30,235 results match your criteria networks proposed

Exponential passivity of discrete-time switched neural networks with transmission delays via an event-triggered sliding mode control.

Neural Netw 2021 Jun 15;143:271-282. Epub 2021 Jun 15.

Department of Basic, Qinghai University, Xining 810016, China.

This paper investigates the exponential passivity of discrete-time switched neural networks (DSNNs) with transmission delays via an event-triggered sliding mode control (SMC). Firstly, a novel discrete-time switched SMC scheme is constructed on the basis of sliding mode control method and event-triggered mechanism. Next, a state observer with transmission delays is designed to estimate the system state. Read More

View Article and Full-Text PDF

Delving Deep into Label Smoothing.

IEEE Trans Image Process 2021 Jun 24;PP. Epub 2021 Jun 24.

Label smoothing is an effective regularization tool for deep neural networks (DNNs), which generates soft labels by applying a weighted average between the uniform distribution and the hard label. It is often used to reduce the overfitting problem of training DNNs and further improve classification performance. In this paper, we aim to investigate how to generate more reliable soft labels. Read More

View Article and Full-Text PDF

Improving Weakly Supervised Temporal Action Localization by Exploiting Multi-resolution Information in Temporal Domain.

IEEE Trans Image Process 2021 Jun 24;PP. Epub 2021 Jun 24.

Weakly supervised temporal action localization is a challenging task as only the video-level annotation is available during the training process. To address this problem, we propose a two-stage approach to fully exploit multi-resolution information in the temporal domain and generate high-quality frame-level pseudo labels based on both appearance and motion information. Specifically, in the first stage, we generate reliable initial frame-level pseudo labels. Read More

View Article and Full-Text PDF

Genetic variant effect prediction by supervised nonnegative matrix tri-factorization.

Mol Omics 2021 Jun 24. Epub 2021 Jun 24.

Department of Genetics and Molecular Biology, School of Medicine, Isfahan University of Medical Sciences, Isfahan, Iran and GTaC Corp., Deputy of Research and Technology, Isfahan University of Medical Sciences, Isfahan, Iran.

Discriminating between deleterious and neutral mutations among numerous non-synonymous single nucleotide variants (nsSNVs) that may be observed through whole exome sequencing (WES) is considered a great challenge. In this regard, many machine learning methods have been developed for the prediction of variant consequences based on the analysis of either protein amino acid sequences or protein structures or their integration with features extracted from various gene level data and phenotype information. Due to the availability of a high number of features and heterogeneity of sources, implementing a suitable integration method plays an important role in predictive models. Read More

View Article and Full-Text PDF

A chemically consistent graph architecture for massive reaction networks applied to solid-electrolyte interphase formation.

Chem Sci 2021 Feb 24;12(13):4931-4939. Epub 2021 Feb 24.

Department of Materials Science and Engineering, University of California Berkeley CA 94720 USA.

Modeling reactivity with chemical reaction networks could yield fundamental mechanistic understanding that would expedite the development of processes and technologies for energy storage, medicine, catalysis, and more. Thus far, reaction networks have been limited in size by chemically inconsistent graph representations of multi-reactant reactions ( A + B → C) that cannot enforce stoichiometric constraints, precluding the use of optimized shortest-path algorithms. Here, we report a chemically consistent graph architecture that overcomes these limitations using a novel multi-reactant representation and iterative cost-solving procedure. Read More

View Article and Full-Text PDF
February 2021

Spiking Neural Network for Fourier Transform and Object Detection for Automotive Radar.

Front Neurorobot 2021 7;15:688344. Epub 2021 Jun 7.

Department of Informatics, Technical University of Munich, Munich, Germany.

The development of advanced autonomous driving applications is hindered by the complex temporal structure of sensory data, as well as by the limited computational and energy resources of their on-board systems. Currently, neuromorphic engineering is a rapidly growing field that aims to design information processing systems similar to the human brain by leveraging novel algorithms based on spiking neural networks (SNNs). These systems are well-suited to recognize temporal patterns in data while maintaining a low energy consumption and offering highly parallel architectures for fast computation. Read More

View Article and Full-Text PDF

Understanding the Impact of Neural Variations and Random Connections on Inference.

