Method For Diagnosis Research Articles

New insight in cervical cancer diagnosis using convolution neural network architecture

<p>The Pap smear is a screening method for early cervical cancer diagnosis. The selection of the right optimizer in the convolutional neural network (CNN) model is key to the success of the CNN in image classification, including the classification of cervical cancer Pap smear images. In this study, stochastic gradient descent (SGD), root mean square propagation (RMSprop), Adam, AdaGrad, AdaDelta, Adamax, and Nadam optimizers were used to classify cervical cancer Pap smear images from the SipakMed dataset. Resnet-18, Resnet-34, and VGG-16 are the CNN architectures used in this study, and each architecture uses a transfer-learning model. Based on the test results, we conclude that the transfer learning model performs better on all CNNs and optimization techniques and that in the transfer learning model, the optimization has little influence on the training of the model. Adamax, with accuracy values of 72.8% and 66.8%, had the best accuracy for the VGG-16 and Resnet-18 architectures, respectively. Resnet-34 had 54.0%. This is 0.034% lower than Nadam. Overall, Adamax is a suitable optimizer for CNN in cervical cancer classification on Resnet-18, Resnet-34, and VGG-16 architectures. This study provides new insights into the configuration of CNN models for Pap smear image analysis.</p>

Subclinical hyperthyroidism and the risk of dementia: A meta-analysis.

Accumulating evidence suggests that thyroid dysfunction may be related to the risk of dementia. However, previous studies evaluating the association between subclinical hyperthyroidism and the risk of dementia showed inconsistent results. This systematic review and meta-analysis were performed to evaluate the relationship between subclinical hyperthyroidism and the incidence of dementia in the general population. Cohort studies relevant were retrieved by searching the electronic databases including PubMed, Web of Science, and Embase. A random-effects model was used to combine the data by incorporating the influence of between-study heterogeneity. Subgroup and meta-regression analyses were performed to investigate the source of heterogeneity. Nine cohort studies including 49,218 community-derived participants were included. Among them, 3177 (6.5%) had subclinical hyperthyroidism at baseline. During a mean follow-up of 10.2 years, 4044 participants developed dementia. The pooled results showed that compared to the participants with euthyroidism, those with subclinical hyperthyroidism had a higher incidence of dementia (risk ratio: 1.38, 95% confidence interval: 1.09 to 1.74, p=.006; I2=47%). Subgroup analyses according to study design, age of the participants, methods for diagnosis of dementia, or analytic model did not significantly change the results. The univariate meta-regression showed that the cutoff of thyroid-stimulating hormone for defining subclinical hyperthyroidism negatively affected the association between subclinical hyperthyroidism and dementia (coefficient: -1.44, p=.009), which completely explained the heterogeneity (residual I2=0%). Subjects with subclinical hyperthyroidism may have a higher risk of dementia compared to those with euthyroidism.

Lightweight Network Bearing Intelligent Fault Diagnosis Based on VMD-FK-ShuffleNetV2

With the increasing complexity of mechanical equipment and diversification of deep learning models, vibration signals collected from such equipment are susceptible to noise interference. Moreover, traditional neural network models struggle to be effectively deployed in production environments with limited computational resources, severely impacting the accurate extraction and effective diagnosis of FK fault characteristics. In response to this challenge, this study proposes a fault diagnosis method for rolling bearings, integrating a lightweight ShuffleNetV2 network with variational mode decomposition (VMD) and the fast kurtogram (FK) algorithm. Initially, this paper introduces an enhanced FK method where the VMD algorithm is employed for data denoising, extracting FK post-denoising. These feature maps not only preserve critical signal information but also simplify data complexity. Subsequently, these feature maps are utilized to train and test the ShuffleNetV2 model, facilitating effective fault identification and classification. Ultimately, by conducting experimental comparisons with several mainstream lightweight network models, such as MobileNet and SqueezeNet, as well as traditional convolutional neural network models, this study validates the effectiveness of the proposed method in extracting fault characteristics from vibration signals, demonstrating superior diagnostic accuracy and computational efficiency. This provides a novel technical approach for health monitoring and fault diagnosis of industrial bearings and offers theoretical and experimental support for the deployment of lightweight networks in industrial applications.

