Search

Arrhythmia is a prevalent cardiovascular disease, which has garnered widespread attention due to its age‐related increases in mortality rates. In the analysis of arrhythmia, the electrocardiogram (ECG) plays an important role. Arrhythmia classification often suffers from a significant data imbalance issue due to the limited availability of data for certain arrhythmia categories. This imbalance problem significantly affects the classification performance of the model. To address this challenge, data augmentation emerges as a viable solution, aiming to neutralize the adverse effects of imbalanced datasets on the model. To this end, this paper proposes a novel Multimodality Data Augmentation Network (MM‐DANet) for arrhythmia classification. The MM‐DANet consists of two modules: the multimodality data matching‐based data augmentation module and the multimodality feature encoding module. In the multimodality data matching‐based data augmentation module, we expand the underrepresented arrhythmia categories to match the size of the largest category. Subsequently, the multimodality feature encoding module employs convolutional neural networks (CNN) to extract the modality‐specific features from both signals and images and concatenate them for efficient and accurate classification. The MM‐DANet was evaluated on the MIT‐BIH Arrhythmia Database and achieving an accuracy of 98.83%, along with an average specificity of 98.87%, average sensitivity of 92.92%, average precision of 91.05%, and average F1_score of 91.96%. Furthermore, its performance was also assessed on the St. Petersburg INCART arrhythmia database and the MIT‐BIH supraventricular arrhythmia database, yielding AUC values of 81.98% and 90.93%, respectively. These outstanding results not only underscore the effectiveness of MM‐DANet but also indicate its potential for facilitating reliable automated analysis of arrhythmias. [ABSTRACT FROM AUTHOR]

RNA‐binding proteins (RBPs) play significant roles in many biological life activities, many algorithms and tools are proposed to predict RBPs for researching biological mechanisms of RNA‐protein binding sites. Deep learning algorithms based on traditional machine learning get better result for predicting RBPs. Recently, deep learning method fused with attention mechanism has attracted huge attention in many fields and gets competitive result. Thus, attention mechanism module may also improve model performance for predicting RNA‐protein binding sites. In this study, we propose convolutional residual multi‐head self‐attention network (CRMSNet) that combines convolutional neural network (CNN), ResNet, and multi‐head self‐attention blocks to find RBPs for RNA sequence. First, CRMSNet incorporates convolutional neural networks, recurrent neural networks, and multi‐head self‐attention block. Second, CRMSNet can draw binding motif pictures from the convolutional layer parameters. Third, attention mechanism module combines the local and global RNA sequence information for capturing long sequence feature. CRMSNet gets competitive AUC (area under the receiver operating characteristic [ROC] curve) result in a large‐scale dataset RBP‐24. And CRMSNet experiment result is also compared with other state‐of‐the‐art methods. The source code of our proposed CRMSNet method can be found in https://github.com/biomg/CRMSNet. [ABSTRACT FROM AUTHOR]

SUMMARY: Lateral organ boundaries domain (LBD) proteins are plant‐specific transcription factors. Class‐I LBD genes have been widely demonstrated to play pivotal roles in organ development; however, knowledge on class‐II genes remains limited. Here, we report that ZmLBD5, a class‐II LBD gene, is involved in the regulation of maize (Zea mays) growth and the drought response by affecting gibberellin (GA) and abscisic acid (ABA) synthesis. ZmLBD5 is mainly involved in regulation of the TPS‐KS‐GA2ox gene module, which is comprised of key enzyme‐encoding genes involved in GA and ABA biosynthesis. ABA insufficiency increases stomatal density and aperture in overexpression plants and causes a drought‐sensitive phenotype by promoting water transpiration. Increased GA1 levels promotes seedling growth in overexpression plants. Accordingly, CRISPR/Cas9 knockout lbd5 seedlings are dwarf but drought‐tolerant. Moreover, lbd5 has a higher grain yield under drought stress conditions and shows no penalty in well‐watered conditions compared to the wild type. On the whole, ZmLBD5 is a negative regulator of maize drought tolerance, and it is a potentially useful target for drought resistance breeding. Significance Statement: Maize (Zea mays) ZmLBD5 is mainly associated with abscisic acid (ABA) and gibberellin (GA) synthesis by regulating the TPS‐KS‐GA2ox gene module, which is comprised of key enzyme‐encoding genes involved in GA and ABA biosynthesis. ZmLBD5 negatively regulates drought tolerance by repressing ABA synthesis and promoting stomatal development and opening; however, lbd5 mutants have higher grain yield under drought stress conditions and show no penalty in well‐watered conditions compared to the wild type. [ABSTRACT FROM AUTHOR]

