Classification Ability Research Articles

Development and multi-institutional validation of a deep learning model for grading of vesicoureteral reflux on voiding cystourethrogram: a retrospective multicenter study

Voiding cystourethrography (VCUG) is the gold standard for the diagnosis and grading of vesicoureteral reflux (VUR). However, VUR grading from voiding cystourethrograms is highly subjective with low reliability. This study aimed to develop a deep learning model to improve reliability for VUR grading on VCUG and compare its performance to that of clinicians. In this retrospective study in China, VCUG images were collected between January 2019 and September 2022 from our institution as an internal dataset for training and 4 external data sets as external testing set for validation. Samples were divided into training (N=1000) and validation sets (N=500), internal testing set (N=168), and external testing set (N=280). An ensemble learning-based model, Deep-VCUG, using Res-Net 101 and the voting methods was developed to predict VUR grade. The grading performance was assessed using heatmaps, area under the receiver operating characteristic curve (AUC), sensitivity, specificity, accuracy, and F1 score in the internal and external testing set. The performances of four clinicians (2 pediatric urologists and 2 radiologists) with and without the Deep-VCUG assisted to predict VUR grade were explored in external testing sets. A total of 1948 VCUG images were collected (Internal dataset=1668; multi-center external dataset=280). For assessing unilateral VUR grading, the Deep-VCUG achieved AUCs of 0.962 (95% confidence interval [CI]: 0.943-0.978) and 0.944 (95% [CI]: 0.921-0.964) in the internal and external testing sets, respectively, for bilateral VUR grading, the Deep-VCUG also achieved high AUCs of 0.960 (95% [CI]: 0.922-0.983) and 0.924 (95% [CI]: 0.887-0.957). The Deep-VCUG model using voting method outperformed single model and clinician in terms of classification based on VCUG image. Moreover, Under the Dee-VCUG assisted, the classification ability of junior and senior clinicians was significantly improved. The Deep-VCUG model is a generalizable, objective, and accurate tool for vesicoureteral reflux grading based on VCUG imaging and had good assistance with clinicians to VUR grading applicability. This study was supported by Natural Science Foundation of China, "Fuqing Scholar" Student Scientific Research Program of Shanghai Medical College, Fudan University, and the Program of Greater Bay Area Institute of Precision Medicine (Guangzhou).

Malingering assessment after severe traumatic brain injury in forensic psychology with a potential embedded symptom validity indicator of Symptom Checklist 90.

Malingering of neuropsychological damage is common among traumatic brain injury patients pursuing disability compensation in forensic contexts. There is an urgent need to explore differences in neuropsychological assessment outcomes with different levels of cooperation. A total of 420 participants with severe traumatic brain injury were classified into malingering group, partial cooperation group, and complete cooperation group according to the Binomial forced-choice digit memory test. The Wechsler Adult Intelligence Scale, event-related potential component, and Symptom Checklist 90 were applied subsequently to assess the psychological status of participants. Participants in the malingering group presented lower scores in the binomial forced-choice digit memory test and the Wechsler Adult Intelligence Scale, lower P3 amplitude, and simultaneously higher scores in the Symptom Checklist 90 than the other two groups. The actual intelligence quotient of participants with malingering tendencies ranged mostly between normal and marginal damage, and they often reported elevated whole scale scores in the Symptom Checklist 90. The Cooperation Index (defined as the ratio of positive symptom distress index to global severity index, CI) was proposed and validated to function as an embedded validity indicator of the Symptom Checklist 90, and the area under the receiver operating characteristic (ROC) curve was 0.938. When valued at 1.28, CI has the highest classification ability in differentiating malingering from non-malingering. Combined with the CI and P3 amplitude, the area under the ROC curve for malingering diagnosis further reached 0.952. Any non-optimal effort in a forensic context will lead to unexpected deviation in psychology evaluation results. CI is a potential candidate to act as an embedded validity indicator of the Symptom Checklist 90. The combination of CI and P3 amplitude can help to identify malingering in participants after severe traumatic brain injury.

