Wyszukiwarka
Filtry
wszystkich: 4340
wybranych: 3500
-
Katalog
- Publikacje 3500 wyników po odfiltrowaniu
- Czasopisma 186 wyników po odfiltrowaniu
- Konferencje 31 wyników po odfiltrowaniu
- Osoby 84 wyników po odfiltrowaniu
- Projekty 11 wyników po odfiltrowaniu
- Kursy Online 83 wyników po odfiltrowaniu
- Wydarzenia 9 wyników po odfiltrowaniu
- Dane Badawcze 436 wyników po odfiltrowaniu
Filtry wybranego katalogu
wyświetlamy 1000 najlepszych wyników Pomoc
Wyniki wyszukiwania dla: ACTIVE LEARNING ALGORITHM
-
Tool Wear Monitoring Using Improved Dragonfly Optimization Algorithm and Deep Belief Network
PublikacjaIn recent decades, tool wear monitoring has played a crucial role in the improvement of industrial production quality and efficiency. In the machining process, it is important to predict both tool cost and life, and to reduce the equipment downtime. The conventional methods need enormous quantities of human resources and expert skills to achieve precise tool wear information. To automatically identify the tool wear types, deep...
-
FPGA realization of an improved alpha max plus beta min algorithm
PublikacjaThe generalized improved version of the alpha max plus beta min square-rooting algorithm and its realization in the Field Programmable Gate Array (FPGA) are presented. The algorithm computes the square root to calculate the approximate magnitude of a complex sample. It is especially useful for pipelined calculations in the DSP. In case of four approximation regions it is possible to reduce the peak error form 3.95% to 0.33%. This...
-
Process of Medical Dataset Construction for Machine Learning-Multifield Study and Guidelines
PublikacjaThe acquisition of high-quality data and annotations is essential for the training of efficient machine learning algorithms, while being an expensive and time-consuming process. Although the process of data processing and training and testing of machine learning models is well studied and considered in the literature, the actual procedures of obtaining data and their annotations in collaboration with physicians are in most cases...
-
Multichannel self-optimizing active noise control scheme
PublikacjaThe problem of cancellation of a nonstationary sinusoidal interference, acting at the output of an unknown multivariable linear stable plant, is considered. The proposed cancellation scheme is a nontrivial extension of the SONIC (self-optimizing narrowband interference canceller) algorithm, developed earlier for single-input, single-output plants. In the important benchmark case - for disturbances with randomwalk-type amplitude...
-
Simulation model for evaluation of QoS routing algorithm in large packet networks
PublikacjaThe variety of traffic transferred via current telecommunication networks includes also voice, which should meet quality requirements. One of mechanisms, which can support QoS in current packet networks, is routing. There exist many routing proposals which should introduce the QoS into the network but practically they don't. Following paper presents the realization of simulation model for evaluation of a new routing algorithm DUMBRA...
-
Arc-length Algorithm Efficiency in the Analysis of Thermally Loaded Multilayered Shells
PublikacjaThis paper concerns the efficiency study of the arc-length algorithm in the geometrically non-linear analysis of thermally loaded multilayered shells. The thermal loading is considered as the one-way thermo-mechanical coupling effect. Two implementations of the arc-length method are examined: the path-following technique available in NX-Nastran and the RiksWempner-Ramm algorithm adopted in the authors’ computer code SHLTH. It is...
-
Data augmentation for improving deep learning in image classification problem
PublikacjaThese days deep learning is the fastest-growing field in the field of Machine Learning (ML) and Deep Neural Networks (DNN). Among many of DNN structures, the Convolutional Neural Networks (CNN) are currently the main tool used for the image analysis and classification purposes. Although great achievements and perspectives, deep neural networks and accompanying learning algorithms have some relevant challenges to tackle. In this...
-
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...
-
Internet photogrammetry as a tool for e-learning
PublikacjaAlong with Internet development, there were interactive applications which allow for remote sensing and photogrammetric analysis. An example of an application that can provide Earth images and make it possible to measure distances in these images is Google Earth. The authors, who have experience from 2001-2015 argue that it is possible and it is important to create more advanced photogrammetric network applications. In this there...
