检索结果-内蒙古大学图书馆

Probe Population Based Initialization and Genetic Pool Based Reproduction for Evolutionary Bi-Objective Feature Selection

引用

IEEE Transactions on Evolutionary Computation 2024年 1-1页

作者： Xu, Hang Xue, Bing Zhang, Mengjie School of Mechanical Electrical and Information Engineering Putian University Putian Fujian Province China Bing Xue and Mengjie Zhang with the Center for Data Science and Artificial Intelligence and School of Engineering and Computer Science Victoria University of Wellington Wellington New Zealand

Feature selection can be treated as a bi-objective optimization problem, if aimed at minimizing both classification error and number of selected features, suitable for multi-objective evolutionary algorithms (MOEAs) to solve. However, traditional MOEAs would encounter setbacks when the number of features explodes to high dimensionality, causing difficulties for searching optimal solutions in large-scale decision space. In this paper, we propose two general methods applicable to integrate with existing MOEA frameworks in addressing bi-objective feature selection, especially for high-dimensional datasets. One based on probe populations for improving initialization is called PPI, and the other based on genetic pools for improving reproduction is called GPR, both aimed at boosting the search ability of MOEAs. Tested on 20 datasets, in terms of four performance metrics (including the computational time), the experimental section can be divided into three parts. First, five state-of-the-art MOEAs are used as baseline algorithms to integrate with PPI and GPR, while the integrated versions are then compared with their own baselines. Second, the PPI method is additionally compared with three representative feature selection initialization methods to further identify its advantages. Third, a complete PPI and GPR based MOEA (termed PGMOEA) is proposed to compare with three cutting-edge evolutionary feature selection algorithms to further position its search ability. In general, it is suggested from the empirical results that either PPI or GPR can significantly improve the overall performance of each integrated MOEA, while adopting both of them takes the most complementary effect. IEEE

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

A Knowledge-and-data-Driven Modeling Approach for Mobile Payment Mode Recognition

A Knowledge-and-Data-Driven Modeling Approach for Mobile Pay...

引用

2024 China Automation Congress, CAC 2024

作者： Zhang, Li-Na Fan, Xing-Rong Zhang, Yu-Bu Engineering Research Centre for Waste Oil Recovery Technology and Equipment Ministry of Education Asset Management Department Chongqing Technology and Business University Chongqing China Engineering Research Centre for Waste Oil Recovery Technology and Equipment Ministry of Education Chongqing Technology and Business University Chongqing China School of Artificial Intelligence School of Computer Science and Information Engineering Chongqing Technology and Business University Chongqing China

ISBN: (纸本)9798350368604

Identifying different mobile payment modes based on cell phone signaling data in user movement is crucial for mobile payment scenario planning, payment risk assessment, and analyzing payment behavior patterns across multiple users. This paper proposes a novel knowledge-and-data-driven modeling approach to optimize the use of signaling data for mobile payment mode recognition. The approach integrates both unparsed signaling data and domain-specific URL-Key knowledge extracted from parsed signaling data that contains payment-related information. First, we develop a data-driven model for mobile payment event recognition, leveraging cell phone signaling data. Next, we establish a knowledge-driven model that utilizes domain URL-Key knowledge to identify mobile payment modes during user movement. These two models are then integrated using a composite coupling operator, and real data from a mobile telecommunication company located in Chongqing are used to calibrate and test our approach. Experimental results show that our approach significantly enhances both performance and efficiency. © 2024 IEEE.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

Harnessing Blockchain and Deep Learning for Enhanced Energy Analytics in Photovoltaic Systems

Harnessing Blockchain and Deep Learning for Enhanced Energy ...

引用

2024 International Conference on System, Computation, Automation and Networking, ICSCAN 2024

作者： Subbulakshmi, G. Sujatha, S. Saraswathi, V. Hemamlini, Ranganathan Rani St Joseph's College of Engineering and Technology Department of Artificial Intelligence and Data Science Engineering Chennai India Bit Campus Anna University Department of Computer Appication Tiruchirappalli India Chennai Institute of Technology Department of Computer Science Engineering Chennai India St. Peter's Institute of Higher Education and Research Department of Electrical and Elctronics Engineering Chennai India

