Search

With the emergence of big data initiatives and the wealth of available chemical data, data-driven approaches are becoming a vital component of materials discovery pipelines or workflows. The screening of materials using machine-learning models, in particular, is increasingly gaining momentum to accelerate the discovery of new materials. However, the black-box treatment of machine-learning methods suffers from a lack of model interpretability, as feature relevance and interactions can be overlooked or disregarded. In addition, naive approaches to model training often lead to irrelevant features being used which necessitates the need for various regularization techniques to achieve model generalization; this incurs a high computational cost. We present a feature-selection workflow that overcomes this problem by leveraging a gradient boosting framework and statistical feature analyses to identify a subset of features, in a recursive manner, which maximizes their relevance to the target variable or classes. We subsequently obtain minimal feature redundancy through multicollinearity reduction by performing feature correlation and hierarchical cluster analyses. The features are further refined using a wrapper method, which follows a greedy search approach by evaluating all possible feature combinations against the evaluation criterion. A case study on elastic material-property prediction and a case study on the classification of materials by their metallicity are used to illustrate the use of our proposed workflow; although it is highly general, as demonstrated through our wider subsequent prediction of various material properties. Our Bayesian-optimized machine-learning models generated results, without the use of regularization techniques, which are comparable to the state-of-the-art that are reported in the scientific literature. [ABSTRACT FROM AUTHOR]

Argument visual states are helpful for detecting structured components of events in videos, and existing methods tend to use object detectors to generate their candidates. However, directly leveraging object features captured by bounding boxes overlooks a deep understanding of object relations and differences between them and real arguments. In this work, we propose a novel framework to generate selective contextual representations of videos, thereby reducing the interference of useless or incorrect object features. Firstly, we construct grid-based object features as graphs based on the internal grid connection and then use graph convolutional network to execute feature aggregation. Secondly, a weighted geometric attention module is designed to obtain the contextual representation of objects, which explicitly combines visual similarity and geometric correlation with different importance proportions. Then, we propose a dual relation-aware selection module for further feature selection. Finally, we utilize labels as the ladder to bridge the gap between object features and semantic roles, while considering the proximity in the semantic space. Experimental results and extensive ablation studies on the VidSitu indicate that our method effectively obtains a deep understanding of events in videos and outperforms state-of-the-art models. [ABSTRACT FROM AUTHOR]

This paper (i) explores the internal structure of two quantum mechanics datasets (QM7b, QM9), composed of several thousands of organic molecules and described in terms of electronic properties, and (ii) further explores an inverse design approach to molecular design consisting of using machine learning methods to approximate the atomic composition of molecules, using QM9 data. Understanding the structure and characteristics of this kind of data is important when predicting the atomic composition from physical‐chemical properties in inverse molecular designs. Intrinsic dimension analysis, clustering, and outlier detection methods were used in the study. They revealed that for both datasets the intrinsic dimensionality is several times smaller than the descriptive dimensions. The QM7b data is composed of well‐defined clusters related to atomic composition. The QM9 data consists of an outer region predominantly composed of outliers, and an inner, core region that concentrates clustered inliner objects. A significant relationship exists between the number of atoms in the molecule and its outlier/inliner nature. The spatial structure exhibits a relationship with molecular weight. Despite the structural differences between the two datasets, the predictability of variables of interest for inverse molecular design is high. This is exemplified by models estimating the number of atoms of the molecule from both the original properties and from lower dimensional embedding spaces. In the generative approach the input is given by a set of desired properties of the molecule and the output is an approximation of the atomic composition in terms of its constituent chemical elements. This could serve as the starting region for further search in the huge space determined by the set of possible chemical compounds. The quantum mechanic's dataset QM9 is used in the study, composed of 133,885 small organic molecules and 19 electronic properties. Different multi‐target regression approaches were considered for predicting the atomic composition from the properties, including feature engineering techniques in an auto‐machine learning framework. High‐quality models were found that predict the atomic composition of the molecules from their electronic properties, as well as from a subset of only 52.6% size. Feature selection worked better than feature generation. The results validate the generative approach to inverse molecular design. [ABSTRACT FROM AUTHOR]

In today's world, agricultural production and operation activities generate a lot of data. As a result, computer-aided agriculture applications have become a hot topic in the study, with various machine learning (ML) algorithms being used to classify agricultural data. This paper presents a comparative study consisting of a combination of ML algorithms with meta-heuristic algorithms for feature selection to improve the classification capability of ML algorithms by finding the features that significantly impact accuracy. We have used six different meta-heuristic algorithms for feature selection. Experiments are conducted on four different agricultural datasets with five classification models. To understand the effect of proposed models, the selected features are fed into the ML algorithms. The results prove that combining ML and meta-heuristic algorithms achieves higher classification accuracy with fewer features on agricultural datasets. [ABSTRACT FROM AUTHOR]

Internet of Things (IoTs) has been playing an important role in many sectors, such as smart cities, smart agriculture, smart healthcare, and smart manufacturing. However, IoT devices are highly vulnerable to cyber-attacks, which may result in security breaches and data leakages. To effectively prevent these attacks, a variety of machine learning-based network intrusion detection methods for IoT networks have been developed, which often rely on either feature extraction or feature selection techniques for reducing the dimension of input data before being fed into machine learning models. This aims to make the detection complexity low enough for real-time operations, which is particularly vital in any intrusion detection systems. This paper provides a comprehensive comparison between these two feature reduction methods of intrusion detection in terms of various performance metrics, namely, precision rate, recall rate, detection accuracy, as well as runtime complexity, in the presence of the modern UNSW-NB15 dataset as well as both binary and multiclass classification. For example, in general, the feature selection method not only provides better detection performance but also lower training and inference time compared to its feature extraction counterpart, especially when the number of reduced features K increases. However, the feature extraction method is much more reliable than its selection counterpart, particularly when K is very small, such as K = 4 . Additionally, feature extraction is less sensitive to changing the number of reduced features K than feature selection, and this holds true for both binary and multiclass classifications. Based on this comparison, we provide a useful guideline for selecting a suitable intrusion detection type for each specific scenario, as detailed in Table 14 at the end of Sect. 4. Note that such the comparison between feature selection and feature extraction over UNSW-NB15 as well as theoretical guideline have been overlooked in the literature. [ABSTRACT FROM AUTHOR]

