Chinese Clinical Named Entity Recognition(CNER)is a crucial step in extracting medical information and is of great significance in promoting medical informatization.However,CNER poses challenges due to the specificity...Chinese Clinical Named Entity Recognition(CNER)is a crucial step in extracting medical information and is of great significance in promoting medical informatization.However,CNER poses challenges due to the specificity of clinical terminology,the complexity of Chinese text semantics,and the uncertainty of Chinese entity boundaries.To address these issues,we propose an improved CNER model,which is based on multi-feature fusion and multi-scale local context enhancement.The model simultaneously fuses multi-feature representations of pinyin,radical,Part of Speech(POS),word boundary with BERT deep contextual representations to enhance the semantic representation of text for more effective entity recognition.Furthermore,to address the model’s limitation of focusing just on global features,we incorporate Convolutional Neural Networks(CNNs)with various kernel sizes to capture multi-scale local features of the text and enhance the model’s comprehension of the text.Finally,we integrate the obtained global and local features,and employ multi-head attention mechanism(MHA)extraction to enhance the model’s focus on characters associated with medical entities,hence boosting the model’s performance.We obtained 92.74%,and 87.80%F1 scores on the two CNER benchmark datasets,CCKS2017 and CCKS2019,respectively.The results demonstrate that our model outperforms the latest models in CNER,showcasing its outstanding overall performance.It can be seen that the CNER model proposed in this study has an important application value in constructing clinical medical knowledge graph and intelligent Q&A system.展开更多
In recent years,in order to achieve the goal of“carbon peaking and carbon neutralization”,many countries have focused on the development of clean energy,and the prediction of photovoltaic power generation has become...In recent years,in order to achieve the goal of“carbon peaking and carbon neutralization”,many countries have focused on the development of clean energy,and the prediction of photovoltaic power generation has become a hot research topic.However,many traditional methods only use meteorological factors such as temperature and irradiance as the features of photovoltaic power generation,and they rarely consider the multi-features fusion methods for power prediction.This paper first preprocesses abnormal data points and missing values in the data from 18 power stations in Northwest China,and then carries out correlation analysis to screen out 8 meteorological features as the most relevant to power generation.Next,the historical generating power and 8 meteorological features are fused in different ways to construct three types of experimental datasets.Finally,traditional time series prediction methods,such as Recurrent Neural Network(RNN),Convolution Neural Network(CNN)combined with eXtreme Gradient Boosting(XGBoost),are applied to study the impact of different feature fusion methods on power prediction.The results show that the prediction accuracy of Long Short-Term Memory(LSTM),stacked Long Short-Term Memory(stacked LSTM),Bi-directional LSTM(Bi-LSTM),Temporal Convolutional Network(TCN),and XGBoost algorithms can be greatly improved by the method of integrating historical generation power and meteorological features.Therefore,the feature fusion based photovoltaic power prediction method proposed in this paper is of great significance to the development of the photovoltaic power generation industry.展开更多
In order to solve the shortcomings of current fatigue detection methods such as low accuracy or poor real-time performance,a fatigue detection method based on multi-feature fusion is proposed.Firstly,the HOG face dete...In order to solve the shortcomings of current fatigue detection methods such as low accuracy or poor real-time performance,a fatigue detection method based on multi-feature fusion is proposed.Firstly,the HOG face detection algorithm and KCF target tracking algorithm are integrated and deformable convolutional neural network is introduced to identify the state of extracted eyes and mouth,fast track the detected faces and extract continuous and stable target faces for more efficient extraction.Then the head pose algorithm is introduced to detect the driver’s head in real time and obtain the driver’s head state information.Finally,a multi-feature fusion fatigue detection method is proposed based on the state of the eyes,mouth and head.According to the experimental results,the proposed method can detect the driver’s fatigue state in real time with high accuracy and good robustness compared with the current fatigue detection algorithms.展开更多
Sentiment analysis in Chinese classical poetry has become a prominent topic in historical and cultural tracing,ancient literature research,etc.However,the existing research on sentiment analysis is relatively small.It...Sentiment analysis in Chinese classical poetry has become a prominent topic in historical and cultural tracing,ancient literature research,etc.However,the existing research on sentiment analysis is relatively small.It does not effectively solve the problems such as the weak feature extraction ability of poetry text,which leads to the low performance of the model on sentiment analysis for Chinese classical poetry.In this research,we offer the SA-Model,a poetic sentiment analysis model.SA-Model firstly extracts text vector information and fuses it through Bidirectional encoder representation from transformers-Whole word masking-extension(BERT-wwmext)and Enhanced representation through knowledge integration(ERNIE)to enrich text vector information;Secondly,it incorporates numerous encoders to remove text features at multiple levels,thereby increasing text feature information,improving text semantics accuracy,and enhancing the model’s learning and generalization capabilities;finally,multi-feature fusion poetry sentiment analysis model is constructed.The feasibility and accuracy of the model are validated through the ancient poetry sentiment corpus.Compared with other baseline models,the experimental findings indicate that SA-Model may increase the accuracy of text semantics and hence improve the capability of poetry sentiment analysis.展开更多
The traditional recommendation algorithm represented by the collaborative filtering algorithm is the most classical and widely recommended algorithm in the practical industry.Most book recommendation systems also use ...The traditional recommendation algorithm represented by the collaborative filtering algorithm is the most classical and widely recommended algorithm in the practical industry.Most book recommendation systems also use this algorithm.However,the traditional recommendation algorithm represented by the collaborative filtering algorithm cannot deal with the data sparsity well.This algorithm only uses the shallow feature design of the interaction between readers and books,so it fails to achieve the high-level abstract learning of the relevant attribute features of readers and books,leading to a decline in recommendation performance.Given the above problems,this study uses deep learning technology to model readers’book borrowing probability.It builds a recommendation system model through themulti-layer neural network and inputs the features extracted from readers and books into the network,and then profoundly integrates the features of readers and books through the multi-layer neural network.The hidden deep interaction between readers and books is explored accordingly.Thus,the quality of book recommendation performance will be significantly improved.In the experiment,the evaluation indexes ofHR@10,MRR,andNDCGof the deep neural network recommendation model constructed in this paper are higher than those of the traditional recommendation algorithm,which verifies the effectiveness of the model in the book recommendation.展开更多
