960 results match your criteria hidden units


Accurate diagnosis of sepsis using a neural network: Pilot study using routine clinical variables.

Comput Methods Programs Biomed 2021 Aug 31;210:106366. Epub 2021 Aug 31.

Instituto Mexicano del Seguro Social, Centro Medico Nacional Siglo XXI, Hospital de cardiología, Mexico 0672, DF, Mexico. Electronic address:

Background And Objectives: Sepsis is a severe infection that increases mortality risk and is one if the main causes of death in intensive care units. Accurate detection is key to successful interventions, but diagnosis of sepsis is complicated because the initial signs and symptoms are not specific. Biomarkers that have been proposed have low specificity and sensitivity, are expensive, and not available in every hospital. Read More

View Article and Full-Text PDF

Continuous Myoelectric Prediction of Future Ankle Angle and Moment Across Ambulation Conditions and Their Transitions.

Front Neurosci 2021 18;15:709422. Epub 2021 Aug 18.

Department of Biomedical Engineering, Marquette University and Medical College of Wisconsin, Milwaukee, WI, United States.

A hallmark of human locomotion is that it continuously adapts to changes in the environment and predictively adjusts to changes in the terrain, both of which are major challenges to lower limb amputees due to the limitations in prostheses and control algorithms. Here, the ability of a single-network nonlinear autoregressive model to continuously predict future ankle kinematics and kinetics simultaneously across ambulation conditions using lower limb surface electromyography (EMG) signals was examined. Ankle plantarflexor and dorsiflexor EMG from ten healthy young adults were mapped to normal ranges of ankle angle and ankle moment during level overground walking, stair ascent, and stair descent, including transitions between terrains (i. Read More

View Article and Full-Text PDF

Improved protein relative solvent accessibility prediction using deep multi-view feature learning framework.

Anal Biochem 2021 Aug 31;631:114358. Epub 2021 Aug 31.

College of Information Engineering, Zhejiang University of Technology, Hangzhou, 310023, China. Electronic address:

The accurate prediction of the relative solvent accessibility of a protein is critical to understanding its 3D structure and biological function. In this study, a novel deep multi-view feature learning (DMVFL) framework that integrates three different neural network units, i.e. Read More

View Article and Full-Text PDF

A Correspondence between Normalization Strategies in Artificial and Biological Neural Networks.

Neural Comput 2021 Aug 30:1-25. Epub 2021 Aug 30.

Cold Spring Harbor Laboratory, Simons Center for Quantitative Biology, Cold Spring Harbor, NY 11724, U.S.A.

A fundamental challenge at the interface of machine learning and neuroscience is to uncover computational principles that are shared between artificial and biological neural networks. In deep learning, normalization methods such as batch normalization, weight normalization, and their many variants help to stabilize hidden unit activity and accelerate network training, and these methods have been called one of the most important recent innovations for optimizing deep networks. In the brain, homeostatic plasticity represents a set of mechanisms that also stabilize and normalize network activity to lie within certain ranges, and these mechanisms are critical for maintaining normal brain function. Read More

View Article and Full-Text PDF

Strong Emergence in Biological Systems: Is It Open to Mathematical Reasoning?

Acta Biotheor 2021 Aug 31. Epub 2021 Aug 31.

International Research Centre for Environmental Membrane Biology, Foshan University, Foshan, People's Republic of China.

Complex, multigenic biological traits are shaped by the emergent interaction of proteins being the main functional units at the molecular scale. Based on a phenomenological approach, algorithms for quantifying two different aspects of emergence were introduced (Wegner and Hao in Progr Biophys Mol Biol 161:54-61, 2021) describing: (i) pairwise reciprocal interactions of proteins mutually modifying their contribution to a complex trait (denoted as weak emergence), and (ii) formation of a new, complex trait by a set of n 'constitutive' proteins at concentrations exceeding individual threshold values (strong emergence). The latter algorithm is modified here to take account of protein redundancy with respect to a complex trait ('full redundancy'). Read More

View Article and Full-Text PDF

Quenched Lewis Acidity: Studies on the Medium Dependent Fluorescence of Zinc(II) Complexes.

