mechanism dedicated for multihop wireless ad hoc networks which nodes may exhibit selfish forwarding behaviour. The main contribution of this paper is an introduction to a novel approach for detecting and coping with the selfish nodes. Paper describes a new framework based on Dempster-Shafer Theory called Dempster-Shafer Theory-based Selfishness Detection...
-
Discovering Rule-Based Learning Systems for the Purpose of Music Analysis
PublikacjaMusic analysis and processing aims at understanding information retrieved from music (Music Information Retrieval). For the purpose of music data mining, machine learning (ML) methods or statistical approach are employed. Their primary task is recognition of musical instrument sounds, music genre or emotion contained in music, identification of audio, assessment of audio content, etc. In terms of computational approach, music databases...
-
Instrument detection and pose estimation with rigid part mixtures model in video-assisted surgeries
PublikacjaLocalizing instrument parts in video-assisted surgeries is an attractive and open computer vision problem. A working algorithm would immediately find applications in computer-aided interventions in the operating theater. Knowing the location of tool parts could help virtually augment visual faculty of surgeons, assess skills of novice surgeons, and increase autonomy of surgical robots. A surgical tool varies in appearance due to...
-
Portable exhaled breath analyzer employing fluctuation-enhanced gas sensing method in resistive gas sensors
PublikacjaThis paper presents a portable exhaled breath analyser, developed to detect selected diseases. The set-up employs resistive gas sensors: commercial MEMS sensors and prototype gas sensors made of WO3 gas sensing layers doped with various metal ingredients. The set-up can modulate the gas sensors by applying UV light to induce physical changes of the gas sensing layers. The sensors are placed in a tiny gas chamber of a volume...
-
Fluctuation-Enhanced Sensing with Organically Functionalized Gold Nanoparticle Gas Sensors Targeting Biomedical Applications
PublikacjaDetection of volatile organic compounds is a useful approach to non-invasive diagnosis of diseases through breath analysis. Our experimental study presents a newly developed prototype gas sensor, based on organically-functionalized gold nanoparticles, and results on formaldehyde detection using fluctuation-enhanced gas sensing. Formaldehyde was easily detected via intense fluctuations of the gas sensor’s resistance, while the cross-influence...
-
On adaptive covariance and spectrum estimation of locally stationary multivariate processes
PublikacjaWhen estimating the correlation/spectral structure of a locally stationary process, one has to make two important decisions. First, one should choose the so-called estimation bandwidth, inversely proportional to the effective width of the local analysis window, in the way that complies with the degree of signal nonstationarity. Too small bandwidth may result in an excessive estimation bias, while too large bandwidth may cause excessive...
-
Detecting Lombard Speech Using Deep Learning Approach
PublikacjaRobust Lombard speech-in-noise detecting is challenging. This study proposes a strategy to detect Lombard speech using a machine learning approach for applications such as public address systems that work in near real time. The paper starts with the background concerning the Lombard effect. Then, assumptions of the work performed for Lombard speech detection are outlined. The framework proposed combines convolutional neural networks...
-
Automatic classification and mapping of the seabed using airborne LiDAR bathymetry
PublikacjaShallow coastal areas are among the most inhabited areas and are valuable for biodiversity, recreation and the economy. Due to climate change and sea level rise, sustainable management of coastal areas involves extensive exploration, monitoring, and protection. Current high-resolution remote sensing methods for monitoring these areas include bathymetric LiDAR. Therefore, this study presents a novel methodological approach to assess...
-
Recurrent potential pulse technique for improvement of glucose sensing ability of 3D polypyrrole
PublikacjaIn this work, a new approach for using a 3D polypyrrole (PPy) conducting polymer as a sensing material for glucose detection is proposed. Polypyrrole is electrochemically polymerized on a platinum screen-printed electrode in an aqueous solution of lithium perchlorate and pyrrole. PPy exhibits a high electroactive surface area and high electrochemical stability, which results in it having excellent electrocatalytic properties. The...
-
INVESTIGATION OF THE LOMBARD EFFECT BASED ON A MACHINE LEARNING APPROACH
PublikacjaThe Lombard effect is an involuntary increase in the speaker’s pitch, intensity, and duration in the presence of noise. It makes it possible to communicate in noisy environments more effectively. This study aims to investigate an efficient method for detecting the Lombard effect in uttered speech. The influence of interfering noise, room type, and the gender of the person on the detection process is examined. First, acoustic parameters...
