A Novel Fiber Bragg Grating Sensor Placement Optimization Approach for Civil Pilots

To investigate the value of texture analysis on unenhanced computed tomography (CT) to potentially differentiate mass-forming pancreatitis (MFP) from pancreatic ductal adenocarcinoma (PDAC). A retrospective study consisting of 109 patients (30 MFP patients vs 79 PDAC patients) who underwent preoperative unenhanced CT between January 2012 and December 2017 was performed. Synthetic minority oversampling technique (SMOTE) algorithm was adopted to reconstruct and balance MFP and PDAC samples. A total of 396 radiomic features were extracted from unenhanced CT images. Mann-Whitney U test and minimum redundancy maximum relevance (MRMR) methods were used for the purpose of dimension reduction. Predictive models were constructed using random forest (RF) method, and were validated using leave group out cross-validation (LGOCV) method. Diagnostic performance of the predictive model, including sensitivity, specificity, accuracy, positive predicting value (PPV), and negative predicting value (NPV), was recorded. We applied 200% of SMOTE to MFP and PDAC patients, resulting in 90 MFP patients compared with 120 PDAC patients. Dimension reduction steps yielded 30 radiomic features using Mann-Whitney U test and MRMR methods. Ten radiomic features were retained using RF method. Four most predictive parameters, including GreyLevelNonuniformity_angle90_offset1, VoxelValueSum, HaraVariance, and ClusterProminence_AllDirection_offset1_SD, were used to generate the predictive model with preferable 92.2% sensitivity, 94.2% specificity, 93.3% accuracy, 92.2% PPV, and 94.2% NPV. Finally, in LGOCV analysis, a high pooled mean sensitivity, specificity, and accuracy (82.6%, 80.8%, and 82.1%, respectively) indicate a relatively reliable and stable predictive model. Unenhanced CT texture analysis can be a promising noninvasive method in discriminating MFP from PDAC.

We propose a approach to determine features directly based on classification target of proteomic profile, which combines minimum redundancy maximum relevance (MRMR) and support vector machines (SVM). Firstly, the profile are preprocessed through iterative minimum in adaptive setting window (IMASW) and searching window methods for correcting negative intensities caused by manual preprocessing and peak picking. Then, MRMR and support vector machines (SVM) techniques were used to identify biomarkers and build discrimination model. With an optimization of the parameters involved in the modeling, a satisfactory model was achieved for ovarian cancer diagnosis based on proteomic peptide profile dataset. To study the performance of MRMR, we applied two statistical method, t test and Wilcoxon signed-rank test, to identify features. The results show that MRMR method is more efficient.

Deep convolutional neural networks perform well in the field of computer vision, but exhibit undesirable behaviors such as memorization and sensitivity to adversarial examples. Therefore, proper regularization strategies are needed to alleviate these problems. Currently, regularization strategies with mixed sample data augmentation perform very well, and these algorithms allow the network to generalize better, improve the baseline performance of the model. However, interpolation-based mixed sample data augmentation distorts the data distribution, while masking-based mixed sample data augmentation results in excessive information loss for overly regular shapes of masks. Although mixed sample data augmentation is proven to be an effective method to improve the baseline performance, generalization ability and robustness of deep convolutional models, there is still room for improvement in terms of maintaining the of image local consistency and image data distribution. In this paper, we propose a new mixed sample data augmentation-LMix, which uses random masking to increase the number of masks in the image to maintain the data distribution, and high-frequency filtering to sharpen the image to highlight recognition regions. We applied the method to train CIFAR-10, CIFAR-100, SVHN, and Tiny-ImageNet datasets under the PreAct-ResNet18 model to evaluate the method, and obtained the latest results of 96.32, 79.85, 97.01, and 64.16%, respectively, which are 1.70, 4.73, and 8.06% higher than the optimal baseline accuracy. The LMix algorithm improves the generalization ability of the state-of-the-art neural network architecture and enhances the robustness to adversarial samples.

