Improving Federated Learning through Abnormal Client Detection and Incentive

Data sharing and privacy protection are made possible by federated learning,which allows for continuous model parameter sharing between several clients and a central server.Multiple reliable and high-quality clients must participate in practical applications for the federated learning global model to be accurate,but because the clients are independent,the central server cannot fully control their behavior.The central server has no way of knowing the correctness of the model parameters provided by each client in this round,so clients may purposefully or unwittingly submit anomalous data,leading to abnormal behavior,such as becoming malicious attackers or defective clients.To reduce their negative consequences,it is crucial to quickly detect these abnormalities and incentivize them.In this paper,we propose a Federated Learning framework for Detecting and Incentivizing Abnormal Clients(FL-DIAC)to accomplish efficient and security federated learning.We build a detector that introduces an auto-encoder for anomaly detection and use it to perform anomaly identification and prevent the involvement of abnormal clients,in particular for the anomaly client detection problem.Among them,before the model parameters are input to the detector,we propose a Fourier transform-based anomaly data detectionmethod for dimensionality reduction in order to reduce the computational complexity.Additionally,we create a credit scorebased incentive structure to encourage clients to participate in training in order tomake clients actively participate.Three training models(CNN,MLP,and ResNet-18)and three datasets(MNIST,Fashion MNIST,and CIFAR-10)have been used in experiments.According to theoretical analysis and experimental findings,the FL-DIAC is superior to other federated learning schemes of the same type in terms of effectiveness.

Predictors of Abnormal Vaginal Discharge among Women of Reproductive Age in Southeast Nigeria

Background: An abnormal vaginal discharge is a common complaint among women of reproductive age, and it can indicate serious conditions like pelvic inflammatory disease and cervical cancer. This study aimed to assess the predictors of abnormal vaginal discharge in women of reproductive age group in Imo State, Southeast Nigeria. Methods: A cross-sectional study was conducted among 368 women of reproductive age group attending the clinic at Federal University Teaching Hospital Owerri, in Imo State, Nigeria. Respondents were recruited using a systematic sampling technique. Data were collected using a pre-tested interviewer-administered questionnaire. Multivariable analysis was performed to determine predictors of abnormal vaginal discharge. Statistical significance was set at p Results: The mean age of the respondents was 30 ± 4.5 years. Predictors of abnormal vaginal discharge were: age 36 - 45 years (OR: 4.5;95% C.I: 1.023 - 8.967, p = 0.041), being a student (OR: 2.4: 95% C.I: 1.496 - 7.336, p = 0.003), use of oral contraceptives (OR: 3.4;95% C.I: 1.068 - 6.932, p = 0.010), use of water cistern (OR: 4.7;C.I: 1.654 - 5.210, p = 0.028) anal hygiene practices (OR: 2.7;95% C.I: 1.142 - 4.809, p Conclusion: These findings suggest that targeted sexual and reproductive health interventions should be provided to reduce the risk of abnormal vaginal discharge in women of reproductive age group.

A Blockchain Based Framework for Stomach Abnormalities Recognition

Wireless Capsule Endoscopy(WCE)is an imaging technology,widely used in medical imaging for stomach infection recognition.However,a one patient procedure takes almost seven to eight minutes and approximately 57,000 frames are captured.The privacy of patients is very important and manual inspection is time consuming and costly.Therefore,an automated system for recognition of stomach infections from WCE frames is always needed.An existing block chain-based approach is employed in a convolutional neural network model to secure the network for accurate recognition of stomach infections such as ulcer and bleeding.Initially,images are normalized in fixed dimension and passed in pre-trained deep models.These architectures are modified at each layer,to make them safer and more secure.Each layer contains an extra block,which stores certain information to avoid possible tempering,modification attacks and layer deletions.Information is stored in multiple blocks,i.e.,block attached to each layer,a ledger block attached with the network,and a cloud ledger block stored in the cloud storage.After that,features are extracted and fused using a Mode value-based approach and optimized using a Genetic Algorithm along with an entropy function.The Softmax classifier is applied at the end for final classification.Experiments are performed on a private collected dataset and achieve an accuracy of 96.8%.The statistical analysis and individual model comparison show the proposed method’s authenticity.

