检索结果-内蒙古大学图书馆

A colorimetric sensor array combined with a hybrid feature selection approach for discrimination of citrus infested by Bactrocera dorsalis (Hendel)

引用

JOURNAL OF FOOD COMPOSITION AND ANALYSIS 2025年 138卷

作者： He, Mi Li, Dapeng Zhang, Xin Jiang, Han Yang, Gan Li, Ling Wen, Tao Cent South Univ Forestry & Technol Coll Mech & Intelligent Mfg Changsha 410083 Hunan Peoples R China

Changes in citrus volatile organic compounds (VOCs) induced by Bactrocera dorsalis (Hendel) infestation can serve as characteristic identifiers for non-destructive detection of infested citrus. This study proposed an innovative method combining colorimetric sensor array (CSA) technology with machine learning algorithms for the discrimination of B. dorsalis infestation in citrus. Gas chromatography-mass spectrometry (GC-MS) analysis identified key VOCs, including d-limonene, linalool, and decanal, as infestation markers. Subsequently, various porphyrin and metalloporphyrin dyes exhibiting sensitivity to these VOCs were selected to construct the CSA. To enhance detection accuracy, a hybrid feature selection method integrating ReliefF and Particle Swarm Optimization (PSO) was implemented. Subsequently, the optimized features subsets were utilized to develop classification models. Specifically, a binary classification model employing the K Nearest Neighbor (KNN) algorithm achieved a high accuracy of 93.89 % in distinguishing between healthy and infected citrus. Furthermore, a multiclass classification model using KNN was developed to differentiate among invasive, incubation, and infestation stages, attaining a remarkable accuracy of 97.78 %. This approach presents a promising solution for early detection of B. dorsalis infestation in citrus.

关键词： Bactrocera dorsalis Colorimetric sensor array Volatile organic compounds ReliefF classification algorithm

来源：评论

学校读者我要写书评

暂无评论

Subconcept perturbation-based classifier for within-class multimodal data

引用

NEURAL COMPUTING & APPLICATIONS 2024年第5期36卷 2479-2491页

作者： Cavalcanti, George D. C. Soares, Rodolfo J. O. Araujo, Edson L. Univ Fed Pernambuco UFPE Ctr Informat CIn Ave Jornalista Anibal Fernandes S-N Recife PE Brazil Univ Fed Vale Sao Francisco Ave Antonio Carlos Magalhaes 510 BR-48902300 Juazeiro BA Brazil

In classification, it is generally assumed that data from one class consist of one pure compact data cluster. However, in many cases, this cluster might consist of multiple subclusters, in other words, within-class multimodality. In such a scenario, it may be difficult or even impossible for a single classifier to find a suitable model using limited data. So, training a model using smaller chunks of data is an alternative that helps avoid complex models and reduces the task's complexity. This paper proposes the subconcept Perturbation-based Classifier (sPerC) that finds the best clusters per class using cluster validation measures, and one meta-classifier is trained per subcluster. This way, each class is represented by a set of meta-classifiers instead of one classifier. Such a design diminishes the complexity of the task, and using a divide-to-conquer strategy favors the precision of each meta-classifier. Through a set of comprehensive experiments on 30 datasets, the sPerC results compared favorably to other classifiers in multi-class classification tasks, showing that creating specialized classifiers per class in different regions of the feature space can be advantageous.

关键词： classification algorithm Multimodal data Subconcepts Cluster validation measures Perturbation

来源：评论

学校读者我要写书评

暂无评论

Detection and classification of Lamination Faults in a 15 kVA Three-Phase Transformer Core Using SVM, KNN and DT algorithms

引用

IEEE ACCESS 2022年 10卷 50925-50932页

作者： Altayef, Ehsan Anayi, Fateh Packianather, M. Benmahamed, Youcef Kherif, Omar Cardiff Univ Wolfson Ctr Magnet Sch Engn Cardiff CF24 3AA Wales Ecole Natl Polytech ENP Lab Rech Electrotech LRE Algiers 16200 Algeria Cardiff Univ Adv High Voltage Engn Res Ctr Sch Engn Cardiff CF24 3AA Wales

This paper deals with the detection and classification of two types of lamination faults (i.e., edge burr and lamination insulation faults) in a three-phase transformer core. Previous experimental results are exploited, which are obtained by employing a 15 kVA transformer under healthy and faulty conditions. Different test conditions were considered such as the flux density, number of the affected laminations, and fault location. Indeed, the current signals were used where four features (Average, Fundamental, Total Harmonic Distortion (THD), and Standard Deviation (STD)) were extracted. Elaborating A total of 328 samples, these features are utilized as input vectors to train and test classification models based on SVM, KNN, and DT algorithms. Based on the selected features, the results confirmed that the transformer current can be used for the detection of lamination faults. An accuracy rate of more than 84% was obtained using three different classifiers. Such findings provided a promising step toward fault detection and classification in electrical transformers, helping to prevent the system and avoid other related issues such as the increase in power loss and temperature.