Summary: Root architecture remodelling is critical for forage moisture in water‐limited soil. DEEPER ROOTING 1 (DRO1) in Oryza, Arabidopsis, and Prunus has been reported to improve drought avoidance by promoting roots to grow downward and acquire water from deeper soil. In the present study, we found that ZmDRO1 responded more strongly to abscisic acid (ABA)/drought induction in Zea mays ssp. mexicana, an ancestral species of cultivated maize, than in B73. It was proposed that this is one of the reasons why Zea mays ssp. mexicana has a more noticeable change in the downward direction angle of the root and fewer biomass penalties under water‐deficient conditions. Thus, a robust, synthetic ABA/drought‐inducible promoter was used to control the expression of ZmDRO1B73 in Arabidopsis and cultivated maize for drought‐resistant breeding. Interestingly, ABA‐inducible ZmDRO1 promoted a larger downward root angle and improved grain yield by more than 40% under water‐limited conditions. Collectively, these results revealed that different responses to ABA/drought induction of ZmDRO1 confer different drought avoidance abilities, and we demonstrated the application of ZmDRO1 via an ABA‐inducible strategy to alter the root architecture of modern maize to improve drought adaptation in the field. [ABSTRACT FROM AUTHOR]

The objective of this article is to solve the current social phenomenon of a large number of fatigue driving, so that social safety becomes more stable in the future, and the detection and application of driving fatigue are more meaningful. This article aims to study the application of graph neural network (GNN) in driving fatigue detection (this article is abbreviated as DFD) based on EEG signals. This article uses a pattern classification method based on a multilayer perceptual overlimit learning machine to find the hidden information of the signal through an unsupervised learning self-encoding structure, which achieves the optimization purpose and has a better classification effect than traditional classifiers. An improved soft threshold (the soft threshold can be used to solve the optimization problem, and the optimization problem solved is similar to the base pursuit noise reduction problem, but it is not the same, and it should be noted that the soft threshold cannot solve the base pursuit noise reduction problem) denoising algorithm is selected, and the collected EEG (a technique for capturing brain activity using electrophysiological markers is the electroencephalogram). The sum of the postsynaptic potentials produced simultaneously by a large number of neurons occurs when the brain is active. It records the process of brain activity in the cerebral cortex or scalp surface) signals are preprocessed, so that the feature extraction efficiency of extracting EEG signals is improved. The final experimental data show that the traditional support vector machine, SVM algorithm, and the KNN convolutional neural (the K-nearest neighbor method, often known as KNN, was first put forth by Cover and Hart in 1968. It is one of the most straightforward machine learning algorithms and a theoretically sound approach) algorithms has a recognition rate of 79% and 81% for fatigue. The improved algorithm in this article has an average recognition rate of 87.5% for driver fatigue, which is greatly improved. [ABSTRACT FROM AUTHOR]

