Filters
total: 248
filtered: 225
Search results for: deblurring, denoising, multi-task learning, video enhancement
-
Multi-task Video Enhancement for Dental Interventions
PublicationA microcamera firmly attached to a dental handpiece allows dentists to continuously monitor the progress of conservative dental procedures. Video enhancement in video-assisted dental interventions alleviates low-light, noise, blur, and camera handshakes that collectively degrade visual comfort. To this end, we introduce a novel deep network for multi-task video enhancement that enables macro-visualization of dental scenes. In particular,...
-
Concurrent Video Denoising and Deblurring for Dynamic Scenes
PublicationDynamic scene video deblurring is a challenging task due to the spatially variant blur inflicted by independently moving objects and camera shakes. Recent deep learning works bypass the ill-posedness of explicitly deriving the blur kernel by learning pixel-to-pixel mappings, which is commonly enhanced by larger region awareness. This is a difficult yet simplified scenario because noise is neglected when it is omnipresent in a wide...
-
Leveraging spatio-temporal features for joint deblurring and segmentation of instruments in dental video microscopy
PublicationIn dentistry, microscopes have become indispensable optical devices for high-quality treatment and micro-invasive surgery, especially in the field of endodontics. Recent machine vision advances enable more advanced, real-time applications including but not limited to dental video deblurring and workflow analysis through relevant metadata obtained by instrument motion trajectories. To this end, the proposed work addresses dental...
-
Analysis of Denoising Autoencoder Properties Through Misspelling Correction Task
PublicationThe paper analyzes some properties of denoising autoencoders using the problem of misspellings correction as an exemplary task. We evaluate the capacity of the network in its classical feed-forward form. We also propose a modification to the output layer of the net, which we called multi-softmax. Experiments show that the model trained with this output layer outperforms traditional network both in learning time and accuracy. We...
-
BP-EVD: Forward Block-Output Propagation for Efficient Video Denoising
PublicationDenoising videos in real-time is critical in many applications, including robotics and medicine, where varying light conditions, miniaturized sensors, and optics can substantially compromise image quality. This work proposes the first video denoising method based on a deep neural network that achieves state-of-the-art performance on dynamic scenes while running in real-time on VGA video resolution with no frame latency. The backbone...
-
Intelligent video and audio applications for learning enhancement
PublicationThe role of computers in school education is briefly discussed. Multimodal interfaces development history is shortly reviewed. Examples of applications of multimodal interfaces for learners with special educational needs are presented, including interactive electronic whiteboard based on video image analysis, application for controlling computers with facial expression and speech stretching audio interface representing audio modality....
-
Task Assignments in Logistics by Adaptive Multi-Criterion Evolutionary Algorithm with Elitist Selection
PublicationAn evolutionary algorithm with elitist selection has been developed for finding Pareto-optimal task assignments in logistics. A multi-criterion optimization problem has been formulated for finding a set of Pareto- optimal solutions. Three criteria have been applied for evaluation of task assignment: the workload of a bottleneck machine, the cost of machines, and the numerical performance of system. The machine constraints have...
-
Machine Learning in Multi-Agent Systems using Associative Arrays
PublicationIn this paper, a new machine learning algorithm for multi-agent systems is introduced. The algorithm is based on associative arrays, thus it becomes less complex and more efficient substitute of artificial neural networks and Bayesian networks, which is confirmed by performance measurements. Implementation of machine learning algorithm in multi-agent system for aided design of selected control systems allowed to improve the performance...
-
Predicting emotion from color present in images and video excerpts by machine learning
PublicationThis work aims at predicting emotion based on the colors present in images and video excerpts using a machine-learning approach. The purpose of this paper is threefold: (a) to develop a machine-learning algorithm that classifies emotions based on the color present in an image, (b) to select the best-performing algorithm from the first phase and apply it to film excerpt emotion analysis based on colors, (c) to design an online survey...