Combinatorial reasoning-based abnormal sensor recognition method for subsea production control system

The subsea production system is a vital equipment for offshore oil and gas production.The control system is one of the most important parts of it.Collecting and processing the signals of subsea sensors is the only way to judge whether the subsea production control system is normal.However,subsea sensors degrade rapidly due to harsh working environments and long service time.This leads to frequent false alarm incidents.A combinatorial reasoning-based abnormal sensor recognition method for subsea production control system is proposed.A combinatorial algorithm is proposed to group sensors.The long short-term memory network(LSTM)is used to establish a single inference model.A counting-based judging method is proposed to identify abnormal sensors.Field data from an offshore platform in the South China Sea is used to demonstrate the effect of the proposed method.The results show that the proposed method can identify the abnormal sensors effectively.

Relationship of Retinal Nerve Fiber Layer Thickness and Retinal Vessel Calibers with Cognitive Impairment in the Asymptomatic Polyvascular Abnormalities Population

Objective Cognitive impairment(CI)in older individuals has a high morbidity rate worldwide,with poor diagnostic methods and susceptible population identification.This study aimed to investigate the relationship between different retinal metrics and CI in a particular population,emphasizing polyvascular status.Methods We collected information from the Asymptomatic Polyvascular Abnormalities Community Study on retinal vessel calibers,retinal nerve fiber layer(RNFL)thickness,and cognitive function of 3,785participants,aged 40 years or older.Logistic regression was used to analyze the relationship between retinal metrics and cognitive function.Subgroups stratified by different vascular statuses were also analyzed.Results RNFL thickness was significantly thinner in the CI group(odds ratio:0.973,95%confidence interval:0.953–0.994).In the subgroup analysis,the difference still existed in the non-intracranial arterial stenosis,non-extracranial carotid arterial stenosis,and peripheral arterial disease subgroups(P<0.05).Conclusion A thin RNFL is associated with CI,especially in people with non-large vessel stenosis.The underlying small vessel change in RNFL and CI should be investigated in the future.

Abnormal Traffic Detection for Internet of Things Based on an Improved Residual Network

Along with the progression of Internet of Things(IoT)technology,network terminals are becoming continuously more intelligent.IoT has been widely applied in various scenarios,including urban infrastructure,transportation,industry,personal life,and other socio-economic fields.The introduction of deep learning has brought new security challenges,like an increment in abnormal traffic,which threatens network security.Insufficient feature extraction leads to less accurate classification results.In abnormal traffic detection,the data of network traffic is high-dimensional and complex.This data not only increases the computational burden of model training but also makes information extraction more difficult.To address these issues,this paper proposes an MD-MRD-ResNeXt model for abnormal network traffic detection.To fully utilize the multi-scale information in network traffic,a Multi-scale Dilated feature extraction(MD)block is introduced.This module can effectively understand and process information at various scales and uses dilated convolution technology to significantly broaden the model’s receptive field.The proposed Max-feature-map Residual with Dual-channel pooling(MRD)block integrates the maximum feature map with the residual block.This module ensures the model focuses on key information,thereby optimizing computational efficiency and reducing unnecessary information redundancy.Experimental results show that compared to the latest methods,the proposed abnormal traffic detection model improves accuracy by about 2%.

Abnormal State Detection in Lithium-ion Battery Using Dynamic Frequency Memory and Correlation Attention LSTM Autoencoder