Graphene oxide (GO) with 0.2, 0.5, and 1.0 wt% loading was used to modify warm‐mix epoxy asphalt binders (WEABs). The thermal stability, structure of GO, rotational viscosity‐curing time performance, dynamic moduli, glass transitions, damping ability, mechanical performance, and phase‐separated morphology of GO/epoxy asphalt composites were investigated in the laboratory. GO significantly enhanced the thermal stability of the pure WEAB. X‐ray scattering analysis revealed that GO layers were delaminated in the epoxy asphalt binder. GO accelerated the cure reaction of the pure WEAB and thus resulted in higher rotational viscosity of GO/epoxy asphalt composites. Furthermore, the viscosity of the modified WEABs slightly increased in the GO content. GO increased the dynamic moduli and Tgs of both epoxy and asphalt for the pure WEAB. However, the damping ability of GO/epoxy asphalt composites was similar to that of the pure WEAB. Confocal microscopy observations revealed that GO was dispersed in both asphalt and epoxy phases of the phase‐separated WEAB. The asphalt domains in the continuous epoxy phase became more spherical and uniform with the existence of GO. Moreover, the dispersion of epoxy in the discontinuous asphalt phase became more evident. The mechanical properties of the pure WEAB were greatly improved with the addition of GO. The tensile toughness and strength of the pure WEAB increased by 31% and 33%, respectively, with the addition of 0.2 wt% GO. [ABSTRACT FROM AUTHOR]

Summary: Browning decreases the quality and shortens the shelf life of fresh‐cut potato, causing enormous economic losses. This study indicated that nitrogen treatment could inhibit this browning process. However, whether microRNAs (miRNAs) are involved in inhibiting the fresh‐cut potato browning by nitrogen remains unclear. Therefore, nine small RNA libraries were constructed and performed high‐throughput sequencing using fresh‐cut potatoes from control and nitrogen‐treated for 1 h groups at 25 °C to identify the miRNAs and their target genes involved in fresh‐cut potato browning inhibition by nitrogen. The results revealed that four common differentially expressed miRNAs (DEmiRNAs) were identified as associated with browning. The correlation analysis indicated that fresh‐cut potato browning was closely related to the expression of DEmiRNAs and their potential target genes. The miR172d targeting APETALA2/ethylene response factor and phospholipase D, miR482e targeting ATPase GET3‐like, and PC‐3p‐17015_391 targeting stachyose synthase are vital in the nitrogen inhibited fresh‐cut potato browning by regulating the ethylene signalling pathway, membrane lipid metabolic process, ATPase activity, and carbohydrate metabolic process. This study provides new insights into fresh‐cut potato browning inhibition and helps to improve the quality of fresh‐cut potato using nitrogen. [ABSTRACT FROM AUTHOR]

At present, the global positioning system has been widely used in outdoor positioning and navigation, but in buildings, thick walls made of cement and bricks have a certain blocking effect on satellite signals, resulting in severely weakened GPS signals, and also extremely it may have an impact on the positioning accuracy, so that the positioning task cannot be completed. Inertial sensor is a kind of sensor mainly detecting and measuring acceleration tilt impact vibration rotation and multi-degree-of-freedom motion, is an important part to solve navigation orientation and motion carrier control. Therefore, we need to study the positioning system and positioning method of the people in the building according to the indoor positioning technology. This article mainly uses inertial sensors as indoor positioning technology for related research. This technology mainly includes linked inertial navigation algorithm and pedestrian dead reckoning algorithm. This paper uses pedestrian dead reckoning algorithm to study the positioning system. The research shows that the PDR algorithm designed this time is more accurate for the positioning of pedestrian movement in the scene of the building. Compared with the previous algorithm research, it has increased by 1%-2% accuracy meets the expected accuracy requirements. [ABSTRACT FROM AUTHOR]

Fatigue driving is one of the main reasons for the occurrence of traffic accidents. Brain-computer interface, as a human-computer interaction method based on EEG signals, can communicate with the outside world and move freely through brain signals without relying on the peripheral neuromuscular system. In this paper, a simulation driving platform composed of driving simulation equipment and driving simulation software is used to simulate the real driving process. The EEG signals of the subjects are collected through simulated driving, and the EEG of five subjects is selected as the training sample, and the remaining one is the subject. As a test sample, perform feature extraction and classification experiments, select any set of normal signals and fatigue signals recorded in the driving fatigue experiment for data analysis, and then study the classification of driver fatigue levels. Experiments have proved that the PSO-H-ELM algorithm has only about 4% advantage compared with the average accuracy of the KNN algorithm and the SVM algorithm. The gap is not as big as expected, but as a new algorithm, it is applied to the detection of fatigue EEG. The two traditional algorithms are indeed more suitable. It shows that the driver fatigue level can be judged by detecting EEG, which will provide a basis for the development of on-board, real-time driving fatigue alarm devices. It will lay the foundation for traffic management departments to intervene in driving fatigue reasonably and provide a reliable basis for minimizing traffic accidents. [ABSTRACT FROM AUTHOR]

