Laplacian Score Research Articles

Experimental and numerical investigation of the sensor effect on the acoustic emission during Pencil-lead Break tests on PMMA plates

Pencil leads are broken on PMMA plates at various source-sensor distances to evaluate the influence of the propagation distance and the sensor type on AE signals. The resulting waves are detected using a broadband or a resonant sensor. The ability of five transducers, PKBBI sensor, MICRO80 sensor, MICRO200HF sensor, Nano30 sensor, and WD sensor, to recreate the characteristic forms of plate waves is evaluated. Because of the response spanning between 300 to 400 kHz frequency range, Nano30 and MICRO80 sensors have a bigger magnitude in the S0 mode than in the A0 mode, especially for small sensor-source distances. Their different responses demonstrate why similar test specimens and test settings can provide diverse findings due to the sensor effect, which is significant for the use of AE data in the classification of AE sources. Then, based on the normalization method, we suggest a procedure to acquire equivalent values for the selected descriptors using Laplacian Score and Principle Component Analysis. In order to gain a thorough understanding of the sensor effect through 3D finite element simulation, a comparative analysis is conducted between the perfect contact sensor and the resonant sensor with sensor effect. The sensor effect arises from the convolution of the Fourier Transform of the signal with the sensitivity curve in the frequency domain. By comparing the waveforms in the time and frequency domain, it is useful to determine how the different sensors differ from the AE signals.

Double-Layer Distributed and Integrated Fault Detection Strategy for Non-Gaussian Dynamic Industrial Systems.

Currently, with the increasing scale of industrial systems, multisensor monitoring data exhibit large-scale dynamic Gaussian and non-Gaussian concurrent complex characteristics. However, the traditional principal component analysis method is based on Gaussian distribution and uncorrelated assumptions, which are greatly limited in practice. Therefore, developing a new fault detection method for large-scale Gaussian and non-Gaussian concurrent dynamic systems is one of the urgent challenges to be addressed. To this end, a double-layer distributed and integrated data-driven strategy based on Laplacian score weighting and integrated Bayesian inference is proposed. Specifically, in the first layer of the distributed strategy, we design a Jarque-Bera test module to divide all multisensor monitoring variables into Gaussian and non-Gaussian blocks, successfully solving the problem of different data distributions. In the second layer of the distributed strategy, we design a dynamic augmentation module to solve dynamic problems, a K-means clustering module to mine local similarity information of variables, and a Laplace scoring module to quantitatively evaluate the structural retention ability of variables. Therefore, this double-layer distributed strategy can simultaneously combine the different distribution characteristics, dynamism, local similarity, and importance of variables, comprehensively mining the local information of the multisensor data. In addition, we develop an integrated Bayesian inference strategy based on detection performance weighting, which can emphasize the differential contribution of local models. Finally, the fault detection results for the Tennessee Eastman production system and a diesel engine working system validate the superiority of the proposed method.

Damage characterisation of GFRP composites based on clustering acoustic emission events utilizing single-failure-cause tests as reference

A new method to identify causes of fracture in composites based on acoustic emission (AE) and clusterization of AE data based on reference datasets is presented within the manuscript. Acoustic Emission (AE) is a widely used non-destructive method for fracture analysis, but data due to their multidimensionality are not easy to analyze especially if the acoustic events appear simultaneously and have similar parameters even if they are an effect of different failure mechanisms. In this research, we utilize an unsupervised learning algorithm besides the simplest K-means, through fuzzy c-means to Gaussian Mixture Model (GMM) and spectral clustering to investigate the dataset obtained from the three-point bending test manufactured by us composite. The analysis is preceded by data curation, feature determination (Laplacian score) and the best number of cluster investigations (DB index, Caliński-Harabasz score, and Silhouette method) To enable interpretation of the clustering we run an additional three groups of tests covering fibre breakage (two methods), resin fracture (in tension and in compression) and delamination (DCB test) creating reference datasets. These datasets were statistically analyzed and kernel density estimators were generated for each AE feature as well as amplitude-frequency characteristics. Clusters obtained for the main dataset were then assigned to particular causes of failure by comparing them with the reference dataset. It was found that clusters generated using spectral clustering were the most realistic ones, as it was possible to assign the cause of failure to them.

