检索结果-内蒙古大学图书馆

Riemann-Based algorithms Assessment for Single- and Multiple-Trial P300 classification in Non-Optimal Environments

IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING 2020年第12期28卷 2754-2761页

作者： Delgado, Juan M. Chau Achanccaray, David Villota, Elizabeth R. Chevallier, Sylvain Pontificia Univ Catolica Peru Dept Engn Lab Invest Biomecan & Robot Aplicada Lima 15088 Peru Tohoku Univ Neurorobot Lab Sendai Miyagi 9808577 Japan Univ Versailles St Quentin En Yvelines Inst Univ Technol Velizy F-78000 Versailles France

The P300 wave is commonly used in Brain-Computer Interface technology due to its higher bit rates when compared to other BCI paradigms. P300 classification pipelines based on Riemannian Geometry provide accuracies on par with state-of-the-art pipelines, without having the need for spatial filters, and also possess the ability to be calibrated with little data. In this study, five different P300 detection pipelines are compared, with three of them using Riemannian Geometry as either feature extraction or classification algorithms. The goal of this study is to assess the viability of Riemannian Geometry-based methods in non-optimal environments with sudden background noise changes, rather than maximizing classification accuracy values. For fifteen subjects, the average single-trial accuracy obtained for each pipeline was: 56.06% for Linear Discriminant Analysis (LDA), 72.13% for Bayesian Linear Discriminant Analysis (BLDA), 63.56% for Riemannian Minimum Distance to Mean (MDM), 69.22% for Riemannian Tangent Space with Logistic Regression (TS-LogR), and 63.30% for Riemannian Tangent Space with Support Vector Machine (TS-SVM). The results are higher for the pipelines based on BLDA and TS-LogR, suggesting that they could be viable methods for the detection of the P300 component when maximizing the bit rate is needed. For multiple-trial classification, the BLDA pipeline converged faster towards higher average values, closely followed by the TS-LogR pipeline. The two remaining Riemannian methods' accuracy also increases with the number of trials, but towards a lower value compared to the aforementioned ones. Single-stimulus detection metrics revealed that the TS-LogR pipeline can be a viable classification method, as its results are only slightly lower than those obtained with BLDA. P300 waveforms were also analyzed to check for evidence of the component being elicited. Finally, a questionnaire was used to retrieve the most intuitive focusing methods employed by the subject

关键词： Pipelines Support vector machines Covariance matrices Feature extraction classification algorithms Bit rate Task analysis Riemannian geometry P300 evoked potential brain-computer interfaces non-optimal environments

来源：评论

学校读者我要写书评

暂无评论

Weighted Contrastive Learning With Hard Negative Mining for Positive and Unlabeled Learning

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2025年第6期36卷 10515-10529页

作者： Yuan, Botai Gong, Chen Tao, Dacheng Yang, Jie Shanghai Jiao Tong Univ Inst Image Proc & Pattern Recognit Dept Automat Shanghai 200240 Peoples R China Nanyang Technol Univ Coll Comp & Data Sci Singapore 639798 Singapore

Positive and unlabeled (PU) learning aims to train a suitable classifier simply based on a set of positive data and unlabeled data. The state-of-the-art methods usually formulate PU learning as a cost-sensitive learning problem, in which every unlabeled example is treated as negative with modified class weights. However, existing methods fail to generate high-quality data representations, which brings about negative-prediction preference and performance decline. To overcome this problem, this article proposes a novel algorithm dubbed weighted contrastive learning with hard negative mining for positive and unlabeled learning (termed WConPU), which specifically designs a new prototypical contrastive strategy for gaining discriminative representations for PU learning. Specifically, our proposed WConPU consists of a contrastive learning (CL) module and a classifier training module, which can benefit from each other in an iterative manner. Moreover, a novel weighted contrastive objective function equipped with a prototype-based hard negative mining module is proposed to further enhance the representation quality. Theoretically, we show that our WConPU can be justified from the perspective of the expectation-maximization (EM) algorithm. Empirically, we compare our method with state-of-the-art PU algorithms on a wide range of real-world benchmark datasets, and the experimental results firmly demonstrate the advantage of our proposed method over the existing PU learning approaches.

