Test Accuracy Research Articles

Training Artificial Neural Networks to Detect Multiple Sclerosis Lesions Using Granulometric Data from Preprocessed Magnetic Resonance Images with Morphological Transformations

The symptoms of multiple sclerosis (MS) are determined by the location of demyelinating lesions in the white matter of the brain and spinal cord. Currently, magnetic resonance imaging (MRI) is the most common tool used for diagnosing MS, understanding the course of the disease, and analyzing the effects of treatments. However, undesirable components may appear during the generation of MRI scans, such as noise or intensity variations. Mathematical morphology (MM) is a powerful image analysis technique that helps to filter the image and extract relevant structures. Granulometry is an image measurement tool for measuring MM that determines the size distribution of objects in an image without explicitly segmenting each object. While several methods have been proposed for the automatic segmentation of MS lesions in MRI scans, in some cases, only simple data preprocessing, such as image resizing to standardize the input dimensions, has been performed before the algorithm training. Therefore, this paper proposes an MRI preprocessing algorithm capable of performing elementary morphological transformations in brain images of MS patients and healthy individuals in order to delete undesirable components and extract the relevant structures such as MS lesions. Also, the algorithm computes the granulometry in MRI scans to describe the size qualities of lesions. Using this algorithm, we trained two artificial neural networks (ANNs) to predict MS diagnoses. By computing the differences in granulometry measurements between an image with MS lesions and a reference image (without lesions), we determined the size characterization of the lesions. Then, the ANNs were evaluated with the validation set, and the performance results (test accuracy = 0.9753; cross-entropy loss = 0.0247) show that the proposed algorithm can support specialists in making decisions to diagnose MS and estimating the disease progress based on granulometry values.

Framework for multivariate carbon price forecasting: A novel hybrid model

The complex characteristics of volatility and non-linearity of carbon price pose a serious challenge to accurately predict carbon price. Therefore, this study proposes a new hybrid model for multivariate carbon price forecasting, including feature selection, deep learning, intelligent optimization algorithms, model combination and evaluation indicators. First, this study collects and organizes the historical carbon price series of Hubei and Shanghai as well as the influencing factors in five dimensions including structured and unstructured data, totaling twenty variables. Second, data dimensionality reduction is performed and input variables are obtained using the least absolute shrinkage and selection operator, followed by the introduction of nine advanced deep learning models to predict carbon price and compare the prediction effects. Then, through the combination of models, three models with the best performance are combined with Pelican optimization algorithm to construct a hybrid forecasting model. Finally, the experimental results show that the developed forecasting model outperforms other comparation models in terms of prediction accuracy, stability and statistical hypothesis testing, and exhibits excellent prediction performance. Furthermore, this study also applies the developed model to European carbon market price prediction and uses the Hubei carbon market as an example for quantitative trading simulation, and the empirical results further verify its robust prediction performance and investment application value. In conclusion, the proposed hybrid prediction model can not only provide high-precision carbon market price prediction for the government and corporate decision makers, but also help investors optimize their trading strategies and improve their returns.

Unity and ROS as a Digital and Communication Layer for Digital Twin Application: Case Study of Robotic Arm in a Smart Manufacturing Cell.

A digital twin (DT) is a virtual/digital model of any physical object (physical twin), interconnected through data exchange. In the context of Industry 4.0, DTs are integral to intelligent automation driving innovation at scale by providing significant improvements in precision, flexibility, and real-time responsiveness. A critical challenge in developing DTs is achieving a model that reflects real-time conditions with precision and flexibility. This paper focuses on evaluating latency and accuracy, key metrics for assessing the efficacy of a DT, which often hinder scalability and adaptability in robotic applications. This article presents a comprehensive framework for developing DTs using Unity and Robot Operating System (ROS) as the main layers of digitalization and communication. The MoveIt package was used for motion planning and execution for the robotic arm, showcasing the framework's versatility independent of proprietary constraints. Leveraging the versatility and open-source nature of these tools, the framework ensures interoperability, adaptability, and scalability, crucial for modern smart manufacturing applications. Our approach was validated by conducting extensive accuracy and latency tests. We measured latency by timestamping messages exchanged between the physical and digital twin, achieving a latency of 77.67 ms. Accuracy was assessed by comparing the joint positions of the DT and the physical robotic arm over multiple cycles, resulting in an accuracy rate of 99.99%. The results highlight the potential of DTs in enhancing operational efficiency and decision-making in manufacturing environments.

