Search

Accurately predicting crop yield is essential for optimizing agricultural practices and ensuring food security. However, existing approaches often struggle to capture the complex interactions between various environmental factors and crop growth, leading to suboptimal predictions. Consequently, identifying the most important feature is vital when leveraging Support Vector Regressor (SVR) for crop yield prediction. In addition, the manual tuning of SVR hyperparameters may not always offer high accuracy. In this paper, we introduce a novel framework for predicting crop yields that address these challenges. Our framework integrates a new hybrid feature selection approach with an optimized SVR model to enhance prediction accuracy efficiently. The proposed framework comprises three phases: preprocessing, hybrid feature selection, and prediction phases. In preprocessing phase, data normalization is conducted, followed by an application of K-means clustering in conjunction with the correlation-based filter (CFS) to generate a reduced dataset. Subsequently, in the hybrid feature selection phase, a novel hybrid FMIG-RFE feature selection approach is proposed. Finally, the prediction phase introduces an improved variant of Crayfish Optimization Algorithm (COA), named ICOA, which is utilized to optimize the hyperparameters of SVR model thereby achieving superior prediction accuracy along with the novel hybrid feature selection approach. Several experiments are conducted to assess and evaluate the performance of the proposed framework. The results demonstrated the superior performance of the proposed framework over state-of-art approaches. Furthermore, experimental findings regarding the ICOA optimization algorithm affirm its efficacy in optimizing the hyperparameters of SVR model, thereby enhancing both prediction accuracy and computational efficiency, surpassing existing algorithms. [ABSTRACT FROM AUTHOR]

In this research, we use several machine learning methods and feature selection to process social media data, namely restaurant reviews. The selection feature used is a combination of information gain (IG) and adaptive boosting (AdaBoost) which is used to see its effect on the classification performance evaluation value of machine learning methods such as Naive Bayes (NB), K-nearest neighbor (KNN), and random forest (RF) which is the aim of this research. NB is very simple and efficient and very sensitive to feature selection. Meanwhile, KNN is known for its weaknesses such as biased k values, overly complex computation, memory limitations, and ignoring irrelevant attributes. Then RF has weaknesses, including that the evaluation value can change significantly with only small data changes. In text classification, feature selection can improve the scalability, efficiency and accuracy of text classification. Based on tests that have been carried out on several machine learning methods and a combination of the two selection features, it was found that the best classifier is the RF algorithm. RF produces a significant increase in value after using the IG and AdaBoost features. Increased accuracy by 10%, precision by 12.43%, recall by 8.14% and F1-score by 10.37%. RF also produces even accuracy, precision, recall, and F1-score values after using IG and AdaBoost with an accuracy value of 84.5%; precision of 85.58%; recall was 86.36%; and F1-score was 85.97%. [ABSTRACT FROM AUTHOR]

With the increasing variation of the network topology and the high complexity of the processing measurement data, the transient voltage stability assessment of the new power system is facing significant challenges in low accuracy and high time costs. To address the shortcomings of the existing method and apply it to online assessment, this paper proposes an assessment method based on feature learning for disturbance signal energy (DSE) from bus voltages. Firstly, the relationship between DSE and system transient voltage stability is established, and the calculation of DSE from bus voltage time series is detailed. Subsequently, a transient voltage stability assessment method based on the ID3 Decision Tree algorithm and DSE is proposed. Finally, by employing the Support Vector Machine (SVM) to construct the optimal boundary in the feature space formed by the key buses, the transient voltage stability margin (TVSM) for specific scenarios is proposed. Simulation results on the IEEE 39-bus system demonstrate that the proposed method can rapidly and accurately assess the transient voltage stability of the system and calculate the stability margin, providing intuitive and interpretable results with high engineering application value. [ABSTRACT FROM AUTHOR]

ABSTRACT To address the challenges of extracting features from complex industrial process data, the reliance of numerous fault detection methodologies on presupposed data distribution types, and the limited generalization capacity of fault detection, this manuscript introduces a sophisticated algorithm for industrial process fault detection. This algorithm harnesses the information gain adaptive (IGA) technique for feature selection and a synergistic model decision mechanism. Initially, the process involves the computation of information gain via decision trees, coupled with the determination of the k$$ k $$ value through cross‐validation. This strategy enables the adaptive selection of features, thereby facilitating data dimensionality reduction and effective feature extraction. The subsequent phase introduces a ternary statistical measure monitoring group for the detection of linear faults, while autoencoders and one‐class SVM methodologies are applied for the monitoring of nonlinear faults. The culmination of this approach is the development of an innovative weighted decision mechanism, designed to amalgamate the findings from both linear and nonlinear detection avenues, yielding more dependable detection results. The validation of this algorithm employs datasets from the water chillers process and Tennessee Eastman (TE) process, demonstrating the IGA‐combined model's superior performance over isolated linear or nonlinear detection algorithms in terms of detection accuracy and robustness. Notably, the efficacy of this method is not contingent upon specific assumptions regarding data distribution, rendering it a versatile and efficacious tool for the fault detection in industrial processes. [ABSTRACT FROM AUTHOR]

This study harnesses RNA sequencing data from the Cancer Genome Atlas to unearth pivotal genetic markers linked to the progression of liver hepatocellular carcinoma (LIHC), a major contributor to cancer-related deaths worldwide, characterized by a dire prognosis and limited treatment avenues. We employ advanced feature selection techniques, including sure independence screening (SIS) combined with the least absolute shrinkage and selection operator (Lasso), smoothly clipped absolute deviation (SCAD), information gain (IG), and permutation variable importance (VIMP) methods, to effectively navigate the challenges posed by ultra-high-dimensional data. Through these methods, we identify critical genes like MED8 as significant markers for LIHC. These markers are further analyzed using advanced survival analysis models, including the Cox proportional hazards model, survival tree, and random survival forests. Our findings reveal that SIS-Lasso demonstrates strong predictive accuracy, particularly in combination with the Cox proportional hazards model. However, when coupled with the random survival forests method, the SIS-VIMP approach achieves the highest overall performance. This comprehensive approach not only enhances the prediction of LIHC outcomes but also provides valuable insights into the genetic mechanisms underlying the disease, thereby paving the way for personalized treatment strategies and advancing the field of cancer genomics. [ABSTRACT FROM AUTHOR]