In current biology, exploring the biological functions of proteins is important. Given the large number of proteins in some organisms, exploring their functions one by one through traditional experiments is impossible. Therefore, developing quick and reliable methods for identifying protein functions is necessary. Considerable accumulation of protein knowledge and recent developments on computer science provide an alternative way to complete this task, that is, designing computational methods. Several efforts have been made in this field. Most previous methods have adopted the protein sequence features or directly used the linkage from a protein–protein interaction (PPI) network. In this study, we proposed some novel multi-label classifiers, which adopted new embedding features to represent proteins. These features were derived from functional domains and a PPI network via word embedding and network embedding, respectively. The minimum redundancy maximum relevance method was used to assess the features, generating a feature list. Incremental feature selection, incorporating RAndom k-labELsets to construct multi-label classifiers, used such list to construct two optimum classifiers, corresponding to two key measurements: accuracy and exact match. These two classifiers had good performance, and they were superior to classifiers that used features extracted by traditional methods.

BackgroundAccurate and early selection of patients with advanced non-small cell lung cancer (NSCLC) who would benefit from immunotherapy is of the utmost clinical importance. The aim of our study was...

Pancreatic cancer, mostly presenting as pancreatic ductal adenocarcinoma (PDAC), has a poor prognosis. The microsatellite-instable (MSI-H)/mismatch repair deficient (MMRd) subtype, however, is more susceptible to immune therapy and is expected to have a better prognosis. Presently, MSI-testing is not routinely performed on PDAC. We assessed whether quantitative imaging features (radiomics) of pretreatment computed tomography (CT) scans could diagnose MSI-H/MMRd. For this pilot study, we analyzed CT-scans of treatment-naïve sporadic or Lynch syndrome (LS)-associated MSI-H or MMRd PDACs, diagnosed or treated in a single center from 2007 to August 2022. CT-scans of resected MSI-stable, MMR proficient, non-LS PDACs formed a control group, after random selection in 1:4 ratio. Upon CT-scan segmentation, 254 well-defined radiomic features were extracted from pancreas and tumor regions. The predictability of the features was assessed within a repeated stratified 3-fold cross-validation framework by designing three models using random forest classifier, with the most discriminating features selected through the minimum redundancy maximum relevance method from three feature sets: tumor radiomics, pancreas radiomics, and combined tumor + pancreas radiomics. Performance was evaluated by area under receiver operating curve (AUC), sensitivity, specificity, positive and negative predictive value. Overall, 95 patients were included: 19 patients with MSI-H/MMRd/LS (36.8% female; median age at diagnosis 72 [IQR 60-77 years]) and 76 matched controls with PDAC (53.9% female; median age at diagnosis 66 [IQR 57-74years]). Median year when CT-scan was done was 2017 and 2018, respectively. The model using radiomic features from the pancreatic tumor reflecting MSI-H/MMRd, had an area under receiver operating curve (AUC) of 0.73. The performance of the model was improved by also incorporating radiomic features from pancreas texture (AUC of combined model 0.83 sensitivity 84%, specificity 78%, negative predictive value 95%). This pilot study suggests that radiomic features could be used to determine MSI/MMRd status in CT-scans of PDAC, but needs further independent multi-site validation in larger cohorts. Routine application of radiomics to determine MSI-status might be of interest in clinical practice to select patients who could benefit from immune therapy.

The world-wide Coronavirus Disease 2019 (COVID-19) pandemic was triggered by the widespread of a new strain of coronavirus named as severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Multiple studies on the pathogenesis of SARS-CoV-2 have been conducted immediately after the spread of the disease. However, the molecular pathogenesis of the virus and related diseases has still not been fully revealed. In this study, we attempted to identify new transcriptomic signatures as candidate diagnostic models for clinical testing or as therapeutic targets for vaccine design. Using the recently reported transcriptomics data of upper airway tissue with acute respiratory illnesses, we integrated multiple machine learning methods to identify effective qualitative biomarkers and quantitative rules for the distinction of SARS-CoV-2 infection from other infectious diseases. The transcriptomics data was first analyzed by Boruta so that important features were selected, which were further evaluated by the minimum redundancy maximum relevance method. A feature list was produced. This list was fed into the incremental feature selection, incorporating some classification algorithms, to extract qualitative biomarker genes and construct quantitative rules. Also, an efficient classifier was built to identify patients infected with SARS-COV-2. The findings reported in this study may help in revealing the potential pathogenic mechanisms of COVID-19 and finding new targets for vaccine design.

