Filtry
wszystkich: 1486
wybranych: 1359
-
Katalog
Filtry wybranego katalogu
wyświetlamy 1000 najlepszych wyników Pomoc
Wyniki wyszukiwania dla: HIGH PERFORMANCE COMPUTINGENERGY EFFICIENCYPARETO OPTIMIZATIONDEEP NEURAL NETWORKS
-
Dynamic coloring of graphs
PublikacjaDynamics is an inherent feature of many real life systems so it is natural to define and investigate the properties of models that reflect their dynamic nature. Dynamic graph colorings can be naturally applied in system modeling, e.g. for scheduling threads of parallel programs, time sharing in wireless networks, session scheduling in high-speed LAN's, channel assignment in WDM optical networks as well as traffic scheduling. In...
-
Cost-Efficient Optical Fronthaul Architectures for 5G and Future 6G Networks
PublikacjaFifth-generation and Beyond (5GB) wireless networks have introduced new centralized architectures such as cloud radio access network (CRAN), which necessitate extremely high-capacity low latency Fronthaul (FH). CRAN has many advantageous features in terms of cost reduction, performance enhancement, ease of deployment, and centralization of network management. Nevertheless, designing and deploying a cost-efficient FH is still a...
-
Nonadditivity of quantum and classical capacities for entanglement breaking multiple-access channels and the butterfly network
PublikacjaWe analyze quantum network primitives which are entanglement breaking. We show superadditivity of quantum and classical capacity regions for quantum multiple-access channels and the quantum butterfly network. Since the effects are especially visible at high noise they suggest that quantum information effects may be particularly helpful in the case of the networks with occasional high noise rates. The present effects provide a qualitative...
-
Determination of chlorine concentration using single temperature modulated semiconductor gas sensor
PublikacjaA periodic temperature modulation using sinusoidal heater voltage was applied to a commercial SnO2 semiconductor gas sensor. Resulting resistance response of the sensor was analyzed using a feature extraction method based on Fast Fourier Transformation (FFT). The amplitudes of the higher harmonics of the FFT from the dynamic nonlinear responses of measured gas were further utilized as an input for Artificial Neural...
-
Optimum Choice of Randomly Oriented Carbon Nanotube Networks for UV-Assisted Gas Sensing Applications
PublikacjaWe investigated the noise and photoresponse characteristics of various optical transparencies of nanotube networks to identify an optimal randomly oriented network of carbon nanotube (CNT)-based devices for UV-assisted gas sensing applications. Our investigation reveals that all of the studied devices demonstrate negative photoconductivity upon exposure to UV light. Our studies confirm the effect of UV irradiation on the electrical...
-
Minimizing Distribution and Data Loading Overheads in Parallel Training of DNN Acoustic Models with Frequent Parameter Averaging
PublikacjaIn the paper we investigate the performance of parallel deep neural network training with parameter averaging for acoustic modeling in Kaldi, a popular automatic speech recognition toolkit. We describe experiments based on training a recurrent neural network with 4 layers of 800 LSTM hidden states on a 100-hour corpora of annotated Polish speech data. We propose a MPI-based modification of the training program which minimizes the...
-
Detecting Lombard Speech Using Deep Learning Approach
PublikacjaRobust Lombard speech-in-noise detecting is challenging. This study proposes a strategy to detect Lombard speech using a machine learning approach for applications such as public address systems that work in near real time. The paper starts with the background concerning the Lombard effect. Then, assumptions of the work performed for Lombard speech detection are outlined. The framework proposed combines convolutional neural networks...
-
The Impact of a New Product’s Novelty and Meaningfulness on its Commercial Performance
Publikacjas new product development (NPD) process encompasses creative actions, so a new product is characterized by two essential dimensions used to describe any creative output – namely novelty and meaningfulness. Therefore, businesses are faced with the questions to what extent and under what market conditions to develop each of these dimensions in order to obtain high new product commercial performance. Based on gaps indentified in the...
-
Position Estimation in Mixed Indoor-Outdoor Environment Using Signals of Opportunity and Deep Learning Approach
PublikacjaTo improve the user's localization estimation in indoor and outdoor environment a novel radiolocalization system using deep learning dedicated to work both in indoor and outdoor environment is proposed. It is based on the radio signatures using radio signals of opportunity from LTE an WiFi networks. The measurements of channel state estimators from LTE network and from WiFi network are taken by using the developed application....
