Good Metrics Research Articles

Analysis of Density-Dependent Cell Structure of EPP Bead Foams Under Compression

Abstract Background Closed cell polymer bead foams are widely used in industrial applications due to their extraordinary damping and insulation properties. To understand the structure-property-relations at different deformation states the volumetric structure of polymer walls, cells and beads should be statistically analysed. Objective The presented work is focused on the statistical analysis of the changing cell structure of expanded polypropylene bead foams of different density at distinct compression states. Methods Cylindrical bead foam specimens are scanned by x-ray computed tomography at 3-5 different compression states. The reconstructed volume information is segmented and statistically analysed. Results It could be shown that, among others, the cell sphericity and their orientation relative to the plane normal to the loading direction are sensitive parameters to the deformation state. With regard to the material symmetry level, a shift of the isotropic foam to transversal isotropic structure was observed. No sudden, stability related, deformation or failure could be observed. Conclusions Good metrics for the deformation analysis of expanded polypropylene bead foams from in-situ computed tomography tests are the cell sphericity and orientation. Compression deformation leads to a gradually change of material symmetry level from isotropy to anisotropy.

Multiple ‘memory-based’ schemes for monitoring Maxwell distributions with measurement errors

In many industrial applications, Maxwell is used as a life distribution to describe the life characteristics of a product. However, the accuracy of the life test results is usually affected by factors such as the way the operator operates and the accuracy of the measuring instrument, which in turn affects the reliability of the test results. Measurement errors can adversely affect the inspection results. In this paper, we focus on solving the problem of measurement error when Maxwell distribution is used as a lifetime distribution. This paper focuses on Shewhart, double exponentially weighted moving average (DEWMA) and homogeneously weighted moving average (HWMA), exponentially weighted moving average (EWMA), and generally weighted moving average (GWMA) control charts with measurement error models are presented, respectively. In addition, corresponding control charts corrected for multiple measurements are provided to minimize the effects of measurement errors and ensure that the Maxwell distribution's lifetime characteristics are accurately monitored. Sometimes, relying only on good zero-state run length metrics can be misleading. Therefore, we used a variety of metrics to assess the performance differences between these control charts, including multiple zero-state run length metrics and conditional delay expectations (CED). Meanwhile, through Monte Carlo simulations, we investigate the effects of relevant parameters on the performance of the control charts. Finally, the effectiveness of these control charts in practical applications is further verified through two real examples.

Proteomics and transcriptomics combined reveal specific immunological markers in autoimmune thyroid disease.

The pathogenesis of AITD remains unclear to date. This study employs a combination of proteomics and transcriptomics analysis to identify and validate specific immune response markers in patients with hyperthyroidism and hypothyroidism, thereby providing a scientific basis for the clinical diagnosis and treatment of AITD. By collecting serum and whole blood tissue samples from patients with hyperthyroidism, hypothyroidism, and healthy controls, this study utilizes a combination of transcriptomics and proteomics to analyze changes in immune-related signaling molecules in patients. Specific biomarkers were identified, and the ELISA method was employed to determine the expression levels of these clinical markers and their correlation with clinical features of the patients, ultimately establishing a predictive model. Transcriptomic and proteomic analyses were conducted to identify differentially expressed genes and proteins in patients with hyperthyroidism and hypothyroidism compared to healthy controls. Enrichment analysis revealed that these differentially expressed genes and proteins are primarily associated with immune function, antigen-antibody binding, and alterations in immune cells. Through the combined analysis of transcriptomics and proteomics, key genes IGHG3, ISG15, and ZNF683 were identified. ELISA results from clinical patient serum samples indicated that the levels of IGHG3 were significantly higher in both the hyperthyroid and hypothyroid groups compared to the control group (P<0.05). Additionally, the serum levels of ISG15 in the hyperthyroid group were greater than those in both the control and hypothyroid groups (P<0.05), while the serum levels of ZNF683 in the hypothyroid group exceeded those in the control and hyperthyroid groups (P<0.05). Furthermore, all three biomarkers correlated with the thyroid function of the patients. Prediction models for hyperthyroid and hypothyroid patients were constructed using IGHG3, ISG15, and ZNF683, demonstrating good performance metrics and decision effect. In patients with hyperthyroidism and hypothyroidism, significant changes primarily occur in immune function and immune cells when compared to healthy individuals. Key signaling molecules were identified: ISG15 for hyperthyroidism, ZNF683 for hypothyroidism, and IGHG3 common to both conditions. These findings provide new biomarkers for the diagnosis and monitoring of clinical patients, thereby offering a scientific basis for research on AITD and personalized treatment approaches.

