Environmental sound classification is one of the important issues in the audio recognition field. Compared with structured sounds such as speech and music, the time-frequency structure of ...environmental sounds is more complicated. In order to learn time and frequency features from Log-Mel spectrogram more effectively, a temporal-frequency attention based convolutional neural network model (TFCNN) is proposed in this paper. Firstly, an experiment that is used as motivation in proposed method is designed to verify the effect of a specific frequency band in the spectrogram on model classification. Secondly, two new attention mechanisms, temporal attention mechanism and frequency attention mechanism, are proposed. These mechanisms can focus on key frequency bands and semantic related time frames on the spectrogram to reduce the influence of background noise and irrelevant frequency bands. Then, a feature information complementarity is formed by combining these mechanisms to more accurately capture the critical time-frequency features. In such a way, the representation ability of the network model can be greatly improved. Finally, experiments on two public data sets, UrbanSound 8 K and ESC-50, demonstrate the effectiveness of the proposed method.
Salmonella
infections in eggs with increasing morbidity and mortality exhibit worldwide prevalence. The present study intends to evaluate the efficacy of
Lactobacillus reuteri
Lb11 (
L. reuteri
Lb11, ...isolated from chicken intestinal tract) in inhibiting the growth of multi-drug resistant (MDR)
Salmonella
Enteritidis SE05 (obtained from egg content). The cell-free cell lysates (CFCL) of
L. reuteri
Lb11 obtained by the agar spot test performed well on inhibition of the MDR (Multi-Drug Resistant)
Salmonella
Enteritidis SE05, The heat-inactivated (HI) fraction of
L. reuteri
Lb11 showed no inhibition activity. By co-culturing with
L. reuteri
Lb11 in vitro
,
the growth of
S.
Enteritidis SE05 decreased along with time, while, the pH value decreased significantly. Furthermore, In order to evaluate the mechanism of action of CFCL of
L.reuteri
Lb11, the genes related to the transcription level of
Acr
AB-
Tol
C efflux pump, outer membrane protein OMPs genes and drug resistance genes have been quantified by real-time PCR, when the
S.
Enteritidis
was
SE05 exposed to the CFCL of
L. reuteri
Lb11 (1 × 10
12
CFU/mL). Almost all of the AcrAB-TolC efflux pump genes, outer membrane protein genes and antibiotic resistance genes were down-regulated. Especially, the level of
ramA
,
tetA and tetB
genes were down-regulated -20.77, -15.85 and -12.42 folds, respectively.
L. reuteri
Lb11 can effectively prevent the formation of efflux pump to inhibit the production of multidrug-resistant
Salmonella
Enteritidis in eggs.
Recently, with the construction of smart city, the research on environmental sound classification (ESC) has attracted the attention of academia and industry. The development of convolutional neural ...network (CNN) makes the accuracy of ESC reach a higher level, but the accuracy improvement brought by CNN is often accompanied by the deepening of network layers, which leads to the rapid growth of parameters and floating-point operations (FLOPs). Therefore, it is difficult to transplant CNN model to embedded devices, and the classification speed is also difficult to accept. In order to reduce the hardware requirements of running CNN and improve the speed of ESC, this paper proposes a resource adaptive convolutional neural network (RACNN). RACNN uses a novel resource adaptive convolutional (RAC) module, which can generate the same number of feature maps as conventional convolution operations more cheaply, and extract the time and frequency features of audio efficiently. The RAC block based on the RAC module is designed to build the lightweight RACNN model, and the RAC module can also be used to upgrade the existing CNN model. Experiments based on public datasets show that RACNN achieves higher performance than the state-of-the-art methods with lower computational complexity.
