To solve the problems of complex lesion region morphology,blurred edges,and limited hardware resources for deploying the recognition model in pneumonia image recognition,an improved EfficientNetV2 pneumo-nia recogniti...To solve the problems of complex lesion region morphology,blurred edges,and limited hardware resources for deploying the recognition model in pneumonia image recognition,an improved EfficientNetV2 pneumo-nia recognition model based on multiscale attention is proposed.First,the number of main module stacks of the model is reduced to avoid overfitting,while the dilated convolution is introduced in the first convolutional layer to expand the receptive field of the model;second,a redesigned improved mobile inverted bottleneck convolution(IMBConv)module is proposed,in which GSConv is introduced to enhance the model’s attention to inter-channel information,and a SimAM module is introduced to reduce the number of model parameters while guaranteeing the model’s recognition performance;finally,an improved multi-scale efficient local attention(MELA)module is proposed to ensure the model’s recognition ability for pneumonia images with complex lesion regions.The experimental results show that the improved model has a computational complexity of 1.96 GFLOPs,which is reduced by 32%relative to the baseline model,and the number of model parameters is also reduced,and achieves an accuracy of 86.67%on the triple classification task of the public dataset Chest X-ray,representing an improvement of 2.74%compared to the baseline model.The recognition accuracies of ResNet50,Inception-V4,and Swin Transformer V2 on this dataset are 84.36%,85.98%,and 83.42%,respectively,and their computational complexities and model parameter counts are all higher than those of the proposed model.This indicates that the proposed model has very high feasibility for deployment in edge computing or mobile healthcare systems.In addition,the improved model achieved the highest accuracy of 90.98%on the four-classification public dataset compared to other models,indicating that the model has better recognition accuracy and generalization ability for pneumonia image recognition.展开更多
Speech Emotion Recognition(SER)has received widespread attention as a crucial way for understanding human emotional states.However,the impact of irrelevant information on speech signals and data sparsity limit the dev...Speech Emotion Recognition(SER)has received widespread attention as a crucial way for understanding human emotional states.However,the impact of irrelevant information on speech signals and data sparsity limit the development of SER system.To address these issues,this paper proposes a framework that incorporates the Attentive Mask Residual Network(AM-ResNet)and the self-supervised learning model Wav2vec 2.0 to obtain AM-ResNet features and Wav2vec 2.0 features respectively,together with a cross-attention module to interact and fuse these two features.The AM-ResNet branch mainly consists of maximum amplitude difference detection,mask residual block,and an attention mechanism.Among them,the maximum amplitude difference detection and the mask residual block act on the pre-processing and the network,respectively,to reduce the impact of silent frames,and the attention mechanism assigns different weights to unvoiced and voiced speech to reduce redundant emotional information caused by unvoiced speech.In the Wav2vec 2.0 branch,this model is introduced as a feature extractor to obtain general speech features(Wav2vec 2.0 features)through pre-training with a large amount of unlabeled speech data,which can assist the SER task and cope with data sparsity problems.In the cross-attention module,AM-ResNet features and Wav2vec 2.0 features are interacted with and fused to obtain the cross-fused features,which are used to predict the final emotion.Furthermore,multi-label learning is also used to add ambiguous emotion utterances to deal with data limitations.Finally,experimental results illustrate the usefulness and superiority of our proposed framework over existing state-of-the-art approaches.展开更多
Wearable pressure sensors capable of adhering comfortably to the skin hold great promise in sound detection.However,current intelligent speech assistants based on pressure sensors can only recognize standard languages...Wearable pressure sensors capable of adhering comfortably to the skin hold great promise in sound detection.However,current intelligent speech assistants based on pressure sensors can only recognize standard languages,which hampers effective communication for non-standard language people.Here,we prepare an ultralight Ti_(3)C_(2)T_(x)MXene/chitosan/polyvinylidene difluoride composite aerogel with a detection range of 6.25 Pa-1200 k Pa,rapid response/recovery time,and low hysteresis(13.69%).The wearable aerogel pressure sensor can detect speech information through the throat muscle vibrations without any interference,allowing for accurate recognition of six dialects(96.2%accuracy)and seven different words(96.6%accuracy)with the assistance of convolutional neural networks.This work represents a significant step forward in silent speech recognition for human–machine interaction and physiological signal monitoring.展开更多
Methyl-CpG binding protein 2(MeCP2) is a basic nuclear protein involved in the regulation of gene expression and microRNA processing.Duplication of MECP2-containing genomic segments causes MECP2 duplication syndrome,a...Methyl-CpG binding protein 2(MeCP2) is a basic nuclear protein involved in the regulation of gene expression and microRNA processing.Duplication of MECP2-containing genomic segments causes MECP2 duplication syndrome,a severe neurodevelopmental disorder characterized by intellectual disability,motor dysfunction,heightened anxiety,epilepsy,autistic phenotypes,and early death.Reversal of the abnormal phenotypes in adult mice with MECP2 duplication(MECP2-TG) by normalizing the MeCP2 levels across the whole brain has been demonstrated.However,whether different brain areas or neural circuits contribute to different aspects of the behavioral deficits is still unknown.Here,we found that MECP2-TG mice showed a significant social recognition deficit,and were prone to display aversive-like behaviors,including heightened anxiety-like behaviors and a fear generalization phenotype.In addition,reduced locomotor activity was observed in MECP2-TG mice.However,appetitive behaviors and learning and memory were comparable in MECP2-TG and wild-type mice.Functional magnetic resonance imaging illustrated that the differences between MECP2-TG and wild-type mice were mainly concentrated in brain areas regulating emotion and social behaviors.We used the CRISPR-Cas9 method to restore normal MeCP2 levels in the medial prefrontal cortex(mPFC) and bed nuclei of the stria terminalis(BST) of adult MECP2-TG mice,and found that normalization of MeCP2 levels in the mPFC but not in the BST reversed the social recognition deficit.These data indicate that the mPFC is responsible for the social recognition deficit in the transgenic mice,and provide new insight into potential therapies for MECP2 duplication syndrome.展开更多