Front Comput Neurosci 2021 7;15:612937. Epub 2021 Jun 7.

Electrical and Computer Engineering Department, Lehigh University, Bethlehem, PA, United States.

Recent research suggests that neural networks created from dissociated neurons may be used for computing and performing machine learning tasks. To develop a better artificial intelligent system, a hybrid bio-silicon computer is worth exploring, but its performance is still inferior to that of a silicon-based computer. One reason may be that a living neural network has many intrinsic properties, such as random network connectivity, high network sparsity, and large neural and synaptic variability. Read More

View Article and Full-Text PDF

Classification of impedance cardiography dZ/dt complex subtypes using pattern recognition artificial neural networks.

Biomed Tech (Berl) 2021 Jun 23. Epub 2021 Jun 23.

Department for Clinical Science, Intervention and Technology, Karolinska Institutet, Stockholm, Sweden.

In impedance cardiography (ICG), the detection of dZ/dt signal (ICG) characteristic points, especially the X point, is a crucial step for the calculation of hemodynamic parameters such as stroke volume (SV) and cardiac output (CO). Unfortunately, for beat-to-beat calculations, the accuracy of the detection is affected by the variability of the ICG complex subtypes. Thus, in this work, automated classification of ICG complexes is proposed to support the detection of ICG characteristic points and the extraction of hemodynamic parameters according to several existing subtypes. Read More

View Article and Full-Text PDF

How to handle noisy labels for robust learning from uncertainty.

Neural Netw 2021 Jun 12;143:209-217. Epub 2021 Jun 12.

Center for Global Converging Humanities, Kyung Hee University, Yongin 17104, South Korea. Electronic address:

Most deep neural networks (DNNs) are trained with large amounts of noisy labels when they are applied. As DNNs have the high capacity to fit any noisy labels, it is known to be difficult to train DNNs robustly with noisy labels. These noisy labels cause the performance degradation of DNNs due to the memorization effect by over-fitting. Read More

View Article and Full-Text PDF

Fast mesh data augmentation via Chebyshev polynomial of spectral filtering.

Neural Netw 2021 Jun 9;143:198-208. Epub 2021 Jun 9.

Department of Biomedical Engineering, National University of Singapore, Singapore; Institute of Data Science, National University of Singapore, Singapore; The N.1 Institute for Health, National University of Singapore, Singapore; The Johns Hopkins University, MD, USA. Electronic address:

Deep neural networks have recently been recognized as one of the powerful learning techniques in computer vision and medical image analysis. Trained deep neural networks need to be generalizable to new data that are not seen before. In practice, there is often insufficient training data available, which can be solved via data augmentation. Read More

View Article and Full-Text PDF

Recursive Deep Prior Video: A super resolution algorithm for time-lapse microscopy of organ-on-chip experiments.

Med Image Anal 2021 Jun 4;72:102124. Epub 2021 Jun 4.

Department of Electronic Engineering, University of Tor Vergata, Via del Politecnico 1, Rome 00133, Italy; Interdisciplinary Center for Advanced Studies on Lab-on-Chip and Organ-on-Chip Applications (ICLOC), University of Tor Vergata, Via del Politecnico 1, Rome 00133, Italy.

Biological experiments based on organ-on-chips (OOCs) exploit light Time-Lapse Microscopy (TLM) for a direct observation of cell movement that is an observable signature of underlying biological processes. A high spatial resolution is essential to capture cell dynamics and interactions from recorded experiments by TLM. Unfortunately, due to physical and cost limitations, acquiring high resolution videos is not always possible. Read More

View Article and Full-Text PDF

IBA-U-Net: Attentive BConvLSTM U-Net with Redesigned Inception for medical image segmentation.

Comput Biol Med 2021 Jun 12;135:104551. Epub 2021 Jun 12.

Department of Systems and Computer Engineering, Carleton University, Ottawa, ON, KIS 5B6, Canada.

Accurate segmentation of medical images plays an essential role in their analysis and has a wide range of research and application values in fields of practice such as medical research, disease diagnosis, disease analysis, and auxiliary surgery. In recent years, deep convolutional neural networks have been developed that show strong performance in medical image segmentation. However, because of the inherent challenges of medical images, such as irregularities of the dataset and the existence of outliers, segmentation approaches have not demonstrated sufficiently accurate and reliable results for clinical employment. Read More

View Article and Full-Text PDF

DNB: A Joint Learning Framework for Deep Bayesian Nonparametric Clustering.