Handwritten digit recognition based on deep learning techniques

The identification of handwritten digits in images recognition and machine learning is a prominent research area. In order to create a handwritten digit recognition model for this investigation, deep learning is introduced. The proposed approach integrates Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), and EfficientNetB0, three separate deep learning models. Specifically, the CNN model utilizes pooling layers and data augmentation techniques to enhance its classification ability, the RNN model takes advantage of its ability to process sequential data, and the EfficientNetB0 model benefits from a deeper and more complex network structure. These models are trained and evaluated using the Modified National Institute of Standards and Technology (MNIST) dataset. The experimental results demonstrate the efficacy of the proposed approach: the CNN model attains a remarkable accuracy of 98.9% on the test set, thereby showcasing its exceptional classification performance. Similarly, the RNN model achieves an accuracy of 96.7%, underscoring its suitability for analyzing sequential data. Furthermore, the EfficientNetB0 model attains an accuracy of 98.1%, thereby elucidating the benefits of the deeper network architecture. The models constructed in this study have significant real-world implications, such as improved object recognition systems, medical diagnostics, and autonomous driving. The EfficientNetB0 model produced an accuracy of 98.1% with its complex network architecture when applied to recognise handwritten digits.

An Introduction to SGTPPR: Sparse Geochemical Tectono‐Magmatic Setting Probabilistic MembershiP DiscriminatoR

AbstractWe present a new and easy‐to‐use geochemical tectono‐magmatic setting discriminator to calculate the probability of membership (the Sparse Geochemical Tectono‐magmatic setting Probabilistic membershiP discriminatoR, SGTPPR) that runs in Excel. It outputs the probability of membership for eight different tectono‐magmatic settings (mid‐ocean ridge, oceanic island, oceanic plateau, continental flood basalt province, intra‐oceanic arc, continental arc, island arc, and back‐arc basin) for a given volcanic rock sample based on major and selected trace element contents (SiO2, TiO2, Al2O3, Fe2O3, MgO, CaO, K2O, Na2O, Rb, Sr, Y, Zr, Nb, and Ba). We consider all possible ratios and multiplications of these contents, in addition to the contents themselves, which improves the discrimination accuracy. We use a statistical method called sparse multinomial logistic regression to construct a robust and predictive discrimination model. By imposing the sparsity, only a small number of essential variables are included in the model. The variables are objectively extracted from 287 possible geochemical variables, including all possible ratios and multiplications of the major and trace element contents. The constructed model exhibits a high classification ability, indicating that tectonic discrimination using major and selected trace elements yields a high classification ability when ratios and multiplications are considered. The system outputs the relative weights of the variables (i.e., contents, and ratios and multiplications of contents) of the input geochemical data to the calculated membership probabilities. This information can be used to evaluate and interpret the results. We apply the model to multiple samples of a geological unit, to determine the tectonic setting.

CLG: Contrastive Label Generation with Knowledge for Few-Shot Learning

Training large-scale models needs big data. However, the few-shot problem is difficult to resolve due to inadequate training data. It is valuable to use only a few training samples to perform the task, such as using big data for application scenarios due to cost and resource problems. So, to tackle this problem, we present a simple and efficient method, contrastive label generation with knowledge for few-shot learning (CLG). Specifically, we: (1) Propose contrastive label generation to align the label with data input and enhance feature representations; (2) Propose a label knowledge filter to avoid noise during injection of the explicit knowledge into the data and label; (3) Employ label logits mask to simplify the task; (4) Employ multi-task fusion loss to learn different perspectives from the training set. The experiments demonstrate that CLG achieves an accuracy of 59.237%, which is more than about 3% in comparison with the best baseline. It shows that CLG obtains better features and gives the model more information about the input sentences to improve the classification ability.

Application of ATR-FTIR spectroscopy and chemometrics for the forensic discrimination of aged peripheral and menstrual bloodstains