Dimensionality reduction methods play an important role in face recognition. Principal component analysis(PCA) and two-dimensional principal component analysis(2DPCA) are two kinds of important methods in this field. ...Dimensionality reduction methods play an important role in face recognition. Principal component analysis(PCA) and two-dimensional principal component analysis(2DPCA) are two kinds of important methods in this field. Recent research seems like that 2DPCA method is superior to PCA method. To prove if this conclusion is always true, a comprehensive comparison study between PCA and 2DPCA methods was carried out. A novel concept, called column-image difference(CID), was proposed to analyze the difference between PCA and 2DPCA methods in theory. It is found that there exist some restrictive conditions when2 DPCA outperforms PCA. After theoretical analysis, the experiments were conducted on four famous face image databases. The experiment results confirm the validity of theoretical claim.展开更多
A benzothiazole-based compound 1, C28H24N4O2S, has been synthesized and characterized by single-crystal X-ray diffraction. It crystallizes in monoclinic, space group P21/c with a = 9.6309（14）, b = 15.230（2）, c = 1...A benzothiazole-based compound 1, C28H24N4O2S, has been synthesized and characterized by single-crystal X-ray diffraction. It crystallizes in monoclinic, space group P21/c with a = 9.6309（14）, b = 15.230（2）, c = 17.197（3）A, β = 105.222（2）°, V = 2433.9（6） A^3, Z = 4, F（000） = 1008, Dc = 1.311 Mg/m^3, Mr = 480.57, μ = 0.166 mm^-1, the final R = 0.0509 and wR = 0.1481 for 6643 observed reflections with I 〉 2σ（I）. The crystal structure of compound 1 is stabilized by C–H…O, N–H…N, N–H…O, O–H…N and C–H…N hydrogen bonds. The spectroscopic studies of the title compound toward various metal ions were also investigated in 25%（V/V） ethanol aqueous solution, and the result showed that it can selectively recognize Cu^2＋ with fluorescence quenching.展开更多
A new naphthol-based compound 1, C22 H22 N2 O2, has been designed and synthesized. The structure of the title compound 1 was confirmed by IR, 1 H NMR, 13 C NMR, H RMS, and X-ray single-crystal diffraction. The crystal...A new naphthol-based compound 1, C22 H22 N2 O2, has been designed and synthesized. The structure of the title compound 1 was confirmed by IR, 1 H NMR, 13 C NMR, H RMS, and X-ray single-crystal diffraction. The crystal belongs to the monoclinic system, space group P21/c, with a = 12.888（9）, b = 15.543（10）, c = 9.119（6） ？, β = 94.05（3）°, V = 1822（2） ？3, Z = 4, Dc = 1.263 g/cm3, Mr = 346.41, μ = 0.081 mm-1, F（000） = 736.0, the final R = 0.0452 and wR = 0.1142 for 3404 observed reflections with（I 〉 2σ（I））. The crystal structure of 1 is stabilized by O–H···N, N–H···O, C–H···O hydrogen bonds and π-π interactions. The spectroscopic studies of 1 toward various metal ions were also investigated in 25%（V/V） ethanol aqueous solution, and the result showed that it can selectively recognize Zn2＋ with fluorescence enhancement.展开更多
Video-based action recognition is becoming a vital tool in clinical research and neuroscientific study for disorder detection and prediction.However,action recognition currently used in non-human primate(NHP)research ...Video-based action recognition is becoming a vital tool in clinical research and neuroscientific study for disorder detection and prediction.However,action recognition currently used in non-human primate(NHP)research relies heavily on intense manual labor and lacks standardized assessment.In this work,we established two standard benchmark datasets of NHPs in the laboratory:Monkeyin Lab(Mi L),which includes 13 categories of actions and postures,and MiL2D,which includes sequences of two-dimensional(2D)skeleton features.Furthermore,based on recent methodological advances in deep learning and skeleton visualization,we introduced the Monkey Monitor Kit(Mon Kit)toolbox for automatic action recognition,posture estimation,and identification of fine motor activity in monkeys.Using the datasets and Mon Kit,we evaluated the daily behaviors of wild-type cynomolgus monkeys within their home cages and experimental environments and compared these observations with the behaviors exhibited by cynomolgus monkeys possessing mutations in the MECP2 gene as a disease model of Rett syndrome(RTT).Mon Kit was used to assess motor function,stereotyped behaviors,and depressive phenotypes,with the outcomes compared with human manual detection.Mon Kit established consistent criteria for identifying behavior in NHPs with high accuracy and efficiency,thus providing a novel and comprehensive tool for assessing phenotypic behavior in monkeys.展开更多
The identification of intercepted radio fuze modulation types is a prerequisite for decision-making in interference systems.However,the electromagnetic environment of modern battlefields is complex,and the signal-to-n...The identification of intercepted radio fuze modulation types is a prerequisite for decision-making in interference systems.However,the electromagnetic environment of modern battlefields is complex,and the signal-to-noise ratio(SNR)of such environments is usually low,which makes it difficult to implement accurate recognition of radio fuzes.To solve the above problem,a radio fuze automatic modulation recognition(AMR)method for low-SNR environments is proposed.First,an adaptive denoising algorithm based on data rearrangement and the two-dimensional(2D)fast Fourier transform(FFT)(DR2D)is used to reduce the noise of the intercepted radio fuze intermediate frequency(IF)signal.Then,the textural features of the denoised IF signal rearranged data matrix are extracted from the statistical indicator vectors of gray-level cooccurrence matrices(GLCMs),and support vector machines(SVMs)are used for classification.The DR2D-based adaptive denoising algorithm achieves an average correlation coefficient of more than 0.76 for ten fuze types under SNRs of-10 d B and above,which is higher than that of other typical algorithms.The trained SVM classification model achieves an average recognition accuracy of more than 96%on seven modulation types and recognition accuracies of more than 94%on each modulation type under SNRs of-12 d B and above,which represents a good AMR performance of radio fuzes under low SNRs.展开更多
Fluorescence detecting both organic and inorganic analytes has aroused tremendous scientific interests, because fluorescence techniques have high sensitivity and are easy to operate. A new threedimensional(3D) MOF {[(...Fluorescence detecting both organic and inorganic analytes has aroused tremendous scientific interests, because fluorescence techniques have high sensitivity and are easy to operate. A new threedimensional(3D) MOF {[(CH_(3))_(2)NH_(2)][Zn_(3)(bbip)(BTDI)1.5(OH)]·DMF·MeOH·3H_(2)O}n(JXUST-13, bbip = 2,6-bis(benzimidazol-1-yl)pyridine and H_(4)BTDI = 5,5-(benzo[c][1,2,5]thiadiazole-4,7-diyl)diisophthalic acid)with new 4,4,8-connceted topology has been successfully synthesized and structurally characterized. Importantly, JXUST-13 could recognize H_(2)PO_(4)-and acetylacetone(Acac) by obvious fluorescence blue shift and slight enhancement with the detection limits of 2.70 μmol/L and 0.21 mmol/L, respectively. In addition, JXUST-13 exhibits relatively good thermal stability, chemical stabilities as well as reusability, and the analytes could be distinguished by naked eye and fluorescence test paper. Remarkably, JXUST-13 is the first dual-responsive MOF sensor based on fluorescence blue shift for the detection of H_(2)PO_(4)-and Acac with good selectivity in a handy, economic, and environmentally friendly manner.展开更多