IEEE Trans Neural Netw Learn Syst 2021 Jun 22;PP. Epub 2021 Jun 22.

Clustering algorithms based on deep neural networks have been widely studied for image analysis. Most existing methods require partial knowledge of the true labels, namely, the number of clusters, which is usually not available in practice. In this article, we propose a Bayesian nonparametric framework, deep nonparametric Bayes (DNB), for jointly learning image clusters and deep representations in a doubly unsupervised manner. Read More

View Article and Full-Text PDF

Memristor-based Neural Network Circuit of Emotion Congruent Memory with Mental Fatigue and Emotion Inhibition.

IEEE Trans Biomed Circuits Syst 2021 Jun 22;PP. Epub 2021 Jun 22.

Most memristor-based neural networks only consider a single mode of memory or emotion, but ignore the relationship between emotion and memory. In this paper, a memristor-based neural network circuit of emotion congruent memory is proposed and verified by the simulation results. The designed circuit consists of a memory module, an emotion module and an association neuron module. Read More

View Article and Full-Text PDF

Mask-R[Formula: see text]CNN: a distance-field regression version of Mask-RCNN for fetal-head delineation in ultrasound images.

Int J Comput Assist Radiol Surg 2021 Jun 22. Epub 2021 Jun 22.

Department of Information Engineering, Università Politecnica delle Marche, Ancona, Italy.

Background And Objectives: Fetal head-circumference (HC) measurement from ultrasound (US) images provides useful hints for assessing fetal growth. Such measurement is performed manually during the actual clinical practice, posing issues relevant to intra- and inter-clinician variability. This work presents a fully automatic, deep-learning-based approach to HC delineation, which we named Mask-R[Formula: see text]CNN. Read More

View Article and Full-Text PDF

Convolutional neural networks for the classification of chest X-rays in the IoT era.

Multimed Tools Appl 2021 Jun 17:1-15. Epub 2021 Jun 17.

Artificial Intelligence Department, Near East University, Nicosia, North Cyprus via Mersin 10, Turkey.

Chest X-ray medical imaging technology allows the diagnosis of many lung diseases. It is known that this technology is frequently used in hospitals, and it is the most accurate way of detecting most thorax diseases. Radiologists examine these images to identify lung diseases; however, this process can require some time. Read More

View Article and Full-Text PDF

UTLDR: an agent-based framework for modeling infectious diseases and public interventions.

J Intell Inf Syst 2021 Jun 17:1-22. Epub 2021 Jun 17.

KDD Laboratory, ISTI-CNR, Pisa, Italy.

Due to the SARS-CoV-2 pandemic, epidemic modeling is now experiencing a constantly growing interest from researchers of heterogeneous study fields. Indeed, due to such an increased attention, several software libraries and scientific tools have been developed to ease the access to epidemic modeling. However, only a handful of such resources were designed with the aim of providing a simple proxy for the study of the potential effects of public interventions (e. Read More

View Article and Full-Text PDF

Chaos synchronization based on cluster fusion in asymmetric coupling semiconductor lasers networks.

Opt Express 2021 May;29(11):16334-16345

A novel cluster fusion method is proposed, based on which chaos synchronization in asymmetric coupling semiconductor lasers (ACSLs) networks is systematically demonstrated. Take the cluster fusion of a mutually-coupled network composed of 7 semiconductor lasers (SLs) for instance, the characteristics of chaos synchronization as well as the influences of coupling strength, bias current, and mismatches of intrinsic parameters and injection strength on the quality of chaos synchronization in hybrid clusters composed of ACSLs are thoroughly investigated. The results show that by using cluster fusion, the ACSLs which originally belong to different clusters can form three types of new hybrid clusters, namely, trivial-hybrid cluster, trivial-nontrivial-hybrid cluster, and nontrivial-hybrid cluster. Read More

View Article and Full-Text PDF

Accuracy-enhanced coherent Ising machine using the quantum adiabatic theorem.