Accurately distinguishing between peripheral and menstrual bloodstains at crime scenes is a major challenge in forensic practice. The time since deposition (TSD) of bloodstains at the crime scene also plays an essential role in determining the postmortem interval or injury time. In this study, we used attenuated total reflection Fourier transform infrared (ATR-FTIR) spectroscopy combined with chemometric methods to differentiate peripheral and menstrual bloodstains considering the TSD and menstrual phase.The results of the principal component analysis (PCA) model showed that the fresh peripheral and menstrual bloodstains were relatively easy to distinguish, while the aged samples (2 W, 4 W, and 6 W TSD) caused a certain level of spectral signature convergence in the spectral features. Subsequently, the partial least squares discriminant analysis (PLS-DA) model and the genetic algorithm combined with PLS-DA (GA-PLSDA) model were constructed considering the TSD.The accuracy of internal cross-validation and external validation of the PLS-DA model demonstrated internal and external classification abilities of 88.3 % and 90.0 % accuracy, respectively. Additionally, the results of GA-PLSDA model showed that the accuracy of external and internal validation was 89.2 % and 90.0 %, respectively.The PCA, PLS-DA, and GA-PLSDA models showed that the critical differences between peripheral and menstrual bloodstains were in protein, phosphoric acid and glucose content. This preliminary study suggests that ATR-FTIR spectroscopy combined with chemometrics may be a potential method to distinguish between peripheral and menstrual bloodstains using complex conditions and provides support for further studies.

Predicting the ash content in coal flotation concentrate based on convolutional neural network

ABSTRACT Convolutional neural networks (CNNs) are currently one of the most popular image classification technologies. Their excellent image classification ability enables the prediction of the ash content in clean coal using coal flotation froth images. Herein, a scheme is proposed to predict the ash content in coal flotation concentrate using coal flotation froth images and CNN architecture. According to the ash content of the concentrate, the coal flotation froth image data set is divided into seven interval categories, and data augmentation is used to expand the data set. Then, several recently trained CNNs (ResNet, EfficientNet, EfficientNetV2, ConvNeXt) are used to classify the coal flotation froth images with different concentrate ash content interval (integer ±1%). The classification performance of each network model, relationship between model performance and hyperparameters, and the abstract pixel features of the best model are visualized. The EfficientNetV2-L network achieves the highest classification accuracy (99%) after fine-tuning. The results indicate that the CNNs are effective in predicting the ash content of clean coal by classifying coal flotation froth images. The optimized CNN model is applied to froth images in the industry, resulting in high classification performance, which demonstrates that the CNN has high potential for industrial applications.

Prediksi Deteksi Penyakit Kanker Payudara dengan Menggunakan Algoritma Decision Tree

Cancer is a deadly disease that is difficult to cure. Early cancer detection can be done through laboratory tests to identify the cancer type. Breast cancer is a type of cancer with initial symptoms in the form of a lump. Data mining and classification methods, such as decision trees with ID3 and C5.0 algorithms, are used to categorize breast cancer. The dataset used is Breast Cancer Coimbra, which was downloaded from UCI Machine Learning in 2018. ID3 has limitations in handling unstructured data and continuous attributes, while C5.0 is better. Both algorithms produce tree models with different levels of accuracy. This study shows that the C5.0 algorithm has the best classification results with 80% accuracy, 84.2% precision, 80% recall, and 80% F1 score. 80% accuracy shows the system's classification ability, so the C5.0 model can be used to predict breast cancer.

Nontechnical Loss Detection for Metered Customers in Alexandria Electricity Distribution Company Using Support Vector Machine

Non-technical losses (NTL) during transmission and distribution (T&D) of electrical energy is a major problem faced by utility companies which is very difficult to fight and detect. For that, more of power utilities spend thousands dollar for research centres to find efficient methods for detecting and controlling abnormalities. Electricity theft and billing irregularities forms the main portion of NTL. With the introduction of smart meter, the frequency of reporting energy consumption data to the utility company has been increased. Incoming and outgoing energy could be monitored and analyzed. Electricity theft is a complex problem with many parameters to be evaluated before implementing any measures to detect and control that. These parameters include some issues like social, economic, regional, managerial, infrastructural, and corruption. In recent years, several data mining and research studies on fraud detection and prediction techniques have been carried out in the electricity distribution sector. Support vector machine (SVM) technique has dominated the research for classifying data and detecting fraudulent electricity customers. SVM technique has good ability in data mining and data classification. The paper objective is to analyze the metered energy consumption data recorded and predict the pattern or the form of daily user’s energy consumption, then using SVM to classify the data whether normal or theft. The suggested technique is then tested using real data from Alexandria Electricity Distribution Company (AEDC). The proposed technique was able to distinguish between healthy and theft cases.

Classification of benign and malignant pulmonary nodule based on local-global hybrid network.

