A Novel Framework for Learning and Classifying the Imbalanced Multi-Label Data

A generalization of supervised single-label learning based on the assumption that each sample in a dataset may belong to more than one class simultaneously is called multi-label learning.The main objective of this work is to create a novel framework for learning and classifying imbalancedmulti-label data.This work proposes a framework of two phases.The imbalanced distribution of themulti-label dataset is addressed through the proposed Borderline MLSMOTE resampling method in phase 1.Later,an adaptive weighted l21 norm regularized(Elastic-net)multilabel logistic regression is used to predict unseen samples in phase 2.The proposed Borderline MLSMOTE resampling method focuses on samples with concurrent high labels in contrast to conventional MLSMOTE.The minority labels in these samples are called difficult minority labels and are more prone to penalize classification performance.The concurrentmeasure is considered borderline,and labels associated with samples are regarded as borderline labels in the decision boundary.In phase II,a novel adaptive l21 norm regularized weighted multi-label logistic regression is used to handle balanced data with different weighted synthetic samples.Experimentation on various benchmark datasets shows the outperformance of the proposed method and its powerful predictive performances over existing conventional state-of-the-art multi-label methods.

IDS-INT:Intrusion detection system using transformer-based transfer learning for imbalanced network traffic

A network intrusion detection system is critical for cyber security against llegitimate attacks.In terms of feature perspectives,network traffic may include a variety of elements such as attack reference,attack type,a subcategory of attack,host information,malicious scripts,etc.In terms of network perspectives,network traffic may contain an imbalanced number of harmful attacks when compared to normal traffic.It is challenging to identify a specific attack due to complex features and data imbalance issues.To address these issues,this paper proposes an Intrusion Detection System using transformer-based transfer learning for Imbalanced Network Traffic(IDS-INT).IDS-INT uses transformer-based transfer learning to learn feature interactions in both network feature representation and imbalanced data.First,detailed information about each type of attack is gathered from network interaction descriptions,which include network nodes,attack type,reference,host information,etc.Second,the transformer-based transfer learning approach is developed to learn detailed feature representation using their semantic anchors.Third,the Synthetic Minority Oversampling Technique(SMOTE)is implemented to balance abnormal traffic and detect minority attacks.Fourth,the Convolution Neural Network(CNN)model is designed to extract deep features from the balanced network traffic.Finally,the hybrid approach of the CNN-Long Short-Term Memory(CNN-LSTM)model is developed to detect different types of attacks from the deep features.Detailed experiments are conducted to test the proposed approach using three standard datasets,i.e.,UNsWNB15,CIC-IDS2017,and NSL-KDD.An explainable AI approach is implemented to interpret the proposed method and develop a trustable model.

Class Imbalanced Problem:Taxonomy,Open Challenges,Applications and State-of-the-Art Solutions

The study of machine learning has revealed that it can unleash new applications in a variety of disciplines.Many limitations limit their expressiveness,and researchers are working to overcome them to fully exploit the power of data-driven machine learning(ML)and deep learning(DL)techniques.The data imbalance presents major hurdles for classification and prediction problems in machine learning,restricting data analytics and acquiring relevant insights in practically all real-world research domains.In visual learning,network information security,failure prediction,digital marketing,healthcare,and a variety of other domains,raw data suffers from a biased data distribution of one class over the other.This article aims to present a taxonomy of the approaches for handling imbalanced data problems and their comparative study on the classification metrics and their application areas.We have explored very recent trends of techniques employed for solutions to class imbalance problems in datasets and have also discussed their limitations.This article has also identified open challenges for further research in the direction of class data imbalance.

A method for establishing a bearing residual life prediction model for process enhancement equipment based on rotor imbalance response analysis

A rotating packed bed is a typical chemical process enhancement equipment that can strengthen micromixing and mass transfer.During the operation of the rotating packed bed,the nonreactants and products irregularly adhere to the wire mesh packing in the rotor,thus resulting in an imbalance in the vibration of the rotor,which may cause serious damage to the bearing and material leakage.This study proposes a model prediction for estimating the bearing residual life of a rotating packed bed based on rotor imbalance response analysis.This method is used to determine the influence of the mass on the imbalance in the vibration of the rotor on bearing damage.The major influence on rotor vibration was found to be exerted by the imbalanced mass and its distribution radius,as revealed by the results of orthogonal experiments.Through implementing finite element analysis,the imbalance response curve for the rotating packed bed rotor was obtained,and a correlation among rotor imbalance mass,distribution radius of imbalance mass,and bearing residue life was established via data fitting.The predicted value of the bearing life can be used as the reference basis for an early safety warning of a rotating packed bed to effectively avoid accidents.