-
Data-driven models for fault detection using kernel pca:a water distribution system case study
PublikacjaKernel Principal Component Analysis (KPCA), an example of machine learning, can be considered a non-linear extension of the PCA method. While various applications of KPCA are known, this paper explores the possibility to use it for building a data-driven model of a non-linear system-the water distribution system of the Chojnice town (Poland). This model is utilised for fault detection with the emphasis on water leakage detection....
-
Evaluation of organic coatings condition with AFM-based method
PublikacjaThe paper presents an atomic force microscopy (AFM)-based approach to evaluation of local protective properties of organic coatings. Apart from topography, it provides local ac and dc characteristics of examined coating. The method consists in application of ac voltage perturbation signal between conductive AFM tip and coated metal substrate. The resulting current is used to determine local impedance characteristics. Both impedance...
-
Elimination of impulsive disturbances from archive audio files – comparison of three noise pulse detection schemes
PublikacjaThe problem of elimination of impulsive disturbances (such as clicks, pops, ticks, crackles, and record scratches) from archive audio recordings is considered and solved using autoregressive modeling. Three classical noise pulse detection schemes are examined and compared: the approach based on open-loop multi-step-ahead signal prediction, the approach based on decision-feedback signal prediction, and the double threshold approach,...
-
Multimodal Approach For Polysensory Stimulation And Diagnosis Of Subjects With Severe Communication Disorders
Publikacjais evaluated on 9 patients, data analysis methods are described, and experiments of correlating Glasgow Coma Scale with extracted features describing subjects performance in therapeutic exercises exploiting EEG and eyetracker are presented. Performance metrics are proposed, and k-means clusters used to define concepts for mental states related to EEG and eyetracking activity. Finally, it is shown that the strongest correlations...
-
Multimodal Surveillance Based Personal Protection System
PublikacjaA novel, multimodal approach for automatic detection of abduction of a protected individual, employing dedicated personal protection device and a city monitoring system is proposed and overviewed. The solution is based on combining four modalities (signals coming from: Bluetooth, fixed and PTZ cameras, thermal camera, acoustic sensors). The Bluetooth signal is used continuously to monitor the protected person presence, and in case...
-
A machine learning approach to classifying New York Heart Association (NYHA) heart failure
PublikacjaAccording 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...
-
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...
-
Damage detection in plates based on Lamb wavefront shape reconstruction
PublikacjaMany of the current studies in the area of damage detection using elastic wave propagation are based on deploying sensor networks with a large number of piezoelectric transducers to detect small-size cracks. A major limitation of these studies is that cracks are usually larger and have different shapes in real cases. Moreover, using a large number of sensing nodes for damage detection is both costly and computationally intensive....
-
Eye Blink Based Detection of Liveness in Biometric Authentication Systems Using Conditional Random Fields
PublikacjaThe goal of this paper was to verify whether the conditional random fields are suitable and enough efficient for eye blink detection in user authentication systems based on face recognition with a standard web camera. To evaluate this approach several experiments were carried on using a specially developed test application and video database.
-
Verification of the Parameterization Methods in the Context of Automatic Recognition of Sounds Related to Danger
PublikacjaW artykule opisano aplikację, która automatycznie wykrywa zdarzenia dźwiękowe takie jak: rozbita szyba, wystrzał, wybuch i krzyk. Opisany system składa się z bloku parametryzacji i klasyfikatora. W artykule dokonano porównania parametrów dedykowanych dla tego zastosowania oraz standardowych deskryptorów MPEG-7. Porównano też dwa klasyfikatory: Jeden oparty o Percetron (sieci neuronowe) i drugi oparty o Maszynę wektorów wspierających....
-
Shore Construction Detection by Automotive Radar for the Needs of Autonomous Surface Vehicle Navigation
PublikacjaAutonomous surface vehicles (ASVs) are becoming more and more popular for performing hydrographic and navigational tasks. One of the key aspects of autonomous navigation is the need to avoid collisions with other objects, including shore structures. During a mission, an ASV should be able to automatically detect obstacles and perform suitable maneuvers. This situation also arises in near-coastal areas, where shore structures like...