Clustering and Interpretation of time-series trajectories of chronic pain using evidential c-means

The most well-known unsupervised classification algorithms allow for the identification of hard or probabilistic partitions. However, when working with complex datasets such as those found in the healthcare domain, it is important to note that these partitions may have limitations, particularly when considering the uncertainty associated with medical data. Indeed, these algorithms do not account for modeling outliers, imprecise, or uncertain observations. In this study, we focused on analyzing time series of barometers attributes related to pain intensity in individuals with chronic pain. Our goal was to identify different typologies of care trajectories, highlighting distinct trajectories of chronic pain through clustering techniques. We propose a soft clustering approach based on feature extraction and selection from sequential data, aiming to improve interpretability and enhance the performance of the clustering procedure. Time series feature extraction and selection effectively handles complex and noisy data, improving interpretability and clustering performance. Evidential soft clustering models data uncertainty and imprecision, providing a better representation of nuances and variations in complex, raw data. The first step involves extracting features from the available time series and selecting the most important attributes. For this purpose, we use a time series feature extractor (Tsfresh) and unsupervised feature selection methods, including unsupervised Random Forest, Laplacian Score, and unsupervised Spectral Feature Selection. The second step involves using the evidential c-means (ECM) clustering algorithm on the extracted attributes. The ECM method, based on belief functions, allows for generating a credal partition that has the ability to model various forms of uncertainty. This partition can then be transformed into a hard partition to study individuals based on this uncertainty criterion. The results reveal the existence of two clusters of chronic pain related to discomfort and well-being, exhibiting excellent separability and compactness. Additionally, an uncertain cluster emerges grouping patients with intermediate characteristics. The interpretability of the determined partitions through descriptive analysis, statistical tests, and repeated measures multinomial regression on clinical and demographic data allowed us to determine the profile of patients in the identified trajectories.

Unsupervised Feature Selection to Identify Important ICD-10 and ATC Codes for Machine Learning on a Cohort of Patients With Coronary Heart Disease: Retrospective Study.

The application of machine learning in health care often necessitates the use of hierarchical codes such as the International Classification of Diseases (ICD) and Anatomical Therapeutic Chemical (ATC) systems. These codes classify diseases and medications, respectively, thereby forming extensive data dimensions. Unsupervised feature selection tackles the "curse of dimensionality" and helps to improve the accuracy and performance of supervised learning models by reducing the number of irrelevant or redundant features and avoiding overfitting. Techniques for unsupervised feature selection, such as filter, wrapper, and embedded methods, are implemented to select the most important features with the most intrinsic information. However, they face challenges due to the sheer volume of ICD and ATC codes and the hierarchical structures of these systems. The objective of this study was to compare several unsupervised feature selection methods for ICD and ATC code databases of patients with coronary artery disease in different aspects of performance and complexity and select the best set of features representing these patients. We compared several unsupervised feature selection methods for 2 ICD and 1 ATC code databases of 51,506 patients with coronary artery disease in Alberta, Canada. Specifically, we used the Laplacian score, unsupervised feature selection for multicluster data, autoencoder-inspired unsupervised feature selection, principal feature analysis, and concrete autoencoders with and without ICD or ATC tree weight adjustment to select the 100 best features from over 9000 ICD and 2000 ATC codes. We assessed the selected features based on their ability to reconstruct the initial feature space and predict 90-day mortality following discharge. We also compared the complexity of the selected features by mean code level in the ICD or ATC tree and the interpretability of the features in the mortality prediction task using Shapley analysis. In feature space reconstruction and mortality prediction, the concrete autoencoder-based methods outperformed other techniques. Particularly, a weight-adjusted concrete autoencoder variant demonstrated improved reconstruction accuracy and significant predictive performance enhancement, confirmed by DeLong and McNemar tests (P<.05). Concrete autoencoders preferred more general codes, and they consistently reconstructed all features accurately. Additionally, features selected by weight-adjusted concrete autoencoders yielded higher Shapley values in mortality prediction than most alternatives. This study scrutinized 5 feature selection methods in ICD and ATC code data sets in an unsupervised context. Our findings underscore the superiority of the concrete autoencoder method in selecting salient features that represent the entire data set, offering a potential asset for subsequent machine learning research. We also present a novel weight adjustment approach for the concrete autoencoders specifically tailored for ICD and ATC code data sets to enhance the generalizability and interpretability of the selected features.

