Random Characteristics Research Articles

Optimizing Random Forest for Predicting Thoracic Surgery Success in Lung Cancer Using Recursive Feature Elimination and GridSearchCV

Abstract. Lung cancer is one of the deadliest forms of cancer, claiming numerous lives annually. Thoracic surgery is a strategy to manage lung cancer patients; however, it poses high risks, including potential nerve damage and fatal complications leading to mortality. Predicting the success rate of thoracic surgery for lung cancer patients can be accomplished using data mining techniques based on classification principles. Medical data mining involves employing mathematical, statistical, and computational methods. In this study, the prediction of thoracic surgery success employs the random forest algorithm with recursive feature elimination for feature selection. The feature selection process yields the top 8 features. The 8 best features include 'DGN', 'PRE4', 'PRE5', 'PRE6', 'PRE10', 'PRE14', 'PRE30', and 'AGE'. Hyperparameter using GridSearchCV is then applied to enhance classification accuracy. The results of this method implementation demonstrate a predictive accuracy of 91.41%. Purpose: The study aims to develop and evaluate a Random Forest model with a Recursive Feature Elimination feature selection and applies hyperparameter GridSearchCV for predicting thoracic surgery success rate. Methods: This study uses the thoracic surgery dataset and applies various data preprocessing techniques. The dataset is then used for classification using the Random Forest algorithm and applies the Recursive Feature Elimination feature selection to obtain the best features. GridSearchCV is used in this study for hyperparameter. Result: The accuracy using the Random Forest algorithm and Recursive Feature Elimination feature selection with hyperparameters tuning GridSearchCV resulted in an accuracy of 91,41%. The accuracy was obtained from the following parameters values: bootstrap set to false, criterion set to gini, n_estimator equal to 100, max_depth set to none, min_samples_split equal to 4, min_samples_leaf equal to 1, max_features set to auto, n_jobs set to -1, and verbose set to 2 with 10-fold cross validation. Novelty: This study comparison and analysis of various dataset preprocessing methods and different model configurations are conducted to find the best model for predicting the success rate of thoracic surgery. The study also employs feature selection to choose the best feature to be used in classification process, as well as hyperparameter tuning to achieve optimal accuracy and discover the optimal values for these hyperparameters.

Random fourier features for asymmetric kernels

Random fourier features for asymmetric kernels

SELFNet: Denoising Shear Wave Elastography Using Spatial-temporal Fourier Feature Networks

ObjectiveUltrasound-based shear wave elastography offers estimation of tissue stiffness through analysis of the propagation of a shear wave induced by a stimulus. Displacement or velocity fields during the process can contain noise as a result of the limited number of acquisitions. With advances in physics-informed deep learning, neural networks can approximate a physics field by minimizing the residuals of governing physics equations. MethodsIn this research, we introduce a shear wave elastography Fourier feature network (SELFNet) using spatial-temporal random Fourier features within a physics-informed neural network framework to estimate and denoise particle displacement signals. The network uses a sparse mapping to increase robustness and incorporates the governing equations for regularization while simultaneously learning the mapping of the shear modulus. The method was evaluated in datasets from tissue-mimicking phantom of lesions and ex vivo tissue. ResultsThe findings indicate that SELFNet is capable of smoothing out the noise in phantom lesions with different stiffness and sizes, outperforming a reference Gaussian filtering method by 17% in relative ℓ2 error, 45% in reconstruction root-mean-square error. Furthermore, the ablation study suggested that SELFNet can prevent over-fitting through the Fourier feature mapping module. An ex vivo study confirmed its applicability to different types of tissue. ConclusionThe implementation of SELFNet shows promise for shear wave elastography with limited acquisitions. In this context, subject to successful translation, it has the potential to be extended to clinical applications, such as the diagnosis of cancer or liver disease.