-
Unsupervised machine-learning classification of electrophysiologically active electrodes during human cognitive task performance
PublicationIdentification of active electrodes that record task-relevant neurophysiological activity is needed for clinical and industrial applications as well as for investigating brain functions. We developed an unsupervised, fully automated approach to classify active electrodes showing event-related intracranial EEG (iEEG) responses from 115 patients performing a free recall verbal memory task. Our approach employed new interpretable...
-
Multi-Stage Video Analysis Framework
Publication -
Multi-Stage Video Analysis Framework
PublicationThe chapter is organized as follows. Section 2 presents the general structure of the proposed framework and a method of data exchange between system elements. Section 3 is describing the low-level analysis modules for detection and tracking of moving objects. In Section 4 we present the object classification module. Sections 5 and 6 describe specialized modules for detection and recognition of faces and license plates, respectively....
-
Dataset Characteristics and Their Impact on Offline Policy Learning of Contextual Multi-Armed Bandits
PublicationThe Contextual Multi-Armed Bandits (CMAB) framework is pivotal for learning to make decisions. However, due to challenges in deploying online algorithms, there is a shift towards offline policy learning, which relies on pre-existing datasets. This study examines the relationship between the quality of these datasets and the performance of offline policy learning algorithms, specifically, Neural Greedy and NeuraLCB. Our results...
-
Design and Implementation of Multi-Band Reflectarray Metasurface for 5G Millimeter Wave Coverage Enhancement
PublicationA compact low-profile multi-band millimeter-wave (mm-wave) reflectarray metasurface design is presented for coverage enhancement in 5G and beyond cellular communication. The proposed single-layer metasurface exhibits a stable reflection response under oblique incidence angles of up to 60o at 24 and 38 GHz, and transmission response at 30 GHz, effectively covering the desired 5G mm-wave frequency bands. The proposed reflectarray...
-
Software Factory project for enhancement of student experiential learning
PublicationProviding opportunities for students to work on real-world software development projects for real customers is critical to prepare students for the IT industry. Such projects help students to understand what they will face in the industry and experience real customer interaction and challenges in collaborative work. To provide this opportunity in an academic environment and enhance the learning and multicultural teamwork experience,...
-
Scent emitting multimodal computer interface for learning enhancement
PublicationKomputerowy interfejs aromatyczny stanowi ważne uzupełnienie procesu stymulacji polisensorycznej. Stymulacja ta odgrywa kluczową rolę w terapii i kształceniu dzieci z zaburzeniami rozwoju (np. w przypadku autyzmu czy ADHD). Opracowany interfejs może stać się elementem wyposażenia tzw. sal doświadczania świata, ale może być także stosowany niezależnie stanowiąc znaczące wzbogacenie komputerowych programów edukacyjnych. Dzięki możliwości...
-
Noise profiling for speech enhancement employing machine learning models
PublicationThis paper aims to propose a noise profiling method that can be performed in near real-time based on machine learning (ML). To address challenges related to noise profiling effectively, we start with a critical review of the literature background. Then, we outline the experiment performed consisting of two parts. The first part concerns the noise recognition model built upon several baseline classifiers and noise signal features...
-
Analyzing the Effectiveness of the Brain–Computer Interface for Task Discerning Based on Machine Learning
PublicationThe aim of the study is to compare electroencephalographic (EEG) signal feature extraction methods in the context of the effectiveness of the classification of brain activities. For classification, electroencephalographic signals were obtained using an EEG device from 17 subjects in three mental states (relaxation, excitation, and solving logical task). Blind source separation employing independent component analysis (ICA) was...
-
Rapid Surrogate-Aided Multi-Criterial Optimization of Compact Microwave Passives Employing Machine Learning and ANNs
PublicationThis article introduces an innovative method for achieving low-cost and reliable multi-objective optimization (MO) of microwave passive circuits. The technique capitalizes on the attributes of surrogate models, specifically artificial neural networks (ANNs), and multi-resolution electromagnetic (EM) analysis. We integrate the search process into a machine learning (ML) framework, where each iteration produces multiple infill points...