Semi-supervised filter feature selection based on natural Laplacian score and maximal information coefficient

Semi-supervised filter feature selection based on natural Laplacian score and maximal information coefficient

Predicting performance of students by optimizing tree components of random forest using genetic algorithm

Prediction of student academic performance is still a problem because of the limitations of the existing methods specifically low generalizability and lack of interpretability. This study suggests a new approach that deals with the current problems and provides more reliable predictions. The proposed approach combines the information gain (IG) and Laplacian score (LS) for feature selection. In this feature selection scheme, combination of IG and LS is used for ranking features and then, Sequential Forward Selection mechanism is used for determining the most relevant indicators. Also, combination of random forest algorithm with a genetic algorithm for is introduced for multi-class classification. This approach strives to attain more accuracy and reliability than current techniques. The case study shows the proposed strategy can predict performance of students with average accuracy of 93.11 % which shows a minimum improvement of 2.25 % compared to the baseline methods. The findings were further confirmed by the analysis of different evaluation metrics (Accuracy, Precision, Recall, F-Measure) to prove the efficiency of the proposed mechanism.

Motor online novelty detection scheme based on one-class hyperdisk

Online novelty detection is of great importance in the series production of motors. This study developed an online novelty detection scheme for motors based on a one-class hyperdisk (OCHD) model. In the OCHD approach, the decision boundary is estimated using a hyperdisk (HD), which is derived from the training sample set. The HD model addresses the underestimation issue commonly associated with convex-hull-based methods by providing a more accurate estimation of the class region. Furthermore, an optimal separating hyperplane is constructed at the nearest point on the HD by solving a quadratically constrained quadratic program problem. Statistical features refined by the Laplacian score are employed in the proposed novelty detection scheme. This study introduces an online novelty detection scheme for assessing motor quality in actual series production. The test results from the offline experiment demonstrate the superiority of the OCHD method. Datasets collected at the end of the production line were evaluated using the proposed novelty detection scheme. The inspection results for motor components confirm that the proposed method effectively identifies faulty motors during the series production process.

LSFSR: Local label correlation-based sparse multilabel feature selection with feature redundancy

In recent studies, existing multilabel feature selection models have focused on either considering the relationship between labels or the redundancy between features. Furthermore, they only use simple sparsity constraints to process high-dimensional data without the intrinsic relationships between features and labels. These issues can have a great impact on the classification effectiveness of feature selection. To address these limitations, this article describes a new local label correlation-based sparse multilabel feature selection approach with feature redundancy. First, a new loss function is established among the matrices of samples, label coefficients, and labels. Then, the Frobenius norm is imposed to investigate the potential relationships between features and labels. The weight matrix is sparsified by the l2,1 norm to ensure that the new loss function has high interpretability. Second, a manifold constraint is employed to capture the local geometric structure between labels and to delve deeper into the latent information among the local labels. Then manifold constraints and Laplacian scores are combined for embedding feature selection to guide the exploration of hidden latent label. Finally, by considering the differences between the feature scores and the redundancy between the samples, feature redundancy is analyzed via the modified cosine similarity, and a candidate feature subset with low redundancy is generated. The l2 norm is used to select features with low redundancy while preserving sparsity, and a novel objective function is developed to optimize this solution. Thus, a sparse feature selection algorithm via local label correlation and feature redundancy is designed, and has demonstrated remarkable classification effectiveness in comparative experiments conducted on 21 multilabel datasets.

DiGAN Breakthrough: Advancing diabetic data analysis with innovative GAN-based imbalance correction techniques

In the rapidly evolving field of medical diagnostics, the challenge of imbalanced datasets, particularly in diabetes classification, calls for innovative solutions. The study introduces DiGAN, a groundbreaking approach that leverages the power of Generative Adversarial Networks (GAN) to revolutionize diabetes data analysis. Marking a significant departure from traditional methods, DiGAN applies GANs, typically seen in image processing, to the realm of diabetes data. This novel application is complemented by integrating the unsupervised Laplacian Score for sophisticated feature selection. The pioneering approach not only surpasses the limitations of existing techniques but also sets a new benchmark in classification accuracy with a 90% weighted F1-score, achieving a remarkable improvement of over 20% compared to conventional methods. Additionally, DiGAN demonstrates superior performance over popular SMOTE-based methods in handling extremely imbalanced datasets. This research, focusing on the integrated use of Laplacian Score, GAN, and Random Forest, stands at the forefront of diabetic classification, offering a uniquely effective and innovative solution to the long-standing data imbalance issue in medical diagnostics.

