Explore the vast range of titles available.

Early blight and ladybug beetle infestation are important factors threatening potato yields. The current research on disease classification using the spectral differences between the healthy and disease-stressed leaves of plants has achieved good progress in a variety of crops, but less research has been conducted on early blight in potato. This paper proposes a CARS-SPA-GA feature selection method. First, the raw spectral data of potato leaves in the visible/near-infrared light region were preprocessed. Then, the feature wavelengths were selected via competitive adaptive reweighted sampling (CARS) and the successive projection algorithm (SPA), respectively. Then, the two sets of wavelengths were reorganized and duplicates were removed, and secondary feature selection was conducted with genetic algorithm (GA). Finally, the feature wavelengths were fed into different classifiers and the parameters were optimized using a real-coded genetic algorithm (RCGA). The experimental results show that the feature wavelengths selected by the CARS-SPA-GA method accounted only for 9% of the full band, and the classification accuracy of the RCGA-optimized support vector machine (SVM) classification model reached 98.366%. These results show that it is feasible to classify early blight and ladybug beetle infestation in potato using visible/near-infrared spectral data, and the CARS-SPA-GA method can substantially improve the accuracy and detection efficiency of potato pest and disease classification.

As 5G technology becomes more widespread, the significant improvement in network speed and connection density has introduced more challenges to network security. In particular, distributed denial of service (DDoS) attacks have become more frequent and complex in software-defined network (SDN) environments. The complexity and diversity of 5G networks result in a great deal of unnecessary features, which may introduce noise into the detection process of an intrusion detection system (IDS) and reduce the generalization ability of the model. This paper aims to improve the performance of the IDS in 5G networks, especially in terms of detection speed and accuracy. It proposes an innovative feature selection (FS) method to filter out the most representative and distinguishing features from network traffic data to improve the robustness and detection efficiency of the IDS. To confirm the suggested method’s efficacy, this paper uses four common machine learning (ML) models to evaluate the InSDN, CICIDS2017, and CICIDS2018 datasets and conducts real-time DDoS attack detection on the simulation platform. According to experimental results, the suggested FS technique may match 5G network requirements for high speed and high reliability of the IDS while also drastically cutting down on detection time and preserving or improving DDoS detection accuracy.

The fast growth of the Internet has made network security problems more noticeable, so intrusion detection systems (IDSs) have become a crucial tool for maintaining network security. IDSs guarantee the normal operation of the network by tracking network traffic and spotting possible assaults, thereby safeguarding data security. However, traditional intrusion detection methods encounter several issues such as low detection efficiency and prolonged detection time when dealing with massive and high-dimensional data. Therefore, feature selection (FS) is particularly important in IDSs. By selecting the most representative features, it can not only improve the detection accuracy but also significantly reduce the computational complexity and attack detection time. This work proposes a new FS approach, BPSO-SA, that is based on the Binary Particle Swarm Optimization (BPSO) and Simulated Annealing (SA) algorithms. It combines these with the Gray Wolf Optimization (GWO) algorithm to optimize the LightGBM model, thereby building a new type of reflective Distributed Denial of Service (DDoS) attack detection model. The BPSO-SA algorithm enhances the global search capability of Particle Swarm Optimization (PSO) using the SA mechanism and effectively screens out the optimal feature subset; the GWO algorithm optimizes the hyperparameters of LightGBM by simulating the group hunting behavior of gray wolves to enhance the detection performance of the model. While showing great resilience and generalizing power, the experimental results show that the proposed reflective DDoS attack detection model surpasses conventional methods in terms of detection accuracy, precision, recall, F1-score, and prediction time.