Efficacy and safety of camrelizumab for the treatment of cervical cancer: a systematic review and meta-analysis.

Cervical cancer (CC) is a prevalent malignancy in women and ranks fourth in global cancer-related mortality. The prognosis for women with metastatic or recurring cervical cancer is unfavorable. Camrelizumab is a humanized high-affinity IgG4-kappa monoclonal antibody targeting programmed cell death 1 (PD-1), which has been progressively documented as a therapy for advanced cervical cancer with good result metrics. Nonetheless, a comprehensive investigation of Camrelizumab's efficacy in treating cervical cancer has yet to be conducted. We conducted a search across PubMed, Ovid Medline, Embase, Web of Science, Cochrane Library, Scopus, ProQuest, CNKI, Wan Fang, VIP database, and CBMdisc, restricting the establishment date of the databases to October 2024. The ROBINS-I Scale was utilized to evaluate the methodological quality of the included studies. Furthermore, information about CR, PR, SD, PD, ORR, DCR, median OS, median PFS, adverse events (AEs), and other relevant data was obtained. A meta-analysis was performed utilizing a random-effects model and effect size for illness. This meta-analysis included six trials, including 238 people with CC. The aggregated outcomes for patients were as follows: CR (0.097, 95% CI: 0.032-0.186), PR (0.465, 95% CI: 0.291-0.638), SD (0.264, 95% CI: 0.124-0.403), PD (0.174, 95% CI: 0.051-0.296), ORR (0.577, 95% CI: 0.354-0.799), DCR (0.784, 95% CI: 0.652-0.916), AEs (all grades: 0.836, 95% CI: 0.629-1.000, ≥grade III: 0.472, 95% CI: 0.111-0.834). The predominant treatment-related adverse events included anemia (≤grade II: 0.295, 95% CI: 0.187-0.402; ≥grade III: 0.124, 95% CI: 0.018-0.230), elevated aspartate aminotransferase (≤grade II: 0.196, 95% CI: 0.013-0.380; ≥grade III: 0.030, 95% CI: 0.007-0.053), neutropenia (≤grade II: 0.206, 95% CI: 0.150-0.261; ≥grade III: 0.114, 95% CI: 0.066-0.162), thrombocytopenia (≤grade II: 0.295, 95% CI: 0.187-0.402), and fatigue (≤grade II: 0.174, 95% CI: 0.046-0.303). This meta-analysis demonstrates that camrelizumab is efficacious and well-tolerated in patients with cervical cancer. https://www.crd.york.ac.uk/prospero/, identifier CRD42024527065.

Sentiment Analysis for Tourism Insights: A Machine Learning Approach

This paper explores international tourism regarding Morocco’s leading touristic city Marrakech, and, more precisely, its two prominent public spaces, Jemaa el-Fna and the Medina. Following a web-scraping process of English reviews on TripAdvisor, a machine learning technique is proposed to gather insights into prominent topics in the data, and their corresponding sentiment with a specific voting model. This process allows decision makers to direct their focus onto certain issues, such as safety concerns, animal conditions, health, or pricing issues. In addition, the voting method outperforms Vader, a widely used sentiment prediction tool. Furthermore, an LLM (Large Language Model) is proposed, the SieBERT-Marrakech. It is a SieBERT model fine-tuned on our data. The model outlines good performance metrics, showing even better results than GPT-4o, and it may be an interesting choice for tourism sentiment predictions in the context of Marrakech.