Wetland waterbirds serve as key ecological indicators for assessing habitat quality and biodiversity.Accurate identification of waterbird species is a cornerstone of long-term ecological monitoring.The resulting data ...Wetland waterbirds serve as key ecological indicators for assessing habitat quality and biodiversity.Accurate identification of waterbird species is a cornerstone of long-term ecological monitoring.The resulting data are critical for assessing wetland ecosystem health and biodiversity.However,prevailing recognition approaches often prioritize detection accuracy at the expense of computational efficiency.They are also hindered by complex background heterogeneity and interspecies visual similarity.These limitations hinder the scalability and practical deployment of such methods for on-site ecological monitoring within wetland ecosystems.To address these challenges,this study proposes an optimized end-to-end framework,ShuffleNetV2-iRMB-ShapeIoU-YOLO(SISYOLO),designed for robust recognition of wetland waterbirds in complex environments.Specifically,the proposed framework integrates ShuffleNetV2 with inverted Residual Mobile Blocks(iRMB) to improve computational efficiency while maintaining robust feature representation.This design further enables deployment on resource-constrained mobile and embedded platforms.Additionally,ShapeIoU,a refined bounding box similarity metric,is introduced to jointly optimize overlap and shape consistency,effectively mitigating misclassification among visually similar species.Experimental results on the IC-Beijing dataset show that SIS-YOLO achieves 91.1% precision and 79.1% mAP@0.5:0.95 with only 2.9 million parameters.Compared with the lightweight baseline YOLOv8n,it improves precision by 2% and mAP@0.5:0.95 by 1.2%,while requiring fewer parameters and offering higher computational efficiency.展开更多
Reliable human action recognition(HAR)in video sequences is critical for a wide range of applications,such as security surveillance,healthcare monitoring,and human-computer interaction.Several automated systems have b...Reliable human action recognition(HAR)in video sequences is critical for a wide range of applications,such as security surveillance,healthcare monitoring,and human-computer interaction.Several automated systems have been designed for this purpose;however,existing methods often struggle to effectively integrate spatial and temporal information from input samples such as 2-stream networks or 3D convolutional neural networks(CNNs),which limits their accuracy in discriminating numerous human actions.Therefore,this study introduces a novel deeplearning framework called theARNet,designed for robustHAR.ARNet consists of two mainmodules,namely,a refined InceptionResNet-V2-based CNN and a Bi-LSTM(Long Short-Term Memory)network.The refined InceptionResNet-V2 employs a parametric rectified linear unit(PReLU)activation strategy within convolutional layers to enhance spatial feature extraction fromindividual video frames.The inclusion of the PReLUmethod improves the spatial informationcapturing ability of the approach as it uses learnable parameters to adaptively control the slope of the negative part of the activation function,allowing richer gradient flow during backpropagation and resulting in robust information capturing and stable model training.These spatial features holding essential pixel characteristics are then processed by the Bi-LSTMmodule for temporal analysis,which assists the ARNet in understanding the dynamic behavior of actions over time.The ARNet integrates three additional dense layers after the Bi-LSTM module to ensure a comprehensive computation of both spatial and temporal patterns and further boost the feature representation.The experimental validation of the model is conducted on 3 benchmark datasets named HMDB51,KTH,and UCF Sports and reports accuracies of 93.82%,99%,and 99.16%,respectively.The Precision results of HMDB51,KTH,and UCF Sports datasets are 97.41%,99.54%,and 99.01%;the Recall values are 98.87%,98.60%,99.08%,and the F1-Score is 98.13%,99.07%,99.04%,respectively.These results highlight the robustness of the ARNet approach and its potential as a versatile tool for accurate HAR across various real-world applications.展开更多
Aryl diketo acid derivatives are one of the most promising HIV-1 integrase（IN） inhibitors. With a view to substitute the critical diketo acid pharmacophore with the diketo benzimidazole unit, the coupling reaction o...Aryl diketo acid derivatives are one of the most promising HIV-1 integrase（IN） inhibitors. With a view to substitute the critical diketo acid pharmacophore with the diketo benzimidazole unit, the coupling reaction of compound 4 with o-phenylenediamine was carried out. However, the reaction product, compound 5, was confirmed to be 3-{ [ 3- （phenylsulfonamido） benzoyl] methylidene t -3,4-dihydroquinoxaline-2 （1H） -one rather than the 2-benzimidazole derivative by using X-ray diffraction. Owing to its low solubility in water, the evaluation of the anti-HIV IN activity of the synthesized compound 5 could not be carried out. Consequently, the ion-binding properties of compound 5 in the absence of HIV-1 IN were investigated with UV-Vis spectroscopy in organic solvents. The results show that such a compound can selectively recognize Cu^2＋.展开更多
Pattern recognition method is used for the investigation of stability,region of filled Ti_2Ni phases in multi-dimensional bond-parameter space.The filling of C,N and O atoms into T_6 octahedra consisting of atoms of e...Pattern recognition method is used for the investigation of stability,region of filled Ti_2Ni phases in multi-dimensional bond-parameter space.The filling of C,N and O atoms into T_6 octahedra consisting of atoms of earhy-transition elements makes the expansion of the stability region of Ti_2Ni phase,and the relative stability of AI_2Cu and MoSi_2 type com- pounds decreases after the introduction of non-metallic elements such as C,N and O.展开更多
In this study,unsupervised and supervised pattern recognition were implemented in combination to achieve real-time health monitoring.Unsupervised recognition(k-means++)was used to label the spectral characteristics of...In this study,unsupervised and supervised pattern recognition were implemented in combination to achieve real-time health monitoring.Unsupervised recognition(k-means++)was used to label the spectral characteristics of acoustic emission(AE)signals after completing the tensile tests at ambient temperature.Using in-plane tensile at 800 and 1000°C as implementing examples,supervised recognition(K-nearest neighbor(KNN))was used to identify damage mode in real time.According to the damage identification results,four main tensile damage modes of 2D C/SiC composites were identified:matrix cracking(122.6–201 kHz),interfacial debonding(201–294.4 kHz),interfacial sliding(20.6–122.6 kHz)and fiber breaking(294.4–1000 kHz).Additionally,the damage evolution mechanisms for the 2D C/SiC composites were analyzed based on the characteristics of AE energy accumulation curve during the in-plane tensile loading at ambient and elevated temperature with oxidation.Meanwhile,the energy of various damage modes was accurately calculated by harmonic wavelet packet and the damage degree of modes could be analyzed.The identification results show that compared with previous studies,using the AE analysis method,the method has higher sensitivity and accuracy.展开更多