Air quality prediction technology can provide effective technical means for environmental governance. In recent years, due to the strong nonlinearity of data, there has been extensive research on data analysis and preprocessing techniques. This paper aims to comprehensively summarize and analyze the methods used in air quality forecasting, specifically focusing on four categories: data decomposition, dimensionality reduction, data correction, and spatial interpolation. Each method's purpose, characteristics, improvements, and implementation details are described in detail. The evaluation of data preprocessing methods is based on popularity, accuracy improvements, time consumption, maturity, and implementation difficulty. Among the existing methods, data decomposition and feature selection are commonly used and well-developed. However, outlier detection and spatial interpolation have limited applications and require further research. Furthermore, this paper discusses current challenges in applying these methods and future development trends, providing a valuable reference for future research. [ABSTRACT FROM AUTHOR]

Artificial Intelligence (AI)-based IDS systems are susceptible to adversarial attacks and face challenges such as complex evaluation methods, elevated false positive rates, absence of effective validation, and time-intensive processes. This study proposes a WCSAN-PSO framework to detect adversarial attacks in IDS based on a weighted conditional stepwise adversarial network (WCSAN) with a particle swarm optimization (PSO) algorithm and SVC (support vector classifier) for classification. The Principal component analysis (PCA) and the least absolute shrinkage and selection operator (LASSO) are used for feature selection and extraction. The PSO algorithm optimizes the parameters of the generator and discriminator in WCSAN to improve the adversarial training of IDS. The study presented three distinct scenarios with quantitative evaluation, and the proposed framework is evaluated with adversarial training in balanced and imbalanced data. Compared with existing studies, the proposed framework accomplished an accuracy of 99.36% in normal and 98.55% in malicious traffic in adversarial attacks. This study presents a comprehensive overview for researchers interested in adversarial attacks and their significance in computer security. [ABSTRACT FROM AUTHOR]

The exponential increase in Internet-facing devices in the last decade has resulted in IP address exhaustion due to the limitations of the existing IPv4 address space. Therefore, the Internet Engineering Task Force engineered a new version of the Internet protocol known as Internet Protocol Version 6 (IPv6) to resolve the issue. However, IPv6 is highly dependent on the neighbor discovery protocol (NDP), which, unfortunately, has well-known vulnerabilities in its underlying messaging protocol, the Internet Control Message Protocol version 6. So, the NDP flaws leave the IPv6 network open to many security threats and attacks, including man-in-the-middle, spoofing, and denial-of-service attacks, which are the most annoying attack at the network layer. Unfortunately, one of the critical issues plaguing the existing anomaly-based detection system is the effectiveness of detecting NDP-based DDoS attacks, which requires urgent attention. This paper suggests a system to find network traffic patterns that are not normal that are caused by NDP-based attacks. It does this by teaching neural networks how to recognize network attack patterns using the backpropagation algorithm. The proposed system is a big step forward from where the field is now because it uses a complex neural network algorithm to create an NDP anomaly-based detection system. Using a real dataset to test the proposed system's performance shows that it can find NDP anomalies with a 99.95% success rate, a 99.92% precision rate, a 99.98% recall rate, an F1-Score of 99.98%, and a 0.040% false positive rate. Also, the proposed approach shows better results compared to other existing approaches. [ABSTRACT FROM AUTHOR]

The Internet of Things (IoT) has garnered considerable attention from academic and industrial circles as a pivotal technology in recent years. The escalation of security risks is observed to be associated with the growing interest in IoT applications. Intrusion detection systems (IDS) have been devised as viable instruments for identifying and averting malicious actions in this context. Several techniques described in academic papers are thought to be very accurate, but they cannot be used in the real world because the datasets used to build and test the models do not accurately reflect and simulate the IoT network. Existing methods, on the other hand, deal with these issues, but they are not good enough for commercial use because of their lack of precision, low detection rate, receiver operating characteristic (ROC), and false acceptance rate (FAR). The effectiveness of these solutions is predominantly dependent on individual learners and is consequently influenced by the inherent limitations of each learning algorithm. This study introduces a new approach for detecting intrusion attacks in an IoT network, which involves the use of an ensemble learning technique based on gray wolf optimizer (GWO). The novelty of this study lies in the proposed voting gray wolf optimizer (GWO) ensemble model, which incorporates two crucial components: a traffic analyzer and a classification phase engine. The model employs a voting technique to combine the probability averages of the base learners. Secondly, the combination of feature selection and feature extraction techniques is to reduce dimensionality. Thirdly, the utilization of GWO is employed to optimize the parameters of ensemble models. Similarly, the approach employs the most authentic intrusion detection datasets that are accessible and amalgamates multiple learners to generate ensemble learners. The hybridization of information gain (IG) and principal component analysis (PCA) was employed to reduce dimensionality. The study utilized a novel GWO ensemble learning approach that incorporated a decision tree, random forest, K-nearest neighbor, and multilayer perceptron for classification. To evaluate the efficacy of the proposed model, two authentic datasets, namely, BoT-IoT and UNSW-NB15, were scrutinized. The GWO-optimized ensemble model demonstrates superior accuracy when compared to other machine learning-based and deep learning models. Specifically, the model achieves an accuracy rate of 99.98%, a DR of 99.97%, a precision rate of 99.94%, an ROC rate of 99.99%, and an FAR rate of 1.30 on the BoT-IoT dataset. According to the experimental results, the proposed ensemble model optimized by GWO achieved an accuracy of 100%, a DR of 99.9%, a precision of 99.59%, an ROC of 99.40%, and an FAR of 1.5 when tested on the UNSW-NB15 dataset. [ABSTRACT FROM AUTHOR]

An intrusion detection system (IDS) is a system that monitors network traffic for malicious activity and generates alerts. In anomaly-based detection, machine learning (ML) algorithms exploit various statistical and probabilistic methods to learn from past or historical experience and detect valuable patterns from large, unstructured, and complex datasets. ML-based network intrusion detection aims to identify malicious behavior and alert a system administrator when an intruder tries to penetrate the network. This paper deals with the study, strategic construction, and implementation of a network intrusion detection model based on ML methods. Among the available IDS datasets, five of the most relevant are chosen for the experimental analysis, which are NSL-KDD-2009, CIC-IDS2017, CIC-IDS2018, IoTID20, and UNSW-NB15 datasets. In order to reduce the computation time in the training sample and achieve computational complexity O (N 2.38 ± δ) , we propose a computationally efficient and feasible algorithmic framework for analyzing the network traffic data. The developed approach mainly consists of two phases, i.e., "Scatter Matrices and Eigenvalue Computation based feature Selection" and "Classification procedure for the reduced dimension data." Experimental evaluation of various test case scenarios for the chosen datasets is carried out in the simulation setting. It is observed that the test results outperform the existing intrusion detection methods for detecting certain attack categories. [ABSTRACT FROM AUTHOR]

