TDSC-Net:一种基于注意力机制与特征融合的二维恒星光谱分类模型

面对信噪比较低的天体,传统一维光谱的分类效果很差。因此,从二维光谱出发,提出了结合注意力机制的特征融合模型TDSC-Net(two-dimensional spectra classification network)用于恒星分类。TDSC-Net通过完全相同的特征提取层分别对恒星蓝端和红端的二维光谱图像进行特征提取,之后针对这些特征进行融合,然后进行分类。本文实验中的恒星光谱数据选自LAMOST(the large sky area multi-object fiber spectroscopic telescope)数据库,预处理采用Z-score进行光谱归一化,以减少由于光谱流量值差别大造成的模型收敛困难问题。使用精确率(Precision)、召回率(Recall)、F1-score和准确率(Accuracy)四个指标来评估模型性能。实验包括:第一部分利用TDSC-Net进行A、F、G、K、M型恒星分类,以验证利用二维光谱对恒星多分类的可靠性;第二部分将二维光谱按照不同的信噪比区间进行分类,以探究信噪比对分类准确率的影响。第一部分的结果表明,进行五分类总的准确率达到84.3%。其中,A、F、G、K、M各自的分类精度分别为87.0%,84.6%,81.2%,87.4%,89.7%,均优于自行抽谱后的一维光谱分类结果。第二部分的结果表明,即使在SNR<30的低信噪比区间,二维光谱分类准确率仍然可以达到78.9%;而当SNR>30之后,信噪比对光谱分类的影响就不明显了。由此证明了低信噪比时使用二维光谱分类的重要性以及TDSC-Net对恒星光谱分类的有效性。

Point Cloud Classification Using Content-Based Transformer via Clustering in Feature Space

Recently, there have been some attempts of Transformer in 3D point cloud classification. In order to reduce computations, most existing methods focus on local spatial attention,but ignore their content and fail to establish relationships between distant but relevant points. To overcome the limitation of local spatial attention, we propose a point content-based Transformer architecture, called PointConT for short. It exploits the locality of points in the feature space(content-based), which clusters the sampled points with similar features into the same class and computes the self-attention within each class, thus enabling an effective trade-off between capturing long-range dependencies and computational complexity. We further introduce an inception feature aggregator for point cloud classification, which uses parallel structures to aggregate high-frequency and low-frequency information in each branch separately. Extensive experiments show that our PointConT model achieves a remarkable performance on point cloud shape classification. Especially, our method exhibits 90.3% Top-1 accuracy on the hardest setting of ScanObjectN N. Source code of this paper is available at https://github.com/yahuiliu99/PointC onT.

Deep Insight of Design,Mechanism,and Cancer Theranostic Strategy of Nanozymes

Since the discovery of enzyme-like activity of Fe3O4 nanoparticles in 2007,nanozymes are becoming the promising substitutes for natural enzymes due to their advantages of high catalytic activity,low cost,mild reaction conditions,good stability,and suitable for large-scale production.Recently,with the cross fusion of nanomedicine and nanocatalysis,nanozyme-based theranostic strategies attract great attention,since the enzymatic reactions can be triggered in the tumor microenvironment to achieve good curative effect with substrate specificity and low side effects.Thus,various nanozymes have been developed and used for tumor therapy.In this review,more than 270 research articles are discussed systematically to present progress in the past five years.First,the discovery and development of nanozymes are summarized.Second,classification and catalytic mechanism of nanozymes are discussed.Third,activity prediction and rational design of nanozymes are focused by highlighting the methods of density functional theory,machine learning,biomimetic and chemical design.Then,synergistic theranostic strategy of nanozymes are introduced.Finally,current challenges and future prospects of nanozymes used for tumor theranostic are outlined,including selectivity,biosafety,repeatability and stability,in-depth catalytic mechanism,predicting and evaluating activities.