Multifaceted functions of Drp1 in hypoxia/ischemia- induced mitochondrial quality imbalance: from regulatory mechanism to targeted therapeutic strategy

Hypoxic-ischemic injury is a common pathological dysfunction in clinical settings.Mitochondria are sensitive organelles that are readily damaged following ischemia and hypoxia.Dynamin-related protein 1(Drp1)regulates mitochondrial quality and cellular functions via its oligomeric changes and multiple modifications,which plays a role in mediating the induction of multiple organ damage during hypoxic-ischemic injury.However,there is active controversy and gaps in knowledge regarding the modification,protein interaction,and functions of Drp1,which both hinder and promote development of Drp1 as a novel therapeutic target.Here,we summarize recent findings on the oligomeric changes,modification types,and protein interactions of Drp1 in various hypoxic-ischemic diseases,as well as the Drp1-mediated regulation of mitochondrial quality and cell functions following ischemia and hypoxia.Additionally,potential clinical translation prospects for targeting Drp1 are discussed.This review provides new ideas and targets for proactive interventions on multiple organ damage induced by various hypoxic-ischemic diseases.

Photobiomodulation provides neuroprotection through regulating mitochondrial fission imbalance in the subacute phase of spinal cord injury

Increasing evidence indicates that mitochonarial lission imbalance plays an important role in derayed neuronal cell death. Our previous study round that photo biomodulation improved the motor function of rats with spinal cord injury.However,the precise mechanism remains unclear.To investigate the effect of photo biomodulation on mitochondrial fission imbalance after spinal cord injury,in this study,we treated rat models of spinal co rd injury with 60-minute photo biomodulation(810 nm,150 mW) every day for 14 consecutive days.Transmission electron microscopy results confirmed the swollen and fragmented alte rations of mitochondrial morphology in neurons in acute(1 day) and subacute(7 and 14 days) phases.Photo biomodulation alleviated mitochondrial fission imbalance in spinal cord tissue in the subacute phase,reduced neuronal cell death,and improved rat posterior limb motor function in a time-dependent manner.These findings suggest that photobiomodulation targets neuronal mitochondria,alleviates mitochondrial fission imbalance-induced neuronal apoptosis,and thereby promotes the motor function recovery of rats with spinal cord injury.

Combined Effect of Concept Drift and Class Imbalance on Model Performance During Stream Classification

Every application in a smart city environment like the smart grid,health monitoring, security, and surveillance generates non-stationary datastreams. Due to such nature, the statistical properties of data changes overtime, leading to class imbalance and concept drift issues. Both these issuescause model performance degradation. Most of the current work has beenfocused on developing an ensemble strategy by training a new classifier on thelatest data to resolve the issue. These techniques suffer while training the newclassifier if the data is imbalanced. Also, the class imbalance ratio may changegreatly from one input stream to another, making the problem more complex.The existing solutions proposed for addressing the combined issue of classimbalance and concept drift are lacking in understating of correlation of oneproblem with the other. This work studies the association between conceptdrift and class imbalance ratio and then demonstrates how changes in classimbalance ratio along with concept drift affect the classifier’s performance.We analyzed the effect of both the issues on minority and majority classesindividually. To do this, we conducted experiments on benchmark datasetsusing state-of-the-art classifiers especially designed for data stream classification.Precision, recall, F1 score, and geometric mean were used to measure theperformance. Our findings show that when both class imbalance and conceptdrift problems occur together the performance can decrease up to 15%. Ourresults also show that the increase in the imbalance ratio can cause a 10% to15% decrease in the precision scores of both minority and majority classes.The study findings may help in designing intelligent and adaptive solutionsthat can cope with the challenges of non-stationary data streams like conceptdrift and class imbalance.

Pharmacological effects of denervated muscle atrophy due to metabolic imbalance in different periods

Denervation-induced skeletal muscle atrophy can potentially cause the decline in the quality of life of patients and an increased risk of mortality.Complex pathophysiological mechanisms with dynamic alterations have been documented in skeletal muscle atrophy resulting from innervation loss.Hence,an in-depth comprehension of the key mechanisms and molecules governing skeletal muscle atrophy at varying stages,along with targeted treatment and protection,becomes essential for effective atrophy management.Our preliminary research categorizes the skeletal muscle atrophy process into four stages using microarray analysis.This review extensively discusses the pathways and molecules potentially implicated in regulating the four stages of denervation and muscle atrophy.Notably,drugs targeting the reactivare oxygen species stage and the inflammation stage assume critical roles.Timely intervention during the initial atrophy stages can expedite protection against skeletal muscle atrophy.Additionally,pharmaceutical intervention in the ubiquitin-proteasome pathway associated with atrophy and autophagy lysosomes can effectively slow down skeletal muscle atrophy.Key molecules within this stage encompass MuRF1,MAFbx,LC3II,p62/SQSTM1,etc.This review also compiles a profile of drugs with protective effects against skeletal muscle atrophy at distinct postdenervation stages,thereby augmenting the evidence base for denervation-induced skeletal muscle atrophy treatment.