-
Wireless Link Selection Methods for Maritime Communication Access Networks—A Deep Learning Approach
PublikacjaIn recent years, we have been witnessing a growing interest in the subject of communication at sea. One of the promising solutions to enable widespread access to data transmission capabilities in coastal waters is the possibility of employing an on-shore wireless access infrastructure. However, such an infrastructure is a heterogeneous one, managed by many independent operators and utilizing a number of different communication...
-
Improvement of speech intelligibility in the presence of noise interference using the Lombard effect and an automatic noise interference profiling based on deep learning
PublikacjaThe Lombard effect is a phenomenon that results in speech intelligibility improvement when applied to noise. There are many distinctive features of Lombard speech that were recalled in this dissertation. This work proposes the creation of a system capable of improving speech quality and intelligibility in real-time measured by objective metrics and subjective tests. This system consists of three main components: speech type detection,...
-
Commercially produced and modified starches
PublikacjaThis book presents some fascinating phenomena associated with the remarkable features of high performance polymers and also provides an update on applications of modern polymers. It offers new research on structure–property relationships, synthesis and purification, and potential applications of high performance polymers. The collection of topics in this book reflects the diversity of recent advances in modern polymers with a broad...
-
VIBRATION SURVEILLANCE DURING MILLING OF FLEXIBLE DETAILS WITH A USE OF THE ACTIVE OPTIMAL CONTROL
PublikacjaThe main goal of modern machining operations is to achieve increasingly better performance. High Speed Machining and/or High Performance Cutting, despite a lot of advantages, have also some drawbacks, for example, a possibility of losing stability and development of self-excited chatter vibration. This paper presents an approach of vibration surveillance during high speed milling with a use of active optimal control. Non-stationary...
-
Optical Sensor Based Gestures Inference Using Recurrent Neural Network in Mobile Conditions
PublikacjaIn this paper the implementation of recurrent neural network models for hand gesture recognition on edge devices was performed. The models were trained with 27 hand gestures recorded with the use of a linear optical sensor consisting of 8 photodiodes and 4 LEDs. Different models, trained off-line, were tested in terms of different network topologies (different number of neurons and layers) and different effective sampling frequency...
-
Evaluation of IEEE 802.21 Handover between IEEE 802.11 and UMTS Networks
PublikacjaThe paper presents IEEE 802.21 - the ongoing standard for network handovers - illustrating its functional features, and considering and simulating a set of scenarios of mobile stations moving between IEEE 802.11 and UMTS networks. In order to evaluate the performance of IEEE 802.21 hanover packet loses and switching delays caused by hanover procedures are investigated. The authors discuss example results of simulation experiments...
-
Efekty egoistycznych ataków na poziomie mac w sieciach ad hoc o topologii wieloskokowej
PublikacjaStacje sieci ad hoc mogą manipulować parametrami dostępu do medium transmisyjnego dla osiągnięcia nienależnie wysokiej jakości usług. Dla środowiska sieci ad hoc o topologii wieloskokowej rozważane są ataki na mechanizmy odłożenia transmisji i klasyfikacji ruchu, przeprowadzane zarówno w stosunku do przepływów źródłowych jak i tranzytowych. Wyniki pozwalają wstępnie ocenić efekty takich ataków oraz skuteczność mechanizmów obronnych.
-
Security Evaluation of IT Systems Underlying Critical Networked Infrastructures
PublikacjaCritical infrastructures have become highly dependent on information and communication technology (ICT). The drawback of this situation is that the consequences of disturbances of the underlying ICT networks may be serious as cascading effects can occur. This raises a high demand for security assurance, with a high importance assigned to security evaluations. In this paper we present an experiment-centric approach for the characterisation...
-
A bound on the number of middle-stage crossbars in f-cast rearrangeable Clos networks
PublikacjaIn 2006 Chen and Hwang gave a necessary and sufficient condition under which a three-stage Clos network is rearrangeable for broadcast connections. Assuming that only crossbars of the first stage have no fan-out property, we give similar conditions for f-cast Clos networks, where f is an arbitrary but fixed invariant of the network. Such assumptions are valid for some practical switching systems, e.g. high-speed crossconnects....