Breast cancer (BC) stands as the most prevalent form of cancer among women and is one of the primary causes of mortality worldwide. With recent advances in genomic research, precision medicine is now being used to treat BC. This study proposes a new Adaptive gene selection-enabled fine-tuned ensemble learning algorithm for BC prediction using Genomic data. We design an information gain-adaptive Northern Goshawk Optimization (IG-ANGO) based feature selection algorithm that uses inertia weights to improve the algorithm's search efficiency and accelerate convergence to optimal solutions. In addition, the Information Gain (IG) based ANGO method, uses ranking data to enhance the quality of selecting key features. The algorithm then employs the Crossover Greylag Goose Optimization (CGGO) algorithm to randomly generate individuals to recommend ideal solutions (i.e. hyperparameter configurations) to the ensemble model. The goal of an ensemble-based classification method is to generate a method with superior predictive capability. The final prediction result is determined by weighted voting based on the prediction probability results. Our experiments demonstrate that our method enhances the classifier's performance compared to other existing methods. The result obtained by our model demonstrates the highest classification accuracy at 99.84%. The proposed approach thus opens the possibility of new chances in BC prediction with Genomic data. [ABSTRACT FROM AUTHOR]

Renewable energy accommodation in power grids leads to frequent load changes in power plants. Sensitive turbine fault monitoring technology is critical to ensure the stable operation of the power system. Existing techniques do not use information sufficiently and are not sensitive to early fault signs. To solve this problem, an unsupervised fault warning method based on hybrid information gain and a convolutional autoencoder (CAE) for turbine intermediate flux is proposed. A high-precision intermediate-stage flux prediction model is established using the CAE. The hybrid information gain calculation method is proposed to filter the features of multi-dimensional sensors. The Hampel filter for time series outlier detection is introduced to deal with factors such as sensor faults and noise. The proposed method achieves the highest fault diagnosis accuracy through experiments on real data compared to traditional methods. Real data experiments show that the proposed method relatively improves the diagnostic accuracy by an average of 2.12% compared to the gate recurrent unit networks, long short-term memory networks, and other traditional models. Meanwhile, the proposed hybrid information gain can effectively improve the detection accuracy of the traditional models, with a maximum of 1.89% relative accuracy improvement. The proposed method is noteworthy for its superiority and applicability. [ABSTRACT FROM AUTHOR]

With the rapid advancement of the Internet of Things, network security has garnered increasing attention from researchers. Applying deep learning (DL) has significantly enhanced the performance of Network Intrusion Detection Systems (NIDSs). However, due to its complexity and "black box" problem, deploying DL-based NIDS models in practical scenarios poses several challenges, including model interpretability and being lightweight. Feature selection (FS) in DL models plays a crucial role in minimizing model parameters and decreasing computational overheads while enhancing NIDS performance. Hence, selecting effective features remains a pivotal concern for NIDSs. In light of this, this paper proposes an interpretable feature selection method for encrypted traffic intrusion detection based on SHAP and causality principles. This approach utilizes the results of model interpretation for feature selection to reduce feature count while ensuring model reliability. We evaluate and validate our proposed method on two public network traffic datasets, CICIDS2017 and NSL-KDD, employing both a CNN and a random forest (RF). Experimental results demonstrate superior performance achieved by our proposed method. [ABSTRACT FROM AUTHOR]

As a severe inflammatory response syndrome, sepsis presents complex challenges in predicting patient outcomes due to its unclear pathogenesis and the unstable discharge status of affected individuals. In this study, we develop a machine learning-based method for predicting the discharge status of sepsis patients, aiming to improve treatment decisions. To enhance the robustness of our analysis against outliers, we incorporate robust statistical methods, specifically the minimum covariance determinant technique. We utilize the random forest imputation method to effectively manage and impute missing data. For feature selection, we employ Lasso penalized logistic regression, which efficiently identifies significant predictors and reduces model complexity, setting the stage for the application of more complex predictive methods. Our predictive analysis incorporates multiple machine learning methods, including random forest, support vector machine, and XGBoost. We compare the prediction performance of these methods with Lasso penalized logistic regression to identify the most effective approach. Each method's performance is rigorously evaluated through ten iterations of 10-fold cross-validation to ensure robust and reliable results. Our comparative analysis reveals that XGBoost surpasses the other models, demonstrating its exceptional capability to navigate the complexities of sepsis data effectively. [ABSTRACT FROM AUTHOR]

In this paper, we are concerned with the process of experimental information gain. Building on previous work, we show that this is a discontinuous process in which the initiating quantum-mechanical matter–instrument interactions are being turned into macroscopically observable events (EOs). In the course of time, such EOs evolve into spatio-temporal patterns of EOs, which allow conceivable alternatives of physical explanation to be distinguished. Focusing on the specific case of photon detection, we show that during their lifetimes, EOs proceed through the four phases of initiation, detection, erasure and reset. Once generated, the observational value of EOs can be measured in units of the Planck quantum of physical action h = 4.136 × 10 − 15 e V s . Once terminated, each unit of entropy of size k B = 8.617 × 10 − 5 e V / K , which had been created in the instrument during the observational phase, needs to be removed from the instrument to ready it for a new round of photon detection. This withdrawal of entropy takes place at an energetic cost of at least two units of the Landauer minimum energy bound of E L a = ln ⁡ 2 k B T D for each unit of entropy of size k B . [ABSTRACT FROM AUTHOR]