External validation of the MAGNIFI-CD index in patients with complex perianal fistulising Crohn's disease.

There is an increasing need for objective treatment monitoring in perianal fistulising Crohn's disease (pfCD). Therefore, the magnetic resonance novel index for fistula imaging in CD (MAGNIFI-CD) index has been designed and internally validated on the ADMIRE-CD trial cohort. The aim of this study was to externally validate the MAGNIFI-CD index to monitor response to medical and surgical treatment regimens in pfCD. A retrospective longitudinal cohort was established of consecutive patients with complex pfCD treated with surgical and/or medical therapy and a baseline and follow-up MRI between January 2007 and May 2021. The MAGNIFI-CD index was scored by two independent, abdominal radiologists blinded for time points and clinical outcomes. Responsiveness, reliability, and test accuracy regarding clinically important improvement were assessed. Cut-offs for response and remission were selected classified on fistula drainage assessment and physician global assessment. A total of 65 patients (51% female, median age 32 years) were included. A clinically relevant responsiveness of the MAGNIFI-CD was shown, with a significant decrease in clinical remitters and responders with a median MAGNIFI-CD of 18.0 [7.5-20.0] to 9.0 [0.8-16.0] (p < 0.001) and non-significant change in non-responders with a median MAGNIFI-CD of 20.0 [12.0-23.0] to 18.0 [13.0-21.0] (p = 0.22). There was an 'almost perfect' interobserver agreement (ICC = 0.87; 95% CI 0.80-0.92) for the MAGNIFI-CD index. An optimal cut-off value was defined as a decrease of 2 points for clinical response, and a MAGNIFI-CD ≤ 6 for remission at follow-up MRI. The MAGNIFI-CD index is a responsive and reliable MRI scoring instrument for treatment monitoring in perianal fistulising Crohn's disease. The MAGNIFI-CD index is a well-structured, responsive scoring instrument to assess fistula severity and activity that allows quantitative detection of changes in therapy response in patients with perianal fistulising Crohn's disease, thereby facilitating endpoints in clinical trials. Well-defined cut-offs for response and remission are needed for objective treatment monitoring of perianal fistulising Crohn's disease (pfCD). Cut-off values for remission and for response at 6 months follow-up were defined. Interobserver agreement was good. The MAGNIFI-CD index is responsive and reliable for treatment monitoring and is suitable for use in clinical trials.

Deceptive Measures of "Success" in Early Cancer Detection.

Early detection of cancer is considered a cornerstone of preventive medicine and is widely perceived as the gateway to reducing cancer deaths. Based on this assumption, large trials are currently underway to evaluate the accuracy of early detection tests. It is imperative, therefore, to set meaningful "success criteria" in early detection that reflect true improvements in health outcomes. This article discusses the pitfalls of measuring the success of early detection tests for cancer, particularly in the context of screening programs, and provides illustrative examples that demonstrate how commonly used metrics can be deceptive. Early detection can result in downstaging (favourable stage shift) when more early-stage cancers are diagnosed, even without reducing late-stage disease, potentially leading to overdiagnosis and overtreatment. Survival statistics, primarily cancer-specific survival, can be misleading due to lead time, where early detection simply extends the known duration of the disease without prolonging actual lifespan or improving overall survival. Additionally, the misuse of relative measures, such as proportions, ratios, and percentages, often make it impossible to ascertain the true benefit of a procedure and can distort the impact of screening as they are influenced by diagnostic practices, misleadingly improving perceived mortality reductions. Understanding these biases is crucial for accurately assessing the effectiveness of cancer detection methods and ensuring appropriate patient care.

An Array of Carbon Nanofiber Bundle_Based 3D In Vitro Intestinal Microvilli for Mimicking Functional and Physical Activities of the Small Intestine.

Researchers have developed in vitro small intestine models of biomimicking microvilli, such as gut-on-a-chip devices. However, fabrication methods developed to date for 2D and 3D in vitro gut still have unsolved limitations. In this study, an innovative fabrication method of a 3D in vitro gut model is introduced for effective drug screening. The villus is formed on a patterned carbon nanofiber (CNF) bundle as a flexible and biocompatible scaffold. Mechanical properties of the fabricated villi structure are investigates. A microfluidic system is applied to induce the movement of CNFs villi. F-actin and Occludin staining of Caco-2 cells on a 2D flat-chip as a control and a 3D gut-chip with or without fluidic stress is observed. A permeability test of FD20 is performed. The proposed 3D gut-chip with fluidic stress achieve the highest value of Papp. Mechano-active stimuli caused by distinct structural and movement effects of CNFs villi as well as stiffness of the suggested CNFs villi not only can help accelerate cell differentiation but also can improve permeability. The proposed 3D gut-chip system further strengthens the potential of the platform to increase the accuracy of various drug tests.

