[Neural network analysis of mechanization's impact on coal miner's occupational health].

In order to clarify the transmission mechanism of the impact of mechanization on the occupational health of miners and to provide empirical evidence for the development of new quality productivity in the coal industry that balances health and efficiency. In August 2022, we selected a typical coal mine, constructed a comprehensive evaluation index of miners' occupational health through a questionnaire survey based on the fully connected neural network model. A Bayesian model was used to verify the influence of mechanization level on miners' occupational health. We found that: the predicted probability of occupational diseases could be used as a comprehensive indicator of the level of occupational health, providing a basis for early intervention and prevention of occupational diseases. Mechanization could directly promote the improvement of miners' occupational health level, and also indirectly affect occupational health level by influencing hazards level and work intensity. The indirect effect of mechanization on work intensity was positive, and the indirect effect of mechanization on hazards level was positive. Presented the "inverted U-shaped" process in the mechanization breakthrough semi-mechanized level would realize the economies of scale of health protection, its impact on the prevention and control of occupational hazards would turn from negative to positive.

Emulation of Pavlovian conditioning and pattern recognition through fully connected neural networks using Holmium oxide (Ho2O3) based synaptic RRAM device.

In this manuscript, we report on the paramagnetic Ho2O3-based synaptic resistive random-access memory device for the implementation of neuronal functionalities such as long-term potentiation, long-term depression and spike timing dependent plasticity respectively. The plasticity of the artificial synapse is also studied by varying pulse amplitude, pulse width, and pulse interval. In addition, we could classify handwritten Modified National Institute of Standards and Technology data set (MNIST) using a fully connected neural network (FCN). The device-based FCN records a high classification accuracy of 93.47% which is comparable to the software-based test accuracy of 97.97%. This indicates the highly optimized behavior of our synaptic device for hardware neuromorphic applications. Successful emulation of Pavlovian classical conditioning for associative learning of the biological brain is achieved. We believe that the present device consists the potential to utilize in neuromorphic applications.

Naive Prediction of Protein Backbone Phi and Psi Dihedral Angles Using Deep Learning.

Protein structure prediction represents a significant challenge in the field of bioinformatics, with the prediction of protein structures using backbone dihedral angles recently achieving significant progress due to the rise of deep neural network research. However, there is a trend in protein structure prediction research to employ increasingly complex neural networks and contributions from multiple models. This study, on the other hand, explores how a single model transparently behaves using sequence data only and what can be expected from the predicted angles. To this end, the current paper presents data acquisition, deep learning model definition, and training toward the final protein backbone angle prediction. The method applies a simple fully connected neural network (FCNN) model that takes only the primary structure of the protein with a sliding window of size 21 as input to predict protein backbone ϕ and ψ dihedral angles. Despite its simplicity, the model shows surprising accuracy for the ϕ angle prediction and somewhat lower accuracy for the ψ angle prediction. Moreover, this study demonstrates that protein secondary structure prediction is also possible with simple neural networks that take in only the protein amino-acid residue sequence, but more complex models are required for higher accuracies.

Reconstructing gene regulatory networks of biological function using differential equations of multilayer perceptrons.

BACKGROUND: Building biological networks with a certain function is a challenge in systems biology. For the functionality of small (less than ten nodes) biological networks, most methods are implemented by exhausting all possible network topological spaces. This exhaustive approach is difficult to scale to large-scale biological networks. And regulatory relationships are complex and often nonlinear or non-monotonic, which makes inference using linear models challenging. RESULTS: In this paper, we propose a multi-layer perceptron-based differential equation method, which operates by training a fully connected neural network (NN) to simulate the transcription rate of genes in traditional differential equations. We verify whether the regulatory network constructed by the NN method can continue to achieve the expected biological function by verifying the degree of overlap between the regulatory network discovered by NN and the regulatory network constructed by the Hill function. And we validate our approach by adapting to noise signals, regulator knockout, and constructing large-scale gene regulatory networks using link-knockout techniques. We apply a real dataset (the mesoderm inducer Xenopus Brachyury expression) to construct the core topology of the gene regulatory network and find that Xbra is only strongly expressed at moderate levels of activin signaling. CONCLUSION: We have demonstrated from the results that this method has the ability to identify the underlying network topology and functional mechanisms, and can also be applied to larger and more complex gene network topologies.

Solving Inverse Electrocardiographic Mapping Using Machine Learning and Deep Learning Frameworks.