-
A 27/26-approximation algorithm for the chromatic sum coloring of bipartitegraphs
PublikacjaWe consider the CHROMATIC SUM PROBLEM on bipartite graphs which appears to be much harder than the classical CHROMATIC NUMBER PROBLEM. We prove that the CHROMATIC SUM PROBLEM is NP-complete on planar bipartite graphs with Delta less than or equal to 5, but polynomial on bipartite graphs with Delta less than or equal to 3, for which we construct an O(n(2))-time algorithm. Hence, we tighten the borderline of intractability for this...
-
Performance evaluation of the parallel object tracking algorithm employing the particle filter
PublikacjaAn algorithm based on particle filters is employed to track moving objects in video streams from fixed and non-fixed cameras. Particle weighting is based on color histograms computed in the iHLS color space. Particle computations are parallelized with CUDA framework. The algorithm was tested on various GPU devices: a desktop GPU card, a mobile chipset and two embedded GPU platforms. The processing speed depending on the number...
-
Problems of Active Dynamic Thermography Measurement Standardization in Medicine
PublikacjaReliability of thermographic diagnostics in medicine is an important practical problem. In the field of static thermography, a great deal of effort has been made to define the conditions for thermographic measurements, which is now the golden standard for such research. In recent years, there are more and more reports on dynamic tests with external stimulation, such as Active Dynamic Thermography, Thermographic Signal Reconstruction...
-
COMPARISON OF SOFTWARE AND HARDWARE REALIZATION OF AES CRYPTOGRAPHIC ALGORITHM
PublikacjaIn this paper hardware and software realization of direct and inverse AES cryptographic algorithm is presented. Both implementations were made using the Virtex-II FPGA and were practically tested. As the criteria of comparison, the resource utilization, achieved performance and power dissipation were chosen. Hardware realization increases throughput of conversion about 190 times over software implementation and decreases the energy...
-
The Usage of the BP-Layers Stereo Matching Algorithm with the EBCA Camera Set
PublikacjaThis paper is concerned with applying a stereo matching algorithm called BP-Layers to a set of many cameras. BP Layers is designed for obtaining disparity maps from stereo cameras. The algorithm takes advantage of convolutional natural networks. This paper presents using this algorithm with a set called Equal Baseline Camera Array. This set consists of up to five cameras with one central camera and other ones aground it. Such a...
-
Innovative e-learning approach in teaching based on case studies - Innocase project
PublikacjaThe article presents the application of innovative e-learning approach for the creation of case study content. Case study methodology is becoming more and more widely applied in modern education, especially in business and management field. Although case study methodology is quite well recognized and used in education, there are still few examples of developing e-learning content on the basis of case studies. This task is to be...
-
Current harmonic controller in multiple reference frames for series active power filter integrated with 18-pulse diode rectifier
PublikacjaThe paper presents the control system and selected results of experimental tests of the AC/DC power converter consisting of an 18-pulse diode rectifier based on coupled reactors and a serial active power filter. Proportional integral controllers with decoupling components are implemented in multiple reference frames for selective line current harmonic suppression. The regulator is provided with a backtracking anti-windup mechanism...
-
Efficient Complex Root Finding Algorithm for Microwave and Optical Propagation Problems
PublikacjaArticle relates to the use of innovative root finding algorithm (on a complex plane) to study propagation properties of microwave and optical waveguides. Problems of this type occur not only in the analysis of lossy structures, but also in the study of complex and leaky modes (radiation phenomena). The proposed algorithm is simple to implement and can be applied for functions with singularities and branch cuts in the complex plane...
-
Explainable machine learning for diffraction patterns
PublikacjaSerial crystallography experiments at X-ray free-electron laser facilities produce massive amounts of data but only a fraction of these data are useful for downstream analysis. Thus, it is essential to differentiate between acceptable and unacceptable data, generally known as ‘hit’ and ‘miss’, respectively. Image classification methods from artificial intelligence, or more specifically convolutional neural networks (CNNs), classify...
-
MACHINE LEARNING APPLICATIONS IN RECOGNIZING HUMAN EMOTIONS BASED ON THE EEG
PublikacjaThis study examined the machine learning-based approach allowing the recognition of human emotional states with the use of EEG signals. After a short introduction to the fundamentals of electroencephalography and neural oscillations, the two-dimensional valence-arousal Russell’s model of emotion was described. Next, we present the assumptions of the performed EEG experiment. Detail aspects of the data sanitization including preprocessing,...