Label-free in-vivo classi-cation and tracking of red blood cells and platelets using Dynamic-YOLOv4 network

In-vivo flow cytometry is a noninvasive real-time diagnostic technique that facilitates continuous monitoring of cells without perturbing their natural biological environment,which renders it a valuable tool for both scientific research and clinical applications.However,the conventional approach for improving classification accuracy often involves labeling cells with fluorescence,which can lead to potential phototoxicity.This study proposes a label-free in-vivo flow cytometry technique,called dynamic YOLOv4(D-YOLOv4),which improves classification accuracy by integrating absorption intensity fluctuation modulation(AIFM)into YOLOv4 to demodulate the temporal features of moving red blood cells(RBCs)and platelets.Using zebrafish as an experimental model,the D-YOLOv4 method achieved average precisions(APs)of 0.90 for RBCs and 0.64 for thrombocytes(similar to platelets in mammals),resulting in an overall AP of 0.77.These scores notably surpass those attained by alternative network models,thereby demonstrating that the combination of physical models with neural networks provides an innovative approach toward developing label-free in-vivoflow cytometry,which holds promise for diverse in-vivo cell classification applications.

Data-driven casting defect prediction model for sand casting based on random forest classification algorithm

The complex sand-casting process combined with the interactions between process parameters makes it difficult to control the casting quality,resulting in a high scrap rate.A strategy based on a data-driven model was proposed to reduce casting defects and improve production efficiency,which includes the random forest(RF)classification model,the feature importance analysis,and the process parameters optimization with Monte Carlo simulation.The collected data includes four types of defects and corresponding process parameters were used to construct the RF model.Classification results show a recall rate above 90% for all categories.The Gini Index was used to assess the importance of the process parameters in the formation of various defects in the RF model.Finally,the classification model was applied to different production conditions for quality prediction.In the case of process parameters optimization for gas porosity defects,this model serves as an experimental process in the Monte Carlo method to estimate a better temperature distribution.The prediction model,when applied to the factory,greatly improved the efficiency of defect detection.Results show that the scrap rate decreased from 10.16% to 6.68%.

An Imbalanced Data Classification Method Based on Hybrid Resampling and Fine Cost Sensitive Support Vector Machine

When building a classification model,the scenario where the samples of one class are significantly more than those of the other class is called data imbalance.Data imbalance causes the trained classification model to be in favor of the majority class(usually defined as the negative class),which may do harm to the accuracy of the minority class(usually defined as the positive class),and then lead to poor overall performance of the model.A method called MSHR-FCSSVM for solving imbalanced data classification is proposed in this article,which is based on a new hybrid resampling approach(MSHR)and a new fine cost-sensitive support vector machine(CS-SVM)classifier(FCSSVM).The MSHR measures the separability of each negative sample through its Silhouette value calculated by Mahalanobis distance between samples,based on which,the so-called pseudo-negative samples are screened out to generate new positive samples(over-sampling step)through linear interpolation and are deleted finally(under-sampling step).This approach replaces pseudo-negative samples with generated new positive samples one by one to clear up the inter-class overlap on the borderline,without changing the overall scale of the dataset.The FCSSVM is an improved version of the traditional CS-SVM.It considers influences of both the imbalance of sample number and the class distribution on classification simultaneously,and through finely tuning the class cost weights by using the efficient optimization algorithm based on the physical phenomenon of rime-ice(RIME)algorithm with cross-validation accuracy as the fitness function to accurately adjust the classification borderline.To verify the effectiveness of the proposed method,a series of experiments are carried out based on 20 imbalanced datasets including both mildly and extremely imbalanced datasets.The experimental results show that the MSHR-FCSSVM method performs better than the methods for comparison in most cases,and both the MSHR and the FCSSVM played significant roles.