The main aim for a 2D spiral recognition algorithm is to learn to discriminate between data distributed on two distinct strands in the x-y plane.This problem is of critical importance since it incorporates temporal ch...The main aim for a 2D spiral recognition algorithm is to learn to discriminate between data distributed on two distinct strands in the x-y plane.This problem is of critical importance since it incorporates temporal characteristics often found in real-time applications.Previous work with this benchmark has witnessed poor results with statistical methods such as discriminant analysis and tedious procedures for better results with neural networks.This paper presents a max-density covering learning algorithm based on constructive neural networks which is efficient in terms of the recognition rate and the speed of recognition.The results show that it is possible to solve the spiral problem instantaneously(up to 100% correct classification on the test set).展开更多
Speech emotion recognition is essential for frictionless human-machine interaction,where machines respond to human instructions with context-aware actions.The properties of individuals’voices vary with culture,langua...Speech emotion recognition is essential for frictionless human-machine interaction,where machines respond to human instructions with context-aware actions.The properties of individuals’voices vary with culture,language,gender,and personality.These variations in speaker-specific properties may hamper the performance of standard representations in downstream tasks such as speech emotion recognition(SER).This study demonstrates the significance of speaker-specific speech characteristics and how considering them can be leveraged to improve the performance of SER models.In the proposed approach,two wav2vec-based modules(a speaker-identification network and an emotion classification network)are trained with the Arcface loss.The speaker-identification network has a single attention block to encode an input audio waveform into a speaker-specific representation.The emotion classification network uses a wav2vec 2.0-backbone as well as four attention blocks to encode the same input audio waveform into an emotion representation.These two representations are then fused into a single vector representation containing emotion and speaker-specific information.Experimental results showed that the use of speaker-specific characteristics improves SER performance.Additionally,combining these with an angular marginal loss such as the Arcface loss improves intra-class compactness while increasing inter-class separability,as demonstrated by the plots of t-distributed stochastic neighbor embeddings(t-SNE).The proposed approach outperforms previous methods using similar training strategies,with a weighted accuracy(WA)of 72.14%and unweighted accuracy(UA)of 72.97%on the Interactive Emotional Dynamic Motion Capture(IEMOCAP)dataset.This demonstrates its effectiveness and potential to enhance human-machine interaction through more accurate emotion recognition in speech.展开更多
Objective: To evaluate the potential adjuvant effect of Agrocybe aegerita lectin(AAL), which was isolated from mushroom, against a virulent H_9N_2 strain in vivo and in vitro. Methods: In trial 1, 50 BALB/c male mice(...Objective: To evaluate the potential adjuvant effect of Agrocybe aegerita lectin(AAL), which was isolated from mushroom, against a virulent H_9N_2 strain in vivo and in vitro. Methods: In trial 1, 50 BALB/c male mice(8 weeks old) were divided into five groups(n=10 each group) which received a subcutaneous injection of inactivated H_9N_2(control), inactivated H_9N_2+0.2%(w/w) alum, inactivated H_9N_2+0.5 mg recombinant AAL/kg body weight(BW), inactivated H_9N_2+1.0 mg AAL/kg BW, and inactivated H_9N_2+2.5 mg AAL/kg BW, respectively, four times at 7-d intervals. In trial 2, 30 BALB/c male mice(8 weeks old) were divided into three groups(n=10 each group) which received a subcutaneous injection of inactivated H_9N_2(control), inactivated H_9N_2+2.5 mg recombinant wild-type AAL(AAL-wt)/kg BW, and inactivated H_9N_2+2.5 mg carbohydrate recognition domain(CRD) mutant AAL(AAL-mut R63H)/kg BW, respectively, four times at 7-d intervals. Seven days after the final immunization, serum samples were collected from each group for analysis. Hemagglutination assay, immunogold electron microscope, lectin blotting, and coimmunoprecipitation were used to study the interaction between AAL and H_9N_2 in vitro. Results: Ig G, Ig G1, and Ig G2 a antibody levels were significantly increased in the sera of mice co-immunized with inactivated H_9N_2 and AAL when compared to mice immunized with inactivated H_9N_2 alone. No significant increase of the Ig G antibody level was detected in the sera of the mice co-immunized with inactivated H_9N_2 and AAL-mut R63 H. Moreover, AAL-wt, but not mutant AAL-mut R63 H, adhered to the surface of H_9N_2 virus. The interaction between AAL and the H_9N_2 virus was further demonstrated to be associated with the CRD of AAL binding to the surface glycosylated proteins, hemagglutinin and neuraminidase. Conclusions: Our findings indicated that AAL could be a safe and effective adjuvant capable of boosting humoral immunity against H_9N_2 viruses in mice through its interaction with the viral surface glycosylated proteins, hemagglutinin and neuraminidase.展开更多
As a new dimension reduction method, the two-dimensional principal component (2DPCA) can be well applied in face recognition, but it is susceptible to outliers. Therefore, this paper proposes a new 2DPCA algorithm bas...As a new dimension reduction method, the two-dimensional principal component (2DPCA) can be well applied in face recognition, but it is susceptible to outliers. Therefore, this paper proposes a new 2DPCA algorithm based on angel-2DPCA. To reduce the reconstruction error and maximize the variance simultaneously, we choose F norm as the measure and propose the Fp-2DPCA algorithm. Considering that the image has two dimensions, we offer the Fp-2DPCA algorithm based on bilateral. Experiments show that, compared with other algorithms, the Fp-2DPCA algorithm has a better dimensionality reduction effect and better robustness to outliers.展开更多
Activity recognition of indoor occupants using indirect sensing with less privacy violation is one of the hot research topics. This paper proposes a CO<sub>2</sub> sensor-based indoor occupant activity mon...Activity recognition of indoor occupants using indirect sensing with less privacy violation is one of the hot research topics. This paper proposes a CO<sub>2</sub> sensor-based indoor occupant activity monitoring system. Using the IoT sensor node that contains CO<sub>2</sub> sensors, the measured CO<sub>2</sub> concentrations in three locations (laboratory, office, and bedroom) were stored in a cloud server for up to 35 days starting July 1, 2023. The CO<sub>2</sub> measurements stored at 30-second intervals were statistically processed to produce a heat-mapped display of the hourly average or maximum CO<sub>2</sub> concentration. From the heatmap visualizations of CO<sub>2</sub> concentration, the proposed system estimated meeting, heating water using a portable stove, and sleep for the occupants’ activity recognition.展开更多
基金supported by the Scientific Research Fund of Hunan Provincial Education Department,China(Grant Nos.21C0439,22A0408).