Chemistry 2021 Aug 25. Epub 2021 Aug 25.

Universitat Bayreuth, Fachbereich Chemie, Universitätsstr. 30, NW I, 95440, Bayreuth, GERMANY.

Three new zinc(II) coordination units [Zn(1 - 3)] based on planar-directing tetradentate Schiff base-like ligands H 2 (1 - 3) were synthesized. Their solid-state structures were investigated by single crystal X-ray diffraction, showing the tendency to overcome the square-planar coordination sphere by axial ligation. Affinity in solution towards axial ligation has been tested by extended spectroscopic studies, both in the absorption and emission mode. Read More

View Article and Full-Text PDF

Refinements of Approximation Results of Conditional Restricted Boltzmann Machines.

IEEE Trans Neural Netw Learn Syst 2021 Aug 24;PP. Epub 2021 Aug 24.

Conditional restricted Boltzmann machines (CRBMs) are the conditional variant of restricted Boltzmann machines (RBMs), which are used to simulate conditional probability distributions. While promising for practical applications, there is a lack of theoretical studies on the approximation ability of CRBMs. In this article, by contributing analysis tools, especially designed for the conditional models, we improve the results of the representational power of CRBMs based on existing work on RBMs. Read More

View Article and Full-Text PDF

Health issue identification in social media based on multi-task hierarchical neural networks with topic attention.

Artif Intell Med 2021 08 31;118:102119. Epub 2021 May 31.

School of Computer Science and Engineering, Key Laboratory of Computer Network and Information Integration, Ministry of Education, Southeast University, Nanjing, Jiangsu Province 210096, China. Electronic address:

Objective: Health issue identification in social media is to predict whether the writers have a disease based on their posts. Numerous posts and comments are shared on social media by users. Certain posts may reflect writers' health condition, which can be employed for health issue identification. Read More

View Article and Full-Text PDF

Highly accurate real-time decomposition of single channel intramuscular EMG.

IEEE Trans Biomed Eng 2021 Aug 13;PP. Epub 2021 Aug 13.

Real-time intramuscular electromyography (iEMG) decomposition, as an identification procedure of individual motor neuron (MN) discharge timings from a streaming iEMG recording, has the potential to be used in human-machine interfacing. However, for these applications, the decomposition accuracy and speed of current approaches need to be improved.

Methods: In our previous work, a real-time decomposition algorithm based on a Hidden Markov Model of EMG, using GPU-implemented Bayesian filter to estimate the spike trains of motor units (MU) and their action potentials (MUAPs), was proposed. Read More

View Article and Full-Text PDF

Idiopathic Ventricular Fibrillation: Look for the Hidden Guilty-A case of aborted cardiac death.

Pediatr Cardiol 2021 Aug 10. Epub 2021 Aug 10.

Pediatric Cardiology and Arrhythmia/Syncope Units, Bambino Gesù Children's Hospital, IRCCS, Rome, Italy.

We report a unique case of a 6-year-old male child with aborted sudden cardiac death due to ventricular fibrillation. A rare anomalous aortic origin of the right coronary artery was detected and supposed to be the cause of the malignant arrhythmia. Clinical exome sequencing did not reveal any pathogenic variant related to channelopathies nor other known heart-related genes. Read More

View Article and Full-Text PDF

Neural-Network Quantum States for Spin-1 Systems: Spin-Basis and Parameterization Effects on Compactness of Representations.

Entropy (Basel) 2021 Jul 9;23(7). Epub 2021 Jul 9.

H.H. Wills Physics Laboratory, University of Bristol, Bristol BS8 1TL, UK.

