检索结果-内蒙古大学图书馆

Weighted rank aggregation based on ranker accuracies for feature selection

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

DXDSENet-CM model: an ensemble learning model based on depthwise Squeeze-and-Excitation ConvMixer architecture for the classification of multi-class skin lesions

引用

Multimedia Tools and Applications 2025年第12期84卷 9903-9938页

作者： Fırat, Hüseyin Üzen, Hüseyin Department of Computer Engineering Faculty of Engineering Dicle University Diyarbakır Turkey Department of Computer Engineering Faculty of Engineering and Architecture Bingol University Bingol Turkey

Skin cancer is acknowledged as the most prevalent form of cancer on a global scale. Failure to detect it in its initial phases can lead to fatality, underscoring the significance of early diagnosis. While visible to the naked eye, the considerable similarities between different classes and the variations within a single class create substantial hurdles for accurate detection. Given the widespread occurrence of this ailment, numerous deep learning-driven automated systems have been created to aid dermatologists in promptly identifying skin anomalies. Within this investigation, an ensemble learning architecture based on Xception, DenseNet201 and Depthwise Squeeze-and-Excitation Network and ConvMixer (DSENet-ConvMixer) architectures is presented for skin lesion classification. Xception, a pre-trained CNN network, utilizes depthwise separable convolutions and residual connections, offering efficient feature extraction from skin lesion images. DenseNet201’s parameter efficiency, feature reuse, and multi-scale information capture make it a valuable addition. DSENet-ConvMixer integrates these components, efficiently merging low-level and high-level features to enhance training and network efficiency. ConvMixer excels at feature extraction, enhancing spatial detail capture. ISIC 2018 and 2019 datasets were employed to assess the classification performance of the proposed architecture. Individual accuracies for Xception, DenseNet201, and DSENet-ConvMixer in ISIC 2018 were 85.91%, 85.71%, 82.02%, respectively, and in ISIC 2019 were 80.93%, 80.50%, 79.08%, respectively. However, the ensemble architecture with these three architectures achieved 88.21% for ISIC 2018 and 92.34% for ISIC 2019, demonstrating superior performance. Literature reviews on both datasets also confirmed the proposed architecture’s effectiveness compared to recent studies. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, 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

Combining evolutionary and swarm algorithms in a hybrid subspace-wise search strategy for feature selection

引用

Cluster Computing 2025年第5期28卷 1-26页

作者： Mohammadi, Mahsa Ramezani, Mohsen Akhlaghian Tab, Fardin Ahmadizar, Fardin Department of Computer Engineering Faculty of Engineering University of Kurdistan Sanandaj Iran Department of Industrial Engineering Faculty of Engineering University of Kurdistan Sanandaj Iran

In recent years, hybrid feature selection methods incorporating global–local frameworks have gained significant attention due to their advantages. Leveraging the capabilities of swarm and evolutionary algorithms, we propose a modified Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) algorithm within a bi-level global–local search framework to achieve improved exploration while maintaining comparable execution time. In this method, we introduce a modified GA to perform the global search step using a subspace-wise search strategy. The primary motivation behind this approach is to reduce the search space, enabling the method to consider all parts of the space and avoid getting trapped in local optima. To enhance diversity without increasing complexity, we introduce a novel encoding scheme where each chromosome represents a subspace of solutions instead of a single solution. During each iteration, the PSO algorithm is employed to perform local search and identify high-quality solutions within each subspace. This step can be applied to subspaces in parallel to make the method faster. Notably, the PSO algorithm is applied only to specific dimensions of the individuals, resulting in significantly faster computation. Consequently, the solution selected by the PSO within each subspace serves as the basis for evaluating the fitness of the corresponding chromosome. Experiments conducted on 30 well-known datasets demonstrate that our method exhibits significantly better performance compared to state-of-the-art methods, both in low and high-dimensional data settings. Furthermore, our method demonstrates stability, making it suitable for real-world applications. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

Dynamic Multi-Graph Spatio-Temporal Graph Traffic Flow Prediction in Bangkok:An Application of a Continuous Convolutional Neural Network

引用

computer Modeling in engineering & Sciences 2025年第1期142卷 579-607页

作者： Pongsakon Promsawat Weerapan Sae-dan Marisa Kaewsuwan Weerawat Sudsutad Aphirak Aphithana Department of Civil Engineering Faculty of EngineeringRamkhamkaeng UniversityBangkok10240Thailand Department of Computer Engineering Faculty of EngineeringRamkhamkaeng UniversityBangkok10240Thailand Department of Statistics Faculty of ScienceRamkhamkaeng UniversityBangkok10240Thailand

