检索结果-内蒙古大学图书馆

3rd International Conference on Science, ICOS 2019

作者： Firdaus, M.B. Widians, J.A. Padant, J.Y. Informatics Engineering Department Faculty of Computer Science and Information Technology Mulawarman University Samarinda Indonesia

Showing the design and layout of the building using a model, making this model requires time and accuracy because the model is built on a scale that has been adjusted to the building to be made later, a problem that often occurs in modeling is the suitability of the scale and detail of the model. Augmented Reality as a variation of the virtual environment. Users of AR technology can see the real world, with virtual objects added to the real world. So, users see virtual objects and real objects in the same place. Submission of information by utilizing the three-dimensional visualization technique is very interesting because it can display the 3D model of an object before it is built in real terms. The faculty of computer Science and Information technology Mulawarman University Samarinda has an exterior building design of a new building, but there are no interactive media that can display the exterior of the building as a whole and in detail. This application is able to be used to apply the 3D model of the building as a whole and can be seen from various viewpoints. © Published under licence by IOP Publishing Ltd.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Privacy-preserving explainable AI: a survey

引用

Science China(Information Sciences) 2025年第1期68卷 23-56页

作者： Thanh Tam NGUYEN Thanh Trung HUYNH Zhao REN Thanh Toan NGUYEN Phi Le NGUYEN Hongzhi YIN Quoc Viet Hung NGUYEN School of Information and Communication Technology Griffith University School of Computer and Communication Sciences Ecole Polytechnique Federale de Lausanne Faculty of Mathematics and Computer Science University of Bremen Faculty of Information Technology HUTECH University Department of Computer Science Hanoi University of Science and Technology School of Electrical Engineering and Computer Science The University of Queensland

As the adoption of explainable AI(XAI) continues to expand, the urgency to address its privacy implications intensifies. Despite a growing corpus of research in AI privacy and explainability, there is little attention on privacy-preserving model explanations. This article presents the first thorough survey about privacy attacks on model explanations and their countermeasures. Our contribution to this field comprises a thorough analysis of research papers with a connected taxonomy that facilitates the categorization of privacy attacks and countermeasures based on the targeted explanations. This work also includes an initial investigation into the causes of privacy leaks. Finally, we discuss unresolved issues and prospective research directions uncovered in our analysis. This survey aims to be a valuable resource for the research community and offers clear insights for those new to this domain. To support ongoing research, we have established an online resource repository, which will be continuously updated with new and relevant findings.

关键词： privacy-preserving explainable AI privacy attacks privacy defences PrivEx PPXAI

来源：评论

学校读者我要写书评

暂无评论

FACNet: Feature alignment fast point cloud completion network

引用

Computational Visual Media 2025年第1期11卷 141-157页

作者： Xinxing Yu Jianyi Li Chi-Chong Wong Chi-Man Vong Yanyan Liang School of Computer Science and Engineering Faculty of Innovation EngineeringMacao University of Science and TechnologyTaipaMacaoChina Faculty of Science and Technology University of MacaoTaipaMacaoChina

Point cloud completion aims to infer complete point clouds based on partial 3D point cloud *** previous methods apply coarseto-fine strategy networks for generating complete point ***,such methods are not only relatively time-consuming but also cannot provide representative complete shape features based on partial *** this paper,a novel feature alignment fast point cloud completion network(FACNet)is proposed to directly and efficiently generate the detailed shapes of *** aligns high-dimensional feature distributions of both partial and complete point clouds to maintain global information about the complete *** its decoding process,the local features from the partial point cloud are incorporated along with the maintained global information to ensure complete and time-saving generation of the complete point *** results show that FACNet outperforms the state-of-theart on PCN,Completion3D,and MVP datasets,and achieves competitive performance on ShapeNet-55 and KITTI ***,FACNet and a simplified version,FACNet-slight,achieve a significant speedup of 3–10 times over other state-of-the-art methods.

