Methodology For Diagnosis Research Articles

Development and evaluation of an ensemble neural network based methodology for rapid diagnosis and fault classification in unmanned aerial vehicles

Development and evaluation of an ensemble neural network based methodology for rapid diagnosis and fault classification in unmanned aerial vehicles

Accurate prediction of colorectal cancer diagnosis using machine learning based on immunohistochemistry pathological images

Colorectal cancer (CRC) ranks as the third most prevalent tumor and the second leading cause of mortality. Early and accurate diagnosis holds significant importance in enhancing patient treatment and prognosis. Machine learning technology and bioinformatics have provided novel approaches for cancer diagnosis. This study aims to develop a CRC diagnostic model based on immunohistochemical staining image features using machine learning methods. Initially, CRC disease-specific genes were identified through bioinformatics analysis, SVM-RFE and Random Forest algorithm utilizing RNA-seq data from both GEO and TCGA databases. Subsequently, verification of these genes was performed using proteomics data from CPTAC and HPA database, resulting in identification of target proteins (AKR1B10, CA2, DHRS9, and ZG16) for further investigation. SVM and CNN were then employed to analyze and integrate the characteristics of immunohistochemical images to construct a reliable CRC diagnostic model. During the training and validation process of this model, cross-validation along with external validation methods were implemented to ensure accuracy and reliability. The results demonstrate that the established diagnostic model exhibits excellent performance in distinguishing between CRC and normal controls (accuracy rate: 0.999), thereby presenting potential prospects for clinical application. These findings are expected to provide innovative perspectives as well as methodologies for personalized diagnosis of CRC while offering more precise references for promising treatment.

Acoustical features as knee health biomarkers: A critical analysis

Acoustical knee health assessment has long promised an alternative to clinically available medical imaging tools, but this modality has yet to be adopted in medical practice. The field is currently led by machine learning models processing acoustical features, which have presented promising diagnostic performances. However, these methods overlook the intricate multi-source nature of audio signals and the underlying mechanisms at play. By addressing this critical gap, the present paper introduces a novel causal framework for validating knee acoustical features. We argue that current machine learning methodologies for acoustical knee diagnosis lack the required assurances and thus cannot be used to classify acoustic features as biomarkers. Our framework establishes a set of essential theoretical guarantees necessary to validate this claim. We apply our methodology to three real-world experiments investigating the effect of researchers’ expectations, the experimental protocol, and the wearable employed sensor. We reveal latent issues such as underlying shortcut learning and performance inflation. This study is the first independent result reproduction study in acoustical knee health evaluation. We conclude by offering actionable insights that address key limitations, providing valuable guidance for future research in knee health acoustics.

Comparative study of methodologies for SOH diagnosis and forecast of LFP and NMC lithium batteries used in electric vehicles

The exponential growth of electric mobility requires alternatives to extend the life of batteries in new applications and reduce the environmental impact of retired lithium batteries. The second life is an economic and environment-friendly alternative for battery management. The development of fast, low-cost, and reliable diagnostic methodologies makes it possible to increase the economic benefits and reduce the remanufacturing time of second-life batteries (SLBs). In the present work, battery state of health (SOH) distribution analysis, incremental capacity (IC), internal resistance (IR), and electrochemical impedance spectroscopy (EIS) were applied as diagnostic methodologies for two different chemistries of lithium-ion batteries previously used in electric vehicles (EV). In addition, module equalization in batteries was done in order to assess whether the state of module charge (SOC) variation affects the SOH. The results demonstrate that the diagnosis methodology depends on the chemistry of the battery, and that there is no single reliable diagnostic procedure that can be applied to all types of lithium-ion batteries. It was determined that the most adequate diagnostic method for LFP batteries (LiFePO4 cathode) is the IC method, while for NMC batteries (LiNi0.33Mn0.33Co0.33O2 cathode) the IR and EIS diagnostic methods are the most appropriate. Similarly, the present work proposed a simple methodology for IC capacity diagnosis and a general expression for SOH determination by IC and incremental voltage diagnosis of LFP batteries. Higher stability of LFP respect to NMC modules was observed during the SLBs performance, retaining >99 % after 500 cycles for LFP, compared with 90.2 % for NMC. The remaining useful life (RUL) shows that there are kinetics and lithium inventory changes in the batteries temperature-dependent.