A Comparative Study of Deep Learning Frameworks Applied to Coffee Plant Detection from Close-Range UAS-RGB Imagery in Costa Rica

Introducing artificial intelligence techniques in agriculture offers new opportunities for improving crop management, such as in coffee plantations, which constitute a complex agroforestry environment. This paper presents a comparative study of three deep learning frameworks: Deep Forest, RT-DETR, and Yolov9, customized for coffee plant detection and trained from images with a high spatial resolution (cm/pix). Each frame had dimensions of 640 × 640 pixels acquired from passive RGB sensors onboard a UAS (Unmanned Aerial Systems) system. The image set was structured and consolidated from UAS-RGB imagery acquisition in six locations along the Central Valley, Costa Rica, through automated photogrammetric missions. It was evidenced that the RT-DETR and Yolov9 frameworks allowed adequate generalization and detection with mAP50 values higher than 90% and mAP5095 higher than 54%, in scenarios of application with data augmentation techniques. Deep Forest also achieved good metrics, but noticeably lower when compared to the other frameworks. RT-DETR and Yolov9 were able to generalize and detect coffee plants in unseen scenarios that include complex forest structures within tropical agroforestry Systems (AFS).

Sharing is CAIRing: Characterizing principles and assessing properties of universal privacy evaluation for synthetic tabular data

Data sharing is a necessity for innovative progress in many domains, especially in healthcare. However, the ability to share data is hindered by regulations protecting the privacy of natural persons. Synthetic tabular data provide a promising solution to address data sharing difficulties but does not inherently guarantee privacy. Still, there is a lack of agreement on appropriate methods for assessing the privacy-preserving capabilities of synthetic data, making it difficult to compare results across studies. To the best of our knowledge, this is the first work to identify properties that constitute good universal privacy evaluation metrics for synthetic tabular data. The goal of universally applicable metrics is to enable comparability across studies and to allow non-technical stakeholders to understand how privacy is protected. We identify four principles for the assessment of metrics: Comparability, Applicability, Interpretability, and Representativeness (CAIR). To quantify and rank the degree to which evaluation metrics conform to the CAIR principles, we design a rubric using a scale of 1–4. Each of the four properties is scored on four parameters, yielding 16 total dimensions. We study the applicability and usefulness of the CAIR principles and rubric by assessing a selection of metrics popular in other studies. The results provide granular insights into the strengths and weaknesses of existing metrics that not only rank the metrics but highlight areas of potential improvements. We expect that the CAIR principles will foster agreement among researchers and organizations on which universal privacy evaluation metrics are appropriate for synthetic tabular data.

The Smart Approach to Selecting Good Cyber Security Metrics

When it comes to the need to manage cyber security, identifying and utilizing good cyber security metrics is essential. This allows organizations to manage their cyber risk more effectively. However, the literature lacks consensus on the properties and characteristics of good metrics. Hence, the objectives of this work are to explore and identify relevant technical metrics proposed by researchers in the cyber security domain, and then to assess them against the SMART (Specific, Measurable, Actionable, Relevant, and Timely) criteria to determine their feasibility and improve the quality of the selected security metrics. We identified 105 metrics, of which 23 passed the SMART criteria. The resulting set of metrics can be considered as a feasible set of metrics to implement. Additionally, we identified additional criteria that may be considered when assessing security metrics, most of which can be regarded as variants of the SMART criteria except two, wherein the metrics should be inexpensive to gather and independently verifiable via an outside reference.

Global evaluation of NOAA-20 VIIRS dark target aerosol products over land and ocean