Credit risk prediction is a binary classification problem. Using two‐way decisions to classify defaulters may lead to decision errors due to insufficient information. To solve this issue, in addition to identifying borrowers as defaulters and nondefaulters, this paper introduced the delay‐decision mechanism in three‐way decisions, so that records acquiring more information do not make decisions immediately. A two‐stage credit risk prediction framework based on three‐way decisions was proposed to reduce decision risk. In this framework, the decision cost values of three‐way decisions were simplified by analyzing the credit risk prediction, and the expression of threshold calculation was also modified. An optimization objective was built according to the trade‐off between information gain and decision cost, and the particle swarm optimization algorithm was applied to learn the decision thresholds. After adding more supplementary information, the samples in the delayed‐decision region were made further decisions. A dataset from a commercial bank in China was employed to conduct experiments, and the results demonstrated that our proposed method outperformed various base classifiers. [ABSTRACT FROM AUTHOR]

The development and evaluation of novel treatment combinations is a key component of modern clinical research. The primary goals of factorial clinical trials of treatment combinations range from the estimation of intervention-specific effects, or the discovery of potential synergies, to the identification of combinations with the highest response probabilities. Most factorial studies use balanced or block randomization, with an equal number of patients assigned to each treatment combination, irrespective of the specific goals of the trial. Here, we introduce a class of Bayesian response-adaptive designs for factorial clinical trials with binary outcomes. The study design was developed using Bayesian decision-theoretic arguments and adapts the randomization probabilities to treatment combinations during the enrollment period based on the available data. Our approach enables the investigator to specify a utility function representative of the aims of the trial, and the Bayesian response-adaptive randomization algorithm aims to maximize this utility function. We considered several utility functions and factorial designs tailored to them. Then, we conducted a comparative simulation study to illustrate relevant differences of key operating characteristics across the resulting designs. We also investigated the asymptotic behavior of the proposed adaptive designs. We also used data summaries from three recent factorial trials in perioperative care, smoking cessation, and infectious disease prevention to define realistic simulation scenarios and illustrate advantages of the introduced trial designs compared to other study designs. [ABSTRACT FROM AUTHOR]

K-nearest neighbors (kNN) is a popular machine learning algorithm because of its clarity, simplicity, and efficacy. kNN has numerous drawbacks, including ignoring issues like class distribution, feature relevance, neighbor contribution, and the number of individuals for each class. In particular, some features could be more important than others for classifying a data point, and increasing their weight in the distance computation can make the kNN algorithm more accurate. Researchers propose different feature weightings, such as correlation-based feature selection, mutual information, and chi-square feature selection. This paper presents a new feature weighting technique based on association rules and information gain. The proposed approach gives a good performance compared to other similar methods. [ABSTRACT FROM AUTHOR]

Network Intrusion Detection System (NIDS) plays a major role in maintaining the integrity and security in computer networks. These systems are created to detect and acknowledge the anomalous activities which specify unauthorized access and malicious internet. Establishing effective NIDS can be difficult, especially identifying network anomalies among the ever-increasing and difficult-to-detect malicious attacks. This study, implemented the Information gain with Deep Bidirectional Long Short-Term Memory (IG-Deep BiLSTM) method utilized to identify the effective intrusions, which will enable an NIDS to gain access to more data. The implemented BiLSTM method can better extract long-term and short-term dependent features and improve classification accuracy. The datasets used to gather data are the ToN-IoT, CIC-IDS-2017, BoT-IoT, and UNSW_NB-15 datasets. Next, pre-processing includes data digitization and encoding, as well as data normalization to convert the actual data into a suitable format and remove noise from the data. The IG is used to select the optimal features, and then the Deep BiLSTM is utilized to classify the network intrusion attacks as normal or malicious. Compared with existing methods, the implemented method achieved high accuracy values of 99.95%, 99.95%, 99.50%, and 99.93% using the CIC-IDS-2017, ToN-IoT, BoT-IoT, and UNSW_NB-15 datasets. [ABSTRACT FROM AUTHOR]

Research on the development of active learning and information search behaviors has been growing rapidly, drawing interest from multiple disciplines, from developmental psychology to cognitive science and artificial intelligence. These different perspectives can open pathways to understanding how preschool‐age children grow into adaptive and efficient active learners. However, the lack of a shared vocabulary, operationalizations, and research paradigms has led to limited cross‐talk and some conflicting findings. In this article, we advocate for using a shared operationalization of a "good" information‐search strategy, as a function of its efficiency and effectiveness within a given ecology, based on the information‐theoretic measure of expected information gain and observed behavioral outcomes, respectively. We also discuss factors that should be considered when designing experiments that examine children's information‐search competence, specifically, using formal models as performance benchmarks and accounting for children's prior knowledge, assumptions, and self‐generated goals. [ABSTRACT FROM AUTHOR]

Abstract Background The blood–brain barrier serves as a critical interface between the bloodstream and brain tissue, mainly composed of pericytes, neurons, endothelial cells, and tightly connected basal membranes. It plays a pivotal role in safeguarding brain from harmful substances, thus protecting the integrity of the nervous system and preserving overall brain homeostasis. However, this remarkable selective transmission also poses a formidable challenge in the realm of central nervous system diseases treatment, hindering the delivery of large-molecule drugs into the brain. In response to this challenge, many researchers have devoted themselves to developing drug delivery systems capable of breaching the blood–brain barrier. Among these, blood–brain barrier penetrating peptides have emerged as promising candidates. These peptides had the advantages of high biosafety, ease of synthesis, and exceptional penetration efficiency, making them an effective drug delivery solution. While previous studies have developed a few prediction models for blood–brain barrier penetrating peptides, their performance has often been hampered by issue of limited positive data. Results In this study, we present Augur, a novel prediction model using borderline-SMOTE-based data augmentation and machine learning. we extract highly interpretable physicochemical properties of blood–brain barrier penetrating peptides while solving the issues of small sample size and imbalance of positive and negative samples. Experimental results demonstrate the superior prediction performance of Augur with an AUC value of 0.932 on the training set and 0.931 on the independent test set. Conclusions This newly developed Augur model demonstrates superior performance in predicting blood–brain barrier penetrating peptides, offering valuable insights for drug development targeting neurological disorders. This breakthrough may enhance the efficiency of peptide-based drug discovery and pave the way for innovative treatment strategies for central nervous system diseases.