DFS-WR: A novel dual feature selection and weighting representation framework for classification

Classification methods relying on multidimensional features have been widely applied in commerce, healthcare, and transportation. Nevertheless, haphazardly selecting inappropriate features may not only hinder the improvement of classification performance but also disrupt the convergence of classifier parameters, leading to prolonged classifier runtime and an increased storage burden. Therefore, this paper proposed a novel framework (dubbed as DFS-WR) to perform dual selection and weighted representation of multidimensional features. Firstly, DFS-WR employs Laplacian scores to conduct a de-redundant operation as the first feature selection. Subsequently, DFS-WR utilizes a correlation coefficient matrix and redundant sorting to eliminate duplicate deployment of similar features in classification through the second selection. Finally, for hierarchical expression, DFS-WR assigns weights by virtue of information gain (IG), thereby emphasizing the significance of dominant features. The performance of DFS-WR was further evaluated across four aspects: classification ability, runtime performance, storage occupancy, and portability and universality, using five public datasets and eleven widely adopted classifiers. Additionally, this paper considered the proper configuration of crucial parameters within DFS-WR and compared it with other related works. The results indicated that the dual selection strategy for eliminating redundancy and similarities among features could improve the performance of classifiers, and the weighted process based on IG outperformed unweighted and ReliefF-based weighted methods. By employing DFS-WR to multidimensional features, the classifier’s runtime and data storage capacity were effectively reduced. In addition, it was proved that the deployment of DFS-WR generally had no limitations on datasets and classifiers, underscoring its good portability and universality in practical applications.

S3LR: Novel feature selection approach for Microarray-Based breast cancer recurrence prediction

Enhancing the accuracy of breast cancer recurrence prediction is crucial, mainly when dealing with genomics data, which presents challenges such as high dimensionality, noise, non-linearity, and limited sample sizes. This paper introduces Semi-Supervised Survival Laplacian Regression (S3LR), a novel feature selection algorithm designed to improve breast cancer recurrence prediction by effectively handling censored, event, and unlabeled data. S3LR modifies the Laplacian Score (LS) by incorporating a distance matrix to calculate the weight matrix, and it integrates heuristic and metaheuristic optimization algorithms to optimize the weighted matrix. These enhancements refine feature selection and overall performance. In our evaluations using three datasets and comparisons with state-of-the-art techniques, S3LR combined with Particle Swarm Optimization (PSO) demonstrates significant improvements in C-index and mean absolute error (MAE). Average C-index values reach 68.80 %, 59.49 %, and 67.66 %, with average MAE values of 15.98, 7.87, and 8.65 months, respectively. These results showcase S3LR's effectiveness in predicting recurrence, even with censored data, for more precise and reliable outcomes. Furthermore, the framework's versatility extends beyond breast cancer and can readily be applied to address other survival and recurrence problems.

Acoustic emission with machine learning in fracture of composites: preliminary study

In this paper, preliminary studies on the failure analysis of hybrid composite materials utilizing acoustic emission and machine learning are presented. The main purpose of this study was to analyze the possibilities of using machine learning techniques as a way to better cluster the data obtained from acoustic emission. In this paper, we focus on data preparation, feature extraction (Laplacian score), determination of cluster number (Caliński–Harabasz, Silhouette, and Davies–Bouldin), and testing three clustering techniques, namely K-means, fuzzy C-means, and spectral clustering. The dataset was obtained by testing fiber metal laminates—composites consisting of metal and composite layers. Two experimental tests were realized on pre-cracked rectangular specimens—one with loading in mode I and one with loading in mode II (DCB—double cantilever beam and ENF—end-notch flexural test). Elastic waves were recorded during these tests via an acoustic emission system. Preliminary studies show that the proposed method can be used successfully to cluster data obtained in this way. The obtained dataset was split into 3 clusters (for the ENF test) and 5 clusters (DCB test). In the next stages of the research campaign, based on the presented results, we intend to change the approach to semi-supervised by running additional single-cause damage tests to enhance the achieved results and enable easier damage recognition.

Patlak-Ki derived from ultra-high sensitivity dynamic total body [18F]FDG PET/CT correlates with the response to induction immuno-chemotherapy in locally advanced non-small cell lung cancer patients.