The Dark Target (DT) algorithm has been applied to the Visible Infrared Imaging Radiometer Suite (VIIRS) aboard the Suomi-NPP (SNPP) and NOAA-20 satellites to extend the aerosol data record from the Moderate Resolution Imaging Spectrometer (MODIS). The newly released VIIRS DT Version 2.0 (V2.0) dataset includes NOAA-20 aerosol products for the first time. This study provides the first evaluation of NOAA-20 VIIRS DT aerosol products, including aerosol optical depth (AOD) and Ångstrom exponent (AE), for the period 2018–2022 using Aerosol Robotic Network (AERONET) and Maritime Aerosol Network (MAN) measurements. In addition, the operational DT aerosol products from SNPP VIIRS (V2.0) and MODIS (Collection 6.1) are also used for comparison purposes. Overall, NOAA-20 AODs over land and ocean exhibit good validation metrics globally, showing comparability to MODIS products and superiority over overestimated SNPP products. Nevertheless, it is worth noting that in South Africa specifically, NOAA-20 land AODs tends to display more pronounced negative biases, despite all products being underestimated. Furthermore, all ocean AE products demonstrate high correlation coefficients (>0.83) with the ground-based data, meeting the fraction of expected accuracy (>80%). Encouragingly, NOAA-20 AE product has significantly improved the persistent issue of overestimation at low-value in MODIS product, making it a more preferable choice for usage. Error analysis reveals that the performance of all three land products decreases in sparsely vegetated areas and when the solar zenith angle is small. However, NOAA-20 AOD exhibits relatively stable performance and is less affected by variations in aerosol loading, observation geometry, and surface vegetation cover. In addition, the performance of AOD and AE over ocean is significantly influenced by scattering angle and wind speed. This research is anticipated to serve as a reference for the utilization of operational VIIRS DT aerosol products and possible algorithm optimization.

A Novel Machine Learning-Based Predictive Model of Clinically Significant Prostate Cancer and Online Risk Calculator

ObjectivesTo create a machine learning predictive model combining PI-RADS score, PSA density, and clinical variables to predict clinically significant prostate cancer (csPCa). MethodsWe evaluated a cohort of patients who underwent prostate biopsy for suspected prostate cancer (PCa) in New Zealand, Australia, and Switzerland. We collected data on age, body mass index (BMI), PSA level, prostate volume, PSA density (PSAD), PI-RADS scores, previous biopsy, and corresponding histology results. The dataset was divided into derivation (training) and validation (test) sets using random splits. An independent dataset was obtained from the Harvard Dataverse for external validation. A cohort of 1272 patients was analyzed. We fitted a Lasso model, XGBoost, and LightGBM to the training set and assessed their accuracy. ResultsAll models demonstrated ROC AUC values ranging from 0.830 to 0.851. LightGBM was considered the superior model, with an ROC of 0.851 [95%CI: 0.804 – 0.897] in the test set and 0.818 [95% CI: 0.798 – 0.831] in the external dataset. The most important variable was PI-RADS, followed by PSA density, history of previous biopsy, age, and BMI. ConclusionsWe developed a predictive model for detecting csPCa that exhibited a high ROC-AUC value for internal and external validations. This suggests that the integration of the clinical parameters outperformed each individual predictor. Additionally, the model demonstrated good calibration metrics, indicative of a more balanced model than the existing models.

Capability of ChatGPT to support the screening process of scoping reviews: A feasibility study

Abstract Background The time-consuming screening phase in health-related evidence syntheses is increasingly supported by artificial intelligence (AI). However, scoping reviews have not benefited as much as systematic reviews from such AI tools as they utilize conceptual rather than keyword-specific search strategies to address broad research questions. Context-understanding chatbots based on large language models could potentially enhance the efficiency of scoping review screenings. This study evaluates the performance of ChatGPT against an open-access AI tool used for abstract screening in systematic reviews and the costs involved. Methods Leveraging data from a prior scoping review, we compared the performance of ChatGPT 4.0 and 3.5 against Rayyan, using human researchers’ decisions as a benchmark. A random set of 50 included and 50 excluded abstracts was used to train Rayyan’s algorithm and to develop ChatGPT’s prompt. ChatGPT 4.0’s evaluation was repeated after 5-7 days to assess response consistency. We computed performance metrics including sensitivity, specificity, and accuracy. Results ChatGPT 4.0 and 3.5 achieved 68% accuracy, 11% precision, 99% negative predictive value, and 67% specificity. Sensitivity was high at 88-89% for ChatGPT 4.0 and 84% for ChatGPT 3.5. ChatGPT 4.0 showed a substantial interrater reliability between the two evaluations and moderate reliability compared to ChatGPT 3.5. The cost of deployment varied, with Rayyan being free, ChatGPT 3.5 costing $9.06 and ChatGPT 4.0 $505.72. Conclusions Given the exponential increase in publications, effective mechanisms to support the screening phase of scoping reviews are needed. Our feasibility study using ChatGPT to decide on abstracts’ inclusion or exclusion achieved good performance metrics. Given further positive evaluation, such chatbots might be incorporated in the standard screening process, possibly replacing a second screener, saving time and costs, and accelerating evidence synthesis. Key messages • ChatGPT performs well in supporting screening for scoping reviews, outperforming a traditional AI tool at reasonable costs. • Employing chatbots like ChatGPT could potentially cut costs and time in scoping reviews.