Attenuate Class Imbalance Problem for Pneumonia Diagnosis Using Ensemble Parallel Stacked Pre-Trained Models

Pneumonia is an acute lung infection that has caused many fatalitiesglobally. Radiologists often employ chest X-rays to identify pneumoniasince they are presently the most effective imaging method for this purpose.Computer-aided diagnosis of pneumonia using deep learning techniques iswidely used due to its effectiveness and performance. In the proposed method,the Synthetic Minority Oversampling Technique (SMOTE) approach is usedto eliminate the class imbalance in the X-ray dataset. To compensate forthe paucity of accessible data, pre-trained transfer learning is used, and anensemble Convolutional Neural Network (CNN) model is developed. Theensemble model consists of all possible combinations of the MobileNetv2,Visual Geometry Group (VGG16), and DenseNet169 models. MobileNetV2and DenseNet169 performed well in the Single classifier model, with anaccuracy of 94%, while the ensemble model (MobileNetV2+DenseNet169)achieved an accuracy of 96.9%. Using the data synchronous parallel modelin Distributed Tensorflow, the training process accelerated performance by98.6% and outperformed other conventional approaches.

Correlation between cognitive impairment and metabolic imbalance of gut microbiota in patients with schizophrenia

BACKGROUND The gut microbiome interacts with the central nervous system through the gutbrain axis,and this interaction involves neuronal,endocrine,and immune mechanisms,among others,which allow the microbiota to influence and respond to a variety of behavioral and mental conditions.AIM To explore the correlation between cognitive impairment and gut microbiota imbalance in patients with schizophrenia.METHODS A total of 498 untreated patients with schizophrenia admitted to our hospital from July 2020 to July 2022 were selected as the case group,while 498 healthy volunteers who underwent physical examinations at our hospital during the same period were selected as a control group.Fluorescence in situ hybridization was employed to determine the total number of bacteria in the feces of the two groups.The cognitive function test package was used to assess the score of cognitive function in each dimension.Then,the relationship between gut microbiota and cognitive function was analyzed.RESULTS There were statistically significant differences in the relative abundance of gut microbiota at both phylum and class levels between the case group and the control group.In addition,the scores of cognitive function,such as attention/alertness and learning ability,were significantly lower in the case group than in the control group(all P<0.05).The cognitive function was positively correlated with Actinomycetota,Bacteroidota,Euryarchaeota,Fusobacteria,Pseudomonadota,and Saccharibacteria,while negatively correlated with Bacillota,Tenericutes,and Verrucomicrobia at the phylum level.While at the class level,the cognitive function was positively correlated with Class Actinobacteria,Bacteroidia,Betaproteobacteria,Proteobacteria,Blastomycetes,and Gammaproteobacteria,while negatively correlated with Bacilli,Clostridia,Coriobacteriia,and Verrucomicrobiae.CONCLUSION There is a relationship between the metabolic results of gut microbiota and cognitive function in patients with schizophrenia.When imbalances occur in the gut microbiota of patients,it leads to more severe cognitive impairment.

Inverse design of nonlinear phononic crystal configurations based on multi-label classification learning neural networks

Phononic crystals,as artificial composite materials,have sparked significant interest due to their novel characteristics that emerge upon the introduction of nonlinearity.Among these properties,second-harmonic features exhibit potential applications in acoustic frequency conversion,non-reciprocal wave propagation,and non-destructive testing.Precisely manipulating the harmonic band structure presents a major challenge in the design of nonlinear phononic crystals.Traditional design approaches based on parameter adjustments to meet specific application requirements are inefficient and often yield suboptimal performance.Therefore,this paper develops a design methodology using Softmax logistic regression and multi-label classification learning to inversely design the material distribution of nonlinear phononic crystals by exploiting information from harmonic transmission spectra.The results demonstrate that the neural network-based inverse design method can effectively tailor nonlinear phononic crystals with desired functionalities.This work establishes a mapping relationship between the band structure and the material distribution within phononic crystals,providing valuable insights into the inverse design of metamaterials.

