Search
displaying 1000 best results Help
Search results for: ai safety · robustness · uncertainty estimation · pedestrian detection · object detection.
-
LDNet: A Robust Hybrid Approach for Lie Detection Using Deep Learning Techniques
PublicationDeception detection is regarded as a concern for everyone in their daily lives and affects social interactions. The human face is a rich source of data that offers trustworthy markers of deception. The deception or lie detection systems are non-intrusive, cost-effective, and mobile by identifying facial expressions. Over the last decade, numerous studies have been conducted on deception detection using several advanced techniques....
-
Interpretable Deep Learning Model for the Detection and Reconstruction of Dysarthric Speech
PublicationWe present a novel deep learning model for the detection and reconstruction of dysarthric speech. We train the model with a multi-task learning technique to jointly solve dysarthria detection and speech reconstruction tasks. The model key feature is a low-dimensional latent space that is meant to encode the properties of dysarthric speech. It is commonly believed that neural networks are black boxes that solve problems but do not...
-
Smart city and fire detection using thermal imaging
PublicationIn this paper, we summarize the results obtained from fire experiments. The aim of the work was to develop new methods of fire detection using IR thermal imaging cameras and dedicated image processing. We conducted 4 experiments in different configurations and with the use of different objects. The conducted experiments have shown the great usefulness of infrared cameras for detecting the seeds of a fire. Even cheap low-resolution...
-
Small rov to detection and identification of dangerous underwater objects
PublicationA small unmanned underwater vehicle (UUV) to inspection of an undersea space is presented in the paper. Its behavior is controlled by a trained pilot. Correct detection and identification of targets depends on vehicle'sprecise displacement along a predefined route. Nowadays, the UUVs are equipped with an automatic control system to execute some basic maneuvers without constant human interventions. Hence, in the paper, an autopilot...
-
Influence of statistical errors on damage detection based on structuralflexibility and mode shape curvature
PublicationDamage detection procedures based on measured natural frequencies and building structure mode shapes are discussed in this paper. Modal curvature and structural flexibility approaches are tested. Attention is paid to the modal identification errors that influence damage detection. This problem is studied using a computer simulation of a simple supported beam. For practical cases, the peak picking methodand its statistical errors...
-
Loudness Scaling Tests in Hearing Problems Detection
PublicationThe number of people using portable audio players has increased significantly over the recent years. This implies the rise in the number of people having hearing loss problems. Therefore, there is a need to find appropriate procedures that simplify the process of the hearing problem detection. Investigations performed show that audiometric tests may not be sufficient to assess hearing in young people. Contrarily, the obtained results...
-
Experimental test of nonclassicality with arbitrarily low detection efficiency
PublicationWe theoretically introduce and experimentally demonstrate the realization of a nonclassicality test that allows for arbitrarily low detection efficiency without invoking an extra assumption of independence of the devices. Our test and its implementation is set in a prepare-and-measure scenario with an upper limit on the classical communication capacity of the channel through which the systems are communicated. The essence for our...
-
Feasibility study of a Raman spectroscopic route to drug detection
PublicationWe present an surface-enhanced Raman spectroscopy (SERS) approach for detection of drugs of abuse in whole human blood. We utilize a near infrared laser with 830 nm excitation wavelength in order to reduce the influence of fluorescence on the spectra of blood. However, regular plasmon resonance peak of plasmonic nanoparticles, such as silver or gold fall in a much lower wavelength regime about 400 nm. Therefore, we have shifted...
-
Spectral Methods for Modelling of Wave Propagation in Structures in Terms of Damage Detection—A Review
PublicationModern methods of detection and identification of structural damage direct the activities of scientific groups towards the improvement of diagnostic methods using for example the phenomenon of mechanical wave propagation. Damage detection methods that use mechanical wave propagation in structural components are extremely effective. Many different numerical approaches are used to model this phenomenon, but, due to their universal...
-
Commercial systems for automatic detection of events. Features, limitations and potential solutions
PublicationVideo Content Analysis (VCA). Motion detection. Example of complex VCA system. Commercial VCA systems and their applications. Limitations and problems. Possible solutions.
-
Algorithms of chemicals detection using raman spectra
PublicationRaman spectrometers are devices which enable fast and non-contact identification of examined chemicals. These devices utilize the Raman phenomenon to identify unknown and often illicit chemicals (e.g. drugs, explosives)without the necessity of their preparation. Now, Raman devices can be portable and therefore can be more widely used to improve security at public places. Unfortunately, Raman spectra measurements is a challenge...
-
The use of machine learning for face regions detection in thermograms
PublicationThe aim of this study is to analyse the methods of detecting characteristic points of the face in thermographic images. As part of the implementation an extensive analysis of scientific publications covering similar issues both for the analysis of images made in visible light and thermographic images was carried out. On the basis of this analysis, 3 models were selected and then they were implemented and tested on the basis of...