Training for Making Wordwall Learning Media for Teachers in SMK PGRI Kuwu, Grobogan Regency

It doesn't feel like the Covid-19 pandemic that has lasted for 2 years has changed the learning model that we have known so far, namely face-to-face, although the blended learning model that combines conventional models with online learning has been introduced as an evolutionary model, but with the pandemic forcing it to happen. for teachers to immediately adapt and implement it in the schools where they teach as a need that must be met considering the demands of the community who want educators and educational institutions to be able to provide quality education in the midst of this crisis. As an affected educational institution, SMK PGRI Kuwu strives to continue to provide quality learning by applying the blended learning model (Purnomo et al., 2016). After communicating with the service team from PGRI Semarang University, consensus was obtained that the problems faced by partners could more or less be solved by implementing information technology in learning, one of which was the introduction of interactive learning media Wordwall with additional Gamification learning models (Putri, 2020). The application and learning model itself uses a Cloud system or Cloud Computing where between teachers and beneficiaries of learning or students can use information technology devices that vary depending on availability, and do not require device specifications with special and updated technology, the most important thing is the availability of internet network connectivity. Sari Yarza, 2021). Wordwall specifically can be used to create learning media such as quizzes, matchmaking, pairing, anagrams, word randomization, word search, word grouping, and several other additional features such as questions and answer results that can be printed on paper making it easier for teachers and students to document results. work as a task (Hasram, 2021). Through this introduction activity or PKM (Community Partnership Program), it is hoped that teachers and lecturers at SMK PGRI Kuwu can implement it in their learning classes, and are expected to be able to overcome the learning gap that has occurred as a result of the Covid-19 pandemic. The results of the ongoing activities in the form of mentoring and evaluation training, carried out for 3 days which were carried out in a blended manner (offline and online) with the results and responses of the activity participants showing positive indications as indicated by the reapitulation of the questionnaire results of participants' responses to this training activity which showed an average result of 3, 85 on a scale of 4 which indicates a good response or a positive response to the implementation of the training activities.

Development and Validation of a Two-step Model to Predict Outcomes After Endovascular Treatment for Patients With Acute Ischemic Stroke.

Physicians and patients are eager to know likely functional outcomes at different stages of treatment after acute ischemic stroke (AIS). The aim of this study was to develop and validate a 2-step model to assess prognosis at different time points (pre- and posttreatment) in patients with AIS having endovascular thrombectomy (EVT). The prediction model was developed using a prospective nationwide Chinese registry (ANGEL-ACT). A total of 1676 patients with AIS who underwent EVT were enrolled into the study and randomly divided into development (n=1351, 80%) and validation (n=325, 20%) cohorts. Multivariate logistic regression, least absolute shrinkage and selection operator regression, and the random forest recursive feature elimination algorithm were used to select predictors of 90-day functional independence. We constructed the model via discrimination, calibration, decision curve analysis, and feature importance. The incidence of 90-day functional independence was 46.3% and 40.6% in the development and validation cohorts, respectively. The area under the curve (AUC) for model 1 which included 5 pretreatment predictors (age, admission National Institutes for Health Stroke Scale score, admission glucose level, admission systolic blood pressure, and Alberta Stroke Program Early Computed Tomography score) was 0.699 (95% confidence interval [CI], 0.668-0.730) in the development cohort and 0.658 (95% CI, 0.592-0.723) in the validation cohort. Two treatment-related predictors (time from stroke onset to puncture and successful reperfusion) were added to model 2 which had an AUC of 0.719 (95% CI, 0.688-0.749) and 0.650 (95% CI, 0.585-0.716) in the development cohort and validation cohorts, respectively. The 2-step prediction model could be useful for predicting the functional independence in patients with AIS 90-days after EVT.