Electrocardiographic imaging (ECGi) reconstructs electrograms at the heart's surface using the potentials recorded at the body's surface. This is called the inverse problem of electrocardiography. This study aimed to improve on the current solution methods using machine learning and deep learning frameworks. Electrocardiograms were simultaneously recorded from pigs' ventricles and their body surfaces. The Fully Connected Neural network (FCN), Long Short-term Memory (LSTM), Convolutional Neural Network (CNN) methods were used for constructing the model. A method is developed to align the data across different pigs. We evaluated the method using leave-one-out cross-validation. For the best result, the overall median of the correlation coefficient of the predicted ECG wave was 0.74. This study demonstrated that a neural network can be used to solve the inverse problem of ECGi with relatively small datasets, with an accuracy compatible with current standard methods.

Highly Dense FBG Temperature Sensor Assisted with Deep Learning Algorithms.

In this paper, we demonstrate the application of deep neural networks (DNNs) for processing the reflectance spectrum from a fiberoptic temperature sensor composed of densely inscribed fiber bragg gratings (FBG). Such sensors are commonly avoided in practice since close arrangement of short FBGs results in distortion of the spectrum caused by mutual interference between gratings. In our work the temperature sensor contained 50 FBGs with the length of 0.95 mm, edge-to-edge distance of 0.05 mm and arranged in the 1500-1600 nm spectral range. Instead of solving the direct peak detection problem for distorted signal, we applied DNNs to predict temperature distribution from entire reflectance spectrum registered by the sensor. We propose an experimental calibration setup where the dense FBG sensor is located close to an array of sparse FBG sensors. The goal of DNNs is to predict the positions of the reflectance peaks of the reference sparse FBG sensors from the reflectance spectrum of the dense FBG sensor. We show that a convolution neural network is able to predict the positions of FBG reflectance peaks of sparse sensors with mean absolute error of 7.8 pm that is slightly higher than the hardware reused interrogator equal to 5 pm. We believe that dense FBG sensors assisted with DNNs have a high potential to increase spatial resolution and also extend the length of a fiber optical sensors.

Deep Neural Network for Visual Stimulus-Based Reaction Time Estimation Using the Periodogram of Single-Trial EEG.

Multiplexed deep neural networks (DNN) have engendered high-performance predictive models gaining popularity for decoding brain waves, extensively collected in the form of electroencephalogram (EEG) signals. In this paper, to the best of our knowledge, we introduce a first-ever DNN-based generalized approach to estimate reaction time (RT) using the periodogram representation of single-trial EEG in a visual stimulus-response experiment with 48 participants. We have designed a Fully Connected Neural Network (FCNN) and a Convolutional Neural Network (CNN) to predict and classify RTs for each trial. Though deep neural networks are widely known for classification applications, cascading FCNN/CNN with the Random Forest model, we designed a robust regression-based estimator to predict RT. With the FCNN model, the accuracies obtained for binary and 3-class classification were 93% and 76%, respectively, which further improved with the use of CNN (94% and 78%, respectively). The regression-based approach predicted RTs with correlation coefficients (CC) of 0.78 and 0.80 for FCNN and CNN, respectively. Investigating further, we found that the left central as well as parietal and occipital lobes were crucial for predicting RT, with significant activities in the theta and alpha frequency bands.

A deep learning approach for acute liver failure prediction with combined fully connected and convolutional neural networks.

BACKGROUND: Acute Liver Failure (ALF) is a critical medical condition with rapid development, often caused by viral infections, hepatotoxic drug abuse, or other severe liver diseases. Timely and accurate prediction of ALF occurrence is clinically crucial. However, predicting ALF poses challenges due to the diverse physiological differences among patients and the dynamic nature of the disease. OBJECTIVE: This study introduces a deep learning approach that combines fully connected and convolutional neural networks for effective ALF prediction. The goal is to overcome limitations of traditional machine learning methods and enhance predictive model performance and generalization. METHODS: The proposed model integrates a fully connected neural network for handling basic patient features and a convolutional neural network dedicated to capturing temporal patterns in patient data. The combination allows automatic learning of complex patterns and abstract features present in highly dynamic medical data associated with ALF. RESULTS: The model's effectiveness is demonstrated through comprehensive experiments and performance evaluations. It outperforms traditional machine learning methods, achieving 94.8% accuracy and superior generalization capabilities. CONCLUSIONS: The study highlights the potential of deep learning in ALF prediction, emphasizing the importance of considering individualized medical factors. Future research should focus on improving model robustness, addressing imbalanced data, and further exploring personalized features for enhanced predictive accuracy in real-world clinical scenarios.