Network traffic classification:Techniques,datasets,and challenges

In network traffic classification,it is important to understand the correlation between network traffic and its causal application,protocol,or service group,for example,in facilitating lawful interception,ensuring the quality of service,preventing application choke points,and facilitating malicious behavior identification.In this paper,we review existing network classification techniques,such as port-based identification and those based on deep packet inspection,statistical features in conjunction with machine learning,and deep learning algorithms.We also explain the implementations,advantages,and limitations associated with these techniques.Our review also extends to publicly available datasets used in the literature.Finally,we discuss existing and emerging challenges,as well as future research directions.

Automatic detection of small bowel lesions with different bleeding risks based on deep learning models

BACKGROUND Deep learning provides an efficient automatic image recognition method for small bowel(SB)capsule endoscopy(CE)that can assist physicians in diagnosis.However,the existing deep learning models present some unresolved challenges.AIM To propose a novel and effective classification and detection model to automatically identify various SB lesions and their bleeding risks,and label the lesions accurately so as to enhance the diagnostic efficiency of physicians and the ability to identify high-risk bleeding groups.METHODS The proposed model represents a two-stage method that combined image classification with object detection.First,we utilized the improved ResNet-50 classification model to classify endoscopic images into SB lesion images,normal SB mucosa images,and invalid images.Then,the improved YOLO-V5 detection model was utilized to detect the type of lesion and its risk of bleeding,and the location of the lesion was marked.We constructed training and testing sets and compared model-assisted reading with physician reading.RESULTS The accuracy of the model constructed in this study reached 98.96%,which was higher than the accuracy of other systems using only a single module.The sensitivity,specificity,and accuracy of the model-assisted reading detection of all images were 99.17%,99.92%,and 99.86%,which were significantly higher than those of the endoscopists’diagnoses.The image processing time of the model was 48 ms/image,and the image processing time of the physicians was 0.40±0.24 s/image(P<0.001).CONCLUSION The deep learning model of image classification combined with object detection exhibits a satisfactory diagnostic effect on a variety of SB lesions and their bleeding risks in CE images,which enhances the diagnostic efficiency of physicians and improves the ability of physicians to identify high-risk bleeding groups.

Evaluation of slope stability through rock mass classification and kinematic analysis of some major slopes along NH-1A from Ramban to Banihal, North Western Himalayas

The network of Himalayan roadways and highways connects some remote regions of valleys or hill slopes,which is vital for India’s socio-economic growth.Due to natural and artificial factors,frequency of slope instabilities along the networks has been increasing over last few decades.Assessment of stability of natural and artificial slopes due to construction of these connecting road networks is significant in safely executing these roads throughout the year.Several rock mass classification methods are generally used to assess the strength and deformability of rock mass.This study assesses slope stability along the NH-1A of Ramban district of North Western Himalayas.Various structurally and non-structurally controlled rock mass classification systems have been applied to assess the stability conditions of 14 slopes.For evaluating the stability of these slopes,kinematic analysis was performed along with geological strength index(GSI),rock mass rating(RMR),continuous slope mass rating(CoSMR),slope mass rating(SMR),and Q-slope in the present study.The SMR gives three slopes as completely unstable while CoSMR suggests four slopes as completely unstable.The stability of all slopes was also analyzed using a design chart under dynamic and static conditions by slope stability rating(SSR)for the factor of safety(FoS)of 1.2 and 1 respectively.Q-slope with probability of failure(PoF)1%gives two slopes as stable slopes.Stable slope angle has been determined based on the Q-slope safe angle equation and SSR design chart based on the FoS.The value ranges given by different empirical classifications were RMR(37-74),GSI(27.3-58.5),SMR(11-59),and CoSMR(3.39-74.56).Good relationship was found among RMR&SSR and RMR&GSI with correlation coefficient(R 2)value of 0.815 and 0.6866,respectively.Lastly,a comparative stability of all these slopes based on the above classification has been performed to identify the most critical slope along this road.