Prediction of Hepatocellular Carcinoma in a Portuguese Population after Hepatitis C Cure: Comparative Accuracy of Noninvasive Tests (Transient Elastography, FIB-4, and aMAP)

Introduction: Chronic infection with hepatitis C virus (HCV) causes 25% of hepatocellular carcinoma (HCC) cases worldwide, a major cause of morbimortality even after sustained virologic response (SVR). Universal screening to all patients with advanced liver fibrosis is currently recommended. A risk-based strategy could improve the detection rate of early HCC and diminish the surveillance burden. Although several risk prediction models exist, exclusion of a subgroup of patients from surveillance has not yet been recommended. The objective of this study was the comparison of the predictive accuracy of transient elastography, FIB-4, and aMAP for HCC in HCV patients after SVR in Portugal. Methods: This was a multicentric retrospective study including patients with HCV after SVR. Comparative, univariate, multivariate, area under the ROC (receiver-operating characteristic) curve (AUC), and Youden’s J-statistic analysis were performed. Results: HCC incidence was 4.2% (1.3/100 patient-years) after a median follow-up of 31 months with inclusion of 337 patients. All patients had a liver stiffness measurement (LSM) before SVR (considered the baseline), but only 148 (43.9%) had a transient elastography after SVR. FIB-4 and aMAP post-SVR were calculated in all patients. Multiple parameters positively correlated with HCC, but only age and baseline transient elastography remained as independent predictors in the multivariate analysis. The optimal cutoffs for prediction of HCC were baseline transient elastography 13.7 kPa, post-SVR transient elastography 16.5 and 15.8 kPa (first and last measurements, respectively), FIB-4 1.6, and aMAP 58. Baseline transient elastography revealed a fair accuracy in predicting HCC (AUC 0.776, p < 0.001), with the cutoff of 13.7 kPa presenting a sensitivity of 85% and a specificity of 69%. Regarding patients who were F3–4 at baseline (n = 162), almost one-third had a baseline LSM ≤13.7 kPa (n = 51, 31.5%), an FIB-4 ≤1.6 (n = 50, 30.9%), and an aMAP score ≤58 (n = 48, 29.6%), and these cutoffs presented an NPV of 98%, 94%, and 96%, respectively, when considering HCC development. Conclusion: Transient elastography (FibroScan) before SVR was a fair predictor of HCC, being more accurate than FIB-4 and aMAP. Transient elastography values ≤13.7 kPa at baseline, FIB-4 ≤1.6 and aMAP ≤58 were the cutoffs considered of low risk for HCC in a Portuguese cohort of HCV patients after SVR with advanced fibrosis. aMAP score is a risk-based surveillance tool that could improve the current HCC screening strategy, but further validation is needed.

Determining the accuracy of the leukocyte esterase reagent strip test in the rapid diagnosis of adult septic arthritis

BackgroundsSeptic arthritis is a dangerous disease that occurs when microorganisms enter synovial fluid. It needs fast and accurate management; otherwise, it can harm the patient’s life. Currently, the tests measure WBC and PMN in SF, so we hypothesized to use a proxy that is easier and faster to measure. Leukocyte esterase is an enzyme secreted by neutrophils that can be found in the synovial fluid of SA patients. In this study, we tried to investigate the sensitivity and specificity of leukocyte esterase in diagnosing septic arthritis.MethodsWe obtained synovial fluid samples from forty-six patients suspected of having septic arthritis and fifty-eight healthy individuals and measured the WBCs, ESR, CRP, PMN, glucose, and protein of SF in 2021. We also used the leukocyte esterase dipstick test to investigate the level of LE in synovial fluid for one minute.ResultsBased on clinical and paraclinical criteria, sixteen out of the forty-six patients were diagnosed with SA. When (++) was considered positive, the sensitivity and specificity of the LE dipstick test for the diagnosis of SA were 93.7% (95% CI: 81.8–100%) and 60% (95% CI: 42.4–77.5%, P = 0.000), respectively. When both (+) and (++) were considered positive, they were 100% and 43.3% (95% CI: 25.6–61.0% P = 0.000), respectively. All the patients in the control group had negative cultures and LE test readings (specificity = 100%).ConclusionThe LE dipstick test can be a valuable diagnostic tool in the initial diagnosis of SA since it is affordable, fast, and reliable.