This paper addresses the challenge of identifying abnormal states in Lithium-ion Battery(LiB)time series data.As the energy sector increasingly focuses on integrating distributed energy resources,Virtual Power Plants(VPP)have become a vital new framework for energy management.LiBs are key in this context,owing to their high-efficiency energy storage capabilities essential for VPP operations.However,LiBs are prone to various abnormal states like overcharging,over-discharging,and internal short circuits,which impede power transmission efficiency.Traditional methods for detecting such abnormalities in LiB are too broad and lack precision for the dynamic and irregular nature of LiB data.In response,we introduce an innovative method:a Long Short-Term Memory(LSTM)autoencoder based on Dynamic Frequency Memory and Correlation Attention(DFMCA-LSTM-AE).This unsupervised,end-to-end approach is specifically designed for dynamically monitoring abnormal states in LiB data.The method starts with a Dynamic Frequency Fourier Transform module,which dynamically captures the frequency characteristics of time series data across three scales,incorporating a memory mechanism to reduce overgeneralization of abnormal frequencies.This is followed by integrating LSTM into both the encoder and decoder,enabling the model to effectively encode and decode the temporal relationships in the time series.Empirical tests on a real-world LiB dataset demonstrate that DFMCA-LSTM-AE outperforms existing models,achieving an average Area Under the Curve(AUC)of 90.73%and an F1 score of 83.83%.These results mark significant improvements over existing models,ranging from 2.4%–45.3%for AUC and 1.6%–28.9%for F1 score,showcasing the model’s enhanced accuracy and reliability in detecting abnormal states in LiB data.

Abnormal Action Detection Based on Parameter-Efficient Transfer Learning in Laboratory Scenarios

Laboratory safety is a critical area of broad societal concern,particularly in the detection of abnormal actions.To enhance the efficiency and accuracy of detecting such actions,this paper introduces a novel method called TubeRAPT(Tubelet Transformer based onAdapter and Prefix TrainingModule).Thismethod primarily comprises three key components:the TubeR network,an adaptive clustering attention mechanism,and a prefix training module.These components work in synergy to address the challenge of knowledge preservation in models pretrained on large datasets while maintaining training efficiency.The TubeR network serves as the backbone for spatio-temporal feature extraction,while the adaptive clustering attention mechanism refines the focus on relevant information.The prefix training module facilitates efficient fine-tuning and knowledge transfer.Experimental results demonstrate the effectiveness of TubeRAPT,achieving a 68.44%mean Average Precision(mAP)on the CLA(Crazy LabActivity)small-scale dataset,marking a significant improvement of 1.53%over the previous TubeR method.This research not only showcases the potential applications of TubeRAPT in the field of abnormal action detection but also offers innovative ideas and technical support for the future development of laboratory safety monitoring technologies.The proposed method has implications for improving safety management systems in various laboratory environments,potentially reducing accidents and enhancing overall workplace safety.

Vehicle Abnormal Behavior Detection Based on Dense Block and Soft Thresholding

With the rapid advancement of social economies,intelligent transportation systems are gaining increasing atten-tion.Central to these systems is the detection of abnormal vehicle behavior,which remains a critical challenge due to the complexity of urban roadways and the variability of external conditions.Current research on detecting abnormal traffic behaviors is still nascent,with significant room for improvement in recognition accuracy.To address this,this research has developed a new model for recognizing abnormal traffic behaviors.This model employs the R3D network as its core architecture,incorporating a dense block to facilitate feature reuse.This approach not only enhances performance with fewer parameters and reduced computational demands but also allows for the acquisition of new features while simplifying the overall network structure.Additionally,this research integrates a self-attentive method that dynamically adjusts to the prevailing traffic conditions,optimizing the relevance of features for the task at hand.For temporal analysis,a Bi-LSTM layer is utilized to extract and learn from time-based data nuances.This research conducted a series of comparative experiments using the UCF-Crime dataset,achieving a notable accuracy of 89.30%on our test set.Our results demonstrate that our model not only operates with fewer parameters but also achieves superior recognition accuracy compared to previous models.