关键词： Training Data mining Contrastive learning classification algorithms Prototypes Linear programming Reliability theory Prediction algorithms Iterative methods Training data Contrastive learning (CL) hard negative mining positive and unlabeled (PU) learning

来源：评论

学校读者我要写书评

暂无评论

Image Inpainting and Digital Camouflage: Methods, Applications, and Perspectives for Remote Sensing

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2025年 18卷 8215-8247页

作者： Karwowska, Kinga Wierzbicki, Damian Kedzierski, Michal Mil Univ Technol Fac Civil Engn & Geodesy Dept Imagery Intelligence PL-00908 Warsaw Poland

Image inpainting refers to the process of restoring missing or damaged areas in an image. This research field has been very active in recent years, driven by various applications such as reconstructing lost fragments, concealing data loss in corrupted image transmissions, removing objects in image editing, and interpolating image content for reconstruction in image-based rendering from various fields of view. This article presents existing methods of image inpainting, covering classical approaches, CNN-based methods, and GAN-based methods. In addition, it explores techniques related to steganography, adversarial image synthesis, and false image generation. Examples of applications are provided for each category of image modification methods. Although image inpainting and digital camouflage are not yet widely studied in the remote sensing community, there has been a growing interest in these topics in recent years. To broaden the understanding of these methods, this study also reviews techniques developed in the field of computer science, which have the potential to be adapted for remote sensing applications. The main contribution of this article is the presentation of various forms of digital masking, extending beyond traditional inpainting. We also provide a curated list of publicly available datasets that can support the development of new solutions, along with a selection of qualitative metrics for the robust evaluation of image inpainting algorithms.

关键词： Reviews Digital images classification algorithms Databases Steganography Satellite images Image reconstruction Satellites Remote sensing Visualization Computer vision (CV) convolutional neural network (CNN) deep learning (DL) image fusion image inpainting image processing

来源：评论

学校读者我要写书评

暂无评论

Fusing Monotonic Decision Tree Based on Related Family

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 2025年第2期37卷 670-684页

作者： Yang, Tian Yan, Fansong Qiao, Fengcai Wang, Jieting Qian, Yuhua Hunan Normal Univ Inst Interdisciplinary Studies Hunan Prov Key Lab Intelligent Comp & Language Inf Changsha Peoples R China Natl Univ Def Technol Coll Adv Interdisciplinary Studies Changsha 410073 Peoples R China Shanxi Univ Inst Big Data Sci & Ind Taiyuan 030006 Peoples R China

Monotonic classification is a special ordinal classification task that involves monotonicity constraints between features and the decision. Monotonic feature selection can reduce dimensionality while preserving the monotonicity constraints, ultimately improving the efficiency and performance of monotonic classifiers. However, existing feature selection algorithms cannot handle large-scale monotonic data sets due to their lack of consideration for monotonic constraints or their high computational complexities. To address these issues, building on our team's previous research, we define the monotonic related family method with lower time complexity to select informative features and obtain multi-reducts carrying complementary information from multi-view for raw feature space. Using bi-directional rank mutual information, we build two trees for each feature subset and fuse all trees using the corresponding decision support level (BFMDT). Compared with six representative algorithms for monotonic feature selection, BFMDT's average classification accuracy increased by 4.06% (FFREMT), 6.77% (FCMT), 5.61% (FPRS_up), 6.05% (FPRS_down), 5.86%(FPRS_global), 4.41% (Bagging), 7.65% (REMT) and 21.89% (FMKNN), the average execution time compared to tree-based algorithms decreased by 83.41% (FFREMT), 96.96% (FCMT), 75.64% (FPRS_up), 59.43% (FPRS_down), 84.65%(FPRS_global), 81.50% (Bagging) and 63.41% (REMT), while most of comparing algorithms were unable to complete computation on six high-dimensional datasets.