Introduction: Untargeted metabolomics studies are expected to cover a wide range of compound classes with high chemical diversity and complexity. Thus, optimizing (pre-)analytical parameters such as the analytical liquid chromatography (LC) column is crucial and the selection of the column depends primarily on the study purpose. Objectives: The current investigation aimed to compare six different analytical columns. First, by comparing the chromatographic resolution of selected compounds. Second, on the outcome of an untargeted toxicometabolomics study using pooled human liver microsomes (pHLM), rat plasma, and rat urine as matrices. Methods: Separation and analysis were performed using three different reversed-phase (Phenyl-Hexyl, BEH C18, and Gold C18), two hydrophilic interaction chromatography (HILIC) (ammonium-sulfonic acid and sulfobetaine), and one porous graphitic carbon (PGC) columns coupled to high-resolution mass spectrometry (HRMS). Their impact was evaluated based on the column performance and the size of feature count, amongst others. Results: All three reversed-phase columns showed a similar performance, whereas the PGC column was superior to both HILIC columns at least for polar compounds. Comparing the size of feature count across all datasets, most features were detected using the Phenyl-Hexyl or sulfobetaine column. Considering the matrices, most significant features were detected in urine and pHLM after using the sulfobetaine and in plasma after using the ammonium-sulfonic acid column. Conclusion: The results underline that the outcome of this untargeted toxicometabolomic study LC-HRMS metabolomic study was highly influenced by the analytical column, with the Phenyl-Hexyl or sulfobetaine column being the most suitable. However, column selection may also depend on the investigated compounds as well as on the investigated matrix. [ABSTRACT FROM AUTHOR]

Patients with superficial peritoneal endometriosis (SPE) present with symptoms suggestive of endometriosis but clinical and imaging exams are inconclusive. Consequently, laparoscopy is usually necessary to confirm diagnosis. The present study aimed to evaluate the accuracy of microRNAs (miRNAs) to diagnose patients with SPE from the ENDOmiARN cohort This prospective study (NCT04728152) included 200 saliva samples obtained between January and June 2021 from women with pelvic pain suggestive of endometriosis. All patients underwent either laparoscopy and/or MRI to confirm the presence of endometriosis. Among the patients with endometriosis, two groups were defined: an SPE phenotype group of patients with peritoneal lesions only, and a non-SPE control group of patients with other endometriosis phenotypes (endometrioma and/or deep endometriosis). Data analysis consisted of two parts: (i) identification of a set of miRNA biomarkers using next-generation sequencing (NGS), and (ii) development of a saliva-based miRNA signature for the SPE phenotype in patients with endometriosis based on a Random Forest (RF) model. Among the 153 patients with confirmed endometriosis, 10.5 % (n = 16) had an SPE phenotype. Of the 2633 known miRNAs, the feature selection method generated a signature of 89 miRNAs of the SPE phenotype. After validation, the best model, representing the most accurate signature had a 100 % sensitivity, specificity, and AUC. This signature could constitute a new diagnostic strategy to detect the SPE phenotype based on a simple biological test and render diagnostic laparoscopy obsolete. We generated a saliva-based signature to identify patients with superficial peritoneal endometriosis which is the most challenging form of endometriosis to diagnose and which is often either misdiagnosed or requires invasive laparoscopy. [ABSTRACT FROM AUTHOR]

Cucumber downy mildew, caused by Pseudoperonospora cubensis , typically remains hidden from view during its initial infection stage. To address this issue, this study proposed an early diagnosis model for greenhouse cucumber downy mildew. This study was conducted under controlled conditions, utilising a large-scale mobile chlorophyll fluorescence imaging system to monitor the samples during their seedling stage on a daily basis from the first day of inoculation. A total of 98 sets of fluorescence parameter values and corresponding fluorescence images were collected. Machine learning methods, such as recursive feature elimination (RFE) and Least Absolute Shrinkage and Selection Operator (LASSO) regression with L1 regularisation, were used to screen the chlorophyll fluorescence parameter Ft_D3, whose corresponding the chlorophyll fluorescence images were used as inputs to the proposed model, following by employing a convolutional neural network (CNN) transfer learning method to the early detection task of cucumber downy mildew in fluorescence images. The study improved the topology structure of ResNet50, the network model with a learning rate of 0.001 and 16 cycles as the optimal feature extractor. The results indicated that the enhanced network displayed improved performance in early detection of cucumber downy mildew compared with other CNNs. Infected leaves were distinguished from healthy leaves in the early stages of infection, specifically 3 days before the appearance of symptoms. The accuracy of the model in the task of early diagnosis of downy mildew was 94.76%. This study presents an efficient approach for the photosynthetic characterisation and early identification of cucumber downy mildew. • Chl-FI showed potential for early diagnosis of downy mildew. • The improved-ResNet model attained 94.76% accuracy for early disease detection. • The data proportion was modified to mimic natural plant disease spread. • The Focal loss function was used to solve the category imbalance problem. [ABSTRACT FROM AUTHOR]

Unmanned aerial vehicles (UAVs) equipped with high-resolution imaging sensors have shown great potential for plant phenotyping in agricultural research. This study aimed to explore the potential of UAV-derived red–green–blue (RGB) and multispectral imaging data for estimating classical phenotyping measures such as plant height and predicting yield and chlorophyll content (indicated by SPAD values) in a field trial of 38 faba bean (Vicia faba L.) cultivars grown at four replicates in south-eastern Norway. To predict yield and SPAD values, Support Vector Regression (SVR) and Random Forest (RF) models were utilized. Two feature selection methods, namely the Pearson correlation coefficient (PCC) and sequential forward feature selection (SFS), were applied to identify the most relevant features for prediction. The models incorporated various combinations of multispectral bands, indices, and UAV-based plant height values at four different faba bean development stages. The correlation between manual and UAV-based plant height measurements revealed a strong agreement with a correlation coefficient (R2) of 0.97. The best prediction of SPAD value was achieved at BBCH 50 (flower bud present) with an R2 of 0.38 and RMSE of 1.14. For yield prediction, BBCH 60 (first flower open) was identified as the optimal stage, using spectral indices yielding an R2 of 0.83 and RMSE of 0.53 tons/ha. This development stage presents an opportunity to implement targeted management practices to enhance yield. The integration of UAVs equipped with RGB and multispectral cameras, along with machine learning algorithms, proved to be an accurate approach for estimating agronomically important traits in faba bean. This methodology offers a practical solution for rapid and efficient high-throughput phenotyping in faba bean breeding programs. [ABSTRACT FROM AUTHOR]

