检索结果-内蒙古大学图书馆

A Novel Partitioned Random Forest Method-Based Facial Emotion Recognition

IEEE ACCESS 2025年 13卷 75085-75099页

作者： Heidari, Hanif Murugappan, M. Shaikh-Mohammed, Javeed Chowdhury, Muhammad E. H. Damghan Univ Dept Appl Math Damghan *** Iran Kuwait Coll Sci & Technol Dept Elect & Commun Engn Intelligent Signal Proc ISP Res Lab Doha 13133 Kuwait Vels Inst Sci Technol & Adv Studies Fac Engn Dept Elect & Commun Engn Chennai 600117 Tamil Nadu India Prince Sattam bin Abdulaziz Univ Coll Appl Med Sci Dept Biomed Technol Al Kharj 11942 Saudi Arabia Qatar Univ Dept Elect Engn Doha Qatar

Facial emotion recognition (FER) has been applied to various sectors, including e-learning, marketing, humanoid robot design, HMI/HCI applications, and medicine. The rapid development of intelligent technologies has led researchers to strive to improve facial emotion recognition techniques. A range of machine learning (ML) methods can be used to recognize facial expressions based on data from small to large datasets. Random Forest (RF) is simpler and more efficient than other ML algorithms. Some modified versions of RF have been developed to improve classification accuracy in the literature. Most improved RF versions modify attribute selection processes or combine them with other machine learning algorithms, increasing their complexity. Identifying an appropriate training dataset and determining its size remain open questions. The partitioned random forests (PRFs) approach is proposed as a modified strategy for improving FER. The proposed method divides multiple regions (different data lengths) into the feature space, allowing the algorithm to learn more complex decision boundaries. Using three statistical measures Lyapunov exponents (LE), Correlation Dimension (CD), and approximate entropy (AE), we evaluated the performance of machine learning algorithms over different data lengths. A crucial role for classification accuracy is played by the Lyapunov exponent or LE and the size of the dataset. A PRF is more effective on smaller datasets and with higher LE values. The proposed method for partitioning the datasets has been successfully tested on the FER dataset to classify six basic emotions (sadness, anger, fear, surprise, disgust, and happiness). Based on our numerical results, PRF performed better than traditional RF and other ML methods for FER, providing 98.37% mean absolute accuracy. Thus, a robust and useful method for improving classification rates is proposed for both small and large datasets.

关键词： Emotion recognition Accuracy classification tree analysis Random forests Machine learning algorithms Support vector machines Face recognition classification algorithms Real-time systems Feature extraction Partitioned random forest random forest machine learning facial emotion recognition classification emotions

来源：评论

学校读者我要写书评

暂无评论

Copula-Driven Learning Techniques for Physical Layer Authentication Using Multimodal Data

引用

IEEE ACCESS 2025年 13卷 24091-24107页

作者： Srikanth, Sahana Gurugopinath, Sanjeev Muhaidat, Sami PES Univ Dept Elect & Commun Engn Bengaluru 560085 India Khalifa Univ KU 6G Res Ctr Dept Comp & Informat Engn Abu Dhabi U Arab Emirates

In this paper, we present a study on copula-driven learning techniques for physical layer authentication (PLA) in wireless communication, using data from multiple modalities. The collective multimodal data is considered as an attribute vector, which is used as a test statistic for the underlying multi-level hypothesis testing problem of PLA. We consider regular-vine copula-based information fusion approaches across various combinations of these attributes resulting in different architectures, which are tested across different datasets. In particular, we consider three datasets which include a Monte Carlo simulations-based synthetic dataset, and publicly available automotive factory (AF) and open area test site (OATS) datasets from National institute of standards and technology (NIST). A comparative performance study of the proposed architectures across the datasets is carried out in terms of detection accuracy. For the classification task, we consider some of the well-known learning algorithms including long short-term memory (LSTM), random forest, K-nearest neighbor, support vector machine and bagging tree techniques. Moreover, we study the effect of correlation introduced across the attributes, and compare it with the case with no correlation among the attributes. Our extensive results provide intra-algorithm, intra-architecture and inter-architecture insights, and show that LSTM offers the best performance, across the datasets and proposed architectures.