Neural network quantum states (NQS) have been widely applied to spin-1/2 systems, where they have proven to be highly effective. The application to systems with larger on-site dimension, such as spin-1 or bosonic systems, has been explored less and predominantly using spin-1/2 Restricted Boltzmann Machines (RBMs) with a one-hot/unary encoding. Here, we propose a more direct generalization of RBMs for spin-1 that retains the key properties of the standard spin-1/2 RBM, specifically trivial product states representations, labeling freedom for the visible variables and gauge equivalence to the tensor network formulation. Read More

View Article and Full-Text PDF

Simultaneous annihilation of microorganisms and volatile organic compounds from municipal solid waste storage rooms with slightly acidic electrolyzed water.

J Environ Manage 2021 Nov 30;297:113414. Epub 2021 Jul 30.

Shanghai Environmental Engineering Design Research Institute, 345 Shilong Rd. (No. 11), Shanghai, 200232, PR China. Electronic address:

Great deal pathogenic bacteria and malodorous gases are hidden in municipal solid waste (MSW), which poses excellent environmental sanitation risks for sanitation workers and residents, and preventive measures should be implemented. In this study, the simultaneous annihilation of microorganisms and volatile organic compounds (VOCs) with slightly acidic electrolyzed water (SAEW) was investigated in an MSW storage room of a residential community in Shanghai, China. The microbial population of airborne, surfaces and handles of waste bins, hands of sanitation workers and the main components of VOCs were measured. Read More

View Article and Full-Text PDF
November 2021

Necrotizing Enterocolitis in Neonates: Has the Brain Taken a Hit 10 Years Later?

J Pediatr Neurosci 2021 Jan-Mar;16(1):30-34. Epub 2021 Jun 25.

Royal London Hospital, London, UK.

Background: The neonate with necrotizing enterocolitis (NEC) is at risk of developing poor neurodevelopmental outcomes. There is a dearth of long-term follow-up studies in this field, with a majority of studies reporting a follow-up duration of 2 years. The aim of this study was to assess neurodevelopment of babies diagnosed with NEC more than a decade ago. Read More

View Article and Full-Text PDF

Deep attributed graph clustering with self-separation regularization and parameter-free cluster estimation.

Neural Netw 2021 Oct 15;142:522-533. Epub 2021 Jul 15.

Beijing Municipal Key Laboratory of Multimedia and Intelligent Software Technology, Faculty of Information Technology, Beijing University of Technology, Beijing, 100124, China; Beijing Artificial Intelligence Institute, Beijing University of Technology, Beijing, 100124, China. Electronic address:

Detecting clusters over attributed graphs is a fundamental task in the graph analysis field. The goal is to partition nodes into dense clusters based on both their attributes and structures. Modern graph neural networks provide facilitation to jointly capture the above information in attributed graphs with a feature aggregation manner, and have achieved great success in attributed graph clustering. Read More

View Article and Full-Text PDF
October 2021

Human EEG and Recurrent Neural Networks Exhibit Common Temporal Dynamics During Speech Recognition.

Front Syst Neurosci 2021 8;15:617605. Epub 2021 Jul 8.

Canadian Centre for Behavioural Neuroscience, Department of Neuroscience, University of Lethbridge, Lethbridge, AB, Canada.

Recent deep-learning artificial neural networks have shown remarkable success in recognizing natural human speech, however the reasons for their success are not entirely understood. Success of these methods might be because state-of-the-art networks use recurrent layers or dilated convolutional layers that enable the network to use a time-dependent feature space. The importance of time-dependent features in human cortical mechanisms of speech perception, measured by electroencephalography (EEG) and magnetoencephalography (MEG), have also been of particular recent interest. Read More

View Article and Full-Text PDF

Opportunistic diagnosis of osteoporosis, fragile bone strength and vertebral fractures from routine CT scans; a review of approved technology systems and pathways to implementation.

Ther Adv Musculoskelet Dis 2021 10;13:1759720X211024029. Epub 2021 Jul 10.

University of Cambridge School of Clinical Medicine, Addenbrooke's Hospital, NIHR Cambridge Biomedical Research Centre, Cambridge, CB2 0QQ, UK.