A deep convolutional neural network for diabetic retinopathy detection via mining local and long-range dependence

Diabetic retinopathy(DR),the main cause of irreversible blindness,is one of the most common complications of diabetes.At present,deep convolutional neural networks have achieved promising performance in automatic DR detection tasks.The convolution operation of methods is a local cross-correlation operation,whose receptive field de-termines the size of the local neighbourhood for processing.However,for retinal fundus photographs,there is not only the local information but also long-distance dependence between the lesion features(e.g.hemorrhages and exudates)scattered throughout the whole image.The proposed method incorporates correlations between long-range patches into the deep learning framework to improve DR detection.Patch-wise re-lationships are used to enhance the local patch features since lesions of DR usually appear as plaques.The Long-Range unit in the proposed network with a residual structure can be flexibly embedded into other trained networks.Extensive experimental results demon-strate that the proposed approach can achieve higher accuracy than existing state-of-the-art models on Messidor and EyePACS datasets.

Detection and defending the XSS attack using novel hybrid stacking ensemble learning-based DNN approach

Existing web-based security applications have failed in many situations due to the great intelligence of attackers.Among web applications,Cross-Site Scripting(XSS)is one of the dangerous assaults experienced while modifying an organization's or user's information.To avoid these security challenges,this article proposes a novel,all-encompassing combination of machine learning(NB,SVM,k-NN)and deep learning(RNN,CNN,LSTM)frameworks for detecting and defending against XSS attacks with high accuracy and efficiency.Based on the representation,a novel idea for merging stacking ensemble with web applications,termed“hybrid stacking”,is proposed.In order to implement the aforementioned methods,four distinct datasets,each of which contains both safe and unsafe content,are considered.The hybrid detection method can adaptively identify the attacks from the URL,and the defense mechanism inherits the advantages of URL encoding with dictionary-based mapping to improve prediction accuracy,accelerate the training process,and effectively remove the unsafe JScript/JavaScript keywords from the URL.The simulation results show that the proposed hybrid model is more efficient than the existing detection methods.It produces more than 99.5%accurate XSS attack classification results(accuracy,precision,recall,f1_score,and Receiver Operating Characteristic(ROC))and is highly resistant to XSS attacks.In order to ensure the security of the server's information,the proposed hybrid approach is demonstrated in a real-time environment.

Intrahepatic portal venous systems in adult patients with cavernous transformation of portal vein: Imaging features and a new classification

Background: Cavernous transformation of the portal vein(CTPV) due to portal vein obstruction is a rare vascular anomaly defined as the formation of multiple collateral vessels in the hepatic hilum. This study aimed to investigate the imaging features of intrahepatic portal vein in adult patients with CTPV and establish the relationship between the manifestations of intrahepatic portal vein and the progression of CTPV. Methods: We retrospectively analyzed 14 CTPV patients in Beijing Tsinghua Changgung Hospital. All patients underwent both direct portal venography(DPV) and computed tomography angiography(CTA) to reveal the manifestations of the portal venous system. The vessels measured included the left portal vein(LPV), right portal vein(RPV), main portal vein(MPV) and the portal vein bifurcation(PVB). Results: Nine males and 5 females, with a median age of 40.5 years, were included in the study. No significant difference was found in the diameters of the LPV or RPV measured by DPV and CTA. The visualization in terms of LPV, RPV and PVB measured by DPV was higher than that by CTA. There was a significant association between LPV/RPV and PVB/MPV in term of visibility revealed with DPV( P = 0.01), while this association was not observed with CTA. According to the imaging features of the portal vein measured by DPV, CTPV was classified into three categories to facilitate the diagnosis and treatment. Conclusions: DPV was more accurate than CTA for revealing the course of the intrahepatic portal vein in patients with CTPV. The classification of CTPV, that originated from the imaging features of the portal vein revealed by DPV, may provide a new perspective for the diagnosis and treatment of CTPV.

