Katedra Architektury Systemów Komputerowych - Jednostki Administracyjne - MOST Wiedzy

Wyszukiwarka

Katedra Architektury Systemów Komputerowych

Filtry

wszystkich: 749

  • Kategoria
  • Rok
  • Opcje

wyczyść wszystkie filtry niedostępne

Katalog Publikacji

Rok 2021
Rok 2020
Rok 2019
  • An Analysis of Neural Word Representations for Wikipedia Articles Classification
    Publikacja

    - CYBERNETICS AND SYSTEMS - Rok 2019

    One 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...

    Pełny tekst do pobrania w serwisie zewnętrznym

  • Bees Detection on Images: Study of Different Color Models for Neural Networks
    Publikacja

    This paper presents an approach to bee detection in video streams using a neural network classifier. We describe the motivation for our research and the methodology of data acquisition. The main contribution to this work is a comparison of different color models used as an input format for a feedforward convolutional architecture applied to bee detection. The detection process has is based on a neural binary classifier that classifies...

    Pełny tekst do pobrania w portalu

  • Big Data and the Internet of Things in Edge Computing for Smart City
    Publikacja

    - Rok 2019

    Requests expressing collective human expectations and outcomes from city service tasks can be partially satisfied by processing Big Data provided to a city cloud via the Internet of Things. To improve the efficiency of the city clouds an edge computing has been introduced regarding Big Data mining. This intelligent and efficient distributed system can be developed for citizens that are supposed to be informed and educated by the...

    Pełny tekst do pobrania w serwisie zewnętrznym

  • Crowdsourcing-Based Evaluation of Automatic References Between WordNet and Wikipedia

    The paper presents an approach to build references (also called mappings) between WordNet and Wikipedia. We propose four algorithms used for automatic construction of the references. Then, based on an aggregation algorithm, we produce an initial set of mappings that has been evaluated in a cooperative way. For that purpose, we implement a system for the distribution of evaluation tasks, that have been solved by the user community....

    Pełny tekst do pobrania w portalu

  • Deep learning in the fog

    In the era of a ubiquitous Internet of Things and fast artificial intelligence advance, especially thanks to deep learning networks and hardware acceleration, we face rapid growth of highly decentralized and intelligent solutions that offer functionality of data processing closer to the end user. Internet of Things usually produces a huge amount of data that to be effectively analyzed, especially with neural networks, demands high...

    Pełny tekst do pobrania w serwisie zewnętrznym

  • Deep Learning Optimization for Edge Devices: Analysis of Training Quantization Parameters
    Publikacja

    - Rok 2019

    This paper focuses on convolution neural network quantization problem. The quantization has a distinct stage of data conversion from floating-point into integer-point numbers. In general, the process of quantization is associated with the reduction of the matrix dimension via limited precision of the numbers. However, the training and inference stages of deep learning neural network are limited by the space of the memory and a...

    Pełny tekst do pobrania w serwisie zewnętrznym

  • Distributed Architectures for Intensive Urban Computing: A Case Study on Smart Lighting for Sustainable Cities
    Publikacja

    - IEEE Access - Rok 2019

    New information and communication technologies have contributed to the development of the smart city concept. On a physical level, this paradigm is characterised by deploying a substantial number of different devices that can sense their surroundings and generate a large amount of data. The most typical case is image and video acquisition sensors. Recently, these types of sensors are found in abundance in urban spaces and are responsible...

    Pełny tekst do pobrania w serwisie zewnętrznym

  • Energy-Aware High-Performance Computing: Survey of State-of-the-Art Tools, Techniques, and Environments

    The paper presents state of the art of energy-aware high-performance computing (HPC), in particular identification and classification of approaches by system and device types, optimization metrics, and energy/power control methods. System types include single device, clusters, grids, and clouds while considered device types include CPUs, GPUs, multiprocessor, and hybrid systems. Optimization goals include various combinations of...