Osteoporosis causes bones to become weak, porous and fracture more easily. While a vertebral fracture is the archetypal fracture of osteoporosis, it is also the most difficult to diagnose clinically. Patients often suffer further spine or other fractures, deformity, height loss and pain before diagnosis. Read More

View Article and Full-Text PDF

Remembering nothing: Encoding and memory processes involved in representing empty locations.

Mem Cognit 2021 Jul 19. Epub 2021 Jul 19.

Department of Psychological Sciences, Birkbeck University of London, Malet St, Bloomsbury, London, WC1E 7HX, UK.

Previous research has provided rich evidence that a set of visual objects can be encoded in isolation along with their exact coordinate positions as well as a global configuration that provides a network of interrelated spatial information. However, much less data is available on how unoccupied locations are encoded and maintained in memory. We tested this ability in adults using a novel paradigm that involved both empty and filled locations and required participants to monitor the addition or deletion of an item, which occurred 50% of the time. Read More

View Article and Full-Text PDF

Prediction of the motion of chest internal points using a recurrent neural network trained with real-time recurrent learning for latency compensation in lung cancer radiotherapy.

Comput Med Imaging Graph 2021 07 28;91:101941. Epub 2021 May 28.

National Institute for Quantum and Radiological Science and Technology, Chiba, Japan.

During the radiotherapy treatment of patients with lung cancer, the radiation delivered to healthy tissue around the tumor needs to be minimized, which is difficult because of respiratory motion and the latency of linear accelerator (LINAC) systems. In the proposed study, we first use the Lucas-Kanade pyramidal optical flow algorithm to perform deformable image registration (DIR) of chest computed tomography (CT) scan images of four patients with lung cancer. We then track three internal points close to the lung tumor based on the previously computed deformation field and predict their position with a recurrent neural network (RNN) trained using real-time recurrent learning (RTRL) and gradient clipping. Read More

View Article and Full-Text PDF

An Overview of Machine Learning within Embedded and Mobile Devices-Optimizations and Applications.

Sensors (Basel) 2021 Jun 28;21(13). Epub 2021 Jun 28.

Department of Electrical and Information Engineering, Covenant University, Ota 112233, Ogun State, Nigeria.

Embedded systems technology is undergoing a phase of transformation owing to the novel advancements in computer architecture and the breakthroughs in machine learning applications. The areas of applications of embedded machine learning (EML) include accurate computer vision schemes, reliable speech recognition, innovative healthcare, robotics, and more. However, there exists a critical drawback in the efficient implementation of ML algorithms targeting embedded applications. Read More

View Article and Full-Text PDF

Learning exact enumeration and approximate estimation in deep neural network models.

Cognition 2021 Oct 26;215:104815. Epub 2021 Jun 26.

Department of Teacher Education, Faculty of Social and Educational Sciences, NTNU-Norwegian University of Science and Technology, Norway. Electronic address:

A system for approximate number discrimination has been shown to arise in at least two types of hierarchical neural network models-a generative Deep Belief Network (DBN) and a Hierarchical Convolutional Neural Network (HCNN) trained to classify natural objects. Here, we investigate whether the same two network architectures can learn to recognise exact numerosity. A clear difference in performance could be traced to the specificity of the unit responses that emerged in the last hidden layer of each network. Read More

View Article and Full-Text PDF
October 2021

Nutritional management of individuals with obesity and COVID-19: ESPEN expert statements and practical guidance.

Clin Nutr 2021 May 11. Epub 2021 May 11.

Department of Clinical Nutrition, CHU Clermont-Ferrand, University of Clermont Auvergne, Human Nutrition Unit, CRNH Auvergne, F-63000, Clermont-Ferrand, France.