关键词： 3D point clouds shape completion geometry processing deep learning

来源：评论

学校读者我要写书评

暂无评论

Automatically weighted focal loss for imbalance learning

引用

Neural Computing and Applications 2025年第5期37卷 4035-4052页

作者： Mahmoodi, Nasibeh Shirazi, Hossein Fakhredanesh, Mohammad DadashtabarAhmadi, Koroush Faculty of Electrical and Computer Malek Ashtar University of Technology Tehran Iran

In the context of class-imbalanced learning, most CNN-based classification algorithms encounter the problem of majority class gradient dominance, which makes them susceptible to bias toward the majority class. It is the consequence of the underlying assumption that the costs of misclassification are equivalent and that the class distribution is reasonably balanced. A standard way for dealing with the data imbalance is by using a loss function that favors the minority class. A constant weight is considered for each class in the loss function, which is generally inversely related to the number of instances in the class. In this paper, for multi-class imbalanced learning, we proposed Dynamic Weighted Focal Loss (DWFL), which determined the weight of each class for the next epoch automatically based on the classifier’s results in all previous epochs. In this way, the better-learned class weighed less, and the less-learned class weighed more. Additionally, the application of focus loss reduced the importance of simple samples while increasing the importance of hard ones compared to cross-entropy. The experiments on several imbalanced datasets revealed that the performance of our suggested strategy (DWFL) is superior to that of previous resampling or reweighting methods with imbalanced classes. The experimental findings demonstrate the efficacy and convergence of the proposed methodology. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Weighted rank aggregation based on ranker accuracies for feature selection

引用

Soft Computing 2025年第4期29卷 1981-2001页

作者： Abdolrazzagh-Nezhad, Majid Kherad, Mahdi Faculty of Engineering Department of Computer Engineering Bozorgmehr University of Qaenat Qaen Iran Department of Computer Science Faculty of Computer and Industrial Engineering Birjand University of Technology Birjand Iran Faculty of Engineering Department of Computer Engineering University of Qom Qom Iran

Rank aggregation is the combination of several ranked lists from a set of candidates to achieve a better ranking by combining information from different sources. In feature selection problem, due to the heterogeneity of methods, there are some base rankers (Filter-based methods) that are of diverse quality and usually the ground truth of ratings is not available. Existing rank aggregation methods that take the diverse quality of base rankers into account do not have any explicit approach for appropriate weighting, require prior assumptions, and suffers from high computational complexity. In this paper, to overcome these challenges, an efficient unsupervised method is introduced for estimating the base rankers’ qualities and aggregating the rankers based on the estimated weights. We first compute the ratio of disagreement between base rankers in ordering different element pairs and then estimate the accuracies in a way that to minimize the discrepancy between these computed ratios and their analytical counterparts. We use the weighted majority voting method for obtaining the aggregated results. To resolve the probable inconsistencies in the final aggregation, the result is formed as a graph, and a greedy algorithm is used to find an acyclic subgraph with the highest weigh. To demonstrate the performance of the proposed method, nine standard UCI datasets are used. The obtained results by the proposed method have higher values of classifier measures than the existing baseline Feature Selection methods and rank aggregation-based multi-filter methods in the most datasets. The experiments show that rank aggregation-based Feature Selection methods outperform individual methods. The proposed method also shows the weight of each Filter-based Feature Selection method, in which the MRMR method has a higher weight than other methods. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Wiener filtering

来源：评论

学校读者我要写书评

暂无评论

Efficient and lightweight CNN model for COVID-19 diagnosis from CT and X-ray images using customized pruning and quantization techniques

引用

Neural Computing and Applications 2025年 1-20页

作者： Sriwiboon, Nattavut Department of Computer Science and Information Technology Faculty of Science and Health Technology Kalasin University Kalasin Thailand