Urban Drainage Network Structure Optimization Using Emperor Penguin Optimization Algorithm

Urban drainage systems are an essential component of urban infrastructure that plays a critical role in managing stormwater and preventing flooding in urban areas. With the changing climate and urbanization, the challenges faced by urban drainage systems are becoming increasingly complex. Additionally, aging infrastructure further exacerbates the problem, creating anurban sewage line that must be made more resilient. Redundancy is just a fundamental characteristic of such a robust urban drainage network. Redundancy in urban drainage systems can help to ensure that the system continues to function during extreme weather events or emergencies, reducing the likelihood of flooding and damage. However, the exact locations where redundancy should be increased and its contribution to resilience are not well understood. In recent years, several studies have focused on developing frameworks for optimising urban drainage structures which account pipeline redundancy.One similar research presented a paradigm for constructing the ideal network layout for urban drainage infrastructure, which considers pipeline redundancy under consideration. The original architecture and structure of the urban drainage network was developed using emperor penguin optimizer algorithms and graph theory in the research. Complicated system modelling was done to find extra water pathways or redundancy which might well be implemented to boost resistance. The suggested approach has been utilised to the test region in Dongying City, Shandong Province, China, and its findings revealed even under rainfall above the design specification, the entire overflow capacity of such urban drainage network including pipeline redundancy significantly decreased about 20-30%, compared to the network without pipeline redundancies. The interest in creating optimization algorithms had also increased recently that can be used to design and manage urban infrastructure systems. One such algorithm is the Emperor Penguin Optimization (EPO) algorithm. EPO was a recently developed swarm-based optimization An algorithm which simulates Emperor penguins behaviour in their search for food in Antarctica. The algorithm has shown promising results in solving complex optimization problems in different fields, including engineering, computer science, and management. The EPO algorithm's key features include an emperor search strategy, local search, and randomization, enabling that to efficiently and successfully examine the search process. The algorithm's emperor penguin search strategy enables it to dynamically adjust the search parameters based on the problem's characteristics and progress. The local search feature allows it to escape local optima and explore the search space further. Finally, the randomization feature adds stochasticity to the search process, helping to ensure that the algorithm can avoid getting stuck in a sub-optimal solution. In this article, we aim to explore the potential of EPO as a tool for optimizing Urban drainage solutions which take into account pipeline redundancy. We will start by reviewing the existing Literature upon that optimization in urban drainage facilities, particularly the application of particle swarm optimization, genetic algorithms, and ant colony enhancement. The EPO algorithm will next be described in full including its working principle, key features, and the steps involved in applying it to an optimization problem. Finally, we will present a case study that applies the EPO technique was developed to optimise the network model of such an urban drainage infrastructure taking into account pipeline redundancies, and compare the results with other optimization algorithms. Through this, we aim to demonstrate the potential of EPO as a powerful tool for designing and managing urban infrastructure systems, particularly for enhancing the resilience of urban drainage systems. The study will provide valuable insights into the optimal design of urban drainage technologies which take into account pipeline redundancy, helping policymakers and urban planners make informed decisions about improvingthe adaptability of urban drainage networks. The findings can contribute to the development of sustainable and resilient urban infrastructure systems, which are essential for ensuring the well-being and prosperity of urban residents.

Multi-Feature Extraction and Selection Method to Diagnose Burn Depth from Burn Images

Burn wound depth is a significant determinant of patient treatment. Typically, the evaluation of burn depth relies heavily on the clinical experience of doctors. Even experienced surgeons may not achieve high accuracy and speed in diagnosing burn depth. Thus, intelligent burn depth classification is useful and valuable. Here, an intelligent classification method for burn depth based on machine learning techniques is proposed. In particular, this method involves extracting color, texture, and depth features from images, and sequentially cascading these features. Then, an iterative selection method based on random forest feature importance measure is applied. The selected features are input into the random forest classifier to evaluate this proposed method using the standard burn dataset. This method classifies burn images, achieving an accuracy of 91.76% when classified into two categories and 80.74% when classified into three categories. The comprehensive experimental results indicate that this proposed method is capable of learning effective features from limited data samples and identifying burn depth effectively.