Opt Express 2021 Jun;29(12):18530-18539

The coherent Ising machine (CIM) implemented by degenerate optical parametric oscillator (DOPO) networks is a novel optical platform to accelerate computation of hard combinatorial optimization problems. Nevertheless, with the increase of the problem size, the probability of the machine being trapped by local minima increases exponentially. According to the quantum adiabatic theorem, a physical system will remain in its instantaneous ground state if the time-dependent Hamiltonian varies slowly enough. Read More

View Article and Full-Text PDF

Brain variability in dynamic resting-state networks identified by fuzzy entropy: a scalp EEG study.

J Neural Eng 2021 Jun 21. Epub 2021 Jun 21.

University of Electronic Science and Technology of China, No.2006, Xiyuan Ave, West Hi-Tech Zone, Chengdu, 611731, CHINA.

Objective: Exploring the temporal variability in spatial topology during the resting state attracts growing interest and becomes increasingly useful to tackle the cognitive process of brain networks. In particular, the temporal brain dynamics during the resting state may be delineated and quantified aligning with cognitive performance, but few studies investigated the temporal variability in the electroencephalogram (EEG) network as well as its relationship with cognitive performance.

Approach: In this study, we proposed an EEG-based protocol to measure the nonlinear complexity of the dynamic resting-state network by applying the fuzzy entropy. Read More

View Article and Full-Text PDF

Iterative confidence relabeling with deep ConvNets for organ segmentation with partial labels.

Comput Med Imaging Graph 2021 May 15;91:101938. Epub 2021 May 15.

Visible Patient, 8 rue Gustave Adolphe Hirn, Strasbourg, 67000, France.

Training deep ConvNets requires large labeled datasets. However, collecting pixel-level labels for medical image segmentation is very expensive and requires a high level of expertise. In addition, most existing segmentation masks provided by clinical experts focus on specific anatomical structures. Read More

View Article and Full-Text PDF

Cancer diagnosis using generative adversarial networks based on deep learning from imbalanced data.

Comput Biol Med 2021 Jun 12;135:104540. Epub 2021 Jun 12.

Department of Electrical and Computer Engineering, University of Virginia, Charlottesville, VA, 22904-4743, USA. Electronic address:

Background And Objective: Cancer is a serious global disease due to its high mortality, and the key to effective treatment is accurate diagnosis. However, limited by sampling difficulty and actual sample size in clinical practice, data imbalance is a common problem in cancer diagnosis, while most conventional classification methods assume balanced data distribution. Therefore, addressing the imbalanced learning problem to improve the predictive performance of cancer diagnosis is significant. Read More

View Article and Full-Text PDF

Economy and carbon emissions optimization of different countries or areas in the world using an improved Attention mechanism based long short term memory neural network.

Sci Total Environ 2021 Jun 16;792:148444. Epub 2021 Jun 16.

College of Information Science & Technology, Beijing University of Chemical Technology, Beijing, China; Engineering Research Center of Intelligent PSE, Ministry of Education in China, Beijing, China. Electronic address:

The combustion of fossil fuels produces a large amount of carbon dioxide (CO), which leads to global warming in the world. How to rationally consume fossil energy and control CO emissions has become an unavoidable problem for human beings while vigorously developing economy. This paper proposes a novel economy and CO emissions prediction model using an improved Attention mechanism based long short term memory (LSTM) neural network (Attention-LSTM) to analyze and optimize the energy consumption structures in different countries or areas. Read More

View Article and Full-Text PDF

Conditional generation of medical images via disentangled adversarial inference.

Med Image Anal 2021 May 24;72:102106. Epub 2021 May 24.

Imagia, Canada; Montréal Institute for Learning Algorithms (MILA), Université de Montréal, Canada; West China Biomedical Big Data Center, West China Hospital of Sichuan University, Chengdu, China. Electronic address:

Synthetic medical image generation has a huge potential for improving healthcare through many applications, from data augmentation for training machine learning systems to preserving patient privacy. Conditional Adversarial Generative Networks (cGANs) use a conditioning factor to generate images and have shown great success in recent years. Intuitively, the information in an image can be divided into two parts: 1) content which is presented through the conditioning vector and 2) style which is the undiscovered information missing from the conditioning vector. Read More

View Article and Full-Text PDF

Heterogeneous networks: Fair power allocation in LTE-A uplink scenarios.