Leveraging machine learning to minimize experimental trials and predict hot deformation behaviour in dual phase high entropy alloys

In recent time, high entropy alloys (HEAs) are widely used due to their wide design space and remarkable properties allowing a vast range of property variations with myriads of possible combinations of constituent elements. This research utilizes machine learning techniques, including Random Forest (RF), K-Nearest Neighbors (KNN), XGBoost (XGB), Decision Tree (DT), and Support Vector Regressor (SVR), to predict the flow stress behavior of the dual FCC phase CoCrCu1.2FeNi high entropy alloy (HEA) at new temperature and strain rates to reduce the experiments dependency. The RF and KNN models were identified as top performers, with R² values of 0.987 and 0.986, respectively. These models successfully predicted flow stresses, aligning closely with actual measurements. A new flow stress-strain curve was generated at new temperature of 1123 K, demonstrating good performance metrics for RF and KNN. with R² values of 0.97 and 0.958 respectively. This approach has the potential to significantly reduce the need for extensive experimental work in determining the mechanical behaviour of HEA, offering substantial savings in time, cost, and energy, and marks a significant advancement in the development of such alloys.

Analyzing the impact of transfer learning on explanation accuracy in deep learning-based ECG recognition systems

Abstract Electrocardiogram (ECG) recognition systems now play a leading role in the early detection of cardiovascular diseases. However, the explanation of judgments made by deep learning models in these systems is prominent for clinical acceptance. This article reveals the effect of transfer learning in ECG recognition systems on decision precision. This article investigated the role of transfer learning in ECG image classification using a customized convolutional neural network (CNN) with and without a VGG16 architecture. The customized CNN model with the VGG16 achieved a good test accuracy of 98.40%. Gradient-weighted class activation mapping (Grad-CAM), for this model, gave the wrong information because it focused on parts of the ECG that were not important for making decisions instead of features necessary for clinical diagnosis, like the P wave, QRS complex, and T wave. A proposed model that only used customized CNN layers and did not use transfer learning performed 99.08% on tests gave correct Grad-CAM explanations and correctly identified the influencing areas of decision-making in the ECG image. Because of these results, it seems that transfer learning might provide good performance metrics, but it might also make things harder to understand, which could make it harder for deep learning models that use ECG recognition to be reliable for diagnosis. This article concludes with a call for careful consideration when using transfer learning in the medical field, as model explanations resulting from such learning may not be appropriate when it comes to domain-specific interpretations.

Supervised star, galaxy, and QSO classification with sharpened dimensionality reduction