Abstract The irregular distribution of non-zero elements of large-scale sparse matrix leads to low data access efficiency caused by the unique architecture of the Sunway many-core processor, which ...brings great challenges to the efficient implementation of sparse matrix–vector multiplication (SpMV) computing by SW26010P many-core processor. To address this problem, a study of SpMV optimization strategies is carried out based on the SW26010P many-core processor. Firstly, we design a memorized data storage transformation strategy to transform the matrix in CSR storage format into BCSR (Block Compressed Sparse Row) storage. Secondly, the dynamic task scheduling method is introduced to the algorithm to realize the load balance between slave cores. Thirdly, the LDM memory is refined and designed, and the slave core dual cache strategy is optimized to further improve the performance. Finally, we selected a large number of representative sparse matrices from the Matrix Market for testing. The results show that the scheme has obviously speedup the processing procedure of sparse matrices with various sizes and sizes, and the master–slave speedup ratio can reach up to 38 times. The optimization method used in this paper has implications for other complex applications of the SW26010P many-core processor.
With the increasing number and types of global power loads and the development and popularization of smart grid technology, a large number of researches on load-level non-intrusive load monitoring ...technology have emerged. However, the unique power characteristics of the load make NILM face the difficult problem of low robustness of feature extraction and low accuracy of classification and identification in the recognition stage. This paper proposes a structured V-I mapping method to address the inherent limitations of traditional V-I trajectory mapping methods from a new perspective. In addition, for the verification of the V-I trajectory mapping method proposed in this paper, the complexity of load characteristics is comprehensively considered, and a lightweight convolutional neural network is designed based on AlexNet. The experimental results on the NILM dataset show that the proposed method significantly improves recognition accuracy compared to existing VI trajectory mapping methods.
This paper studies the problem of finite-time stabilization for nonlinear systems. We prove that
global finite-time stabilizability of uncertain nonlinear systems that are dominated by a ...lower-triangular system can be achieved by Hölder continuous state feedback. The proof is based on the finite-time Lyapunov stability theorem and the nonsmooth feedback design method developed recently for the control of inherently nonlinear systems that cannot be dealt with by any smooth feedback. A recursive design algorithm is developed for the construction of a Hölder continuous, global finite-time stabilizer as well as a
C
1
positive definite and proper Lyapunov function that guarantees finite-time stability.
Pseudomonas protegens
H78 produces multiple secondary metabolites, including antibiotics and iron carriers. The guanosine pentaphosphate or tetraphosphate ((p)ppGpp)-mediated stringent response is ...utilized by bacteria to survive during nutritional starvation and other stresses. RelA/SpoT homologues are responsible for the biosynthesis and degradation of the alarmone (p)ppGpp. Here, we investigated the global effect of
relA/spoT
dual deletion on the transcriptomic profiles, physiology, and metabolism of
P. protegens
H78 grown to mid- to late log phase. Transcriptomic profiling revealed that
relA/spoT
deletion globally upregulated the expression of genes involved in DNA replication, transcription, and translation; amino acid metabolism; carbohydrate and energy metabolism; ion transport and metabolism; and secretion systems. Bacterial growth was partially increased, while the cell survival rate was significantly reduced by
relA/spoT
deletion in H78. The utilization of some nutritional elements (C, P, S, and N) was downregulated due to
relA/spoT
deletion. In contrast,
relA/spoT
mutation globally inhibited the expression of secondary metabolic gene clusters (
plt, phl
,
prn
,
ofa, fit
,
pch
,
pvd
, and
has
)
.
Correspondingly, antibiotic and iron carrier biosynthesis, iron utilization, and antibiotic resistance were significantly downregulated by the
relA/spoT
mutation. This work highlights that the (p)ppGpp-mediated stringent response regulatory system plays an important role in inhibiting primary metabolism and activating secondary metabolism in
P. protegens
.