The paper introduces a new concept of large-scale security of cyberspace and physical environments that are based on swarm intelligence and multi-agent intrusion detection systems. The suggested approach employs Robust Z-Score Normalization with Winsorization as an effective way of preprocessing the data, in the case of outliers and noise. Minimum Redundancy Maximum Relevance method is used to select the most relevant features and hence the most efficient way to train the classifier. A Graph Attention Networkis used as the classifier, and the advantage of multi-agent interactions is exploited to increase the accuracy of detection and scalability. The system is deployed in its entirety with Databricks Lakehouse that enables real-time processing and smooth management of the data. The experimental findings indicate that the proposed approach exhibits significantly better results than the conventional approaches to IDS, and possesses greater accuracy of detection, precision and recall. The paper shows that swarm intelligence and multi-agent systems can be used to enhance security of complex cyber-physical infrastructure.

Intrahepatic cholangiocarcinoma (IHC) is an aggressive liver cancer with a five-year survival rate of less than 10%. Surgery is the only curative treatment. However, most patients die of disease recurrence, with more than 50% recurring within 2 years. The liver is the most common site. Recurrence at liver within a short period after surgery is common and eventually leads to death. Currently, there is no way to assess the risk of early recurrence or death in these patients. Methods to predict these risks would help physicians select the best treatment plan for individual patients; patients at high risk of recurrence could be treated early or at the time of surgery with chemotherapy or radiation. Such changes in patient management would greatly impact patients’ prospects of survival. The objective of the present study is to identify preoperative computed tomography (CT)-based quantitative imaging predictors of early hepatic recurrence. Two hundred fifty four texture features were extracted from CT-tumor and future liver remnant (FLR) along with tumor size. With features selected using minimum redundancy maximum relevance method and AdaBoost classifier, we obtained an area under the receiver operating characteristic curve of 0.78 using a 3-fold cross-validation for a cohort of 139 patients with IHC.

Simple SummaryRadiotherapy for cancer patients can cause abnormal DNA methylation. We developed a computational workflow that can identify crucial methylation alterations related to treatment exposure in childhood cancer survivors.Radiotherapy is a helpful treatment for cancer, but it can also potentially cause changes in many molecules, resulting in adverse effects. Among these changes, the occurrence of abnormal DNA methylation patterns has alarmed scientists. To explore the influence of region-specific radiotherapy on blood DNA methylation, we designed a computational workflow by using machine learning methods that can identify crucial methylation alterations related to treatment exposure. Irrelevant methylation features from the DNA methylation profiles of 2052 childhood cancer survivors were excluded via the Boruta method, and the remaining features were ranked using the minimum redundancy maximum relevance method to generate feature lists. These feature lists were then fed into the incremental feature selection method, which uses a combination of deep forest, k-nearest neighbor, random forest, and decision tree to find the most important methylation signatures and build the best classifiers and classification rules. Several methylation signatures and rules have been discovered and confirmed, allowing for a better understanding of methylation patterns in response to different treatment exposures.

The prediction of particles less than 2.5 micrometers in diameter (PM2.5) in fog and haze has been paid more and more attention, but the prediction accuracy of the results is not ideal. Haze prediction algorithms based on traditional numerical and statistical prediction have poor effects on nonlinear data prediction of haze. In order to improve the effects of prediction, this paper proposes a haze feature extraction and pollution level identification pre-warning algorithm based on feature selection and integrated learning. Minimum Redundancy Maximum Relevance method is used to extract low-level features of haze, and deep confidence network is utilized to extract high-level features. eXtreme Gradient Boosting algorithm is adopted to fuse low-level and high-level features, as well as predict haze. Establish PM2.5 concentration pollution grade classification index, and grade the forecast data. The expert experience knowledge is utilized to assist the optimization of the pre-warning results. The experiment results show the presented algorithm can get better prediction effects than the results of Support Vector Machine (SVM) and Back Propagation (BP) widely used at present, the accuracy has greatly improved compared with SVM and BP.