文摘To solve the problems of complex lesion region morphology,blurred edges,and limited hardware resources for deploying the recognition model in pneumonia image recognition,an improved EfficientNetV2 pneumo-nia recognition model based on multiscale attention is proposed.First,the number of main module stacks of the model is reduced to avoid overfitting,while the dilated convolution is introduced in the first convolutional layer to expand the receptive field of the model;second,a redesigned improved mobile inverted bottleneck convolution(IMBConv)module is proposed,in which GSConv is introduced to enhance the model’s attention to inter-channel information,and a SimAM module is introduced to reduce the number of model parameters while guaranteeing the model’s recognition performance;finally,an improved multi-scale efficient local attention(MELA)module is proposed to ensure the model’s recognition ability for pneumonia images with complex lesion regions.The experimental results show that the improved model has a computational complexity of 1.96 GFLOPs,which is reduced by 32%relative to the baseline model,and the number of model parameters is also reduced,and achieves an accuracy of 86.67%on the triple classification task of the public dataset Chest X-ray,representing an improvement of 2.74%compared to the baseline model.The recognition accuracies of ResNet50,Inception-V4,and Swin Transformer V2 on this dataset are 84.36%,85.98%,and 83.42%,respectively,and their computational complexities and model parameter counts are all higher than those of the proposed model.This indicates that the proposed model has very high feasibility for deployment in edge computing or mobile healthcare systems.In addition,the improved model achieved the highest accuracy of 90.98%on the four-classification public dataset compared to other models,indicating that the model has better recognition accuracy and generalization ability for pneumonia image recognition.
基金supported by Chongqing University of Posts and Telecommunications Ph.D.Innovative Talents Project(Grant No.BYJS202106)Chongqing Postgraduate Research Innovation Project(Grant No.CYB21203).
文摘Speech Emotion Recognition(SER)has received widespread attention as a crucial way for understanding human emotional states.However,the impact of irrelevant information on speech signals and data sparsity limit the development of SER system.To address these issues,this paper proposes a framework that incorporates the Attentive Mask Residual Network(AM-ResNet)and the self-supervised learning model Wav2vec 2.0 to obtain AM-ResNet features and Wav2vec 2.0 features respectively,together with a cross-attention module to interact and fuse these two features.The AM-ResNet branch mainly consists of maximum amplitude difference detection,mask residual block,and an attention mechanism.Among them,the maximum amplitude difference detection and the mask residual block act on the pre-processing and the network,respectively,to reduce the impact of silent frames,and the attention mechanism assigns different weights to unvoiced and voiced speech to reduce redundant emotional information caused by unvoiced speech.In the Wav2vec 2.0 branch,this model is introduced as a feature extractor to obtain general speech features(Wav2vec 2.0 features)through pre-training with a large amount of unlabeled speech data,which can assist the SER task and cope with data sparsity problems.In the cross-attention module,AM-ResNet features and Wav2vec 2.0 features are interacted with and fused to obtain the cross-fused features,which are used to predict the final emotion.Furthermore,multi-label learning is also used to add ambiguous emotion utterances to deal with data limitations.Finally,experimental results illustrate the usefulness and superiority of our proposed framework over existing state-of-the-art approaches.
基金supported by the National Nature Science Foundation of China(No.62122030,62333008,62371205,52103208)National Key Research and Development Program of China(No.2021YFB3201300)+1 种基金Application and Basic Research of Jilin Province(20130102010 JC)Fundamental Research Funds for the Central Universities,Jilin Provincial Science and Technology Development Program(20230101072JC)。
文摘Wearable pressure sensors capable of adhering comfortably to the skin hold great promise in sound detection.However,current intelligent speech assistants based on pressure sensors can only recognize standard languages,which hampers effective communication for non-standard language people.Here,we prepare an ultralight Ti_(3)C_(2)T_(x)MXene/chitosan/polyvinylidene difluoride composite aerogel with a detection range of 6.25 Pa-1200 k Pa,rapid response/recovery time,and low hysteresis(13.69%).The wearable aerogel pressure sensor can detect speech information through the throat muscle vibrations without any interference,allowing for accurate recognition of six dialects(96.2%accuracy)and seven different words(96.6%accuracy)with the assistance of convolutional neural networks.This work represents a significant step forward in silent speech recognition for human–machine interaction and physiological signal monitoring.
基金supported by National Natural Science Foundation of China grants (31625013 and 91732302)a Shanghai Brain-Intelligence Project of the Science and Technology Commission of Shanghai Municipality(16JC1420501)+4 种基金the Strategic Priority Research Program of the Chinese Academy of Sciences (XDBS01060200)Program of Shanghai Academic Research Leaderthe Open Large Infrastructure Research of Chinese Academy of Sciencesthe Shanghai Municipal Science and Technology Major Project (2018SHZDZX05)National Natural Science Foundation of China (81801354)。
文摘Methyl-CpG binding protein 2(MeCP2) is a basic nuclear protein involved in the regulation of gene expression and microRNA processing.Duplication of MECP2-containing genomic segments causes MECP2 duplication syndrome,a severe neurodevelopmental disorder characterized by intellectual disability,motor dysfunction,heightened anxiety,epilepsy,autistic phenotypes,and early death.Reversal of the abnormal phenotypes in adult mice with MECP2 duplication(MECP2-TG) by normalizing the MeCP2 levels across the whole brain has been demonstrated.However,whether different brain areas or neural circuits contribute to different aspects of the behavioral deficits is still unknown.Here,we found that MECP2-TG mice showed a significant social recognition deficit,and were prone to display aversive-like behaviors,including heightened anxiety-like behaviors and a fear generalization phenotype.In addition,reduced locomotor activity was observed in MECP2-TG mice.However,appetitive behaviors and learning and memory were comparable in MECP2-TG and wild-type mice.Functional magnetic resonance imaging illustrated that the differences between MECP2-TG and wild-type mice were mainly concentrated in brain areas regulating emotion and social behaviors.We used the CRISPR-Cas9 method to restore normal MeCP2 levels in the medial prefrontal cortex(mPFC) and bed nuclei of the stria terminalis(BST) of adult MECP2-TG mice,and found that normalization of MeCP2 levels in the mPFC but not in the BST reversed the social recognition deficit.These data indicate that the mPFC is responsible for the social recognition deficit in the transgenic mice,and provide new insight into potential therapies for MECP2 duplication syndrome.
基金Projects(50275150,61173052)supported by the National Natural Science Foundation of China
文摘Dimensionality reduction methods play an important role in face recognition. Principal component analysis(PCA) and two-dimensional principal component analysis(2DPCA) are two kinds of important methods in this field. Recent research seems like that 2DPCA method is superior to PCA method. To prove if this conclusion is always true, a comprehensive comparison study between PCA and 2DPCA methods was carried out. A novel concept, called column-image difference(CID), was proposed to analyze the difference between PCA and 2DPCA methods in theory. It is found that there exist some restrictive conditions when2 DPCA outperforms PCA. After theoretical analysis, the experiments were conducted on four famous face image databases. The experiment results confirm the validity of theoretical claim.