Automated echocardiographic diastolic function grading: A hybrid multi-task deep learning and machine learning approach

BackgroundAssessing left ventricular diastolic function (LVDF) with echocardiography as per ASE guidelines is tedious and time-consuming. The study aims to develop a fully automatic approach of this procedure by a lightweight hybrid algorithm combining deep learning (DL) and machine learning (ML). MethodsThe model features multi-modality input and multi-task output, measuring LV ejection fraction (LVEF), left atrial end-systolic volume (LAESV), and Doppler parameters: mitral E wave velocity (E), A wave velocity (A), mitral annulus e’ velocity (e’), and tricuspid regurgitation velocity (TRmax). The algorithm was trained and tested on two internal datasets (862 and 239 echocardiograms) and validated using three external datasets, including EchoNet-Dynamic and CAMUS. The ASE diastolic function decision tree and total probability theory were used to provide diastolic grading probabilities. ResultsThe algorithm, named MMnet, demonstrated high accuracy in both test and validation datasets, with Dice coefficients for segmentation between 0.922 and 0.932 and classification accuracies between 0.9977 and 1.0. The mean absolute errors (MAEs) for LVEF and LAESV were 3.7 % and 5.8 ml, respectively, and for LVEF in external validation, MAEs ranged from 4.9 % to 5.6 %. The diastolic function grading accuracy was 0.88 with hard criteria and up to 0.98 with soft criteria which account for the top two probability in total probability theory. ConclusionsMMnet can automatically grade ASE diastolic function with high accuracy and efficiency by annotating 2D videos and Doppler images.

Psychometric Synthesis of the Drug Abuse Screening Test (DAST) Versions

Problem Statement Among individuals aged 12 years or older, 14.3% (40.0 million) reporting the use of an illicit drug in the previous year. Given the prevalence of drug abuse, it is increasingly important to determine effective screening practices, treatment procedures, and best practices among various subpopulations to identify drug use-related consequences. The DAST is one of the most commonly used and accurate drug screening tests. Method This psychometric synthesis of four versions of the Drug Abuse Screening Test (DAST-10, DAST-20, DAST-28, DAST-A) provided aggregated evidence from 346 articles over 40 years of published literature for score reliability, structure, diagnostic, and convergent validity, and descriptive statistics, all with the goal of informing counseling and medical practice and research. Results Results indicated adequate internal consistency (α = 0.81–0.84 across all four versions) and mostly medium to large effect size convergent correlations with comparison measures. Aggregated diagnostic validity data indicate optimal cutoff scores of 7 for DAST-10, 8 for DAST-20, 10 for DAST-28, and 6 for DAST-A. Discussion The DAST-10 appears the best choice for practical and psychometric reasons. Additional studies of the various DAST versions are needed to expand use across participant demographics. Public Statement of Relevance Drug use continues to be a societal problem and mental health practitioners need effective screening practices, treatment procedures, and best practices among various subpopulations to identify drug use-related consequences. This study synthesized 40 years of research on the four versions of the Drug Abuse Screening Test (DAST-10, DAST-20, DAST-28, DAST-A) and found acceptable levels of score reliability and validity for screening purposes.

Modeling test study on influence mechanism of large-span double-arch tunnels in proximity to existing tracks

This paper aims to study the influence mechanism of the large-span double-arch tunnels in proximity to existing tracks using 1 g model test. A novel non-contact device able to measure settlements automatically is developed to improve the test accuracy. During the test, the strata settlement, surrounding rock stress and track deformation induced by tunnel excavation are measured simultaneously. The results show that: (1) The excavation of the double-arch tunnel induces an asymmetric “W”-shaped horizontal surface settlement. The horizontal surface settlement near the centerline of the first excavation side is the largest. (2) The U-shaped groove structure exhibits an “M”-shaped deformation, while its structure produces bulges near the maximum horizontal surface settlement. (3) After excavation, the longitudinal surface settlement gradually decreases along the excavation direction, which causes the tilting or bottom voids of the U-shaped groove structure. The U-shaped groove structure may experience torsional shear damage under the load imposed by the train.