Abnormal Action Recognition with Lightweight Pose Estimation Network in Electric Power Training Scene

Electric power training is essential for ensuring the safety and reliability of the system.In this study,we introduce a novel Abnormal Action Recognition(AAR)system that utilizes a Lightweight Pose Estimation Network(LPEN)to efficiently and effectively detect abnormal fall-down and trespass incidents in electric power training scenarios.The LPEN network,comprising three stages—MobileNet,Initial Stage,and Refinement Stage—is employed to swiftly extract image features,detect human key points,and refine them for accurate analysis.Subsequently,a Pose-aware Action Analysis Module(PAAM)captures the positional coordinates of human skeletal points in each frame.Finally,an Abnormal Action Inference Module(AAIM)evaluates whether abnormal fall-down or unauthorized trespass behavior is occurring.For fall-down recognition,three criteria—falling speed,main angles of skeletal points,and the person’s bounding box—are considered.To identify unauthorized trespass,emphasis is placed on the position of the ankles.Extensive experiments validate the effectiveness and efficiency of the proposed system in ensuring the safety and reliability of electric power training.

First record of abnormal body coloration in a rockfish Sebastes koreanus(Scorpaenoidei:Sebastidae)from coastal water of China based on morphological characteristics and DNA barcoding

The first record of abnormal body coloration in Sebastes koreanus Kim and Lee,1994,from the Yellow Sea of China,was documented based on morphological characteristics and DNA barcoding.The two rockfish specimens were collected from the coastal waters of Qingdao,China,and the whole body and all fins of them were red.Of the two red-colored rockfish,there were tiny deep red spots on each fin,2 red radial stripes behind and below the eyes and 1 large deep red blotch on the opercula,while the similar stripe and spot patterns are also present in the S.koreanus specimens with normal body coloration.The countable characteristics of the two specimens are in the range of the morphometry of S.koreanus.To further clarify the species identity and taxonomic status of the two specimens,DNA barcode analysis was carried out.The genetic distance between the red-colored rockfish and S.koreanus was 0,and the minimum net genetic distances between the red-colored rockfish and other Sebastes species except for S.koreanus were 3.0%,which exceeds the threshold of species delimitation.The phylogenetic analysis showed that the DNA barcoding sequences of the two red-colored rockfish clustered with the S.koreanus sequences.The above results of DNA barcode analysis also support that the two red-colored rockfish could be identified as the species of S.koreanus.The mechanism of color variation in S.koreanus is desirable for further research and the species could be an ideal model to study the color-driven speciation of the rockfishes.

A Clinical Study to Assess the Effectiveness of Oral Combination Kit Therapy in Syndromic Management of Abnormal Vaginal Discharge (FEMINE Study) in Kinshasa, Democratic Republic of Congo

Background: Vaginal discharge is one of most common and nagging problems that women face. About 20% - 25% of women who visit gynecology department complain of vaginal discharge and leucorrhoea. An orally administered combination kit, containing 2 g secnidazole, 1 g azithromycin and 150 mg fluconazole (Azimyn FS Kit), has been successfully evaluated in clinical trials and used in several countries for management syndromic vaginal discharge due to infections. Methods: This is a longitudinal study which aimed to verify the clinical efficacy of the combined oral kit containing secnidazole, azithromycin and fluconazole (Azimyn FS Kit®) in the syndromic treatment of abnormal vaginal discharge in patients received in outpatient consultations in Kinshasa/DR Congo from March to September 2023. Results: Majority of patients had whitish vaginal discharge (51.6%) of average abundance (56.2%), accompanied by pruritus in 72.1% of cases, and dyspareunia in 23.5% of cases and hypogastralgia in 40.2% of cases. One week after treatment with the Azimyn FS® combined kit, at the greatest majority of patients (97.3%), abnormal vaginal discharge had decreased by more than 50% (84.1%). Two weeks after treatment with the Azimyn FS® combined kit, almost all patients (97.3%) no longer had abnormal vaginal discharge which had completely disappeared. Conclusion: A single dose of secnidazole, azithromycin and fluconazole in the form of an oral combi-kit (Azimyn FS Kit) has shown excellent therapeutic effectiveness in the syndromic treatment of abnormal vaginal discharge wherein patients were treated without diagnostic confirmation.