基金financially supported by the National Natural Science Foundation of China(21603069)College Students’ Science and Technology Innovation Project of Hubei Polytechnic University(No.14cx16)Young College Teachers’ Entering into Enterprises Program of Hubei Provincial Department of Education(No.XD2014677)
文摘A benzothiazole-based compound 1, C28H24N4O2S, has been synthesized and characterized by single-crystal X-ray diffraction. It crystallizes in monoclinic, space group P21/c with a = 9.6309（14）, b = 15.230（2）, c = 17.197（3）A, β = 105.222（2）°, V = 2433.9（6） A^3, Z = 4, F（000） = 1008, Dc = 1.311 Mg/m^3, Mr = 480.57, μ = 0.166 mm^-1, the final R = 0.0509 and wR = 0.1481 for 6643 observed reflections with I 〉 2σ（I）. The crystal structure of compound 1 is stabilized by C–H…O, N–H…N, N–H…O, O–H…N and C–H…N hydrogen bonds. The spectroscopic studies of the title compound toward various metal ions were also investigated in 25%（V/V） ethanol aqueous solution, and the result showed that it can selectively recognize Cu^2＋ with fluorescence quenching.
基金supported by the National Natural Science Foundation of China(No.21271035)the Natural Science Foundation of Anhui Province(No.KJ2016A512)+1 种基金Key projects of Anhui Province University Outstanding Youth Talent Support Program(No.gxyqZD2016372)the Natural Science Foundation of Chizhou University(No.2017ZRZ002)
文摘A new naphthol-based compound 1, C22 H22 N2 O2, has been designed and synthesized. The structure of the title compound 1 was confirmed by IR, 1 H NMR, 13 C NMR, H RMS, and X-ray single-crystal diffraction. The crystal belongs to the monoclinic system, space group P21/c, with a = 12.888（9）, b = 15.543（10）, c = 9.119（6） ？, β = 94.05（3）°, V = 1822（2） ？3, Z = 4, Dc = 1.263 g/cm3, Mr = 346.41, μ = 0.081 mm-1, F（000） = 736.0, the final R = 0.0452 and wR = 0.1142 for 3404 observed reflections with（I 〉 2σ（I））. The crystal structure of 1 is stabilized by O–H···N, N–H···O, C–H···O hydrogen bonds and π-π interactions. The spectroscopic studies of 1 toward various metal ions were also investigated in 25%（V/V） ethanol aqueous solution, and the result showed that it can selectively recognize Zn2＋ with fluorescence enhancement.
基金supported by the National Key R&D Program of China (2021ZD0202805,2019YFA0709504,2021ZD0200900)National Defense Science and Technology Innovation Special Zone Spark Project (20-163-00-TS-009-152-01)+4 种基金National Natural Science Foundation of China (31900719,U20A20227,82125008)Innovative Research Team of High-level Local Universities in Shanghai,Science and Technology Committee Rising-Star Program (19QA1401400)111 Project (B18015)Shanghai Municipal Science and Technology Major Project (2018SHZDZX01)Shanghai Center for Brain Science and Brain-Inspired Technology。
文摘Video-based action recognition is becoming a vital tool in clinical research and neuroscientific study for disorder detection and prediction.However,action recognition currently used in non-human primate(NHP)research relies heavily on intense manual labor and lacks standardized assessment.In this work,we established two standard benchmark datasets of NHPs in the laboratory:Monkeyin Lab(Mi L),which includes 13 categories of actions and postures,and MiL2D,which includes sequences of two-dimensional(2D)skeleton features.Furthermore,based on recent methodological advances in deep learning and skeleton visualization,we introduced the Monkey Monitor Kit(Mon Kit)toolbox for automatic action recognition,posture estimation,and identification of fine motor activity in monkeys.Using the datasets and Mon Kit,we evaluated the daily behaviors of wild-type cynomolgus monkeys within their home cages and experimental environments and compared these observations with the behaviors exhibited by cynomolgus monkeys possessing mutations in the MECP2 gene as a disease model of Rett syndrome(RTT).Mon Kit was used to assess motor function,stereotyped behaviors,and depressive phenotypes,with the outcomes compared with human manual detection.Mon Kit established consistent criteria for identifying behavior in NHPs with high accuracy and efficiency,thus providing a novel and comprehensive tool for assessing phenotypic behavior in monkeys.
基金National Natural Science Foundation of China under Grant No.61973037China Postdoctoral Science Foundation 2022M720419 to provide fund for conducting experiments。
文摘The identification of intercepted radio fuze modulation types is a prerequisite for decision-making in interference systems.However,the electromagnetic environment of modern battlefields is complex,and the signal-to-noise ratio(SNR)of such environments is usually low,which makes it difficult to implement accurate recognition of radio fuzes.To solve the above problem,a radio fuze automatic modulation recognition(AMR)method for low-SNR environments is proposed.First,an adaptive denoising algorithm based on data rearrangement and the two-dimensional(2D)fast Fourier transform(FFT)(DR2D)is used to reduce the noise of the intercepted radio fuze intermediate frequency(IF)signal.Then,the textural features of the denoised IF signal rearranged data matrix are extracted from the statistical indicator vectors of gray-level cooccurrence matrices(GLCMs),and support vector machines(SVMs)are used for classification.The DR2D-based adaptive denoising algorithm achieves an average correlation coefficient of more than 0.76 for ten fuze types under SNRs of-10 d B and above,which is higher than that of other typical algorithms.The trained SVM classification model achieves an average recognition accuracy of more than 96%on seven modulation types and recognition accuracies of more than 94%on each modulation type under SNRs of-12 d B and above,which represents a good AMR performance of radio fuzes under low SNRs.