Fault stands out in contrast: Zero-shot diagnosis method based on dual-level contrastive fusion network for control moment gyroscopes predictive maintenance

Fault stands out in contrast: Zero-shot diagnosis method based on dual-level contrastive fusion network for control moment gyroscopes predictive maintenance

Connexin 43 controls metastatic behavior in triple negative breast cancer through TGFβ1-Smad3-intergin αV signaling axis Based on optical image diagnosis

Abnormal expression of connexin 43 (Cx43) contributes to the development and progression of cancer. However, its regulation is complex and dependent on the environment. The expression of Cx43 in triple-negative cancer lesions was analyzed by immunohistochemistry and optical coherence tomography using experimental models and clinical samples. The model of TGFβ1-SMad3-in-αv signal axis was established and verified by experiments. The results show that Cx43 plays a key role in the regulation of triple-negative cancer metastasis. In vivo, over-expressed Cx43 decreased tumor volume and inhibited ITGαV, TGF-β1, Smad3 and N-cadherin expressions, but enhanced the E-cadherin. Cx43 had the lowest expression in the TNBC samples, especially in lymph node metastatic TNBC patients and had a negative correlation with ITG alpha V, TGF-β1 and Smad3.The study demonstrated Cx43 controlled metastatic behavior through TGF-β1 -Smad3-ITG αV signaling axis in MDA-MB-231 cells, providing evidence for Cx43’s function in TNBC. The optical image diagnosis method can realize the identification and quantitative evaluation of early cancer triple negative, and provide a new strategy and means for the treatment of cancer triple negative.

Rolling bearings fault diagnosis based on two-stage signal fusion and deep multi-scale multi-sensor network

In order to realize high-precision diagnosis of bearings faults in a multi-sensor detection environment, a fault diagnosis method based on two-stage signal fusion and deep multi-scale multi-sensor networks is proposed. Firstly, the signals are decomposed and fused using weighted empirical wavelet transform to enhance weak features and reduce noise. Secondly, an improved random weighting algorithm is proposed to perform a second weighted fusion of the signals to reduce the total mean square error. The fused signals are input into the deep multi-scale residual network, the feature information of different convolutional layers is extracted through dilated convolution, and the features are fused using pyramid theory. Finally, the bearings states are classified according to the fusion features. Experiment results show the effectiveness and superiority of this method.

Diagnosis of Pancreatic Tumors: How Much Does the Triple Diagnosis Method Help?

Diagnosis of Pancreatic Tumors: How Much Does the Triple Diagnosis Method Help?

Explainable fault diagnosis method for process flow based on data augmentation with system graph relationship

The main objective of process industrial systems is to ensure safe operation. Signal fluctuations resulting from equipment failures and variable abnormalities can progressively propagate over the entire system, potentially resulting in fault conditions. However, the sporadic occurrence of fault conditions leads to a scarcity of data samples for diagnosis models. A fault diagnosis method for process flow based on data augmentation with system graph relationships is proposed. Propagation paths of fault signals are generated through graph relationships of systems. Simultaneously, the data of multiple nodes in paths is transformed to generate augmentation samples. To ensure comprehensive learning of the information included in augmentation samples, a large number of samples are generated for pre-training based on real-world data from a system. The explainability analysis method is used to analyze the focus area of diagnostic networks on samples with and without augmentation. The experimental results demonstrate that the proposed method can substantially improve diagnostic accuracy and explainability, hence offering advantages for diagnosis tasks in small sample cases.

A novel bearing fault diagnosis method for compound defects via zero-shot learning

A novel bearing fault diagnosis method for compound defects via zero-shot learning

New Fault Diagnosis Method for Rolling Bearings Based on Improved Residual Shrinkage Network Combined with Transfer Learning.

The fault diagnosis of rolling bearings is faced with the problem of a lack of fault data. Currently, fault diagnosis based on traditional convolutional neural networks decreases the diagnosis rate. In this paper, the developed adaptive residual shrinkage network model is combined with transfer learning to solve the above problems. The model is trained on the Case Western Reserve dataset, and then the trained model is migrated to a small-sample dataset with a scaled-down sample size and the Jiangnan University bearing dataset to conduct the experiments. The experimental results show that the proposed method can efficiently learn from small-sample datasets, improving the accuracy of the fault diagnosis of bearings under variable loads and variable speeds. The adaptive parameter-rectified linear unit is utilized to adapt the nonlinear transformation. When rolling bearings are in operation, noise production is inevitable. In this paper, soft thresholding and an attention mechanism are added to the model, which can effectively process vibration signals with strong noise. In this paper, the real noise is simulated by adding Gaussian white noise in migration task experiments on small-sample datasets. The experimental results show that the algorithm has noise resistance.