Enhancing brain tumor MRI classification with an ensemble of deep learning models and transformer integration.

Brain tumors are widely recognized as the primary cause of cancer-related mortality globally, necessitating precise detection to enhance patient survival rates. The early identification of brain tumor is presented with significant challenges in the healthcare domain, necessitating the implementation of precise and efficient diagnostic methodologies. The manual identification and analysis of extensive MRI data are presented as a challenging and laborious task, compounded by the importance of early tumor detection in reducing mortality rates. Prompt initiation of treatment hinges upon identifying the specific tumor type in patients, emphasizing the urgency for a dependable deep learning methodology for precise diagnosis. In this research, a hybrid model is presented which integrates the strengths of both transfer learning and the transformer encoder mechanism. After the performance evaluation of the efficacy of six pre-existing deep learning model, both individually and in combination, it was determined that an ensemble of three pretrained models achieved the highest accuracy. This ensemble, comprising DenseNet201, GoogleNet (InceptionV3), and InceptionResNetV2, is selected as the feature extraction framework for the transformer encoder network. The transformer encoder module integrates a Shifted Window-based Self-Attention mechanism, sequential Self-Attention, with a multilayer perceptron layer (MLP). These experiments were conducted on three publicly available research datasets for evaluation purposes. The Cheng dataset, BT-large-2c, and BT-large-4c dataset, each designed for various classification tasks with differences in sample number, planes, and contrast. The model gives consistent results on all three datasets and reaches an accuracy of 99.34%, 99.16%, and 98.62%, respectively, which are improved compared to other techniques.

Optimizing protocols for the 919 strain-based bovine ephemeral fever virus vaccine (Ultravac®, Zoetis™): Evaluation of dose-dependent effectiveness and long-term immunity

Bovine Ephemeral Fever (BEF) is an arthropod-borne virus (arbovirus) that presents a significant challenge to the cattle industry due to its economic impact, primarily through the loss of milk production in dairy cows. Vaccination is the predominant strategy for managing the disease. We recently showed a vaccine effectiveness (VE) of 60 % of a vaccine based on the Australian 919 BEFV isolate, with a natural challenge occurring shortly after the administration of the second dose of the vaccine. Still, there is a lack of data regarding the duration of protective immunity after vaccination and its potential enhancement after the administration of three and four vaccine doses. To answer these questions we conducted a retrospective cohort study of 850 cows (7 herds), analyzing the influence of different vaccination regimens on VE and a serosurvey of 71 cows to test the longevity of BEFV-specific serum-neutralizing antibodies (SNAb). We adopted a quantitative methodology for BEF diagnosis with the use of commercially validated precision dairy monitoring technologies for milk reduction identification. Survival analysis was used to analyze the vaccine dose effectiveness. A Cox regression mixed-effect model (COXME) was fitted to the data. The analysis demonstrated the following VE compared to zero vaccine doses: 82 % (p-value<0.001) for four doses, 66 % (p-value<0.026) for three doses and 39 % (p-value = 0.3) for two doses. Corroborating with the VE results, the four-dose regimen exhibited the highest geometric mean titer (GMT) value (4.45, CI95% = 3.99, 4.91), followed by the three-dose regimen (3.53, CI95% = 3.08,3.98), and the two-dose regimen (2.17, CI95% = 1.77,2.57). In light of these findings, we recommend vaccinating calves as early as four to six months old with two doses spaced one month apart, followed by a third and even fourth dose administered between six to 12 months later, ideally close to the onset of the high-risk season.