We explored the use of broadband colors to classify stars, galaxies, and quasi-stellar objects (QSOs). Specifically, we applied sharpened dimensionality reduction (SDR)-aided classification to this problem, with the aim of enhancing cluster separation in the projections of high-dimensional data clusters to allow for better classification performance and more informative projections. The main objective of this work was to apply SDR to large sets of broadband colors derived from the CPz catalog to obtain projections with clusters of star, galaxy, and QSO data that exhibit a high degree of separation. The SDR method achieves this by combining density-based clustering with conventional dimensionality-reduction techniques. To make SDR scalable and have the ability to project samples using the earlier-computed projection, we used a deep neural network trained to reproduce the SDR projections. Subsequently classification was done by applying a $k$-nearest neighbors ($k$-NN) classifier to the sharpened projections. Based on a qualitative and quantitative analysis of the embeddings produced by SDR, we find that SDR consistently produces accurate projections with a high degree of cluster separation. A number of projection performance metrics are used to evaluate this separation, including the trustworthiness, continuity, Shepard goodness, and distribution consistency metrics. Using the $k$-NN classifier and consolidating the results of various data sets, we obtain precisions of 99.7&lt;!PCT!&gt;, 98.9&lt;!PCT!&gt;, and 98.5&lt;!PCT!&gt; for classifying stars, galaxies, and QSOs, respectively. Furthermore, we achieve completenesses of 97.8&lt;!PCT!&gt;, 99.3&lt;!PCT!&gt;, and 86.8&lt;!PCT!&gt;, respectively. In addition to classification, we explore the structure of the embeddings produced by SDR by cross-matching with data from Gaia DR3, Galaxy Zoo 1, and a catalog of specific star formation rates, stellar masses, and dust luminosities. We discover that the embeddings reveal astrophysical information, which allows one to understand the structure of the high-dimensional broadband color data in greater detail. We find that SDR-aided star, galaxy, and QSO classification performs comparably to another unsupervised learning method using hierarchical density-based spatial clustering of applications with noise (HDBSCAN) but offers advantages in terms of scalability and interpretability. Furthermore, it outperforms traditional color selection methods in terms of QSO classification performance. Overall, we demonstrate the potential of SDR-aided classification to provide an accurate and physically insightful classification of astronomical objects based on their broadband colors.

A semi-supervised learning algorithm for multi-label classification and multi-assignment clustering problems based on a Multivariate Data Analysis

Classically, in classification and clustering problems, an individual is exclusively assigned to a class (labeled data) or a cluster (unlabeled data). However, the assignment to a single class or cluster may be too strict in several real-world domains. In many cases, an individual may belong to multiple classes or clusters at the same time. On the other hand, we are starting to see machine learning algorithms that solve the problem of multi-label classification and multiple cluster assignment, but there are no algorithms that solve both problems simultaneously. Classic semi-supervised algorithms can work with labeled and unlabeled data simultaneously, but these types of algorithms assign individuals to a single class or a single cluster. Today, artificial intelligence faces the challenge of developing semi-supervised learning algorithms to work with semi-labeled data that can be assigned to different classes or clusters at the same time. In particular, this paper proposes a semi-supervised learning algorithm to fill this gap, which can solve the problems of multi-label classification and multiple cluster assignment simultaneously, on a semi-labeled dataset. This proposal is based on the LAMDA algorithm (Learning Algorithm for Multivariate Data Analysis), which calculates the degree of membership of a data to a group/class. In this work, a membership threshold is defined, which allows individuals to be assigned to classes or clusters that have a membership greater than this membership threshold. Thus, the main contribution of this work is the development of a semi-supervised algorithm that can process semi-labeled datasets to assign them to multiple classes and/or clusters. Furthermore, the work defines a metric to evaluate its efficiency in a semi-supervised context, called Multi Label-Cluster Index (MULCI). This proposal is tested on several datasets from the domains of multi-label classification or multi-assignment clustering, or a combination of both, showing very encouraging results. Very good quality metrics results are achieved in multiclass and multicluster tasks.

Achieving High-Performance Polymer-Wrapper-Free Aligned Carbon Nanotube Field-Effect Transistors Through Degradable Polymer Wrapping and Efficient Removal Techniques.