ILYCROsite: Identification of lysine crotonylation sites based on FCM-GRNN undersampling technique.

Protein lysine crotonylation is an important post-translational modification that regulates various cellular activities. For example, histone crotonylation affects chromatin structure and promotes histone replacement. Identification and understanding of lysine crotonylation sites is crucial in the field of protein research. However, due to the increasing amount of non-histone crotonylation sites, existing classifiers based on traditional machine learning may encounter performance limitations. In order to address this problem, a novel deep learning-based model for identifying crotonylation sites is presented in this study, given the unique advantages of deep learning techniques for sequence data analysis. In this study, an MLP-Attention-based model was developed for the identification of crotonylation sites. Firstly, three feature extraction strategies, namely Amino Acid Composition, K-mer, and Distance-based residue features extraction strategy, were used to encode crotonylated and non-crotonylated sequences. Then, in order to balance the training dataset, the FCM-GRNN undersampling algorithm combining fuzzy clustering and generalized neural network approaches was introduced. Finally, to improve the effectiveness of crotonylation site identification, we explored various classification algorithms, and based on the relevant experimental performance comparisons, the multilayer perceptron (MLP) combined with the superimposed self-attention mechanism was finally selected to construct the prediction model ILYCROsite. The results obtained from independent testing and five-fold cross-validation demonstrated that the model proposed in this study, ILYCROsite, had excellent performance. Notably, on the independent test set, ILYCROsite achieves an AUC value of 87.93 %, which is significantly better than the existing state-of-the-art models. In addition, SHAP (Shapley Additive exPlanations) values were used to analyze the importance of features and their impact on model predictions. Meanwhile, in order to facilitate researchers to use the prediction model constructed in this study, we developed a prediction program to identify the crotonylation sites in a given protein sequence. The data and code for this program are available at: https://github.com/wmqskr/ILYCROsite.

Photoacoustic imaging of squirrel monkey cortical responses induced by peripheral mechanical stimulation.

Non-human primates (NHPs) are crucial models for studies of neuronal activity. Emerging photoacoustic imaging modalities offer excellent tools for studying NHP brains with high sensitivity and high spatial resolution. In this research, a photoacoustic microscopy (PAM) device was used to provide a label-free quantitative characterization of cerebral hemodynamic changes due to peripheral mechanical stimulation. A 5 × 5 mm area within the somatosensory cortex region of an adult squirrel monkey was imaged. A deep, fully connected neural network was characterized and applied to the PAM images of the cortex to enhance the vessel structures after mechanical stimulation on the forelimb digits. The quality of the PAM images was improved significantly with a neural network while preserving the hemodynamic responses. The functional responses to the mechanical stimulation were characterized based on the improved PAM images. This study demonstrates capability of PAM combined with machine learning for functional imaging of the NHP brain.

Machine Learning-Aided Design of Highly Conductive Anion Exchange Membranes for Fuel Cells and Water Electrolyzers.

Alkaline anion exchange membrane (AEM)-based fuel cells (AEMFCs) and water electrolyzers (AEMWEs) are vital for enabling the efficient and large-scale utilization of hydrogen energy. However, the performance of such energy devices is impeded by the relatively low conductivity of AEMs. The conventional trial-and-error approach to designing membrane structures has proven to be both inefficient and costly. To address this challenge, a fully connected neural network (FCNN) model is developed based on acid-catalyzed AEMs to analyze the relationship between structure and conductivity among 180,000 AEM variations. Under machine learning guidance, anilinium cation-type membranes are designed and synthesized. Molecular dynamics simulations and Mulliken charge population analysis validated that the presence of a large anilinium cation domain is a result of the inductive effect of N+ and benzene rings. The interconnected anilinium cation domains facilitated the formation of a continuous ion transport channel within the AEMs. Additionally, the incorporation of the benzyl electron-withdrawing group heightened the inductive effect, leading to high conductivity AEM variant as screened by the machine learning model. Furthermore, based on the highly active and low-cost monomers given by machine learning, the large-scale synthesis of anilinium-based AEMs confirms the potential for commercial applications.

Neural networks contribution in face mask detection to reduce the spread of COVID-19.