This study aimed to investigate the predictive value of metabolic features in response to induction immuno-chemotherapy in patients with locally advanced non-small cell cancer (LA-NSCLC), using ultra-high sensitivity dynamic total body [18F]FDG PET/CT. The study analyzed LA-NSCLC patients who received two cycles of induction immuno-chemotherapy and underwent a 60-min dynamic total body [18F]FDG PET/CT scan before treatment. The primary tumors (PTs) were manually delineated, and their metabolic features, including the Patlak-Ki, Patlak-Intercept, maximum SUV (SUVmax), metabolic tumor volume (MTV) and total lesion glycolysis (TLG) were evaluated. The overall response rate (ORR) to induction immuno-chemotherapy was evaluated according to RECIST 1.1 criteria. The Patlak-Ki of PTs was calculated from the 20-60min frames using the Patlak graphical analysis. The best feature was selected using Laplacian feature importance scores, and an unsupervised K-Means method was applied to cluster patients. ROC curve was used to examine the effect of selected metabolic feature in predicting tumor response to treatment. The targeted next generation sequencing on 1021 genes was conducted. The expressions of CD68, CD86, CD163, CD206, CD33, CD34, Ki67 and VEGFA were assayed through immunohistochemistry. The independent samples t test and the Mann-Whitney U test were applied in the intergroup comparison. Statistical significance was considered at P < 0.05. Thirty-seven LA-NSCLC patients were analyzed between September 2020 and November 2021. All patients received two cycles of induction chemotherapy combined with Nivolumab/ Camrelizumab. The Laplacian scores showed that the Patlak-Ki of PTs had the highest importance for patient clustering, and the unsupervised K-Means derived decision boundary of Patlak-Ki was 2.779ml/min/100g. Patients were categorized into two groups based on their Patlak-Ki values: high FDG Patlak-Ki (H-FDG-Ki, Patlak-Ki > 2.779ml/min/100g) group (n = 23) and low FDG Patlak-Ki (L-FDG-Ki, Patlak-Ki ≤ 2.779ml/min/100g) group (n = 14). The ORR to induction immuno-chemotherapy was 67.6% (25/37) in the whole cohort, with 87% (20/23) in H-FDG-Ki group and 35.7% (5/14) in L-FDG-Ki group (P = 0.001). The sensitivity and specificity of Patlak-Ki in predicting the treatment response were 80% and 75%, respectively [AUC = 0.775 (95%CI 0.605-0.945)]. The expression of CD3+/CD8+ T cells and CD86+/CD163+/CD206+ macrophages were higher in the H-FDG-Ki group, while Ki67, CD33+ myeloid cells, CD34+ micro-vessel density (MVD) and tumor mutation burden (TMB) were comparable between the two groups. The total body [18F]FDG PET/CT scanner performed a dynamic acquisition of the entire body and clustered LA-NSCLC patients into H-FDG-Ki and L-FDG-Ki groups based on the Patlak-Ki. Patients with H-FDG-Ki demonstrated better response to induction immuno-chemotherapy and higher levels of immune cell infiltration in the PTs compared to those with L-FDG-Ki. Further studies with a larger patient cohort are required to validate these findings.

Vibration-based looseness identification of bolted structures via quasi-analytic wavelet packet and optimized large margin distribution machine

Bolted joints are the most widely utilized connection types in industries, and therein looseness identification of bolted structures is of great significance to guarantee structural reliability. In this article, a comprehensive study of bolt looseness identification under random excitation is presented. To fulfill this task, this research focuses on three prominent difficulties, including nonstationary signal processing, subtle feature extraction, and robust state classification. First, a novel filter bank structure of quasi-analytic dual-tree complex wavelet packet transform is constructed to analyze the measured vibration response signals, for purpose of capturing subtle feature information. Then, multiple features are extracted from subband signals to capture the variations of dynamic characteristics, and sensitive features are selected by Laplacian score to construct the low-dimensional feature set. Subsequently, a novel classifier with better generalization performance, named large margin distribution machine, is optimized with the wavelet kernel function and the whale optimization algorithm, in order to handle the intrinsic uncertainty related to the looseness states of bolted structures. After feeding the low-dimensional feature set, the proposed classifier is trained to identify looseness states of bolted structures. Finally, experiments of a two-bolt lapped beam under random excitation are conducted to verify the effectiveness of the proposed method, and two typical loading conditions (paired-bolt looseness and single-bolt looseness) are considered. Besides, the superiority of the proposed method is demonstrated by comparing with other analogical methods. This research can provide a promising implement in practical applications of bolt looseness identification under random excitation.