-
Detection of Alzheimer's disease using Otsu thresholding with tunicate swarm algorithm and deep belief network
PublikacjaIntroduction: Alzheimer’s Disease (AD) is a degenerative brain disorder characterized by cognitive and memory dysfunctions. The early detection of AD is necessary to reduce the mortality rate through slowing down its progression. The prevention and detection of AD is the emerging research topic for many researchers. The structural Magnetic Resonance Imaging (sMRI) is an extensively used imaging technique in detection of AD, because...
-
A space-efficient algorithm for computing the minimum cycle mean in a directed graph
PublikacjaAn algorithm is introduced for computing the minimum cycle mean in a strongly connected directed graph with n vertices and m arcs that requires O(n) working space. This is a considerable improvement for sparse graphs in comparison to the classical algorithms that require O(n^2) working space. The time complexity of the algorithm is still O(nm). An implementation in C++ is made publicly available at http://www.pawelpilarczyk.com/cymealg/.
-
Statistically efficient smoothing algorithm for time-varying frequency estimation
PublikacjaThe problem of extraction/elimination of a nonstationary sinusoidal signal from noisy measurements is considered. This problem is usually solved using adaptive notch filtering (ANF) algorithms. It is shown that the accuracy of frequency estimates can be significantly increased if the results obtained from ANF are backward-time filtered by an appropriately designed lowpass filter. The resulting adaptive notch smoothing (ANS) algorithm...
-
Interpretable Deep Learning Model for the Detection and Reconstruction of Dysarthric Speech
PublikacjaWe 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...
-
An Algorithm for Listing All Minimal 2-Dominating Sets of a Tree
PublikacjaWe provide an algorithm for listing all minimal 2-dominating sets of a tree of order n in time O(1.3248n) . This implies that every tree has at most 1.3248 n minimal 2-dominating sets. We also show that this bound is tigh.
-
Distributed measurement system with data transmission secured using XXTEA algorithm
PublikacjaThe paper deals with wireless data transmission security in the distributed measurement and control system. An overview of cryptographic algorithms was presented paying special attention to the algorithm dedicated to units with low processing power, which is important due to minimization of energy consumption. Measurement modules equipped with simple microcontrollers send data wirelessly to the central unit. The transmission was...
-
Design and evaluation of a base module of active power electronic transformer
PublikacjaThis paper presents an active power electronic transformer (APET) based on modular structure. The proposed three phase APET consists of at least three base modules (BM). The input/output stage of the BM is based on half-bridge sub modules. The isolation stage includes a medium frequency transformer and is realized as a dual half-bridge. The paper describes construction process and explains the control strategy. The theoretical...
-
An algorithm for listing all minimal double dominating sets of a tree
PublikacjaWe provide an algorithm for listing all minimal double dominating sets of a tree of order $n$ in time $\mathcal{O}(1.3248^n)$. This implies that every tree has at most $1.3248^n$ minimal double dominating sets. We also show that this bound is tight.
-
Semi complex navigation with an active optical gesture sensor
PublikacjaThis paper presents the methods of diversified touchless interactions between a user and a mobile platform utilizing the optical gesture sensor. The sensor uses 8 photodiodes to measure the reflected light in the active mode (using embedded LEDs) or it measures shadows caused by fingers in the passive mode. Several algorithms were implemented: automatic mode switching, adaptive illumination level compensation, resolution improvements...
-
Hybrid DUMBRA: an efficient QoS routing algorithm for networks with DiffServ architecture
PublikacjaDynamic routing is very important issue of current packet networks. It may support the QoS and help utilize available network resources. Unfortunately current routing mechanisms are not sufficient to fully support QoS. Although many research has been done in this area no generic QoS routing algorithm has been proposed that could be used across all network structures. Existing QoS routing algorithms are either dedicated to limited...
-
Improving Clairvoyant: reduction algorithm resilient to imbalanced process arrival patterns
PublikacjaThe Clairvoyant algorithm proposed in “A novel MPI reduction algorithm resilient to imbalances in process arrival times” was analyzed, commented and improved. The comments concern handling certain edge cases in the original pseudocode and description, i.e., adding another state of a process, improved cache friendliness more precise complexity estimations and some other issues improving the robustness of the algorithm implementation....