The frontal eye field (FEF) is a key part of the oculomotor system, with dominant responses to the direction of single saccades. However, whether and how FEF contributes to sequential saccades remain largely unknown. By training rhesus monkeys to perform saccade sequences, we found sequence‐related activities in FEF neurons, whose selectivity to saccade direction undergoes dynamic changes during sequential vs. single saccades. These sequence‐related activities are context‐dependent, exhibiting different firing activities during memory‐ vs. visually guided sequences. When the monkey was performing the sequential saccade task, the thresholds of microstimulation to evoke saccades in FEF were increased and the percentage of the successfully induced saccades was significantly reduced compared with the fixation condition. Pharmacological inactivation of FEF impaired the monkey's performance of previously learned sequential saccades, with different effects on the same actions depending on its position within the sequence. These results reveal the context‐dependent, sequence‐specific dynamic encoding of saccades in FEF, and underscore the crucial role of FEF in the planning and execution of sequential saccades. Key points: FEF neurons respond differently during sequential vs. single saccadesSequence‐related FEF activity is context‐dependentThe microstimulation threshold in FEF was increased during the sequential task but the evoked saccade did not alter the sequence structureFEF inactivation severely impaired the performance of sequential saccades [ABSTRACT FROM AUTHOR]

Driving fatigue is a physiological phenomenon that often occurs during driving. When the driver enters a fatigue state, they will become distracted and unresponsive, which can easily lead to traffic accidents. The driving fatigue detection method based on a single information source has poor stability in a specific driving environment and has great limitations. This work helps with being able to judge the fatigue state of the driver more comprehensively and achieving a higher accuracy rate of driving fatigue detection. This work mainly introduces research into different signal fusion methods to detect fatigue drive. This work will take the normal driver's breathing signal, eye signals, and steering wheel signal as research objects and collect and isolate the characteristics of the fatigue detection signal. Research was then conducted on different signal fusion methods for the detected depth of breath. Change of steering angle, eyelid closure, and blinking marks and the fatigue driving experiment was designed to evaluate the results of different data fusion methods. Experimental results show that the detection accuracy of the heterogeneous signal fusion method in fatigue detection is as high as 80%. [ABSTRACT FROM AUTHOR]

Epoxy asphalt bond coat (EABC) has been widely used as a bonding layer in the construction of orthotropic steel deck bridges. To withstand the vibration of the steel deck, EABC needs to have strong bonding strength. In present article, sodium montmorillonite (Mt) was used to reinforce the neat EABC. The morphology and properties of EABC/Mt nanocomposites were characterized by scanning electron microscopy, X‐ray diffraction, Brookfield rotational viscometer, dynamic mechanical analysis, thermogravimetric analysis, automatic adhesion tester, and universal testing machine. No intercalation structure formed in the EABC/Mt nanocomposites. Mt dispersed uniformly in the EABC matrix. The inclusion of Mt increased the viscosity of the neat EABC in the initial stage of chemical reaction. Whereas, in the later curing stage, the viscosity of the neat EABC was higher than those of EABC/Mt nanocomposites. The presence of Mt slightly reduced the glass transition temperature of the neat EABC. The damping performance of the neat EABC was improved with the inclusion of 1 wt% Mt. Mt had a marginal effect on the thermal stability of the neat EABC. The incorporation of Mt significantly enhanced the mechanical properties of the neat EABC. The tensile strength and toughness of the neat EABC increased by 30% and 26%, respectively, with the inclusion of 3 wt% Mt. The existence of Mt greatly enhanced adhesion strength of the neat EABC. The lap‐shear adhesion strength and pull‐off adhesion strength of the EABC nanocomposite with 5 wt% Mt were 33% and 29% higher than those of the neat EABC. [ABSTRACT FROM AUTHOR]