Attribute reduction is a core technique in the rough set domain and an important step in data preprocessing. Researchers have proposed numerous innovative methods to enhance the capability of attribute reduction, such as the emergence of multi-granularity rough set models, which can effectively process distributed and multi-granularity data. However, these innovative methods still have numerous shortcomings, such as addressing complex constraints and conducting multi-angle effectiveness evaluations. Based on the multi-granularity model, this study proposes a new method of attribute reduction, namely using multi-granularity neighborhood information gain ratio as the measurement criterion. This method combines both supervised and unsupervised perspectives, and by integrating multi-granularity technology with neighborhood rough set theory, constructs a model that can adapt to multi-level data features. This novel method stands out by addressing complex constraints and facilitating multi-perspective effectiveness evaluations. It has several advantages: (1) it combines supervised and unsupervised learning methods, allowing for nuanced data interpretation and enhanced attribute selection; (2) by incorporating multi-granularity structures, the algorithm can analyze data at various levels of granularity. This allows for a more detailed understanding of data characteristics at each level, which can be crucial for complex datasets; and (3) by using neighborhood relations instead of indiscernibility relations, the method effectively handles uncertain and fuzzy data, making it suitable for real-world datasets that often contain imprecise or incomplete information. It not only selects the optimal granularity level or attribute set based on specific requirements, but also demonstrates its versatility and robustness through extensive experiments on 15 UCI datasets. Comparative analyses against six established attribute reduction algorithms confirms the superior reliability and consistency of our proposed method. This research not only enhances the understanding of attribute reduction mechanisms, but also sets a new benchmark for future explorations in the field. [ABSTRACT FROM AUTHOR]

A measurement performed on a quantum system is an act of gaining information about its state. However, in the foundations of quantum theory, the concept of information is multiply defined, particularly in the area of quantum reconstruction, and its conceptual foundations remain surprisingly under-explored. In this paper, we investigate the gain of information in quantum measurements from an operational viewpoint in the special case of a two-outcome probabilistic source. We show that the continuous extension of the Shannon entropy naturally admits two distinct measures of information gain, differential information gain and relative information gain, and that these have radically different characteristics. In particular, while differential information gain can increase or decrease as additional data are acquired, relative information gain consistently grows and, moreover, exhibits asymptotic indifference to the data or choice of Bayesian prior. In order to make a principled choice between these measures, we articulate a Principle of Information Increase, which incorporates a proposal due to Summhammer that more data from measurements leads to more knowledge about the system, and also takes into consideration black swan events. This principle favours differential information gain as the more relevant metric and guides the selection of priors for these information measures. Finally, we show that, of the symmetric beta distribution priors, the Jeffreys binomial prior is the prior that ensures maximal robustness of information gain for the particular data sequence obtained in a run of experiments. [ABSTRACT FROM AUTHOR]

Traffic state classification and relevance calculation at intersections are both difficult problems in traffic control. In this paper, we propose an intersection relevance model based on a temporal graph attention network, which can solve the above two problems at the same time. First, the intersection features and interaction time of the intersections are regarded as input quantities together with the initial labels of the traffic data. Then, they are inputted into the temporal graph attention (TGAT) model to obtain the classification accuracy of the target intersections in four states—free, stable, slow moving, and congested—and the obtained neighbouring intersection weights are used as the correlation between the intersections. Finally, it is validated by VISSIM simulation experiments. In terms of classification accuracy, the TGAT model has a higher classification accuracy than the three traditional classification models and can cope well with the uneven distribution of the number of samples. The information gain algorithm from the information entropy theory was used to derive the average delay as the most influential factor on intersection status. The correlation from the TGAT model positively correlates with traffic flow, making it interpretable. Using this correlation to control the division of subareas improves the road network's operational efficiency more than the traditional correlation model does. This demonstrates the effectiveness of the TGAT model's correlation. [ABSTRACT FROM AUTHOR]

Music resources are characterized by quantization, diversification and complication. With the rapid increase of the demand for music resources, the storage of music resources is very large. In order to improve the retrieval effect of music resources, a massive music resources retrieval method based on ant colony algorithm is proposed to effectively use music resources. This paper constructs autocorrelation function to extract pitch feature of music resource, classifies the music resource information by calculating feature similarity. Using ant colony algorithm to correlate the feature of music resource, gain the result of correlative, locate the result of detection and get the result of multi-module. Simulation results show that the proposed method has high precision and recall, short retrieval time and can effectively retrieve massive music resources. [ABSTRACT FROM AUTHOR]

In order to enhance the accuracy of Air Traffic Control (ATC) cybersecurity attack detection, in this paper, a new clustering detection method is designed for air traffic control network security attacks. The feature set for ATC cybersecurity attacks is constructed by setting the feature states, adding recursive features, and determining the feature criticality. The expected information gain and entropy of the feature data are computed to determine the information gain of the feature data and reduce the interference of similar feature data. An autoencoder is introduced into the AI (artificial intelligence) algorithm to encode and decode the characteristics of ATC network security attack behavior to reduce the dimensionality of the ATC network security attack behavior data. Based on the above processing, an unsupervised learning algorithm for clustering detection of ATC network security attacks is designed. First, determine the distance between the clustering clusters of ATC network security attack behavior characteristics, calculate the clustering threshold, and construct the initial clustering center. Then, the new average value of all feature objects in each cluster is recalculated as the new cluster center. Second, it traverses all objects in a cluster of ATC network security attack behavior feature data. Finally, the cluster detection of ATC network security attack behavior is completed by the computation of objective functions. The experiment took three groups of experimental attack behavior data sets as the test object, and took the detection rate, false detection rate and recall rate as the test indicators, and selected three similar methods for comparative test. The experimental results show that the detection rate of this method is about 98%, the false positive rate is below 1%, and the recall rate is above 97%. Research shows that this method can improve the detection performance of security attacks in air traffic control network. [ABSTRACT FROM AUTHOR]