-
Machine Learning Assisted Interactive Multi-objectives Optimization Framework: A Proposed Formulation and Method for Overtime Planning in Software Development Projects
PublicationMachine Learning Assisted Interactive Multi-objectives Optimization Framework: A Proposed Formulation and Method for Overtime Planning in Software Development Projects Hammed A. Mojeed & Rafal Szlapczynski Conference paper First Online: 14 September 2023 161 Accesses Part of the Lecture Notes in Computer Science book series (LNAI,volume 14125) Abstract Software development project requires proper planning to mitigate risk and...
-
Adaptive Sampling for Non-intrusive Reduced Order Models Using Multi-Task Variance
PublicationNon-intrusive reduced order modeling methods (ROMs) have become increasingly popular for science and engineering applications such as predicting the field-based solutions for aerodynamic flows. A large sample size is, however, required to train the models for global accuracy. In this paper, a novel adaptive sampling strategy is introduced for these models that uses field-based uncertainty as a sampling metric. The strategy uses...
-
Cost-Efficient Multi-Objective Design of Miniaturized Microwave Circuits Using Machine Learning and Artificial Neural Network
PublicationDesigning microwave components involves managing multiple objectives such as center frequencies, impedance matching, and size reduction for miniaturized structures. Traditional multi-objective optimization (MO) approaches heavily rely on computationally expensive population-based methods, especially when exe-cuted with full-wave electromagnetic (EM) analysis to guarantee reliability. This paper introduces a novel and cost-effective...
-
Expedited Machine-Learning-Based Global Design Optimization of Antenna Systems Using Response Features and Multi-Fidelity EM Analysis
PublicationThe design of antenna systems poses a significant challenge due to stringent per-formance requirements dictated by contemporary applications and the high com-putational costs associated with models, particularly full-wave electromagnetic (EM) analysis. Presently, EM simulation plays a crucial role in all design phases, encompassing topology development, parametric studies, and the final adjustment of antenna dimensions. The latter...
-
The Effectiveness of Using a Pretrained Deep Learning Neural Networks for Object Classification in Underwater Video
Publication -
POPULATION-BASED MULTI-AGENT APPROACH TO SOLVING MACHINE LEARNING PROBLEMS
Publication -
Supervised-learning-based development of multi-bit RCS-reduced coding metasurfaces
PublicationCoding metasurfaces have been introduced as efficient tools allowing meticulous control over the electromagnetic (EM) scattering. One of their relevant application areas is radar cross section (RCS) reduction, which principally relies on the diffusion of impinging EM waves. Despite its significance, careful control of the scattering properties poses a serious challenge at the level of practical realization. This article is concerned...
-
Enhancement of lift and drag performances of a NACA0012 airfoil by multi-DBD plasma actuator with additional floating interelectrodes
PublicationIt is clear that the improvement of aircraft aerodynamic performances is currently and will continue to be a significant area of research for the aeronautical industry. The current study is focused on theenhancement of aerodynamic airfoil performances by using a multi-DBD plasma actuator mounted around the model leading-edge. Experiments have been conducted at the University of Orleans, in the 2 m x 2 m test section of a large...
-
Solvent Screening for Solubility Enhancement of Theophylline in Neat, Binary and Ternary NADES Solvents: New Measurements and Ensemble Machine Learning
PublicationTheophylline, a typical representative of active pharmaceutical ingredients, was selected to study the characteristics of experimental and theoretical solubility measured at 25 °C in a broad range of solvents, including neat, binary mixtures and ternary natural deep eutectics (NADES) prepared with choline chloride, polyols and water. There was a strong synergistic effect of organic solvents mixed with water, and among the experimentally...
-
Modeling of Performance And Safety of a Multi-Task Unmanned Autonomous Maritime Vehicle / Modelowanie Ruchu i Bezpieczeństwa Wielozadaniowego Bezzałogowego Autonomicznego Pojazdu Wodnego
Publication -
Modeling of performance and safety of a multi-task unmanned autonomous maritime vehicle = Modelowanie ruchu i bezpieczeństwa wielozadaniowego bezzałogowego autonomicznego pojazdu wodnego
PublicationAt the beginning of the paper the aim of research is presented. Then the method is introduced. Next, the unmanned autonomous maritime vehicle is briefly described. The following chapter concerns a model of vehicle performance including the ballasting and motion. Some information on an integrated steering, positioning and stabilization system of the vehicle is briefly presented in the paper. Such the system enables to obtain a fully...