Feature selection for binary classification based on class labeling, SOM, and hierarchical clustering

Feature selection plays an important role in algorithms for processing high-dimensional data. Traditional pattern classification and information theory methods are widely applied to feature selection methods. However, traditional pattern classification methods such as Fisher Score, Laplacian Score, and relief use class labels inadequately. Previous information theory based feature selection methods such as MIFS ignore the intra-class to tight inter-class to sparse property of the samples. To address these problems, a feature selection algorithm for the binary classification problem is proposed, which is based on class label transformation using self-organizing mapping neural network (SOM) and cohesive hierarchical clustering. The algorithm first converts class labels without numerical meaning into numerical values that can participate in operations and retain classification information through class label mapping, and constitutes a two-dimensional vector from it and the attribute values to be judged. Then, these two-dimensional vectors are clustered by using SOM neural network and hierarchical clustering. Finally, evaluation function value is calculated, that is closely related to intra-cluster to tightness, inter-cluster separation, and division accuracy after clustering, and is used to evaluate the ability of alternative attributes to distinguish between classes. It is experimentally verified that the algorithm is robust and can effectively screen attributes with strong classification ability and improve the prediction performance of the classifier.

Value of Patlak-Ki from ultra-high sensitivity dynamic total body [18F]FDG PET/CT for evaluation of treatment response to induction immuno-chemotherapy in locally advanced non-small cell lung cancer (LA-NSCLC) patients.

e20508 Background: This study aimed to explore the value of metabolic features in predicting the response to induction immuno-chemotherapy in locally advanced NSCLC, using dynamic total body [18F]FDG PET/CT. Methods: The LA-NSCLC patients who received two cycles of induction immuno-chemotherapy were analyzed in the study. The 60-minute dynamic total body [18F]FDG PET/CT scan was administered before treatment. The primary tumors (PTs) were manually delineated. The metabolic features including the Patlak-Ki, Patlak-Intercept, the SUVmax, metabolic tumor volume (MTV) and total lesion glycolysis (TLG) of PTs were evaluated. Using the Patlak graphical analysis, the Patlak-Ki of PTs was calculated from the 20-60 minutes frames. The Laplacian feature importance scores was used to select the best feature and an unsupervised K-Means method was applied to cluster patients. ROC curve was used to examine the effect of selected metabolic feature in predicting tumor response to treatment. The targeted next generation sequencing on 1021 genes was conducted. The expressions of CD68, CD86, CD163, CD206, CD33, CD34, Ki67 and VEGFA were assayed by immunohistochemistry. The independent samples t test and the Mann-Whitney U test were applied in the intergroup comparison. Results: Thirty-seven LA-NSCLC patients were analyzed between September 2020 and November 2021. All patients received two cycles of induction chemotherapy combined with Nivolumab/ Camrelizumab. The Laplacian scores showed that the Patlak-Ki of PTs had the highest importance for patient clustering, and the unsupervised K-Means derived decision boundary of Patlak-Ki was 2.779 ml/min/100g. Then Patients were divided into a high FDG Patlak-Ki (H-FDG-Ki, Patlak-Ki &gt; 2.779 ml/min/100g) group (n = 23) and a low FDG Patlak-Ki (L-FDG-Ki, Patlak-Ki ≤ 2.779 ml/min/100g) group (n = 14). The ORR to induction immuno-chemotherapy was 67.6% (25/37) in the whole cohort, with 87% (20/23) in H-FDG-Ki group and 35.7% (5/14) in the L-FDG-Ki group (P = 0.001). The sensitivity and specificity of Patlak-Ki in predicting the treatment response were 80% and 75%, respectively [AUC = 0.775 (95%CI 0.605-0.945)]. The expression of CD3+/CD8+ T cells and CD86+/CD163+/CD206+ macrophages were higher in the H-FDG-Ki group, while Ki67, CD33+ myeloid cells, CD34+ micro-vessel density (MVD) and tumor mutation burden (TMB) were comparable between the two groups. Conclusions: The total body [18F]FDG PET/CT scanner performed a dynamic acquisition of the entire body and clustered LA-NSCLC patients into H-FDG-Ki and L-FDG-Ki groups based on the Patlak-Ki. H-FDG-Ki patients had better response to induction immuno-chemotherapy and higher immune cells infiltrations in the PTs than L-FDG-Ki patients. Further studies in a large patient cohort are warranted.