Identification, prediction and classification of hydrogen-fueled Wankel rotary engine knock by data-driven based on combustion parameters

Hydrogen-fueled Wankel rotary engine has excellent power density and low backfire possibility, however, as well as the severe knock. The knock is closely related to the in-cylinder combustion process, therefore, the present work is conducted to identify, predict and classify the knock by data-driven based on combustion parameters in the hydrogen-fueled Wankel rotary engine. The results show that: Knock type can be identified well according to knock intensity and crank angle of peak knock pressure through the Gaussian Mixture Model. There are 141 strong knock cycles and 809 weak knock cycles in test data. Compared with Support Vector Machines and Back-propagation Neural Networks, Multiple Linear Regression has a better global performance in knock-level prediction based on combustion parameters. The maximum pressure rising rate and CA50 have more significant impacts on knock, the partial of regression coefficients of which is about 0.42 and −0.58, respectively. In particular, due to different formation mechanisms, the prediction models of two types of knock are recommended to be established separately. In addition, the Support Vector Machine can be applied to conduct knock classification. Among kernel functions in Support Vector Machine, the linear kernel function can achieve optimal mean test accuracy, about 88.66 %.

Kruskal Wallis and mRMR Feature Selection based Online Signature Verification System using Multiple SVM and KNN

Signature verification is a very important research area. Signature has been widely accepted as a person authentication method for centuries. It is mostly used in financial transactions, document authentication and agreements. It is more susceptible to being forged than any other biometrics. Online signature verification is used in real-time applications like e-commerce, online resource access, online financial transactions, physical access into a restricted area and many more. In order to achieve high efficiency in online signature verification systems, feature extraction and feature selection play a significant role. A suitable signature verification system is needed to prevent forgery and accept the genuine signer. We have extracted 30 global features from all 40 signers for verification. Here, k fold cross-validation technique is used to enhance the model's performance on unseen data. User-specific feature selection and ranking are done using Kruskal Wallis and Minimum Redundancy Maximum Relevance (mRMR) algorithm to hunt which performs better in our case. Kruskal-Wallis method tests if two or more classes have an equal median and gives the value of P based on which discriminative features are selected, whereas the mRMR algorithm ranks the whole feature set according to its importance. It evaluates the relevance of a feature and penalizes redundancy. Finally, multiple SVM and KNN classifiers are trained and tested with various selected features using Kruskal Wallis and mRMR to determine which combination performs best for the online signature verification system. Our model is trained, validated and tested on the SVC 2004 Task 1 database, which consists of skill forgery signatures. Here, one to one verification is done using each user's genuine and skill forgery signatures, which is the hardest to detect. Best average testing accuracy achieved in our case is 90.25% using Weighted KNN and Kruskal Wallis selected 15 features.

Real-World Accuracy of Wearable Activity Trackers for Detecting Medical Conditions: Systematic Review and Meta-Analysis.

Wearable activity trackers, including fitness bands and smartwatches, offer the potential for disease detection by monitoring physiological parameters. However, their accuracy as specific disease diagnostic tools remains uncertain. This systematic review and meta-analysis aims to evaluate whether wearable activity trackers can be used to detect disease and medical events. Ten electronic databases were searched for studies published from inception to April 1, 2023. Studies were eligible if they used a wearable activity tracker to diagnose or detect a medical condition or event (eg, falls) in free-living conditions in adults. Meta-analyses were performed to assess the overall area under the curve (%), accuracy (%), sensitivity (%), specificity (%), and positive predictive value (%). Subgroup analyses were performed to assess device type (Fitbit, Oura ring, and mixed). The risk of bias was assessed using the Joanna Briggs Institute Critical Appraisal Checklist for Diagnostic Test Accuracy Studies. A total of 28 studies were included, involving a total of 1,226,801 participants (age range 28.6-78.3). In total, 16 (57%) studies used wearables for diagnosis of COVID-19, 5 (18%) studies for atrial fibrillation, 3 (11%) studies for arrhythmia or abnormal pulse, 3 (11%) studies for falls, and 1 (4%) study for viral symptoms. The devices used were Fitbit (n=6), Apple watch (n=6), Oura ring (n=3), a combination of devices (n=7), Empatica E4 (n=1), Dynaport MoveMonitor (n=2), Samsung Galaxy Watch (n=1), and other or not specified (n=2). For COVID-19 detection, meta-analyses showed a pooled area under the curve of 80.2% (95% CI 71.0%-89.3%), an accuracy of 87.5% (95% CI 81.6%-93.5%), a sensitivity of 79.5% (95% CI 67.7%-91.3%), and specificity of 76.8% (95% CI 69.4%-84.1%). For atrial fibrillation detection, pooled positive predictive value was 87.4% (95% CI 75.7%-99.1%), sensitivity was 94.2% (95% CI 88.7%-99.7%), and specificity was 95.3% (95% CI 91.8%-98.8%). For fall detection, pooled sensitivity was 81.9% (95% CI 75.1%-88.1%) and specificity was 62.5% (95% CI 14.4%-100%). Wearable activity trackers show promise in disease detection, with notable accuracy in identifying atrial fibrillation and COVID-19. While these findings are encouraging, further research and improvements are required to enhance their diagnostic precision and applicability. Prospero CRD42023407867; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=407867.