Fault diagnosis and intelligent maintenance of industry 4.0 power system based on internet of things technology and thermal energy optimization

The application of Internet of Things technology provides a new opportunity for the fault diagnosis and maintenance of power system. This study aims to explore how to improve the fault diagnosis ability of power system through Internet of Things technology, and realize the efficient utilization of heat energy, so as to achieve the goal of intelligent maintenance. Based on the analysis of current power system operation status, this paper determines the key role of thermal energy management in improving system operation efficiency and reducing energy consumption. It then uses iot sensors and data analytics to monitor heat flow and loss in the power system in real time, identifying potential points of failure through big data. In order to realize intelligent maintenance, this paper designs a fault prediction model based on thermal energy optimization, combined with machine learning algorithm, to further improve the accuracy of fault diagnosis. The experimental results show that the fault diagnosis method combined with the Internet of Things technology can significantly reduce the fault incidence and optimize the efficiency of heat energy use. By applying this model, the overall operating cost of the power system is reduced and the maintenance efficiency is improved.

A Bearing Fault Diagnosis Method Based on Vibration Signal Extension and Time–Frequency Information Fusion Network Under Small Sample Conditions

A Bearing Fault Diagnosis Method Based on Vibration Signal Extension and Time–Frequency Information Fusion Network Under Small Sample Conditions

Analysis of the structural integrity of wooden structures in service: case study with diagnostic methodologies and rehabilitation strategies

The rehabilitation, restoration, or reinforcement of wooden structures requires a thorough assessment of their "health" status. This evaluation is akin to Structural Integrity Assessment (SIA), which employs multidisciplinary techniques to determine the state of accumulated damage and its growth rate, enabling the prediction of the remaining service life of the structure and the scheduling of corrective actions. This case study aims to investigate the structural health of a wooden pergola in Belo Horizonte, MG, Brazil, applying SIA based on methods of propedeutics, diagnosis, and therapy. Non-destructive tests such as acoustic tomography, controlled penetration test (Resistograph), and impact test (Pilodyn) were conducted for propedeutics and diagnosis. Macroscopic visual assessment identified the wood species used in the pergola: Cumaru, Angelim Vermelho, and an unidentified species. The wood strength class was determined by the resistograph, and biotic, abiotic, and structural damages were evaluated. The structural performance analysis, considering the actual sections and the physical and mechanical characteristics of the wood, was performed using SAP 2000 software, with the verification of structural elements and connections according to the Brazilian standard NBR 7190. The study concludes by presenting therapies of a constructive nature, treatment and protection, and structural character.

Unraveling Alzheimer’s Disease Classification with Deep Learning: A Comprehensive Review

Abstract: Alzheimer's disease (AD) is a neurological disease that progresses over time and is the primary global cause of dementia. Timely and accurate diagnosis is essential for therapeutic and interventional success. Conventional approaches, like clinical evaluations and neuroimaging procedures, are not always able to detect the illness at an early stage. This paper provides an extensive overview of current developments in using deep learning methods for AD early diagnosis and Identification. Numerous approaches have been put up, utilizing diverse forms of data such as MRI scans, eye-tracking actions, and text data that is clinically significant. Convolutional neural networks (CNNs), deep neural networks (DNNs), and long short-term memory networks (LSTMs) are just a few of the deep learning designs used by these models, which highlight how flexible and adaptive these methods are. Using cutting-edge methods to extract discriminative features from the data, feature extraction and selection have become essential components of these models. Additionally, a number of studies have concentrated on improving model performance through the use of methods such as depth-wise convolutional procedures, ensemble learning approaches, and particle swarm optimization for hyperparameter tweaking. Even with high accuracy rates attained, there is still opportunity for development, particularly with regard to managing data scarcity and model interpretability. This survey indicates possible routes for future research and offers insightful information about the state of deep learning applications in AD categorization.