ISBN: (纸本)9798331510022

The rapid evolution of solar energy in industrial sectors has sparked a growing interest in renewable energy, particularly within the context of smart grids and systems. The effective detection and management of energies within photovoltaic (PV) systems stand as crucial tasks in this landscape. This abstract introduces a proposed model aimed at exploring the integration of blockchain networks within large-scale solar energy infrastructures. The primary objective is to establish a framework that enables the distribution of solar energy in a decentralized manner to end-users while ensuring secure energy transactions between producers and consumers. Blockchain technology serves as the cornerstone of this model, encompassing intelligent techniques to address energy mitigation challenges within the solar energy network. By leveraging blockchain, the detection of energies within solar power plants becomes shared knowledge accessible to all users connected to the solar power network. The research within this framework emphasizes the exploration and application of diverse Deep Learning (DL) architectures, including autoencoders, Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM) networks, Deep Stacking Networks (DSNs), and Deep Belief Networks (DBNs). Furthermore, this research extends beyond conventional machine learning approaches, incorporating knowledge-driven methodologies. It incorporates generative models such as adversarial networks and transfer learning, elevating the scope of machine learning in optimizing energy detection, distribution, and consumption within the block chain-based solar energy infrastructure. This interdisciplinary approach signifies a significant stride in fortifying renewable energy systems. By amalgamating blockchain's decentralized nature with sophisticated DL architectures and knowledge-driven models, it establishes a resilient and efficient renewable energy infrastructure capable of meeting escalating demands for sustainabl

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Dynamic Scheduling for Semiconductor Manufacturing with High Uncertainty of Automated Material Handling System Capability 2

Deep Learning-Based Dynamic Scheduling for Semiconductor Man...

引用

2nd International Conference on data science and Information System, ICDSIS 2024

作者： Dineshkumar, R. Al-Attabi, Kassem Kumar, Komuravelly Sudheer Madhura, G.K. Sharma, Jaya Saveetha Institute Of Medical And Technical Sciences Saveetha University Saveetha School Of Engineering Department Of Ece Chennai India The Islamic University College Of Technical Engineering Department Of Computers Techniques Engineering Najaf Iraq Sr University School Of Computer Science & Artificial Intelligence Telangana Warangal India Nitte Meenakshi Institute Of Technology Department Of Artificial Intelligence And Machine Learning Bengaluru India Gitam University Department Of Cse Bengaluru India

ISBN: (纸本)9798350381665

To improve the dynamic responsiveness and production efficiency of manufacturing workshops to personalized orders, a multi-agent manufacturing system. However, the previous methods cannot work well in a changeable workshop environment when encountering a large number of stochastic disturbances of orders and resources. Develop a robust scheduling approach for dynamic workshop environments, effectively managing stochastic disturbances in orders and resources to optimize production efficiency and minimize disruptions. Dynamic scheduling approach for semiconductor manufacturing using Proximal Policy Optimization (PPO) and Autoencoder (AE) for feature extraction, defining state space to capture task and production attributes. Action space design employs dispatching rules for operation selection, while the reward function adapts production to demand, trained in action and state phases. Autoencoders compress high-dimensional input data into a lower-dimensional latent space while preserving important features. The obtained results demonstrate that the proposed method achieves better performance Delivery data Rate (DDR) of 41.20 %, Mean Cycle Time (MCT) of 51.66%, Mean of 12.85%, and Execution time of 5.07s. These results ensure superior dynamic scheduling performance compared to other existing methods, such as Dynamic Scheduling Using Flexible Job Shop Scheduling problem (FJSP), and Multiple-DynamicScheduling-Rule (MDSR). © 2024 IEEE.

关键词： Production efficiency

来源：评论

学校读者我要写书评

暂无评论

Multi-modal and Multi-perspective Machine Translation by Collecting Diverse Alignments 18th

Multi-modal and Multi-perspective Machine Translation by Col...

引用

18th Pacific Rim International Conference on artificial intelligence, PRICAI 2021

作者： Li, Lin Tayir, Turghun Hu, Kaixi Zhou, Dong School of Computer and Artificial Intelligence Wuhan University of Technology Wuhan China School of Computer Science and Engineering Hunan University of Science and Technology Xiangtan China