The accurate classification of pulmonary nodules has great application value in assisting doctors in diagnosing conditions and meeting clinical needs. However, the complexity and heterogeneity of pulmonary nodules make it difficult to extract valuable characteristics of pulmonary nodules, so it is still challenging to achieve high-accuracy classification of pulmonary nodules. In this paper, we propose a local-global hybrid network (LGHNet) to jointly model local and global information to improve the classification ability of benign and malignant pulmonary nodules. First, we introduce the multi-scale local (MSL) block, which splits the input tensor into multiple channel groups, utilizing dilated convolutions with different dilation rates and efficient channel attention to extract fine-grained local information at different scales. Secondly, we design the hybrid attention (HA) block to capture long-range dependencies in spatial and channel dimensions to enhance the representation of global features. Experiments are carried out on the publicly available LIDC-IDRI and LUNGx datasets, and the accuracy, sensitivity, precision, specificity, and area under the curve (AUC) of the LIDC-IDRI dataset are 94.42%, 94.25%, 93.05%, 92.87%, and 97.26%, respectively. The AUC on the LUNGx dataset was 79.26%. The above classification results are superior to the state-of-the-art methods, indicating that the network has better classification performance and generalization ability.

Location and segmentation of important railway signs based on improved segmentation

Purpose With the rapid development of railway-intelligent video technology, scene understanding is becoming more and more important. Semantic segmentation is a major part of scene understanding. There is an urgent need for an algorithm with high accuracy and real-time to meet the current railway requirements for railway identification. In response to this demand, this paper aims to explore a variety of models, accurately locate and segment important railway signs based on the improved SegNeXt algorithm, supplement the railway safety protection system and improve the intelligent level of railway safety protection. Design/methodology/approach This paper studies the performance of existing models on RailSem19 and explores the defects of each model through performance so as to further explore an algorithm model dedicated to railway semantic segmentation. In this paper, the authors explore the optimal solution of SegNeXt model for railway scenes and achieve the purpose of this paper by improving the encoder and decoder structure. Findings This paper proposes an improved SegNeXt algorithm: first, it explores the performance of various models on railways, studies the problems of semantic segmentation on railways and then analyzes the specific problems. On the basis of retaining the original excellent MSCAN encoder of SegNeXt, multiscale information fusion is used to further extract detailed features such as multihead attention and mask, solving the problem of inaccurate segmentation of current objects by the original SegNeXt algorithm. The improved algorithm is of great significance for the segmentation and recognition of railway signs. Research limitations/implications The model constructed in this paper has advantages in the feature segmentation of distant small objects, but it still has the problem of segmentation fracture for the railway, which is not completely segmented. In addition, in the throat area, due to the complexity of the railway, the segmentation results are not accurate. Social implications The identification and segmentation of railway signs based on the improved SegNeXt algorithm in this paper is of great significance for the understanding of existing railway scenes, which can greatly improve the classification and recognition ability of railway small object features and can greatly improve the degree of railway security. Originality/value This article introduces an enhanced version of the SegNeXt algorithm, which aims to improve the accuracy of semantic segmentation on railways. The study begins by investigating the performance of different models in railway scenarios and identifying the challenges associated with semantic segmentation on this particular domain. To address these challenges, the proposed approach builds upon the strong foundation of the original SegNeXt algorithm, leveraging techniques such as multi-scale information fusion, multi-head attention, and masking to extract finer details and enhance feature representation. By doing so, the improved algorithm effectively resolves the issue of inaccurate object segmentation encountered in the original SegNeXt algorithm. This advancement holds significant importance for the accurate recognition and segmentation of railway signage.

A novel semi-supervised prototype network with two-stream wavelet scattering convolutional encoder for TBM main bearing few-shot fault diagnosis