High-grade serous carcinoma of the fallopian tube in a young woman with chromosomal 4q abnormality:A case report

BACKGROUND Few studies have reported an association between an increased risk of acquiring cancers and survival in patients with 4q deletion syndrome.This study presents a rare association between chromosome 4q abnormalities and fallopian tube highgrade serous carcinoma(HGSC)in a young woman.CASE SUMMARY A 35-year-old woman presented with acute dull abdominal pain and a known chromosomal abnormality involving 4q13.3 duplication and 4q23q24 deletion.Upon arrival at the emergency room,her abdomen appeared ovoid and distended with palpable shifting dullness.Ascites were identified through abdominal ultrasound,and computed tomography revealed an omentum cake and an enlarged bilateral adnexa.Blood tests showed elevated CA-125 levels.Paracentesis was conducted,and immunohistochemistry indicated that the cancer cells favored an ovarian origin,making us suspect ovarian cancer.The patient underwent debulking surgery,which led to a diagnosis of stage IIIC HGSC of the fallopian tube.Subsequently,the patient received adjuvant chemotherapy with carboplatin and paclitaxel,resulting in stable current condition.CONCLUSION This study demonstrates a rare correlation between a chromosome 4q abnormality and HGSC.UBE2D3 may affect crucial cancer-related pathways,including P53,BRCA,cyclin D,and tyrosine kinase receptors,thereby possibly contributing to cancer development.In addition,ADH1 and DDIT4 may be potential influencers of both carcinogenic and therapeutic responses.

Analysis of the Efficacy of Prenatal B-Ultrasound in Diagnosing Fetal Abnormalities

Objective:To explore the positive significance of using prenatal B-ultrasound in diagnosing fetal abnormalities.Methods:A total of 200 pregnant women who visited Shaanxi Provincial People’s Hospital between January 2023 and January 2024 were recruited as the research subjects.All pregnant women received prenatal examinations.A retrospective analysis was carried out to analyze the positive significance of prenatal B-ultrasound examination in the diagnosis of fetal abnormalities.Results:Prenatal B-ultrasound examination detected 10 cases of fetal abnormalities,with a detection rate of 5.00%.When compared with the postnatal examination results of 5.50%,the difference was insignificant(P>0.05).Moreover,comparing the fetal limb abnormalities and cardiovascular abnormalities in prenatal B-ultrasound examination and postnatal examination,one case of congenital heart disease was missed in the prenatal B-ultrasound examination,and the others were consistent with the postnatal examination results,with a coincidence rate of 90.91%,indicating a high compliance rate.Conclusion:Fetal abnormalities have a great impact on mothers,babies,and families,and it is particularly important to strengthen diagnosis during this process.Prenatal B-ultrasound examination can improve the accuracy of diagnosis of fetal abnormalities and can be promoted in clinical practice as a basis for screening fetal abnormalities.

A NEW KIND OF SURFACTANT:LONG-CHAIN ALKYLTRIPHENYLPHOSPHONIUM HALIDES Ⅲ.AN“ABNORMAL”QUENCHING OF PYRENE FLUORESCENCE BY PHOSPHONIUMS WITH DIFFERENT LENGTHS OF ALKYL CHAIN

A study of the quenching of pyrene fluorescence by a series of alkyltriphenylphosphonium bromides indi- cated the coiling conformation of ionic surfactant in aqueous solution.Formation of pyrene excimer in cetyltriph- enylphosphonium solution strengthened the conclusion.

Evaluation of Fourier Transform Infrared Spectroscopy for Diagnosis of Peroxisomal Diseases with Abnormal Very-Long-Chain Fatty Acid Metabolism

Very long chain fatty acids (VLCFAs) are accumulated in cells and blood in patients with peroxisomal diseases, such as adrenoleukodystrophy (ALD) and Zellwger Syndrome (ZS). The purpose of this study is to investigate usefulness of Fourier transform infrared spectroscopy (FTIR) with attenuated total reflection (ATR) analysis method for clinical diagnosis of those diseases, thereby we measured the infrared spectra of the sera of patients and healthy controls. Correlation coefficients between 2nd derivative FTIR spectra of the serum samples and the VLCFA content ratio which is used as a clinical parameter to date were comprehensively calculated to investigate which wavenumber showed high correlation with the VLCFA ratio. Multiple regression analysis using the serum FTIR spectra showed that high correlations were observed with VLCFA ratios (C26:0/C22:0 ratio), and we could construct a suitable regression model (R2 = 0.97, p ﹣19). In addition, the model system using various VLCFAs in newborn bovine serum also showed that several FTIR peaks in 800 ~ 900 cm﹣1 region were found to have good correlation with VLCFA ratios. Our results support that FTIR analysis is useful for diagnosis of peroxisomal diseases.