Teosinte, an ancestor to modern maize, displays an excellent performance regarding resistance to stress, but its yield potential has rarely been reported. To evaluate the potential contribution of teosinte to maize improvement, two maize–teosinte backcrossed recombination inbred line (RIL) populations and their corresponding test‐cross hybrids were planted for trait assessment. In RN and ZP RIL populations, the average coefficients of variation of 31 agronomic traits were 9.14% (Range, 0.38%‒25.21%) and 6.85% (Range, 0.55%‒27.73%), respectively. The correlation coefficients of 13 common shared traits between RIL populations and test‐cross hybrid populations ranged from 0.10 to 0.60 and from 0.06 to 0.72, respectively. A total of 39 and 3 recombined inbred lines, and 29 and 47 test‐cross hybrids exhibited higher yields than their checks (RP125, Zheng58, CD189 and ZD958) with the BLUP data, respectively. Furthermore, four test‐cross hybrids including RN034/SCML1950, ZP068/Chang7‐2, ZP079/Chang7‐2 and ZP122/Chang7‐2 showed a more stable yield performance, with yield gains of +7.07%, +3.64%, +5.83% and +3.82% over checks, respectively. In conclusion, teosinte could serve as an alien germplasm for maize breeding. [ABSTRACT FROM AUTHOR]

Objective To explore high-resolution computed tomography (HRCT) characteristics of arytenoid cartilage in patients with laryngeal contact granuloma (LCG). Setting Tertiary hospitals. Study Design Individual case-control study. Methods HRCT scans were obtained before treatment from 42 patients with LCG. Similar scans were obtained from 50 patients with glottic laryngeal cancer or vocal cord leukoplakia without vocal process involvement. Results Forty-two male patients with LCG were enrolled in the study. There were 41 patients with unilateral vocal cord lesions, and 1 patient had bilateral lesions. All 50 eligible patients in the laryngeal lesion group were men. There were 39 patients with unilateral lesions, and 11 had bilateral lesions. The rate of arytenoid cartilage sclerosis in the LCG group was 79.07% (34/43) on the lesion side and 7.32% (3/41) on the healthy side. In the laryngeal lesion group, the rate of arytenoid cartilage sclerosis was 13.11% (8/61) on the lesion side and 2.56% (1/39) on the healthy side. The rate of arytenoid cartilage sclerosis on the lesion side of patients with LCG was significantly higher than on the healthy side of patients with LCG and significantly higher than both the healthy and lesion sides of patients with laryngeal lesions ( P < .001). Conclusions Arytenoid cartilage sclerosis was observed on the lesion side in most patients with LCG, and the presence of sclerosis may support the diagnosis of LCG. [ABSTRACT FROM AUTHOR]

Colorectal cancer (CRC) is the third leading causes of cancer mortality, and the early-stage detection could significantly enhance survival rates. Cancer influences the important metabolic pathways and the changes in metabolite levels had been used in many studies as the potential biomarkers. This study is aimed at screening metabolite biomarkers with CRC diagnosis potentials. The direct infusion mass spectrometry (MS) metabolomic analysis based on dried blood spot was used to distinguish CRC from polyp. The target metabolites were composed of 23 amino acids and 26 acylcarnitines. The 21 metabolites in blood were selected via multivariate analysis. A regression model was established based on parameters C16, Arg, C4/C8, C5/C3, Val, Phe/Tyr, Ala, C4/C3. Tenfold cross validation (CV) method was used to test this model and showed sensitivity of 81.18% and specificity of 83.95%. The metabolomic analysis is a practicable method for CRC detection. The use of direct MS analysis in metabolite screening could be finished in several minutes and served as a higher-throughput method to distinguish CRC and polyps. © 2017 IUBMB Life, 69(5):347-354, 2017 [ABSTRACT FROM AUTHOR]

