Browse
Submit Data
Databases
API
Help

Dataset Information

23 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

FAN-MCCD: Fast and Accurate Network for Multi-Scale Chinese Character Detection

ABSTRACT: Inaccurate localization due to scale-variation during character detection causes a widespread issue overconfidence in results of the document analysis community, for the most part in historical and handwritten documents. In this work, we explored the performance of a state-of-the-art network with a simple pipeline that fast and accurately predicts handwritten Chinese characters in old documents. In order to adapt to locations of characters with multi-scale more precisely, excluding pre-processing and in-between steps, we utilized a network with multi-scale feature maps. Then, across each feature map, pre-selected boxes of unalike scales and aspect ratios were employed. The last step was to prune the bounding boxes, sending them to non-maximum suppression to yield the final results. Focusing on a well-designed neural network architecture and loss function that presents well-classified examples, we found our experiments on Caoshu, Character, and Src-images datasets demonstrated that detection performance was enhanced for the detection rate (DT), the false positive per character (FPPC), and the F-score in the order of 98.84%, 0.71, and 97.64%, respectively. In comparison with SSD (single-shot detector), the detection performance of a detection rate (DT), the false positive per character (FPPC), and the F-score were 61.12%, 6.12, and 60.33%, respectively.

SUBMITTER: Alnaasan M

PROVIDER: S-EPMC8586960 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Similar Datasets

QuartetS: a fast and accurate algorithm for large-scale orthology detection.

Project description:The unparalleled growth in the availability of genomic data offers both a challenge to develop orthology detection methods that are simultaneously accurate and high throughput and an opportunity to improve orthology detection by leveraging evolutionary evidence in the accumulated sequenced genomes. Here, we report a novel orthology detection method, termed QuartetS, that exploits evolutionary evidence in a computationally efficient manner. Based on the well-established evolutionary concept that gene duplication events can be used to discriminate homologous genes, QuartetS uses an approximate phylogenetic analysis of quartet gene trees to infer the occurrence of duplication events and discriminate paralogous from orthologous genes. We used function- and phylogeny-based metrics to perform a large-scale, systematic comparison of the orthology predictions of QuartetS with those of four other methods [bi-directional best hit (BBH), outgroup, OMA and QuartetS-C (QuartetS followed by clustering)], involving 624 bacterial genomes and >2 million genes. We found that QuartetS slightly, but consistently, outperformed the highly specific OMA method and that, while consuming only 0.5% additional computational time, QuartetS predicted 50% more orthologs with a 50% lower false positive rate than the widely used BBH method. We conclude that, for large-scale phylogenetic and functional analysis, QuartetS and QuartetS-C should be preferred, respectively, in applications where high accuracy and high throughput are required.

| S-EPMC3141274 | biostudies-literature

DeepSleep convolutional neural network allows accurate and fast detection of sleep arousal.

Project description:Sleep arousals are transient periods of wakefulness punctuated into sleep. Excessive sleep arousals are associated with symptoms such as sympathetic activation, non-restorative sleep, and daytime sleepiness. Currently, sleep arousals are mainly annotated by human experts through looking at 30-second epochs (recorded pages) manually, which requires considerable time and effort. Here we present a deep learning approach for automatically segmenting sleep arousal regions based on polysomnographic recordings. Leveraging a specific architecture that 'translates' input polysomnographic signals to sleep arousal labels, this algorithm ranked first in the "You Snooze, You Win" PhysioNet Challenge. We created an augmentation strategy by randomly swapping similar physiological channels, which notably improved the prediction accuracy. Our algorithm enables fast and accurate delineation of sleep arousal events at the speed of 10 seconds per sleep recording. This computational tool would greatly empower the scoring process in clinical settings and accelerate studies on the impact of arousals.

| S-EPMC7782826 | biostudies-literature

Fast and Accurate Large-Scale Detection of β-Lactamase Genes Conferring Antibiotic Resistance.