-
Fragmentation of Hydrographic Big Data Into Subsets During Reduction Process
PublikacjaThe article presented problems of fragmentation of hydrographic big data into smaller subsets during reduction process. Data reduction is a processing of reduce the value of the data set, in order to make them easier and more effective for the goals of the analysis. The main aim of authors is to create new reduction method. The article presented the first stage of this method – fragmentation of bathymetric data into subsets. It...
-
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...
-
Comparison of Deep Neural Network Learning Algorithms for Mars Terrain Image Segmentation
PublikacjaThis paper is dedicated to the topic of terrain recognition on Mars using advanced techniques based on the convolutional neural networks (CNN). The work on the project was conducted based on the set of 18K images collected by the Curiosity, Opportunity and Spirit rovers. The data were later processed by the model operating in a Python environment, utilizing Keras and Tensorflow repositories. The model benefits from the pretrained...
-
Towards 5G — Cloud-based Radio Access Networks
PublikacjaIn the paper a general concept of the 5G network architecture is presented as well as system requirements having impact on innovative solutions in the 5G network are highlighted. A major part of the paper is both presentation and discussion of the problem of Cloud Radio Access Network introduction for public networks in which the cell and resource virtualisation will be implemented. On the other hand, the problem of resource virtualization...
-
MODEL FOR MEASUREMENT OF FLOW INSTALLATION TIME IN SDN SWITCH
PublikacjaSDN is the approach in telecommunication networks that separates control plane from data forwarding plane by specifying a single network entity as a controller that defines rules (called flows) of traffic forwarding for the switches connected to it. The time that is required for installation of these rules might be a hindrance for the overall performance of SDN network. In the paper, a model for testing and evaluating the influence...
-
A new approach to design of weather disruption-tolerant wireless mesh networks
PublikacjaWireless Mesh Networks, offering transmission rates of 1–10 Gb/s per a millimeter-wave link (utilizing the 71–86 GHz band) seem to be a promising alternative to fiber optic backbone metropolitan area networks because of significantly lower costs of deployment and maintenance. However, despite providing high transmission rates in good weather conditions, high-frequency wireless links are very susceptible to weather disruptions....
-
Quantitative Risk Assessment in Construction Disputes Based on Machine Learning Tools
PublikacjaA high monetary value of the construction projects is one of the reasons of frequent disputes between a general contractor (GC) and a client. A construction site is a unique, one-time, and single-product factory with many parties involved and dependent on each other. The organizational dependencies and their complexity make any fault or mistake propagate and influence the final result (delays, cost overruns). The constant will...
-
Comparative study on the effectiveness of various types of road traffic intensity detectors
PublikacjaVehicle 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...
-
Urban scene semantic segmentation using the U-Net model
PublikacjaVision-based semantic segmentation of complex urban street scenes is a very important function during autonomous driving (AD), which will become an important technology in industrialized countries in the near future. Today, advanced driver assistance systems (ADAS) improve traffic safety thanks to the application of solutions that enable detecting objects, recognising road signs, segmenting the road, etc. The basis for these functionalities...
-
Categorization of emotions in dog behavior based on the deep neural network
PublikacjaThe aim of this article is to present a neural system based on stock architecture for recognizing emotional behavior in dogs. Our considerations are inspired by the original work of Franzoni et al. on recognizing dog emotions. An appropriate set of photographic data has been compiled taking into account five classes of emotional behavior in dogs of one breed, including joy, anger, licking, yawning, and sleeping. Focusing on a particular...
-
Possibilities of heat transfer augmentation in heat exchangers with minichannels for marine applications
PublikacjaIn the paper, new trends in development of microchannel heat exchangers are presented. The exchangers developed in this way can be applied in marine applications. Main attention was focused on heat exchangers design with reduced size of passages namely based on microchannels. In our opinion future development of high power heat exchangers will be based on networks micro heat exchangers.
-
New Product Creativity Dimensions and Performance
PublikacjaA new product’s meaningfulness and novelty are recognized as two distinct and important dimensions. Thus, researchers started to investigate their impact on new product performance. However, researchers’ reports on the impact of novelty on performance are still mixed, and several issues need to be solved. One of these problems is comparing how strongly each of these dimensions affects the new product performance. The other is to...