-
Piotr Szczuko dr hab. inż.
PeoplePiotr Szczuko received his M.Sc. degree in 2002. His thesis was dedicated to examination of correlation phenomena between perception of sound and vision for surround sound and digital image. He finished Ph.D. studies in 2007 and one year later completed a dissertation "Application of Fuzzy Rules in Computer Character Animation" that received award of Prime Minister of Poland. His interests include: processing of audio and video, computer...
-
Overhead wires detection by FPGA real-time image processing
PublicationThe paper presents design and hardware implementation of real-time image filtering for overhead wires detection divided on image processing and results presentation blocks. The image processing block was separated from the whole implementation, and its delay and hardware complexity was analysed. Also the maximum frequency of image processing of the proposed implementation was estimated.
-
Bees Detection on Images: Study of Different Color Models for Neural Networks
PublicationThis paper presents an approach to bee detection in video streams using a neural network classifier. We describe the motivation for our research and the methodology of data acquisition. The main contribution to this work is a comparison of different color models used as an input format for a feedforward convolutional architecture applied to bee detection. The detection process has is based on a neural binary classifier that classifies...
-
The effectivness of fault detection in common rail injectors examination methods
PublicationThe article presents the effectiveness tests of fault detection in common rail injectors. 40 injectors with different wear levels were tested. Testing was made on two test benches of a completely different design. Research includes comparison of accuracy, reproducibility and testability to detect specific defects. A device was created for visualization of the fuel injector spraying steam.
-
Analysis of Drone Signals Based on Change Point Detection Algorithm
PublicationThe work presents an algorithm characterized by high precision and efficiency in identifying signals related to data transmission between the controller and the drone. Using an efficient change point detection algorithm and parallel analysis capabilities, this method facilitates rapid signal analysis. These features make the proposed algorithm a solid basis for developing an effective anti-drone defense system.
-
Real-time PCR approach in dermatophyte detection and Trichophyton rubrum identification
PublicationDermatophytes are keratinophilic molds that infect human hair, nails and skin. Diagnosis of dermatophytosis is based on morphological, serological and biochemical features. However, identification is difficult and laborious due to similarities between microorganisms. Thus, there is considerable interest to develop mycological diagnostic procedures based on molecular biology methods. In this study, fast, two-step DNA extraction...
-
Automatic detection and correction of detuned singing system for use with query-by-humming applications
PublicationThe 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...
-
Application of method of differential magnetometric system for detection of sunken objects
PublicationThis paper presents a magnetometric system with scalar sensors mounted on two independent platforms, which is used to detect sunken shipwrecks. Increasing the distance between the sensors allows for more precise measurement of the difference in the magnetic induction module than in the case of sensors mounted e.g. on the aeroplane’s wings. This type of system makes it possible to enlarge detection range of the sunken wrecks.
-
Speed Sensorless AC Drive with Inverter LC Filter and Fault Detection Using Load Torque Signal
PublicationThe industrial development in recent years has seen a major increase in the use of induction motors, whereby the cost has to be as low as possible and the lifetime as long as possible. To follow up this desire, investigations in this area have become very intense. For that reason, this paper presents a solution for driving an induction motor and simultaneous fault detection with no need for additional sensors. In order to achieve...
-
Stress Detection of Children With ASD Using Physiological Signals
PublicationThis paper proposes a physiological signal-based stress detection approach for children with autism spectrum disorder (ASD) to be used in social and assistive robot inter- vention. Electrodermal activity (EDA) and blood volume pulse (BVP) signals are collected with an E4 smart wristband from children with ASD in different countries. The peak count and signal amplitude features are derived from EDA signal and used in order to detect...
-
Automatic detection and correction of detuned singing system for use with query-by-humming applications
PublicationThe 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...
-
Labeler-hot Detection of EEG Epileptic Transients
PublicationPreventing early progression of epilepsy and sothe severity of seizures requires effective diagnosis. Epileptictransients indicate the ability to develop seizures but humansoverlook such brief events in an electroencephalogram (EEG)what compromises patient treatment. Traditionally, trainingof the EEG event detection algorithms has relied on groundtruth labels, obtained from the consensus...
-
Optical fiber aptasensor for label-free bacteria detection in small volumes
PublicationHighly sensitive devices for fast bacteria detection are sought to be developed with the task of quantifying the worldwide problem of pathogenic bacteria and thus helping to take control over spreading bacterial infections. This work concerns a sensing solution based on microcavity in-line Mach-Zehnder interferometer (μIMZI) induced in an optical fiber. Such a device exhibits ultrahigh sensitivity to refractive index changes...
