Sökning: "Memory errors"

Visar resultat 1 - 5 av 90 uppsatser innehållade orden Memory errors.

  1. 1. Punctuation Restoration as Post-processing Step for Swedish Language Automatic Speech Recognition

    Magister-uppsats, Luleå tekniska universitet/Institutionen för system- och rymdteknik

    Författare :Ishika Gupta; [2023]
    Nyckelord :Transformer; BERT; KB-BERT; NLP; punctuation restoration; deep learning; neural networks;

    Sammanfattning : This thesis focuses on the Swedish language, where punctuation restoration, especially as a postprocessing step for the output of Automatic Speech Recognition (ASR) applications, needs furtherresearch. I have collaborated with NewsMachine AB, a company that provides large-scale mediamonitoring services for its clients, for which it employs ASR technology to convert spoken contentinto text. LÄS MER

  3. 2. Design and Evaluation of a logging system in a power-constrained environment

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

    Författare :Morgan Adamsson; [2023]
    Nyckelord :Low power; logging; embedded systems; power supply; Bluetooth Low Energy; WiFi; flash memory; Låg effekt; loggning; inbyggda system; strömförsörjning; Bluetooth Low Energy; WiFi; flashminne;

    Sammanfattning : Logging plays a crucial role in debugging endeavors, assisting technicians in identifying errors and improving the overall sustainability of electrical systems. This thesis focuses on integrating local logging capabilities into the Balise Transmission Module (BTM), a legacy control system that lacks such features. LÄS MER

  4. 3. Forecasting Codeword Errors in Networks with Machine Learning

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

    Författare :Angus Hansson Svan; [2023]
    Nyckelord :Forecasting; Codeword Errors; Hybrid Fiber-Coaxial; Long Short-Term Memory; Multilayer Perceptron; Hybridfiber-koaxialt nätverk; HFC; LSTM; MLP;

    Sammanfattning : With an increasing demand for rapid high-capacity internet, the telecommunication industry is constantly driven to explore and develop new technologies to ensure stable and reliable networks. To provide a competitive internet service in this growing market, proactive detection and prevention of disturbances are key elements for an operator. LÄS MER

  5. 4. Does Rust SPARK joy? : Recommendations for safe cross-language bindings between Rust and SPARK

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

    Författare :Aïssata Maiga; [2023]
    Nyckelord :Rust; Ada; SPARK; Foreign Function Interface FFI ; memory safety; type safety; ownership; Rust; Ada; SPARK; Gränssnitt för främmande funktioner FFI ; minnessäkerhet; typsäkerhet; ägarskap;

    Sammanfattning : This thesis aims to provide recommendations for interfacing two memory-safe programming languages, Rust and SPARK. The comparison of Rust and C/C++, as well as SPARK and C/C++, has been thoroughly researched. However, this level of investigation hasn’t been as extensive between memory-safe languages. LÄS MER

  7. 5. System Integration and Verification Verdict Automation using Machine Learning

    Master-uppsats, Blekinge Tekniska Högskola/Institutionen för datavetenskap

    Författare :Anthony Kommareddy; [2023]
    Nyckelord :Error Detection; Machine Learning; Deep Learning; Log Files; Verdicts.;

    Sammanfattning : Context: The volume of log files is massive as they contain vital information about the application’s behavior; they map out broad parts of the application, allowing us to understand how every component behaves, whether normally or abnormally. As a result, it is critical to examine the log files to see if the system is deviating from its usual path. LÄS MER