关键词： Correlation Authentication classification algorithms Vectors Open area test sites Computer architecture Random forests OFDM NIST Long short term memory Copula theory information fusion multimodal attributes learning techniques physical layer authentication

来源：评论

学校读者我要写书评

暂无评论

Information Extraction Based on Line Chart for Research Paper in Chemical Science

引用

IEEE ACCESS 2025年 13卷 297-303页

作者： Yan, Hairong Yang, Shaohan Beijing Univ Technol Sch Comp Sci Fac Informat Technol Beijing 100124 Peoples R China Intellectual Property Publishing House Co Ltd Document Publishing Dept Beijing 100088 Peoples R China

In chemical science research progress, reading other researcher research paper in same type area, will speed up the generation of their own research method. Researchers want to automate the extraction of information from charts in paper, because there are detail of what element involved and how experiment environment changed in the charts. This paper designs and implements a line chart information extraction algorithm using neural networks and Hough Transform. First, a large dataset of line charts was collected and annotated to provide a foundation for neural network training. Secondly, detect the line charts in the literature and save them as separate images. Then, the Hough transform line detection algorithm was used to detect the axes, and the line charts were segmented. For each segmented part, different recognition algorithms were designed to identify various elements in the line charts, including axes, line regions, and legends. To validate the effectiveness of the algorithm, experimental tests were conducted in the field of inorganic catalysis, automatically extracting information from line charts in the literature. The experimental results show that the designed algorithm can accurately recognize various elements in line charts and effectively extract experimental data. Compared with traditional manual methods, automated extraction not only saves a considerable amount of time but also improves the accuracy and consistency of data extraction on paper fast reading. In summary, this method provides researchers with an efficient tool that accelerates the acquisition and comparison of experimental data, thereby advancing the progress of related research electronic document.

关键词： classification algorithms Feature extraction Text recognition Data mining Information retrieval Image resolution Image recognition Catalysis Web and internet services Visualization Line chart information extraction neural network YOLOv8 paper fast reading

来源：评论

学校读者我要写书评

暂无评论

Integrating Time Series Anomaly Detection Into DevOps Workflows

引用

IEEE ACCESS 2025年 13卷 46459-46477页

作者： Kanahols, Gustav Hasan, Shahriar Erik Strandberg, Per Malardalen Univ Sch Innovat Design & Engn S-72123 Vasteras Sweden Westermo Network Technol AB S-72130 Vasteras Sweden

Anomaly detection in the monitoring systems of DevOps environments is crucial for ensuring system reliability, preventing downtime, and maintaining the efficiency of continuous integration and continuous deployment pipelines. Artificial Intelligence (AI)-based solutions for automated anomaly detection in DevOps workflows are attracting growing research interest. However, challenges remain regarding the lack of ground truth data from DevOps systems, as well as difficulties in storing, processing, and visualizing the collected data. Furthermore, most of these datasets are unlabeled, making it unclear what constitutes anomalous system behavior, and no generalized approach exists for selecting the most suitable AI algorithms for anomaly detection in such contexts. To address these challenges, this paper publishes a comprehensive time series dataset from 19 different DevOps test systems, comprising 24 performance metrics sampled twice per minute over 30 days. Moreover, to benchmark the dataset, we first label a subset of the dataset based on feedback from the DevOps experts within the industry context. Then six different algorithms are employed on the dataset and their performance in anomaly detection is evaluated using three different Area Under the Curve (AUC) metrics. Additionally, this paper presents a tool for storing, visualizing, monitoring, and integrating anomaly detection algorithms and makes it available to the community. The performance evaluation results aiming to establish a baseline for further research show that AI-based anomaly detection can significantly benefit DevOps workflows but emphasize the need for algorithm selection and parameter tuning tailored to the specific industry context and dataset.