关键词： Power transformers Power transformer insulation Lamination Feature extraction Transformer cores Insulation Circuit faults Edge burrs classification algorithm decision tree algorithm fault detection lamination insulation KNN classifier SVM classifier transformer core

来源：评论

学校读者我要写书评

暂无评论

Rotation-Tolerant Wireless Power Transmission Scheme with Smart Positioning for Cognitive Research on Moving Animals

引用

IEEE TRANSACTIONS ON BIOMEDICAL CIRCUITS AND SYSTEMS 2024年第1期18卷 123-130页

作者： Pahlavan, Saeideh Ashtiani, Shahin Jafarabadi Univ Tehran Coll Engn Sch Elect & Comp Engn Tehran 14395515 Iran

This article presents a novel wireless power transmission scheme designed for moving loads. Specifically focused on compensating for the tilt misalignment of the receiver. By utilizing phase-shifted excitation signals from an array of transmitters, the proposed scheme effectively mitigates the impact of misalignment, locally. The application of this scheme holds particular relevance for studying the behavior of moving animals in cognitive research. The system incorporates a cage with two transmitter arrays positioned on the top and bottom sides. To smart determining the receiver's position, the proposed structure utilizes current feedback from the driving circuits and employs SVM (Support Vector Machine) classification algorithms for positioning. Furthermore, when the receiver coil is tilted, a phase shift mechanism significantly enhances the power delivered to the receiver. Additionally, the use of an overlapped transmitter array enhances rotation tolerance and improves the uniformity of the magnetic fields for moving objects. The performance of the proposed scheme is validated through extensive simulations and measurements using a fabricated prototype. Notably, the designed system achieves a power delivery of 296 mW to the load at a 90 degrees angular misalignment, compared to 1.67 mu W delivered by conventional array system.

关键词： classification algorithm free-positioning phase shift transmitter array wireless power transfer

来源：评论

学校读者我要写书评

暂无评论

Advancements and Challenges in Non-Invasive Electrocardiography for Prenatal, Intrapartum, and Postnatal Care: A Comprehensive Review

引用

IEEE ACCESS 2024年 12卷 44730-44747页

作者： Marnani, Roya Aghadavoud Jaros, Rene Pavlicek, Jan Martinek, Radek Kahankova, Radana Vilimkova VSB Tech Univ Ostrava Fac Elect Engn & Comp Sci Dept Cybernet & Biomed Engn Ostrava 70800 Czech Republic Univ Hosp Ostrava Dept Pediat Ostrava 70800 Czech Republic Ostrava Univ Fac Med Ostrava 70800 Czech Republic

Non-invasive electrocardiography (NI-ECG) has become an indispensable tool for monitoring fetal and neonatal cardiac activity throughout the stages of pregnancy and postpartum care. This review emphasizes the distinct advantages of NI-ECG, including extended monitoring capabilities and valuable insights into fetal and neonatal health. The exploration of textile electrodes is highlighted as a promising alternative, offering improved comfort and reduced skin irritation compared to traditional adhesive electrodes. However, challenges in NI-ECG persist, with electrode placement, quantity, and noise removal being key considerations. The review underscores the significance of addressing interference sources, such as maternal and fetal body signals, motion artifacts, and electrode-skin contact. Additionally, the discussion extends to computer-aided diagnostics, presenting novel approaches for classifying fetal and neonatal health during pregnancy and delivery. Ongoing research aims to optimize electrode placement, develop advanced noise reduction algorithms, and explore sophisticated classification methodologies. These advancements hold the potential to enhance electronic monitoring, enabling early detection of abnormalities and promoting improved outcomes in prenatal and neonatal care.

关键词： Pediatrics Electrocardiography Electrodes Fetal heart rate Fetus Biomedical monitoring Abdomen Patient monitoring Neonatology Noninvasive treatment Biomedical signal processing Deep learning Machine learning Artificial intelligence classification algorithms Abdominal monitoring fetal electrocardiography fetal heart rate monitoring neonatal electrocardiography non-invasive monitoring signal processing textile electrodes artificial intelligence classification algorithm deep learning machine learning

来源：评论

学校读者我要写书评

暂无评论

Application of K-Shell algorithm in Key Point Identification and Cascading Failure in Urban Public Safety Transportation Network

引用

IEEE ACCESS 2024年 12卷 32152-32163页

作者： Xiao, You Ren, Yuan Wuhan Univ Sci & Technol Sch Law & Econ Wuhan 430065 Peoples R China Wuhan Univ Sci & Technol Inst Adv Studies Humanities & Social Sci Wuhan 430065 Peoples R China