Investigating Feature Selection Techniques to Enhance the Performance of EEG-Based Motor Imagery Tasks Classification

Analyzing electroencephalography (EEG) signals with machine learning approaches has become an attractive research domain for linking the brain to the outside world to establish communication in the name of the Brain-Computer Interface (BCI). Many researchers have been working on developing successful motor imagery (MI)-based BCI systems. However, they still face challenges in producing better performance with them because of the irrelevant features and high computational complexity. Selecting discriminative and relevant features to overcome the existing issues is crucial. In our proposed work, different feature selection algorithms have been studied to reduce the dimension of multiband feature space to improve MI task classification performance. In the procedure, we first decomposed the MI-based EEG signal into four sets of the narrowband signal. Then a common spatial pattern (CSP) approach was employed for each narrowband to extract and combine effective features, producing a high-dimensional feature vector. Three feature selection approaches, named correlation-based feature selection (CFS), minimum redundancy and maximum relevance (mRMR), and multi-subspace randomization and collaboration-based unsupervised feature selection (SRCFS), were used in this study to select the relevant and effective features for improving classification accuracy. Among them, the SRCFS feature selection approach demonstrated outstanding performance for MI classification compared to other schemes. The SRCFS is based on the multiple k-nearest neighbour graphs method for learning feature weight based on the Laplacian score and then discarding the irrelevant features based on the weight value, reducing the feature dimension. Finally, the selected features are fed into the support vector machines (SVM), linear discriminative analysis (LDA), and multi-layer perceptron (MLP) for classification. The proposed model is evaluated with two benchmark datasets, namely BCI Competition III dataset IVA and dataset IIIB, which are publicly available and mainly used to recognize the MI tasks. The LDA classifier with the SRCFS feature selection algorithm exhibits better performance. It proves the superiority of our proposed study compared to the other state-of-the-art BCI-based MI task classification systems.

Risk state evaluation model for China's food import using G1-LS and variable weight SPA based on bottom-line thinking

PurposeTo maintain the bottom line of food import risk in China, this paper proposes a novel risk state evaluation model based on bottom-line thinking after analyzing the decision-making ideas embedded in the bottom-line thinking method.Design/methodology/approachFirst, the order relation analysis method (G1 method) and Laplacian score (LS) are applied to calculate the constant weights of indexes. Then, the worst-case scenario of food import risk can be estimated to strive for the best result, so the penalty state variable weight function is introduced to obtain variable weights of indexes. Finally, the study measures the risk state of China's food import from the overall situation using the set pair analysis (SPA) method and identifies the key factors affecting food import risk.FindingsThe risk states of food supply in eight countries are in the state of average potential and partial back potential as a whole. The results indicate that China's food import risks are at medium and upper-medium risk levels in most years, fluctuating slightly from 2010 to 2020. In addition, some factors are diagnosed as the primary control objects for holding the bottom line of food import risk in China, including food output level, food export capacity, bilateral relationship and political risk.Originality/valueThis paper proposes a novel risk state evaluation model following bottom-line thinking for food import risk in China. Besides, SPA is first applied to the risk evaluation of food import, expanding the application field of the SPA method.

Parkinson’s Disease Diagnosis Using Laplacian Score, Gaussian Process Regression and Self-Organizing Maps

Parkinson's disease (PD) is a complex degenerative brain disease that affects nerve cells in the brain responsible for body movement. Machine learning is widely used to track the progression of PD in its early stages by predicting unified Parkinson's disease rating scale (UPDRS) scores. In this paper, we aim to develop a new method for PD diagnosis with the aid of supervised and unsupervised learning techniques. Our method is developed using the Laplacian score, Gaussian process regression (GPR) and self-organizing maps (SOM). SOM is used to segment the data to handle large PD datasets. The models are then constructed using GPR for the prediction of the UPDRS scores. To select the important features in the PD dataset, we use the Laplacian score in the method. We evaluate the developed approach on a PD dataset including a set of speech signals. The method was evaluated through root-mean-square error (RMSE) and adjusted R-squared (adjusted R²). Our findings reveal that the proposed method is efficient in the prediction of UPDRS scores through a set of speech signals (dysphonia measures). The method evaluation showed that SOM combined with the Laplacian score and Gaussian process regression with the exponential kernel provides the best results for R-squared (Motor-UPDRS = 0.9489; Total-UPDRS = 0.9516) and RMSE (Motor-UPDRS = 0.5144; Total-UPDRS = 0.5105) in predicting UPDRS compared with the other kernels in Gaussian process regression.