Background: The blood–brain barrier serves as a critical interface between the bloodstream and brain tissue, mainly composed of pericytes, neurons, endothelial cells, and tightly connected basal membranes. It plays a pivotal role in safeguarding brain from harmful substances, thus protecting the integrity of the nervous system and preserving overall brain homeostasis. However, this remarkable selective transmission also poses a formidable challenge in the realm of central nervous system diseases treatment, hindering the delivery of large-molecule drugs into the brain. In response to this challenge, many researchers have devoted themselves to developing drug delivery systems capable of breaching the blood–brain barrier. Among these, blood–brain barrier penetrating peptides have emerged as promising candidates. These peptides had the advantages of high biosafety, ease of synthesis, and exceptional penetration efficiency, making them an effective drug delivery solution. While previous studies have developed a few prediction models for blood–brain barrier penetrating peptides, their performance has often been hampered by issue of limited positive data. Results: In this study, we present Augur, a novel prediction model using borderline-SMOTE-based data augmentation and machine learning. we extract highly interpretable physicochemical properties of blood–brain barrier penetrating peptides while solving the issues of small sample size and imbalance of positive and negative samples. Experimental results demonstrate the superior prediction performance of Augur with an AUC value of 0.932 on the training set and 0.931 on the independent test set. Conclusions: This newly developed Augur model demonstrates superior performance in predicting blood–brain barrier penetrating peptides, offering valuable insights for drug development targeting neurological disorders. This breakthrough may enhance the efficiency of peptide-based drug discovery and pave the way for innovative treatment strategies for central nervous system diseases. [ABSTRACT FROM AUTHOR]

The concept of entropy and information gain of BE-algebras in scientific disciplines such as information theory, data science, supply chain and machine learning assists us to calculate the uncertanity of the scientific processes of phenomena. In this respect the notion of filter entropy for a transitive BE-algebra is introduced and its properties are investigated. The notion of a dynamical system on a transitive BE-algebra is introduced. The concept of the entropy for a transitive BE-algebra dynamical system is developed and, its characteristics are considered. The notion of equivalent transitive BE-algebra dynamical systems is defined, and it is proved the fact that two equivalent BE-algebra dynamical systems have the same entropy. Theorems to help calculate the entropy are given. Specifically, a new version of Kolmogorov– Sinai Theorem has been proved. The study introduces the concept of information gain of a transitive BE-algebra with respect to its filters and investigates its properties. This study proposes the use of filter entropy to approximate the level of risk introduced by a BE-algebra dynamical system. This aim is reached by defining the information gain with respect to the filters of a BE-algebra. This methodology is well developed for use in engineering, especially in industrial networks. This paper proposes a novel approach to assess the quantity of uncertainty, and the impact of information gain of a BE-algebra dynamical system. [ABSTRACT FROM AUTHOR]

Early-stage prediction of a disease is an important and challenging task. The application of machine learning techniques is playing an important role in this era. Thyroid is one of the chronic endocrine diseases, and approximately 42 million people in India are affected by this disease. This paper presents a comprehensive investigation into the enhancement of classification performance through the novel 'FeatureBoostThyro' (FBT) model. The study evaluates various machine learning algorithms, including stochastic gradient descent (SGD), K nearest neighbor (KNN), logistic regression (LR), naive bayes (NB), and support vector machine (SVM), in conjunction with diverse feature selection methods. The research systematically explores the impact of feature selection techniques such as information gain, relief F, chi-square, gini index, forward selection, backward selection, recursive feature elimination, and LASSO on model performance across the chosen algorithms. The analysis reveals notable variations in performance metrics, including accuracy, precision, recall, and F1-score, providing valuable insights into the interplay between algorithm and feature selection. One main contribution of this research is the introduction of the FBT model, which consistently outperforms other models across various feature selection methods, making it a promising tool for addressing complex classification tasks. The findings contribute to a broader understanding of model selection and optimization in machine learning applications. The proposed model undergoes evaluation using two distinct datasets: the primary dataset acquired from Lata Mangeshkar Hospital in Nagpur and the secondary dataset obtained from the UCI dataset. [ABSTRACT FROM AUTHOR]

Bayesian inference typically focuses upon two issues. The first is estimating the parameters of some model from data, and the second is quantifying the evidence for alternative hypotheses—formulated as alternative models. This paper focuses upon a third issue. Our interest is in the selection of data—either through sampling subsets of data from a large dataset or through optimising experimental design—based upon the models we have of how those data are generated. Optimising data-selection ensures we can achieve good inference with fewer data, saving on computational and experimental costs. This paper aims to unpack the principles of active sampling of data by drawing from neurobiological research on animal exploration and from the theory of optimal experimental design. We offer an overview of the salient points from these fields and illustrate their application in simple toy examples, ranging from function approximation with basis sets to inference about processes that evolve over time. Finally, we consider how this approach to data selection could be applied to the design of (Bayes-adaptive) clinical trials. [ABSTRACT FROM AUTHOR]

It is argued that all physical knowledge ultimately stems from observation and that the simplest possible observation is that an event has happened at a certain space–time location X → = x → , t . Considering historic experiments, which have been groundbreaking in the evolution of our modern ideas of matter on the atomic, nuclear, and elementary particle scales, it is shown that such experiments produce as outputs streams of macroscopically observable events which accumulate in the course of time into spatio-temporal patterns of events whose forms allow decisions to be taken concerning conceivable alternatives of explanation. Working towards elucidating the physical and informational characteristics of those elementary observations, we show that these represent hugely amplified images of the initiating micro-events and that the resulting macro-images have a cognitive value of 1 bit and a physical value of W o b s = E o b s τ o b s ≫ h . In this latter equation, E o b s stands for the energy spent in turning the initiating micro-events into macroscopically observable events, τ o b s for the lifetimes during which the generated events remain macroscopically observable, and h for Planck's constant. The relative value G o b s = W o b s / h finally represents a measure of amplification that was gained in the observation process. [ABSTRACT FROM AUTHOR]