Enhancing Cancer Classification through a Hybrid Bio-Inspired Evolutionary Algorithm for Biomarker Gene Selection

In this study,our aim is to address the problem of gene selection by proposing a hybrid bio-inspired evolutionary algorithm that combines Grey Wolf Optimization(GWO)with Harris Hawks Optimization(HHO)for feature selection.Themotivation for utilizingGWOandHHOstems fromtheir bio-inspired nature and their demonstrated success in optimization problems.We aimto leverage the strengths of these algorithms to enhance the effectiveness of feature selection in microarray-based cancer classification.We selected leave-one-out cross-validation(LOOCV)to evaluate the performance of both two widely used classifiers,k-nearest neighbors(KNN)and support vector machine(SVM),on high-dimensional cancer microarray data.The proposed method is extensively tested on six publicly available cancer microarray datasets,and a comprehensive comparison with recently published methods is conducted.Our hybrid algorithm demonstrates its effectiveness in improving classification performance,Surpassing alternative approaches in terms of precision.The outcomes confirm the capability of our method to substantially improve both the precision and efficiency of cancer classification,thereby advancing the development ofmore efficient treatment strategies.The proposed hybridmethod offers a promising solution to the gene selection problem in microarray-based cancer classification.It improves the accuracy and efficiency of cancer diagnosis and treatment,and its superior performance compared to other methods highlights its potential applicability in realworld cancer classification tasks.By harnessing the complementary search mechanisms of GWO and HHO,we leverage their bio-inspired behavior to identify informative genes relevant to cancer diagnosis and treatment.

National guidelines for the diagnosis and treatment of hilar cholangiocarcinoma

A consensus meeting of national experts from all major national hepatobiliary centres in the country was held on May 26,2023,at the Pakistan Kidney and Liver Institute&Research Centre(PKLI&RC)after initial consultations with the experts.The Pakistan Society for the Study of Liver Diseases(PSSLD)and PKLI&RC jointly organised this meeting.This effort was based on a comprehensive literature review to establish national practice guidelines for hilar cholangiocarcinoma(hCCA).The consensus was that hCCA is a complex disease and requires a multidisciplinary team approach to best manage these patients.This coordinated effort can minimise delays and give patients a chance for curative treatment and effective palliation.The diagnostic and staging workup includes high-quality computed tomography,magnetic resonance imaging,and magnetic resonance cholangiopancreato-graphy.Brush cytology or biopsy utilizing endoscopic retrograde cholangiopancreatography is a mainstay for diagnosis.However,histopathologic confirmation is not always required before resection.Endoscopic ultrasound with fine needle aspiration of regional lymph nodes and positron emission tomography scan are valuable adjuncts for staging.The only curative treatment is the surgical resection of the biliary tree based on the Bismuth-Corlette classification.Selected patients with unresectable hCCA can be considered for liver transplantation.Adjuvant chemotherapy should be offered to patients with a high risk of recurrence.The use of preoperative biliary drainage and the need for portal vein embolisation should be based on local multidisciplinary discussions.Patients with acute cholangitis can be drained with endoscopic or percutaneous biliary drainage.Palliative chemotherapy with cisplatin and gemcitabine has shown improved survival in patients with irresectable and recurrent hCCA.

BSTFNet:An Encrypted Malicious Traffic Classification Method Integrating Global Semantic and Spatiotemporal Features

While encryption technology safeguards the security of network communications,malicious traffic also uses encryption protocols to obscure its malicious behavior.To address the issues of traditional machine learning methods relying on expert experience and the insufficient representation capabilities of existing deep learning methods for encrypted malicious traffic,we propose an encrypted malicious traffic classification method that integrates global semantic features with local spatiotemporal features,called BERT-based Spatio-Temporal Features Network(BSTFNet).At the packet-level granularity,the model captures the global semantic features of packets through the attention mechanism of the Bidirectional Encoder Representations from Transformers(BERT)model.At the byte-level granularity,we initially employ the Bidirectional Gated Recurrent Unit(BiGRU)model to extract temporal features from bytes,followed by the utilization of the Text Convolutional Neural Network(TextCNN)model with multi-sized convolution kernels to extract local multi-receptive field spatial features.The fusion of features from both granularities serves as the ultimate multidimensional representation of malicious traffic.Our approach achieves accuracy and F1-score of 99.39%and 99.40%,respectively,on the publicly available USTC-TFC2016 dataset,and effectively reduces sample confusion within the Neris and Virut categories.The experimental results demonstrate that our method has outstanding representation and classification capabilities for encrypted malicious traffic.