Accurately sensing the main bearing state and diagnosing fault types is crucial to ensure the safe operation of the main drive system of tunnel boring machines. Currently, the research on large-scale bearing fault diagnosis in industrial scenarios is severely limited by the quality and quantity of monitoring data. Conventional external vibration monitoring devices are difficult to adapt to complex and harsh working conditions of excavation equipment, and constantly changing low-speed and heavy-load operating conditions make similar labeled samples very scarce. To tackle this concern, we propose a semi-supervised prototype network with the two-stream wavelet scattering convolutional encoder (TWSCE-SSPN) based on roller state signals. By fusing radial and axial features of rollers using the two-stream structure and employing wavelet scattering transform and attention mechanism in the convolutional feature encoder, the model exhibits excellent feature mapping capabilities. Following the semi-supervised meta-learning paradigm, the proposed model uses the prototype generated by unlabeled sample features to modify the initial prototype generated by labeled sample features to augment the accuracy of classification in few-shot learning. The integrated sensing roller main bearing testbed was set up and fault datasets were established to verify the few-shot classification and anti-noise ability of the algorithm. Experimental results show that TWSCE-SSPN achieved 98.17 % accuracy at 1 shot, which is at least 18.17 % higher than existing methods. Furthermore, even under a signal-to-noise ratio of 0 dB, the few-shot recognition accuracy can remain 91.83 %. This verifies the superiority of the model in diagnosing main bearing faults under few-shot and strong noise conditions.

A hyperspectral band selection algorithm for identifying high oleic acid peanuts

High oleic acid peanuts have higher oleic acid content and stronger oxidation stability than common peanuts, but their appearances are similar, which imposes difficulties for classifying. Based on this, the study aims to classify high oleic acid peanut to ensure its purity by using hyperspectral imaging technology. However, classification accuracy and efficiency are limited given the large amount of redundant information of hyperspectral images. The band iteration algorithm (BIA) is proposed to select characteristic bands by reducing the redundant information between spectral bands for the peanut classification. Hyperspectral images with 616 bands (from 400 nm to 1100 nm) of 126 high oleic acid peanuts and 126 common peanuts were collected. Then, BIA selected optimal bands as characteristic bands from adjacent bands according to the classification accuracy of each band subsets. Thirdly, three classification models, namely linear discriminant analysis, support vector machine, and partial least squares-discriminant analysis (PLS-DA), were employed to compare the performance of BIA with successive projections algorithm and competitive adaptive reweighted sampling, respectively. The experimental results show that BIA can effectively improve the classification ability of spectral data. The BIA-PLS-DA model had the best classification efficiency, and the accuracy of the test set reached 93.26%. For peanut individuals, only one peanut sample was misclassified with a classification error rate of 1.43%.

Deep learning-based immunohistochemical estimation of breast cancer via ultrasound image applications.

Breast cancer is the key global menace to women's health, which ranks first by mortality rate. The rate reduction and early diagnostics of breast cancer are the mainstream of medical research. Immunohistochemical examination is the most important link in the process of breast cancer treatment, and its results directly affect physicians' decision-making on follow-up medical treatment. This study aims to develop a computer-aided diagnosis (CAD) method based on deep learning to classify breast ultrasound (BUS) images according to immunohistochemical results. A new depth learning framework guided by BUS image data analysis was proposed for the classification of breast cancer nodes in BUS images. The proposed CAD classification network mainly comprised three innovation points. First, a multilevel feature distillation network (MFD-Net) based on CNN, which could extract feature layers of different scales, was designed. Then, the image features extracted at different depths were fused to achieve multilevel feature distillation using depth separable convolution and reverse depth separable convolution to increase convolution depths. Finally, a new attention module containing two independent submodules, the channel attention module (CAM) and the spatial attention module (SAM), was introduced to improve the model classification ability in channel and space. A total of 500 axial BUS images were retrieved from 294 patients who underwent BUS examination, and these images were detected and cropped, resulting in breast cancer node BUS image datasets, which were classified according to immunohistochemical findings, and the datasets were randomly subdivided into a training set (70%) and a test set (30%) in the classification process, with the results of the four immune indices output simultaneously from training and testing, in the model comparison experiment. Taking ER immune indicators as an example, the proposed model achieved a precision of 0.8933, a recall of 0.7563, an F1 score of 0.8191, and an accuracy of 0.8386, significantly outperforming the other models. The results of the designed ablation experiment also showed that the proposed multistage characteristic distillation structure and attention module were key in improving the accuracy rate. The extensive experiments verify the high efficiency of the proposed method. It is considered the first classification of breast cancer by immunohistochemical results in breast cancer image processing, and it provides an effective aid for postoperative breast cancer treatment, greatly reduces the difficulty of diagnosis for doctors, and improves work efficiency.