This study addressed the complex challenges associated with landslide detection along the Karakoram Highway (KKH), where tectonic events and data availability limitations posed significant obstacles. To overcome these hurdles, the research framework encompassed several critical components. First, it tackled the issue of multicollinearity through the application of statistical measures such as Variable Inflation Factor (VIF) and Information Gain (IG). Secondly, the study emphasized the importance of selecting a study area that would comprehensively represent the multivariate landscape, with KKH serving as an illustrative example. In striving for an equilibrium between implementation ease and algorithmic performance, the research favored the adoption of Random Forest (RF) and Extremely Randomized Trees (EXT) over XGBoost. Lastly, to fine-tune the algorithms and optimize their parameters, the study employed Particle Swarm Optimization (PSO) and evaluated their performance using metrics like the Area Under the Curve (AUC). Remarkably, this comprehensive approach yielded accuracy rates exceeding 90% for all algorithms tested (RF, EXT, and K-Nearest Neighbor (KNN)), with specific AUC values of 0.967, 0.968, and 0.914, respectively. These findings offer invaluable insights into enhancing disaster prevention strategies and informing land-use planning efforts along the KKH highway.

Background & aimsLiver disease carries significant healthcare burden and frequently requires a combination of blood tests, imaging, and invasive liver biopsy to diagnose. Distinguishing between inflammatory liver diseases, which may have similar clinical presentations, is particularly challenging. In this study, we implemented a machine learning pipeline for the identification of diagnostic gene expression biomarkers across several alcohol-associated and non-alcohol-associated liver diseases, using either liver tissue or blood-based samples.MethodsWe collected peripheral blood mononuclear cells (PBMCs) and liver tissue samples from participants with alcohol-associated hepatitis (AH), alcohol-associated cirrhosis (AC), non-alcohol-associated fatty liver disease, chronic HCV infection, and healthy controls. We performed RNA sequencing (RNA-seq) on 137 PBMC samples and 67 liver tissue samples. Using gene expression data, we implemented a machine learning feature selection and classification pipeline to identify diagnostic biomarkers which distinguish between the liver disease groups. The liver tissue results were validated using a public independent RNA-seq dataset. The biomarkers were computationally validated for biological relevance using pathway analysis tools.ResultsUtilizing liver tissue RNA-seq data, we distinguished between AH, AC, and healthy conditions with overall accuracies of 90% in our dataset, and 82% in the independent dataset, with 33 genes. Distinguishing 4 liver conditions and healthy controls yielded 91% overall accuracy in our liver tissue dataset with 39 genes, and 75% overall accuracy in our PBMC dataset with 75 genes.ConclusionsOur machine learning pipeline was effective at identifying a small set of diagnostic gene biomarkers and classifying several liver diseases using RNA-seq data from liver tissue and PBMCs. The methodologies implemented and genes identified in this study may facilitate future efforts toward a liquid biopsy diagnostic for liver diseases.Lay summaryDistinguishing between inflammatory liver diseases without multiple tests can be challenging due to their clinically similar characteristics. To lay the groundwork for the development of a non-invasive blood-based diagnostic across a range of liver diseases, we compared samples from participants with alcohol-associated hepatitis, alcohol-associated cirrhosis, chronic hepatitis C infection, and non-alcohol-associated fatty liver disease. We used a machine learning computational approach to demonstrate that gene expression data generated from either liver tissue or blood samples can be used to discover a small set of gene biomarkers for effective diagnosis of these liver diseases.

Unmanned aerial vehicles (UAVs) are increasingly being deployed in crucial missions for the armed forces, law enforcement, industrial control monitoring, and other sectors. However, these hostile operating circumstances, along with the UAVs’ dependence on wireless protocols, pose substantial security threats, limiting their mainstream application. With network security being such a major issue for UAV networks, the machine learning-based intrusion detection system (IDS) has been determined to be an effective strategy for protecting them. Additionally, though the existing methods offer effective strategies for detecting and categorizing abnormalities in the system, they are limited by their inability to adjust to various attack patterns. The dataset used as well as the memory and computational requirement of existing models, poses new challenges. One of the main concerns pertains to the reduced computational and memory demands of these models. So, the work carried out in this paper addresses this challenge. A new dimensional reduction technique based on correlation coefficient, information gain, and principal component analysis (PCA) is introduced to reduce the dimensionality of the UAV Attack Dataset. A novel intrusion detection system based on an artificial neural network (ANN) and genetic algorithm (GA) is then proposed. The genetic algorithm is used to generate the optimal weights of the artificial neural network. A comparison is made between the proposed model and the backpropagation network and its variant in terms of its convergence and prediction accuracy. Furthermore, the performance of the proposed model is compared with that of other classifiers. This comparison reveals that the proposed model is time efficient with an increased prediction accuracy of at least 6% more than other classifiers.

This study harnesses RNA sequencing data from the Cancer Genome Atlas to unearth pivotal genetic markers linked to the progression of liver hepatocellular carcinoma (LIHC), a major contributor to cancer-related deaths worldwide, characterized by a dire prognosis and limited treatment avenues. We employ advanced feature selection techniques, including sure independence screening (SIS) combined with the least absolute shrinkage and selection operator (Lasso), smoothly clipped absolute deviation (SCAD), information gain (IG), and permutation variable importance (VIMP) methods, to effectively navigate the challenges posed by ultra-high-dimensional data. Through these methods, we identify critical genes like MED8 as significant markers for LIHC. These markers are further analyzed using advanced survival analysis models, including the Cox proportional hazards model, survival tree, and random survival forests. Our findings reveal that SIS-Lasso demonstrates strong predictive accuracy, particularly in combination with the Cox proportional hazards model. However, when coupled with the random survival forests method, the SIS-VIMP approach achieves the highest overall performance. This comprehensive approach not only enhances the prediction of LIHC outcomes but also provides valuable insights into the genetic mechanisms underlying the disease, thereby paving the way for personalized treatment strategies and advancing the field of cancer genomics.