In order to estimate the likelihood of 1, 3, 6 and 12 month mortality in patients with hip fractures, we applied a variety of machine learning methods using readily available, preoperative data. We used prospectively collected data from a single university hospital in Copenhagen, Denmark for consecutive patients with hip fractures, aged 60 years and older, treated between September 2008 to September 2010 (n = 1186). Preoperative biochemical and anamnestic data were used as predictors and outcome was survival at 1, 3, 6 and 12 months after the fracture. After feature selection for each timepoint a stratified split was done (70/30) before training and validating Random Forest models, extreme gradient boosting (XGB) and Generalized Linear Models. We evaluated and compared each model using receiver operator characteristic (ROC), calibration slope and intercept, Spiegelhalter's z- test and Decision Curve Analysis. Using combinations of between 10 and 13 anamnestic and biochemical parameters we were able to successfully estimate the likelihood of mortality with an area under the curve on ROC curves of 0.79, 0.80, 0.79 and 0.81 for 1, 3, 6 and 12 month, respectively. The XGB was the overall best calibrated and most promising model. The XGB model most successfully estimated the likelihood of mortality postoperatively. An easy-to-use model could be helpful in perioperative decisions concerning level of care, focused research and information to patients. External validation is necessary before widespread use and is currently underway, an online tool has been developed for educational/experimental purposes (https://hipfx.shinyapps.io/hipfx/). [ABSTRACT FROM AUTHOR]

In supervised learning, feature selection methods identify the most relevant predictors to include in a model. For linear models, the inclusion or exclusion of each variable may be represented as a vector of bits playing the role of the genetic material that defines the model. Genetic algorithms reproduce the strategies of natural selection on a population of models to identify the best. We derive the distribution of the importance scores for parallel genetic algorithms under the null hypothesis that none of the features has predictive power. They, hence, provide an objective threshold for feature selection that does not require the visual inspection of a bubble plot. We also introduce the eradication strategy, akin to forward stepwise selection, where the genes of useful variables are sequentially forced into the models. The method is illustrated on real data, and simulation studies are run to describe its performance. [ABSTRACT FROM AUTHOR]

Summary: Flying ad hoc network (FANET) is a technology that has seen tremendous growth in the past years due to its application in various military and civil developments. Conventional topology‐aided routing schemes are not suitable for large‐scale FANETs. This is because of the higher mobility rate in UAVs with the architecture differences. Hence, several path entries in routing become invalid and the neighboring nodes can be occupied before the interruption. Hence, it is very important to solve the afore‐explained issues in FANET. Initially, the task is assigned to the UAVs. These tasks are performed by satisfying the demands such as timing, congestion, and energy to attain the effective load‐balancing performance. Then, the optimal clustering and cluster head (CH) selection are performed using the developed Percentage of Circle Search and Spotted Hyena Optimizer (PCSSHO) in the communication path. Here, the feature selection is done based on constraints like position, speed, moving direction, height variation, link quality, and inter‐ and intra‐cluster distance. Then, the developed PCSSHO model performs routing by considering different constraints such as "end‐to‐end delay, delivery ratio, power consumption, and link quality." Thus, the recommenced load balancing model in FANET secures an enhanced performance rate than the conventional load balancing frameworks. [ABSTRACT FROM AUTHOR]

Agriculture is an essential part of human life. The crop productivity is based on the soil and environmental factors. Different crops are cultivated in different areas. Nowadays, the crop productivity level is affected by the climate change and diseases in the crops. Due to this pest infestation, the crop growth is heavily affected. To overcome this problem, the right fertilizer for a particular crop has to be chosen and fertilizer helps farmers to improve the crop productivity rate. This process can be done by using various machine learning techniques. In this work, various features selection techniques with classifiers used to predict the suitable fertilizer for a crop. The experimental results show that recursive feature elimination along the proposed Heterogeneous Stacked Ensemble classifier gives better prediction rate than other methods. [ABSTRACT FROM AUTHOR]

To establish a machine-learning model based on dynamic contrast-enhanced (DCE) magnetic resonance imaging (MRI) to differentiate combined hepatocellular–cholangiocarcinoma (cHCC-CC) from hepatocellular carcinoma (HCC) before surgery. Clinical and MRI data of 194 patients with histopathologically diagnosed cHCC-CC (n= 52) or HCC (n= 142) were analysed retrospectively. ITK-SNAP software was used to delineate three-dimensional (3D) lesions and extract high-throughput features. Feature selection was carried out based on Pearson's correlation coefficient and least absolute shrinkage and selection operator (LASSO) regression analysis. A radiomics model (radiomics features), a clinical model (i.e., clinical-image features), and a fusion model (i.e., radiomics features + clinical-image features) were established using six machine-learning classifiers. The performance of each model in distinguishing between cHCC-CC and HCC was evaluated with the receiver operating characteristic (ROC) curve, the area under the ROC curve (AUC), sensitivity, and specificity. Significant differences in liver cirrhosis, tumour number, shape, edge, peritumoural enhancement in the arterial phase, and lipid were identified between cHCC-CC and HCC patients (p< 0.05). The AUC of the fusion model based on logistic regression was 0.878 (95% CI: 0.766–0.949) in the arterial phase in the test set, and the sensitivity/specificity was 0.844/0.714; however, the AUC of the clinical and radiomics models was 0.759 (95% CI: 0.663–0.861) and 0.838 (95% CI: 0.719–0.921) in the test set, respectively. The fusion model based on DCE-MRI in the arterial phase can significantly improve the diagnostic rate of cHCC-CC and HCC as compared with conventional approaches. • The radiomics based on DCE-MRI performs well differentiating cHCC-CC from HCC. • Logistic regression has important value in determining whether cHCC-CC from HCC. • The AUC of the fusion model is 0.878 in differentiating cHCC-CC from HCC. [ABSTRACT FROM AUTHOR]

Hyper spectral imaging (HSI) is an advanced and fascinating remote sensing method in various domains. Every sample in HS remote sensing images possesses high-size features and has a massive amount of spatial and spectral data that enhances the complexity of feature selection and mining. Also, it improves the interpretational complications and thus surpasses the prediction accuracy of the system. To counterpart such issues, this article introduces an innovative system for HSI categorization wielding introduced Fractional Snake Honey Badger Optimization (FSHBO). Here, image segmentation is done through U-Net, which is trained by Snake Honey Badger Optimization (SHBO). The Deep Belief Network (DBN) is employed for HSI classification that outputs the pixel-wise classified result and this DBN is efficiently tuned using the proposed FSHBO. It is recorded that the proposed FSHBO-DBN has outperformed diverse classical models in terms of accuracy of 0.907, sensitivity of 0.914, and specificity of 0.904. [ABSTRACT FROM AUTHOR]

