Search

The most common manifestation of neurological disorders in children is the occurrence of epileptic seizures. In this study, we propose a multi-branch graph convolutional network (MGCNA) framework with a multi-head attention mechanism for detecting seizures in children. The MGCNA framework extracts effective and reliable features from high-dimensional data, particularly by exploring the relationships between EEG features and electrodes and considering the spatial and temporal dependencies in epileptic brains. This method incorporates three graph learning approaches to systematically assess the connectivity and synchronization of multi-channel EEG signals. The multi-branch graph convolutional network is employed to dynamically learn temporal correlations and spatial topological structures. Utilizing the multi-head attention mechanism to process multi-branch graph features further enhances the capability to handle local features. Experimental results demonstrate that the MGCNA exhibits superior performance on patient-specific and patient-independent experiments. Our end-to-end model for automatic detection of epileptic seizures could be employed to assist in clinical decision-making.

Increased physical activity can help reduce the occurrence of cardiovascular disease. However, cardiovascular disease during strenuous exercise also brings certain risks, so a convenient and effective method is needed to accurately identify heart rate. Due to the low amplitude characteristics of ECG signals, automatic classification of the imperceptibility and irregularities of ECG signals remains a great challenge. To address this issue, we propose an automatic heart rate detection method using a two-dimensional convolutional neural network. First, the ECG data is preprocessed to convert the multi-lead single-channel ECG data into dual-channel ECG data. Then, the ECG image is input into the convolutional neural network. To enhance the diagnostic accuracy of an abnormal heart rate diagnosis model, this study integrates a multi-scale pyramid module into the network to fully extract image contextual information. Experimental analysis utilizes MIT-BIH and Sudden Cardiac Death Holter public datasets for training and testing. The results show that the final classification accuracy reaches 99.12% and 98.40%, respectively. The method requires no manual pre-processing of converted ECG images, has high accuracy, can effectively monitor abnormal heart rate, and minimize sudden death caused by abnormal heart rate.

With the rapid advancement of wireless communication technology, automatic modulation classification (AMC) plays a crucial role in drone communication systems, ensuring reliable and efficient communication in various non-cooperative environments. Deep learning technology has demonstrated significant advantages in the field of AMC, effectively and accurately extracting and classifying modulation signal features. However, existing deep learning models often have high computational costs, making them difficult to deploy on resource-constrained drone communication devices. To address this issue, this study proposes a lightweight Mobile Automatic Modulation Classification Transformer (MobileAmcT). This model combines the advantages of lightweight convolutional neural networks and efficient Transformer modules, incorporating the Token and Channel Conv (TCC) module and the EfficientShuffleFormer module to enhance the accuracy and efficiency of the automatic modulation classification task. The TCC module, based on the MetaFormer architecture, integrates lightweight convolution and channel attention mechanisms, significantly improving local feature extraction efficiency. Additionally, the proposed EfficientShuffleFormer innovatively improves the traditional Transformer architecture by adopting Efficient Additive Attention and a novel ShuffleConvMLP feedforward network, effectively enhancing the global feature representation and fusion capabilities of the model. Experimental results on the RadioML2016.10a dataset show that compared to MobileNet-V2 (CNN-based) and MobileViT-XS (ViT-based), MobileAmcT reduces the parameter count by 74% and 65%, respectively, and improves classification accuracy by 1.7% and 1.09% under different SNR conditions, achieving an accuracy of 62.93%. This indicates that MobileAmcT can maintain high classification accuracy while significantly reducing the parameter count and computational complexity, clearly outperforming existing state-of-the-art AMC methods and other lightweight deep learning models.

Since ECG contains key characteristic information of arrhythmias, extracting this information is crucial for identifying arrhythmias. Based on this, in order to effectively extract ECG data features and realize automatic detection of arrhythmia, a multi-classification method of arrhythmia based on multi-scale residual neural network and multi-channel data fusion is proposed. First, the features of single-lead ECG signals are extracted and converted into two-dimensional images, and the feature data sets are labeled and divided according to different types of arrhythmias. The improved residual neural network is trained on the training set to obtain the classification model of the neural network. Finally, the classification model is applied to the automatic detection of arrhythmias during exercise. The accuracy of the classification model of this method is as high as 99.60%, and it has high accuracy and generalization ability. The automatic identification of arrhythmia also contributes to the research and development of future wearable devices.