The Heritage Building Information Modeling Methodology for Structural Diagnosis: An Integrated System of Digital Models for the Baptistery of San Giovanni in Pisa

The Heritage Building Information Modeling Methodology for Structural Diagnosis: An Integrated System of Digital Models for the Baptistery of San Giovanni in Pisa

Compound fault recognition and diagnosis of rolling bearing in open-set-recognition setting

The established bearing fault diagnosis methods are built to predict fault which is known at training time, leading to false predictions when unknown faults occur. To address this, this paper proposes a novel intelligent fault diagnosis methodology. To detect unknown faults in open-set-recognition (OSR) setting, the developed method proposes the evidential neural network involving two fully connected layers to classify and recognize faults. And a novel evidence prediction function is developed to improve diagnosis performance. To achieve more effective fault diagnosis in OSR setting, rather than unknown fault recognition, a Fourier transform based data augmentation is applied to diagnose the unknown compound fault. The experimental results show superior performance of the method. It’s able to classify new fault with 97% accuracy and diagnose compound faults (that involves previously unknown faults) with impressive 80% accuracy. The proposed method provides industries a new alternative to diagnose rotating equipment faults in open environments.

Determining the Level of Emotional Intelligence of Future Cynologists

The purpose of the paper is to investigate the essence of emotional intelligence (EI) as an important component for future cynologists’ fruitful work in the sphere of rehabilitation of people who have been affected by the war consiquences. The authors studied the scientific literature on EI and its role in “Human-Human” and “Human-Animal” interactions in the working sphere. The authors determined the existing EI level of students who have Cynology as their major, outlined the theoretic and empiric outcomes, and stated recommendations for improving future cynologists’ professional training. Methodology. The empirical survey had a sample of 36 respondents. They were second-year students aged 18-21, 20 were male, and 16 were female. It was conducted by means of Google Forms on the basis of “Methodology of emotional intelligence diagnosis” by N. Hall (adapted) with subsequent processing and analysis of the results. Results. The study of the literature revealed that EI is of crucial importance for future cynologists’ professional fulfillment as it is responsible for the emotional regulation of their behavior, self-motivation, empathy, etc. However, empirically, it was found out that the EI of the respondents had not been sufficiently developed, as 68% of the respondents had a low level of EI integrative index, 22% of the students had the medium level of EI integrative index. Solely 10% of the respondents were recorded to have a high-level EI integrative index. Conclusions. The outcomes of the study revealed that most respondents do not have sufficient EI development, but they have the potential to enhance it. The authors insist on the organization of special educational courses and training to develop the ability of future cynologists to understand their own emotions and the emotions of other people, emotional behavior management, self-motivation, etc.

Power Transformer Fault Diagnosis Based on Random Forest and Improved Particle Swarm Optimization–Backpropagation–AdaBoost

This paper proposes a novel fault diagnosis methodology for oil-immersed transformers to improve the diagnostic accuracy influenced by gas components in power transformer oil. Firstly, the Random Forest (RF) algorithm is utilized to evaluate and filter the raw data features, solving the problem of determining significant features in the dataset. Secondly, a multi-strategy Improved Particle Swarm Optimization (IPSO) is applied to optimize a double-hidden layer backpropagation neural network (BPNN), which overcomes the challenge of determining hyperparameters in the model. Four enhancement strategies, including SPM chaos mapping based on opposition-based learning, adaptive weight, spiral flight search, and crisscross strategies, are introduced based on traditional Particle Swarm Optimization (PSO) to enhance the model’s optimization capabilities. Lastly, AdaBoost is integrated to fortify the resilience of the IPSO-BP network. Ablation experiments demonstrate an enhanced convergence rate and model accuracy of IPSO. Case analysis using Dissolved Gas Analysis (DGA) samples compares the proposed IPSO–BP–AdaBoost model with other swarm intelligence optimization algorithms integrated with BPNN. The experimental findings highlight the superior diagnostic accuracy and classification performance of the IPSO–BP–AdaBoost model.