Credit Card Fraud Detection(CCFD)is an essential technology for banking institutions to control fraud risks and safeguard their reputation.Class imbalance and insufficient representation of feature data relating to cr...Credit Card Fraud Detection(CCFD)is an essential technology for banking institutions to control fraud risks and safeguard their reputation.Class imbalance and insufficient representation of feature data relating to credit card transactions are two prevalent issues in the current study field of CCFD,which significantly impact classification models’performance.To address these issues,this research proposes a novel CCFD model based on Multifeature Fusion and Generative Adversarial Networks(MFGAN).The MFGAN model consists of two modules:a multi-feature fusion module for integrating static and dynamic behavior data of cardholders into a unified highdimensional feature space,and a balance module based on the generative adversarial network to decrease the class imbalance ratio.The effectiveness of theMFGAN model is validated on two actual credit card datasets.The impacts of different class balance ratios on the performance of the four resamplingmodels are analyzed,and the contribution of the two different modules to the performance of the MFGAN model is investigated via ablation experiments.Experimental results demonstrate that the proposed model does better than state-of-the-art models in terms of recall,F1,and Area Under the Curve(AUC)metrics,which means that the MFGAN model can help banks find more fraudulent transactions and reduce fraud losses.展开更多
The deployment of vehicle micro-motors has witnessed an expansion owing to the progression in electrification and intelligent technologies.However,some micro-motors may exhibit design deficiencies,component wear,assem...The deployment of vehicle micro-motors has witnessed an expansion owing to the progression in electrification and intelligent technologies.However,some micro-motors may exhibit design deficiencies,component wear,assembly errors,and other imperfections that may arise during the design or manufacturing phases.Conse-quently,these micro-motors might generate anomalous noises during their operation,consequently exerting a substantial adverse influence on the overall comfort of drivers and passengers.Automobile micro-motors exhibit a diverse array of structural variations,consequently leading to the manifestation of a multitude of distinctive auditory irregularities.To address the identification of diverse forms of abnormal noise,this research presents a novel approach rooted in the utilization of vibro-acoustic fusion-convolutional neural network(VAF-CNN).This method entails the deployment of distinct network branches,each serving to capture disparate features from the multi-sensor data,all the while considering the auditory perception traits inherent in the human auditory sys-tem.The intermediary layer integrates the concept of adaptive weighting of multi-sensor features,thus affording a calibration mechanism for the features hailing from multiple sensors,thereby enabling a further refinement of features within the branch network.For optimal model efficacy,a feature fusion mechanism is implemented in the concluding layer.To substantiate the efficacy of the proposed approach,this paper initially employs an augmented data methodology inspired by modified SpecAugment,applied to the dataset of abnormal noise sam-ples,encompassing scenarios both with and without in-vehicle interior noise.This serves to mitigate the issue of limited sample availability.Subsequent comparative evaluations are executed,contrasting the performance of the model founded upon single-sensor data against other feature fusion models reliant on multi-sensor data.The experimental results substantiate that the suggested methodology yields heightened recognition accuracy and greater resilience against interference.Moreover,it holds notable practical significance in the engineering domain,as it furnishes valuable support for the targeted management of noise emanating from vehicle micro-motors.展开更多
针对自动驾驶路面上目标漏检和错检的问题,提出一种基于改进Centerfusion的自动驾驶3D目标检测模型。该模型通过将相机信息和雷达特征融合,构成多通道特征数据输入,从而增强目标检测网络的鲁棒性,减少漏检问题;为了能够得到更加准确丰富...针对自动驾驶路面上目标漏检和错检的问题,提出一种基于改进Centerfusion的自动驾驶3D目标检测模型。该模型通过将相机信息和雷达特征融合,构成多通道特征数据输入,从而增强目标检测网络的鲁棒性,减少漏检问题;为了能够得到更加准确丰富的3D目标检测信息,引入了改进的注意力机制,用于增强视锥网格中的雷达点云和视觉信息融合;使用改进的损失函数优化边框预测的准确度。在Nuscenes数据集上进行模型验证和对比,实验结果表明,相较于传统的Centerfusion模型,提出的模型平均检测精度均值(mean Average Precision,mAP)提高了1.3%,Nuscenes检测分数(Nuscenes Detection Scores,NDS)提高了1.2%。展开更多
Coronavirus 2019(COVID-19)is the current global buzzword,putting the world at risk.The pandemic’s exponential expansion of infected COVID-19 patients has challenged the medical field’s resources,which are already fe...Coronavirus 2019(COVID-19)is the current global buzzword,putting the world at risk.The pandemic’s exponential expansion of infected COVID-19 patients has challenged the medical field’s resources,which are already few.Even established nations would not be in a perfect position to manage this epidemic correctly,leaving emerging countries and countries that have not yet begun to grow to address the problem.These problems can be solved by using machine learning models in a realistic way,such as by using computer-aided images during medical examinations.These models help predict the effects of the disease outbreak and help detect the effects in the coming days.In this paper,Multi-Features Decease Analysis(MFDA)is used with different ensemble classifiers to diagnose the disease’s impact with the help of Computed Tomography(CT)scan images.There are various features associated with chest CT images,which help know the possibility of an individual being affected and how COVID-19 will affect the persons suffering from pneumonia.The current study attempts to increase the precision of the diagnosis model by evaluating various feature sets and choosing the best combination for better results.The model’s performance is assessed using Receiver Operating Characteristic(ROC)curve,the Root Mean Square Error(RMSE),and the Confusion Matrix.It is observed from the resultant outcome that the performance of the proposed model has exhibited better efficient.展开更多
Nickel-based superalloys are extensively used in the crucial hot-section components of industrial gas turbines,aeronautics,and astronautics because of their excellent mechanical properties and corrosion resistance at ...Nickel-based superalloys are extensively used in the crucial hot-section components of industrial gas turbines,aeronautics,and astronautics because of their excellent mechanical properties and corrosion resistance at high temperatures.Fusion welding serves as an effective means for joining and repairing these alloys;however,fusion welding-induced liquation cracking has been a challenging issue.This paper comprehensively reviewed recent liquation cracking,discussing the formation mechanisms,cracking criteria,and remedies.In recent investigations,regulating material composition,changing the preweld heat treatment of the base metal,optimizing the welding process parameters,and applying auxiliary control methods are effective strategies for mitigating cracks.To promote the application of nickel-based superalloys,further research on the combination impact of multiple elements on cracking prevention and specific quantitative criteria for liquation cracking is necessary.展开更多