In front of COVID-19 propagation, we can protect our self by taking precautionary measures such as wearing face masks. It may be mandatory in particular public place although some persons ignore this rule. Several research in face mask detection area have emerged and most of studies are based on deep learning. In this paper, we present a method to detect whether person wear a mask or not to prevent the propagation of virus. The approach is based on combination of Pulse Couple Neural Network and Fully Connected Neural Network and the processing is divided in three steps: geometrical, feature extraction and decision. The geometrical module selects the Region of Interest for given image and the feature extraction module composed by Pulse Couple Neural Network extracts all pertinent information which will be used by the last module for decision. This decision module makes directly a decision in case of non-complex classification without neural network training overwise the Fully Connected Neural Network continues the treatment. The input image may be captured from video surveillance sequence, the system triggers a signal alarm once a person doesn't wear face mask. Our proposed approach was tested with different datasets like Kaggle, AIZOO, Moxa3K, Real-World Masked Face Dataset, Medical Masks Dataset, Face Mask Dataset and the accuracy varies from 83.2% to 100% with minimum computation time.

From sequence to function through structure: Deep learning for protein design.

The process of designing biomolecules, in particular proteins, is witnessing a rapid change in available tooling and approaches, moving from design through physicochemical force fields, to producing plausible, complex sequences fast via end-to-end differentiable statistical models. To achieve conditional and controllable protein design, researchers at the interface of artificial intelligence and biology leverage advances in natural language processing (NLP) and computer vision techniques, coupled with advances in computing hardware to learn patterns from growing biological databases, curated annotations thereof, or both. Once learned, these patterns can be used to provide novel insights into mechanistic biology and the design of biomolecules. However, navigating and understanding the practical applications for the many recent protein design tools is complex. To facilitate this, we 1) document recent advances in deep learning (DL) assisted protein design from the last three years, 2) present a practical pipeline that allows to go from de novo-generated sequences to their predicted properties and web-powered visualization within minutes, and 3) leverage it to suggest a generated protein sequence which might be used to engineer a biosynthetic gene cluster to produce a molecular glue-like compound. Lastly, we discuss challenges and highlight opportunities for the protein design field.

A neural network based framework for effective laparoscopic video quality assessment.

Video quality assessment is a challenging problem having a critical significance in the context of medical imaging. For instance, in laparoscopic surgery, the acquired video data suffers from different kinds of distortion that not only hinder surgery performance but also affect the execution of subsequent tasks in surgical navigation and robotic surgeries. For this reason, we propose in this paper neural network-based approaches for distortion classification as well as quality prediction. More precisely, a Residual Network (ResNet) based approach is firstly developed for simultaneous ranking and classification task. Then, this architecture is extended to make it appropriate for the quality prediction task by using an additional Fully Connected Neural Network (FCNN). To train the overall architecture (ResNet and FCNN models), transfer learning and end-to-end learning approaches are investigated. Experimental results, carried out on a new laparoscopic video quality database, have shown the efficiency of the proposed methods compared to recent conventional and deep learning based approaches.

An x-ray crosstalk correction method using FCNN for a novel energy resolving scheme in spectral CT.

Spectral computed tomography has great potential for multi-energy imaging and anti-artifacts. The complete absorption-based energy resolving scheme of x-rays has been used for the integrity of detected information. However, this scheme is limited by the fact that the detector pixel thickness is high and fixed. Here, an energy resolving scheme is proposed using the crosstalk correction method for the incomplete absorption detection of x-rays. A fully connected neural network (FCNN)-based method was used to correct the difference caused by internal x-ray crosstalk of the edge-on detector. The energy and spatial features of the data which is collected in layers were combined to establish the mapping between the ideal data and the data with crosstalk at the pre-processing stage. Thereafter, to reconstruct the stable and highly accurate energy-resolving equations, the layers with low relative energy difference were selected and grouped together to reduce the accumulation difference. The experiment results demonstrate the feasibility of this energy resolving scheme. The differences caused by crosstalk can be suppressed through the proposed FCNN-based method. The resolving accuracy can be further improved by grouping more layers at forward positions in the pixel. Moreover, this improvement can be observed in the reconstructed images with reduced artifacts and improved quality.

Classifying the tracing difficulty of 3D neuron image blocks based on deep learning.