关键词： Anomaly detection Time series analysis DevOps classification algorithms Measurement Software Monitoring Training data Servers Machine learning algorithms deep learning machine learning time series analysis

来源：评论

学校读者我要写书评

暂无评论

Semi-Patchcore: A Novel Two-Staged Method for Semi-Supervised Anomaly Detection and Localization

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2025年 74卷

作者： Xie, Shuo Wu, Xiaojun Yu Wang, Michael Harbin Inst Technol Shenzhen Sch Mech Engn & Automat Shenzhen 518055 Peoples R China Great Bay Univ Sch Adv Engn Dongguan 523000 Peoples R China

Product surface defect detection is a crucial technology in industrial production. The adoption of deep learning-based algorithms for inspecting product surface defects has been steadily increasing due to their superior detection capability and enhanced generalization performance. However, current deep learning-based algorithms primarily focus on supervised approaches, which can be inefficient and costly. In this article, we present a novel pipeline for semi-supervised defect detection called Semi-Patchcore, which achieves comparable defect detection performance to weakly supervised methods using only defect-free and unlabeled samples for training. Initially, we establish a memory bank using a labeled defect-free training dataset. Subsequently, we compare the unlabeled mixed data with the features in the memory bank to derive pseudo-class labels. Finally, we train a segmentation network based on DeepLabV3+ using the pseudo-classification labels. To evaluate the performance of our approach, we conduct comparative experiments on four public datasets: MVTecAD dataset, DAGM dataset, BTAD dataset, and KSDD2 dataset. The experimental results demonstrate that our method outperforms state-of-the-art semi-supervised or unsupervised methods in terms of superiority and generalization. Additionally, we explore the impact of label issues on supervised learning observed in this study. Our method also surpasses some weakly supervised segmentation algorithms, showcasing its effectiveness in industrial defect detection.

关键词： Feature extraction Defect detection Anomaly detection Training Image reconstruction Location awareness Generative adversarial networks Costs classification algorithms Semantic segmentation detection and localization memory bank Semi-Patchcore semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Improved Butterfly Optimization Algorithm for Parameter Identification of Various Photovoltaic Models Including Power Station

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2025年 74卷

作者： He, Kai Zhang, Yong Leung, Henry Univ Sci & Technol Liaoning Sch Elect & Informat Engn Anshan 114051 Peoples R China Univ Calgary Dept Elect & Comp Engn Calgary AB T2N 1N4 Canada

Parameter identification of photovoltaic models (PIPM) is essential for controlling a photovoltaic (PV) system. However, due to its complexity, most existing methods still suffer from problems such as low accuracy, sensitivity to initial values, and local optima. For this, an improved butterfly optimization algorithm (DLBOA) with dimension differential learning is proposed. First, a new adaptive fragrance is introduced to optimize the instability caused by target differences and improve convergence performance. Second, the proposed dimension differential learning strategy improves butterflies' position by utilizing the excellent dimension information within the population, thereby reinforcing interindividual learning and enhancing population balancing and diversity, ultimately escaping from local optima. Then, after evaluating based on CEC2022, DLBOA identified the parameters for eight models across five materials and outperformed nine state-of-the-art algorithms in terms of accuracy, robustness, and promoting percentage. DLBOA is further compared with nine existing PIPM methods including five numerical methods. Finally, applying DLBOA to the YL PV station in China Guizhou Power Grid under a dynamic climate, multiple metrics confirm DLBOA's outstanding accuracy, with the reconstructed I-V and P-V curves closely matching synthesized curves. The statistical analysis results demonstrate that the proposed method effectively enhances the robustness of parameter identification while also strengthening the ability to escape local optima, demonstrating the potential to improve PIPM accuracy.