-
Measurement of the Development of a Learning IT Organization Supported by a Model of Knowledge Acquisition and Processing
PublikacjaThe paper presents a model of knowledge acquisition and processing for the development of learning organizations. The theory of a learning organization provides neither metrics nor tools to measure its development The authors' studies in this field are based on their experience gathered after projects realized in real IT organizations. The authors have described the construction of the model and the methods of its verification...
-
Attention-Based Deep Learning System for Classification of Breast Lesions—Multimodal, Weakly Supervised Approach
PublikacjaBreast cancer is the most frequent female cancer, with a considerable disease burden and high mortality. Early diagnosis with screening mammography might be facilitated by automated systems supported by deep learning artificial intelligence. We propose a model based on a weakly supervised Clustering-constrained Attention Multiple Instance Learning (CLAM) classifier able to train under data scarcity effectively. We used a private...
-
Multimodal Genetic Algorithm with Phase Analysis to Solve Complex Equations of Electromagnetic Analysis
PublikacjaIn this contribution, a new genetic-algorithm-based method of finding roots and poles of a complex function of a complex variable is presented. The algorithm employs the phase analysis of the function to explore the complex plane with the use of the genetic algorithm. Hence, the candidate regions of root and pole occurrences are selected and verified with the use of discrete Cauchy's argument principle. The algorithm is evaluated...
-
Compensation of Dead Time Effects for Shunt Active Power Filters
PublikacjaThe paper presents a comprehensive approach to the compensation of the grid current distortion for shunt active power filter systems. Four different sources of current distortion are addressed: imperfect grid synchronization caused by the distortion in the grid voltages, time delays in the estimation of compensating currents and grid voltages, fluctuations of the dc bus voltage, and the distortion of inverter output voltages due...
-
Rehabilitation device supporting active and passive upper limb exercises
PublikacjaThis article presents a mechatronic solution for rehabilitation devices supporting active and passive exercises in persons with motor dysfunctions of the upper limbs in the area of the elbow and shoulder joints. A planar positioner integrated with original software and a control system, served as the basis for creating the present solution. Bellman’s programming method was applied to optimize the motion trajectory of the planar...
-
Finite-difference time-domain analyses of active cloaking for electrically-large objects
PublikacjaInvisibility cloaking devices constitute a unique and potentially disruptive technology, but only if they can work over broad bandwidths for electrically-large objects. So far, the only known scheme that allows for broadband scattering cancellation from an electrically-large object is based on an active implementation where electric and magnetic sources are deployed over a surface surrounding the object, but whose ‘switching on’...
-
Selection of energy storage units by genetic algorithm for mitigating voltage deviations
PublikacjaIn recent years, energy storage units have become very popular. They are applied both for economic and technical purposes. Unfortunately, the cost of such devices is still high and selecting their proper location and rated power have to be performed precisely. In this paper, a Genetic-Algorithm-based optimization method for selecting the best configuration of energy storage units in the power network is proposed. The presented...
-
Removal of Pharmaceutically Active Compounds in Sequencing Batch Reactor
PublikacjaIn recent years, considerable attention was paid to the presence of organic micro-pollutants such as Active Pharmaceutical Ingredients (API) in the aquatic environment due to their negative impact on public health and aquatic ecosystems. Numerous papers have pointed out API presence as common constituents of effluents from Wastewater Treatment Plants (WWTPs). This is the result of various efficiencies of API removal by conventional...
-
Active management of equipment cooling in hoteling data centers
PublikacjaHoteling data centers are designated for housing computing and storage units of many, usually small customers, as opposed to traditional data centers supporting own computing and storage resources of a bigger company. One of the services to be provided to consumer’s equipment is cooling. Cooling in data centers is prevalently achieved by circulating air in computer room. Efficient cooling requires delivering cold air from central...
-
Organizational Wisdom: The Impact of Organizational Learning on the Absorptive Capacity of an Enterprise
PublikacjaPurpose: In this article, we analyze the concept of organizational wisdom, indicating its key elements and verifieng the relationships between them. Design/Methodology/Approach: The study was conducted at Vive Textile Recycling Sp. z o.o in Poland. Empirical data was collected from 138 managers using the PAPI technique. Structural equation modelling (SEM) was performed to test the research hypotheses. Additionally, the significance...