Effectiveness of serological markers of gastric mucosal atrophy in the gastric precancer screening and in cancer prevention

BACKGROUND New markers are needed to improve the effectiveness of serological screening for atrophic gastritis.AIM To develop a cost-effective method for serological screening of atrophic gastritis with a high level of sensitivity.METHODS Of the 169 patients with atrophic gastritis,selected by the visual endoscopic Kimura-Takemoto method,165 showed histological mucosal atrophy using the updated Kimura-Takemoto method.All 169 patients were examined for postprandial levels of gastrin-17(G17)and pepsinogen-1(PG1)using Gastro-Panel®(Biohit Plc,Helsinki,Finland).RESULTS We used the histological standard of five biopsies of the gastric mucosa,in accordance with the Kimura-Takemoto classification system to assess the sensitivity of G17 in detecting gastric mucosal atrophy.We also compared the morphofunctional relationships between the detected histological degree of gastric mucosal atrophy and the serological levels of G17 and PG1,as the markers of atrophic gastritis.The sensitivity of postprandial G17 was 62.2%for serological levels of G17(range:0-4 pmol/L)and 100%for serological G17(range:0-10 pmol/L)for the detection of monofocal severe atrophic gastritis.No strong correlation was found between the levels of PG1 and degree of histological atrophy determined by the Kimura-Takemoto classification system to identify the severity of mucosal atrophy of the gastric corpus.In the presented clinical case of a 63-year-old man with multifocal atrophic gastritis,there is a pronounced positive long-term dynamics of the serological marker of atrophy-postprandial G17,after five months of rennet replacement therapy.CONCLUSION Serological screening of multifocal atrophic gastritis by assessment of postprandial G17 is a cost-effective method with high sensitivity.Postprandial G17 is an earlier marker of regression of atrophic gastritis than a morphological examination of a gastric biopsy in accordance with the Sydney system.Therefore,postprandial G17 is recommended for dynamic monitoring of atrophic gastritis after treatment.

DeepSVDNet:A Deep Learning-Based Approach for Detecting and Classifying Vision-Threatening Diabetic Retinopathy in Retinal Fundus Images

Artificial Intelligence(AI)is being increasingly used for diagnosing Vision-Threatening Diabetic Retinopathy(VTDR),which is a leading cause of visual impairment and blindness worldwide.However,previous automated VTDR detection methods have mainly relied on manual feature extraction and classification,leading to errors.This paper proposes a novel VTDR detection and classification model that combines different models through majority voting.Our proposed methodology involves preprocessing,data augmentation,feature extraction,and classification stages.We use a hybrid convolutional neural network-singular value decomposition(CNN-SVD)model for feature extraction and selection and an improved SVM-RBF with a Decision Tree(DT)and K-Nearest Neighbor(KNN)for classification.We tested our model on the IDRiD dataset and achieved an accuracy of 98.06%,a sensitivity of 83.67%,and a specificity of 100%for DR detection and evaluation tests,respectively.Our proposed approach outperforms baseline techniques and provides a more robust and accurate method for VTDR detection.