The problem of selecting a subset of genes relevant to a particular disease classification task from high-dimensional gene microarray data has been an area of active research in the scientific community. A wide variety of methods ranging from assigning scores to genes based on their interactions with the output to the Gravity inspired clustering algorithm with the hybrid approach have been proposed. The feature sets selected by this approach have been evaluated by using the Support Vector Machine (SVM) with Leave One Out Cross Validation (LOOCV). The method has been evaluated on twelve different publicly available microarray cancer datasets and the proposed method provided good accuracy of 90.16% to the colon dataset, 98.59% to the ALL-AML dataset, 97.03% to the lung cancer dataset, 93.07% to the prostate cancer dataset, 98.41% to the meningioma dataset, 83.72% to the brain tumour dataset and has been shown to compete with existing methods. [ABSTRACT FROM AUTHOR]

This research focuses on understanding the spatial variation of Soil Organic Matter (SOM) and pH levels in the North of Morocco. The study employs a comprehensive approach to enhance predictive modelling, incorporating the Boruta algorithm for effective environmental covariates selection and optimizing model parameters through hyperparameter optimization. Utilizing a Random Forest (RF) model with remote sensing indices and topographic features, the research predicts SOM and pH to identify key contributors to their spatial variability. SOM prediction saw significant success, with a notable correlation to remote sensing indices such as the RVI, NDVI, and TNDVI. These indices, indicative of vegetation health and productivity, emerged as primary influencers of SOM. In comparison, the influence of topographic features like elevation, slope, and aspect was found to be less significant. Conversely, predicting pH was challenging due to the minimal spatial variability within the dataset. Addressing this limitation could involve dataset expansion or alternative models for low-correlated data handling. Despite the RF model's limited efficacy in pH prediction, an observable correlation between SOM and pH was identified, consistent with prior research. Areas with higher SOM exhibited lower pH values, indicating relative soil acidification from organic matter decomposition. The study's RF model demonstrated potential in SOM prediction using remote sensing indices, but enhancing pH prediction is essential. Future research may explore dataset expansion, diverse sampling, or testing alternative predictive models for better performance with low-correlated datasets. The study offers valuable insights for advanced predictive model development and enriches understanding of soil management practices. [ABSTRACT FROM AUTHOR]

Brain tumor is an anomalous growth of glial and neural cells and is considered as one of the primary causes of death worldwide. Therefore, it is essential to identify the tumor as soon as possible for reducing the mortality rate throughout the world. However, the classification of brain tumor is a challenging task due to presence of irrelevant features that cause misclassification during detection. In this research, the adaptive manta ray foraging optimization (AMRFO) is proposed for performing an effective feature selection to avoid the problem of overfitting while performing the classification. The adaptive control parameter strategy is incorporated in the AMRFO for enhancing the search process while selecting the feature subset. The linear intensity distribution information and regularization parameter-based intuitionistic fuzzy C-means algorithm namely LRIFCM is used to perform the segmentation of tumor regions. Next, LeeNET, gray-level co-occurrence matrix, local ternary pattern, histogram of gradients, and shape features are used to extract essential features from the segmented regions. Further, the attention-based long short-term memory (ALSTM) is used to classify the brain tumor types according to the features selected by AMRFO. The datasets utilized in this research study for the evaluation of AMRFO-ALSTM method are BRATS 2017, BRATS 2018, and Figshare brain datasets. Segmentation and classification are the two different evaluations examined for the AMRFO-ALSTM. The structural similarity index measure, Jaccard, dice, accuracy, and sensitivity are utilized during segmentation evaluation, while accuracy, specificity, sensitivity, precision, and F1-score are used during classification evaluation. The existing researches namely, transformer-enhanced convolutional neural network, Chan Vese (CV)-support vector machine, CV-K-nearest neighbor, deep convolutional neural network (DCNN), and salp water optimization with deep belief network are used to compare with the AMRFO-ALSTM. The accuracy of AMRFO-ALSTM for Figshare brain dataset is 99.80 which is a greater achievement when compared to the DCNN. [ABSTRACT FROM AUTHOR]

In sewer networks, failure prediction plays a significant role in operation and maintenance plans of wastewater utilities. This study aims to determine the effective variables on the failures by using feature selection algorithms (FS) and achieve maximum model accuracy with minimum variables. Also, four scenarios based on the suggested FS algorithms were developed. In these scenarios, the best prediction models were investigated using machine learning classifiers (ML) such as neural network classifier (NNC), gradient boosting machine (GBM), random forest (FR), and hybrid model (HM). The classification performance of ML models was evaluated using accuracy, precision, F1_score, and receiver operating characteristics (ROC) curve. The model accuracies ranging from 0.99 for accuracy to 1 for the ROC curve were achieved through ML algorithms. In conclusion, the ML algorithms suggested in this study may be a decision support tool for wastewater utilities in prioritizing the replacement, maintenance, and inspection of sewer pipes. [ABSTRACT FROM AUTHOR]

Discovering the most effective anti-SARS-CoV-2 drugs is the optimal solution to get back to a normal life without COVID-19. Drug repurposing, also known as drug repositioning, has become one of the most important solutions for developing new COVID-19 drugs. However, this alternative requires long-term laboratory experiments to reach the optimal drug that involves the best combination of drug features to resist the COVID-19 virus. In response to this challenge, the COVID-19 drug repurposing (C19-DR) model based on pigeon-inspired optimizer (PIO) and rough sets theory (RST) is proposed. The proposed model presents a new rough set-based feature selection technique that uses a pigeon-inspired optimizer algorithm to find and validate the optimal reduct of drug features to design an effective COVID-19 drug. Moreover, the proposed model can investigate the efficiency of multiple medications against the COVID-19 virus based on the half-maximal inhibitory concentration (IC50) threshold. The effectiveness of the proposed COVID-19 drug repurposing model has been validated using a laboratory drug dataset consisting of 60 medications. The practical results show that the optimized rough set reduct of {hydrogen bonding acceptor (HBA) and number of chiral centers} is the most significant reduct that can be used to design an effective COVID-19 drug. Moreover, the proposed drug design model could verify the efficiency of a selected dataset of drug models based on evaluating the IC50 metric. The verification results proved the high effectiveness of the proposed model in evaluating the predicted IC50 with an accuracy of 91.4% and MSE of 0.034. These findings might be a promising solution that can assist researchers in developing and repurposing novel medications to treat COVID-19 and its new viral mutants. [ABSTRACT FROM AUTHOR]

