Phase extraction from repetitive movements is one crucial part in various applications such as interactive robotics, physical rehabilitation, or gait analysis. However, pre-existing automatic phase extraction techniques are specific to a target movement due to some handcrafted-features. To make it more universal, a novel unsupervised-learning-based phase extraction technique is proposed. A neural network architecture and a cost function are designed to learn the concept of phase from records of a repetitive movement without any given phase label. The method is tested on a rat's gait cycle and a human's upper limb movement. The phases are successfully extracted at the sample level despite the variations in movement speed, trajectory, or subject's anthropometric features.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1109/EMBC.2018.8512196 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
A novel 3D-printed sample preparation method for benzodiazepine quantification in human serum.
Anal Chim Acta
February 2025
Department of Pharmaceutical Chemistry, Medical University of Gdansk, Hallera 107, 80-416, Gdansk, Poland.
Background: Benzodiazepine abuse remains a significant public health concern. Current sample preparation methods for benzodiazepine analysis from human serum often involve complex procedures that require large sample volumes and extensive organic solvent use. To address these limitations, this study presents a novel and efficient sample preparation method utilizing 3D-printed sorbent devices.
View Article and Find Full Text PDFDTI-MHAPR: optimized drug-target interaction prediction via PCA-enhanced features and heterogeneous graph attention networks.
BMC Bioinformatics
January 2025
School of Information and Artificial Intelligence, Anhui Agricultural University, Changjiang West Road, Hefei, 230036, Anhui, China.
Drug-target interactions (DTIs) are pivotal in drug discovery and development, and their accurate identification can significantly expedite the process. Numerous DTI prediction methods have emerged, yet many fail to fully harness the feature information of drugs and targets or address the issue of feature redundancy. We aim to refine DTI prediction accuracy by eliminating redundant features and capitalizing on the node topological structure to enhance feature extraction.
View Article and Find Full Text PDFSample preparation using deep eutectic solvents in combination with nanomaterials in analytical procedures: A review.
Anal Chim Acta
February 2025
School of Pharmacy, Sungkyunkwan University, Suwon, Gyeonggi-do, 16419, Republic of Korea. Electronic address:
Background: Sample preparation can be a critical stage of analytical procedures that profoundly influences their performance, environmental impact, and overall efficiency. While nanomaterials have revolutionized sample preparation owing to their high surface area-to-volume ratios, tunable surface chemistry, and enhanced adsorption capacities, limitations persist. Researchers have ushered in a new era of efficient sample preparation methodologies that could overcome the limitations of nanomaterials by introducing deep eutectic solvents (DESs), which have unique advantages such as low volatility and toxicity, biodegradability, and tunability.
View Article and Find Full Text PDFDetermination of five alternaria toxins in peppermint by dispersive solid-phase extraction coupled with ultra-high performance liquid chromatography-tandem mass spectrometry based on MOF-808-TFA.
Food Chem
January 2025
School of Chemistry and Chemical Engineering, Nanchang University, Nanchang 330031, People's Republic of China; State Key Laboratory of Food Science and Resources, Nanchang University, Nanchang 330031, People's Republic of China. Electronic address:
An efficient and rapid ultra-high performance liquid chromatography-tandem mass spectrometry (UHPLC-MSMS) method was developed for simultaneous determination of 5 alternaria toxins (ATs) in edible and medicinal plant - peppermint using MOF-808-trifluoroacetic acid (MOF-808-TFA) as the adsorbent. Characterization methods such as scanning electron microscopy (SEM), X-ray diffraction (XRD), X-ray photoelectron spectroscopy (XPS) and N adsorption-desorption demonstrated that the synthesized MOF-808-TFA had a regular ortho-octahedral configuration and high specific surface area. Under the optimal conditions, the 5 ATs showed good linearity (R ≥ 0.
View Article and Find Full Text PDFLittle is known about the impact of environmental pollution on thyroid function in the non-occupationally exposed population of Kazakhstan. This study aimed to investigate serum levels of thyroxine (T4), thyroid-stimulating hormone (TSH), and anti-thyroid peroxidase (TPO) antibodies in the environmentally exposed population of Kazakhstan in relation to symptoms of anxiety. A total of 1,388 nominally healthy individuals residing in areas exposed to three major types of environmental pollution prevalent in Kazakhstan-non-ferrous metallurgy, condensate gas extraction, and activities of the Semipalatinsk Nuclear Test Site (SNTS)-were enrolled.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!