-
The System of the Supervision and the Visualization of Multimedia Data for BG
PublicationMonitoring of country maritime border is an important task of the Border Guard. This task can be facilitated with the use of the technology enabling gathering information from distributed sources and its supervision and visualization. The system presented in the paper is an extension and enhancement of the previously developed distributed system map data exchange system. The added functionalities allow supplementation of map data...
-
Streaming Real-time Data in Distributed Dispatcher and Teleinformation Systems for Visualization of Multimedia Data of the Border Guard
PublicationSurveillance of the sea borders is a very important task for the Border Guard. Monitoring of country maritime border is an important task of the Border Guard. This task can be facilitated with the use of the technology enabling gathering information from distributed sources and its supervision and visualization. This task can be accomplished using a technology that allows to collect information from distributed sensors of different...
-
Bimodal deep learning model for subjectively enhanced emotion classification in films
PublicationThis research delves into the concept of color grading in film, focusing on how color influences the emotional response of the audience. The study commenced by recalling state-of-the-art works that process audio-video signals and associated emotions by machine learning. Then, assumptions of subjective tests for refining and validating an emotion model for assigning specific emotional labels to selected film excerpts were presented....
-
Performance Evaluation of the Parallel Codebook Algorithm for Background Subtraction in Video Stream
PublicationA background subtraction algorithm based on the codebook approach was implemented on a multi-core processor in a parallel form, using the OpenMP system. The aim of the experiments was to evaluate performance of the multithreaded algorithm in processing video streams recorded from monitoring cameras, depending on a number of computer cores used, method of task scheduling, image resolution and degree of image content variability....
-
Superresolution algorithm to video surveillance system
PublicationAn application of a multiframe SR (superresolution) algorithm applied to video monitoring is described. The video signal generated by various types of video cameras with different parameters and signal distortions which may be very problematic for superresolution algorithms. The paper focuses on disadvantages in video signal which occur in video surveillance systems. Especially motion estimation and its influence on superresolution...
-
Aktywny system RFID do lokalizacji i identyfikacji obiektów w wielomodalnej infrastrukturze bezpieczeństwa
PublicationPrzedstawiono prace koncepcyjne, badawcze oraz implementacyjne skoncentrowane na praktycznej realizacji systemu detekcji obiektów z wykorzystaniem kamer wizyjnych i identyfikacji radiowej. Zaproponowano rozbudowę wielomodalnego teleinformatycznego systemu bezpieczeństwa o warstwę identyfikacji radiowej obiektów. Omówiono założenia zaprojektowanego systemu oraz opracowaną warstwę sprzętową. Zaproponowano i przedyskutowano praktyczne...
-
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...
-
Instructor Presence in Video Lectures: Preliminary Findings From an Online Experiment
PublicationMotivation. Despite the widespread use of video lectures in online and blended learning environments, there is still debate whether the presence of an instructor in the video helps or hinders learning. According to social agency theory, seeing the instructor makes learners believe that s/he is personally teaching them, which leads to deeper cognitive processing and, in turn, better learning outcomes. Conversely, according to cognitive...
-
Fault diagnosis of marine 4-stroke diesel engines using a one-vs-one extreme learning ensemble
PublicationThis paper proposes a novel approach for intelligent fault diagnosis for stroke Diesel marine engines, which are commonly used in on-road and marine transportation. The safety and reliability of a ship's work rely strongly on the performance of such an engine; therefore, early detection of any type of failure that affects the engine is of crucial importance. Automatic diagnostic systems are of special importance because they can...