基金supported by the National Natural Science Foundation of China (Nos. 22061019, 21861018, 22161019 and 12174172)the NSF of Jiangxi Province (No. 20202ACBL213001)+4 种基金Jiangxi Provincial Key Laboratory of Functional Molecular Materials Chemistry(No. 20212BCD42018)Fujian Key Laboratory of Functional Marine Sensing Materials,Minjiang University (No. MJUKF-FMSM202010)the Youth Jinggang Scholars Program in Jiangxi Province (No.QNJG2019053)the Two Thousand Program in Jiangxi Province (No.jxsq2019201068)the Special Foundation for Postgraduate Innovation in Jiangxi Province (No. YC_(2)020-B155)。
文摘Fluorescence detecting both organic and inorganic analytes has aroused tremendous scientific interests, because fluorescence techniques have high sensitivity and are easy to operate. A new threedimensional(3D) MOF {[(CH_(3))_(2)NH_(2)][Zn_(3)(bbip)(BTDI)1.5(OH)]·DMF·MeOH·3H_(2)O}n(JXUST-13, bbip = 2,6-bis(benzimidazol-1-yl)pyridine and H_(4)BTDI = 5,5-(benzo[c][1,2,5]thiadiazole-4,7-diyl)diisophthalic acid)with new 4,4,8-connceted topology has been successfully synthesized and structurally characterized. Importantly, JXUST-13 could recognize H_(2)PO_(4)-and acetylacetone(Acac) by obvious fluorescence blue shift and slight enhancement with the detection limits of 2.70 μmol/L and 0.21 mmol/L, respectively. In addition, JXUST-13 exhibits relatively good thermal stability, chemical stabilities as well as reusability, and the analytes could be distinguished by naked eye and fluorescence test paper. Remarkably, JXUST-13 is the first dual-responsive MOF sensor based on fluorescence blue shift for the detection of H_(2)PO_(4)-and Acac with good selectivity in a handy, economic, and environmentally friendly manner.
基金supported by National Natural Science Foundation of China (32401569,32371874)Beijing Natural Science Foundation(6244053)。
文摘Wetland waterbirds serve as key ecological indicators for assessing habitat quality and biodiversity.Accurate identification of waterbird species is a cornerstone of long-term ecological monitoring.The resulting data are critical for assessing wetland ecosystem health and biodiversity.However,prevailing recognition approaches often prioritize detection accuracy at the expense of computational efficiency.They are also hindered by complex background heterogeneity and interspecies visual similarity.These limitations hinder the scalability and practical deployment of such methods for on-site ecological monitoring within wetland ecosystems.To address these challenges,this study proposes an optimized end-to-end framework,ShuffleNetV2-iRMB-ShapeIoU-YOLO(SISYOLO),designed for robust recognition of wetland waterbirds in complex environments.Specifically,the proposed framework integrates ShuffleNetV2 with inverted Residual Mobile Blocks(iRMB) to improve computational efficiency while maintaining robust feature representation.This design further enables deployment on resource-constrained mobile and embedded platforms.Additionally,ShapeIoU,a refined bounding box similarity metric,is introduced to jointly optimize overlap and shape consistency,effectively mitigating misclassification among visually similar species.Experimental results on the IC-Beijing dataset show that SIS-YOLO achieves 91.1% precision and 79.1% mAP@0.5:0.95 with only 2.9 million parameters.Compared with the lightweight baseline YOLOv8n,it improves precision by 2% and mAP@0.5:0.95 by 1.2%,while requiring fewer parameters and offering higher computational efficiency.
基金supported and funded by theDeanship of Scientific Research at ImamMohammad Ibn Saud Islamic University(IMSIU)(grant number IMSIU-DDRSP2504).
文摘Reliable human action recognition(HAR)in video sequences is critical for a wide range of applications,such as security surveillance,healthcare monitoring,and human-computer interaction.Several automated systems have been designed for this purpose;however,existing methods often struggle to effectively integrate spatial and temporal information from input samples such as 2-stream networks or 3D convolutional neural networks(CNNs),which limits their accuracy in discriminating numerous human actions.Therefore,this study introduces a novel deeplearning framework called theARNet,designed for robustHAR.ARNet consists of two mainmodules,namely,a refined InceptionResNet-V2-based CNN and a Bi-LSTM(Long Short-Term Memory)network.The refined InceptionResNet-V2 employs a parametric rectified linear unit(PReLU)activation strategy within convolutional layers to enhance spatial feature extraction fromindividual video frames.The inclusion of the PReLUmethod improves the spatial informationcapturing ability of the approach as it uses learnable parameters to adaptively control the slope of the negative part of the activation function,allowing richer gradient flow during backpropagation and resulting in robust information capturing and stable model training.These spatial features holding essential pixel characteristics are then processed by the Bi-LSTMmodule for temporal analysis,which assists the ARNet in understanding the dynamic behavior of actions over time.The ARNet integrates three additional dense layers after the Bi-LSTM module to ensure a comprehensive computation of both spatial and temporal patterns and further boost the feature representation.The experimental validation of the model is conducted on 3 benchmark datasets named HMDB51,KTH,and UCF Sports and reports accuracies of 93.82%,99%,and 99.16%,respectively.The Precision results of HMDB51,KTH,and UCF Sports datasets are 97.41%,99.54%,and 99.01%;the Recall values are 98.87%,98.60%,99.08%,and the F1-Score is 98.13%,99.07%,99.04%,respectively.These results highlight the robustness of the ARNet approach and its potential as a versatile tool for accurate HAR across various real-world applications.
基金Supported by the National Natural Science Foundation of China(No. 20402001)Special Foundation for Beijing Municipal In-telligent(No. 20041D0501520)Beijing Natural Science Foundation(No. 2062003).
文摘Aryl diketo acid derivatives are one of the most promising HIV-1 integrase（IN） inhibitors. With a view to substitute the critical diketo acid pharmacophore with the diketo benzimidazole unit, the coupling reaction of compound 4 with o-phenylenediamine was carried out. However, the reaction product, compound 5, was confirmed to be 3-{ [ 3- （phenylsulfonamido） benzoyl] methylidene t -3,4-dihydroquinoxaline-2 （1H） -one rather than the 2-benzimidazole derivative by using X-ray diffraction. Owing to its low solubility in water, the evaluation of the anti-HIV IN activity of the synthesized compound 5 could not be carried out. Consequently, the ion-binding properties of compound 5 in the absence of HIV-1 IN were investigated with UV-Vis spectroscopy in organic solvents. The results show that such a compound can selectively recognize Cu^2＋.
文摘Pattern recognition method is used for the investigation of stability,region of filled Ti_2Ni phases in multi-dimensional bond-parameter space.The filling of C,N and O atoms into T_6 octahedra consisting of atoms of earhy-transition elements makes the expansion of the stability region of Ti_2Ni phase,and the relative stability of AI_2Cu and MoSi_2 type com- pounds decreases after the introduction of non-metallic elements such as C,N and O.
基金the National Natural Science Foundation of China(Grant No.12172304)the 111 Project(Grant No.BP0719007).