关键词： Feature extraction Decision trees classification algorithms Bagging Accuracy Rough sets Mutual information Prediction algorithms Entropy Data processing Rough set granular computing related family monotonic classification decision tree feature selection

来源：评论

学校读者我要写书评

暂无评论

Alpine Wetlands Information Extraction Using Optimized Multifeatures and Random Forest Algorithm

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2025年 18卷 7347-7363页

作者： Wang, Dongchuan Yang, Fei Jia, Shijie Wang, Zhiheng Dong, Chunhua Lang, Mingwei Ye, Kai Liu, Haotian Li, Tingrong Tianjin Chengjian Univ Sch Geol & Geomat Tianjin 300384 Peoples R China

Alpine wetlands are a special ecosystem that is extremely sensitive to global climate change. The unique geographical location and climatic conditions of the Yellow-River-Source National Park give rise to diverse wetland types at the land-water interface, which exhibit phenomena such as "same object with different spectra" and "different objects with the same spectrum." These complexities pose significant challenges in accurately extracting information from alpine wetlands in the study area. To address these challenges, this study proposes a novel integrated multialgorithm feature optimization model that combines three filtering algorithms with a random forest (RF) algorithm for classifying alpine wetland information. First, the rich feature information in the image is initially filtered using a fusion of the three algorithms. Then, the RF algorithm is applied to optimize the filtered features. Finally, the RF classification model is used to refine wetland extraction based on this optimized feature set. The results show that 1) the fused filtering algorithm demonstrates higher stability than each individual algorithm and takes into consideration the strengths and weaknesses of each individual algorithm;2) the classification accuracy of the RF algorithm reaches its highest value when the number of feature variables is 21;3) the optimal classification of alpine wetlands is achieved using the RF classification model based on the best set of feature variables, resulting in an overall accuracy of 93.32% and a Kappa coefficient of 91.65% . Compared to existing land cover datasets, the proposed method provides a more detailed classification of alpine wetlands.

关键词： Climate change Random forests Wetlands Ecosystems classification algorithms Radio frequency Filtering algorithms Information filters Stability analysis Optimization models Land surface Alpine wetlands feature selection filter algorithms random forest (RF)

来源：评论

学校读者我要写书评

暂无评论

Performance Comparison Between Deep Neural Network and Machine Learning Based Classifiers for Huntington Disease Prediction From Human DNA Sequence

引用

IEEE TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS 2025年第1期22卷 52-63页

作者： Vishnuppriya, C. Tamilpavai, G. Govt Coll Engn Dept Comp Sci & Engn Tirunelveli 627007 Tamil Nadu India

Huntington Disease (HD) is a type of neurodegenerative disorder which causes problems like psychiatric disturbances, movement problem, weight loss and problem in sleep. It needs to be addressed in earlier stage of human life. Nowadays Deep Learning (DL) based system could help physicians provide second opinion in treating patient's disease. In this work, human Deoxyribo Nucleic Acid (DNA) sequence is analyzed using Deep Neural Network (DNN) algorithm to predict the HD disease. The main objective of this work is to identify whether the human DNA is affected by HD or not. Human DNA sequences are collected from National Center for Biotechnology Information (NCBI) and synthetic human DNA data are also constructed for process. Then numerical conversion of human DNA sequence data is done by Chaos Game Representation (CGR) method. After that, numerical values of DNA data are used for feature extraction. Mean, median, standard deviation, entropy, contrast, correlation, energy and homogeneity are extracted. Additionally, the following features such as counts of adenine, thymine, guanine and cytosine are extracted from the DNA sequence data itself. The extracted features are used as input to the DNN classifier and other machine learning based classifiers such as NN (Neural Network), Support Vector Machine (SVM), Random Forest (RF) and classification Tree with Forward Pruning (CTWFP). Six performance measures are used such as Accuracy, Sensitivity, Specificity, Precision, F1 score and Mathew Correlation Co-efficient (MCC). The study concludes DNN, NN, SVM, RF achieve 100% accuracy and CTWFP achieves accuracy of 87%.