Semiconducting carbon nanotubes (s-CNTs) have emerged as a promising alternative to traditional silicon for ultrascaled field-effect transistors (FETs), owing to their exceptional properties. Aligned s-CNTs (A-CNTs) are particularly favored for practical applications due to their ability to provide higher driving current and lower contact resistance compared with individual s-CNTs or random networks. Achieving high-semiconducting-purity A-CNTs typically involves conjugated polymer wrapping for selective separation of s-CNTs, followed by self-assembly techniques. However, the presence of the polymer wrapper on A-CNTs can adversely impact electrical contact, gating efficiency, carrier transport, and device-to-device variations, necessitating its complete removal. While various methods have been explored for polymer removal, accurately characterizing the extent of removal remains a challenge. Traditional techniques such as absorption spectroscopy and X-ray photoelectron spectroscopy (XPS) may not accurately depict the remaining polymer content on A-CNTs due to their inherent detection limits. Consequently, the performance of FETs based on pure polymer-wrapper-free A-CNTs is unclear. In this study, we present an approach for preparing high-semiconducting-purity and polymer-wrapper-free A-CNTs using poly[(9,9-dioctylfluorenyl-2,7-dinitrilomethine)-(9,9-dioctylfluorenyl-2,7-dimethine)] (PFO-N-PFO), a degradable polymer, in conjunction with a modified dimension-limited self-alignment process (m-DLSA). Comprehensive transmission electron microscopy (TEM) characterizations, complemented by absorption and XPS characterizations, provide robust evidence of the successful near-complete removal of the polymer wrapper via a cleaning procedure involving acidic degradation, hot solvent rinsing, and vacuum annealing. Furthermore, top-gated FETs based on these high-semiconducting-purity and polymer-wrapper-free A-CNTs exhibit good performance metrics, including an on-current (Ion) of 2.2 mA/μm, peak transconductance (gm) of 1.1 mS/μm, low contact resistance (Rc) of 191 Ω·μm, and negligible hysteresis, representing a significant advancement in the CNT-based FET technology.

Development and initial evaluation of a clinical prediction model for risk of treatment resistance in first-episode psychosis: Schizophrenia Prediction of Resistance to Treatment (SPIRIT).

A clinical tool to estimate the risk of treatment-resistant schizophrenia (TRS) in people with first-episode psychosis (FEP) would inform early detection of TRS and overcome the delay of up to 5 years in starting TRS medication. To develop and evaluate a model that could predict the risk of TRS in routine clinical practice. We used data from two UK-based FEP cohorts (GAP and AESOP-10) to develop and internally validate a prognostic model that supports identification of patients at high-risk of TRS soon after FEP diagnosis. Using sociodemographic and clinical predictors, a model for predicting risk of TRS was developed based on penalised logistic regression, with missing data handled using multiple imputation. Internal validation was undertaken via bootstrapping, obtaining optimism-adjusted estimates of the model's performance. Interviews and focus groups with clinicians were conducted to establish clinically relevant risk thresholds and understand the acceptability and perceived utility of the model. We included seven factors in the prediction model that are predominantly assessed in clinical practice in patients with FEP. The model predicted treatment resistance among the 1081 patients with reasonable accuracy; the model's C-statistic was 0.727 (95% CI 0.723-0.732) prior to shrinkage and 0.687 after adjustment for optimism. Calibration was good (expected/observed ratio: 0.999; calibration-in-the-large: 0.000584) after adjustment for optimism. We developed and internally validated a prediction model with reasonably good predictive metrics. Clinicians, patients and carers were involved in the development process. External validation of the tool is needed followed by co-design methodology to support implementation in early intervention services.

A novel domain adaptive method for gearbox fault diagnosis using maximum multiple-classifier discrepancy network

Abstract Domain adaptive gearbox fault diagnosis methods have made impressive achievements for the past several years. However, most of the traditional domain adaptive methods have significant limitations under fluctuating operating conditions. The acquired acceleration signals will result in different signal vibration spectra and peak vibration amplitudes due to the different working conditions between the source and target domains. There is an obvious discrepancy between the distribution of fault samples in the source domain and the target domain, which in turn makes it difficult to classify the target domain samples with fuzzy fault category boundaries. Therefore, how to measure the discrepancy between two distributions has been an important research direction in machine learning. A good metric helps to discover better features and build better models. In this paper, a novel domain adaptive method for gearbox fault diagnosis using maximum multiple-classifier discrepancy network (MMCDN) is proposed. The sparse stack autoencoder is used by the MMCDN as a feature extractor for fault feature extraction, and a kind of composite distance is adopted for domain discrepancy measurement of source and target domain features for domain alignment. Then the extracted features are input into a three-classifier of the model for adversarial training. The trained model classifiers have high performance in fault classification. The combination of domain adaptation and multi-classifier discrepancy output can effectively solve the impact of working condition changes and the misclassification problem for fuzzy samples with class boundaries. Experimental validation with two planetary gearbox datasets shows that the MMCDN has more favorable diagnostic accuracy and performance than other methods.