About the global strategy for the prevention of influenza in 2019–2030

The development of modern methods of epidemiological control, on the one hand, and the creation of modern methods of diagnosis, prevention, and treatment, which will be available to all strata of society, on the other hand, is the key to preventing the pandemic spread of influenza in the world. Today, influenza is a serious threat to human health globally, which covers all countries of the world. Thus, according to the World Health Organization estimates, about 1 billion cases of influenza are registered annually worldwide, of which 3–5 million are severe cases and 290,000–650,000 are cases of death due to severe complications of respiratory dysfunction caused by influenza. Children are more susceptible to acute respiratory viral infections and influenza in the general population due to the physiological instability of the immune system, being mostly in crowded places and in large social groups (kindergartens, schools, entertainment centers), which increases the probability of infection. The risk group consists of patients with chronic pathology, particularly affecting the heart and lungs, who have problems with the immune system.

A new chiller fault diagnosis method under the imbalanced data environment via combining an improved generative adversarial network with an enhanced deep extreme learning machine

The existing chiller fault diagnosis approaches often ignore the problem of data imbalance of chiller, which leads to low accuracy in diagnosing minority class fault samples. To conquer this issue, this paper proposes an improved generative adversarial network (IGAN) with an enhanced deep extreme learning machine (EDELM) method. Firstly, to better learn the latent structure of chiller fault data, the multi-head attention (MHA) mechanism is integrated into the traditional generative adversarial network (GAN) method to generate new samples that are more in line with the distribution of minority class fault samples for the purpose of obtaining a rebalanced dataset. Secondly, to fully handle the nonlinear features hidden in the massive chiller data, the deep extreme learning machine (DELM) basic classifier is trained on the rebalanced dataset. To enhance more attention to the misclassified samples, the adaptive boosting (AdaBoost) ensemble strategy is employed to train multiple DELM basic classifiers by updating the sample weights following the classification results through the iterative rounds. The voting weight of the current DELM basic classifier is given according to its fault diagnosis accuracy. Finally, multiple DELM basic classifiers are ensembled according to their voting weights to obtain the final ensemble classifier. The pattern of the snapshot sample is determined through the weighted voting strategy. Detailed experimental results based on the research project 1043 (RP-1043) conducted by the American society of heating, refrigeration, and air conditioning engineers (ASHRAE) confirm the effectiveness of the proposed IGAN-EDELM approach under imbalanced data environments.

Review of imbalanced fault diagnosis technology based on generative adversarial networks

Abstract In the field of industrial production, machine failures not only negatively affect productivity and product quality, but also lead to safety accidents, so it is crucial to accurately diagnose machine failures in time and take appropriate measures. However, machines cannot operate with faults for extended periods, and the diversity of fault modes results in limited data collection, posing challenges to building accurate fault prediction models. Despite recent advancements, intelligent fault diagnosis methods based on traditional sampling and machine learning have shown notable progress. Nonetheless, these methods heavily rely on human expertise, making it challenging to extract comprehensive feature information. To address these challenges, numerous imbalance fault diagnosis methods based on generative adversarial networks (GANs) have emerged, GANs can generate realistic samples that conform to the distribution of the original data, showing promising results in diagnosing imbalances in critical components such as bearings and gears, despite their great potential, GAN methods also face challenges, including difficulties in training and generating abnormal samples. However, whether it is GAN-based resampling technology or traditional sampling technology, there are fewer reviews on noise-containing imbalance, intra- and inter-class dual imbalance, multi-class imbalance, time series imbalance and other problems in small samples, and there is a lack of a more comprehensive summary of the solutions to the above imbalance problems. Therefore, the purpose of this paper is to deeply explore the imbalance problems under various failure modes, and review and analyze the research methods and results based on GANs on this basis. By suggesting future research directions, this paper aims to provide guidance and reference for research in the field of industrial production maintenance.