Behavioural asymmetries displayed by individuals, such as hand preference and foot preference, tend to be lateralized in the same direction (left or right). This may be because their co-ordination conveys functional benefits for a variety of motor behaviours. To explore the potential functional relationship between key motor asymmetries, we examined whether footedness, handedness, or throwing arm was the strongest predictor of eyedness. Behavioural asymmetries were measured by self-report in 578 left-handed and 612 right-handed individuals. Cluster analysis of the asymmetries revealed four handedness groups: consistent right-handers, left-eyed right-handers, consistent left-handers, and inconsistent left-handers (who were left-handed but right-lateralized for footedness, throwing and eyedness). Supervised machine learning models showed the importance of footedness, in addition to handedness, in determining eyedness. In right-handers, handedness was the best predictor of eyedness, followed closely by footedness, and for left-handers it was footedness. Overall, predictors were more informative in predicting eyedness for individuals with consistent lateral preferences. Implications of the findings in relation to the origins and genetics of handedness and sports training are discussed. Findings are related to fighting theories of handedness and to bipedalism, which evolved after manual dexterity, and which may have led to some humans being right-lateralized for ballistic movements and left-lateralized for hand dexterity. [ABSTRACT FROM AUTHOR]

The use of online movie streaming media has increased significantly, particularly among movie enthusiasts. However, fan comments are frequently informal and comprise informal language, subjectivity, and contexts that reflect their preferences. A significant challenge in sentiment analysis of movie reviews is how to classify sentiments in reviews that are often unstructured and subjective. This study aims to improve the accuracy of sentiment classification in movie reviews by proposing several methods, including a hybrid TF-IDF+N-Gram model that can extract pertinent information from word and phrase sequences in reviews. Then, feature selection with Information Gain (IG) is performed to identify the most informative sentiment classification features. This strategy seeks to overcome informal language and noise to improve review context comprehension. The results demonstrated a significant gain in the accuracy of sentiment classification. TFIDF+Bigram+IG achieved 78% accuracy (up 8% from 70% previously), and TFIDF+Trigram+IG achieved 66% accuracy (up 22% from 44% previously). Using this hybrid model, the study significantly enhanced the accuracy of sentiment classification, thereby enhancing the performance of SVM in the face of complex movie evaluations. [ABSTRACT FROM AUTHOR]

There generally exists a critical state or tipping point from a stable state to another in the development of colorectal cancer (CRC) beyond which a significant qualitative transition occurs. Gut microbiome sequencing data can be collected non-invasively from fecal samples, making it more convenient to obtain. Furthermore, intestinal microbiome sequencing data contain phylogenetic information at various levels, which can be used to reliably identify critical states, thereby providing early warning signals more accurately and effectively. Yet, pinpointing the critical states using gut microbiome data presents a formidable challenge due to the high dimension and strong noise of gut microbiome data. To address this challenge, we introduce a novel approach termed the specific network information gain (SNIG) method to detect CRC's critical states at various taxonomic levels via gut microbiome data. The numerical simulation indicates that the SNIG method is robust under different noise levels and that it is also superior to the existing methods on detecting the critical states. Moreover, utilizing SNIG on two real CRC datasets enabled us to discern the critical states preceding deterioration and to successfully identify their associated dynamic network biomarkers at different taxonomic levels. Notably, we discovered certain 'dark species' and pathways intimately linked to CRC progression. In addition, we accurately detected the tipping points on an individual dataset of type I diabetes. [ABSTRACT FROM AUTHOR]

What drives children to explore and learn when external rewards are uncertain or absent? Across three studies, we tested whether information gain itself acts as an internal reward and suffices to motivate children's actions. We measured 24–56‐month‐olds' persistence in a game where they had to search for an object (animal or toy), which they never find, hidden behind a series of doors, manipulating the degree of uncertainty about which specific object was hidden. We found that children were more persistent in their search when there was higher uncertainty, and therefore, more information to be gained with each action, highlighting the importance of research on artificial intelligence to invest in curiosity‐driven algorithms. Research Highlights: Across three studies, we tested whether information gain itself acts as an internal reward and suffices to motivate preschoolers' actions.We measured preschoolers' persistence when searching for an object behind a series of doors, manipulating the uncertainty about which specific object was hidden.We found that preschoolers were more persistent when there was higher uncertainty, and therefore, more information to be gained with each action.Our results highlight the importance of research on artificial intelligence to invest in curiosity‐driven algorithms. [ABSTRACT FROM AUTHOR]

Accidents of leaks and emissions of flammable, explosive, and toxic substances severely threaten people's health and public safety. Traditional heuristic algorithms for source localization that utilize wind information to guide the robots to search for plumes in the airflow environment, substantial potential plume information is not fully considered, reducing the success rate and precision of source localization. To solve this problem, in this study, we propose a novel strategy for plume source localization using information gain. This strategy is inspired by the navigation and foraging behaviors of the salps in the ocean, and the robots use a mutation random salp swarm algorithm to track the plume. This strategy utilizes the Dirichlet process Gaussian mixture model to color the plume information and achieve a dynamic update of the plume information distribution. Therefore, this developed strategy provides potential source location clues for the robots, dynamically adjusting the robots' search behaviors and enhancing the source-seeking success rate and efficiency. This strategy is verified by experimental validations. The test results show that with two methods that use wind information, namely, the improved whale optimization algorithm and wind utilization II particle swarm optimization, and two approaches independent of wind information, namely, the fixed-step fruit fly optimization algorithm and improved particle swarm optimization, the proposed strategy improves the source localization success rate by 5% to 33% and accelerates the efficiency by 0.1 to 2.6 times in the obstacle-free scenario, and improves the source localization success rate by 4% to 100% and accelerates the efficiency by 0.4 to 2.2 times in the obstacle environment. [ABSTRACT FROM AUTHOR]