Adaptive fusion graph convolutional network based interpretable fault diagnosis method for HVAC systems enhanced by unlabeled data

Fault diagnosis is critical in maintaining the operational stability and reliability of Heating, Ventilation, and Air Conditioning (HVAC) systems, which are crucial for ensuring indoor environmental quality and energy efficiency in buildings. However, traditional fault diagnosis methodologies face substantial challenges in accurately capturing the dynamic interactions within these systems and effectively utilizing unlabeled data. To overcome these limitations, an innovative fault diagnosis approach utilizing the Adaptive Fusion Graph Convolution Network (AFGCN) is proposed in this paper. This method significantly enhances the model's learning and inference abilities, particularly in scenarios with limited labeled data, by adaptively integrating the associative graph features of both unlabeled and labeled data. Furthermore, to augment the transparency and trustworthiness of the diagnostic outcomes, this paper introduces an interpretability analysis module. This module is designed to quantify the contribution of each sensor node in the fault diagnosis process. Experimental evaluations using the ASHRAE RP-1043, actual building operating chillers datasets, and LBNL FDD Data Sets_SDAHU indicate that this method offers substantial performance improvements in diagnosing faults in HVAC systems.

Development of a Machine‐Learning Model for Diagnosis of Pancreatic Cancer from Serum Samples Analyzed by Thermal Liquid Biopsy

Pancreatic ductal adenocarcinoma (PDAC) poses a considerable diagnostic and therapeutic challenge due to the lack of specific biomarkers and late diagnosis. Early detection is crucial for improving prognosis, but current techniques are insufficient. An innovative approach based on differential scanning calorimetry (DSC) of blood serum samples, thermal liquid biopsy (TLB), combined with machine‐learning (ML) analysis, may offer a more efficient method for diagnosing PDAC. Serum samples from a cohort of 212 PDAC patients and 184 healthy controls are studied. DSC thermograms are analyzed using ML models. The generated models are built applying algorithms based on penalized regression, resampling, categorization, cross validation, and variable selection. The ML‐based model demonstrates outstanding ability to discriminate between PDAC patients and control subjects, with a sensitivity of 90% and an area under the ROC receiver operating characteristic curve of 0.83 in the training and test groups. Application of the model to an independent validation cohort of 113 PDAC patients confirms its robustness and utility as a diagnosis tool. The application of ML to serum TLB data emerges as a promising methodology for early diagnosis, representing a significant advance for detecting and managing PDAC, envisaging a minimally invasive and more efficient methodology for identifying biomarkers.

Dementia Classification Approach Based on Non-Singleton General Type-2 Fuzzy Reasoning

Dementia is the most critical neurodegenerative disease that gradually destroys memory and other cognitive functions. Therefore, early detection is essential, and to build an effective detection model, it is required to understand its type, symptoms, stages and causes, and diagnosis methodologies. This paper presents a novel approach to classify dementia based on a data set with some relevant patient features. The classification methodology employs non-singleton general type-2 fuzzy sets, non-singleton interval type-2 fuzzy sets, and non-singleton type 1 fuzzy sets. These advanced fuzzy sets are compared with traditional singleton fuzzy sets to evaluate their performance. The Takagi–Sugeno–Kang TSK inference method is used to handle fuzzy reasoning. In the process, the parameters of the membership functions (MFs) and rules are obtained using ANFIS, and non-singleton MFs are optimized with PSO. The results demonstrate that non-singleton general type-2 fuzzy sets improve classification accuracy compared to singleton fuzzy sets, demonstrating their ability to model the uncertainties inherent in the diagnosis of dementia. This improvement suggests that non-singleton fuzzy systems offer a more robust framework for developing effective diagnostic tools in the medical domain. Accurate classification of dementia is of utmost importance to improve patient care and advance medical research.