Two-sided matching theory-based second-hand house transaction evaluation and recommendation by the modified PLC-DEMATEL method

To enhance the two-sided matching efficiency in a multi-source heterogeneous environment, this paper takes the randomness and unstructured features of the online comments into consideration, and proposes a new matching mechanism by introducing the complex information representation tool. Firstly, the concept of the probabilistic linguistic normal cloud (PLNC) model is introduced to preserve information cohesion and characteristic distribution. Next, the basic operation laws and corresponding operators are given. Then, an innovative maximum boundary concept skipping the indirect approach is presented to update the similarity degree and distance measures, also the correlation coefficient. Furthermore, for the multi-indicator systems with interactions, the peer experts are invited to evaluate the relationship between indicators, a modified algorithm based on the Decision-Making and Trial Evaluation Laboratory (DEMATEL) method is applied to obtain the subjective weights of indicators. After that, a whole matching process and a correlation coefficient cluster method-based recommendation algorithm are presented. A case study is provided to illustrate the method, wherein a new indicator system is constructed by analyzing the correlation of multiple indicators based on online linguistic evaluations. The random forest model is combined to obtain the objective weights and balance its reliability. Finally, sensitivity analysis and comparative analysis are employed to validate the effectiveness and applicability.

Gaussian Process-Gated Hierarchical Mixtures of Experts.

In this article, we propose novel Gaussian process-gated hierarchical mixtures of experts (GPHMEs). Unlike other mixtures of experts with gating models linear in the input, our model employs gating functions built with Gaussian processes (GPs). These processes are based on random features that are non-linear functions of the inputs. Furthermore, the experts in our model are also constructed with GPs. The optimization of the GPHMEs is performed by variational inference. The proposed GPHMEs have several advantages. They outperform tree-based HME benchmarks that partition the data in the input space, and they achieve good performance with reduced complexity. Another advantage is the interpretability they provide for deep GPs, and more generally, for deep Bayesian neural networks. Our GPHMEs demonstrate excellent performance for large-scale data sets, even with quite modest sizes.

Identification of novel mitophagy-related biomarkers for Kawasaki disease by integrated bioinformatics and machine-learning algorithms.

Kawasaki disease (KD) is a systemic vasculitis primarily affecting the coronary arteries in children. Despite growing attention to its symptoms and pathogenesis, the exact mechanisms of KD remain unclear. Mitophagy plays a critical role in inflammation regulation, however, its significance in KD has only been minimally explored. This study sought to identify crucial mitophagy-related biomarkers and their mechanisms in KD, focusing on their association with immune cells in peripheral blood. This research used four datasets from the Gene Expression Omnibus (GEO) database that were categorized as the merged and validation datasets. Screening for differentially expressed mitophagy-related genes (DE-MRGs) was conducted, followed by Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analyses. A weighted gene co-expression network analysis (WGCNA) identified the hub module, while machine-learning algorithms [random forest-recursive feature elimination (RF-RFE) and support vector machine-recursive feature elimination (SVM-RFE)] pinpointed the hub genes. Receiver operating characteristic (ROC) curves were generated for these genes. Additionally, the CIBERSORT algorithm was used to assess the infiltration of 22 immune cell types to explore their correlations with hub genes. Interactions between transcription factors (TFs), genes, and Gene-microRNAs (miRNAs) of hub genes were mapped using the NetworkAnalyst platform. The expression difference of the hub genes was validated using quantitative reverse transcriptase polymerase chain reaction (qRT-PCR). Initially, 306 DE-MRGs were identified between the KD patients and healthy controls. The enrichment analysis linked these MRGs to autophagy, mitochondrial function, and inflammation. The WGCNA revealed a hub module of 47 KD-associated DE-MRGs. The machine-learning algorithms identified cytoskeleton-associated protein 4 (CKAP4) and serine-arginine protein kinase 1 (SRPK1) as critical hub genes. In the merged dataset, the area under the curve (AUC) values for CKAP4 and SRPK1 were 0.933 [95% confidence interval (CI): 0.901 to 0.964] and 0.936 (95% CI: 0.906 to 0.966), respectively, indicating high diagnostic potential. The validation dataset results corroborated these findings with AUC values of 0.872 (95% CI: 0.741 to 1.000) for CKAP4 and 0.878 (95% CI: 0.750 to 1.000) for SRPK1. The CIBERSORT analysis connected CKAP4 and SRPK1 with specific immune cells, including activated cluster of differentiation 4 (CD4) memory T cells. TFs such as MAZ, SAP30, PHF8, KDM5B, miRNAs like hsa-mir-7-5p play essential roles in regulating these hub genes. The qRT-PCR results confirmed the differential expression of these genes between the KD patients and healthy controls. CKAP4 and SRPK1 emerged as promising diagnostic biomarkers for KD. These genes potentially influence the progression of KD through mitophagy regulation.