Parkinson's disease (PD) arises from brain cell damage and necessitates early detection for effective treatment and symptom management. While various methods such as voice, speech, and written exams have been explored, utilizing automated tools is crucial to enhance accuracy. Recent advancements in artificial intelligence (AI) and deep learning (DL) provide an opportunity for precise early-stage PD identification. This study introduces a novel approach known as Quantum Mayfly Optimization-based feature subset selection with hybrid convolutional neural network (QMFOFS-HCNN) to improve PD detection and classification. QMFOFS-HCNN is designed to identify optimal feature subsets and overcome the dimensionality challenge. It combines a quantum mayfly optimization approach for feature selection with a convolutional neural network with attention-based long short-term memory for PD detection and classification. Additionally, hyperparameter selection is optimized using the Nadam optimizer. Experimental validation using benchmark datasets yielded compelling results. The QMFOFS-HCNN technique achieved accuracy rates: 96.35% for HandPD Spiral, 96.7% for HandPD Meander, 98.5% for Speech PD, and a perfect 100% for Voice PD datasets. These quantitative findings underscore the potential of AI and DL to enhance early PD detection accuracy significantly. These results offer promising prospects for improving healthcare outcomes in managing PD and related neurological disorders. [ABSTRACT FROM AUTHOR]

The growing concern of pediatric mortality demands heightened preparedness in clinical settings, especially within intensive care units (ICUs). As respiratory-related admissions account for a substantial portion of pediatric illnesses, there is a pressing need to predict ICU mortality in these cases. This study based on data from 1188 patients, addresses this imperative using machine learning techniques and investigating different class balancing methods for pediatric ICU mortality prediction. This study employs the publicly accessible "Paediatric Intensive Care database" to train, validate, and test a machine learning model for predicting pediatric patient mortality. Features were ranked using three machine learning feature selection techniques, namely Random Forest, Extra Trees, and XGBoost, resulting in the selection of 16 critical features from a total of 105 features. Ten machine learning models and ensemble techniques are used to make accurate mortality predictions. To tackle the inherent class imbalance in the dataset, we applied a unique data partitioning technique to enhance the model's alignment with the data distribution. The CatBoost machine learning model achieved an area under the curve (AUC) of 72.22%, while the stacking ensemble model yielded an AUC of 60.59% for mortality prediction. The proposed subdivision technique, on the other hand, provides a significant improvement in performance metrics, with an AUC of 85.2% and an accuracy of 89.32%. These findings emphasize the potential of machine learning in enhancing pediatric mortality prediction and inform strategies for improved ICU readiness. [ABSTRACT FROM AUTHOR]

Cancer heterogeneity analysis is essential for precision medicine. Most of the existing heterogeneity analyses only consider a single type of data and ignore the possible sparsity of important features. In cancer clinical practice, it has been suggested that two types of data, pathological imaging and omics data, are commonly collected and can produce hierarchical heterogeneous structures, in which the refined sub‐subgroup structure determined by omics features can be nested in the rough subgroup structure determined by the imaging features. Moreover, sparsity pursuit has extraordinary significance and is more challenging for heterogeneity analysis, because the important features may not be the same in different subgroups, which is ignored by the existing heterogeneity analyses. Fortunately, rich information from previous literature (for example, those deposited in PubMed) can be used to assist feature selection in the present study. Advancing from the existing analyses, in this study, we propose a novel sparse hierarchical heterogeneity analysis framework, which can integrate two types of features and incorporate prior knowledge to improve feature selection. The proposed approach has satisfactory statistical properties and competitive numerical performance. A TCGA real data analysis demonstrates the practical value of our approach in analyzing data heterogeneity and sparsity. [ABSTRACT FROM AUTHOR]

Bulk metallic glasses (BMGs) have been receiving extensive attention in the community of physics and materials science due to their attractive properties. The traditional trial-and-error approach is inefficient in designing good BMGs, then it is imperative to elaborate a prediction scheme to accelerate the development of BGMs. This work combines a composite feature selection (c-FS) and machine learning (ML) algorithm to construct a more effective strategy for predicting the critical diameter (Dmax) of BMGs. Apart from the characteristic temperatures, parameters involving domain knowledge such as thermodynamics, dynamics, and topology are also considered as the candidate features. A c-FS was devised to optimize the features, and a most efficient model was developed using the optimal subset. Our model holds the highest R2 score (0.807) compared to the 29 criteria reported. In addition, the SHapley Additive exPlanation (SHAP) approach was introduced to boost the interpretability of the model. Benefiting from our model and SHAP approach, a formation rule for large-size BMGs is uncovered. The efficacy of this model provides new guidance for the design of BMGs. [ABSTRACT FROM AUTHOR]

Understanding long-term Terrestrial water storage (TWS) variations is vital for investigating hydrological extreme events, managing water resources, and assessing climate change impacts. However, the limited data duration from the Gravity Recovery and Climate Experiment (GRACE) and its follow-on missions (GRACE-FO) poses challenges for comprehensive long-term analysis. In this study, we reconstruct TWS anomalies (TWSA) for the period Jan 1960 to Dec 2022 thereby filling data gaps between GRACE and GRACE-FO missions as well as generating a complete dataset for the pre-GRACE era. The workflow involves identifying optimal predictors from land surface model (LSM) outputs, meteorological variables, and climatic indices using a novel Bayesian Network (BN) technique for grid-based TWSA simulations. Climate indices, like the Oceanic Niño Index and Dipole Mode Index, are selected as optimal predictors for a large number of grids globally, along with TWSA from LSM outputs. The most effective machine learning (ML) algorithms among Convolutional Neural Network (CNN), Support Vector Regression (SVR), Extra Trees Regressor (ETR), and Stacking Ensemble Regression (SER) models are evaluated at each grid location to achieve optimal reproducibility. Globally, ETR performs best for most of the grids which is also noticed at the river-basin scale, particularly for the Ganga-Brahmaputra-Meghana, Godavari, Krishna, Limpopo, and Nile river basins. The simulated TWSA (BNML_TWSA) outperformed the TWSA from LSM outputs when evaluated against GRACE datasets. Improvements are particularly noted in the river basins such as Godavari, Krishna, Danube, Amazon, etc., with median values of the correlation coefficient, Nash-Sutcliffe efficiency, and RMSE for all grids in Godavari, India, being 0.927, 0.839, and 63.7 mm respectively. A comparison with TWSA reconstructed in recent studies indicates that the proposed BNML_TWSA outperforms them globally as well as for all the 11 major river basins examined. The presented dataset is published at https://doi.org/10.6084/m9.figshare.25376695 (Mandal et al., 2024) and updates will be published when needed. [ABSTRACT FROM AUTHOR]