关键词： Diseases Feature extraction DNA Accuracy Support vector machines Long short term memory Convolutional neural networks classification algorithms Proteins classification tree analysis CAG repeat chaos game representation deep neural network deoxyribo nucleic acid huntington disease

来源：评论

学校读者我要写书评

暂无评论

Enhancing Social Media Users Trust: A Comprehensive Framework for Detecting Malicious Profiles Using Multi-Dimensional Analytics

引用

IEEE ACCESS 2025年 13卷 7071-7093页

作者： Terumalasetti, Sailaja Reeja, S. R. VIT AP Univ Sch Comp Sci & Engn Amaravati 522237 India

Information transparency, user privacy, and digital security are significantly vulnerable to the proliferation of counterfeit bot accounts on OSN. Traditional methods for distinguishing these accounts archetypally depend on an inadequate set of features, which hampers their effectiveness in contrast to the progressively sophisticated maneuvers employed by malicious users. A state-of-the-art methodology for Fake Bot Account Detection (FAD) that assimilates sophisticated deep learning techniques to scrutinize multimodal data, such as visual content, temporal activity patterns, and network interactions, to incredulous this challenge Visual features are analyzed using sophisticated methods, including deconstructing into smaller segments and extracting high-level patterns using encoder models. Specialized convolutions are employed to identify dependencies in user behavior over time from sequential data. By aggregating features from connected nodes and considering numerous forms of relationships, network analysis is accompanied by the social graph to learn node representations. A unified representation is created by merging these multimodal features. This representation is then transmitted through a completely associated layer and an activation function to predispose whether a bot account is genuine or counterfeit. The detection accuracy of false bot accounts is improved by integrating these diverse data modalities, which addresses the limitations of single-modality approaches. Compared with conventional methods, the FAD method is validated using the Cresci 2017 dataset, demonstrating substantial enhancements in momentous performance metrics. The consequences suggest that the proposed methodology effectively captures the multifaceted character of fake bot accounts, providing a robust tool for enhancing the security of OSNs.

关键词： Chatbots Social networking (online) Feature extraction Accuracy Security Blogs Visualization classification algorithms Deep learning Data models Bot account detection OSN malicious user multidimensional data deep learning security

来源：评论

学校读者我要写书评

暂无评论

A Quantum-Based Machine Learning Approach for Autism Detection Using Common Spatial Patterns of EEG Signals

引用

IEEE ACCESS 2025年 13卷 15739-15750页

作者： Saranya, S. Menaka, R. Vellore Inst Technol Sch Elect Engn Chennai 600127 Tamil Nadu India Vellore Inst Technol Ctr Cyber Phys Syst Chennai 600127 Tamil Nadu India

Autism Spectrum Disorder (ASD) significantly impacts social communication, interaction, and behavior. Early diagnosis and timely intervention can improve outcomes by enabling tailored therapeutic strategies. Electroencephalography (EEG) has emerged as a non-invasive tool to capture brain activity and facilitate the early detection of ASD using machine learning techniques. However, attaining high accuracy with minimal EEG channels remains a challenge. This study analyzed EEG data from 10 children with ASD and 10 Typically Developed (TD) children using three electrode combinations: C3-C4, C3-Cz, and C4-Cz. EEG signals were spatially filtered using a wavelet-based regularized filter bank common spatial pattern. Key features, including peak-to-peak amplitude, were extracted, and correlation-based feature selection identified the most informative features. classification with Support Vector Machine (SVM) identified the C4-Cz pair as the most effective, achieving the highest accuracy. Further analysis applied Neural Networks (NN), Quantum Support Vector Machines (QSVM), and Quantum Neural Networks (QNN) to classify data from the C4-Cz pair. QSVM with amplitude embedding feature map outperformed others, achieving an accuracy of 94.7%. Performance was further improved by incorporating an enhanced feature set comprising peak frequency, Stockwell transform coefficients, and peak-to-peak amplitude. The proposed system, leveraging these refined features and QSVM, achieved an exceptional accuracy of 98.9%. To our knowledge, this is the first study utilizing an enhanced feature set derived from reduced brain lobes and quantum machine learning for ASD classification, offering a novel and highly accurate diagnostic approach.