Sex differences in association of healthy eating pattern with all-cause mortality and cardiovascular mortality

BackgroundAlthough the Healthy Eating Index (HEI) is widely recommended to reduce the risk of cardiovascular disease and all-cause death, there are significant differences in physiological and nutritional factors between the sexes. The potential impact of sex on adult dietary health is still poorly understood. The study was designed to assess whether the health benefits of diet differed by sex.MethodsIn a prospective study of 39,567 U.S. adults (51.2% female, age 46.8 ± 17.6 years), we examined sex-specific, multivariable-adjusted associations of HEI with all-cause mortality and cardiovascular disease mortality. Restricted cubic splines (RCS), subgroup analysis, propensity score matching (PSM), random forest feature importance, and sensitivity analysis were also used.ResultsDuring 328,403 person-years of follow-up, a total of 4754 all-cause deaths were recorded, including 1481 cardiovascular deaths. Compared to the lowest quartile of HEI, the all-cause mortality rate of females and males in the highest quartile array decreased by 34% (HR 0.66 [95% CI 0.55–0.8]) and 15% (HR 0.85 [95% CI 0.73–0.99]), respectively. The restricted cubic spline showed a linear inverse association between baseline HEI and all-cause mortality and CVD mortality, with similar sex-specific results. Similarly, component scores were sex-specific for mortality risk, with females benefiting more from diet. The benefits of dairy products, vegetables, and sodium scores on the risk of all-cause death were higher in males and females. However, the benefits of vegetable, sodium, and fatty acid scores on the risk of cardiovascular death were different.ConclusionsIn the adult population of the U.S., there are more opportunities for females to reduce the risk of all-cause mortality and cardiovascular mortality from the same dose of healthy dietary intake than males. These findings could reduce the risk of death by motivating the population, especially females, to consume healthy dietary components, especially vegetables and dairy products.

Tracking paddy rice acreage, flooding impacts, and mitigations during El Niño flooding events using Sentinel-1/2 imagery and cloud computing

The frequent occurrence of El Niño events, in the context of climate change, brings heavy precipitation and extreme heat, severely disrupting agricultural production. Previous efforts have focused on monitoring crop planting areas and evaluating affected crops during disasters. Nevertheless, a comprehensive analysis, including crop planting area mapping, crop damage assessment, and mitigation effectiveness throughout the entire course of a disaster, has been seldom addressed. In this study, we built a comprehensive framework to rapidly investigate the areas of early rice, the extent of flooding impacts, and the post-flood mitigations of early rice during the El Niño flooding event in a typical rice production region – Jiangxi Province in 2023. Early rice planting areas were first mapped by integrating 15-day time series gap-filled Sentinel-1/2 datasets using the Google Earth Engine (GEE) platform, based on a random forest classifier built with the 55 optimized training features. Then the flood-affected early rice map was produced by integrating the early rice planting areas and the Sentinel-1 images-based flood map. Finally, the post-flood newly planted rice fields were identified using the random forest algorithm and classification features from the Sentinel-1/2 images composited during four phenology phases of newly planted rice. The results showed the early rice planting area map, the flooding map, and the newly planted early rice map have overall accuracies of over 90 %. The early rice planting areas reached 120 × 104 ha, and an area of 3.60 × 104 ha (3 %) was flooded due to the heavy rain, and 3.43 × 104 ha flooded areas were newly planted, eventually mitigating the flooding impacts on the production of early rice. This study showcases the potential of all the available Sentinel-1/2 data, cloud computing, and well-established mapping algorithms for tracking rice areas, flooding impacts, and mitigations (i.e., after-flooding replanting) during extreme climate events. The established framework is expected to serve as an early warning system for agricultural adaptation to extreme climate events.

