Sökning: "Hierarchical Temporal"

Visar resultat 1 - 5 av 38 uppsatser innehållade orden Hierarchical Temporal.

  1. 1. Unsupervised Online Anomaly Detection in Multivariate Time-Series

    Uppsats för yrkesexamina på avancerad nivå, Uppsala universitet/Datorteknik

    Författare :Ludvig Segerholm; [2023]
    Nyckelord :unsupervised; online; anomaly detection; explainable ai; machine learning; mahalanobis distance;

    Sammanfattning : This research aims to identify a method for unsupervised online anomaly detection in multivariate time series in dynamic systems in general and on the case study of Devwards IoT-system in particular. A requirement of the solution is its explainability, online learning and low computational expense. LÄS MER

  2. 2. Towards Greener Pastures: Management of Corporate Sustainability Tensions in Internal Investment Decision-Making Processes

    D-uppsats, Handelshögskolan i Stockholm/Institutionen för redovisning och finansiering

    Författare :Ludwig Donath; Martin Lindström; [2023]
    Nyckelord :Internal Investment Decision-Making; Corporate Sustainability Tensions; Resource Allocation Process; Capital Budgeting Process; Paradox Theory;

    Sammanfattning : This qualitative study investigates the integration of corporate sustainability in the internal investment decision-making process and how potential corporate sustainability tensions are managed through the process. The two investment processes for capital investments and product developments were analyzed as the processes consider different Scope emissions and are both essential in organizations' endeavors towards a greener future. LÄS MER

  3. 3. Segmenting Countries in the Food Packaging Market: A Cluster Analysis Approach

    Magister-uppsats, Lunds universitet/Statistiska institutionen; Lunds universitet/Nationalekonomiska institutionen

    Författare :Ninda Atikah Mawaddah; Aksaraphak Nijsathorn; [2023]
    Nyckelord :Unsupervised Machine Learning; Clustering; K-Means Clustering; Hierarchical Clustering; Principal Component Analysis; Business and Economics;

    Sammanfattning : The food packaging market has been witnessing substantial growth due to changing consumer lifestyles, urbanization, increased purchasing power, and growing environmental sustainability awareness. This growth presents significant opportunities for companies operating in this market. LÄS MER

  4. 4. Large-scale Exploratory Text Visualisation

    Magister-uppsats, Linköpings universitet/Medie- och Informationsteknik; Linköpings universitet/Tekniska fakulteten

    Författare :Wilma Axelsson; Nellie Engström; [2023]
    Nyckelord :Natural language processing; information visualisation; text visualisation; Swedish news articles; dynamic topic modeling; hierarchical topic modeling; BERTopic;

    Sammanfattning : The amount of available text data has increased rapidly in the latest years, making it difficult for an everyday user to find relevant information. To solve this, NLP and visualisation methods have been developed for extracting valuable information from text and presenting it to the user. LÄS MER

  5. 5. Hierarchical Fusion Approaches for Enhancing Multimodal Emotion Recognition in Dialogue-Based Systems : A Systematic Study of Multimodal Emotion Recognition Fusion Strategy

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

    Författare :Yuqi Liu; [2023]
    Nyckelord :Multimodal; emotion recognition; hierarchical fusion; context modeling; attention mechanism; feature-level fusion; decision-level fusion; machine learning; deep learning; Multimodal; emotion recognition; hierarkisk fusion; kontextmodellering; uppmärksamhetsmekanism; funktionssammanfogning på nivån för egenskaper; beslutsnivås-funktionssammanfogning; maskininlärning; djupinlärning;

    Sammanfattning : Multimodal Emotion Recognition (MER) has gained increasing attention due to its exceptional performance. In this thesis, we evaluate feature-level fusion, decision-level fusion, and two proposed hierarchical fusion methods for MER systems using a dialogue-based dataset. LÄS MER