The rapid development of modern urban public transportation and people's demand for efficient transportation have made intelligent management of urban public transportation networks a hot research field. In view of this, a composite complex traffic network node classification algorithm model is established based on the shell decomposition algorithm combined with a cascading failure model. The final research findings denote that the classification refinement level of the comprehensive shell decomposition value is about 50% higher than that of the WK-shell decomposition value. The comprehensive shell decomposition algorithm, which integrates global and local influence factors, can almost achieve one shell decomposition value per node in classification. The number of layers with nodes below 30 in the actual transportation network dataset test accounts for about 98% of the total number under the improved comprehensive shell decomposition algorithm, and roughly 50% under the composite shell decomposition algorithm, indicating that the accuracy of the former algorithm is higher. When the relationship ratio in robustness testing is 1:1:1, the average comprehensive shell decomposition value is at a higher position, which is about 3% higher than the WK-shell decomposition value and about 5% higher than the traditional shell decomposition value. In addition, when the proportions are 5:1:1, 1:5:1, and 1:1:5, the failure points tested under the comprehensive shell decomposition value are still the most, indicating that the comprehensive shell decomposition value considers more factors, is more cautious, and is closer to the actual situation. Through experimental data, the proposed composite complex traffic network node classification algorithm model, which integrates improved shell decomposition algorithm and cascading failure model, has certain practicality and feasibility.

关键词： classification algorithms Analytical models Neural networks Mathematical models Predictive models Fault diagnosis Public transportation Intelligent systems Management Urban areas Traffic control Intelligent transportation systems Pattern analysis intelligent management shell decomposition algorithm cascading failure model classification algorithm

来源：评论

学校读者我要写书评

暂无评论

Research on Online Shopping Mall Product classification Recommendation Based on Graph Neural Network 3

Research on Online Shopping Mall Product Classification Reco...

引用

3rd IEEE International Conference on Electrical Engineering, Big Data and algorithms, EEBDA 2024

作者： Yi, Jucai Deng, Ye Software College Jiangxi Agricultural University Jiangxi Nanchang China

ISBN: (纸本)9798350380989

The practical application of graph neural networks in online shopping malls is a significant area within real-life scenarios. As neural network technology continually advances, an increasing emphasis is being placed on how to efficiently leverage graph data for enhancing the functionality and performance of these e-commerce platforms. Nonetheless, prevailing methodologies commonly employ conventional adjacency matrices or basic attention mechanisms to consolidate and model data pertaining to items, users, and their interactions. To some extent, these approaches overlook the intricacy of graph structures and prove challenging to implement effectively on a grand scale. Running on graph data requires a large amount of computing resources, leading to performance issues. To address these issues, we propose a new method based on hierarchical transformation aggregation model to process graph data in online shopping malls more efficiently. This method first selects nodes at various levels and regions through random walks, and then uses graph convolutional neural networks (GCN) for information aggregation. Upon acquiring node features for each layer, a transformed attention mechanism is further introduced to more effectively consolidate the node features from every layer, thereby obtaining the ultimate representation of each node. This method better captures the local and global characteristics of graph data by considering node information at different levels, improving the performance and user experience of the mall. Ultimately, we substantiate the dependability of this model through multiple real-world dataset validations, thereby evidencing its practical application feasibility in online shopping malls. This method based on the hierarchical transformation aggregation model provides a more efficient way for malls to process and analyze graph data, and is expected to improve the performance of recommendation systems, personalized recommendations, and user shopping experienc

关键词： classification algorithm GCN neural network online mall

来源：评论

学校读者我要写书评

暂无评论

An Improved Count-Based Classifier for Categorical Data

引用

IEEE ACCESS 2024年 12卷 125427-125445页

作者： Singh, Sanskriti Sanjay Kumar Chauhan, Alok Vellore Inst Technol Sch Comp Sci & Engn Chennai 600127 India

The classification of categorical data is a fundamental task in machine learning, with numerous algorithms and techniques available. However, existing approaches often face challenges related to interpretability, scalability, and handling sparse or imbalanced datasets. This study presents an optimized version of the Count-Based Classifier, a novel approach that leverages the simplicity of counting occurrences to perform classification on categorical data. The optimized algorithm addresses the limitations of the original Count-Based Classifier, improving its computational efficiency, robustness, and overall performance. Through a comprehensive evaluation across 21 diverse categorical datasets, the Optimized Count-Based Classifier demonstrates competitive performance, consistently matching or surpassing established classifiers such as Decision Trees, Support Vector Machines, etc. The classifier's inherent interpretability, stemming from its reliance on counting operations, is a valuable asset, particularly in domains where transparency and explainability are crucial. Furthermore, the study explores the classifier's characteristics, including its tendency for overfitting, result consistency, and robustness against label errors. Experimental analyses reveal a low propensity for overfitting, high result consistency, and remarkable resilience to mislabeled data, further solidifying the classifier's practical applicability. The Optimized Count-Based Classifier has been implemented in Python and deployed as a user-friendly package, fostering accessibility and adoption within the machine learning community. By addressing the limitations of traditional approaches and offering a simple yet effective solution, this work contributes to the advancement of count-based classification techniques and their application in real-world scenarios.