A novel deep learning-based intrusion detection system for IoT DDoS security

Intrusion detection systems (IDS) for IoT devices are critical for protecting against a wide range of possible attacks when dealing with Distributed Denial of Service (DDoS) attacks. These attacks have become a primary concern for IoT networks. Intelligent decision-making techniques are required for DDoS attacks, which pose serious threats. The range of devices connected to the IoT ecosystem is growing, and the data traffic they generate is continually changing; the need for models more resistant to new attack types and existing attacks is of research interest. Motivated by this gap, this paper provides an effective IDS powered by deep learning models for IoT networks based on the recently published CICIoT2023 dataset. In this work, we improved the detection and mitigation of potential security threats in IoT networks. To increase performance, we performed preprocessing operations on the dataset, such as random subset selection, feature elimination, duplication removal, and normalization. A two-level IDS using deep-learning models containing binary and multiclass classifiers has been designed to identify DDoS attacks in IoT networks. The effectiveness of several deep-learning models in real-time and detection performance has been evaluated. We trained fully connected, convolutional, and LSTM-based deep learning models for detecting DDoS attacks and sub-classes. According to the results on a partially balanced sub-dataset, two staged models performed better than baseline models such as DNN (Deep Neural Networks), CNN (Convolutional Neural Networks), LSTM (Long Short Term Memory), RNN (Recurrent Neural Network).

Abnormal low-magnitude seismicity preceding large-magnitude earthquakes

Unraveling the precursory signals of potentially destructive earthquakes is crucial to understand the Earth’s crust dynamics and to provide reliable seismic warnings. Earthquake precursors are ambiguous, but recent experimental studies suggest that robust warning signs may precede large seismic events in the short (day-to-months) term. Here, we show that the M6.4-M7.1 2019 Ridgecrest sequence (California) and the M7.1 2018 Anchorage earthquake (Alaska) were preceded by up to ~3 months of tectonic unrest on regional scales, as evidenced by abnormal low-magnitude seismicity spreading over the ~15-25% of Southern California and Southcentral Alaska. This precursory unrest has been discovered with an algorithm that integrates an innovative random forest machine learning approach and statistical features built from earthquake catalogs. Supported by a novel suite of finite element solid mechanics models, we propose that precursory, abnormal, low-magnitude seismicity arises if the pore fluid pressure within large fault segments escalates significantly as they approach failure, which leads to major uneven changes in the regional stress field. Our findings and method may open up new perspectives for surveillance agencies to anticipate when a region approaches an earthquake of great magnitude weeks to months before it occurs.

Coal allocation optimization based on a hybrid residual prediction model with an improved genetic algorithm

The objective of the coal blending optimization problem is to find an optimal coal blending in the feasible domain such that the blended coal meets the quality requirements at the end of the coking process and the cost of coal blending is minimized. This paper proposes a hybrid residual prediction model and an improved genetic algorithm to solve this problem and predict coke quality. For this purpose, a hybrid residual prediction model is used to predict coke quality. The model first uses a random forest feature extraction method to reduce the dimensionality of the data, and then trains several prediction models such as eXtreme Gradient Boosting (XGBoost), Adaboost and Light Gradient-Boosting Machine (lightGBM) for different coke indicators an improved genetic algorithm based on the adaptive weighted genetic algorithm (awGA) and another improved genetic algorithm based on a priori knowledge and adaptive random initialization method were designed and implemented to solve the optimization problem under strict constraints (P-awGA). The experimental results show that using the hybrid residual prediction model and the improved genetic algorithm can accurately predict the coke quality and use less time to obtain a lower-cost coal blending solution.