Pedestrians’ intent to cross in a fully autonomous vehicle environment; looking at crossing opportunity, eHMI message and wait time

Objectives Currently, pedestrians’ road-crossing decisions depend on the traffic at the crossing point, crossing opportunities, and circumstantial elements. Longer wait times on the curb and time pressure raise the number of traffic violations among pedestrians. The era of fully autonomous vehicles (FAVs) promises new interactions. External Human-Machine Interfaces (eHMIs) aim to increase the understanding of FAVs’ intentions and will influence pedestrians’ intent to cross. Yet, how pedestrian behaviors will change in the FAV era remains unclear. Further, there are no good metrics for evaluating the intricate interaction of crossing-related factors. Methods In a laboratory study, sixty participants observed crossing scenarios of a typical one-lane road with 10–12 FAVs driving along, two possible eHMI messages (“Cross!”/“Stop!”), and varying crossing opportunities (safe, risky, and unsafe). Participants had to indicate when they intended to cross the road using a designated button. Half of the participants were induced to feel time pressure. We developed index scores to convey the complexity of such crossing situations from the perspective of a pedestrian and used them to analyze the experimental data. Results In total, 48% of participants’ indications were to cross in safe crossing opportunities, 34% risky, and 18% unsafe; 69% were made when the eHMI proposition was “Cross!” and 31% for “Stop!”. High, significant, and negative correlations were found for compatible responses, e.g., with a safe crossing gap and an eHMI sign to “Cross!”. The opposite was true for incompatibility, e.g., a safe crossing gap and an eHMI sign to “Stop!” or an unsafe crossing gap and an eHMI sign to “Cross!”. The time pressure group’s median times to cross were shorter, making riskier decisions. Conclusion Our findings reflect a tendency to comply with the eHMI. In more complex scenarios where the crossing opportunity was uncertain or waiting times were longer, we observed that pedestrians were more inclined to follow the eHMI’s guidance to cross. These findings suggest that pedestrians may be more likely to follow the eHMI’s suggestion to cross than their self-skill, especially under time pressure. Our indices and metrics reflect the intricate interaction aspects of pedestrian behavior with eHMIs.

Good Rates From Bad Coordinates: The Exponential Average Time-dependent Rate Approach.

Our ability to calculate rate constants of biochemical processes using molecular dynamics simulations is severely limited by the fact that the time scales for reactions, or changes in conformational state, scale exponentially with the relevant free-energy barrier heights. In this work, we improve upon a recently proposed rate estimator that allows us to predict transition times with molecular dynamics simulations biased to rapidly explore one or several collective variables (CVs). This approach relies on the idea that not all bias goes into promoting transitions, and along with the rate, it estimates a concomitant scale factor for the bias termed the "CV biasing efficiency" γ. First, we demonstrate mathematically that our new formulation allows us to derive the commonly used Infrequent Metadynamics (iMetaD) estimator when using a perfect CV, where γ = 1. After testing it on a model potential, we then study the unfolding behavior of a previously well characterized coarse-grained protein, which is sufficiently complex that we can choose many different CVs to bias, but which is sufficiently simple that we are able to compute the unbiased rate directly. For this system, we demonstrate that predictions from our new Exponential Average Time-Dependent Rate (EATR) estimator converge to the true rate constant more rapidly as a function of bias deposition time than does the previous iMetaD approach, even for bias deposition times that are short. We also show that the γ parameter can serve as a good metric for assessing the quality of the biasing coordinate. We demonstrate that these results hold when applying the methods to an atomistic protein folding example. Finally, we demonstrate that our approach works when combining multiple less-than-optimal bias coordinates, and adapt our method to the related "OPES flooding" approach. Overall, our time-dependent rate approach offers a powerful framework for predicting rate constants from biased simulations.