The COVID-19 pandemics has created unprecedented challenges and threats to patients and healthcare systems worldwide. Acute respiratory complications that require intensive care unit (ICU) management are a major cause of morbidity and mortality in COVID-19 patients. Among other important risk factors for severe COVID-19 outcomes, obesity has emerged along with undernutrition-malnutrition as a strong predictor of disease risk and severity. Read More

View Article and Full-Text PDF

Evidence of a new hidden neural network into deep fasciae.

Sci Rep 2021 Jun 16;11(1):12623. Epub 2021 Jun 16.

Department of Neurosciences, Institute of Human Anatomy, University of Padua, Via A. Gabelli 65, 35121, Padova, Italy.

It is recognized that different fasciae have different type of innervation, but actually nothing is known about the specific innervation of the two types of deep fascia, aponeurotic and epymisial fascia. In this work the aponeurotic thoracolumbar fascia and the epymisial gluteal fascia of seven adult C57-BL mice were analysed by Transmission Electron Microscopy and floating immunohistochemistry with the aim to study the organization of nerve fibers, the presence of nerve corpuscles and the amount of autonomic innervation. The antibodies used were Anti-S100, Anti-Tyrosine Hydroxylase and Anti-PGP, specific for the Schwann cells forming myelin, the sympathetic nerve fibers, and the peripheral nerve fibers, respectively. Read More

View Article and Full-Text PDF

Monitoring Parkinson's disease progression based on recorded speech with missing ordinal responses and replicated covariates.

Comput Biol Med 2021 07 28;134:104503. Epub 2021 May 28.

Departamento de Tecnologías de Los Computadores y de Las Comunicaciones, Escuela Politécnica, Universidad de Extremadura, 10003, Cáceres, Spain.

Monitoring Parkinson's Disease (PD) progression is an important task to improve the life quality of the affected people. This task can be performed by extracting features from voice recordings and applying specifically designed statistical models, leading to systems that improve the ability of monitoring the progression of PD in an objective, remote, non-invasive, fast, and economically sustainable way. An experiment has been conducted with 36 subjects to study the progression of the PD over 4 years by using the Hoehn and Yahr (HY) scale and features extracted from the phonation of the vowel/a/. Read More

View Article and Full-Text PDF

Selective, Modular Probes for Thioredoxins Enabled by Rational Tuning of a Unique Disulfide Structure Motif.

J Am Chem Soc 2021 Jun 1;143(23):8791-8803. Epub 2021 Jun 1.

Department of Pharmacy, Ludwig Maximilians University Munich, Butenandtstraße 5-13, 81377 Munich, Germany.

Specialized cellular networks of oxidoreductases coordinate the dithiol/disulfide-exchange reactions that control metabolism, protein regulation, and redox homeostasis. For probes to be selective for redox enzymes and effector proteins (nM to μM concentrations), they must also be able to resist non-specific triggering by the ca. 50 mM background of non-catalytic cellular monothiols. Read More

View Article and Full-Text PDF

Cataloguing the bacterial diversity in the active ectomycorrhizal zone of from a dry deciduous forest of Shorea.

Biodivers Data J 2021 19;9:e63086. Epub 2021 May 19.

Department of Botany, Dr Shyama Prasad Mukherjee University, Ranchi-834008, India Department of Botany, Dr Shyama Prasad Mukherjee University Ranchi-834008 India.

The plant microbiome has been considered one of the most researched areas of microbial biodiversity, yet very little information is available on the microbial communities prevailing in the mushroom's ectomycorrhizosphere. Ectomycorrhizal symbioses often result in the formation of a favourable niche which enables the thriving of various microbial symbionts where these symbionts endorse functions, such as quorum sensing, biofilm formation, volatile microbial compound (VOC) production, regulation of microbial gene expression, symbiosis and virulence. The identification of hidden uncultured microbial communities around the active ectomycorrhizal zone of from dry deciduous sal forest of Jharkhand, India was carried out using MinION Oxford Nanopore sequencing of 16S rRNA amplicons genes. Read More

View Article and Full-Text PDF

Allopatric differentiation in the Enteromius anoplus complex in South Africa, with the revalidation of Enteromius cernuus and Enteromius oraniensis, and description of a new species, Enteromius mandelai (Teleostei: Cyprinidae).