An Integrated Hybrid Convolutional-Support Vector Machine (CSVM) Model with the CWT Method for Hearing Disorder Detection using AEP Signals

Hearing disorder is the most widespread sensory disability worldwide, impairing human communication and learning. An early and accurate hearing disorder detection system using an electroencephalogram (EEG) is the appropriate technique for dealing with this concern. The most significant modality for diagnosing hearing deficiency among EEG control signals is the auditory evoked potential (AEP), which is generated in the cortical region of the brain through auditory stimulus. This study aims to develop an efficient approach for detecting hearing disorders. For this purpose, this study has designed a hybrid model based on the convolutional operation of CNN and the SVM classifier. Initially, the CWT method was utilized to transform the raw AEP signals into time-frequency images. Then, the extracted features were classified using the proposed CSVM model. To test the robustness of the proposed model, this study also implemented a convolutional neural network (CNN) and support vector machine (SVM) with the same parameters. The experimental results with the hybrid CSVM model showed superior performance on the publicly available AEP dataset by achieving 94.48% testing accuracy, 96.40% precision, 92.96% recall, 94.65% F1 score, 88.95% Cohen Kappa score, which indicates that the proposed hybrid model could be used for early hearing disorder detection. Future enhancements will concentrate on identifying different hearing-signal-based data and the cloud-based, automated classification of AEP signals.

Analisa Shock Absorber Sepeda Motor dengan Alat Uji Mekanis

The use of motorcycles on unstable roads, such as off-road and potholes, demands the importance of a reliable suspension system for riding comfort and safety. Conventional testing of s is often ineffective in accuracy and data recording, so this research proposes the use of an automatic measuring instrument to improve test efficiency and accuracy, allowing users to evaluate deflection in real-time and determine the optimal comfort level. The purpose of this research is to determine the effect of load and brand of motorcycle on deflection value and deflection time. The research method used in this study is the experimental method, which involves a series of trials to collect empirical data related to the characteristics of the . This study uses independent variables in the form of load weight (60 kg, 80 kg, 100 kg) and brand (Aspira, Showa, Kayaba). The measured dependent variables include deflection (mm) and deflection time (s) to evaluate the performance. The results showed that load and brand had a significant effect on deflection and deflection time. Increasing load caused deflection to increase, with Aspira showing deflection of 40-42 mm at 60 kg load and 36-38 mm at 100 kg load. Kayaba had a shorter deflection time of 178.45–180.95 seconds at 100 kg load, compared to Showa's 245.45-275.75 seconds. This shows that Kayaba is more responsive in managing loads, with lower deflection and shorter deflection times than other brands, making it a more effective choice for dealing with varied road conditions.

Landsat-based spatiotemporal estimation of subtropical forest aboveground carbon storage using machine learning algorithms with hyperparameter tuning.