Laser powder bed fusion(L-PBF)of Mg alloys has provided tremendous opportunities for customized production of aeronautical and medical parts.Layer thickness(LT)is of great significance to the L-PBF process but has not...Laser powder bed fusion(L-PBF)of Mg alloys has provided tremendous opportunities for customized production of aeronautical and medical parts.Layer thickness(LT)is of great significance to the L-PBF process but has not been studied for Mg alloys.In this study,WE43 Mg alloy bulk cubes,porous scaffolds,and thin walls with layer thicknesses of 10,20,30,and 40μm were fabricated.The required laser energy input increased with increasing layer thickness and was different for the bulk cubes and porous scaffolds.Porosity tended to occur at the connection joints in porous scaffolds for LT40 and could be eliminated by reducing the laser energy input.For thin wall parts,a large overhang angle or a small wall thickness resulted in porosity when a large layer thicknesses was used,and the porosity disappeared by reducing the layer thickness or laser energy input.A deeper keyhole penetration was found in all occasions with porosity,explaining the influence of layer thickness,geometrical structure,and laser energy input on the porosity.All the samples achieved a high fusion quality with a relative density of over 99.5%using the optimized laser energy input.The increased layer thickness resulted to more precipitation phases,finer grain sizes and decreased grain texture.With the similar high fusion quality,the tensile strength and elongation of bulk samples were significantly improved from 257 MPa and 1.41%with the 10μm layer to 287 MPa and 15.12%with the 40μm layer,in accordance with the microstructural change.The effect of layer thickness on the compressive properties of porous scaffolds was limited.However,the corrosion rate of bulk samples accelerated with increasing the layer thickness,mainly attributed to the increased number of precipitation phases.展开更多
Multi-material laser-based powder bed fusion (PBF-LB) allows manufacturing of parts with 3-dimensional gradient and additional functionality in a single step. This research focuses on the combination of thermally-cond...Multi-material laser-based powder bed fusion (PBF-LB) allows manufacturing of parts with 3-dimensional gradient and additional functionality in a single step. This research focuses on the combination of thermally-conductive CuCr1Zr with hard M300 tool steel.Two interface configurations of M300 on CuCr1Zr and CuCr1Zr on M300 were investigated. Ultra-fine grains form at the interface due to the low mutual solubility of Cu and steel. The material mixing zone size is dependent on the configurations and tunable in the range of0.1–0.3 mm by introducing a separate set of parameters for the interface layers. Microcracks and pores mainly occur in the transition zone.Regardless of these defects, the thermal diffusivity of bimetallic parts with 50vol% of CuCr1Zr significantly increases by 70%–150%compared to pure M300. The thermal diffusivity of CuCr1Zr and the hardness of M300 steel can be enhanced simultaneously by applying the aging heat treatment.展开更多
The perception module of advanced driver assistance systems plays a vital role.Perception schemes often use a single sensor for data processing and environmental perception or adopt the information processing results ...The perception module of advanced driver assistance systems plays a vital role.Perception schemes often use a single sensor for data processing and environmental perception or adopt the information processing results of various sensors for the fusion of the detection layer.This paper proposes a multi-scale and multi-sensor data fusion strategy in the front end of perception and accomplishes a multi-sensor function disparity map generation scheme.A binocular stereo vision sensor composed of two cameras and a light deterction and ranging(LiDAR)sensor is used to jointly perceive the environment,and a multi-scale fusion scheme is employed to improve the accuracy of the disparity map.This solution not only has the advantages of dense perception of binocular stereo vision sensors but also considers the perception accuracy of LiDAR sensors.Experiments demonstrate that the multi-scale multi-sensor scheme proposed in this paper significantly improves disparity map estimation.展开更多
Fusing hand-based features in multi-modal biometric recognition enhances anti-spoofing capabilities.Additionally,it leverages inter-modal correlation to enhance recognition performance.Concurrently,the robustness and ...Fusing hand-based features in multi-modal biometric recognition enhances anti-spoofing capabilities.Additionally,it leverages inter-modal correlation to enhance recognition performance.Concurrently,the robustness and recognition performance of the system can be enhanced through judiciously leveraging the correlation among multimodal features.Nevertheless,two issues persist in multi-modal feature fusion recognition:Firstly,the enhancement of recognition performance in fusion recognition has not comprehensively considered the inter-modality correlations among distinct modalities.Secondly,during modal fusion,improper weight selection diminishes the salience of crucial modal features,thereby diminishing the overall recognition performance.To address these two issues,we introduce an enhanced DenseNet multimodal recognition network founded on feature-level fusion.The information from the three modalities is fused akin to RGB,and the input network augments the correlation between modes through channel correlation.Within the enhanced DenseNet network,the Efficient Channel Attention Network(ECA-Net)dynamically adjusts the weight of each channel to amplify the salience of crucial information in each modal feature.Depthwise separable convolution markedly reduces the training parameters and further enhances the feature correlation.Experimental evaluations were conducted on four multimodal databases,comprising six unimodal databases,including multispectral palmprint and palm vein databases from the Chinese Academy of Sciences.The Equal Error Rates(EER)values were 0.0149%,0.0150%,0.0099%,and 0.0050%,correspondingly.In comparison to other network methods for palmprint,palm vein,and finger vein fusion recognition,this approach substantially enhances recognition performance,rendering it suitable for high-security environments with practical applicability.The experiments in this article utilized amodest sample database comprising 200 individuals.The subsequent phase involves preparing for the extension of the method to larger databases.展开更多