Diabetes is a persistent metabolic disorder linked to elevated levels of blood glucose, commonly referred to as blood sugar. This condition can have detrimental effects on the heart, blood vessels, eyes, kidneys, and nerves as time passes. It is a chronic ailment that arises when the body fails to produce enough insulin or is unable to effectively use the insulin it produces. When diabetes is not properly managed, it often leads to hyperglycemia, a condition characterized by elevated blood sugar levels or impaired glucose tolerance. This can result in significant harm to various body systems, including the nerves and blood vessels. In this paper, we propose a multiclass diabetes mellitus detection and classification approach using an extremely imbalanced Laboratory of Medical City Hospital data dynamics. We also formulate a new dataset that is moderately imbalanced based on the Laboratory of Medical City Hospital data dynamics. To correctly identify the multiclass diabetes mellitus, we employ three machine learning classifiers namely support vector machine, logistic regression, and k-nearest neighbor. We also focus on dimensionality reduction (feature selection—filter, wrapper, and embedded method) to prune the unnecessary features and to scale up the classification performance. To optimize the classification performance of classifiers, we tune the model by hyperparameter optimization with 10-fold grid search cross-validation. In the case of the original extremely imbalanced dataset with 70:30 partition and support vector machine classifier, we achieved maximum accuracy of 0.964, precision of 0.968, recall of 0.964, F1-score of 0.962, Cohen kappa of 0.835, and AUC of 0.99 by using top 4 feature according to filter method. By using the top 9 features according to wrapper-based sequential feature selection, the k-nearest neighbor provides an accuracy of 0.935 and 1.0 for the other performance metrics. For our created moderately imbalanced dataset with an 80:20 partition, the SVM classifier achieves a maximum accuracy of 0.938, and 1.0 for other performance metrics. For the multiclass diabetes mellitus detection and classification, our experiments outperformed conducted research based on the Laboratory of Medical City Hospital data dynamics. [ABSTRACT FROM AUTHOR]

AbstractAs a highly prevalent and recurrent cancer, detecting the degree of differentiation in oral cancer is crucial. Current methods rely on biopsies in the presence of significant lesions, which are time-consuming. This study introduces an efficient and rapid approach for mass determination of oral cancer differentiation levels. By leveraging serum Raman spectroscopy combined with deep neural networks and extreme gradient boosting, we performed feature selection and interaction on oral cancer samples of varying differentiation levels, achieving the most accurate and reliable classification of oral cancer differentiation stages. [ABSTRACT FROM AUTHOR]

Stress recognition, particularly using machine learning (ML) with physiological data such as heart rate variability (HRV), holds promise for mental health interventions. However, limited datasets in affective computing and healthcare research can lead to inaccurate conclusions regarding the ML model performance. This study employed supervised learning algorithms to classify stress and relaxation states using HRV measures. To account for limitations associated with small datasets, robust strategies were implemented based on methodological recommendations for ML with a limited dataset, including data segmentation, feature selection, and model evaluation. Our findings highlight that the random forest model achieved the best performance in distinguishing stress from non-stress states. Notably, it showed higher performance in identifying stress from relaxation (F1-score: 86.3%) compared to neutral states (F1-score: 65.8%). Additionally, the model demonstrated generalizability when tested on independent secondary datasets, showcasing its ability to distinguish between stress and relaxation states. While our performance metrics might be lower than some previous studies, this likely reflects our focus on robust methodologies to enhance the generalizability and interpretability of ML models, which are crucial for real-world applications with limited datasets. [ABSTRACT FROM AUTHOR]

During robot-assisted rehabilitation, failure to recognize lower limb movement may efficiently limit the development of exoskeleton robots, especially for individuals with knee pathology. A major challenge encountered with surface electromyography (sEMG) signals generated by lower limb movements is variability between subjects, such as motion patterns and muscle structure. To this end, this paper proposes an sEMG-based lower limb motion recognition using an improved support vector machine (SVM). Firstly, non-negative matrix factorization (NMF) is leveraged to analyze muscle synergy for multi-channel sEMG signals. Secondly, the multi-nonlinear sEMG features are extracted, which reflect the complexity of muscle status change during various lower limb movements. The Fisher discriminant function method is utilized to perform feature selection and reduce feature dimension. Then, a hybrid genetic algorithm-particle swarm optimization (GA-PSO) method is leveraged to determine the best parameters for SVM. Finally, the experiments are carried out to distinguish 11 healthy and 11 knee pathological subjects by performing three different lower limb movements. Results demonstrate the effectiveness and feasibility of the proposed approach in three different lower limb movements with an average accuracy of 96.03% in healthy subjects and 93.65% in knee pathological subjects, respectively. [ABSTRACT FROM AUTHOR]

The domain of human locomotion identification through smartphone sensors is witnessing rapid expansion within the realm of research. This domain boasts significant potential across various sectors, including healthcare, sports, security systems, home automation, and real-time location tracking. Despite the considerable volume of existing research, the greater portion of it has primarily concentrated on locomotion activities. Comparatively less emphasis has been placed on the recognition of human localization patterns. In the current study, we introduce a system by facilitating the recognition of both human physical and location-based patterns. This system utilizes the capabilities of smartphone sensors to achieve its objectives. Our goal is to develop a system that can accurately identify different human physical and localization activities, such as walking, running, jumping, indoor, and outdoor activities. To achieve this, we perform preprocessing on the raw sensor data using a Butterworth filter for inertial sensors and a Median Filter for Global Positioning System (GPS) and then applying Hamming windowing techniques to segment the filtered data. We then extract features from the raw inertial and GPS sensors and select relevant features using the variance threshold feature selection method. The extrasensory dataset exhibits an imbalanced number of samples for certain activities. To address this issue, the permutation-based data augmentation technique is employed. The augmented features are optimized using the Yeo–Johnson power transformation algorithm before being sent to a multi-layer perceptron for classification. We evaluate our system using the K-fold cross-validation technique. The datasets used in this study are the Extrasensory and Sussex Huawei Locomotion (SHL), which contain both physical and localization activities. Our experiments demonstrate that our system achieves high accuracy with 96% and 94% over Extrasensory and SHL in physical activities and 94% and 91% over Extrasensory and SHL in the location-based activities, outperforming previous state-of-the-art methods in recognizing both types of activities. [ABSTRACT FROM AUTHOR]

We propose a method for selecting the optimal set of weather features for wind energy prediction. This problem is tackled by developing a wrapper approach that employs binary differential evolution to search for the best feature subset, and an ensemble of artificial neural networks to predict the energy production from a wind plant. The main novelties of the approach are the use of features provided by different weather forecast providers and the use of an ensemble composed of a reduced number of models for the wrapper search. Its effectiveness is verified using weather and energy production data collected from a 34 MW real wind plant. The model is built using the selected optimal subset of weather features and allows for (i) a 1% reduction in the mean absolute error compared with a model that considers all available features and a 4.4% reduction compared with the model currently employed by the plant owners, and (ii) a reduction in the number of selected features by 85% and 50%, respectively. Reducing the number of features boosts the prediction accuracy. The implication of this finding is significant as it allows plant owners to create profitable offers in the energy market and efficiently manage their power unit commitment, maintenance scheduling, and energy storage optimization. [ABSTRACT FROM AUTHOR]