    Pełny tekst do pobrania w portalu

  • Evaluating Accuracy of Respiratory Rate Estimation from Super Resolved Thermal Imagery

    Non-contact estimation of Respiratory Rate (RR) has revolutionized the process of establishing the measurement by surpassing some issues related to attaching sensors to a body, e.g. epidermal stripping, skin disruption and pain. In this study, we perform further experiments with image processing-based RR estimation by using various image enhancement algorithms. Specifically, we employ Super Resolution (SR) Deep Learning (DL) network...

    Pełny tekst do pobrania w serwisie zewnętrznym

  • Evaluating Performance and Accuracy Improvements for Attention-OCR

    In this paper we evaluated a set of potential improvements to the successful Attention-OCR architecture, designed to predict multiline text from unconstrained scenes in real-world images. We investigated the impact of several optimizations on model’s accuracy, including employing dynamic RNNs (Recurrent Neural Networks), scheduled sampling, BiLSTM (Bidirectional Long Short-Term Memory) and a modified attention model. BiLSTM was...

    Pełny tekst do pobrania w serwisie zewnętrznym

  • Exact-match Based Wikipedia-WordNet Integration
    Publikacja

    Ability to link between WordNet synsets and Wikipedia articles allows usage of those resources by computers during natural language processing. A lot of work was done in this field, however most of the approaches focus on similarity between Wikipedia articles and WordNet synsets rather than creation of perfect matches. In this paper we proposed a set of methods for automatic perfect matching generation. The proposed methods were...

    Pełny tekst do pobrania w serwisie zewnętrznym

  • Extended investigation of performance-energy trade-offs under power capping in HPC environments
    Publikacja

    —In the paper we present investigation of performance-energy trade-offs under power capping using modern processors. The results are presented for systems targeted at both server and client markets and were collected from Intel Xeon E5 and Intel Xeon Phi server processors as well as from desktop and mobile Intel Core i7 processors. The results, when using power capping, show that we can find various interesting combinations of...

  • Influence of Thermal Imagery Resolution on Accuracy of Deep Learning based Face Recognition
    Publikacja

    Human-system interactions frequently require a retrieval of the key context information about the user and the environment. Image processing techniques have been widely applied in this area, providing details about recognized objects, people and actions. Considering remote diagnostics solutions, e.g. non-contact vital signs estimation and smart home monitoring systems that utilize person’s identity, security is a very important factor....

    Pełny tekst do pobrania w serwisie zewnętrznym

  • Low-Power WSN System for Honey Bee Monitoring
    Publikacja

    - Rok 2019

    The paper presents a universal low-power system for biosensory data acquisition in scope of bees monitoring. We describe the architecture of the system, energy-saving components as well as we discuss the selection of used sensors. The work focuses on energy optimization in a scope of wireless communication. A custom protocol was implemented, which is the basis for presented energy-efficient devices. Data exchange process during...

    Pełny tekst do pobrania w serwisie zewnętrznym

  • Multi-agent large-scale parallel crowd simulation with NVRAM-based distributed cache

    This paper presents the architecture, main components and performance results for a parallel and modu-lar agent-based environment aimed at crowd simulation. The environment allows to simulate thousandsor more agents on maps of square kilometers or more, features a modular design and incorporates non-volatile RAM (NVRAM) with a fail-safe mode that can be activated to allow to continue computationsfrom a recently analyzed state in...

    Pełny tekst do pobrania w serwisie zewnętrznym

  • Performance evaluation of Unified Memory with prefetching and oversubscription for selected parallel CUDA applications on NVIDIA Pascal and Volta GPUs
    Publikacja

    The paper presents assessment of Unified Memory performance with data prefetching and memory oversubscription. Several versions of code are used with: standard memory management, standard Unified Memory and optimized Unified Memory with programmer-assisted data prefetching. Evaluation of execution times is provided for four applications: Sobel and image rotation filters, stream image processing and computational fluid dynamic simulation,...

    Pełny tekst do pobrania w serwisie zewnętrznym

  • Performance/energy aware optimization of parallel applications on GPUs under power capping
    Publikacja

    In the paper we present an approach and results from application of the modern power capping mechanism available for NVIDIA GPUs to the bench- marks such as NAS Parallel Benchmarks BT, SP and LU as well as cublasgemm- benchmark which are widely used for assessment of high performance computing systems’ performance. Specifically, depending on the benchmarks, various power cap configurations are best for desired trade-off of performance...