Cross-domain zero-shot learning for enhanced fault diagnosis in high-voltage circuit breakers

Ensuring the stability of high-voltage circuit breakers (HVCBs) is crucial for maintaining an uninterrupted supply of electricity. Existing fault diagnosis methods typically rely on extensive labeled datasets, which are challenging to obtain due to the unique operational contexts and complex mechanical structures of HVCBs. Additionally, these methods often cater to specific HVCB models and lack generalizability across different types, limiting their practical applicability. To address these challenges, we propose a novel cross-domain zero-shot learning (CDZSL) approach specifically designed for HVCB fault diagnosis. This approach incorporates an adaptive weighted fusion strategy that combines vibration and current signals. To bypass the constraints of manual fault semantics, we develop an automatic semantic construction method. Furthermore, a multi-channel residual convolutional neural network is engineered to distill deep, low-level features, ensuring robust cross-domain diagnostic capabilities. Our model is further enhanced with a local subspace embedding technique that effectively aligns semantic features within the embedding space. Comprehensive experimental evaluations demonstrate the superior performance of our CDZSL approach in diagnosing faults across various HVCB types.

Diagnostic and prognostic value of serum Cys-C, retinol-binding protein, and ischemia-modified albumin in patients with coronary heart disease: A diagnostic accuracy study.

The use of 3 biomarkers - cystatin-C (Cys-C), retinol-binding protein (RBP), and ischemia-modified albumin (IMA) - for the clinical classification and outcome of coronary heart disease (CHD) has not been adequately evaluated. We explored the serum levels of these 3 markers and evaluated their diagnostic and prognostic values in patients with CHD. This retrospective case-control study, conducted between June 2017 and June 2018, included 201 patients with CHD hospitalized at the Henan Provincial People's Hospital and 127 healthy individuals from Henan Provincial People's Hospital as controls. Cys-C, RBP, IMA levels, and other laboratory parameters in the 2 groups were determined, and patient outcomes were analyzed. Cys-C, RBP, and IMA levels were higher in the case group than in the control group (P < .05). Logistic regression analysis confirmed that these 3 biomarkers were independent risk factors for CHD. Each indicator has clinical significance in the diagnosis and prognosis of CHD, with RBP being the most significant. The AUC value for CHD detection using a combination of the 3 indicators was 0.783, and the sensitivity and specificity values were 78% and 74.6%, respectively. Simultaneous detection of Cys-C, RBP, and IMA could be an optimal method for early diagnosis and prognosis of CHD.

Технология получения вакуумных ионно-плазменных износостойких покрытий

A review of the technologies of vacuum ion plasma (VIP) coating spraying based on the reasonability of science intensity, its criteria and evaluation methods is carried out. The technological features of producing VIP coatings are viewed with the emphasis on the process of coating formation on a substrate, which occurs under the impact of the most powerful forces in nature, i.e. these are forces of interatomic interaction. This leads to a very high level of cohesive strength of the coatings, which results in wear resistance and corrosion resistance. This leads to a very high level of cohesive strength of the coatings, succeeding in wear and corrosion resistance. Methods of research, diagnosis and testing of VIP coatings, due to the peculiarities of their structure and properties, include, as a rule, equipment and techniques of leading world manufacturers in the field of electron microscopy, microrentgen spectral analysis, diffraction analysis, X-ray photoelectron spectrometry, continuous and dynamic indentation, bench testing of unique properties. With respect to scientific and practical activities of the authors, examples of coatings of various nature (nitride, carbon, metalloceramic), different architectures (monolayer – single-phase, multilayer – 2D composites, dispersed – 3D composites) and various applications (wear–resistant, tribotechnical, antierosion, thermal barrier) are given. In particular, some types of nitride coatings TiN, TiAlN, CrAlSiN, which are characterized by high hardness H  24 GPa and abrasive wear resistance, are in the focus. However, in conditions of relatively smooth sliding friction, only the multiphase nanostructured CrAlSiN coating retains wear resistance. In conditions of drop-impact erosion, nanocompositional multilayer VIP coatings of TiN/MoN composition demonstrate the highest resistance, which compete with the recognized champion in this field - welded plates of stellite VZK (WCoCr). Despite the fact that the thickness of the VIP coatings viewed in the paper is a film of 1...10 microns, whereas the stellite plates have a thickness of at least 4 mm. In conclusion, it is noted that VIP technology continues to develop new materials, for example, to create diamond-like coatings or coatings made of high-entropy alloys. VIP technology corresponds to a high level of science intensity, and VIP coatings are promising for putting to use in mechanical engineering.