The specific emitter identification is widely used in electronic countermeasures, spectrum control, wireless network security and other civil and military fields. In response to the problems that the traditional specific emitter identification algorithm relies on a priori knowledge and has poor generalizability, and the existing specific emitter identification algorithm based on deep learning has poor feature selection and the adopted feature extraction network is not targeted, etc., the specific emitter identification algorithm based on multi-sequence feature learning is proposed. Firstly, multiple sequence features of the emitted signal of the communication radiation source are extracted, and these features are combined into multiple sequence features. Secondly, the multiple sequence fusion convolutional network is constructed to fuse and deeply extract the multiple sequence features and complete the classification of individual communication radiation sources through the classifier of neural network. The selected sequence features of this algorithm contain more and more essential RFF information, while the targeted design of the multi-sequence feature fusion learning network can effectively extract the essential RFF information. The results show that the algorithm can significantly improve the performance of SEI compared with the benchmark algorithm, with a recognition rate gain of about 17%. [ABSTRACT FROM AUTHOR]

This study investigates the application of cavitation in non-invasive abdominal fat reduction and body contouring, a topic of considerable interest in the medical and aesthetic fields. We explore the potential of cavitation to alter abdominal fat composition and delve into the optimization of fat prediction models using advanced hyperparameter optimization techniques, Hyperopt and Optuna. Our objective is to enhance the predictive accuracy of abdominal fat dynamics post-cavitation treatment. Employing a robust dataset with abdominal fat measurements and cavitation treatment parameters, we evaluate the efficacy of our approach through regression analysis. The performance of Hyperopt and Optuna regression models is assessed using metrics such as mean squared error, mean absolute error, and R-squared score. Our results reveal that both models exhibit strong predictive capabilities, with R-squared scores reaching 94.12% and 94.11% for post-treatment visceral fat, and 71.15% and 70.48% for post-treatment subcutaneous fat predictions, respectively. Additionally, we investigate feature selection techniques to pinpoint critical predictors within the fat prediction models. Techniques including F-value selection, mutual information, recursive feature elimination with logistic regression and random forests, variance thresholding, and feature importance evaluation are utilized. The analysis identifies key features such as BMI, waist circumference, and pretreatment fat levels as significant predictors of post-treatment fat outcomes. Our findings underscore the effectiveness of hyperparameter optimization in refining fat prediction models and offer valuable insights for the advancement of non-invasive fat reduction methods. This research holds important implications for both the scientific community and clinical practitioners, paving the way for improved treatment strategies in the realm of body contouring. [ABSTRACT FROM AUTHOR]

Typhoon trajectory related data involve many factors, such as atmospheric factors, oceanic factors, and physical factors. It has the characteristics of high dimension, strong spatio-temporal correlation, and nonlinear correlation, which increases the difficulty of typhoon trajectory prediction. Using feature selection approaches to select appropriate prediction factors becomes an important means to reduce the dimension of typhoon trajectory related data and improve the performance and accuracy of typhoon trajectory prediction methods. However, the existing feature selection methods based on linear correlation analysis cannot well depict the nonlinear correlation between data features, which results in low accuracy of feature selection. The feature selection methods based on nonlinear correlation analysis are computationally expensive, which affects the timeliness of feature selection. To solve the problem, we propose a parallel feature selection method NX-Spark-DC based on the Spark platform for typhoon trajectory related data. The method firstly filters out the redundant features of typhoon related data by normalized mutual information (NMI) method, subsequently eliminates the useless features by XGBoost machine learning model, and thus reducing the dimension of typhoon related data. On this basis, an improved Spark-based parallel distance correlation algorithm (Spark-DC) is proposed to select the feature combinations with strong correlation. A series of experimental results show that NX-Spark-DC method has high execution efficiency and accuracy, which is significantly better than the existing methods. [ABSTRACT FROM AUTHOR]

This paper proposes a novel method for robot navigation in high-dimensional environments that reduce the dimension of the state space using local and soft feature selection. The algorithm selects relevant features based on local correlations between states, avoiding duplicate inappropriate information and adjusting sensor values accordingly. By optimizing the value function approximation based on the local weighted features of states in the reinforcement learning process, the method shows improvements in the robot's motion flexibility, learning time, the distance traveled to reach its goal, and the minimization of collisions with obstacles. This approach was tested on an E-puck robot using the Webots robot simulator in different test environments. [ABSTRACT FROM AUTHOR]

In model selection problems, robustness is one important feature for selecting an adequate model from the candidates. We focus on statistical divergence-based selection criteria and investigate their robustness. We mainly consider BHHJ divergence and related classes of divergence measures. BHHJ divergence is a representative robust divergence measure that has been utilized in, for example, parametric estimation, hypothesis testing, and model selection. We measure the robustness against outliers of a selection criterion by approximating the difference of values of the criterion between the population with outliers and the non-contaminated one. We derive and compare the conditions to guarantee robustness for model selection criteria based on BHHJ and related divergence measures. From the results, we find that conditions for robust selection differ depending on the divergence families, and that some expanded classes of divergence measures require stricter conditions for robust model selection. Moreover, we prove that robustness in estimation does not always guarantee robustness in model selection. Through numerical experiments, we confirm the advantages and disadvantages of each divergence family, asymptotic behavior, and the validity for employing criteria on the basis of robust divergence. Especially, we reveal the superiority of BHHJ divergence in robust model selection for extensive cases. [ABSTRACT FROM AUTHOR]

Machine learning classifiers have been widely used for crop mapping; however, employing numerous features can reduce classifier accuracy. Feature selection is a widely recognized technique that addresses the issue of high dimensionality by choosing the most relevant subset of features with the highest degree of relevance and practicality. Therefore, the optimal combination of feature selection methods and classifiers for high-precision crop mapping remains an open problem. In this study, we introduce a novel hybrid feature selection approach to obtain the optimal subset of features for effective crop mapping. Initially, spectro-temporal remote sensing features from the dataset were ranked using two distinct feature selection techniques: Mutual Information (MI) and ReliefF filter. The most relevant features from each filter-based approach were combined into a union subset. Subsequently, the Gray Wolf Optimization (GWO), a metaheuristic optimization technique, was applied to enhance the feature set generated in the initial step. In the final stage, a random forest classifier leveraged the optimized feature subset for accurate crop type prediction. The effectiveness of the proposed approach was evaluated in Behiera governorate, Egypt. Comparative analysis against existing crop mapping methods demonstrated the superior performance of the proposed approach, achieving an accuracy rate of 82%. Furthermore, this approach showcased a significant reduction in the feature count, streamlining the set from 308 down to only 26 features. [ABSTRACT FROM AUTHOR]