Sökning: "Hybrid Network"
Visar resultat 21 - 25 av 204 uppsatser innehållade orden Hybrid Network.
21. Transformer-Based Multi-scale Technical Reports Analyser for Science Projects Cost Prediction
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Intrinsic value prediction is a Natural Language Processing (NLP) problem consisting in determining a numerical value contained implicitly and non-trivially in a text. In this project, we introduce the SWORDSMAN model (Sentence and Word-level Oracle for Research Documents by Semantic Multi-scale ANalysis), a deep neural network architecture based on transformers whose goal is to predict the cost of research projects from the analysis of their abstract. LÄS MER
22. Challenges in establishing flexible work arrangements: an exploratory study on managers' and employees' perspectives
Magister-uppsats, Lunds universitet/Företagsekonomiska institutionenSammanfattning : The increased adoption of flexible work arrangements and changes in the habits and behaviors of employees since the COVID-19 pandemic have prompted companies to adapt their policies to accommodate these developments in the conditions of work. Despite being pioneers in flexible work arrangements, companies in Sweden still need to continuously refine their policies to meet the changing needs of their managers and employees. LÄS MER
23. Data-driven Fault Detection and Diagnosis inHardware-in-the-loop Environment
Master-uppsats, Uppsala universitet/Institutionen för informationsteknologiSammanfattning : The automotive industry has grown rapidly in the previous decades, and with the move toward electrification and driving assistance, the need for faster testing and development is rising.Model-based design(MBD) development cycles partly address the issues by allowing testing to happen before the physical product is created. LÄS MER
24. Team Leadership in remote settings An Actor-Network Theory Analysis
Master-uppsats, Göteborgs universitet/Graduate SchoolSammanfattning : Team Leadership (TL) is a topic that has been widely studied throughout the years. Previous studies on TL were focused on the individual and collective perspective. In recent years, technologies were included in the collective perspectives of TL under a remote setting by with the formation of Virtual Teams (VTs). LÄS MER
25. Establishment of a deep learning algorithm for dosimetry of radiopharmaceuticals
Master-uppsats,Sammanfattning : Purpose: The aim of this study was to introduce a volumetric convolutional neural network for segmentation of the kidneys in SPECT images and to apply it in the dosimetry of radiopharmaceuticals of this organ, in order to decrease segmentation time and to standardize the segmentation of the kidneys. Method: Three networks were trained using two network architectures and a total of 216 retrospectively collected images from patients that underwent imaging procedures at Sahlgrenska University Hospital between 2009 and 2018. LÄS MER