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.

Multi-Label Image Classification Based on Object Detection and Dynamic Graph Convolutional Networks

Multi-label image classification is recognized as an important task within the field of computer vision,a discipline that has experienced a significant escalation in research endeavors in recent years.The widespread adoption of convolutional neural networks(CNNs)has catalyzed the remarkable success of architectures such as ResNet-101 within the domain of image classification.However,inmulti-label image classification tasks,it is crucial to consider the correlation between labels.In order to improve the accuracy and performance of multi-label classification and fully combine visual and semantic features,many existing studies use graph convolutional networks(GCN)for modeling.Object detection and multi-label image classification exhibit a degree of conceptual overlap;however,the integration of these two tasks within a unified framework has been relatively underexplored in the existing literature.In this paper,we come up with Object-GCN framework,a model combining object detection network YOLOv5 and graph convolutional network,and we carry out a thorough experimental analysis using a range of well-established public datasets.The designed framework Object-GCN achieves significantly better performance than existing studies in public datasets COCO2014,VOC2007,VOC2012.The final results achieved are 86.9%,96.7%,and 96.3%mean Average Precision(mAP)across the three datasets.

Multi-Label Feature Selection Based on Improved Ant Colony Optimization Algorithm with Dynamic Redundancy and Label Dependence

The world produces vast quantities of high-dimensional multi-semantic data.However,extracting valuable information from such a large amount of high-dimensional and multi-label data is undoubtedly arduous and challenging.Feature selection aims to mitigate the adverse impacts of high dimensionality in multi-label data by eliminating redundant and irrelevant features.The ant colony optimization algorithm has demonstrated encouraging outcomes in multi-label feature selection,because of its simplicity,efficiency,and similarity to reinforcement learning.Nevertheless,existing methods do not consider crucial correlation information,such as dynamic redundancy and label correlation.To tackle these concerns,the paper proposes a multi-label feature selection technique based on ant colony optimization algorithm(MFACO),focusing on dynamic redundancy and label correlation.Initially,the dynamic redundancy is assessed between the selected feature subset and potential features.Meanwhile,the ant colony optimization algorithm extracts label correlation from the label set,which is then combined into the heuristic factor as label weights.Experimental results demonstrate that our proposed strategies can effectively enhance the optimal search ability of ant colony,outperforming the other algorithms involved in the paper.

Classification research of TCM pulse conditions based on multi-label voice analysis

Objective:To explore the feasibility of remotely obtaining complex information on traditional Chinese medicine(TCM)pulse conditions through voice signals.Methods: We used multi-label pulse conditions as the entry point and modeled and analyzed TCM pulse diagnosis by combining voice analysis and machine learning.Audio features were extracted from voice recordings in the TCM pulse condition dataset.The obtained features were combined with information from tongue and facial diagnoses.A multi-label pulse condition voice classification DNN model was built using 10-fold cross-validation,and the modeling methods were validated using publicly available datasets.Results: The analysis showed that the proposed method achieved an accuracy of 92.59%on the public dataset.The accuracies of the three single-label pulse manifestation models in the test set were 94.27%,96.35%,and 95.39%.The absolute accuracy of the multi-label model was 92.74%.Conclusion: Voice data analysis may serve as a remote adjunct to the TCM diagnostic method for pulse condition assessment.

Model Development and Adaptive Imbalance Vibration Control of Magnetic Suspended System

A system model is developed to describe the translational and rotational motion of an active-magnetic-bearing-suspended rigid rotor in a single-gimbal control moment gyro onboard a rigid satellite. This model strictly reflects the motion characteristics of the rotor by considering the dynamic and static imbalance as well as the coupling between the gimbal＇s and the rotor＇s motion on a satellite platform. Adaptive auto-centering control is carefully constructed for the rotor with unknown dynamic and static imbalance. The rotor makes its rotation about the principal axis of inertia through identifying the small rotational angles between the geometric axis and the principal axis as well as the displacements from the geometric center to the mass center so as to tune a stabilizing controller composed of a decentralized PD controller with cross-axis proportional gains and high- and low-pass filters. The main disturbance in the wheel spinning can thereby be completely removed and the vibration acting on the satellite attenuated.