Exploring White Matter Abnormalities in Young Children with Autism Spectrum Disorder: Integrating Multi-shell Diffusion Data and Machine Learning Analysis

This study employed tract-based spatial statistics (TBSS) to investigate abnormalities in the white matter microstructure among children with autism spectrum disorder (ASD). Additionally, an eXtreme Gradient Boosting (XGBoost) model was developed to effectively classify individuals with ASD and typical developing children (TDC). Multi-shell diffusion weighted images were acquired from 62 children with ASD and 44 TDC. Using the Pydesigner procedure, diffusion tensor (DT), diffusion kurtosis (DK), and white matter tract integrity (WMTI) metrics were computed. Subsequently, TBSS analysis was applied to discern differences in these diffusion parameters between ASD and TDC groups. The XGBoost model was then trained using metrics showing significant differences, and Shapley Additive explanations (SHAP) values were computed to assess the feature importance in the model's predictions. TBSS analysis revealed a significant reduction in axonal diffusivity (AD) in the left posterior corona radiata and the right superior corona radiata. Among the DK indicators, mean kurtosis, axial kurtosis, and kurtosis fractional anisotropywere notably increased in children with ASD, with no significant difference in radial kurtosis. WMTI metrics such as axonal water fraction, axonal diffusivity of the extra-axonal space (EAS_AD), tortuosity of the extra-axonal space (EAS_TORT), and diffusivity of intra-axonal space (IAS_Da) were significantly increased, primarily in the corpus callosum and fornix. Notably, there was no significant difference in radial diffusivity of the extra-axial space (EAS_RD). The XGBoost model demonstrated excellent classification ability, and the SHAP analysis identified EAS_TORT as the feature with the highest importance in the model's predictions. This study utilized TBSS analyses with multi-shell diffusion data to examine white matter abnormalities in pediatric autism. Additionally, the developed XGBoost model showed outstanding performance in classifying ASD and TDC. The ranking of SHAP values based on the XGBoost model underscored the significance of features in influencing model predictions.

Inter-turn short circuit and demagnetization fault diagnosis of ship PMSM based on multiscale residual dilated CNN and BiLSTM

Inter-turn short circuit (ITSC) and demagnetization of permanent magnet synchronous motors (PMSMs) can lead to serious ship accidents, timely and accurate fault diagnosis of these faults is very important. A multi-signal fusion fault diagnosis method (MD-CNN-BiLSTM) is proposed based on multi-scale residual dilated convolutional neural network (D-CNN) and bidirectional long and short-term memory (BiLSTM) for PMSM fault diagnosis. This method first takes three-phase current and vibration signals as input; uses a three-column parallel CNN structure with different scales to extract both global signal and local feature. A residual connection in the expanded CNN is then used to eliminate the problems of gradient disappearance or explosion; and finally, BiLSTM is used to further extract features and identify the fault. A 2.2 kW permanent magnet synchronous motor was used to build a fault simulation test rig. The motor stator was rewound to simulate the ITSC fault, and different sizes of permanent magnets were replaced to simulate demagnetization fault. ITSC, demagnetization and their coupled faults were simulated under 10 specific motor speeds and loads respectively. The test proved that the diagnostic accuracy of the proposed method was 4.2% higher than that of ordinary CNN and 29.06% higher than that of BiLSTM. It also had the best diagnostic effect under the noise interference of different intensities. It was verified that the proposed method has good noise interference and strong classification ability.

Enhancing Agricultural Decision-Making through Data Analysis: Predicting Crop Health Outcomes

This research employs advanced data analysis techniques to predict crop health outcomes during harvest seasons, with a focus on insect count, pesticide use, and soil type. The study encompasses two main components: feature correlation and predictive modeling. Feature engineering techniques are applied to capture variations in pesticide use and insect infestation, enhancing predictive capabilities. Ensemble methods, including Random Forest, XGBoost, and Decision Trees, are employed to forecast patterns of crop damage based on identified trends. Decision Trees exhibit robust capabilities, achieving an impressive accuracy rate of 90.03%. Random Forest excels with a robust accuracy of 90.35%, highlighting its classification abilities. XGBoost stands out with an accuracy rate of 86.51%. In contrast, Logistic Regression, Naive Bayes, and Convolutional Neural Networks face challenges, displaying lower accuracy. The evaluation further emphasizes the strength of ensemble methods and Decision Trees through precision, recall, and F1-Score metrics, providing a comprehensive understanding of relationships within pesticide damage. The framework of the study introduced in this paper can be seen as a major step forward with regard to agricultural decision-making. We present actionable strategies to enhance crop health while reducing damage through the integration of feature correlation, predictive modeling and precise evaluation metrics. The innovativeness is in the use of ensemble methods and Decision Trees that are implemented to promote informed decision-making among stakeholders through a sustainable approach to agriculture.