The ability to accurately predict urban traffic flows is crucial for optimising city ***,various methods for forecasting urban traffic have been developed,focusing on analysing historical data to understand complex mobility *** learning techniques,such as graph neural networks(GNNs),are popular for their ability to capture spatio-temporal ***,these models often become overly complex due to the large number of hyper-parameters *** this study,we introduce Dynamic Multi-Graph Spatial-Temporal Graph Neural Ordinary Differential Equation Networks(DMST-GNODE),a framework based on ordinary differential equations(ODEs)that autonomously discovers effective spatial-temporal graph neural network(STGNN)architectures for traffic prediction *** comparative analysis of DMST-GNODE and baseline models indicates that DMST-GNODE model demonstrates superior performance across multiple datasets,consistently achieving the lowest Root Mean Square Error(RMSE)and Mean Absolute Error(MAE)values,alongside the highest *** the BKK(Bangkok)dataset,it outperformed other models with an RMSE of 3.3165 and an accuracy of 0.9367 for a 20-min interval,maintaining this trend across 40 and 60 ***,on the PeMS08 dataset,DMST-GNODE achieved the best performance with an RMSE of 19.4863 and an accuracy of 0.9377 at 20 min,demonstrating its effectiveness over longer *** Los_Loop dataset results further emphasise this model’s advantage,with an RMSE of 3.3422 and an accuracy of 0.7643 at 20 min,consistently maintaining superiority across all time *** numerical highlights indicate that DMST-GNODE not only outperforms baseline models but also achieves higher accuracy and lower errors across different time intervals and datasets.

关键词： Graph neural networks convolutional neural network deep learning dynamic multi-graph spatio-temporal

来源：评论

学校读者我要写书评

暂无评论

Drug–target interactions prediction based on similarity graph features extraction and deep learning

引用

Neural Computing and Applications 2025年第6期37卷 4303-4322页

作者： Torkey, Hanaa El-Behery, Heba Attia, Abdel-Fattah El-Fishawy, Nawal Computer Science and Engineering Department Faculty of Electronic Engineering Menoufia University Menouf Egypt Department of Computer Science and Engineering Faculty of Engineering Kafrelsheikh University Kafrelsheikh Egypt Department of Computer Science College of Computer Engineering and Sciences Prince Sattam Bin Abdulaziz University Al-Kharj Saudi Arabia

Identifying drug–target interactions (DTIs) is a critical step in both drug repositioning. The labor-intensive, time-consuming, and costly nature of classic DTI laboratory studies makes it imperative to create efficient computer algorithms to forecast possible DTIs. However, current computational approaches that predict potential drug–target interactions (DTIs) suffer from some limitations, like finding the best similarity measures or negative samples, and thus require substantial performance improvement. This study proposes an integrated approach based on feature representation and deep learning to predict DTIs. We extract the relevant features of drugs and proteins from heterogeneous networks using graph mining techniques. The proposed approach constructs a heterogeneous graph from the known drug–protein interactions, protein–protein, and drug–drug similarities. Then applying two feature extraction techniques to extract the features, then utilizing these features in training a deep learning model to predict the potential DTIs. Also, a novel algorithm is proposed to find the negative samples based on the drug and protein similarity matrices. Four Benchmark datasets are used to evaluate the proposed approach. Our approach achieves the highest AUC (area under the ROC curve) across all datasets (0.98) with around 2% increases over the existing methods. Experimental results demonstrate that our proposed approach outperforms the baseline methods in predicting DTI, and our negative sample-identifying algorithm could be established as a competitive solution. © 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

A new bi-level deep human action representation structure based on the sequence of sub-actions

引用

Neural Computing and Applications 2025年第2期37卷 985-1008页

作者： Akhlaghian Tab, Fardin Ramezani, Mohsen Afshoon, Hadi Seyedi, Seyed Amjad Moradyani, Atefeh Department of Computer Engineering Faculty of Engineering University of Kurdistan Sanandaj Iran Department of Computer Science University of Kurdistan Sanandaj Iran

Human action recognition is applicable in different domains. Previously proposed methods cannot appropriately consider the sequence of sub-actions. Herein, we propose a semantical action model based on the sequence of sub-actions. A technique is used to segment actions on the time axis based on body movements via an energy diagram. After dividing actions into sub-actions, a novel bi-level deep structure is used to extract their features. Then, the sequence of sub-action features is modeled by a deep network to create the action model. As extracted sub-actions have fewer variations in execution manner, their representation is more stable, and modeling their sequence would be an efficient model. Experimental results on UCF-YouTube, UCF-Sport, and Human Motion DataBase (HMDB) datasets indicate the sustainable performance of this method. Overall, the accuracy of the proposed method is 0.972 on average, while the value for the second-best method is 0.925. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Human form models

来源：评论

学校读者我要写书评

暂无评论

A novel data-driven algorithm for object detection, tracking, distance estimation, and size measurement in stereo vision systems

引用

Multimedia Tools and Applications 2025年第12期84卷 11041-11061页

作者： Taromi, Amirhossein Dadashzadeh Klidbary, Sajad Haghzad Department of Engineering University of Zanjan Zanjan Iran Faculty of Engineering Department of Electrical and Computer Engineering University of Zanjan Zanjan Iran