Project description:Fast detection of β-lactamase (bla) genes allows improved surveillance studies and infection control measures, which can minimize the spread of antibiotic resistance. Although several molecular diagnostic methods have been developed to detect limited bla gene types, these methods have significant limitations, such as their failure to detect almost all clinically available bla genes. We developed a fast and accurate molecular method to overcome these limitations using 62 primer pairs, which were designed through elaborate optimization processes. To verify the ability of this large-scale bla detection method (large-scaleblaFinder), assays were performed on previously reported bacterial control isolates/strains. To confirm the applicability of the large-scaleblaFinder, the assays were performed on unreported clinical isolates. With perfect specificity and sensitivity in 189 control isolates/strains and 403 clinical isolates, the large-scaleblaFinder detected almost all clinically available bla genes. Notably, the large-scaleblaFinder detected 24 additional unreported bla genes in the isolates/strains that were previously studied, suggesting that previous methods detecting only limited types of bla genes can miss unexpected bla genes existing in pathogenic bacteria, and our method has the ability to detect almost all bla genes existing in a clinical isolate. The ability of large-scaleblaFinder to detect bla genes on a large scale enables prompt application to the detection of almost all bla genes present in bacterial pathogens. The widespread use of the large-scaleblaFinder in the future will provide an important aid for monitoring the emergence and dissemination of bla genes and minimizing the spread of resistant bacteria.

| S-EPMC4576124 | biostudies-literature

Bayesian Multi-objective Hyperparameter Optimization for Accurate, Fast, and Efficient Neural Network Accelerator Design.

Project description:In resource-constrained environments, such as low-power edge devices and smart sensors, deploying a fast, compact, and accurate intelligent system with minimum energy is indispensable. Embedding intelligence can be achieved using neural networks on neuromorphic hardware. Designing such networks would require determining several inherent hyperparameters. A key challenge is to find the optimum set of hyperparameters that might belong to the input/output encoding modules, the neural network itself, the application, or the underlying hardware. In this work, we present a hierarchical pseudo agent-based multi-objective Bayesian hyperparameter optimization framework (both software and hardware) that not only maximizes the performance of the network, but also minimizes the energy and area requirements of the corresponding neuromorphic hardware. We validate performance of our approach (in terms of accuracy and computation speed) on several control and classification applications on digital and mixed-signal (memristor-based) neural accelerators. We show that the optimum set of hyperparameters might drastically improve the performance of one application (i.e., 52-71% for Pole-Balance), while having minimum effect on another (i.e., 50-53% for RoboNav). In addition, we demonstrate resiliency of different input/output encoding, training neural network, or the underlying accelerator modules in a neuromorphic system to the changes of the hyperparameters.

| S-EPMC7396641 | biostudies-literature

Fast and Accurate Disulfide Bridge Detection

Project description:Recombinant expression of proteins, propelled by therapeutic antibodies, has evolved into a multi-billion-dollar industry. Essential here is quality control assessment of critical attributes such as sequence fidelity, proper folding, and post-translational modifications (PTMs). Errors can lead to diminished bioactivity and, in the context of therapeutic proteins, an elevated risk for immunogenicity. Over the years, many techniques were developed and applied to validate proteins in a standardized and high-throughput fashion. One parameter has, however, so far been challenging to assess. Disulfide bridges, covalent bonds linking two Cysteine residues, assist in the correct folding and stability of proteins and thus have a major influence on their efficacy. Mass spectrometry promises to be an optimal technique to uncover them in a fast and accurate fashion. In this work, we present a unique combination of sample preparation, data acquisition and analysis facilitating the rapid and accurate assessment of disulfide bridges in purified proteins. Through microwave-assisted acid hydrolysis (MAAH), the proteins are digested rapidly and artifact-free into peptides, with a substantial degree of overlap over the sequence. The nonspecific nature of this procedure, however, introduces chemical background which is efficiently removed by integrating ion mobility preceding the mass spectrometric measurement. The nonspecific nature of the digestion step additionally necessitates new developments in data analysis, for which we extended the XlinkX node in Proteome Discoverer (XlinkX/PD) to efficiently process the data and ensure correctness through effective false discovery rate correction. The entire workflow can be completed within one hour, allowing for high-throughput, high-accuracy disulfide mapping

2024-04-08 | PXD046855 | Pride

MA-CharNet: Multi-angle fusion character recognition network.