Advances in molecular imaging for early detection of lung cancer

Lung cancer remains the second most commonly diagnosed cancer globally and the leading cause of cancer-related deaths, a trend consistent in the United States as of 2023. One of the key reasons for the high mortality rate of lung cancer is its poor prognosis, with 75% of patients diagnosed at middle and advanced stages. Early detection of subclinical lung cancer, metastases, and their fibrotic stroma is crucial for enabling timely treatment, reducing reoccurrence, and stratifying patients. Current diagnostic methods, such as lung biopsy for patients with small nodules, are highly invasive and technically challenging. The radiological gold standard, computed tomography (CT), is associated with ionizing radiation. However, positron emission tomography (PET) and magnetic resonance imaging (MRI) have emerged as promising methodologies for lung cancer diagnosis. PET tracers with a variety of targeting mechanisms are currently under development in human trials. With advancements in hardware and software over the past decades, radiation-free MRI has been clinically and preclinically validated as an alternative to CT. Moreover, novel-targeted MRI contrast agents have been tested in animal models and show strong translational potential. In this review, we summarize the state-of-the-art progress in molecular imaging for the early detection of lung cancer and its potential biomarkers.

A Literature Review of Fault Detection and Diagnostic Methods in Three-Phase Voltage-Source Inverters

This review paper offers a comprehensive examination of the various types of faults that occur in inverters and the methods used for their identification. The introductory segment investigates the internal component failures of voltage-source inverters (VSIs), examining their failure rates and the consequent effects on the overall system performance. Subsequently, this paper classifies and clarifies the potential malfunctions in components and sensors, placing particular emphasis on their frequency of occurrence and the severity of their impact. The examination encompasses issues associated with transistors, including open circuits, short circuits, gate firing anomalies, as well as failures in capacitors, diodes, and sensors. Following this, the paper delivers a comparative assessment of fault diagnosis techniques pertinent to each type of component, appraised against specific criteria. The concluding section encapsulates the findings for each fault category, delineates the fault detection and diagnosis (FDD) methodologies, analyzes the outcomes, and provides recommendations for future scholarly investigation.

Recent advances in journal bearings: wear fault diagnostics, condition monitoring and fault diagnosis methodologies

Recent advances in journal bearings: wear fault diagnostics, condition monitoring and fault diagnosis methodologies

Review of image processing and artificial intelligence methodologies for apple leaf disease diagnosis

&lt;span lang="EN-US"&gt;Apple leaf disease (ALD) potentially affects the apple tree's health by reducing fruit yield and its capability to grow healthy. The prime purpose of the proposed study is to review and assess the strengths and weaknesses associated with the frequently exercised methods of ALD diagnosis using image processing and artificial intelligence (AI). Although these are widely adopted in recent studies, the core notion is to find the pros and cons associated with the practical viability. A desk research methodology is undertaken to carry out proposed review work where a database of recent scientific manuscripts is collected and studied very closely. The existing approaches are reviewed concerning identified problems, adopted solutions, advantages, and limitations. Finally, the paper contributes towards offering insight into potential research gap which will guide the upcoming researchers to make wise decisions for planning their models. The results acquired from this review work show that generalized challenges of ALD are not addressed, less emphasis on illumination variability, reduced target to minimize complexity, lesser evidence towards real-time processing, no evidence towards interpretability, limitation of available dataset, and tradeoff-between image processing and AI.&lt;/span&gt;

Fast Isolation and Sensitive Multicolor Visual Detection of Small Extracellular Vesicles by Multifunctional Polydopamine Nanospheres.