The existingmultipath routing in Software Defined Network (SDN) is relatively blind and inefficient, and there is alack of cooperation between the terminal and network sides, making it difficult to achieve dynamic ada...The existingmultipath routing in Software Defined Network (SDN) is relatively blind and inefficient, and there is alack of cooperation between the terminal and network sides, making it difficult to achieve dynamic adaptationof service requirements and network resources. To address these issues, we propose a multi-constraint pathoptimization scheme based on information fusion in SDN. The proposed scheme collects network topology andnetwork state information on the network side and computes disjoint paths between end hosts. It uses the FuzzyAnalytic Hierarchy Process (FAHP) to calculate the weight coefficients of multiple constrained parameters andconstructs a composite quality evaluation function for the paths to determine the priority of the disjoint paths. TheSDN controller extracts the service attributes by analyzing the packet header and selects the optimal path for flowrule forwarding. Furthermore, the service attributes are fed back to the path composite quality evaluation function,and the path priority is dynamically adjusted to achieve dynamic adaptation between service requirements andnetwork status. By continuously monitoring and analyzing the service attributes, the scheme can ensure optimalrouting decisions in response to varying network conditions and evolving service demands. The experimentalresults demonstrated that the proposed scheme can effectively improve average throughput and link utilizationwhile meeting the Quality of Service (QoS) requirements of various applications.展开更多
Due to the selective absorption of light and the existence of a large number of floating media in sea water, underwater images often suffer from color casts and detail blurs. It is therefore necessary to perform color...Due to the selective absorption of light and the existence of a large number of floating media in sea water, underwater images often suffer from color casts and detail blurs. It is therefore necessary to perform color correction and detail restoration. However,the existing enhancement algorithms cannot achieve the desired results. In order to solve the above problems, this paper proposes a multi-stream feature fusion network. First, an underwater image is preprocessed to obtain potential information from the illumination stream, color stream and structure stream by histogram equalization with contrast limitation, gamma correction and white balance, respectively. Next, these three streams and the original raw stream are sent to the residual blocks to extract the features. The features will be subsequently fused. It can enhance feature representation in underwater images. In the meantime, a composite loss function including three terms is used to ensure the quality of the enhanced image from the three aspects of color balance, structure preservation and image smoothness. Therefore, the enhanced image is more in line with human visual perception.Finally, the effectiveness of the proposed method is verified by comparison experiments with many stateof-the-art underwater image enhancement algorithms. Experimental results show that the proposed method provides superior results over them in terms of MSE,PSNR, SSIM, UIQM and UCIQE, and the enhanced images are more similar to their ground truth images.展开更多
Driving fatigue is a physiological phenomenon that often occurs during driving.After the driver enters a fatigued state,the attentionis lax,the response is slow,and the ability todeal with emergencies is significantly...Driving fatigue is a physiological phenomenon that often occurs during driving.After the driver enters a fatigued state,the attentionis lax,the response is slow,and the ability todeal with emergencies is significantly reduced,which can easily cause traffic accidents.Therefore,studying driver fatigue detectionmethods is significant in ensuring safe driving.However,the fatigue state of actual drivers is easily interfered with by the external environment(glasses and light),which leads to many problems,such as weak reliability of fatigue driving detection.Moreover,fatigue is a slow process,first manifested in physiological signals and then reflected in human face images.To improve the accuracy and stability of fatigue detection,this paper proposed a driver fatigue detection method based on image information and physiological information,designed a fatigue driving detection device,built a simulation driving experiment platform,and collected facial as well as physiological information of drivers during driving.Finally,the effectiveness of the fatigue detection method was evaluated.Eye movement feature parameters and physiological signal features of drivers’fatigue levels were extracted.The driver fatigue detection model was trained to classify fatigue and non-fatigue states based on the extracted features.Accuracy rates of the image,electroencephalogram(EEG),and blood oxygen signals were 86%,82%,and 71%,separately.Information fusion theory was presented to facilitate the fatigue detection effect;the fatigue features were fused using multiple kernel learning and typical correlation analysis methods to increase the detection accuracy to 94%.It can be seen that the fatigue driving detectionmethod based onmulti-source feature fusion effectively detected driver fatigue state,and the accuracy rate was higher than that of a single information source.In summary,fatigue drivingmonitoring has broad development prospects and can be used in traffic accident prevention and wearable driver fatigue recognition.展开更多
Because of their economy and applicability,high-power thyristor devices are widely used in the power supply systems for large fusion devices.When high-dose neutrons produced by deuterium–tritium(D–T)fusion reactions...Because of their economy and applicability,high-power thyristor devices are widely used in the power supply systems for large fusion devices.When high-dose neutrons produced by deuterium–tritium(D–T)fusion reactions are irradiated on a thyristor device for a long time,the electrical characteristics of the device change,which may eventually cause irreversible damage.In this study,with the thyristor switch of the commutation circuit in the quench protection system(QPS)of a fusion device as the study object,the relationship between the internal physical structure and external electrical parameters of the irradiated thyristor is established.Subsequently,a series of targeted thyristor physical simulations and neutron irradiation experiments are conducted to verify the accuracy of the theoretical analysis.In addition,the effect of irradiated thyristor electrical characteristic changes on the entire QPS is studied by accurate simulation,providing valuable guidelines for the maintenance and renovation of the QPS.展开更多
Heavy Ion Fusion makes use of the Relativistic Heavy Ion Collider at Brookhaven National Lab and the Large Hadron Collider in Geneva, Switzerland for Inertial Confinement Fusion. Two Storage Rings, which may or may no...Heavy Ion Fusion makes use of the Relativistic Heavy Ion Collider at Brookhaven National Lab and the Large Hadron Collider in Geneva, Switzerland for Inertial Confinement Fusion. Two Storage Rings, which may or may not initially be needed, added to each of the Colliders increases the intensity of the Heavy Ion Beams making it comparable to the Total Energy delivered to the DT target by the National Ignition Facility at the Lawrence Livermore Lab. The basic Physics involved gives Heavy Ion Fusion an advantage over Laser Fusion because heavy ions have greater penetration power than photons. The Relativistic Heavy Ion Collider can be used as a Prototype Heavy Ion Fusion Reactor for the Large Hadron Collider.展开更多
基金This study was supported by the National Natural Science Foundation of China(61911540482 and 61702324).
