Essays about: "innovativa metoder"

Showing result 1 - 5 of 71 essays containing the words innovativa metoder.

1. 1. Modulating Depth Map Features to Estimate 3D Human Pose via Multi-Task Variational Autoencoders

   University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Author : Kobe Moerman; [2023]
   Keywords : 3D pose estimation; Joint landmarks; Variational autoencoder; Multi-task model; Loss discrimination; Latent-space modulation; Depth map; 3D-positionsuppskattning; Gemensamma landmärken; Variationell autoencoder; Multitask-modell; Förlustdiskriminering; Latent-space-modulering; Djupkarta;

   Abstract : Human pose estimation (HPE) constitutes a fundamental problem within the domain of computer vision, finding applications in diverse fields like motion analysis and human-computer interaction. This paper introduces innovative methodologies aimed at enhancing the accuracy and robustness of 3D joint estimation. READ MORE

3. 2. EMONAS : Evolutionary Multi-objective Neuron Architecture Search of Deep Neural Network

   University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Author : Jiayi Feng; [2023]
   Keywords : DNN Deep Neural Network ; NAS Neural Architecture Search ; EA Evolutionary Algorithm ; Multi-Objective Optimization; Binary One Optimization; Embedded Systems; DNN Deep Neural Network ; NAS Neural Architecture Search ; EA Evolutionary Algorithm ; Multi-Objective Optimization; Binary One Optimization; Inbyggda system;

   Abstract : Customized Deep Neural Network (DNN) accelerators have been increasingly popular in various applications, from autonomous driving and natural language processing to healthcare and finance, etc. However, deploying them directly on embedded system peripherals within real-time operating systems (RTOS) is not easy due to the paradox of the complexity of DNNs and the simplicity of embedded system devices. READ MORE

4. 3. Cyber Threat Detection using Machine Learning on Graphs : Continuous-Time Temporal Graph Learning on Provenance Graphs

   University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Author : Jakub Reha; [2023]
   Keywords : Graph neural networks; Temporal graphs; Benchmark datasets; Anomaly detection; Heterogeneous graphs; Provenance graphs; Grafiska neurala nätverk; temporala grafer; benchmark-datauppsättningar; anomalidetektering; heterogena grafer; härkomstgrafer;

   Abstract : Cyber attacks are ubiquitous and increasingly prevalent in industry, society, and governmental departments. They affect the economy, politics, and individuals. READ MORE

5. 4. Tuning Photovoltaic Properties of Two-dimensional Molybdenum Disulfide by Alloying: An ab initio study

   University essay from KTH/Materialvetenskap

   Author : Mochen Li; [2023]
   Keywords : Photovoltaic; Molybdenum disulfide; Absorption coefficient; ab initio material design; Fotovoltaisk; Molybdendisulfid; Absorptionskoefficient; ab initio materialdesign;

   Abstract : Addressing the urgent need for innovative energy solutions amidst increasing environmental concerns, the focus on photovoltaic solar cells is intensifying. Currently limited by the Shockley-Queisser limit, conventional silicon-based solar cells offer a maximum power conversion efficiency of 32%. READ MORE

6. 5. Enhancing Long-Term Human Motion Forecasting using Quantization-based Modelling. : Integrating Attention and Correlation for 3D Motion Prediction

   University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Author : Luis González Gudiño; [2023]
   Keywords : Human Motion Forecasting; Long-Term Prediction; VQ-VAE; Quantization; 3D Human Motion; CMU MoCap Dataset; Transformer; Mänsklig Rörelseprognos; Långsiktig Prognos; VQ-VAE; Kvantisering; 3D-mänsklig rörelse; CMU MoCap Dataset; Transformer;

   Abstract : This thesis focuses on addressing the limitations of existing human motion prediction models by extending the prediction horizon to very long-term forecasts. The objective is to develop a model that achieves one of the best stable prediction horizons in the field, providing accurate predictions without significant error increase over time. READ MORE