Small extracellular vesicles (sEVs) assume pivotal roles as vital messengers in intercellular communication, boasting a plethora of biological functions and promising clinical applications. However, efficient isolation and sensitive detection of sEVs continue to present formidable challenges. In this study, we report a novel method for fast isolation and highly sensitive multicolor visual detection of sEVs using aptamer-functionalized polydopamine nanospheres (SIMPLE). In the SIMPLE strategy, aptamer-functionalized polydopamine nanospheres (Apt-PDANS) with 170 nm diameters were synthesized and exhibited a remarkable ability to selectively bind to specific proteins on the surface of sEVs. The binding between sEVs and Apt-PDANS engenders an increase in the overall size of the sEVs, allowing fast isolation of sEVs by filtration (a filter membrane with a pore size of 200 nm). The fast isolation strategy not only circumvents the interference posed by unbound proteins and excessive probes as well as the intricacies associated with conventional ultracentrifugation methods but also expedites the separation of sEVs. Concurrently, the incorporation of Fe3+-doped PDANS permits the multicolor visual detection of sEVs, enabling quantitative analysis by the discernment of visual cues. The proposed strategy achieves a detection limit of 3.2 × 104 sEV mL-1 within 1 h, devoid of any reliance on instrumental apparatus. Furthermore, we showcase the potential application of this methodology in epithelial-mesenchymal transition monitoring and cancer diagnosis, while also envisioning its widespread adoption as a straightforward, rapid, sensitive, and versatile platform for disease monitoring and functional exploration.

DRIS nutritional norms and sufficiency range for the perola pineapple cultivation

Pineapple plants needs to be nutritionally balanced to reach maximum productivity potential. Therefore, the most current parameters must be used, centered on plant nutritional status diagnosis methodologies developed through leaf chemical analysis, which consider the relationships between nutrients and take advantage of data from productivity monitoring and foliar diagnosis of crops. This study aimed to establish nutrient norms and sufficiency ranges for pineapple in the Triângulo Mineiro, MG, Brazil, using the Diagnosis and Recommendation Integrated System (DRIS). To achieve the proposed objectives, productivity data and chemical analysis of leaf tissue from 88 commercial farming plots of 'Pérola’ pineapple, sampled between the 2018 and 2019 harvests, in the Triângulo Mineiro were used. The DRIS method was used to establish the norms and sufficiency ranges of N, P, K, Ca, Mg, S, B, Cu, Fe, Mn, and Zn. The average nutritional balance index (NBIm) did not correlate with productivity. However, the content of P, Ca, Mg, S, B, Cu, Fe, Mn, and Zn highly correlated with their respective nutritional indices. The sufficiency ranges and the adequacy levels of nutrients differed from the values established for pineapple in the literature.

Virtual reality tolerability, sense of presence and usability in Huntington disease: a pilot study.

Several studies demonstrated the utility of immersive virtual reality (VR) as a complementary approach to conventional therapy for improving motor, psychological and cognitive impairment in some pathological conditions. Our pilot study aims to evaluate for the first time: 1) sense of presence, tolerability and usability of VR immersive experience in patients with early stages of Huntington disease (eHDp) compared to healthy controls (HC); 2) correlation between the use of technology/cybersickness and the variables of presence/usability; 3) correlation between clinical characteristics (genetic, motor, functional and cognitive) and VR's variables. We recruited 10 eHDp and 10 age, gender and education matched HC. Participants completed questionnaires about sense of presence, usability, tolerability and technology use profile. Subjects were exposed to different VR scenarios from a first-person perspective through a standalone VR headset. Our results showed no significant statistical difference between eHDp and HC for the sense of presence (p=0.910), usability (p=0.744) and tolerability (p=0.730) during the VR experience. Familiarity with the use of technology was also comparable between groups (p=0.676). Regarding correlations in eHDp group, our results showed no correlations between use of technology/tolerability and the sense of presence/usability. Moreover, clinical characteristics of eHDp (genetic, motor, functional and cognitive scores) did not influence the sense of presence, tolerability and usability. Our research presents preliminary evidence for the applicability of VR in eHDp. These results open up the possibility to explore future applications of this methodology in rehabilitation (i.e., cognitive training, physiotherapy), diagnosis and psychological support in Huntington disease patients.