J Fish Biol 2021 Sep 25;99(3):931-954. Epub 2021 May 25.

Department of Ichthyology and Fisheries Science, Rhodes University, Makhanda, South Africa.

The chubbyhead barb, Enteromius anoplus, as currently described, is the most widely distributed freshwater fish in South Africa. The species occurs in almost all the major river systems across the country, with the exception of the small coastal drainages on the south coast. The use of a comprehensive data set of mitochondrial (mtDNA) cytochrome b (cyt b) sequences uncovered the presence of four distinct lineages or operational taxonomic units (OTUs) within E. Read More

View Article and Full-Text PDF
September 2021

"We can't just have a casual conversation": An institutional ethnography-informed study of work in labour and birth.

Soc Sci Med 2021 06 29;279:113975. Epub 2021 Apr 29.

Wilson Centre for Research in Education, University Health Network, University of Toronto, Canada; University of Toronto's Centre for Interprofessional Education, University Health Network, Canada; Department of Speech-Language Pathology, University of Toronto, Canada.

Labour and delivery units often become contested workplaces with tensions between obstetrics, nursing, and midwifery practices. These tensions can impede communication and raise concerns about provider wellness and patient safety. Remedying such tensions requires inquiry into the drivers of recurrent problems in interprofessional practice. Read More

View Article and Full-Text PDF

Surveying keratose sponges (Porifera, demospongiae, Dictyoceratida) reveals hidden diversity of host specialist barnacles (Crustacea, Cirripedia, Balanidae).

Mol Phylogenet Evol 2021 08 20;161:107179. Epub 2021 Apr 20.

Collections & Research, Western Australian Museum, 49 Kew St, Welshpool 6106 WA, Australia.

Sponges represent one of the most species-rich hosts for commensal barnacles yet host utilisation and diversity have not been thoroughly examined. This study investigated the diversity and phylogenetic relationships of sponge-inhabiting barnacles within a single, targeted host group, primarily from Western Australian waters. Specimens of the sponge order Dictyoceratida were surveyed and a total of 64 host morphospecies, representing four families, were identified as barnacle hosts during the study. Read More

View Article and Full-Text PDF

Evolving in islands of mud: old and structured hidden diversity in an endemic freshwater crayfish from the Chilean hotspot.

Sci Rep 2021 Apr 21;11(1):8573. Epub 2021 Apr 21.

Instituto de Ciencias Ambientales y Evolutivas, Facultad de Ciencias, Universidad Austral de Chile, Campus Isla Teja S/N, Valdivia, Chile.

Parastacus is a genus of South American freshwater crayfishes disjunctively distributed in southern Chile, Northern Argentina, Uruguay and Southeastern Brazil. Parastacus pugnax is a Chilean endemic distributed along 700 km of latitude in central-southern Chile from the Pacific coast to the Andean piedmont, which is intensively captured for consumption for local communities. Considering the habitat (wet meadows) and natural history (primary burrower, non-migrant) of the species, we tested a hypothesis of highly structured genetic diversity using mtDNA of 465 specimens gathered at 56 localities across the species range. Read More

View Article and Full-Text PDF

The impact of nurse staffing levels on nursing-sensitive patient outcomes: a multilevel regression approach.

Eur J Health Econ 2021 Jul 19;22(5):833-846. Epub 2021 Apr 19.

Hamburg Center for Health Economics, University of Hamburg, Esplanade 36, 20354, Hamburg, Germany.

The goal of this study is to provide empirical evidence of the impact of nurse staffing levels on seven nursing-sensitive patient outcomes (NSPOs) at the hospital unit level. Combining a very large set of claims data from a German health insurer with mandatory quality reports published by every hospital in Germany, our data set comprises approximately 3.2 million hospital stays in more than 900 hospitals over a period of 5 years. Read More

View Article and Full-Text PDF