Epilepsy is a common neurological disorder, and its diagnosis mainly relies on the analysis of electroencephalogram (EEG) signals. However, the raw EEG signals contain limited recognizable features, and in order to increase the recognizable features in the input of the network, the differential features of the signals, the amplitude spectrum and the phase spectrum in the frequency domain are extracted to form a two-dimensional feature vector. In order to solve the problem of recognizing multimodal features, a neural network model based on a multimodal dual-stream network is proposed, which uses a mixture of one-dimensional convolution, two-dimensional convolution and LSTM neural networks to extract the spatial features of the EEG two-dimensional vectors and the temporal features of the signals, respectively, and combines the advantages of the two networks, using the hybrid neural network to extract both the temporal and spatial features of the signals at the same time. In addition, a channel attention module was used to focus the model on features related to seizures. Finally, multiple sets of experiments were conducted on the Bonn and New Delhi data sets, and the highest accuracy rates of 99.69% and 97.5% were obtained on the test set, respectively, verifying the superiority of the proposed model in the task of epileptic seizure detection.

Depression is an undetectable mental disease. Most of the patients with depressive symptoms do not know that they are suffering from depression. Since the novel Coronavirus pandemic 2019, the number of patients with depression has increased rapidly. There are two kinds of traditional depression diagnosis. One is that professional psychiatrists make diagnosis results for patients, but it is not conducive to large-scale depression detection. Another is to use electroencephalography (EEG) to record neuronal activity. Then, the features of the EEG are extracted using manual or traditional machine learning methods to diagnose the state and type of depression. Although this method achieves good results, it does not fully utilize the multi-channel information of EEG. Aiming at this problem, an EEG diagnosis method for depression based on multi-channel data fusion cropping enhancement and convolutional neural network is proposed. First, the multi-channel EEG data are transformed into 2D images after multi-channel fusion (MCF) and multi-scale clipping (MSC) augmentation. Second, it is trained by a multi-channel convolutional neural network (MCNN). Finally, the trained model is loaded into the detection device to classify the input EEG signals. The experimental results show that the combination of MCF and MSC can make full use of the information contained in the single sensor records, and significantly improve the classification accuracy and clustering effect of depression diagnosis. The method has the advantages of low complexity and good robustness in signal processing and feature extraction, which is beneficial to the wide application of detection systems.

Reasonable exercise is beneficial to human health. However, it is difficult for ordinary athletes to judge whether they are already in a state of fatigue that is not suitable for exercise. In this case, it is easy to cause physical damage or even life-threatening. Therefore, to health sports, protecting the human body in sports not be injured by unreasonable sports, this study proposes an exercise fatigue diagnosis method based on short-time Fourier transform (STFT) and convolutional neural network (CNN). The method analyzes and diagnoses the real-time electrocardiogram, and obtains whether the current exerciser has exercise fatigue according to the electrocardiogram. The algorithm first performs short-time Fourier transform on the electrocardiogram (ECG) signal to obtain the time spectrum of the signal, which is divided into training set and validation set. The training set is then fed into the convolutional neural network for learning, and the network parameters are adjusted. Finally, the trained convolutional neural network model is applied to the test set, and the recognition result of fatigue level is output. The validity and feasibility of the method are verified by the ECG experiment of exercise fatigue degree. The experimental recognition accuracy rate can reach 97.70%, which proves that the constructed sports fatigue diagnosis model has high diagnostic accuracy and is feasible for practical application.

Pseudonocardia species are emerging as important microorganisms of global concern with unique and increasingly significant ecological roles and represent a prominent source of bioactive natural products, but genetic engineering of these organisms for biotechnological applications is greatly hindered due to the limitation of efficient genetic manipulation tools. In this regard, we report here the establishment of an efficient genetic manipulation system for a newly isolated strain, Pseudonocardia alni Shahu, based on plasmid conjugal transfer from Escherichia coli to Pseudonocardia. Conjugants were yielded upon determining the optimal ratio between the donor and recipient cells, and designed genome modifications were efficiently accomplished, including exogenous gene integration based on an integrative plasmid and chromosomal stretch removal by homologous recombination using a suicidal non-replicating vector. Collectively, this work has made the P. alni Shahu accessible for genetic engineering, and provided an important reference for developing genetic manipulation methods in other rare actinomycetes.