-
Biomolecular influenza virus detection based on the electrochemical impedance spectroscopy using the nanocrystalline boron-doped diamond electrodes with covalently bound antibodies
PublikacjaNew rapid pathogen detection methods with improved cost-effectiveness and efficiency are currently in the focus of the scientists from all over the world. Based on the experiences from the rapid spread of the influenza virus pandemic in 2009 it is clear that the development of the system for early diagnosis of this infection is essential. The crucial stage of the treatment is the detection of the viral infection during its initial...
-
Highlighting interlanguage phoneme differences based on similarity matrices and convolutional neural network
PublikacjaThe goal of this research is to find a way of highlighting the acoustic differences between consonant phonemes of the Polish and Lithuanian languages. For this purpose, similarity matrices are employed based on speech acoustic parameters combined with a convolutional neural network (CNN). In the first experiment, we compare the effectiveness of the similarity matrices applied to discerning acoustic differences between consonant...
-
Multiclass AdaBoost Classifier Parameter Adaptation for Pattern Recognition
PublikacjaThe article presents the problem of parameter value selection of the multiclass ``one against all'' approach of an AdaBoost algorithm in tasks of object recognition based on two-dimensional graphical images. AdaBoost classifier with Haar features is still used in mobile devices due to the processing speed in contrast to other methods like deep learning or SVM but its main drawback is the need to assembly the results of binary...
-
Hierarchical 2-step neural-based LEGO bricks detection and labeling
PublikacjaLEGO bricks are extremely popular and allow the creation of almost any type of construction due to multiple shapes available. LEGO building requires however proper brick arrangement, usually done by shape. With over 3700 different LEGO parts this can be troublesome. In this paper, we propose a solution for object detection and annotation on images. The solution is designed as a part of an automated LEGO bricks arrangement. The...
-
Diver Observations by Means of Acoustic Methods
PublikacjaSearching for objects, especially small ones, moving under water near its the free surface, is always not an easy task. Designing tools for the detection of such targets is a real challenge when the possibility of a terrorist attack is a real threat. This paper presents some aspects of diver detection by means of acoustics methods, both active (side scan sonar) and passive ones (linear receiving antenna). This approach is quite...
-
Damage localisation in a stiffened plate structure using a propagating wave
PublikacjaThe paper presents an application of changes in propagating waves for damage detection in a stiffened aluminium plate. The experimental investigation was conducted on an aluminium plate with riveted two L-shape stiffeners. The wave has been excited with a piezoelectric transducer and measured with the Laser Scanning Doppler Vibrometer. Recorded signals were analysed using the special signal processing techniques developed for damage...
-
Real-Time Facial Features Detection from Low Resolution Thermal Images with Deep Classification Models
PublikacjaDeep networks have already shown a spectacular success for object classification and detection for various applications from everyday use cases to advanced medical problems. The main advantage of the classification models over the detection models is less time and effort needed for dataset preparation, because classification networks do not require bounding box annotations, but labels at the image level only. Yet, after passing...
-
Optimized AVHRR land surface temperature downscaling method for local scale observations: case study for the coastal area of the Gulf of Gdańsk
PublikacjaSatellite imaging systems have known limitations regarding their spatial and temporal resolution. The approaches based on subpixel mapping of the Earth’s environment, which rely on combining the data retrieved from sensors of higher temporal and lower spatial resolution with the data characterized by lower temporal but higher spatial resolution, are of considerable interest. The paper presents the downscaling process of the land...
-
Automatic detection and correction of detuned singing system for use with query-by-humming applications
PublikacjaThe aim of the paper is to present an idea of using the automatic detection and correction of detuned singing as a subsystem in query-by-humming (QBH) applications. The common approach to searching for a requested song basing on the melody retrieved from hummed pattern usually employs the so-called Parsons code or melody contour. In such a case information about sound pitch is discarded. It was thought out that an additional module...
-
Detection and Direction-of-Arrival Estimation of Weak Spread Spectrum Signals Received with Antenna Array
PublikacjaThis paper presents a method for the joint detection and direction of arrival (DOA) estimation of low probability of detection (LPD) signals. The proposed approach is based on using the antenna array to receive spread-spectrum signals hidden below the noise floor. Array processing exploits the spatial correlation between phase-delayed copies of the signal and allows us to evaluate the parameter used to make the decision about the...