关键词： Mathematical models Parameter estimation Accuracy classification algorithms Metaheuristics Heuristic algorithms Time division multiplexing Solar power generation Integrated circuit modeling Reliability Butterfly optimization algorithm (BOA) dimension differential learning parameter identification photovoltaic (PV) models PV power station

来源：评论

学校读者我要写书评

暂无评论

A Cloud-Based Optimized Ensemble Model for Risk Prediction of Diabetic Progression-An Azure Machine Learning Perspective

引用

IEEE ACCESS 2025年 13卷 11560-11575页

作者： Daliya, V. K. Ramesh, T. K. Amrita Vishwa Vidyapeetham Dept Elect & Commun Engn Amrita Sch Engn Bengaluru 560035 India

The application of Machine Learning for predictive analysis in healthcare, particularly for diseases like diabetes, has proven highly beneficial. This study introduces an optimized Light Gradient-Boosting Machine (Light GBM) and K-Nearest Neighbour (KNN) based ensemble algorithm for predicting diabetic progression of Type 2 Diabetes, classifying it as high or low risk, using patient health parameters and serum measurements. Our model uses LightGBM, a rapid and efficient gradient boosting framework, coupled with KNN, which uses proximity to classify data points. The proposed model uses various optimization techniques, such as 10 fold cross validation, grid search method etc. to get the best results out of the ensemble model. As the model combines optimized version of LightGBM and KNN through a voting classifier which uses soft voting technique to find the final class, it utilizes the predictive capabilities of both the methods in an effective manner. The experiment is performed and implemented in Microsoft's Azure cloud, using Azure Machine Learning service, that leverages the advantages of cloud computing with respect to scalability, security and its potential integration possibilities into IoT-based smart healthcare *** aspect highlights its versatility and impact with respect to remote monitoring of patients as well. The ensemble achieves an 83.2% Area Under the Curve (AUC) of Receiver Operating Characteristics (ROC) score, indicating good classification efficiency. It produced 75% accuracy as well. The proposed model is compared with other classification and ensemble models, showcasing its superiority against other *** ensemble is also tested with some meta heuristic optimization methods, which produced comparable scores. The method's effectiveness is validated against another risk prediction dataset, proving its reliability. The model's accurate predictions can aid individuals in understanding disease progression risks and guide medical professio

关键词： Diabetes Diseases Predictive models Glucose Prediction algorithms Optimization Machine learning classification algorithms Nearest neighbor methods Accuracy Diabetic prediction ensemble learning KNN LightGBM voting classifier azure cloud azure machine learning

来源：评论

学校读者我要写书评

暂无评论

Robust Attribute Reduction Exploring Class-Separability and Attribute-Correlation for Ordered Decision Systems

引用

IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS 2025年第6期55卷 3941-3953页

作者： Sang, Binbin Yang, Lei Chen, Hongmei Li, Tianrui Xu, Weihua Chongqing Normal Univ Coll Comp & Informat Sci Chongqing 401331 Peoples R China Southwest Jiaotong Univ Sch Comp & Artificial Intelligence Chengdu 611756 Peoples R China Southwest Univ Coll Artificial Intelligence Chongqing 400715 Peoples R China

Robust knowledge acquisition approaches are one of the research hotspots in data mining. The fuzzy dominance rough sets (FDRS) model is an important knowledge acquisition tool for ordinal classification tasks. However, it has been proved in practice that this model usually performs poorly fault tolerance, and only one noisy sample can cause huge interference in acquiring knowledge. Attribute reduction is one of the nontrivial applications of the FDRS. At present, most attribute reduction methods for ordinal classification tasks mainly focus on the dependence of decision to attributes, while ignoring the information provided by the separability of classes and the correlation of attributes for ordinal classification. In view of these two issues, this article first proposes a robust FDRS model with filterable noise samples. Then, the class-separability and attribute-correlation are explored in robust fuzzy dominance rough approximation space, and corresponding attribute evaluation index is designed. Finally, an attribute reduction algorithm is designed to select the attribute subset with the highest classification performance. The experimental results show that the proposed algorithm has better robustness and classification performance.

