Wyszukiwarka
Wyniki wyszukiwania dla: SUPERVISED LEARNING
-
Adaptive Method of Adjusting Flowgraph for Route Reconstruction in Video Surveillance Systems
PublikacjaPawlak’s flowgraph has been applied as a suitable data structure for description and anal- ysis of human behaviour in the area supervised with multicamera video surveillance system. Infor- mation contained in the flowgraph can be easily used to predict consecutive movements of a partic- ular object. Moreover, utilization of the flowgraph can support reconstructing object route from the past video images. However, such a flowgraph with...
-
Flood Classification in a Natural Wetland for Early Spring Conditions Using Various Polarimetric SAR Methods
PublikacjaAbstract--- One of the major limitations of remote sensing flood detection is the presence of vegetation. Our study focuses on a flood classification using Radarsat-2 Quad-Pol data in a natural floodplain during leafless, dry vegetation (early spring) state. We conducted a supervised classification of a data set composed of nine polarimetric decompositions and Shannon entropy followed by the predictors' importance estimation to...
-
Quadrotor Flight Controller Design Using Classical Tools
PublikacjaA principal aspect of quadrocopter in-flight operation is to maintain the required attitude of the craft’s frame, which is done either automatically in the so-called supervised flight mode or manually during man-operated flight mode. This paper deals with the problem of flight controller (logical) structure and algorithm design dedicated for the man-operated flight mode. The role of the controller is to stabilise the rotational...
-
Automatic Clustering of EEG-Based Data Associated with Brain Activity
PublikacjaThe aim of this paper is to present a system for automatic assigning electroencephalographic (EEG) signals to appropriate classes associated with brain activity. The EEG signals are acquired from a headset consisting of 14 electrodes placed on skull. Data gathered are first processed by the Independent Component Analysis algorithm to obtain estimates of signals generated by primary sources reflecting the activity of the brain....
-
Artificial intelligence models in prediction of response to cardiac resynchronization therapy: a systematic review
PublikacjaThe aim of the presented review is to summarize the literature data on the accuracy and clinical applicability of artificial intelligence (AI) models as a valuable alternative to the current guidelines in predicting cardiac resynchronization therapy (CRT) response and phenotyping of patients eligible for CRT implantation. This systematic review was performed...
-
A Parallel Genetic Algorithm for Creating Virtual Portraits of Historical Figures
PublikacjaIn this paper we present a genetic algorithm (GA) for creating hypothetical virtual portraits of historical figures and other individuals whose facial appearance is unknown. Our algorithm uses existing portraits of random people from specific historical period and social background to evolve a set of face images potentially resembling the person whose image is to be found. We then use portraits of the person's relatives to judge...
-
Rapid Evaluation of Poultry Meat Shelf Life Using PTR-MS
PublikacjaThe use of proton transfer reaction mass spectrometry (PTR-MS) for freshness classification of chicken and turkey meat samples was investigated. A number of volatile organic compounds (VOCs) were selected based on the correlation (> 95%) of their concentration during storage at 4 °C over a period of 5 days with the results of the microbial analysis. In order to verify if the selected compounds are not sample-specific, a number...
-
Weakly-Supervised Word-Level Pronunciation Error Detection in Non-Native English Speech
PublikacjaWe 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...
-
seafloor characterisation combined approach using multibeam sonar echo signal processing and image analysis
PublikacjaThe authors propose the approach to seafloor characterisation which relies on the combined, concurrent use of two different techniques: (i) multibeam sonar image analysis and (ii) multibeam seabed echoes processing. The first technique is based on constructing the grey-level sonar images of the seabed extracted from the echoes received in the consecutive soundings. Then, the set of parameters describing the local region of sonar...
-
Using angular dependence of multibeam echo features in seabed classification
PublikacjaThe new approach to seabed classification based on processing multibeam sonar echoes is presented. The multibeam sonars, besides their well verified and widely used applications like high resolution bathymetry measurements or underwater object imaging, are also the promising tool in seafloor identification and classification, having several advantages over conventional single beam echosounders. The proposed seabed classification...
-
Environmental risk assessment of Polish wastewater treatment plant activity
PublikacjaWastewater treatment plants (WWTPs) play an extremely important role in shaping modern society's environmental wellbeing and awareness, however only well operated and supervised systems can be considered as environmentally sustainable. For this reason, an attempt was undertaken to assess the environmental burden posed by WWTPs in major Polish cities by collecting water samples prior to and just after wastewater release points....
-
Monitoring Trends of Land Use and Land Cover Changes in Rajang River Basin
PublikacjaIn this study, the spatiotemporal changes in land use and land cover (LULC) were evaluated from 1992 to 2015 for the Rajang River Basin (RRB) located in the Sarawak State of Malaysia. The changes in water bodies cropped lands, and forests were assessed based on the available remotely sensed satellite data. Supervised classification with the Maximum-Likelihood-Algorithm technique was adopted for monitoring the LULC changes using...
-
Expedited optimization of antenna input characteristics with adaptive Broyden updates
PublikacjaSimulation-driven adjustment of geometry and/or material parameters is a necessary step in the design of contemporary antenna structures. Due to their topological complexity, other means, such as supervised parameter sweeping, does not usually lead to satisfactory results. On the other hand, rigorous numerical optimization is computationally expensive due to a high cost of underlying full-wave electromagnetic (EM) analyses, otherwise...