-
Traffic Type Influence on QoS Network Performance of Streaming Traffic Class
PublikacjaFeasibility study on QoS routing proved that the traffic type influence the network performance. The performance is defined here as a number of packets serviced by the network. In the paper additional element - buffers lengths used in service system was verified in terms of dependencies with routing performance. We present results obtained by simulation for many simulation scenarios. Analysis was done for two different network...
-
Introduction to the ONDM 2022 special issue
PublikacjaThis JOCN special issue contains extended versions of selected papers presented at the 26th International Conference on Optical Network Design and Modeling (ONDM 2022), which took place 16–19 May 2022 at Warsaw University of Technology, Warsaw, Poland. The topics covered by the papers represent trends in optical networking research: application of machine learning to network management, cross-layer network performance optimization,...
-
Protection in elastic optical networks
PublikacjaIn this article, we analyze gains resulting from the use of EON architectures with special focus on transportation of cloud-ready and content-oriented traffic in the context of network resilience. EONs are a promising approach for future optical transport networks and, apart from improving the network spectral efficiency, bring such new capabilities as squeezed protection, which reduces resource requirements in failure scenarios....
-
A METHOD OF TRUST MANAGEMENT IN WIRELESS SENSOR NETWORKS
PublikacjaThe research problem considered in this paper is how to protect wireless sensor networks (WSN) against cyber-threats by applying trust management and how to strengthen network resilience to attacks targeting the trust management mechanism itself. A new method, called WSN Cooperative Trust Management Method (WCT2M), of distributed trust management in multi-layer wireless sensor networks is proposed and its performance is evaluated....
-
Modelling of wastewater treatment plant for monitoring and control purposes by state - space wavelet networks
PublikacjaMost of industrial processes are nonlinear, not stationary, and dynamical with at least few different time scales in their internal dynamics and hardly measured states. A biological wastewater treatment plant falls into this category. The paper considers modelling such processes for monitorning and control purposes by using State - Space Wavelet Neural Networks (SSWN). The modelling method is illustrated based on bioreactors of...
-
Velocity measurement using the fdoa method in ground-based radio navigation system
PublikacjaVelocity is one of the main navigation parameters of the moving objects. However some systems of position estimation using radio wave measurements cannot provide velocity data due to limitation of their performance. In this paper a velocity measurement method for DS-CDMA radio navigation system is proposed, which doesn’t require full synchronization of reference stations carrier frequencies. The article presents basics of FDOA...
-
Deep learning techniques for biometric security: A systematic review of presentation attack detection systems
PublikacjaBiometric technology, including finger vein, fingerprint, iris, and face recognition, is widely used to enhance security in various devices. In the past decade, significant progress has been made in improving biometric sys- tems, thanks to advancements in deep convolutional neural networks (DCNN) and computer vision (CV), along with large-scale training datasets. However, these systems have become targets of various attacks, with...
-
Vehicle detector training with minimal supervision
PublikacjaRecently many efficient object detectors based on convolutional neural networks (CNN) have been developed and they achieved impressive performance on many computer vision tasks. However, in order to achieve practical results, CNNs require really large annotated datasets for training. While many such databases are available, many of them can only be used for research purposes. Also some problems exist where such datasets are not...
-
An Analysis of Neural Word Representations for Wikipedia Articles Classification
PublikacjaOne of the current popular methods of generating word representations is an approach based on the analysis of large document collections with neural networks. It creates so-called word-embeddings that attempt to learn relationships between words and encode this information in the form of a low-dimensional vector. The goal of this paper is to examine the differences between the most popular embedding models and the typical bag-of-words...
-
Networking and Familiness as Factors Stimulating the Early Internationalization of High-Tech Firms
PublikacjaThe problem of the role and importance of time in the process of firm’s internationalization belongs to the mainstream of international business research, as is the problem of the key role of high-tech firms operating across borders. The main goal of the paper is to understand how selected factors determine early internationalization of high-tech firms in Poland as an emerging market. The theoretical framework of the article is...