文摘Chinese Clinical Named Entity Recognition(CNER)is a crucial step in extracting medical information and is of great significance in promoting medical informatization.However,CNER poses challenges due to the specificity of clinical terminology,the complexity of Chinese text semantics,and the uncertainty of Chinese entity boundaries.To address these issues,we propose an improved CNER model,which is based on multi-feature fusion and multi-scale local context enhancement.The model simultaneously fuses multi-feature representations of pinyin,radical,Part of Speech(POS),word boundary with BERT deep contextual representations to enhance the semantic representation of text for more effective entity recognition.Furthermore,to address the model’s limitation of focusing just on global features,we incorporate Convolutional Neural Networks(CNNs)with various kernel sizes to capture multi-scale local features of the text and enhance the model’s comprehension of the text.Finally,we integrate the obtained global and local features,and employ multi-head attention mechanism(MHA)extraction to enhance the model’s focus on characters associated with medical entities,hence boosting the model’s performance.We obtained 92.74%,and 87.80%F1 scores on the two CNER benchmark datasets,CCKS2017 and CCKS2019,respectively.The results demonstrate that our model outperforms the latest models in CNER,showcasing its outstanding overall performance.It can be seen that the CNER model proposed in this study has an important application value in constructing clinical medical knowledge graph and intelligent Q&A system.
基金supported by the State Grid Gansu Electric Power Research Institute(Nos.SGGSKY00WYJS2100164 and 52272220002W).
文摘In recent years,in order to achieve the goal of“carbon peaking and carbon neutralization”,many countries have focused on the development of clean energy,and the prediction of photovoltaic power generation has become a hot research topic.However,many traditional methods only use meteorological factors such as temperature and irradiance as the features of photovoltaic power generation,and they rarely consider the multi-features fusion methods for power prediction.This paper first preprocesses abnormal data points and missing values in the data from 18 power stations in Northwest China,and then carries out correlation analysis to screen out 8 meteorological features as the most relevant to power generation.Next,the historical generating power and 8 meteorological features are fused in different ways to construct three types of experimental datasets.Finally,traditional time series prediction methods,such as Recurrent Neural Network(RNN),Convolution Neural Network(CNN)combined with eXtreme Gradient Boosting(XGBoost),are applied to study the impact of different feature fusion methods on power prediction.The results show that the prediction accuracy of Long Short-Term Memory(LSTM),stacked Long Short-Term Memory(stacked LSTM),Bi-directional LSTM(Bi-LSTM),Temporal Convolutional Network(TCN),and XGBoost algorithms can be greatly improved by the method of integrating historical generation power and meteorological features.Therefore,the feature fusion based photovoltaic power prediction method proposed in this paper is of great significance to the development of the photovoltaic power generation industry.
文摘In order to solve the shortcomings of current fatigue detection methods such as low accuracy or poor real-time performance,a fatigue detection method based on multi-feature fusion is proposed.Firstly,the HOG face detection algorithm and KCF target tracking algorithm are integrated and deformable convolutional neural network is introduced to identify the state of extracted eyes and mouth,fast track the detected faces and extract continuous and stable target faces for more efficient extraction.Then the head pose algorithm is introduced to detect the driver’s head in real time and obtain the driver’s head state information.Finally,a multi-feature fusion fatigue detection method is proposed based on the state of the eyes,mouth and head.According to the experimental results,the proposed method can detect the driver’s fatigue state in real time with high accuracy and good robustness compared with the current fatigue detection algorithms.
文摘Sentiment analysis in Chinese classical poetry has become a prominent topic in historical and cultural tracing,ancient literature research,etc.However,the existing research on sentiment analysis is relatively small.It does not effectively solve the problems such as the weak feature extraction ability of poetry text,which leads to the low performance of the model on sentiment analysis for Chinese classical poetry.In this research,we offer the SA-Model,a poetic sentiment analysis model.SA-Model firstly extracts text vector information and fuses it through Bidirectional encoder representation from transformers-Whole word masking-extension(BERT-wwmext)and Enhanced representation through knowledge integration(ERNIE)to enrich text vector information;Secondly,it incorporates numerous encoders to remove text features at multiple levels,thereby increasing text feature information,improving text semantics accuracy,and enhancing the model’s learning and generalization capabilities;finally,multi-feature fusion poetry sentiment analysis model is constructed.The feasibility and accuracy of the model are validated through the ancient poetry sentiment corpus.Compared with other baseline models,the experimental findings indicate that SA-Model may increase the accuracy of text semantics and hence improve the capability of poetry sentiment analysis.
基金This work was partly supported by the Basic Ability Improvement Project for Young andMiddle-aged Teachers in Guangxi Colleges andUniversities(2021KY1800,2021KY1804).
文摘The traditional recommendation algorithm represented by the collaborative filtering algorithm is the most classical and widely recommended algorithm in the practical industry.Most book recommendation systems also use this algorithm.However,the traditional recommendation algorithm represented by the collaborative filtering algorithm cannot deal with the data sparsity well.This algorithm only uses the shallow feature design of the interaction between readers and books,so it fails to achieve the high-level abstract learning of the relevant attribute features of readers and books,leading to a decline in recommendation performance.Given the above problems,this study uses deep learning technology to model readers’book borrowing probability.It builds a recommendation system model through themulti-layer neural network and inputs the features extracted from readers and books into the network,and then profoundly integrates the features of readers and books through the multi-layer neural network.The hidden deep interaction between readers and books is explored accordingly.Thus,the quality of book recommendation performance will be significantly improved.In the experiment,the evaluation indexes ofHR@10,MRR,andNDCGof the deep neural network recommendation model constructed in this paper are higher than those of the traditional recommendation algorithm,which verifies the effectiveness of the model in the book recommendation.