Reben Kurda

PLoS One 2021 21;16(6):e0252421. Epub 2021 Jun 21.

Department of Information System Engineering Techniques, Erbil Technical Engineering College, Erbil Polytechnic University, Erbil, Iraq.

Effective management of radio resources and service quality assurance are two of the essential aspects to furnish high-quality service in Long Term Evolution (LTE) networks. Despite the base station involving several ingenious scheduling schemes for resource allocation, the intended outcome might be influenced by the interference, especially in heterogeneous scenarios, where many kinds of small cells can be deployed under the coverage of macrocell area. To develop the network of small cells, it is essential to take into account such boundaries, in particular, mobility, interference and resources scheduling a strategy which assist getting a higher spectral efficiency in anticipate small cells. Read More

View Article and Full-Text PDF

Eigenvalue-based entropy in directed complex networks.

PLoS One 2021 21;16(6):e0251993. Epub 2021 Jun 21.

School of Computer, Qinghai Normal University, Xining, China.

Entropy is an important index for describing the structure, function, and evolution of network. The existing research on entropy is primarily applied to undirected networks. Compared with an undirected network, a directed network involves a special asymmetric transfer. Read More

View Article and Full-Text PDF

Automatic assessment of Pectus Excavatum severity from CT images using deep learning.

IEEE J Biomed Health Inform 2021 Jun 21;PP. Epub 2021 Jun 21.

Pectus excavatum (PE) is the most common abnormality of the thoracic cage, whose severity is evaluated by extracting three indices (Haller, correction and asymmetry) from computed tomography (CT) images. To date, this analysis is performed manually, which is tedious and prone to variability. In this paper, a fully automatic framework for PE severity quantification from CT images is proposed, comprising three steps: (1) identification of the sternue's greatest depression point; (2) detection of 8 anatomical keypoints relevant for severity assessment; and (3) measurements' geometric regularization and extraction. Read More

View Article and Full-Text PDF

Essential Protein Prediction Based on node2vec and XGBoost.

J Comput Biol 2021 Jun 21. Epub 2021 Jun 21.

School of Computer Science and Engineering, Central South University, Changsha, P.R. China.

Essential proteins are a vital part of the survival of organisms and cells. Identification of essential proteins lays a solid foundation for understanding protein functions and discovering drug targets. The traditional biological experiments are expensive and time-consuming. Read More

View Article and Full-Text PDF

Automating Periodontal bone loss measurement via dental landmark localisation.

Int J Comput Assist Radiol Surg 2021 Jun 21. Epub 2021 Jun 21.

Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS) and Department of Computer Science, University College London, London, UK.

Purpose: Periodontitis is the sixth most prevalent disease worldwide and periodontal bone loss (PBL) detection is crucial for its early recognition and establishment of the correct diagnosis and prognosis. Current radiographic assessment by clinicians exhibits substantial interobserver variation. Computer-assisted radiographic assessment can calculate bone loss objectively and aid in early bone loss detection. Read More

View Article and Full-Text PDF

A flexible microfluidic strategy to generate grooved microfibers for guiding cell alignment.

Biomater Sci 2021 Jun 21. Epub 2021 Jun 21.

CAS Key Laboratory of SSAC, Dalian Institute of Chemical Physics, Chinese Academy of Sciences, Dalian, 116023, P.R. China. and University of Chinese Academy of Sciences, Beijing, 100049, P.R. China and Institute for Stem Cell and Regeneration, Chinese Academy of Sciences, Beijing, 100101, P.R. China and CAS Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences, Shanghai, 200031, China.

Hydrogel microfibers are widely applied in tissue engineering and regenerative medicine due to their tunable morphology, componential anisotropy, and good biocompatibility. Specifically, grooved microfibers with unique advantages can facilitate cell alignment for mimicking the microstructures of myobundles. Herein, a microfluidic spinning system is proposed for flexibly generating grooved microfibers relying on the volume change after ionic crosslinking of sodium alginate (NaA) with different concentrations. Read More

View Article and Full-Text PDF