-
Rotor Blade Geometry Optimisation in Kaplan Turbine
PublikacjaThe paper presents the description of method and results of rotor blade shape optimisation. The rotor blading constitutes a part ofturbine flow path. Optimisation consists in selection of the shape that minimises ratio of polytrophic loss. Shape of the blade isdefined by the mean camber line and thickness of the airfoil. Thickness is distributed around the camber line based on the ratio ofdistribution. Global optimisation was done...
-
Dataset Related Experimental Investigation of Chess Position Evaluation Using a Deep Neural Network
PublikacjaThe idea of training Articial Neural Networks to evaluate chess positions has been widely explored in the last ten years. In this paper we investigated dataset impact on chess position evaluation. We created two datasets with over 1.6 million unique chess positions each. In one of those we also included randomly generated positions resulting from consideration of potentially unpredictable chess moves. Each position was evaluated...
-
Comparing the Effectiveness of ANNs and SVMs in Forecasting the Impact of Traffic-Induced Vibrations on Building
PublikacjaTraffic - induced vibrations may cause damage to structural elements and may even lead to structural collapse. The aim of the article is to compare the effectiveness of algorithms in forecasting the impact of vibrations on buildings using the Machine Learning (ML) methods. The paper presents two alternative approaches by using Artificial Neural Networks (ANNs) and Support Vector Machines (SVMs). Factors that may affect traffic-induced...
-
Analyzing the Effectiveness of the Brain–Computer Interface for Task Discerning Based on Machine Learning
PublikacjaThe 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...
-
Dekodowanie kodów iterowanych z użyciem sieci neuronowej
PublikacjaNadmiarowe kody iterowane są jedną z prostych metod pozyskiwania długich kodów korekcyjnych zapewniających dużą ochronę przed błędami. Jednocześnie, chociaż ich podstawowy iteracyjny dekoder jest prosty koncepcyjnie oraz łatwy w implementacji, to nie jest on rozwiązaniem optymalnym. Poszukując alternatywnych rozwiązań zaproponowano, przedstawioną w pracy, strukturę dekodera tego typu kodów wspomaganą przez sieci neuronowe. Zaproponowane...
-
Nodal cooperation equilibrium analysis in multi-hop wireless ad hoc networks with a reputation system
PublikacjaMotivated by the concerns of cooperation security, this work examines selected principles of state-of-the-art reputation systems for multi-hop ad hoc networks and their impact upon optimal strategies for rational nodes. An analytic framework is proposed and used for identification of effective cooperation-enforcement schemes. It is pointed out that optimum rather than high reputation can be expected to be sought by rational nodes.
-
Automatic labeling of traffic sound recordings using autoencoder-derived features
PublikacjaAn approach to detection of events occurring in road traffic using autoencoders is presented. Extensions of existing algorithms of acoustic road events detection employing Mel Frequency Cepstral Coefficients combined with classifiers based on k nearest neighbors, Support Vector Machines, and random forests are used. In our research, the acoustic signal gathered from the microphone placed near the road is split into frames and converted...
-
Influence of Self-Similar Traffic Type on Performance of QoS Routing Algorithms
PublikacjaProviding a Quality of Services (QoS) into current telecommunication networks based on packet technology is a big challenge nowadays. Network operators have to support a number of new services like voice or video which generate new type of traffic. This traffic serviced with QoS in consequence requires access to appropriate network resources. Additionally, new traffic type is mixed with older one, like best-effort. Analysis of...
-
Three dimensional simulations of FRC beams and panels with explicit definition of fibres-concrete interaction
PublikacjaHigh performance concrete (HPC) is a quite novel material which has been rapidly developed in the last few decades. It exhibits superior mechanical properties and durability comparing to normal concrete. HPC can achieve also superior tensile performance if strong fibres (steel or carbon) are implemented in the matrix. Thus, there exist the unabated interest in studying how the addition of different types of fibres modifies the...
-
Sources of Market Information, Its Quality and New Product Financial Performance
PublikacjaWhile we observe a growing interest in the role of market information in new product development (NPD), existing research has still largely ignored the quality of market information that is a crucial issue in the era of the information society. What does affect the quality of market information in new product development projects, and how does this quality influence the financial performance of new products? In this paper, we address...