Single-pixel object classification using ordered illumination patterns

The fixed-ordering illumination patterns lack an effective information interchange with objects. This leads to the light intensity values carrying random feature information, affecting the model's building and recognition capability. Furthermore, this method needs numerous illumination pattern projection counts, which results in low sampling efficiency. Therefore, we propose a new optimized-ordering illumination patterns method. In this paper, we first integrate fixed-ordering illumination patterns with category-representative images to obtain light intensity values that carry category feature information. Subsequently, the mechanisms of intra-category feature importance and inter-category feature differences are introduced to reorder the light intensity values and eliminate index numbers to generate an optimized-ordering index array. Finally, based on this index array, illumination patterns are extracted from the original fixed ordering method to form the new optimized-ordering illumination patterns. Experimental results show that in simulation experiments using the MNIST, Fashion MNIST, TRI, and Multi-category datasets, the optimized ordering method achieved recognition accuracies of 90.00%, 80.00%, 80.00%, and 80.00% with only 30 sampling times. Actual tests with physical objects such as mini numbers and clothing also confirmed these findings. The method offers a new research approach by enhancing recognition accuracy and sampling efficiency in single-pixel object classification.

A Machine Learning-Driven Approach to Uncover the Influencing Factors Resulting in Soil Mass Displacement

For most landslides, several destabilising processes act simultaneously, leading to relative sliding along the soil or rock mass surface over time. A number of machine learning approaches have been proposed recently for accurate relative and cumulative landside displacement prediction, but researchers have limited their studies to only a few indicators of displacement. Determining which influencing factors are the most important in predicting different stages of failure is an ongoing challenge due to the many influencing factors and their inter-relationships. In this study, we take a data-driven approach to explore correlations between various influencing factors triggering slope movement to perform dimensionality reduction, then feature selection and extraction to identify which measured factors have the strongest influence in predicting slope movements via a supervised regression approach. Further, through hierarchical clustering of the aforementioned selected features, we identify distinct types of displacement. By selecting only the most effective measurands, this in turn informs the subset of sensors needed for deployment on slopes prone to failure to predict imminent failures. Visualisation of the important features garnered from correlation analysis and feature selection in relation to displacement show that no one feature can be effectively used in isolation to predict and characterise types of displacement. In particular, analysis of 18 different sensors on the active and heavily instrumented Hollin Hill Landslide Observatory in the north west UK, which is several hundred metres wide and extends two hundred metres downslope, indicates that precipitation, atmospheric pressure and soil moisture should be considered jointly to provide accurate landslide prediction. Additionally, we show that the above features from Random Forest-embedded feature selection and Variational Inflation Factor features (Soil heat flux, Net radiation, Wind Speed and Precipitation) are effective in characterising intermittent and explosive displacement.

Radiomic study of antenatal prediction of severe placenta accreta spectrum from MRI.