-
Face with Mask Detection in Thermal Images Using Deep Neural Networks
PublicationAs the interest in facial detection grows, especially during a pandemic, solutions are sought that will be effective and bring more benefits. This is the case with the use of thermal imaging, which is resistant to environmental factors and makes it possible, for example, to determine the temperature based on the detected face, which brings new perspectives and opportunities to use such an approach for health control purposes. The...
-
Vehicle Detection with Self-Training for Adaptative Video Processing Embedded Platform
PublicationTraffic monitoring from closed-circuit television (CCTV) cameras on embedded systems is the subject of the performed experiments. Solving this problem encounters difficulties related to the hardware limitations, and possible camera placement in various positions which affects the system performance. To satisfy the hardware requirements, vehicle detection is performed using a lightweight Convolutional Neural Network (CNN), named...
-
A Simple Neural Network for Collision Detection of Collaborative Robots
PublicationDue to the epidemic threat, more and more companies decide to automate their production lines. Given the lack of adequate security or space, in most cases, such companies cannot use classic production robots. The solution to this problem is the use of collaborative robots (cobots). However, the required equipment (force sensors) or alternative methods of detecting a threat to humans are usually quite expensive. The article presents...
-
Specific detection of Alternaria alternata by PCR and real-time PCR
PublicationFungi of Alternaria genus are cosmopolitan organisms, which spores can be found in the air, soil, water, clothing and food. They commonly occur as saprotrophs on the plant remains, contributing to the decomposition of organic matter. Additionally, they are components of the normal human and animal skin flora. Alternaria spp. are also known human allergens, causing hay fever and allergic reactions that can lead to the development...
-
Detection of anomalies in bee colony using transitioning state and contrastive autoencoders
PublicationHoneybees plays vital role for the environmental sustainability and overall agricultural economy. Assisting bee colonies within their proper functioning brings the attention of researchers around the world. Electronics systems and machine learning algorithms are being developed for classifying specific undesirable bee behaviors in order to alert about upcoming substantial losses. However, classifiers could be impaired when used...
-
Visual Lip Contour Detection for the Purpose of Speech Recognition
PublicationA method for visual detection of lip contours in frontal recordings of speakers is described and evaluated. The purpose of the method is to facilitate speech recognition with visual features extracted from a mouth region. Different Active Appearance Models are employed for finding lips in video frames and for lip shape and texture statistical description. Search initialization procedure is proposed and error measure values are...
-
Anomaly Detection in Railway Sensor Data Environments: State-of-the-Art Methods and Empirical Performance Evaluation
PublicationTo date, significant progress has been made in the field of railway anomaly detection using technologies such as real-time data analytics, the Internet of Things, and machine learning. As technology continues to evolve, the ability to detect and respond to anomalies in railway systems is once again in the spotlight. However, railway anomaly detection faces challenges related to the vast infrastructure, dynamic conditions, aging...
-
Detection of immunological agent by optical fiber sensor: preliminary study
PublicationThe objective of this study is the application of optical methods for detection of immunological agent concentration. As the agent we used the Cyclaid, produced by Apotex Inc. In this article we investigated different Cyclaid concentrations in water. We used a Fabry-Pérot interferometer working in a reflective mode, the measurements were performed with source with central wavelength λ = 1550 nm. The preliminary investigation have...
-
Real-Time Facial Features Detection from Low Resolution Thermal Images with Deep Classification Models
PublicationDeep 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...
-
Outlier detection method by using deep neural networks
PublicationDetecting outliers in the data set is quite important for building effective predictive models. Consistent prediction can not be made through models created with data sets containing outliers, or robust models can not be created. In such cases, it may be possible to exclude observations that are determined to be outlier from the data set, or to assign less weight to these points of observation than to other points of observation....
-
Automatic Detection of Nerves in Confocal Corneal Images with Orientation-Based Edge Merging
PublicationThe paper presents an algorithm for improving results of automatic nerve detections in confocal microscopy images of human corneal. The method is designed as a postprocessing step of regular detection. After the nerves are initially detected, the algorithms attempts to improve the results by filling unde-sired gaps between single nerves detections in order to correctly mark the entire nerve instead of only parts of it. This approach...
-
Guided Wave Propagation in Detection of Partial Circumferential Debonding in Concrete Structures
PublicationThe following article presents results of investigating the damage detection in reinforced concrete beams with artificially introduced debonding between the rod and cover, using a non-destructive method based on elastic waves propagation. The primary aim of the research was to analyze the possible use of guided waves in partial circumferential debonding detection. Guided waves were excited and registered in reinforced concrete...
-
An Overview of Image Analysis Techniques in Endoscopic Bleeding Detection
PublicationAuthors 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...