-
Impact resistance of plain and twill fabric in GFRP measured by active thermography
PublikacjaThis paper discusses the impact resistance of glass-fibre reinforced polymer (GFRP) composites depending on the type of reinforcement – plain or twill weave. The values of impact energy were: 3J, 10J and 15J. Specimens featuring twill weave transferred higher force during the impact as compared with plain weave specimens. It was observed that an increase of impact energy was accompanied by an increase of the disproportion in...
-
Standing Waves in a Rectangular Resonator Containing Acoustically Active Gases
PublikacjaThe distribution of perturbations of pressure and velocity in a rectangular resonator is considered. A resonator contains a gas where thermodynamic processes take place, such as exothermic chemical reaction or excitation of vibrational degrees of a molecule’s freedom. These processes make the gas acoustically active under some conditions. We conclude that the incident and reflected compounds of a sound beam do not interact in the...
-
Sensorless predictive control of three-phase parallel active filter
PublikacjaThe paper presents the control system of parallel active power filter (APF) with predictive reference current calculation and model based predictive current control. The novel estimator and predictor of grid emf is proposed for AC voltage sensorless operation of APF, regardless of distortion of this voltage. Proposed control system provides control of APF current with high precision and dynamics limited only by filter circuit parameters....
-
Consequences of New Approach of Chemical Stability Tests of Active Pharmaceutical Ingredients (APIs)
PublikacjaThere is a great need of broaden look on stability tests of active pharmaceuticalingredients (APIs) in comparison with current requirements contained in pharmacopeia.By usage of many modern analytical methods the conception of monitoring the changesof APIs during initial stage of their exposure to harmful factors has been developed. Newknowledge must be acquired in terms of identification of each degradation...
-
Using Isolation Forest and Alternative Data Products to Overcome Ground Truth Data Scarcity for Improved Deep Learning-based Agricultural Land Use Classification Models
PublikacjaHigh-quality labelled datasets represent a cornerstone in the development of deep learning models for land use classification. The high cost of data collection, the inherent errors introduced during data mapping efforts, the lack of local knowledge, and the spatial variability of the data hinder the development of accurate and spatially-transferable deep learning models in the context of agriculture. In this paper, we investigate...
-
Is it too late now to say we’re sorry? Examining anxiety contagion and crisis communication strategies using machine learning
PublikacjaIn this paper, we explore the role of perceived emotions and crisis communication strategies via organizational computer-mediated communication in predicting public anxiety, the default crisis emotion. We use a machine-learning approach to detect and predict anxiety scores in organizational crisis announcements on social media and the public’s responses to these posts. We also control for emotional and language tones in organizational...
-
Neural modelling of dynamic systems with time delays based on an adjusted NEAT algorithm
PublikacjaA problem related to the development of an algorithm designed to find an architecture of artificial neural network used for black-box modelling of dynamic systems with time delays has been addressed in this paper. The proposed algorithm is based on a well-known NeuroEvolution of Augmenting Topologies (NEAT) algorithm. The NEAT algorithm has been adjusted by allowing additional connections within an artificial neural network and...
-
A new optimal algorithm for a time-dependent scheduling problem
PublikacjaIn this article a single machine time-dependent scheduling problem with total completion time criterion is considered. There are n given jobs j_1, ..., j_n and the processing time pi of the i-th job is given by p_i = 1 + b_is_i, where si is the starting time of the i-th job, i = 1, ..., n. If all jobs have different and non-zero deterioration rates and bi > bj => bi >= (b_min+1)/(b_min) b_j + 1/b_min, where b_min = min{b_i}, then...
-
Electronic nose algorithm design using classical system identification for odour intensity detection
PublikacjaThe two elements considered crucial for constructing an efficient environmental odour intensity monitoring systems are sensors and algorithms typically addressed to as electronic nose sensor (e-nose). Due to operational complexity of biochemical sensors developed in human bodies algorithms based on computational methods of artificial intelligence are typically considered superior to classical model based approaches in development...
-
FPGA computation of magnitude of complex numbers using modified CORDIC algorithm
PublikacjaIn this work we present computation of the magnitude of complex numbers using a modified version of the CORDIC algorithm that uses only five iterations. The relationship between the computation error and the number of CORDIC iterations are presented for floating-point and integer arithmetics. The proposed modification of CORDIC for integer arithmetic relies upon the introduction of correction once basic computations are performed...