A5056767452- Bioinformatics and Genomic Networks
- Cell Image Analysis Techniques
- Genetics, Bioinformatics, and Biomedical Research
- Biotin and Related Studies
- Machine Learning in Bioinformatics
- Radiomics and Machine Learning in Medical Imaging
- Radiopharmaceutical Chemistry and Applications
- Muscle activation and electromyography studies
- S100 Proteins and Annexins
- Virus-based gene therapy research
- EEG and Brain-Computer Interfaces
- AI in cancer detection
- Neuroscience and Neural Engineering
- Cell Adhesion Molecules Research
- Cytokine Signaling Pathways and Interactions
- RNA Research and Splicing
- Immunodeficiency and Autoimmune Disorders
- Advanced MIMO Systems Optimization
- bioluminescence and chemiluminescence research
- Stroke Rehabilitation and Recovery
- Advanced Wireless Network Optimization
- Digital Imaging for Blood Diseases
- Brain Tumor Detection and Classification
- Cooperative Communication and Network Coding
- Recommender Systems and Techniques
Deutsches Zentrum für Luft- und Raumfahrt e. V. (DLR)
2019-2023
Friedrich-Alexander-Universität Erlangen-Nürnberg
2022
Italian Institute of Technology
2018-2020
Center for Nano Science and Technology
2018
University of Pisa
2016
Sapienza University of Rome
2016
A hand amputation is a highly disabling event, having severe physical and psychological repercussions on person's life. Despite extensive efforts devoted to restoring the missing functionality via dexterous myoelectric prostheses, natural robust control usable in everyday life still challenging. Novel techniques have been proposed overcome current limitations, among them fusion of surface electromyography with other sources contextual information. We present dataset investigate inclusion eye...
This paper studies the base station (BS) spatial distributions across different scenarios in urban, rural, and coastal zones, based on real BS deployment data sets obtained from two European countries (i.e., Italy Croatia). Basically, this takes into account representative statistical to characterize probability density function of density, including Poisson, generalized Pareto, Weibull, lognormal, α-Stable. Based a thorough comparison with sets, our results clearly assess that α-Stable...
An emerging research area named Learning-to-Rank (LtR) has shown that effective solutions to the ranking problem can leverage machine learning techniques applied a large set of features capturing relevance candidate document for user query. Large-scale search systems must however answer queries very fast, and computation documents comply with strict back-end latency constraints. The number cannot thus grow beyond given limit, Feature Selection (FS) have be exploited find subset both meets...
The instability of myoelectric signals over time complicates their use to control poly-articulated prosthetic hands. To address this problem, studies have tried combine surface electromyography with modalities that are less affected by the amputation and environment, such as accelerometry gaze information. In latter case, hypothesis is a subject looks at object he or she intends manipulate, visual characteristics allow better predict desired hand posture. method we present in paper...
Natural myocontrol is the intuitive control of a prosthetic limb via user's voluntary muscular activations. This type usually implemented by means pattern recognition, which uses set training data to create model that can decipher these A consequence this approach reliability system depends on how representative for all types signal variability may be encountered when amputee puts prosthesis into real use. Myoelectric signals are indeed known vary according position and orientation limb,...
We consider the spatial distribution of Base Stations (BSs) in different scenarios a European country, with goal finding best theoretical fitting real data. focus on set possible distributions, including: Poisson, Weibull, generalized Pareto, Lognormal and α-Stable. Our results show that is rural scenario, while α-Stable most realistic one an urban case. This confirmed for sample areas, cellular technologies (i.e., 2G 3G).
Unsupervised myocontrol methods aim to create control models for myoelectric prostheses while avoiding the complications of acquiring reliable, regular, and sufficient labeled training data. A limitation current unsupervised is that they fix number controlled prosthetic functions a priori, thus requiring an initial assessment user's motor skills neglecting development novel over time.
Abstract Hand amputation is a highly disabling event, having severe physical and psychological repercussions on person’s life. Despite extensive efforts devoted to restoring the missing functionality via dexterous myoelectric hand prostheses, natural robust control usable in everyday life still challenging. Novel techniques have been proposed overcome current limitations, among which fusion of surface electromyography with other sources contextual information. We present dataset investigate...
Natural myocontrol employs pattern recognition to allow users control a robotic limb intuitively using their own voluntary muscular activations. The reliability of strongly depends on the signals initially collected from users, which must appropriately capture variability encountered later during operation. Since myoelectric can vary based position and orientation limb, it has become best practice gather data in multiple body postures. We hereby concentrate this acquisition protocol...
Abstract Objective. Pattern-recognition-based myocontrol can be unreliable, which may limit its use in the clinical practice and everyday activities. One cause for this is poor generalization of underlying machine learning models to untrained conditions. Acquiring training data building model more interactively reduce problem. For example, user could encouraged target model’s instabilities during acquisition supported by automatic feedback guidance. Interactivity an emerging trend upper-limb...
Applications of simultaneous and proportional control for upper-limb prostheses typically rely on supervised machine learning to map muscle activations prosthesis movements. This scheme often poses problems individuals with limb differences, as they may not be able reliably reproduce the training required construct a natural motor mapping. We propose an unsupervised myocontrol paradigm that eliminates need labeled data by mapping most salient synergies in arbitrary order number predefined...
The instability of myoelectric signals over time complicates their use to control highly articulated prostheses. To address this problem, studies have tried combine surface electromyography with modalities that are less affected by the amputation and environment, such as accelerometry or gaze information. In latter case, hypothesis is a subject looks at object he she intends manipulate knowing object's affordances allows constrain set possible grasps. paper, we develop an automated way...