Application of Abnormal Touchdown PCR with High Degeneracy Primer in Amplification of Large-Family Genes

[Objective] The aim was to explore the special methods for amplification of large-family genes by using primers with high degeneracy.[Method] By using the primers with high degeneracy,conventional PCR,conventional touchdown PCR and the optimized abnormal touchdown PCR were respectively carried out to amplify the genomic DNA of Cyprinus carpio.[Result] Only one evident electrophoretic band and a few Sox genes were obtained by using normal PCR;no obvious electrophoretic band but dispersive product was obtained by normal touchdown PCR;ideal result was obtained by the abnormal touchdown PCR that three evident electrophoretic bands and much more Sox genes were amplified.[Conclusion] The research provided theoretical basis for the optimization and selection of PCR amplification conditions of the large-family genes.

CATGUT EMBEDDING FOR TREATMENT OF SIMPLE OBESITY COMPLICATED WITH ABNORMAL BLOOD FAT

Objective To compare the therapeutic effect of catgut embedding combined with diet plus exercise with that of diet plus exercise in treating simple obesity complicated with abnormal blood fat. Methods A prescription of diet plus exercise was given to the patients in a control group, and catgut embedding was added to the prescription in a treatment group. It was given once every 15 days for the 1st three treatments, and once every month for the 2^nd three treatments. Six treatments constituted a therapeutic course. Body weight and blood fat were measured before and half a year since treatment. Results After treatment, BMI, TO, TG and LDL were very significantly improved in the treatment group （P〈0.01）, and BMI and TG were very significantly （P〈0.01） and TO and LDL were significantly （P〈0.05） improved in the control group. HDL was not obviously improved in both groups （P〉0.05）. The improvement of TO, TG and LDL in the treatment group was significantly more than that in the control group （P〈0.01）, but no difference in improvement of BMI and HDL was found between the two groups （P〉0.05）. Conclusion The therapy of diet plus exercise was effective in body weight reduction and lowering blood fat in patients with simple obesity complicated with abnormal blood fat, and catgut embedding used in combination was even better in lowering blood fat.

Analysis on the Features of Abnormal Meteorological Elements before Chongqing Earthquakes

The situations of four major earthquakes occurred in Chongqing in modern times were analyzed in this paper.According to the study of the relationship between drought and earthquake and the study on five abnormal indices of meteorological elements,the pre-earthquake abnormal meteorological elements of these earthquakes occurred in Tongjing Town of Yubei,Chongqing in 1989,Xuxi of Rongchang in Chongqing in 1997,Rongchang County of Chongqing in 1999 respectively were systemically tested.Finally,the assumption of establishing an earthquake warning system of abnormal meteorological elements in the whole nation,especially in some high-risk earthquake areas was proposed.

Abnormality of Magnetic Behavior and Resistivity of La_(0.7-x)Dy_x Sr_(0.3)MnO_3 (0.00≤x≤0.30)System at Low Temperature

By measuring M-T curves, ρ-T curves and MR-T curves of the samples under different temperatures, the influence of Dy doping （0.00 ≤ x ≤0.30） on the magnetic and electric properties of La0.7-xDyxSr0.3MnO3 has been studied. The experimental results show that, with the increase of the Dy content, the system undergoes a transition from long range ferromagnetic order to the cluster-spin glass state and further to antiferromagnetic order. For the samples with x=0.20 and 0.30, their magnetic behaviors are abnormal at low temperature, and their resistivities at low temperature have a minimum value. These peculiar phenomena not only come from the lattice effect induced by doping, but also from extra magnetic coupling induced by doping.