关键词： classification algorithms Training Boosting Support vector machines Prediction algorithms Noise measurement Scalability algorithm design and theory Machine learning Supervised learning algorithm design classification algorithm count-based classifier machine learning supervised learning

来源：评论

学校读者我要写书评

暂无评论

Financial customer classification by combined model

引用

APPLIED MATHEMATICS AND NONLINEAR SCIENCES 2022年第2期8卷 431-446页

作者： Lin, Cong Zheng, Jinju Ningbo Univ Technol Ningbo 315000 Zhejiang Peoples R China

This paper explores the pros and cons of different algorithm models on the same selection problem, and then uses the combined prediction theory to obtain a new combined prediction model to explore its prediction accuracy. The actual problem to be solved is to help financial institutions to scientifically classify customers who choose financial products. We select the bank data set in the UCI database, which is derived from the survey data of a customer conducted by a financial institution in Portugal for a wealth management product. Decision tree C5.0 algorithm, naive Bayes classification algorithm and binary logit model are individually used to carry out a single model of empirical research on financial product customer classification. Through the empirical analysis of the five combination models, it is concluded that in the model that uses the least squares weighting method to determine the weight, the weight appears negative, which does not conform to the actual situation. The model that is based on the least squares weighting method and the model that is based on the simple weighting method are excluded. In contrast, the arithmetic mean weighted model is better than the reciprocal variance weighted model and the reciprocal mean square model. The accuracy reaches 89.91%, which is 0.43% higher than the accuracy of a single model. It can be concluded that the model that is based on the arithmetic average weighting is a better combination forecasting model.

关键词： combined forecasting classification algorithm financial products

来源：评论

学校读者我要写书评

暂无评论

Enhancing patient rehabilitation outcomes: artificial intelligence-driven predictive modeling for home discharge in neurological and orthopedic conditions

引用

JOURNAL OF NEUROENGINEERING AND REHABILITATION 2025年第1期22卷 1-16页

作者： Buscarini, Leonardo Romano, Paola Cocco, Elena Sofia Damiani, Carlo Pournajaf, Sanaz Franceschini, Marco Infarinato, Francesco IRCCS San Raffaele Roma Rehabil Bioengn Lab I-00166 Rome Italy IRCCS San Raffaele Roma Dept Neurol & Rehabil Sci Neurorehabil & Robot Rehabil I-00166 Rome Italy IRCCS San Raffaele Roma Dept Neurol & Rehabil Sci Rome Italy Univ Campania Luigi Vanvitelli Dept Mental & Phys Hlth & Prevent Med Naples Italy

In recent years, the fusion of the medical and computer science domains has gained significant traction in the scientific research landscape. Progress in both fields has enabled the generation of a vast amount of data used for making predictions and identifying interesting clusters and pathways. The Machine Learning (ML) model's application in the medical domain is one of the most compelling and challenging topics to explore, bridging the gap between Artificial Intelligence (AI) and healthcare. The combination of AI and medical information offers the possibility to create tools that can benefit both healthcare providers and physicians. This enables the enhancement of rehabilitation therapy and patient care. In the rehabilitation context, this work provides an alternative perspective: prediction of patients' home discharge upon completing the rehabilitation protocol. Demographic and clinical data were collected on 7282 inpatients from electronic Medical Record, each record was categorized into Neurological Patients (NP, N = 3222) or Orthopedic Patients (OP, N = 4060). To identify the most suitable machine learning model, an extensive data preprocessing phase was conducted. This process involved variables recoding, scaling, and the evaluation of different dataset balancing methods to optimize model performance. Following a thorough review and comparison of algorithms commonly employed in the clinical-rehabilitative field, the Random Over Sampling (ROS) technique, in combination with the Random Forest (RF) machine learning model, was selected. Subsequently, a comprehensive hyperparameter tuning phase was performed using a grid search approach. The optimized model achieved an average accuracy of 98% for OP and 96% for NP, based on 10-fold cross-validation applied to the balanced training set (unrealistic scenario). When tested on the unbalanced dataset (real-world condition), the RF model maintained strong generalization performance, achieving 90% accuracy for OP and 83

关键词： Personalized rehabilitation Machine learning classification algorithm Random forest Unbalance Hyperparameters optimization Accuracy

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：