ФОРМИРОВАНИЕ И РЕДУКЦИЯ БАЗЫ ЗНАНИЙ ДЛЯ ОЦЕНКИ ЦЕЛЕСООБРАЗНОСТИ БУРЕНИЯ СКВАЖИН НА НЕФТЯНЫХ МЕСТОРОЖДЕНИЯХ

The article discusses the issues of forming and reducing a fuzzy knowledge base designed to assess the feasibility of drilling wells in oil fields as part of a decision support system. The initial knowledge base was formed using a specially developed software package that implements neuro-fuzzy modeling technology based on a group of fuzzy neural networks. To train them and form a knowledge base, initial data were required that described the dependence of the influence of the characteristics of producing wells on their efficiency in terms of the production rate of oil produced. The initial data for the analysis of 3187 records were presented for 46 oil field objects with carbonate reservoirs. Each record was characterized by the values of the input parameters “absolute rock permeability”, “rock porosity”, “average flow rate of neighboring wells” and “minimum water cut of neighboring wells”. The output parameter determined the efficiency of the well as the average oil flow rate for the first 3 years of operation. When training a team of 5 fuzzy neural networks, 5 gradations of input parameters were selected. The total number of fuzzy rules in the original knowledge base was 319. To assess its classification ability, the values of the Accuracy, Precision, Recall and F1-Score metrics were calculated. To reduce the knowledge base, a specially developed software package was used that implements 2 stages of genetic optimization: structural-parametric transformations of the fuzzy rules of the original knowledge base to obtain an intermediate knowledge base and minimizing the composition of the fuzzy rules of the intermediate knowledge base to obtain the desired (reduced) knowledge base. As a result of the reduction, the quantitative composition of knowledge bases, as well as the values of classification quality metrics, changed. The number of rules in the intermediate knowledge base was 131, and in the reduced one - 33. The overall reduction in the volume of the knowledge base was 89.66%. After the 1st stage of reduction, the values of the Accuracy, Precision, Recall and F1-Score metrics on the test data set increased, respectively, by 7.88%, 6.8%, 0.34% and 0.53%. After the 2nd stage of reduction, the overall increase in the values of these metrics was, respectively, 9.02%, 7.55%, 1.58% and 1.68%. The results obtained were tested at Tatneft and used to form and optimize the knowledge base when developing a decision support system for assessing the feasibility of drilling wells in oil fields.

Toward Reducing IDS Misclassification Using Hybrid DL and ML Approach

Operation centers often face challenges due to the high rate of misclassifications caused by the lower precision in Intrusion Detection System (IDS) models. Despite several research contributions ranging from machine learning and deep learning techniques aiming to reduce false positives and negatives, researchers and security experts consistently encounter a tradeoff between these two types of errors. This indicates a significant opportunity for further contributions in this field. We propose a hybrid model that combines Recurrent Neural Networks (RNN) feature extraction capabilities with Support Vector Machines (SVM) classification abilities. Our model achieves an impressive accuracy rate of 98.2% and significantly reduces misclassification errors compared to contemporary state-of-the-art models. This work shows the potential of hybrid approaches in improving accuracy and reducing false positive and negative errors.

Some methods to stimulate interest in exploring the plant world for 5-6 year old children in preschool

Stimulating children's interest in exploring the plant world is a means to communicate and familiarize them with the surrounding environment, to interact and express their desires, forming and understanding the phenomena around them, educating them to behave appropriately towards nature and society. Through these methods, teachers develop children's skills in observation, critical thinking, analysis, synthesis, and abstraction. Exploring the plant world for preschool children satisfies their curiosity and desire for knowledge about the phenomena of the surrounding world, while also contributing to the development of their sensory sensitivity and abilities in memory, imagination, comparison, synthesis, and classification... Helping children recognize the relationship between natural phenomena and the familiar social environment. This fosters in children a love for nature, their country, and people, and helps expand their knowledge base.