-
Fluctuation-Enhanced Sensing for Biological Agent Detection and Identification
PublicationPrzedstawiono wcześniejsze wyniki badań dotyczące trzech różnych sposobów wykrywania obecności substancji biologicznych za pomocą zjawisk fluktuacyjnych: 1) wirusów wnikających do komórek, 2) zapachów emitowanych przez mikroby, 3) rozkładu widma i wartości chwilowych szumów podczas rozpraszania światła używanego do wykrywania zarodników na podstawie wyznaczenia współczynnika dyfuzji opisująceo ich ruch.We survey and show our earlier...
-
Uncertainty of Postmortem Time Estimation Based on Potassium Ion Determination in Vitreous Humor Using Potentiometric Ion-Selective Electrode and Microwave-Induced Plasma with Optical Emission Spectrometry Methods
PublicationThere is a need for a reliable and independent evaluation and confirmation of the post-mortem interval (PMI) based on objective factors other than only postmortem changes or temperature measurements. Estimating the PMI by examining the concentration of potassium ions in the vitreous humor (VH) has a tradition in forensic toxicology dating back to the mid-20th century. So far, the methods for determining the presence of potassium...
-
A Multi-Antenna Scheme for Early Detection and Mitigation of Intermediate GNSS Spoofing
PublicationThis article presents a method for detecting and mitigating intermediate GNSS spoofing. In this type of attack, at its early stage, a spoofer transmits counterfeit signals which have slight time offsets compared to true signals arriving from satellites. The anti-spoofing method proposed in this article fuses antenna array processing techniques with a multipath detection algorithm. The latter is necessary to separate highly correlated...
-
Feature type and size selection for adaboost face detection algorithm
PublicationThe article presents different sets of Haar-like features defined for adaptive boosting (AdaBoost) algorithm for face detection. Apart from a simple set of pixel intensity differences between horizontally or vertically neighboring rectangles, the features based on rotated rectangles are considered. Additional parameter that limits the area on which the features are calculated is also introduced. The experiments carried out on...
-
Experimental verification and comparison of mode shape-based damage detection methods
PublicationThis paper presents experimental verification and comparison of damage detection methods based on changes in mode shapes such as: mode shape curvature (MSC), modal assurance criterion (MAC), strain energy (SE), modified Laplacian operator (MLO), generalized fractal dimension (GFD) and Wavelet Transform (WT).
-
Efficiency of gas mixtures detection by resistive gas sensors
PublicationResistive gas sensors are very popular and are commonly used to detect various gases and their mixtures. Theeir main disadvantage is very limited selectivity. Practical use of gas sensors in environenmental applications requires determination of concentration of a few mixed gases at the same time. We would like to present recent results of gas detection improvement by utilizing a single gas sensor and additional measurements to...
-
Detection of Face Position and Orientation Using Depth Data
PublicationIn this paper an original approach is presented for real-time detection of user's face position and orientation based only on depth channel from a Microsoft Kinect sensor which can be used in facial analysis on scenes with poor lighting conditions where traditional algorithms based on optical channel may have failed. Thus the proposed approach can support, or even replace, algorithms based on optical channel or based on skeleton...
-
Histogram of Gradients with Cell Average Intensity for Human Detection
PublicationThe modification of the descriptor in human detector using Histogram of Oriented Gradients and support vector machine is presented. The proposed modification requires inserting the average cell intensitiesresulting with the increase of the length of the descriptor from 3780 to 4200 values, but it is easy to compute and instantly gives 14-26% of miss rate improvement at 10^-4 False Positives Per Window (FPPW). The modification...
-
Optimal placement of IMU sensor for the detection of children activity
PublicationIn this paper an investigation to determine the optimal placement of IMU sensors for the purpose of children characteristic activity detection is presented. The article compares four different placement of two IMU sensors on human body. Ten healthy volunteers participated within the study. Data were collected firstly from two wireless 9-axial IMU sensors placed at the left and right wrists, then sensors were placed at lower back...
-
Real-Time Bleeding Detection in Gastrointestinal Tract Endoscopic Examinations Video
PublicationThe article presents a novel approach to medical video data analysis and recognition of bleedings. Emphasis has been put on adapting pre-existing algorithms dedicated to the detection of bleedings for real-time usage in a medical doctor’s office during an endoscopic examination. A real-time system for analyzing endoscopic videos has been designed according to the most significant requirements of medical doctors. The main goal of...
-
Reusable Biosensor for Easy RNA Detection from Unfiltered Saliva
PublicationBiosensors are transforming point-of-care diagnostics by simplifying the detection process and enabling rapid, accurate testing. This study introduces a novel, reusable biosensor designed for direct viral RNA detection from unfiltered saliva, targeting SARS-CoV-2. Unlike conventional methods requiring filtration, our biosensor leverages a unique electrode design that prevents interference from saliva debris, allowing precise measurements....
-
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...