We previously demonstrated the potential of radiomics for the prediction of severe histological placenta accreta spectrum (PAS) subtypes using T2-weighted MRI. We aim to validate our model using an additional dataset. Secondly, we explore whether the performance is improved using a new approach to develop a new multivariate radiomics model. Multi-centre retrospective analysis was conducted between 2018 and 2023. Inclusion criteria: MRI performed for suspicion of PAS from ultrasound, clinical findings of PAS at laparotomy and/or histopathological confirmation. Radiomic features were extracted from T2-weighted MRI. The previous multivariate model was validated. Secondly, a 5-radiomic feature random forest classifier was selected from a randomized feature selection scheme to predict invasive placenta increta PAS cases. Prediction performance was assessed based on several metrics including area under the curve (AUC) of the receiver operating characteristic curve (ROC), sensitivity, and specificity. We present 100 women [mean age 34.6 (±3.9) with PAS], 64 of whom had placenta increta. Firstly, we validated the previous multivariate model and found that a support vector machine classifier had a sensitivity of 0.620 (95% CI: 0.068; 1.0), specificity of 0.619 (95% CI: 0.059; 1.0), an AUC of 0.671 (95% CI: 0.440; 0.922), and accuracy of 0.602 (95% CI: 0.353; 0.817) for predicting placenta increta. From the new multivariate model, the best 5-feature subset was selected via the random subset feature selection scheme comprised of 4 radiomic features and 1 clinical variable (number of previous caesareans). This clinical-radiomic model achieved an AUC of 0.713 (95% CI: 0.551; 0.854), accuracy of 0.695 (95% CI 0.563; 0.793), sensitivity of 0.843 (95% CI 0.682; 0.990), and specificity of 0.447 (95% CI 0.167; 0.667). We validated our previous model and present a new multivariate radiomic model for the prediction of severe placenta increta from a well-defined, cohort of PAS cases. Radiomic features demonstrate good predictive potential for identifying placenta increta. This suggests radiomics may be a useful adjunct to clinicians caring for women with this high-risk pregnancy condition.

Self-organizing broad network with frequency-domain analysis

The broad network (BN) based on random feature extraction has fast computational nature. However, it usually suffers from redundant features due to its randomization in dealing with massive samples, which brings the risk of overfitting. To overcome this problem, a self-organizing BN (SO-BN) is proposed in this article. First, several groups of polynomial-based fuzzy rules (P-FRs) are embedded into BN instead of the original feature nodes. Then, P-FR with the form of approximated bell functions has the capability to cope with the uncertainties of feature extraction. Second, a frequency domain parameter calculation algorithm is presented to update the parameters of P-FRs in SO-BN. Different from traditional randomization, P-FRs are shaped with frequency-domain analysis for achieving the representative features of samples. Third, an efficient self-organizing mechanism is built to adjust the structure of the enhancement layer dynamically. Then, the enhancement layer can be expanded and pruned rapidly to reduce the redundant feature as well as improve the performance of SO-BN. Finally, the proposed SO-BN is tested on two benchmark datasets and three real-world engineering applications, especially the prediction of sunspot numbers, electrical output and total phosphorus concentration. The results indicate that SO-BN can achieve superior prediction performance than other models.

A novel BiGRU multi-step wind power forecasting approach based on multi-label integration random forest feature selection and neural network clustering

Accurate wind power forecasting helps to carry out effective scheduling and scientific management of wind power, and improve the security and reliability of the power grid. However, the intermittency, volatility and instability of wind energy make wind power forecasting challenging. Therefore, in order to improve the accuracy and stability of wind power forecasting, this paper proposes a bidirectional gated recurrent unit (BiGRU) multi-step wind power forecasting approach based on multi-label integration random forest (MLRF) feature selection and neural network clustering (NNClustering). The proposed MLRF method extends the applicability of random forest through multiple criteria and enables feature selection for multi-step forecasting tasks of multi-factor time series to obtain optimal input features and time steps, which reduces the computational cost and improves the generalization ability of the model. The proposed NNClustering method establishes a novel convolution-based clustering structure and adjusts the parameters by gradient descent method to obtain the optimal clustering centers, and the robust data applicability of the method is validated in multiple seasonal experiments. The WOA-BiGRU forecasting model is constructed separately for each cluster, which reduces the modeling difficulty and better extracts the characteristics. The BiGRU model extracts more efficient characteristics by processing sequences in both directions and the important parameters of BiGRU are optimized by the whale optimization algorithm (WOA) to obtain the optimal forecasting model. Experimental results over multiple seasons show that the proposed hybrid approach has good forecasting performance and robustness, which provides a novel and efficient solution for wind power forecasting.