Project description:Irregular text recognition of natural scene is a challenging task due to large span of character angles and morphological diversity of a word. Recent work first rectifies curved word region, and then employ sequence algorithm to complete the recognition task. However, this strategy largely depends on rectification quality of the text region, and cannot be applied to large difference between tilt angles of character. In this work, a novel anchor-free network structure of rotating character detection is proposed, which includes multiple sub-angle domain branch networks, and the corresponding branch network can be selected adaptively according to character tilt angle. Meanwhile, a curvature Adaptive Text linking method is proposed to connect the discrete strings detected on the two-dimensional plane into words according to people's habits. We achieved state-of-the-art performance on two irregular texts (TotalText, CTW1500), outperforming state-of-the-art by 2.4% and 2.7%, respectively. The experimental results demonstrate the effectiveness of the proposed algorithm.

| S-EPMC9423680 | biostudies-literature

Multi-scale analysis of the European airspace using network community detection.

Project description:We show that the European airspace can be represented as a multi-scale traffic network whose nodes are airports, sectors, or navigation points and links are defined and weighted according to the traffic of flights between the nodes. By using a unique database of the air traffic in the European airspace, we investigate the architecture of these networks with a special emphasis on their community structure. We propose that unsupervised network community detection algorithms can be used to monitor the current use of the airspace and improve it by guiding the design of new ones. Specifically, we compare the performance of several community detection algorithms, both with fixed and variable resolution, and also by using a null model which takes into account the spatial distance between nodes, and we discuss their ability to find communities that could be used to define new control units of the airspace.

| S-EPMC4014470 | biostudies-literature

RaPID: ultra-fast, powerful, and accurate detection of segments identical by descent (IBD) in biobank-scale cohorts.

Project description:While genetic relatedness, usually manifested as segments identical by descent (IBD), is ubiquitous in modern large biobanks, current IBD detection methods are not efficient at such a scale. Here, we describe an efficient method, RaPID, for detecting IBD segments in a panel with phased haplotypes. RaPID achieves a time and space complexity linear to the input size and the number of reported IBDs. With simulation, we showed that RaPID is orders of magnitude faster than existing method while offering competitive power and accuracy. In UK Biobank, RaPID identified 3,335,807 IBDs with a lenght ≥ 10 cM among 223,507 male X chromosomes in 11 min.

| S-EPMC6659282 | biostudies-literature

Towards Robust and Accurate Detection of Abnormalities in Musculoskeletal Radiographs with a Multi-Network Model.

Project description:This study proposes a novel multi-network architecture consisting of a multi-scale convolution neural network (MSCNN) with fully connected graph convolution network (GCN), named MSCNN-GCN, for the detection of musculoskeletal abnormalities via musculoskeletal radiographs. To obtain both detailed and contextual information for a better description of the characteristics of the radiographs, the designed MSCNN contains three subnetwork sequences (three different scales). It maintains high resolution in each sub-network, while fusing features with different resolutions. A GCN structure was employed to demonstrate global structure information of the images. Furthermore, both the outputs of MSCNN and GCN were fused through the concat of the two feature vectors from them, thus making the novel framework more discriminative. The effectiveness of this model was verified by comparing the performance of radiologists and three popular CNN models (DenseNet169, CapsNet, and MSCNN) with three evaluation metrics (Accuracy, F1 score, and Kappa score) using the MURA dataset (a large dataset of bone X-rays). Experimental results showed that the proposed framework not only reached the highest accuracy, but also demonstrated top scores on both F1 metric and kappa metric. This indicates that the proposed model achieves high accuracy and strong robustness in musculoskeletal radiographs, which presents strong potential for a feasible scheme with intelligent medical cases.

| S-EPMC7309003 | biostudies-literature

BASS: multi-scale and multi-sample analysis enables accurate cell type clustering and spatial domain detection in spatial transcriptomic studies.

Project description:Spatial transcriptomic studies are reaching single-cell spatial resolution, with data often collected from multiple tissue sections. Here, we present a computational method, BASS, that enables multi-scale and multi-sample analysis for single-cell resolution spatial transcriptomics. BASS performs cell type clustering at the single-cell scale and spatial domain detection at the tissue regional scale, with the two tasks carried out simultaneously within a Bayesian hierarchical modeling framework. We illustrate the benefits of BASS through comprehensive simulations and applications to three datasets. The substantial power gain brought by BASS allows us to reveal accurate transcriptomic and cellular landscape in both cortex and hypothalamus.

| S-EPMC9351148 | biostudies-literature

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data