关键词： Feature extraction Electroencephalography Support vector machines Accuracy Autism Filter banks Brain modeling Nearest neighbor methods classification algorithms Motors Autism spectrum disorder quantum neural network quantum support vector machine wavelet common spatial pattern

来源：评论

学校读者我要写书评

暂无评论

AS-Faster-RCNN: An Improved Object Detection Algorithm for Airport Scene Based on Faster R-CNN

引用

IEEE ACCESS 2025年 13卷 36050-36064页

作者： He, Zhige He, Yuanqing Civil Aviat Flight Univ China Sch Comp Sci Guanghan 618307 Peoples R China

Currently, the rapid development of the aviation industry has made the safety of the airport becomes more and more important. The most important part of this is the capability of discriminate the different type of objects correctly. However, the existing detection models have the problems of degradation, lacking of detection capability for deformed and small objects and single feature extraction, causing low detection accuracy. To overcome these problems, we design an object detection method for airport scene named AS-Faster-RCNN. Firstly the ResNet-101 substitute for VGG-16 as the backbone network to improve the ability of detecting small objects, prevent the degradation and enhance the ability of detecting the small objects. Secondly, The DCN (Deformable Convolution Network) is employed in the backbone to strengthen the ability of extracting features for deformed objects. Finally, the CBAM (Convolutional Block Attention Module) is added to the backbone to extract multidimensional features to enhance performance of the model. We design some experiemnts to prove the feasibility of the method and the results demonstrate the mAP(mean Average Precision) has increased by 5.3% comapred to the basline model, and compared with other object detection models, its mAP also increased to a certain extent.

关键词： Feature extraction Object detection Airports Atmospheric modeling Accuracy Proposals Deep learning classification algorithms Deformable models Convolution Airport scene objection detection faster-RCNN CBAM ResNet DCN

来源：评论

学校读者我要写书评

暂无评论

Adaptive Learning in Imbalanced Data Streams With Unpredictable Feature Evolution

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 2025年第4期37卷 1527-1541页

作者： Tu, Jiahang Tang, Xijia Gu, Shilin Dai, Yucong Fan, Ruidong Hou, Chenping Natl Univ Def Technol Dept Math & Syst Sci Changsha 410073 Peoples R China

Learning from data streams collected sequentially over time are widely spread in real-world applications. Previous methods typically assume that the data stream has a feature space with a fixed or clearly defined evolution pattern, as well as a balanced class distribution. However, in many practical scenarios, such as environmental monitoring systems, the frequency of anomalous events is significantly imbalanced compared to normal ones and the feature space dynamically changes due to ecological evolution and sensor lifespan. To alleviate this important but rarely studied problem, we propose the Adaptive Learning in Imbalace data streams with Unpredictable feature evolution (ALIU) algorithm. As data streams with imbalanced class distribution arrive, ALIU first mitigates the model's bias for the majority class by reweighting the adaptive gradient descent magnitudes between different classes. Then, a new loss function is proposed that simultaneously focuses on misclassifications and maintains model robustness. Further, when imbalanced data streams arrive with feature evolutions, we reuse the previously learned model and update the incomplete and augmented features by adopting the adaptive gradient strategy and ensemble method, respectively. Finally, we utilize the projected technique to build a sparse yet efficient model. Based on a few common and mild assumptions, we theoretically analyze that the ALIU satisfies a sub-linear regret bound under both convex and strong convex loss functions and the performance of model can be improved with the assistance of old features. Besides, extensive experimental results further demonstrate the effectiveness of our proposed algorithm.

关键词： Streams Data models classification algorithms Adaptation models Biological system modeling Disasters Heuristic algorithms Ensemble learning Environmental monitoring Ecosystems Data streams imbalanced class distribution feature evolution sub-linear regret bound

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：