Although consumption of sugar-sweetened beverages (SSBs) and artificially sweetened beverages (ASBs) has increasingly been linked with obesity, type 2 diabetes mellitus, hypertension, and all-cause mortality, evidence remains conflicted and dose–response meta-analyses of the associations are lacking. We conducted an updated meta-analysis to synthesize the knowledge about their associations and to explore their dose–response relations. We comprehensively searched PubMed, EMBASE, Web of Science, and Open Grey up to September 2019 for prospective cohort studies investigating the associations in adults. Summary relative risks (RRs) and 95% confidence intervals (CIs) were estimated for the dose–response association. Restricted cubic splines were used to evaluate linear/non-linear relations. We included 39 articles in the meta-analysis. For each 250-mL/d increase in SSB and ASB intake, the risk increased by 12% (RR = 1.12, 95% CI 1.05–1.19, I 2  = 67.7%) and 21% (RR = 1.21, 95% CI 1.09–1.35, I 2  = 47.2%) for obesity, 19% (RR = 1.19, 95% CI 1.13–1.25, I 2  = 82.4%) and 15% (RR = 1.15, 95% CI 1.05–1.26, I 2  = 92.6%) for T2DM, 10% (RR = 1.10, 95% CI 1.06–1.14, I 2  = 58.4%) and 8% (RR = 1.08, 95% CI 1.06–1.10, I 2  = 24.3%) for hypertension, and 4% (RR = 1.04, 95% CI 1.01–1.07, I 2  = 58.0%) and 6% (RR = 1.06, 95% CI 1.02–1.10, I 2  = 80.8%) for all-cause mortality. For SSBs, restricted cubic splines showed linear associations with risk of obesity ( P non-linearity  = 0.359), T2DM ( P non-linearity  = 0.706), hypertension ( P non-linearity  = 0.510) and all-cause mortality ( P non-linearity  = 0.259). For ASBs, we found linear associations with risk of obesity ( P non-linearity  = 0.299) and T2DM ( P non-linearity  = 0.847) and non-linear associations with hypertension ( P non-linearity  = 0.019) and all-cause mortality ( P non-linearity  = 0.048). Increased consumption of SSBs and ASBs is associated with risk of obesity, T2DM, hypertension, and all-cause mortality. However, the results should be interpreted cautiously because the present analyses were based on only cohort but not intervention studies.

Real-time diagnosis of strawberry diseases plays a key role in sustaining yield and improving field management. However, achieving reliable recognition remains challenging. Lesions often display irregular shapes and appear at different scales, which complicates detection. Field images also contain cluttered backgrounds, while many diseases look visually alike, making differentiation more difficult. In addition, collecting data under real conditions is not easy, resulting in small datasets on which deep learning models tend to overfit and fail to generalize. To address these issues, this study introduces ENet-CAEM, a redesigned EfficientNetB0 framework equipped with modules tailored for disease recognition. The Channel Context Module helps the network capture key lesion features while suppressing background noise. The Multi-Scale Efficient Channel Attention module applies multiple one-dimensional filters of varying sizes in parallel, enabling the model to highlight critical patterns, tell apart similar diseases, and adapt to lesions of different scales. A lightweight version of Atrous Spatial Pyramid Pooling is further integrated, allowing the network to perceive features at multiple spatial ranges. To balance local detail with global context, a mixed pooling strategy is adopted, enhancing robustness when lesion shapes change. Finally, Learnable DropPath and label smoothing are applied as regularization strategies, reducing overfitting and improving generalization on limited data. Experiments show that ENet-CAEM achieves 85.84% accuracy on a self-built dataset, outperforming the baseline by 4.29%. On a public strawberry dataset, the model reaches 97.39%, surpassing existing approaches. The proposed ENet-CAEM model shows superior accuracy and robustness over existing methods, providing an effective solution for strawberry disease recognition in practical field environments.

Timely and accurate detection of ear tag dropout is crucial for standardized precision breeding, health monitoring, and breeding evaluation. Reserve breeding pigs exhibit high activity levels and frequent interactions, leading to a higher prevalence of ear tag dropout. However, detection is challenging due to motion blur, small tag size, and significant target scale variations. To address this, we propose a motion blur-aware multi-scale framework, Adapt-Cascade. First, a Weight-Adaptive Attention Module (WAAM) enhances the extraction of motion blur features. Second, Density-Aware Dilated Convolution (DA-DC) dynamically adjusts the convolutional receptive field to improve small ear tag detection. Third, a Feature-Guided Multi-Scale Region Proposal strategy (FGMS-RP) strengthens multi-scale target detection. Integrated into the Cascade Mask R-CNN framework with Focal Loss, Adapt-Cascade achieves 93.46% accuracy at 19.2 frames per second in detecting ear tag dropout in reserve breeding pigs. This model provides a high-accuracy solution for intelligent pig farm management.

