Sökning: "learning loop"

Visar resultat 31 - 35 av 68 avhandlingar innehållade orden learning loop.

  1. 31. Prediction of zinc-binding sites in proteins and efficient protein structure description and comparison

    Författare :Nanjiang Shu; Sven Hovmöller; Elisabeth Sauer-Eriksson; Alexander Luybartsev; Stockholms universitet; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; zinc-binding; shape strings; protein structures; secondary structures; machine learning; Molecular biology; Molekylärbiologi; Biochemistry; Biokemi; Bioinformatics; Bioinformatik; Structural biology; Strukturbiologi; Biochemistry; biokemi; strukturbiologi; Structural Biology; Molecular Biology; molekylärbiologi;

    Sammanfattning : A large number of proteins require certain metals to stabilize their structures or to function properly. About one third of all proteins in the Protein Data Bank (PDB) contain metals and it is estimated that approximately the same proportion of all proteins are metalloproteins. LÄS MER

  3. 32. Migration strategies of raptors – spatio-temporal adaptations and constraints in travelling and foraging

    Författare :Roine Strandberg; Biologiska institutionen; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; route convergence; loop migration; mortality; spatio-temporal distribution patterns; pre- and post-migratory movements; daily travel routines; satellite tracking; fly-and-forage migration; raptors;

    Sammanfattning : My dissertation is about bird migration and addresses questions about how raptors adapt to the fluctuating environments during the transition seasons between breeding and wintering. The migration is highly affected by local prey abundance, foraging strategies, weather conditions and landscape patterns along the migration routes as well as navigation and orientation mechanisms and cues. LÄS MER

  4. 33. High-Density Electromyography-Based Methods for Joint Torque Prediction and Motor Unit Behavior Observation

    Författare :Asta Kizyte; Ruoli Wang; Elena Gutierrez-Farewik; Christian Antfolk; KTH; []
    Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Ankle; isometric contractions; machine learning; neuromuscular control; spinal cord injury; Fotled; isometriska kontraktioner; maskininlärning; neuromuskulär kontroll; ryggmärgsskada; Teknisk mekanik; Engineering Mechanics;

    Sammanfattning : Electromyography (EMG) is a technique that measures the electrical activity of muscles. It reflects muscle activation and provides an interface to the central nervous system at the level of the muscle or individual motor units, which helps us understand the mechanisms of muscle force production, control, and coordination. LÄS MER

  5. 34. Interactive Optimisation in Marine Propeller Design

    Författare :Ioli Gypa; Chalmers tekniska högskola; []
    Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; NATURVETENSKAP; NATURAL SCIENCES; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; marine propeller design; support-vector machines; machine learning; NSGA-II; optimisation; interactive genetic algorithms; progressively interactive evolutionary computation;

    Sammanfattning : Marine propeller design is a complex engineering problem that depends on the collaboration of several scientific disciplines. During the design process, the blade designers need to consider contradicting requirements and come up with one optimal propeller design as a solution to the specific problem. LÄS MER

  7. 35. Towards clinically viable neuromuscular control of bone-anchored prosthetic arms with sensory feedback

    Författare :Enzo Mastinu; Chalmers tekniska högskola; []
    Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; NATURVETENSKAP; NATURAL SCIENCES; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Electromyography; prosthetics; sensory feedback; closed-loop; osseointegration; embedded system; pattern recognition; neurostimulation;

    Sammanfattning : Promising developments are currently ongoing worldwide in the field of neuroprosthetics and artificial limb control. It is now possible to chronically connect a robotic limb to bone, nerves, and muscles of a human being, and to use the signals sourced from these connections to enable movements of the artificial limb. LÄS MER