The misuse and overuse of antibiotics result in the emergence of resistant bacteria and fungi, which make an urgent need of the new antimicrobial agents. Nowadays, antimicrobial peptides have attracted great attention of researchers. However, the low physiological stability in biological system limits the application of naturally occurring antimicrobial peptides as novel therapeutics. In the present study, we synthesized derivatives of protonectin by substituting all the amino acid residues or the cationic lysine residue with the corresponding D-amino acids. Both the D-enantiomer of protonectin ( D-prt) and D-Lys-protonectin ( D-Lys-prt) exhibited strong antimicrobial activity against bacteria and fungi. Moreover, D-prt showed strong stability against trypsin, chymotrypsin and the human serum, while D-Lys-prt only showed strong stability against trypsin. Circular dichroism analysis revealed that D-Lys-prt still kept typical α-helical structure in the membrane mimicking environment, while D-prt showed left hand α-helical structure. In addition, propidium iodide uptake assay and bacteria and fungi killing experiments indicated that all D-amino acid substitution or partially D-amino acid substitution analogs could disrupt the integrity of membrane and lead the cell death. In summary, these findings suggested that D-prt and D-Lys-prt might be promising candidate antibiotic agents for therapeutic application against resistant bacteria and fungi infection. Copyright © 2017 European Peptide Society and John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

The segmentation of coronary arteries is a vital process that helps cardiovascular radiologists detect and quantify stenosis. In this paper, we propose a fully automated coronary artery segmentation from cardiac data volume. The method is built on a statistics region growing together with a heuristic decision. First, the heart region is extracted using a multi-atlas-based approach. Second, the vessel structures are enhanced via a 3D multiscale line filter. Next, seed points are detected automatically through a threshold preprocessing and a subsequent morphological operation. Based on the set of detected seed points, a statistics-based region growing is applied. Finally, results are obtained by setting conservative parameters. A heuristic decision method is then used to obtain the desired result automatically because parameters in region growing vary in different patients, and the segmentation requires full automation. The experiments are carried out on a dataset that includes eight-patient multivendor cardiac computed tomography angiography (CTA) volume data. The DICE similarity index, mean distance, and Hausdorff distance metrics are employed to compare the proposed algorithm with two state-of-the-art methods. Experimental results indicate that the proposed algorithm is capable of performing complete, robust, and accurate extraction of coronary arteries. [ABSTRACT FROM AUTHOR]

Trimethylolpropanetriacrylate (TMPTA) was added to the polysulfide-manganese dioxide (PSF-MnO2) liquid mixtures as a crosslinker to improve their crosslinking capability. The samples were cured at room temperature for different times and the crosslinking degree was characterized by extraction and swelling tests. Mechanical properties of the cured samples including tensile, compression (stress relaxation, permanent set, and cyclic compression), and dynamic mechanical behaviors were investigated. The results indicated that the TMPTA crosslinker significantly increased the crosslinking degree and the homogeneity of the formed PSF networks. As a result, the tensile and compression stress and relaxation performances of the cured PSF rubber were dramatically improved. This result was also consistent with the results from the swelling, cyclic compression, and dynamic mechanical measurements. Interestingly, the tensile strength of the TMPTA cured samples did not show apparent change when the curing time was longer than 14 days, whereas their compression stress and relaxation performance were growing remarkably from 14 to 60 days. The improved performances were attributed to the high efficiency of thiol-acrylate Michael addition reaction for the crosslinking. It promoted the curing rate, resulting in good compression properties in a much shorter curing time.POLYM. ENG. SCI., 2011. © 2011 Society of Plastics Engineers [ABSTRACT FROM AUTHOR]

The curing process of a polysulfide (PSF) with a triacrylate crosslinker in the presence of an amine catalyst at room temperature is a rapid Michael addition. This reaction was monitored by real-time infrared spectrum (RTIR). The results of the RTIR show that the consumptions of thiol and acrylate are stoichiometric until 80% conversion, indicating the characteristics of a 'click' reaction. Dielectric analyzer (DEA) and dynamic mechanical analyzer (DMA) were employed to investigate the curing kinetics from which the activation energies of this curing reaction were obtained and shown to correlate with each other. In addition, the influences of the types and amount of amine catalyst, the different molecular weights of PSFs, and the triacrylate crosslinkers were discussed. Copyright © 2011 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]