Sökning: "hårdvara prestanda"

Visar resultat 1 - 5 av 116 uppsatser innehållade orden hårdvara prestanda.

  1. 1. Exploration and Evaluation of RNN Models on Low-Resource Embedded Devices for Human Activity Recognition

    Master-uppsats, KTH/Mekatronik och inbyggda styrsystem

    Författare :Helgi Hrafn Björnsson; Jón Kaldal; [2023]
    Nyckelord :Recurrent Neural Networks; Long Short-Term Memory Networks; Embedded Systems; Human Activity Recognition; Edge AI; TensorFlow Lite Micro; Recurrent Neural Networks; Long Short-Term Memory Networks; Innbyggda systyem; Mänsklig aktivitetsigenkänning; Edge AI; TensorFlow Lite Micro;

    Sammanfattning : Human activity data is typically represented as time series data, and RNNs, often with LSTM cells, are commonly used for recognition in this field. However, RNNs and LSTM-RNNs are often too resource-intensive for real-time applications on resource constrained devices, making them unsuitable. LÄS MER

  3. 2. A Comparison Between Implementations of Cryptographic Algorithms and Their Efficiency in Smartphone Computing Environments : Exploring the Performance Trade-offs of Performing Cryptographic Work in Different Smartphone Development Frameworks

    Kandidat-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Ossian Dillner; [2023]
    Nyckelord :Cryptography; Security; Privacy; Smartphones; Kryptografi; Säkerhet; Integritet; Smartphones;

    Sammanfattning : In the recent decade concern for privacy has massively increased in the public consciousness. As a result of this development, demand for end-to-end secure communications in all manner of applications has also seen a rapid increase. This development can however often be at odds with other consumer demands. LÄS MER

  4. 3. Comparative Study of the Inference of an Image Quality Assessment Algorithm : Inference Benchmarking of an Image Quality Assessment Algorithm hosted on Cloud Architectures

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Jesper Petersson; [2023]
    Nyckelord :Machine learning; Cloud Computing; Benchmark; Image Quality Assessment; Maskininlärning; Molntjänster; Jämförelse; Bildkvalitetsbedömning;

    Sammanfattning : an instance has become exceedingly more time and resource consuming. To solve this issue, cloud computing is being used to train and serve the models. However, there’s a gap in research where these cloud computing platforms have been evaluated for these tasks. LÄS MER

  5. 4. Autonomous Navigation in Partially-Known Environment using Nano Drones with AI-based Obstacle Avoidance : A Vision-based Reactive Planning Approach for Autonomous Navigation of Nano Drones

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Mattia Sartori; [2023]
    Nyckelord :Nano Drones; Obstacle Avoidance; Autonomous Exploration; Autonomous Surveillance; Resource-Constrained Drones; Safe Navigation; Reactive Planning; Vision-based Navigation; Nanodrönare; Undvikande av Hinder; Autonom Utforskning; Autonom Övervakning; Resursbegränsade Drönare; Säker Navigering; Reaktiv Planering; Visionsbaserad Navigering;

    Sammanfattning : The adoption of small-size Unmanned Aerial Vehicles (UAVs) in the commercial and professional sectors is rapidly growing. The miniaturisation of sensors and processors, the advancements in connected edge intelligence and the exponential interest in Artificial Intelligence (AI) are boosting the affirmation of autonomous nano-size drones in the Internet of Things (IoT) ecosystem. LÄS MER

  7. 5. En prestandajämförelse mellan objektorienterad design och dataorienterad design i C++, Java och Java Project Valhalla

    M1-uppsats, KTH/Hälsoinformatik och logistik

    Författare :Andreas Isacsson; Christopher Renström; [2023]
    Nyckelord :Project Valhalla; primitive classes; Java; C ; data-oriented design; object-oriented design; cache; TLB; Project Valhalla; primitiva klasser; Java; C ; dataorienterad design; objektorienterad design; cacheminne; TLB;

    Sammanfattning : Datorspel behöver utnyttja hårdvara effektivt för att kunna vara tillgänglig på så många system som möjligt med varierande kapacitet. En viktig del i detta är att optimera användandet av processorns cacheminnen. Programmerare kan följa en dataorienterad design för att implementera cacheeffektiv kod. LÄS MER