    Pełny tekst do pobrania w portalu

  • Przetwarzanie wielkoskalowych danych w ochronie zdrowia - możliwości i korzyści
    Publikacja

    - Rok 2019

    W rozdziale przedstawiona została idea, pojęcia związane z przetwarzaniem wielkoskalowych danych oraz uogólniona architektura aktualnie wykorzystywanych tego typu systemów w zastosowaniach medycznych. Opisano funkcje oferowane przez bazowe elementy architektury ze szczególnym uwzględnieniem możliwości komponentu analityki dużych zbiorów danych medycznych. Na bazie dostępnej literatury przedmiotu dokonano zestawienia kluczowych...

  • Residual MobileNets

    As modern convolutional neural networks become increasingly deeper, they also become slower and require high computational resources beyond the capabilities of many mobile and embedded platforms. To address this challenge, much of the recent research has focused on reducing the model size and computational complexity. In this paper, we propose a novel residual depth-separable convolution block, which is an improvement of the basic...

    Pełny tekst do pobrania w serwisie zewnętrznym

  • Review of the Complexity of Managing Big Data of the Internet of Things
    Publikacja

    - COMPLEXITY - Rok 2019

    Tere is a growing awareness that the complexity of managing Big Data is one of the main challenges in the developing feld of the Internet of Tings (IoT). Complexity arises from several aspects of the Big Data life cycle, such as gathering data, storing them onto cloud servers, cleaning and integrating the data, a process involving the last advances in ontologies, such as Extensible Markup Language (XML) and Resource Description...

    Pełny tekst do pobrania w serwisie zewnętrznym

  • Review on Wikification methods
    Publikacja

    - AI COMMUNICATIONS - Rok 2019

    The paper reviews methods on automatic annotation of texts with Wikipedia entries. The process, called Wikification aims at building references between concepts identified in the text and Wikipedia articles. Wikification finds many applications, especially in text representation, where it enables one to capture the semantic similarity of the documents. Also, it can be considered as automatic tagging of the text. We describe typical...

    Pełny tekst do pobrania w serwisie zewnętrznym

  • Some Artificial Intelligence Driven Algorithms For Mobile Edge Computing in Smart City
    Publikacja

    - Rok 2019

    Smart mobile devices can share computing workload with the computer cloud that is important when artificial intelligence tools support computer systems in a smart city. This concept brings computing on the edge of the cloud, closer to citizens and it can shorten latency. Edge computing removes a crucial drawback of the smart city computing because city services are usually far away from citizens, physically. Besides, we introduced...

    Pełny tekst do pobrania w serwisie zewnętrznym

  • Study on population dynamics for triple-linked food chain using a simulation-based approach
    Publikacja

    - Evolving Systems - Rok 2019

    The procedures based on simulation have become a feasible testing method that does not require investing valuable resources to create a concrete prototype, especially with the increasing computational power of computers. Thus, design changes can be adopted and design errors can be fixed before it is too late. Simulation turns to be a cheap, safe and often more acceptable from an ethical perspective. In our work we summarize the...

    Pełny tekst do pobrania w portalu

  • Systematic approach to binary classification of images in video streams using shifting time windows

    in the paper, after pointing out of realistic recordings and classifications of their frames, we propose a new shifting time window approach for improving binary classifications. We consider image classification in tewo steps. in the first one the well known binary classification algorithms are used for each image separately. In the second step the results of the previous step mare analysed in relatively short sequences of consecutive...

    Pełny tekst do pobrania w serwisie zewnętrznym

  • The preferable ways of decision-making in IT teams

    Software development team collaboration requires various decisions regarding essential aspects of a project’s progress. General and particular decision-making models are considered, and their main aspects such as team types, problem solving categories, and decision-making ways are analyzed. The research concerns representative groups of IT specialists and their preferences in decision-making are investigated. Four possible cases were...

    Pełny tekst do pobrania w portalu