High-performance channel estimation and compensation scheme for OFDMreceivers with IQ imbalances

A pilot pattern across two orthogonal frequency division multiplexing OFDM symbols with a special structure is designed for the channel estimation of OFDM systems with inphase and quadrature IQ imbalances at the receiver.A high-efficiency time-domain TD least square LS channel estimator and a low-complexity frequency-domain Gaussian elimination GE equalizer are proposed to eliminate IQ distortion.The former estimator can significantly suppress channel noise by a factor N/L＋1 over the existing frequency-domain FD LS where N and L＋1 are the total number of subcarriers and the length of cyclic prefix and the proposed GE requires only 2N complex multiplications per OFDM symbol.Simulation results show that by exploiting the TD property of the channel the proposed TD-LS channel estimator obtains a significant signal-to-noise ratio gain over the existing FD-LS one whereas the proposed low-complexity GE compensation achieves the same bit error rate BER performance as the existing LS one.

Co-effect of Demand-control-support Model and Effort-reward Imbalance Model on Depression Risk Estimation in Humans: Findings from Henan Province of China

Objective To investigate the co-effect of Demand-control-support （DCS） model and Effort-reward Imbalance （ERI） model on the risk estimation of depression in humans in comparison with the effects when they are used respectively. Methods A total of 3 632 males and 1 706 females from 13 factories and companies in Henan province were recruited in this cross-sectional study. Perceived job stress was evaluated with the Job Content Questionnaire and Effort-Reward Imbalance Questionnaire （Chinese version）. Depressive symptoms were assessed by using the Center for Epidemiological Studies Depression Scale （CES-D）. Results DC （demands/job control ratio） and ERI were shown to be independently associated with depressive symptoms. The outcome of low social support and overcommitment were similar. High DC and low social support （SS）, high ERI and high overcommitment, and high DC and high ERI posed greater risks of depressive symptoms than each of them did alone. ERI model and SS model seem to be effective in estimating the risk of depressive symptoms if they are used respectively. Conclusion The DC had better performance when it was used in combination with low SS. The effect on physical demands was better than on psychological demands. The combination of DCS and ERI models could improve the risk estimate of depressive symptoms in humans.

Endocrine milieu and erectile dysfunction： is oestradio-testosterone imbalance, a risk factor in the elderly？

Oestrogens are not exclusive to the female gender but occur in moderate circulating levels of 25-70 pg ml^-1 in men, compared to 44- 153 pg ml^-1 in women. Arising from aromatisation of testosterone （T）, oestrogen is considered to have many opposing physiological functions and the progressive T decline in the aging male is associated with relative and/or absolute increase in serum oestradiol （E2）. Sexual disinterest and erectile dysfunction （ED） in the elderly may well be due to pathophysiological E2-T imbalance; the altered hormonal ratio may also explain the higher incidence of ED in hyperestrogenism or following exposure to environmental/plant oestrogens.

China’s financial conundrum and global imbalances

China’s financial conundrum arises from two sources: (1) its large trade (saving) surplus results in a currency mismatch because it is an immature creditor that cannot lend in its own currency. Instead foreign currency claims (largely dollars) build up within domestic financial institutions. And (2) economists – both American and Chinese – mistakenly attribute the surpluses to an undervalued renminbi. To placate the United States, the result is a gradual appreciation of the renminbi against the dollar of 6% or more per year. This predictable appreciation since 2004, and the fall in US interest rates since mid 2007, not only attracts hot money inflows but inhibits private capital outflows from financing China’s huge trade surplus. This one-way bet in the foreign exchange markets can no longer be offset by relatively low interest rates in China compared to the United States, as had been the case in 2005-06. Thus, the People’s Bank of China (PBOC) now must intervene heavily to prevent the renminbi from ratcheting upwards – and so becomes the country’s sole international financial intermediary. Despite massive efforts by the PBOC to sterilize the monetary consequences of the reserve buildup, inflation in China is increasing, with excess liquidity that spills over into the world economy. China has been transformed from a deflationary force on American and European price levels into an inflationary one. Because of the currency mismatch, floating the RMB is neither feasible nor desirable – and a higher RMB would not reduce China’s trade surplus. Instead, monetary control and normal private-sector finance for the trade surplus require a return to a credibly fixed nominal yuan/dollar rate similar to that which existed between 1995 and 2004. But for any newly reset yuan/dollar rate to be credible as a monetary anchor, foreign "China bashing" to get the RMB up must end. Currency stabilization would allow the PBOC to regain monetary control and quash inflation. Only then can the Chinese government take decisive steps to reduce the trade (saving) surplus by tax cuts, increased social expenditures, and higher dividend payouts. But as long as the economy remains overheated, the government hesitates to take these trade-surplus-reduction measures because of their near-term inflationary consequences.