Performance evaluation of seven multi-label classification methods on real-world patent and publication datasets

Purpose:Many science,technology and innovation(STI)resources are attached with several different labels.To assign automatically the resulting labels to an interested instance,many approaches with good performance on the benchmark datasets have been proposed for multi-label classification task in the literature.Furthermore,several open-source tools implementing these approaches have also been developed.However,the characteristics of real-world multi-label patent and publication datasets are not completely in line with those of benchmark ones.Therefore,the main purpose of this paper is to evaluate comprehensively seven multi-label classification methods on real-world datasets.Research limitations:Three real-world datasets differ in the following aspects:statement,data quality,and purposes.Additionally,open-source tools designed for multi-label classification also have intrinsic differences in their approaches for data processing and feature selection,which in turn impacts the performance of a multi-label classification approach.In the near future,we will enhance experimental precision and reinforce the validity of conclusions by employing more rigorous control over variables through introducing expanded parameter settings.Practical implications:The observed Macro F1 and Micro F1 scores on real-world datasets typically fall short of those achieved on benchmark datasets,underscoring the complexity of real-world multi-label classification tasks.Approaches leveraging deep learning techniques offer promising solutions by accommodating the hierarchical relationships and interdependencies among labels.With ongoing enhancements in deep learning algorithms and large-scale models,it is expected that the efficacy of multi-label classification tasks will be significantly improved,reaching a level of practical utility in the foreseeable future.Originality/value:(1)Seven multi-label classification methods are comprehensively compared on three real-world datasets.(2)The TextCNN and TextRCNN models perform better on small-scale datasets with more complex hierarchical structure of labels and more balanced document-label distribution.(3)The MLkNN method works better on the larger-scale dataset with more unbalanced document-label distribution.

Study on neutron-gamma discrimination methods based on GMM-KNN and LabVIEW implementation

Machine learning algorithms are considered as effective methods for improving the effectiveness of neutron-gamma(n-γ)discrimination.This study proposed an intelligent discrimination method that combined a Gaussian mixture model(GMM)with the K-nearest neighbor(KNN)algorithm,referred to as GMM-KNN.First,the unlabeled training and test data were categorized into three energy ranges:0–25 keV,25–100 keV,and 100–2100 keV.Second,GMM-KNN achieved small-batch clustering in three energy intervals with only the tail integral Q_(tail) and total integral Q_(total) as the pulse features.Subsequently,we selected the pulses with a probability greater than 99%from the GMM clustering results to construct the training set.Finally,we improved the KNN algorithm such that GMM-KNN realized the classification and regression algorithms through the LabVIEW language.The outputs of GMM-KNN were the category or regression predictions.The proposed GMM-KNN constructed the training set using unlabeled real pulse data and realized n-γdiscrimination of ^(241)Am-Be pulses using the LabVIEW program.The experimental results demonstrated the high robustness and flexibility of GMM-KNN.Even when using only 1/4 of the training set,the execution time of GMM-KNN was only 2021 ms,with a difference of only 0.13%compared with the results obtained on the full training set.Furthermore,GMM-KNN outperformed the charge comparison method in terms of accuracy,and correctly classified 5.52%of the ambiguous pulses.In addition,the GMM-KNN regressor achieved a higher figure of merit(FOM),with FOM values of 0.877,1.262,and 1.020,corresponding to the three energy ranges,with a 32.08%improvement in 0–25 keV.In conclusion,the GMM-KNN algorithm demonstrates accurate and readily deployable real-time n-γdiscrimination performance,rendering it suitable for on-site analysis.

AI Fairness-From Machine Learning to Federated Learning

This article reviews the theory of fairness in AI-frommachine learning to federated learning,where the constraints on precision AI fairness and perspective solutions are also discussed.For a reliable and quantitative evaluation of AI fairness,many associated concepts have been proposed,formulated and classified.However,the inexplicability of machine learning systems makes it almost impossible to include all necessary details in the modelling stage to ensure fairness.The privacy worries induce the data unfairness and hence,the biases in the datasets for evaluating AI fairness are unavoidable.The imbalance between algorithms’utility and humanization has further reinforced suchworries.Even for federated learning systems,these constraints on precision AI fairness still exist.Aperspective solution is to reconcile the federated learning processes and reduce biases and imbalances accordingly.