Railway operational equipment is crucial for ensuring the safe, smooth, and efficient operation of trains. Comprehensive analysis and mining of historical railway operational equipment failure (ROEF) reports are of significant importance for improving railway safety. Currently, significant challenges in comprehensively analyzing ROEF reports arise due to limitations in text mining technologies. To address this concern, this study leverages advanced text mining techniques to thoroughly analyze these reports. Firstly, real historical failure report data provided by a Chinese railway bureau is used as the data source. The data is preprocessed and an ROEF corpus is constructed according to the related standard. Secondly, based on this corpus, text mining techniques are introduced to build an innovative named entity recognition (NER) model. This model combines bidirectional encoder representations from transformers (BERT), bidirectional long short-term memory (BiLSTM) networks, and conditional random fields (CRF), with an additional entity attention layer to deeply extract entity features. This network architecture is used to classify specific entities in the unstructured data of failure reports. Finally, a knowledge graph (KG) is constructed using the Neo4j database to store and visualize the extracted ROEF-related entities and relationships. The results indicate that by constructing the topological relationships of the ROEF network, this study enables the analysis and visualization of potential relationships of historical failure factors, laying a foundation for predicting failures and enhancing railway safety, while also filling the current gap in the mining and analysis of ROEF reports.

With the increasing popularity of Android smartphones, malware targeting the Android platform is showing explosive growth. Currently, mainstream detection methods use static analysis methods to extract features of the software and apply machine learning algorithms for detection. However, static analysis methods can be less effective when faced with Android malware that employs sophisticated obfuscation techniques such as altering code structure. In order to effectively detect Android malware and improve the detection accuracy, this paper proposes a dynamic detection model for Android malware based on the combination of an Improved Zebra Optimization Algorithm (IZOA) and Light Gradient Boosting Machine (LightGBM) model, called IZOA-LightGBM. By introducing elite opposition-based learning and firefly perturbation strategies, IZOA enhances the convergence speed and search capability of the traditional zebra optimization algorithm. Then, the IZOA is employed to optimize the LightGBM model hyperparameters for the dynamic detection of Android malware multi-classification. The results from experiments indicate that the overall accuracy of the proposed IZOA-LightGBM model on the CICMalDroid-2020, CCCS-CIC-AndMal-2020, and CIC-AAGM-2017 datasets is 99.75%, 98.86%, and 97.95%, respectively, which are higher than the other comparative models.

Vulnerability detection in software source code is crucial in ensuring software security. Existing models face challenges with dataset class imbalance and long training times. To address these issues, this paper introduces a multi-feature screening and integrated sampling model (MFISM) to enhance vulnerability detection efficiency and accuracy. The key innovations include (i) utilizing abstract syntax tree (AST) representation of source code to extract potential vulnerability-related features through multiple feature screening techniques; (ii) conducting analysis of variance (ANOVA) and evaluating feature selection techniques to identify representative and discriminative features; (iii) addressing class imbalance by applying an integrated over-sampling strategy to create synthetic samples from vulnerable code to expand the minority class sample size; (iv) employing outlier detection technology to filter out abnormal synthetic samples, ensuring high-quality synthesized samples. The model employs a bidirectional long short-term memory network (Bi-LSTM) to accurately identify vulnerabilities in the source code. Experimental results demonstrate that MFISM improves the F1 score performance by approximately 10% compared to existing DeepBalance methods and reduces the training time to 2–3 h. These results confirm the effectiveness and superiority of MFISM in source code vulnerability detection tasks.

In this study, the necessity of radiotherapy (RT) for hormone receptor-negative older breast cancer patients after breast-conserving surgery (BCS) was investigated. The data of hormone receptor-negative invasive breast cancer patients who underwent BCS were extracted from the Surveillance, Epidemiology, and End Results (SEER) database from 2010 to 2015. All patients were separated into two groups, namely, the RT group and the no radiotherapy (No RT) group. The 3- and 5-year overall survival (OS) and cancer-specific survival (CSS) rates were compared between the No RT and RT groups after propensity score matching (PSM). The nomograms for predicting the survival of patients were constructed from variables identified by univariate or multivariate Cox regression analysis. A total of 2504 patients were enrolled in the training cohort, and 630 patients were included in the validation cohort. After PSM, 738 patients were enrolled in the No RT group and RT group. We noted that RT can improve survival in hormone receptor-negative older breast cancer patients who undergo BCS. Based on the results of multivariate Cox analysis, age, race, tumour grade, receipt of RT and chemotherapy, pathological T stage, N status, M status and HER2 status were linked to OS and CSS for these patients, and nomograms for predicting OS and CSS were constructed and validated. Moreover, RT improved OS and CSS in hormone receptor-negative older breast cancer patients who underwent BCS. In addition, the proposed nomograms more accurately predicted OS and CSS for hormone receptor-negative older breast cancer patients after BCS.