Over the last few years, Big Data has sparked a lot of interest in a variety of engineering and scientific fields. Despite its numerous advantages, big data presents several issues such as big data management, big data analytics, big data security, and privacy which must be addressed to improve service quality. The proposed method focuses on data preprocessing, feature extraction, and classification. At first, data preprocessing has been performed and the weights have been assigned by the automated weight assignment model. In addition, the feature extraction model applies Principal Component Analysis (PCA) which employs feature correlation at the initial level, with best Information Gain (IG) and time-series data's similarity search with Kernel Dynamic Time Wrapping (DTW) method. On this basis, an Enhanced dynamic KPCA algorithm is introduced by integrating the kernel trick, DTW algorithm, PCA, and information gain. Then Convolutional multi-layer Bi-LSTM algorithms have been applied for classification. To analyze the big data performance, 8 types of datasets such as 32-pendigits, Bank-Marketing, Click Prediction, EEG, Electricity-normalized, Jm1, Magic telescope, and Amazon employee access are used. The performances are evaluated by different metrics with existing methods of LSTM, BRNN, MFC, and DL methods. [ABSTRACT FROM AUTHOR]

The autonomous exploration task we consider requires Unmanned Aerial Vehicles (UAVs) to actively navigate through unknown environments with the goal of fully perceiving and mapping the environments. Some existing exploration strategies suffer from rough cost budgets, ambiguous Information Gain (IG), and unnecessary backtracking exploration caused by Fragmented Regions (FRs). In our work, a hierarchical spatio-temporal-aware exploration framework is proposed to alleviate these problems. At the local exploration level, the Asymmetrical Traveling Salesman Problem (ATSP) is solved by comprehensively considering exploration time, IG, and heading consistency to avoid blindly exploring. Specifically, the exploration time is reasonably budgeted by fast marching in an artificial potential field. Meanwhile, a transformer-based map occupancy predictor is designed to assist in IG calculation by imagining spatial clues out of the Field of View (FoV), facilitating the prescient exploration. We verify that our local exploration is effective in alleviating the unnecessary back-and-forth movements caused by FRs and the interference of potential obstacle occlusion on the IG calculation. At the global exploration level, the classical Next Best View Points (NBVP) are generalized to Next Best Sub-Regions (NBSR) to choose informative sub-regions for further forward-looking exploration based on a well-designed utility function. Safe flight paths and dynamically feasible trajectories are reasonably generated throughout the exploration process by fast marching and B-spline curve optimization. Comparative simulations and benchmark tests demonstrate that our proposed exploration strategy is quite competitive in terms of exploration path length, total exploration time, and exploration ratio. [ABSTRACT FROM AUTHOR]

This article presents the findings of an empirical study on the performance of different distance metrics in machine learning algorithms. The study compares the accuracy rates of various metrics on benchmark datasets and highlights the importance of selecting the right metric for accurate classification. The results show that each metric performs well on datasets that align with its assumptions. The study also discusses the principles of metric spaces and introduces the concept of the No Free Lunch theorems. Overall, the article provides valuable insights into the performance of distance metrics in machine learning. [Extracted from the article]

Theoretical‐information approach applied to the clinical trial designs appeared to bring several advantages when tackling a problem of finding a balance between power and expected number of successes (ENS). In particular, it was shown that the built‐in parameter of the weight function allows finding the desired trade‐off between the statistical power and number of treated patients in the context of small population Phase II clinical trials. However, in real clinical trials, randomized designs are more preferable. The goal of this research is to introduce randomization to a deterministic entropy‐based sequential trial procedure generalized to multiarm setting. Several methods of randomization applied to an entropy‐based design are investigated in terms of statistical power and ENS. Namely, the four design types are considered: (a) deterministic procedures, (b) naive randomization using the inverse of entropy criteria as weights, (c) block randomization, and (d) randomized penalty parameter. The randomized entropy‐based designs are compared to randomized Gittins index (GI) and fixed randomization (FR). After the comprehensive simulation study, the following conclusion on block randomization is made: for both entropy‐based and GI‐based block randomization designs the degree of randomization induced by forward‐looking procedures is insufficient to achieve a decent statistical power. Therefore, we propose an adjustment for the forward‐looking procedure that improves power with almost no cost in terms of ENS. In addition, the properties of randomization procedures based on randomly drawn penalty parameter are also thoroughly investigated. [ABSTRACT FROM AUTHOR]

A fundamental challenge for recommendation systems is the cold-start problem, i.e., recommending with no or few user-item interactions. An emerging direction alleviates the problem with meta-learning. These methods utilize the prior knowledge learned from previous recommendation tasks to facilitate the learning of a new task with a small number of interactions, i.e., the support set. The new task involves making recommendations for cold users or items. However, a support set may contain uninformative items and fail to capture the personality of new users, jeopardizing the recommendation quality. This paper proposes Information gain driven cold-start Recommendation (InfoRec), which actively acquires informative items for constructing the support set. Specifically, our InfoRec quantifies item informativeness with the reduction of model uncertainty about the user preference for items that are not in the support set. Experiments demonstrate that InfoRec outperforms baseline methods on two benchmark datasets in both non-cold-start and cold-start scenarios. [ABSTRACT FROM AUTHOR]

Computers have become increasingly vulnerable to malicious attacks with an increase in popularity and the proliferation of open system architectures. There are numerous malware detection technologies available to protect the computer operating system from such attacks. This type of malware detector targets programs based on patterns detected in the properties of computer applications. As the amount of analytical data increases, the computer defense system is adversely affected. The performance of the detection mechanism has been hindered due to the presence of numerous irrelevant characteristics. The goal of this study is to provide a feature selection approach that will help malware detection systems be more accurate by detecting pertinent and significant traits. Furthermore, by selecting the most important features, it is possible to maintain an acceptable level of accuracy in the detection of malware while significantly lowering the computational cost. The proposed method displays the most important features (MIFs) obtained from each machine learning method, including data cleaning and feature selection. Furthermore, the method applies six machine learning classification techniques to the selected feature set. Several classifiers were evaluated based on several characteristics for malware detection, including Support Vector Machines (SVM), Logistic Regression (LR), K-nearest neighbor (K-NN), Decision Tree (DT), Naive Bayes (NB), and Random Forest (RF). Our suggested model was tested on two malware datasets to determine its effectiveness. In terms of accuracy, precision, F1 scores, and recall, the experimental findings show that RF and DT classifiers beat other techniques.