The gearbox is an important component in the mechanical transmission system and plays a key role in aerospace, wind power and other fields. Gear failure is one of the main causes of gearbox failure, and therefore it is very important to accurately diagnose the type of gear failure under different operating conditions. Aiming at the problem that it is difficult to effectively identify the fault types of gears using traditional methods under complex and changeable working conditions, a fault diagnosis method based on multi-sensor information fusion and Visual Geometry Group (VGG) is proposed. First, the power spectral density is calculated with the raw frequency domain signal collected by multiple sensors before being transformed into a power spectral density energy map after information fusion. Second, the obtained energy map is combined with VGG to obtain the fault diagnosis model of the gear. Finally, two datasets are used to verify the effectiveness and generalization ability of the method. The experimental results show that the accuracy of the method can reach 100% at most on both datasets.

Establishment of production platforms through prokaryotic engineering in microbial organisms would be one of the most efficient means for chemicals, protein, and biofuels production. Despite the fact that CRISPR (clustered regularly interspaced short palindromic repeats)–based technologies have readily emerged as powerful and versatile tools for genetic manipulations, their applications are generally limited in prokaryotes, possibly owing to the large size and severe cytotoxicity of the heterogeneous Cas (CRISPR-associated) effector. Nevertheless, the rich natural occurrence of CRISPR-Cas systems in many bacteria and most archaea holds great potential for endogenous CRISPR-based prokaryotic engineering. The endogenous CRISPR-Cas systems, with type I systems that constitute the most abundant and diverse group, would be repurposed as genetic manipulation tools once they are identified and characterized as functional in their native hosts. This article reviews the major progress made in understanding the mechanisms of invading DNA immunity by type I CRISPR-Cas and summarizes the practical applications of endogenous type I CRISPR-based toolkits for prokaryotic engineering.

Objective: Antibodies to CA 125 have been used to predict relapse of ovarian cancer, but have performed poorly as therapeutic agents. One rationale for this is antibody binding to circulating shed antigen. Our aim in this study was to develop antibodies to human CA 125 that have enhanced selectivity for the cell-associated form of the antigen. Methods: Monoclonal antibodies were raised to a recombinant fragment of CA 125 that included sequence proximal to the putative membrane attachment site. Antibodies were characterized in terms of their binding site, affinity and selectivity for cell-associated CA 125. Results: In assays using patient-derived CA 125, a subset of high-affinity (KD <5 nM) monoclonal antibodies demonstrated a 10- to greater than 200-fold increase in selectivity for cell-associated CA 125 when compared with controls. Based on mapping of the various monoclonal antibodies obtained, it was determined that shedding of CA 125 most likely occurs in the most C-terminal repeat domain. Conclusion: Results from competition analysis using patient-derived shed antigen predict that the antibodies described in this study may have significantly enhanced tumor-targeting properties when compared with existing antibodies to CA 125 in a tumor environment having high concentrations (>10,000 CA 125 units) of shed CA 125. Copyright © 2006 S. Karger AG, Basel [ABSTRACT FROM AUTHOR]

Tissue factor (TF) is a type I transmembrane protein and the initiator of the extrinsic blood coagulation pathway. TF plays a critical role in tumor development and its overexpression is observed in many tumors. To understand the prevalence and relative level of TF expression in nonsmall-cell lung cancer (NSCLC), we analyzed 50 NSCLC tumors by immunohistochemical staining and found that 88% of human NSCLC tumors overexpressed TF. We then generated a high affinity anti-TF antibody, TF278, which specifically binds TF on the surface of cells and is internalized upon binding. An 111In-labeled TF278 demonstrated favorable tumor accumulation in an SW-900 xenograft tumor model with a maximum mean percent of injected dose per gram of tissue (%ID/g) of 73.1% at 96 hours postinjection. In addition, we labeled the antibody with 90Y and tested its ability to inhibit the growth of tumors in an SW-900 xenograft tumor model in immunocompromised mice. The 90Y-TF278 slowed the growth of SW-900 tumors at a 50 Ci dose and completely regressed SW-900 tumors at a 150 Ci dose with little toxicity. [ABSTRACT FROM AUTHOR]

Examines the retroviral-mediated transmission of a mouse VL30 RNA to human melanoma cells. Promotion of metastasis in an immunodeficient mouse model; Structural features of retroviral genome; Transmission of cellular gene from other cells.