Lead (Pb) is a heavy metal environmental pollutant that can cause functional damage and anemia of immune organs. More and more evidence indicate that the toxicity of lead was related to apoptosis ...driven by oxidative stress and endoplasmic reticulum stress. This article mainly discusses the protective effect and mechanism of folic acid intervention on lead-induced spleen injury and apoptosis. In this study, Sprague-Dawley rats were randomly divided into control group, lead exposure group (0.2% lead acetate), folic acid + lead group (0.4 mg/kg folic acid and 0.2% lead acetate), and folic acid group (0.4 mg/kg folic acid). By recording and calculating the rat's initial body weight, final body weight, net weight gain, daily weight gain, and spleen index, observe the rat's weight change and spleen weight. And adopt the immunofluorescence staining method to determine the expression level of NrF2, HO-1, GRP78, CHOP protein in the spleen. The results showed that The 0.4 mg/kg folic acid diet did not significantly improve in the body weight and spleen index of lead-exposed rats (P > 0.05). While compared with the control group, the expression levels of HO-1 and CHOP protein were significantly increased in the lead exposure group (P < 0.05), and the expression levels of HO-1 and CHOP protein were significantly reduced in the folic acid intervention group (P < 0.05). In conclusion, lead exposure increased the expression levels of HO-1 and CHOP in the spleen of rats, and caused damage to the spleen. Folic acid down-regulated the expression levels of HO-1 and CHOP proteins through the two pathways of NrF2/HO-1 and GRP78/CHOP, thereby exerting a certain protective effect and alleviating the spleen caused by lead-induced oxidative stress and endoplasmic reticulum stress damage.
Display omitted
•To evaluate the changes of folic acid on the body weight ,spleen index,Nrf2 ,HO-1,GRP78 and CHOP of lead poisoned rats .•Folic acid down-regulated the expression levels of HO-1 and CHOP protein,its protective effect and mechanism were clarified.•The effective drugs were provided for the prevention and treatment of spleen oxidative damage caused by acute lead exposure.
In recent years, with the construction of intelligent cities, the importance of environmental sound classification (ESC) research has become increasingly prominent. However, due to the non-stationary ...nature of environment sound and the strong interference of ambient noise, the recognition accuracy of ESC is not high enough. Even with deep learning methods, it is difficult to fully extract features from models with a single input. Aiming to improve the recognition accuracy of ESC, this paper proposes a two-stream convolutional neural network (CNN) based on raw audio CNN (RACNN) and logmel CNN (LMCNN). In this method, a pre-emphasis module is first constructed to deal with raw audio signal. The processed audio data and logmel data are imported into RACNN and LMCNN, respectively to obtain both of time and frequency features of audio. In addition, a random-padding method is proposed to patch shorter data sequences. In such a way, the available data for experiment are greatly increased. Finally, the effectiveness of the methods has been verified based on UrbanSound8K dataset in experimental part.
Previously, we had cross-sectionally explored the characteristics of T cell receptor (TCR) repertoires from occupational medicamentosa-like dermatitis due to trichloroethylene (OMDT) patients, now we ...further analyzed the dynamic features of OMDT TCR repertoires. Peripheral blood TCR β-chain complementarity-determining region 3 (CDR3) genes were detected with the high throughput sequencing in 24 OMDT cases in their acute, chronic and recovery stages, respectively, and in 24 trichloroethylene-exposed healthy controls. The TCR repertoire diversity, TRBV/TRBD/TRBJ gene usage and combination, frequencies of CDR3 nucleotide (nt) and amino acid (aa) sequences in the cases in different stages and in the controls were analyzed. TRBV6-4 and TRBV7-9 frequencies significantly differed between the cases and controls (both P < 6.1 × 10
). TRBV6-4 combination with TRBJ2-1, TRBJ2-2, TRBJ2-3, and TRBJ2-6, and TRBV7-9 combination with TRBJ2-1 were associated with the stage by OMDT severity (all P < 0.001). Ten CDR3-nt and 7 CDR3-aa sequences in TRBV7-9-TRBJ2-1 combination and 1 CDR3-nt and 1 CDR3-aa sequences in TRBV6-4-TRBJ2-1 combination were identified as associated with the severity of OMDT (all P < 0.001). We revealed further how TCR repertoires vary with the severity in the development of OMDT, and severity-related TCRs may provide important therapeutic targets for OMDT in clinical practice.
PDF