Preserving the performance of a trained model while removing unique characteristics of marked training data points is challenging. Recent research usually suggests retraining a model from scratch with remaining training data or refining the model by reverting the model optimization on the marked data points. Unfortunately, aside from their computational inefficiency, those approaches inevitably hurt the resulting model's generalization ability since they remove not only unique characteristics but also discard shared (and possibly contributive) information. To address the performance degradation problem, this paper presents a novel approach called Performance Unchanged Model Augmentation (PUMA). The proposed PUMA framework explicitly models the influence of each training data point on the model's generalization ability with respect to various performance criteria. It then complements the negative impact of removing marked data by reweighting the remaining data optimally. To demonstrate the effectiveness of the PUMA framework, we compared it with multiple state-of-the-art data removal techniques in the experiments, where we show the PUMA can effectively and efficiently remove the unique characteristics of marked training data without retraining the model that can 1) fool a membership attack, and 2) resist performance degradation. In addition, as PUMA estimates the data importance during its operation, we show it could serve to debug mislabelled data points more efficiently than existing approaches.

In machine translation evaluation, the traditional wisdom measures model's generalization ability in an average sense, for example by using corpus BLEU. However, the statistics of corpus BLEU cannot provide comprehensive understanding and fine-grained analysis on model's generalization ability. As a remedy, this paper attempts to understand NMT at fine-grained level, by detecting contextual barriers within an unseen input sentence that cause the degradation in model's translation quality. It proposes a principled definition of source contextual barriers as well as its modified version which is tractable in computation and operates at word-level. Based on the modified one, three simple methods are proposed for barrier detection by search-aware risk estimation through counterfactual generation. Extensive analyses are conducted on those detected contextual barrier words on both Zh $\Leftrightarrow$ En NIST benchmarks. Potential usages motivated from barrier words are also discussed.

Support vector machine is a machine learning method. It takes on the good generalization ability and prediction accuracy. But the parameters of SVM model seriously affect the generalization ability and prediction accuracy of SVM model on the great extent. So an improved particle swarm optimization (PSO) algorithm based on chaotic search is introduced into the SVM model in propose a novel data classification (AMPSVM) method for processing the complex data. The first, the ergodicity, stochastic property, and regularity of chaos is used to chaotically search the current best individual, which randomly replaces the selected individual in the population in order to speed up evolution, improve the searching ability, convergence speed and accuracy. Then the improved PSO algorithm is used to select and optimize the parameters of the SVM (AMPSVM) model in order to improve the learning performance and generalization ability of the SVM model. In order to verify the effectiveness of the AMPSVM method, UCI data is selected in here. The experiment results show that the proposed AMPSVM method takes on the strong generalization ability, best sensitivity and higher classification accuracy.

Almost all scientists benefit from using questionnaire forms in performing statistical analysis. In most cases, these forms consist of mixed-type scales. To analyze such scales is inconvenient because of the measurement differences, and this problem remains unsolved. In many studies, analysis of mixed-type scales is limited based on the score points of the factors. This study proposes an alternative approach to combine mixed-type scale data using linear transformation functions. Using this approach, it is possible to transform mixed data to the same scale, with the main benefit of allowing the analysis of the mixed data. It also makes it possible to interpret among different types of scales. We show that this transformation approach minimizes the loss of information between the original scale structure and the transformed data. To show the usefulness of our approach, we consider Bayesian structural equation modeling (SEM) within the threshold value approach. Application studies demonstrate that our transformation performs well, especially in the presence of non normality. The transformation approach also gains an advantage with respect to timing costs and the simplicity of the models.