-
Pawlak's flow graph extensions for video surveillance systems
PublikacjaThe idea of the Pawlak's flow graphs is applicable to many problems in various fields related to decision algorithms or data mining. The flow graphs can be used also in the video surveillance systems. Especially in distributed multi-camera systems which are problematic to be handled by human operators because of their limited perception. In such systems automated video analysis needs to be implemented. Important part of this analysis...
-
Self-Organising map neural network in the analysis of electromyography data of muscles acting at temporomandibular joint.
PublikacjaThe temporomandibular joint (TMJ) is the joint that via muscle action and jaw motion allows for necessary physiological performances such as mastication. Whereas mandible translates and rotates [1]. Estimation of activity of muscles acting at the TMJ provides a knowledge of activation pattern solely of a specific patient that an electromyography (EMG) examination was carried out [2]. In this work, a Self-Organising Maps (SOMs)...
-
A new method for real-time monitoring of volatiles in frying fumes using proton transfer reaction mass spectrometry with time-of-flight analyse
PublikacjaTo safeguard the consumers’ well-being, it is necessary to develop novel methods for determination of carcinogens in food, including volatiles generated during frying. The currently used procedures for analysis of volatile fraction of vegetable oils are not based on real-time measurements and thus do not enable the determination of carcinogenic compounds in frying fumes; instead, only the headspace or liquid fraction is sampled....
-
Expedited Globalized Antenna Optimization by Principal Components and Variable-Fidelity EM Simulations: Application to Microstrip Antenna Design
PublikacjaParameter optimization, also referred to as design closure, is imperative in the development of modern antennas. Theoretical considerations along with rough dimension adjustment through supervised parameter sweeping can only yield initial designs that need to be further tuned to boost the antenna performance. The major challenges include handling of multi-dimensional parameter spaces while accounting for several objectives and...
-
Information retrieval with semantic memory model
PublikacjaPsycholinguistic theories of semantic memory form the basis of understanding of natural language concepts. These theories are used here as an inspiration for implementing a computational model of semantic memory in the form of semantic network. Combining this network with a vector-based object-relation-feature value representation of concepts that includes also weights for confidence and support, allows for recognition of concepts...
-
Algorithms and Tools for Intelligent Control of Critical Infrastructure Systems
PublikacjaCritical Infrastructure Systems (CIS) are spatially distributed and of a network structure. The dynamics are nonlinear, uncertain and with several time scales. There is a variety of different objectives to be reliably met under a wide range of operational conditions. The operational conditions are influenced by the disturbance inputs, operating ranges of the CIS, faults in the sensors and actuators and abnormalities occurring in...
-
Integrated monitoring, control and security of Critical Infrastructure Systems
PublikacjaModern societies have reached a point where everyday life relies heavily on desired operation of critical infrastructures, in spite of accidental failures and/or deliberate attacks. The issue of desired performance operation of CIS at high security level receives considerable attention worldwide. The pioneering generic methodologies and methods are presented in the paper project for designing systems capable of achieving these...
-
Accelerated Gradient-Based Optimization of Antenna Structures Using Multi-Fidelity Simulations and Convergence-Based Model Management Scheme
PublikacjaThe importance of numerical optimization has been steadily growing in the design of contemporary antenna structures. The primary reason is the increasing complexity of antenna topologies, [ a typically large number of adjustable parameters that have to be simultaneously tuned. Design closure is no longer possible using traditional methods, including theoretical models or supervised parameter sweeping. To ensure reliability, optimization...
-
Processing of Satellite Data in the Cloud
PublikacjaThe dynamic development of digital technologies, especially those dedicated to devices generating large data streams, such as all kinds of measurement equipment (temperature and humidity sensors, cameras, radio-telescopes and satellites – Internet of Things) enables more in-depth analysis of the surrounding reality, including better understanding of various natural phenomenon, starting from atomic level reactions, through macroscopic...
-
Shoreline Extraction Based on LiDAR Data Obtained Using an USV
PublikacjaThis article explores the use of Light Detection And Ranging (LiDAR) derived point clouds to extract the shoreline of the Lake Kłodno (Poland), based on their geometry properties. The data collection was performed using the Velodyne VLP‐16 laser scanner, which was mounted on the HydroDron Unmanned Surface Vehicle (USV). A modified version of the shoreline extraction method proposed by Xu et al. was employed, comprising of the following...
-
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...
-
Fuzzy Divisive Hierarchical Clustering of Solvents According to Their Experimentally and Theoretically Predicted Descriptors
PublikacjaThe present study describes a simple procedure to separate into patterns of similarity a large group of solvents, 259 in total, presented by 15 specific descriptors (experimentally found and theoretically predicted physicochemical parameters). Solvent data is usually characterized by its high variability, dierent molecular symmetry, and spatial orientation. Methods of chemometrics can usefully be used to extract and explore accurately...
-
Olgun Aydin dr
OsobyOlgun Aydin finished his PhD by publishing a thesis about Deep Neural Networks. He works as a Principal Machine Learning Engineer in Nike, and works as Assistant Professor in Gdansk University of Technology in Poland. Dr. Aydin is part of editorial board of "Journal of Artificial Intelligence and Data Science" Dr. Aydin served as Vice-Chairman of Why R? Foundation and is member of Polish Artificial Intelligence Society. Olgun is...