文摘In this study,unsupervised and supervised pattern recognition were implemented in combination to achieve real-time health monitoring.Unsupervised recognition(k-means++)was used to label the spectral characteristics of acoustic emission(AE)signals after completing the tensile tests at ambient temperature.Using in-plane tensile at 800 and 1000°C as implementing examples,supervised recognition(K-nearest neighbor(KNN))was used to identify damage mode in real time.According to the damage identification results,four main tensile damage modes of 2D C/SiC composites were identified:matrix cracking(122.6–201 kHz),interfacial debonding(201–294.4 kHz),interfacial sliding(20.6–122.6 kHz)and fiber breaking(294.4–1000 kHz).Additionally,the damage evolution mechanisms for the 2D C/SiC composites were analyzed based on the characteristics of AE energy accumulation curve during the in-plane tensile loading at ambient and elevated temperature with oxidation.Meanwhile,the energy of various damage modes was accurately calculated by harmonic wavelet packet and the damage degree of modes could be analyzed.The identification results show that compared with previous studies,using the AE analysis method,the method has higher sensitivity and accuracy.
基金Sponsored by the National High Technology Research Development Program of China(Grant No.2001AA413130).
文摘The main aim for a 2D spiral recognition algorithm is to learn to discriminate between data distributed on two distinct strands in the x-y plane.This problem is of critical importance since it incorporates temporal characteristics often found in real-time applications.Previous work with this benchmark has witnessed poor results with statistical methods such as discriminant analysis and tedious procedures for better results with neural networks.This paper presents a max-density covering learning algorithm based on constructive neural networks which is efficient in terms of the recognition rate and the speed of recognition.The results show that it is possible to solve the spiral problem instantaneously(up to 100% correct classification on the test set).
基金supported by the Chung-Ang University Graduate Research Scholarship in 2021.
文摘Speech emotion recognition is essential for frictionless human-machine interaction,where machines respond to human instructions with context-aware actions.The properties of individuals’voices vary with culture,language,gender,and personality.These variations in speaker-specific properties may hamper the performance of standard representations in downstream tasks such as speech emotion recognition(SER).This study demonstrates the significance of speaker-specific speech characteristics and how considering them can be leveraged to improve the performance of SER models.In the proposed approach,two wav2vec-based modules(a speaker-identification network and an emotion classification network)are trained with the Arcface loss.The speaker-identification network has a single attention block to encode an input audio waveform into a speaker-specific representation.The emotion classification network uses a wav2vec 2.0-backbone as well as four attention blocks to encode the same input audio waveform into an emotion representation.These two representations are then fused into a single vector representation containing emotion and speaker-specific information.Experimental results showed that the use of speaker-specific characteristics improves SER performance.Additionally,combining these with an angular marginal loss such as the Arcface loss improves intra-class compactness while increasing inter-class separability,as demonstrated by the plots of t-distributed stochastic neighbor embeddings(t-SNE).The proposed approach outperforms previous methods using similar training strategies,with a weighted accuracy(WA)of 72.14%and unweighted accuracy(UA)of 72.97%on the Interactive Emotional Dynamic Motion Capture(IEMOCAP)dataset.This demonstrates its effectiveness and potential to enhance human-machine interaction through more accurate emotion recognition in speech.
基金supported by the National Natural Science Foundation of China(Nos.30771501 and 81102850)the National Basic Research Program(973)of China(No.2011CB811302)+2 种基金the National Mega Project on Major Drug Development(No.2009ZX09301-014-1)the Chinese 111 Project(No.B06018)the Wuhan Municipal Project(No.201160923296),China
文摘Objective: To evaluate the potential adjuvant effect of Agrocybe aegerita lectin(AAL), which was isolated from mushroom, against a virulent H_9N_2 strain in vivo and in vitro. Methods: In trial 1, 50 BALB/c male mice(8 weeks old) were divided into five groups(n=10 each group) which received a subcutaneous injection of inactivated H_9N_2(control), inactivated H_9N_2+0.2%(w/w) alum, inactivated H_9N_2+0.5 mg recombinant AAL/kg body weight(BW), inactivated H_9N_2+1.0 mg AAL/kg BW, and inactivated H_9N_2+2.5 mg AAL/kg BW, respectively, four times at 7-d intervals. In trial 2, 30 BALB/c male mice(8 weeks old) were divided into three groups(n=10 each group) which received a subcutaneous injection of inactivated H_9N_2(control), inactivated H_9N_2+2.5 mg recombinant wild-type AAL(AAL-wt)/kg BW, and inactivated H_9N_2+2.5 mg carbohydrate recognition domain(CRD) mutant AAL(AAL-mut R63H)/kg BW, respectively, four times at 7-d intervals. Seven days after the final immunization, serum samples were collected from each group for analysis. Hemagglutination assay, immunogold electron microscope, lectin blotting, and coimmunoprecipitation were used to study the interaction between AAL and H_9N_2 in vitro. Results: Ig G, Ig G1, and Ig G2 a antibody levels were significantly increased in the sera of mice co-immunized with inactivated H_9N_2 and AAL when compared to mice immunized with inactivated H_9N_2 alone. No significant increase of the Ig G antibody level was detected in the sera of the mice co-immunized with inactivated H_9N_2 and AAL-mut R63 H. Moreover, AAL-wt, but not mutant AAL-mut R63 H, adhered to the surface of H_9N_2 virus. The interaction between AAL and the H_9N_2 virus was further demonstrated to be associated with the CRD of AAL binding to the surface glycosylated proteins, hemagglutinin and neuraminidase. Conclusions: Our findings indicated that AAL could be a safe and effective adjuvant capable of boosting humoral immunity against H_9N_2 viruses in mice through its interaction with the viral surface glycosylated proteins, hemagglutinin and neuraminidase.
文摘As a new dimension reduction method, the two-dimensional principal component (2DPCA) can be well applied in face recognition, but it is susceptible to outliers. Therefore, this paper proposes a new 2DPCA algorithm based on angel-2DPCA. To reduce the reconstruction error and maximize the variance simultaneously, we choose F norm as the measure and propose the Fp-2DPCA algorithm. Considering that the image has two dimensions, we offer the Fp-2DPCA algorithm based on bilateral. Experiments show that, compared with other algorithms, the Fp-2DPCA algorithm has a better dimensionality reduction effect and better robustness to outliers.
文摘Activity recognition of indoor occupants using indirect sensing with less privacy violation is one of the hot research topics. This paper proposes a CO<sub>2</sub> sensor-based indoor occupant activity monitoring system. Using the IoT sensor node that contains CO<sub>2</sub> sensors, the measured CO<sub>2</sub> concentrations in three locations (laboratory, office, and bedroom) were stored in a cloud server for up to 35 days starting July 1, 2023. The CO<sub>2</sub> measurements stored at 30-second intervals were statistically processed to produce a heat-mapped display of the hourly average or maximum CO<sub>2</sub> concentration. From the heatmap visualizations of CO<sub>2</sub> concentration, the proposed system estimated meeting, heating water using a portable stove, and sleep for the occupants’ activity recognition.