Distance and size estimation of objects of interests is an inevitable task for many navigation and obstacle avoidance algorithms mainly used in autonomus and robotic systems. Stereo vision systems, inspired by human visual perception, can infer depth from images as a cheap and accessible solution. On one hand, accurately calibrating cameras is a challenging task and the main source of error in current stereo vision based distance and size estimation algorithms. On the other hand, considering the recent advancements in Deep Learning, alongside the fact that human eyes do not need calibration but human brain can estimate the distance and size of objects fairly accurate was the main motivation behind this study. The proposed algorithm uses YOLOv8 as the object detector, and an MLP to learn the relation between distance, size, and disparity from collected data in a stereo vision system. In our experiments, conducted at distances ranging from 50 to 200 centimeters with calibrated and uncalibrated cameras, our proposed algorithm showcased accurate performance in both scenarios. It achieved distance measurements with an accuracy of up to 99.99% in select cases and maintained the mean accuracy of 98.15% for distance, 92.87% for width, and 93.92% for height estimations. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

A new approach data processing: density-based spatial clustering of applications with noise (DBSCAN) clustering using game-theory

引用

Soft Computing 2025年第3期29卷 1331-1346页

作者： Kazemi, Uranus Soleimani, Seyfollah Department of Computer Engineering Faculty of Engineering Arak University Arak38156-8-8349 Iran

Due to the unpredictable growth of data in various fields, rapid clustering of big data is seriously needed in order to identify the hidden structure of data and discover the relationships between objects. Among clustering methods, density-based clustering methods have an acceptable processing speed for dealing with big data with high dimensions. However, some methods have fixed parameters that are certainly not optimized for all sections. In addition, the complexity of these clustering methods strongly depends on the number of objects. In this paper, a clustering method is presented in order to increase clustering performance and parameter sensitivity according to game-theory and using the concept of Nash equilibrium and dense games, the optimal parameter for clustering is selected and between noise and points clusters make a difference. This method includes (1) searching the grid with several spaces in which there is no cluster, (2) identifying the player through high density data points in order to determine the parameters and (3) combining the clusters to make the game and (4) merging the nearby clusters. The performance of the proposed method was evaluated in four big synthetic datasets, eight real datasets labeled and unlabeled. The obtained results indicate the superiority of the proposed method over SOM, K-means, DBSCAN, SCGPSC methods in terms of accuracy and purity in processing time. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Nash equilibrium

来源：评论

学校读者我要写书评

暂无评论

Better with fewer features: climate dynamics estimation for Van Lake basin using feature selection

引用

Environmental Science and Pollution Research 2025年第10期32卷 5849-5873页

作者： Çoban, Önder Esit, Musa Yalçın, Sercan Bozkurt, Ferhat Department of Computer Engineering Faculty of Engineering Ataturk University Erzurum Turkey Department of Civil Engineering Adıyaman University Adıyaman Turkey Department of Computer Engineering Adıyaman University Adıyaman Turkey

Even though there exist many research efforts trying to develop forecasting models based on machine learning (ML) or statistical techniques, feature selection is not employed in a large majority of the studies. To fill this gap, this study builds prediction models involving feature selection through one-step ahead estimation of climatological parameters (i.e., temperature and evapotranspiration), considering the aforementioned shortcomings. In addition, the best models are used to make estimations for a long horizon of 30 years. The experimental results performed on three stations located at the Van Lake Closed basin of Turkey showed that the Bayesian Ridge regressor (BRR) often outperforms other regressors. The respective best models involving BRR also enabled us to obtain R2 scores ranging from 0.961 to 0.988. On the other hand, feature selection helps us to reach or go beyond the respective baseline performance of any model by using a lower number of features. Finally, the overall evaluation is stated to have a limitation in that it needs non-sparse and complete time series data to produce satisfying results. It will also be a challenging task to employ our regression-based ML pipeline on any sparse time series dataset. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

VoteDroid: a new ensemble voting classifier for malware detection based on fine-tuned deep learning models

引用

Multimedia Tools and Applications 2025年第12期84卷 10923-10944页

作者： Bakır, Halit Faculty of Engineering and Natural Sciences Department of Computer Engineering Sivas University of Science and Technology Sivas Turkey

In this work, VoteDroid a novel fine-tuned deep learning models-based ensemble voting classifier has been proposed for detecting malicious behavior in Android applications. To this end, we proposed adopting the random search optimization algorithm for deciding the structure of the models used as voter classifiers in the ensemble classifier. We specified the potential components that can be used in each model and left the random search algorithm taking a decision about the structure of the model including the number of each component that should be used and its location in the structure. This optimization method has been used to build three different deep learning models namely CNN-ANN, pure CNN, and pure ANN. After selecting the best structure for each DL model, the selected three models have been trained and tested using the constructed image dataset. Afterward, we suggested hybridizing the fine-tuned three deep-learning models to form one ensemble voting classifier with two different working modes namely MMR (Malware Minority Rule) and LMR (Label Majority Rule). To our knowledge, this is the first time that an ensemble classifier has been fine-tuned and hybridized in this way for malware detection. The results showed that the proposed models were promising, where the classification accuracy exceeded 97% in all experiments. © The Author(s) 2024.

关键词： Android malware

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：