The aboveground carbon storage (AGC) in forests serves as a crucial metric for evaluating both the composition of the forest ecosystem and the quality of the forest. It also plays a significant role in assessing the quality of regional ecosystems. However, current technical limitations introduce a degree of uncertainty in estimating forest AGC at a regional scale. Despite these challenges, remote sensing technology provides an accurate means of monitoring forest AGC. Furthermore, the implementation of machine learning algorithms can enhance the precision of AGC estimates. Lishui City, with its rich forest resources and an approximate forest coverage rate of 80%, serves as a representative example of the typical subtropical forest distribution in Zhejiang Province. Therefore, this study uses Landsat remote sensing images, employing backpropagation neural network (BPNN), random forest (RF), and categorical boosting (CatBoost) to model the forest AGC of Lishui City, selecting the best model to estimate and analyze its forest AGC spatiotemporal dynamics over the past 30 years (1989-2019). The study shows that: (1) The texture information calculated based on 9×9 and 11×11 windows is an important variable in constructing the remote sensing estimation model of the forest AGC in Lishui City; (2) All three machine learning techniques are capable of estimating forest AGC in Lishui City with high precision. Notably, the CatBoost algorithm outperforms the others in terms of accuracy, achieving a model training accuracy and testing accuracy R2 of 0.95 and 0.83, and RMSE of 2.98 Mg C ha-1 and 4.93 Mg C ha-1, respectively. (3) Spatially, the central and southwestern regions of Lishui City exhibit high levels of forest AGC, whereas the eastern and northeastern regions display comparatively lower levels. Over time, there has been a consistent increase in the total forest AGC in Lishui City over the past three decades, escalating from 1.36×107 Mg C in 1989 to 6.16×107 Mg C in 2019. This study provided a set of effective hyperparameters and model of machine learning suitable for subtropical forests and a reference data for improving carbon sequestration capacity of subtropical forests in Lishui City.

Automatic elimination of invalid impact-echo signals for detecting delamination in concrete bridge decks based on deep learning

The impact-echo (IE) method is effective for evaluating invisible defects. However, it might return misleading results when its signals are invalid. This challenge aggravates when the tests are conducted using robotic devices that automatically collect massive data. This study proposes an automatic method to eliminate invalid signals based on the ResNet model. First, the signals are visualized into two-dimensional images as the input for ResNet. The input data can then be classified into valid and invalid data via the ResNet model, which is trained with 11,290 signals and tested with 5664 signals. Finally, defects can be detected using the dominant frequencies of the valid-class data. A case study with IE data from two concrete bridges was employed to validate the feasibility of the proposed approach. The results indicate that the method can achieve an average accuracy of 90.6% for eliminating invalid signals and significantly improve the IE test accuracy.

Development of filtration-based RPA–CRISPR/Cas12a system for rapid, sensitive and visualized detection of Salmonella in ready-to-eat salads

Salmonella contamination of ready-to-eat (RTE) salads, a pathogen that causes foodborne diseases worldwide, continues to increase. Since RTE salads are consumed without any processing processes that remove pathogens, such as heat treatment, rapid and accurate testing is essential to effectively prevent such foodborne contamination. Therefore, in this study, I developed the recombinase polymerase amplification (RPA)–clustered regularly interspaced short palindromic repeats (CRISPR)/Cas12a system to amplify Salmonella gene (invA) in 20 min through RPA and visually detect it within 5 min using CRISPR/Cas12a. I successfully visually detected 101 CFU/mL of Salmonella pure culture using this system. Furthermore, for food sample preparation, I introduced the filtration based approach as a pretreatment method, which successfully reduced detection time and improved detection sensitivity. In conclusion, the developed filtration-based RPA CRISPR/Cas12a system enabled the visual detection of Salmonella in salads as low as 101 CFU/g. This system, which integrates filtration-based RPA-CRISPR/Cas12a, is a rapid, sensitive, and visually intuitive method for detecting Salmonella in RTE salads. It is also a useful technology with high applicability in POCT.

Causal Discovery Using Weight-Based Conditional Independence Test

Conditional independence (CI) tests play an essential role in causal discovery from observational data, enabling the measurement of independence between two nodes. However, traditional CI tests ignore the imbalanced occurrence probabilities of node values, which may affect the accuracy of determining independence between nodes. To address this problem, we first introduce a new concept of the Node-imbalance phenomenon to describe the imbalance of node values in the Bayesian network data and analyze the influence of the Node-imbalance phenomenon on the traditional CI tests, then we propose a W eight-based C onditional I ndependence test (WCI) to improve the accuracy of CI tests in the presence of Node-imbalance. In the experiments, we verify that WCI effectively measures the dependency between nodes in the Node-imbalance phenomenon compared with the traditional independence tests, and the state-of-the-art causal discovery algorithms reduce the number of false causal orientations through WCI.