The coronavirus disease 2019 (COVID-19) has posed significant challenges globally, with image classification becoming a critical tool for detecting COVID-19 from chest X-ray and CT images. Convolutional neural network (CNN) architectures are widely employed for this purpose, yet many previous models have struggled to balance high accuracy with low storage requirements, limiting their applicability in resource-constrained environments. This paper introduces an efficient and lightweight CNN model optimized for COVID-19 diagnosis through pruning and quantization techniques, addressing these limitations. Our approach significantly reduces storage size and parameter count while maintaining high accuracy. We customized several CNNs, particularly EfficientNetV2 and MobileNetV2, to achieve these goals. We specifically selected EfficientNetV2 and MobileNetV2 due to their superior balance of accuracy and efficiency, making them well-suited for lightweight medical applications. EfficientNetV2’s storage size has been reduced from 568 to 142 KB through customized pruning, achieving 98.9% accuracy for 2-class and 98.28% for 3-class X-ray classification, as well as 98.3% and 98.05% for 2-class and 3-class CT classification, respectively. MobileNetV2, after hybrid pruning and quantization, achieved a remarkably low storage size of 70 KB, making it highly effective for deployment in environments with limited resources. Despite a slight accuracy decrease of 0.9 to 1.58%, both models have maintained robust performance suitable for COVID-19 diagnosis. The results demonstrate that our pruning and quantization techniques are effective in developing lightweight, high-performance CNN models, making them suitable for broader applications in medical imaging where both efficiency and accuracy are critical. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Impact of machine learning-based imputation techniques on medical datasets- a comparative analysis

引用

Multimedia Tools and Applications 2025年第9期84卷 5905-5925页

作者： Tiwaskar, Shweta Rashid, Mamoon Gokhale, Prasad Department of Computer Engineering Faculty of Science and Technology Vishwakarma University Pune India

In the realm of medical datasets, particularly when considering diabetes, the occurrence of data incompleteness is a prevalent issue. Unveiling valuable patterns through medical data analysis is crucial for early and precise medical predictions. However, the quality of data and the proper handling of missing data hold significant significance. To address this challenge, imputation stands as a robust approach. The main goal of this paper aims to provide a comprehensive investigation into the effects brought about by Machine Learning (ML) based imputation techniques, specifically K Nearest Neighbor Imputation (KNNI), Multiple Imputation by Chained Equations (MICE), and MissForest. Results of all three techniques are compared with the complete dataset for five missing rates (10% to 50%), and evaluated using four categories of evaluation criteria i.e. (1) model performance, (2) imputation error rate (Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), Coefficient of Determination (R^2) values), (3) Pearson correlation analysis and, (4) model selection basis (Bayesian information criterion (BIC), Akaike information criterion (AIC), values). Model performance includes accuracy, precision, recall, F1 score, and Matthews Correlation Coefficient (Mcoff) score of four ML classifiers viz. (a) Random Forest (RF), (b) Support vector machine (SVM), (c) AdaBoost, (d) XGBoost (XGB). For all missing rate cases, the MissForest technique is better than the KNNI and MICE in accuracy and Mcoff in 80% of cases, precision in 40% of cases, recall in 60% of cases, F1 score, MAE, RMSE, R^2 in 100% of cases, AIC in 80% of cases, and BIC values in 100% of cases. Also, the correlation analysis confirms that the MissForest imputation preserves association between the variables, like the complete dataset. Overall, our findings suggest that MissForest is a better machine learning-based imputation technique for handling missing data in diabetes research. © The Author(s), under exclusive lice

关键词： Adaptive boosting

来源：评论

学校读者我要写书评

暂无评论

Leveraging CuMeta for enhanced document classification in cursive languages with transformer stacking

引用

Multimedia Tools and Applications 2025年 1-26页

作者： Shahid, Muhammad Iqbal, Muhammad Amjad Umair, Muhammad Faculty of Information Technology and Computer Science University of Central Punjab Lahore Pakistan