Quickly and accurately tracing neuronal morphologies in large-scale volumetric microscopy data is a very challenging task. Most automatic algorithms for tracing multi-neuron in a whole brain are designed under the Ultra-Tracer framework, which begins the tracing of a neuron from its soma and traces all signals via a block-by-block strategy. Some neuron image blocks are easy for tracing and their automatic reconstructions are very accurate, and some others are difficult and their automatic reconstructions are inaccurate or incomplete. The former are called low Tracing Difficulty Blocks (low-TDBs), while the latter are called high Tracing Difficulty Blocks (high-TDBs). We design a model named 3D-SSM to classify the tracing difficulty of 3D neuron image blocks, which is based on 3D Residual neural Network (3D-ResNet), Fully Connected Neural Network (FCNN) and Long Short-Term Memory network (LSTM). 3D-SSM contains three modules: Structure Feature Extraction (SFE), Sequence Information Extraction (SIE) and Model Fusion (MF). SFE utilizes a 3D-ResNet and a FCNN to extract two kinds of features in 3D image blocks and their corresponding automatic reconstruction blocks. SIE uses two LSTMs to learn sequence information hidden in 3D image blocks. MF adopts a concatenation operation and a FCNN to combine outputs from SIE. 3D-SSM can be used as a stop condition of an automatic tracing algorithm in the Ultra-Tracer framework. With its help, neuronal signals in low-TDBs can be traced by the automatic algorithm and in high-TDBs may be reconstructed by annotators. 12732 training samples and 5342 test samples are constructed on neuron images of a whole mouse brain. The 3D-SSM achieves classification accuracy rates 87.04% on the training set and 84.07% on the test set. Furthermore, the trained 3D-SSM is tested on samples from another whole mouse brain and its accuracy rate is 83.21%.

Ensemble Learning-Based Pulse Signal Recognition: Classification Model Development Study.

BACKGROUND: In pulse signal analysis and identification, time domain and time frequency domain analysis methods can obtain interpretable structured data and build classification models using traditional machine learning methods. Unstructured data, such as pulse signals, contain rich information about the state of the cardiovascular system, and local features of unstructured data can be extracted and classified using deep learning. OBJECTIVE: The objective of this paper was to comprehensively use machine learning and deep learning classification methods to fully exploit the information about pulse signals. METHODS: Structured data were obtained by using time domain and time frequency domain analysis methods. A classification model was built using a support vector machine (SVM), a deep convolutional neural network (DCNN) kernel was used to extract local features of the unstructured data, and the stacking method was used to fuse the above classification results for decision making. RESULTS: The highest average accuracy of 0.7914 was obtained using only a single classifier, while the average accuracy obtained using the ensemble learning approach was 0.8330. CONCLUSIONS: Ensemble learning can effectively use information from structured and unstructured data to improve classification accuracy through decision-level fusion. This study provides a new idea and method for pulse signal classification, which is of practical value for pulse diagnosis objectification.

DeepBindPoc: a deep learning method to rank ligand binding pockets using molecular vector representation.

Accurate identification of ligand-binding pockets in a protein is important for structure-based drug design. In recent years, several deep learning models were developed to learn important physical-chemical and spatial information to predict ligand-binding pockets in a protein. However, ranking the native ligand binding pockets from a pool of predicted pockets is still a hard task for computational molecular biologists using a single web-based tool. Hence, we believe, by using closer to real application data set as training and by providing ligand information, an enhanced model to identify accurate pockets can be obtained. In this article, we propose a new deep learning method called DeepBindPoc for identifying and ranking ligand-binding pockets in proteins. The model is built by using information about the binding pocket and associated ligand. We take advantage of the mol2vec tool to represent both the given ligand and pocket as vectors to construct a densely fully connected layer model. During the training, important features for pocket-ligand binding are automatically extracted and high-level information is preserved appropriately. DeepBindPoc demonstrated a strong complementary advantage for the detection of native-like pockets when combined with traditional popular methods, such as fpocket and P2Rank. The proposed method is extensively tested and validated with standard procedures on multiple datasets, including a dataset with G-protein Coupled receptors. The systematic testing and validation of our method suggest that DeepBindPoc is a valuable tool to rank near-native pockets for theoretically modeled protein with unknown experimental active site but have known ligand. The DeepBindPoc model described in this article is available at GitHub (https://github.com/haiping1010/DeepBindPoc) and the webserver is available at (http://cbblab.siat.ac.cn/DeepBindPoc/index.php).