基金supported by the National Key R&D Program of China(Nos.2022YFB3104103,and 2019QY1406)the National Natural Science Foundation of China(Nos.61732022,61732004,61672020,and 62072131).
文摘Credit Card Fraud Detection(CCFD)is an essential technology for banking institutions to control fraud risks and safeguard their reputation.Class imbalance and insufficient representation of feature data relating to credit card transactions are two prevalent issues in the current study field of CCFD,which significantly impact classification models’performance.To address these issues,this research proposes a novel CCFD model based on Multifeature Fusion and Generative Adversarial Networks(MFGAN).The MFGAN model consists of two modules:a multi-feature fusion module for integrating static and dynamic behavior data of cardholders into a unified highdimensional feature space,and a balance module based on the generative adversarial network to decrease the class imbalance ratio.The effectiveness of theMFGAN model is validated on two actual credit card datasets.The impacts of different class balance ratios on the performance of the four resamplingmodels are analyzed,and the contribution of the two different modules to the performance of the MFGAN model is investigated via ablation experiments.Experimental results demonstrate that the proposed model does better than state-of-the-art models in terms of recall,F1,and Area Under the Curve(AUC)metrics,which means that the MFGAN model can help banks find more fraudulent transactions and reduce fraud losses.
基金The author received the funding from Sichuan Natural Science Foundation(2022NSFSC1892).
文摘The deployment of vehicle micro-motors has witnessed an expansion owing to the progression in electrification and intelligent technologies.However,some micro-motors may exhibit design deficiencies,component wear,assembly errors,and other imperfections that may arise during the design or manufacturing phases.Conse-quently,these micro-motors might generate anomalous noises during their operation,consequently exerting a substantial adverse influence on the overall comfort of drivers and passengers.Automobile micro-motors exhibit a diverse array of structural variations,consequently leading to the manifestation of a multitude of distinctive auditory irregularities.To address the identification of diverse forms of abnormal noise,this research presents a novel approach rooted in the utilization of vibro-acoustic fusion-convolutional neural network(VAF-CNN).This method entails the deployment of distinct network branches,each serving to capture disparate features from the multi-sensor data,all the while considering the auditory perception traits inherent in the human auditory sys-tem.The intermediary layer integrates the concept of adaptive weighting of multi-sensor features,thus affording a calibration mechanism for the features hailing from multiple sensors,thereby enabling a further refinement of features within the branch network.For optimal model efficacy,a feature fusion mechanism is implemented in the concluding layer.To substantiate the efficacy of the proposed approach,this paper initially employs an augmented data methodology inspired by modified SpecAugment,applied to the dataset of abnormal noise sam-ples,encompassing scenarios both with and without in-vehicle interior noise.This serves to mitigate the issue of limited sample availability.Subsequent comparative evaluations are executed,contrasting the performance of the model founded upon single-sensor data against other feature fusion models reliant on multi-sensor data.The experimental results substantiate that the suggested methodology yields heightened recognition accuracy and greater resilience against interference.Moreover,it holds notable practical significance in the engineering domain,as it furnishes valuable support for the targeted management of noise emanating from vehicle micro-motors.
文摘针对自动驾驶路面上目标漏检和错检的问题,提出一种基于改进Centerfusion的自动驾驶3D目标检测模型。该模型通过将相机信息和雷达特征融合,构成多通道特征数据输入,从而增强目标检测网络的鲁棒性,减少漏检问题;为了能够得到更加准确丰富的3D目标检测信息,引入了改进的注意力机制,用于增强视锥网格中的雷达点云和视觉信息融合;使用改进的损失函数优化边框预测的准确度。在Nuscenes数据集上进行模型验证和对比,实验结果表明,相较于传统的Centerfusion模型,提出的模型平均检测精度均值(mean Average Precision,mAP)提高了1.3%,Nuscenes检测分数(Nuscenes Detection Scores,NDS)提高了1.2%。
基金This work was supported by the Deanship of Scientific Research,Vice Presidency for Graduate Studies and Scientific Research,King Faisal University,Saudi Arabia(Project no.GRANT 324).
文摘Coronavirus 2019(COVID-19)is the current global buzzword,putting the world at risk.The pandemic’s exponential expansion of infected COVID-19 patients has challenged the medical field’s resources,which are already few.Even established nations would not be in a perfect position to manage this epidemic correctly,leaving emerging countries and countries that have not yet begun to grow to address the problem.These problems can be solved by using machine learning models in a realistic way,such as by using computer-aided images during medical examinations.These models help predict the effects of the disease outbreak and help detect the effects in the coming days.In this paper,Multi-Features Decease Analysis(MFDA)is used with different ensemble classifiers to diagnose the disease’s impact with the help of Computed Tomography(CT)scan images.There are various features associated with chest CT images,which help know the possibility of an individual being affected and how COVID-19 will affect the persons suffering from pneumonia.The current study attempts to increase the precision of the diagnosis model by evaluating various feature sets and choosing the best combination for better results.The model’s performance is assessed using Receiver Operating Characteristic(ROC)curve,the Root Mean Square Error(RMSE),and the Confusion Matrix.It is observed from the resultant outcome that the performance of the proposed model has exhibited better efficient.