Classifying textual data is crucial in the expanding digital landscape, especially for underrepresented cursive languages like Urdu, which pose unique challenges due to their intricate linguistic features and vast digital content. Despite the growing demand, research in effective Urdu text classification remains limited. This study introduces CuMeta, a novel meta-stacking classifier designed specifically to address these challenges. CuMeta integrates the strengths of various deep learning algorithms, including CNN and LSTM, alongside multiple Transformer-based models, to provide a comprehensive solution to issues such as tokenization, spatial inconsistencies, lack of case distinctions, and complex dialects inherent in Urdu. Through rigorous evaluation across diverse datasets, CuMeta has demonstrated its superiority over traditional and deep learning models, achieving an impressive F1-score of 97.52%. The innovative approach of CuMeta not only enhances text classification for Urdu but also offers significant implications for other low-resource, cursive-script languages like Arabic and Persian. This research marks a significant advancement in NLP, particularly for languages that have historically been underrepresented in digital and academic platforms. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Enhanced Distance-based Weighted K-Nearest Neighbor Algorithm for Data Classification

引用

KSII Transactions on Internet and Information Systems 2025年第4期19卷 1097-1121页

作者： Amer, Ali A. Ravana, Sri Devi Habeeb, Riyaz Ahamed Ariyaluran Department of Information Systems Faculty of Computer Science & Information Technology Universiti Malaya Malaysia

The k-Nearest Neighbors (kNN) algorithm is one of the most widely used techniques for data classification. However, the imbalanced class is a key problem for its declining performance. Therefore, the kNN algorithm is kept updated to mitigate this problem’s effects. Following the pattern of the literature, our paper proposes a novel weighted kNN that aims to significantly reduce the negative consequences of this problem. An enhanced distance-based weighted KNN, EDWkNN, is developed to improve the overall KNN performance. For the test sample, the number of neighbors (k) is initially determined. Next, normalized weights are computed for these neighbors and assigned a value between 0 and 1. The weights of the nearest and farthest neighbors are 1 and 0, respectively. The weight values of the remaining neighbors range from 0 to 1, with the closest one having a heavier weight and the farthest neighbor having a lower weight value. In extreme circumstances, a few neighbors have equal distance from the test sample, leading to assigning uniform weights to each of these neighbors. Further, the EDWkNN considers both the magnitude of the distance and the proximity of neighbors. Comparing EDWkNN to its state-of-the-art rivals, its simplistic architecture and competitive performance demonstrate its uniqueness. In four experimental phases, a thorough assessment study is conducted utilizing four evaluation metrics (accuracy, precision, recall, and MAE) over forty-four datasets. The findings show that, on average and for individual k values, EDWkNN is substantially promising. Copyright © 2025 KSII.

关键词： Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

Abnormal Data Detection Model Based on Autoencoder and Random Forest Algorithm: Camera Sensor Data in Autonomous Driving Systems

引用

International Journal of Advanced computer Science and Applications 2025年第3期16卷 222-231页

作者： Shengwen, Geng Osman, Mohd Hafeez Faculty of Computer Science and Information Technology Universiti Putra Malaysia Serdang43400 Malaysia

This project develops an AI-based anomaly detection system. In the field of autonomous driving, abnormal data will directly affect the safety of autonomous driving systems, especially in terms of abnormal camera sensor data. Sensor failure, environmental changes, or bad weather can lead to the emergence of abnormal data, which can affect the decision-making process and may have disastrous consequences. Based on the above problems, this study addresses this challenge by proposing a hybrid anomaly detection model (called CAE-RF) that combines convolutional autoencoders and random forest algorithms to achieve efficient and accurate identification of abnormal data patterns to improve the safety of autonomous driving systems. The proposed method will use convolutional autoencoders to calculate the reconstruction error and combine the hidden features extracted by the encoder as the input of the random forest to distinguish normal data from abnormal data. The key performance indicators such as accuracy, precision, recall, and F1 score are used to evaluate the model, and the robustness is guaranteed by cross-validation. Experimental results show that the CAE-RF model has an accuracy of 92% in distinguishing normal and abnormal data. Compared with traditional methods, the CAE-RF model achieves higher accuracy and reliability. The implementation of this model can timely identify and process abnormal data, reduce the risks brought by sensor failure or external environment changes, prevent potential accidents, and improve the safety and reliability of the autonomous driving system. © (2025), (Science and Information Organization). All rights reserved.

关键词： Tachometers

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：