-
Comparative study on the effectiveness of various types of road traffic intensity detectors
PublicationVehicle detection and speed measurements are crucial tasks in traffic monitoring systems. In this work, we focus on several types of electronic sensors, operating on different physical principles in order to compare their effectiveness in real traffic conditions. Commercial solutions are based on road tubes, microwave sensors, LiDARs, and video cameras. Distributed traffic monitoring systems require a high number of monitoring...
-
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...
-
Limitations of Emotion Recognition from Facial Expressions in e-Learning Context
PublicationThe paper concerns technology of automatic emotion recognition applied in e-learning environment. During a study of e-learning process the authors applied facial expressions observation via multiple video cameras. Preliminary analysis of the facial expressions using automatic emotion recognition tools revealed several unexpected results, including unavailability of recognition due to face coverage and significant inconsistency...
-
Fusion-based Representation Learning Model for Multimode User-generated Social Network Content
PublicationAs mobile networks and APPs are developed, user-generated content (UGC), which includes multi-source heterogeneous data like user reviews, tags, scores, images, and videos, has become an essential basis for improving the quality of personalized services. Due to the multi-source heterogeneous nature of the data, big data fusion offers both promise and drawbacks. With the rise of mobile networks and applications, UGC, which includes...
-
Generalized Formulation of Response Features for Reliable Optimization of Antenna Input Characteristics
PublicationElectromagnetic (EM)-driven parameter adjustment has become imperative in the design of modern antennas. It is necessary because the initial designs rendered through topology evolution, parameter sweeping, or theoretical models, are often of poor quality and need to be improved to satisfy stringent performance requirements. Given multiple objectives, constraints, and a typically large number of geometry parameters, the design closure...
-
Divide and not forget: Ensemble of selectively trained experts in Continual Learning
PublicationClass-incremental learning is becoming more popular as it helps models widen their applicability while not forgetting what they already know. A trend in this area is to use a mixture-of-expert technique, where different models work together to solve the task. However, the experts are usually trained all at once using whole task data, which makes them all prone to forgetting and increasing computational burden. To address this limitation,...
-
Spatiotemporal Assessment of Satellite Image Time Series for Land Cover Classification Using Deep Learning Techniques: A Case Study of Reunion Island, France
PublicationCurrent Earth observation systems generate massive amounts of satellite image time series to keep track of geographical areas over time to monitor and identify environmental and climate change. Efficiently analyzing such data remains an unresolved issue in remote sensing. In classifying land cover, utilizing SITS rather than one image might benefit differentiating across classes because of their varied temporal patterns. The aim...
-
AffecTube — Chrome extension for YouTube video affective annotations
PublicationThe shortage of emotion-annotated video datasets suitable for training and validating machine learning models for facial expression-based emotion recognition stems primarily from the significant effort and cost required for manual annotation. In this paper, we present AffecTube as a comprehensive solution that leverages crowdsourcing to annotate videos directly on the YouTube platform, resulting in ready-to-use emotion-annotated...
-
A Review of Emotion Recognition Methods Based on Data Acquired via Smartphone Sensors
PublicationIn recent years, emotion recognition algorithms have achieved high efficiency, allowing the development of various affective and affect-aware applications. This advancement has taken place mainly in the environment of personal computers offering the appropriate hardware and sufficient power to process complex data from video, audio, and other channels. However, the increase in computing and communication capabilities of smartphones,...
-
Neural network agents trained by declarative programming tutors
PublicationThis paper presents an experimental study on the development of a neural network-based agent, trained using data generated using declarative programming. The focus of the study is the application of various agents to solve the classic logic task – The Wumpus World. The paper evaluates the effectiveness of neural-based agents across different map configurations, offering a comparative analysis to underline the strengths and limitations...
-
When Neural Networks Meet Decisional DNA: A Promising New Perspective for Knowledge Representation and Sharing
PublicationABSTRACT In this article, we introduce a novel concept combining neural network technology and Decisional DNA for knowledge representation and sharing. Instead of using traditional machine learning and knowledge discovery methods, this approach explores the way of knowledge extraction through deep learning processes based on a domain’s past decisional events captured by Decisional DNA. We compare our approach with kNN (k-nearest...