基金financially supported by the National Science and Technology Major Project of China(No.J2019-VI-0004-0117)。
文摘Nickel-based superalloys are extensively used in the crucial hot-section components of industrial gas turbines,aeronautics,and astronautics because of their excellent mechanical properties and corrosion resistance at high temperatures.Fusion welding serves as an effective means for joining and repairing these alloys;however,fusion welding-induced liquation cracking has been a challenging issue.This paper comprehensively reviewed recent liquation cracking,discussing the formation mechanisms,cracking criteria,and remedies.In recent investigations,regulating material composition,changing the preweld heat treatment of the base metal,optimizing the welding process parameters,and applying auxiliary control methods are effective strategies for mitigating cracks.To promote the application of nickel-based superalloys,further research on the combination impact of multiple elements on cracking prevention and specific quantitative criteria for liquation cracking is necessary.
基金funded by the National Key Research and Development Program of China(2018YFE0104200)National Natural Science Foundation of China(51875310,52175274,82172065)Tsinghua Precision Medicine Foundation.
文摘Laser powder bed fusion(L-PBF)of Mg alloys has provided tremendous opportunities for customized production of aeronautical and medical parts.Layer thickness(LT)is of great significance to the L-PBF process but has not been studied for Mg alloys.In this study,WE43 Mg alloy bulk cubes,porous scaffolds,and thin walls with layer thicknesses of 10,20,30,and 40μm were fabricated.The required laser energy input increased with increasing layer thickness and was different for the bulk cubes and porous scaffolds.Porosity tended to occur at the connection joints in porous scaffolds for LT40 and could be eliminated by reducing the laser energy input.For thin wall parts,a large overhang angle or a small wall thickness resulted in porosity when a large layer thicknesses was used,and the porosity disappeared by reducing the layer thickness or laser energy input.A deeper keyhole penetration was found in all occasions with porosity,explaining the influence of layer thickness,geometrical structure,and laser energy input on the porosity.All the samples achieved a high fusion quality with a relative density of over 99.5%using the optimized laser energy input.The increased layer thickness resulted to more precipitation phases,finer grain sizes and decreased grain texture.With the similar high fusion quality,the tensile strength and elongation of bulk samples were significantly improved from 257 MPa and 1.41%with the 10μm layer to 287 MPa and 15.12%with the 40μm layer,in accordance with the microstructural change.The effect of layer thickness on the compressive properties of porous scaffolds was limited.However,the corrosion rate of bulk samples accelerated with increasing the layer thickness,mainly attributed to the increased number of precipitation phases.
基金supported by VTT Technical Research Centre of Finland,Aalto University,Aerosint SA,and partially from European Union Horizon 2020 (No.768775)。
文摘Multi-material laser-based powder bed fusion (PBF-LB) allows manufacturing of parts with 3-dimensional gradient and additional functionality in a single step. This research focuses on the combination of thermally-conductive CuCr1Zr with hard M300 tool steel.Two interface configurations of M300 on CuCr1Zr and CuCr1Zr on M300 were investigated. Ultra-fine grains form at the interface due to the low mutual solubility of Cu and steel. The material mixing zone size is dependent on the configurations and tunable in the range of0.1–0.3 mm by introducing a separate set of parameters for the interface layers. Microcracks and pores mainly occur in the transition zone.Regardless of these defects, the thermal diffusivity of bimetallic parts with 50vol% of CuCr1Zr significantly increases by 70%–150%compared to pure M300. The thermal diffusivity of CuCr1Zr and the hardness of M300 steel can be enhanced simultaneously by applying the aging heat treatment.
基金the National Key R&D Program of China(2018AAA0103103).
文摘The perception module of advanced driver assistance systems plays a vital role.Perception schemes often use a single sensor for data processing and environmental perception or adopt the information processing results of various sensors for the fusion of the detection layer.This paper proposes a multi-scale and multi-sensor data fusion strategy in the front end of perception and accomplishes a multi-sensor function disparity map generation scheme.A binocular stereo vision sensor composed of two cameras and a light deterction and ranging(LiDAR)sensor is used to jointly perceive the environment,and a multi-scale fusion scheme is employed to improve the accuracy of the disparity map.This solution not only has the advantages of dense perception of binocular stereo vision sensors but also considers the perception accuracy of LiDAR sensors.Experiments demonstrate that the multi-scale multi-sensor scheme proposed in this paper significantly improves disparity map estimation.
基金funded by the National Natural Science Foundation of China(61991413)the China Postdoctoral Science Foundation(2019M651142)+1 种基金the Natural Science Foundation of Liaoning Province(2021-KF-12-07)the Natural Science Foundations of Liaoning Province(2023-MS-322).
文摘Fusing hand-based features in multi-modal biometric recognition enhances anti-spoofing capabilities.Additionally,it leverages inter-modal correlation to enhance recognition performance.Concurrently,the robustness and recognition performance of the system can be enhanced through judiciously leveraging the correlation among multimodal features.Nevertheless,two issues persist in multi-modal feature fusion recognition:Firstly,the enhancement of recognition performance in fusion recognition has not comprehensively considered the inter-modality correlations among distinct modalities.Secondly,during modal fusion,improper weight selection diminishes the salience of crucial modal features,thereby diminishing the overall recognition performance.To address these two issues,we introduce an enhanced DenseNet multimodal recognition network founded on feature-level fusion.The information from the three modalities is fused akin to RGB,and the input network augments the correlation between modes through channel correlation.Within the enhanced DenseNet network,the Efficient Channel Attention Network(ECA-Net)dynamically adjusts the weight of each channel to amplify the salience of crucial information in each modal feature.Depthwise separable convolution markedly reduces the training parameters and further enhances the feature correlation.Experimental evaluations were conducted on four multimodal databases,comprising six unimodal databases,including multispectral palmprint and palm vein databases from the Chinese Academy of Sciences.The Equal Error Rates(EER)values were 0.0149%,0.0150%,0.0099%,and 0.0050%,correspondingly.In comparison to other network methods for palmprint,palm vein,and finger vein fusion recognition,this approach substantially enhances recognition performance,rendering it suitable for high-security environments with practical applicability.The experiments in this article utilized amodest sample database comprising 200 individuals.The subsequent phase involves preparing for the extension of the method to larger databases.