关键词： Rough sets classification algorithms Robustness Computational modeling Numerical models Feature extraction Noise Knowledge acquisition Uncertainty Correlation Attribute-correlation attribute reduction class-separability (CS) ordered decision systems (ODSs) robust fuzzy dominance rough sets (RFDRS)

来源：评论

学校读者我要写书评

暂无评论

Positive-Unlabeled Constraint Learning for Inferring Nonlinear Continuous Constraints Functions From Expert Demonstrations

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2025年第2期10卷 1593-1600页

作者： Peng, Baiyu Billard, Aude EPFL Swiss Fed Inst Technol Lausanne Sch Engn LASA CH-1015 Lausanne Switzerland

Planning for diverse real-world robotic tasks necessitates to know and write all constraints. However, instances exist where these constraints are either unknown or challenging to specify accurately. A possible solution is to infer the unknown constraints from expert demonstration. This letter presents a novel two-step Positive-Unlabeled Constraint Learning (PUCL) algorithm to infer a continuous constraint function from demonstrations, without requiring prior knowledge of the true constraint parameterization or environmental model as existing works. We treat all data in demonstrations as positive (feasible) data, and learn a control policy to generate potentially infeasible trajectories, which serve as unlabeled data. The proposed two-step learning framework first identifies reliable infeasible data using a distance metric, and secondly learns a binary feasibility classifier (i.e., constraint function) from the feasible demonstrations and reliable infeasible data. The proposed method is flexible to learn complex-shaped constraint boundary and will not mistakenly classify demonstrations as infeasible as previous methods. The effectiveness of the proposed method is verified in four constrained environments, using a networked policy or a dynamical system policy. It successfully infers the continuous nonlinear constraints and outperforms other baseline methods in terms of constraint accuracy and policy safety.

关键词： Trajectory Reliability Robots Learning systems Shape Optimization Measurement classification algorithms Accuracy User preference Learning from demonstration reinforcement learning transfer learning

来源：评论

学校读者我要写书评

暂无评论

Automated Zebrafish Spine Scoring System Based on Instance Segmentation

引用

IEEE ACCESS 2025年 13卷 18814-18826页

作者： Chen, Wen-Hsin Kuo, Tien-Ying Wei, Yu-Jen Ho, Cheng-Jung Lin, Ming-der Chen, Huan Lin, Wen-Ying Natl Taipei Univ Technol Dept Elect Engn Taipei 10608 Taiwan Tzu Chi Univ Dept Mol Biol & Human Genet Hualien 97004 Taiwan Natl Chung Hsing Univ Dept Comp Sci & Engn Taichung 40202 Taiwan

In studying new medicines for osteoporosis, researchers use zebrafish as animal subjects to test drugs and observe the growth situation of their vertebrae in the spine to confirm the efficacy of new medicines. However, the current method for evaluating efficacy is time-consuming and labor-intensive, requiring manual observation. Taking advantage of advancements in deep learning technology, we propose an automatic method for detecting and recognizing zebrafish vertebrae of the images captured from image sensors to solve this problem. Our method was designed using Mask R-CNN as the instance segmentation backbone, enhanced with a mask enhancement module and a small object preprocessing approach to strengthen its detection abilities. Compared to the original Mask R-CNN architecture, our method improved the mean average precision (mAP) score for vertebra bounding box and mask detection by 7.1% to 97.7% and by 1.2% to 96.6%, respectively. Additionally, we developed a system using these detection algorithms to automatically calculate spinal vertebra growth scores, providing a valuable tool for researchers to assess drug efficacy.

关键词： Feature extraction Accuracy Micromechanical devices classification algorithms Object recognition Instance segmentation Deep learning Computer architecture Proposals Prediction algorithms machine learning object segmentation image analysis

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：