基金the National Key R&D Program of China(No.2021YFB2700800)the GHfund B(No.202302024490).
文摘The existingmultipath routing in Software Defined Network (SDN) is relatively blind and inefficient, and there is alack of cooperation between the terminal and network sides, making it difficult to achieve dynamic adaptationof service requirements and network resources. To address these issues, we propose a multi-constraint pathoptimization scheme based on information fusion in SDN. The proposed scheme collects network topology andnetwork state information on the network side and computes disjoint paths between end hosts. It uses the FuzzyAnalytic Hierarchy Process (FAHP) to calculate the weight coefficients of multiple constrained parameters andconstructs a composite quality evaluation function for the paths to determine the priority of the disjoint paths. TheSDN controller extracts the service attributes by analyzing the packet header and selects the optimal path for flowrule forwarding. Furthermore, the service attributes are fed back to the path composite quality evaluation function,and the path priority is dynamically adjusted to achieve dynamic adaptation between service requirements andnetwork status. By continuously monitoring and analyzing the service attributes, the scheme can ensure optimalrouting decisions in response to varying network conditions and evolving service demands. The experimentalresults demonstrated that the proposed scheme can effectively improve average throughput and link utilizationwhile meeting the Quality of Service (QoS) requirements of various applications.
基金supported by the national key research and development program (No.2020YFB1806608)Jiangsu natural science foundation for distinguished young scholars (No.BK20220054)。
文摘Due to the selective absorption of light and the existence of a large number of floating media in sea water, underwater images often suffer from color casts and detail blurs. It is therefore necessary to perform color correction and detail restoration. However,the existing enhancement algorithms cannot achieve the desired results. In order to solve the above problems, this paper proposes a multi-stream feature fusion network. First, an underwater image is preprocessed to obtain potential information from the illumination stream, color stream and structure stream by histogram equalization with contrast limitation, gamma correction and white balance, respectively. Next, these three streams and the original raw stream are sent to the residual blocks to extract the features. The features will be subsequently fused. It can enhance feature representation in underwater images. In the meantime, a composite loss function including three terms is used to ensure the quality of the enhanced image from the three aspects of color balance, structure preservation and image smoothness. Therefore, the enhanced image is more in line with human visual perception.Finally, the effectiveness of the proposed method is verified by comparison experiments with many stateof-the-art underwater image enhancement algorithms. Experimental results show that the proposed method provides superior results over them in terms of MSE,PSNR, SSIM, UIQM and UCIQE, and the enhanced images are more similar to their ground truth images.
基金the Fundamental Research Funds for the Central Universities(GrantNo.IR2021222)received by J.Sthe Future Science and Technology Innovation Team Project of HIT(216506)received by Q.W.
文摘Driving fatigue is a physiological phenomenon that often occurs during driving.After the driver enters a fatigued state,the attentionis lax,the response is slow,and the ability todeal with emergencies is significantly reduced,which can easily cause traffic accidents.Therefore,studying driver fatigue detectionmethods is significant in ensuring safe driving.However,the fatigue state of actual drivers is easily interfered with by the external environment(glasses and light),which leads to many problems,such as weak reliability of fatigue driving detection.Moreover,fatigue is a slow process,first manifested in physiological signals and then reflected in human face images.To improve the accuracy and stability of fatigue detection,this paper proposed a driver fatigue detection method based on image information and physiological information,designed a fatigue driving detection device,built a simulation driving experiment platform,and collected facial as well as physiological information of drivers during driving.Finally,the effectiveness of the fatigue detection method was evaluated.Eye movement feature parameters and physiological signal features of drivers’fatigue levels were extracted.The driver fatigue detection model was trained to classify fatigue and non-fatigue states based on the extracted features.Accuracy rates of the image,electroencephalogram(EEG),and blood oxygen signals were 86%,82%,and 71%,separately.Information fusion theory was presented to facilitate the fatigue detection effect;the fatigue features were fused using multiple kernel learning and typical correlation analysis methods to increase the detection accuracy to 94%.It can be seen that the fatigue driving detectionmethod based onmulti-source feature fusion effectively detected driver fatigue state,and the accuracy rate was higher than that of a single information source.In summary,fatigue drivingmonitoring has broad development prospects and can be used in traffic accident prevention and wearable driver fatigue recognition.
基金supported by the Fundamental Research Funds for the Central University(No.JZ2023HGTA0182)Comprehensive Research Facility for Fusion Technology Program of China(No.2018-000052-73-01-001228)。
文摘Because of their economy and applicability,high-power thyristor devices are widely used in the power supply systems for large fusion devices.When high-dose neutrons produced by deuterium–tritium(D–T)fusion reactions are irradiated on a thyristor device for a long time,the electrical characteristics of the device change,which may eventually cause irreversible damage.In this study,with the thyristor switch of the commutation circuit in the quench protection system(QPS)of a fusion device as the study object,the relationship between the internal physical structure and external electrical parameters of the irradiated thyristor is established.Subsequently,a series of targeted thyristor physical simulations and neutron irradiation experiments are conducted to verify the accuracy of the theoretical analysis.In addition,the effect of irradiated thyristor electrical characteristic changes on the entire QPS is studied by accurate simulation,providing valuable guidelines for the maintenance and renovation of the QPS.
文摘Heavy Ion Fusion makes use of the Relativistic Heavy Ion Collider at Brookhaven National Lab and the Large Hadron Collider in Geneva, Switzerland for Inertial Confinement Fusion. Two Storage Rings, which may or may not initially be needed, added to each of the Colliders increases the intensity of the Heavy Ion Beams making it comparable to the Total Energy delivered to the DT target by the National Ignition Facility at the Lawrence Livermore Lab. The basic Physics involved gives Heavy Ion Fusion an advantage over Laser Fusion because heavy ions have greater penetration power than photons. The Relativistic Heavy Ion Collider can be used as a Prototype Heavy Ion Fusion Reactor for the Large Hadron Collider.