ISBN: (纸本)9783030893620

Multi-modal machine translation (MMT) is one of the most active research directions in the natural language processing. Recently, Seq2Seq translation model with images shows promising performance in enhancing translation quality. However, the existing technologies inadequately consider diverse multi-modal alignments when using different ways of adding images. We observe that this diversity can produce differentiated knowledge and further generates distinct translation outputs. In order to address the above problem, this paper proposes a Multi-perspective and Multi-modal Machine Translation Method by Collecting Diverse Alignments (M 3 -CoDA) which introduces different granularities of image features to the attention mechanism, aiming at forming diverse implicit multi-modal alignments. Moreover, those implicit alignments will produce MMT results from different perspectives. This paper further designs a sequence ensemble to aggregate multiple translation results. The experimental results on the Multi30k dataset show that our proposed method significantly improves translation quality compared with several popular baselines in terms of BLEU. © 2021, Springer Nature Switzerland AG.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

Cross-user Gesture Recognition Based on Deep Domain Adaptation Networks 43

Cross-user Gesture Recognition Based on Deep Domain Adaptati...

引用

43rd Chinese Control Conference, CCC 2024

作者： Fu, Zhongzheng He, Xinrun Wang, Haoyuan Chen, Xingjian Li, Yixuan Huang, Jian Huazhong University of Science and Technology Ministry of Education Key Laboratory of Image Processing and Intelligent Control Hubei Key Laboratory of Brain-inspired Intelligent Systems School of Artificial Intelligence and Automation Wuhan430074 China

ISBN: (纸本)9789887581581

This study introduces an innovative approach for gesture recognition in smart wearable devices using a deep domain adaptation model, focusing on the challenges posed by heterogeneous user environments and the need for precise, adaptable, and personalized gesture recognition systems. Traditional methods based on machine learning and deep learning techniques, while effective, struggle with the variance in data distribution among different users, leading to accuracy challenges. To address this, the study proposes the Domain Kernel-Alignment Adaptation Network (DKAN) model, utilizing a new Kernel-Aligned Multi-kernel Maximum Mean Discrepancy (KAMMD) method within deep networks. By calculating kernel alignments between source and target domains and adjusting weights of Gaussian kernels accordingly, DKAN emphasizes features conducive to transfer learning, enabling more accurate cross-user gesture recognition. The model achieves a significant average accuracy of 97.3% across 21 gestures, highlighting its potential in practical applications. This advancement addresses challenges in traditional gesture recognition methods and sets a new direction for future research in smart wearable technology. © 2024 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Random Forest based Coral Reef Health Classification Using Satellite Imagery and Geographical Information System

Random Forest based Coral Reef Health Classification Using S...

引用

2024 International Conference on Intelligent Algorithms for Computational intelligence Systems, IACIS 2024

作者： Jagadish, Sripelli Pradeep Kumar, S. Riad Al-Fatlawy, Ramy Ameer, S. Abdul Kiran, J. Sr University School of Computer Science & Artificial Intelligence Warangal India Nitte Meenakshi Institute of Technology Department of Ece Bengaluru India The Islamic University Engineering College of Technical Engineering Department of Computers Techniques Najaf Iraq Ahl Al Bayt University Karbala Iraq Reva University School of Computing and Information Technology Bengaluru India

ISBN: (纸本)9798350360660

Understanding the coral reefs' health in varied climate changes is challenging with the traditional methods. To address this, the proposed research developed a Machine Learning (ML) framework for effective classification using Geographical Information System (GIS). The data in this research, is collected from Great Barrier Reef (GBR) in Australia which includes the satellite Landsat 8 images for monitoring coral reefs condition. The data is pre-processed using normalization and scatter plots to analyse various coral reef classes using the training samples. The images features are extracted using Gray-Level Co-occurrence Matrix (GLCM) and analysed the spectral indices to capture specific type of information about the coral reefs. The coral reef images are then segmented using Pixel Based (PB) and Object Based (OB) segmentation to achieve effective Coral Reef Health Classification (CRHC). To analyse the large amount of data with the non-linear relationships between the variables, the Random Forest (RF) classifier is used. The experimental results showed that the proposed RF-CRHC achieved better accuracy with 99.59% and precision with 97.79% when compared to the existing methods Multi-Local Perception Network (ML-Net) and Clustering based RF. © 2024 IEEE.

关键词： Landsat

来源：评论

学校读者我要写书评

暂无评论

Predicting Pedestrian Movement in Unsignalized Crossings: A Contextual Cue-Based Approach

Predicting Pedestrian Movement in Unsignalized Crossings: A ...

引用

International Communication Systems and Networks and Workshops, COMSNETS

作者： Kaliprasana Muduli Vikas Sahu Indrajit Ghosh Civil Engineering Department Indian Institute of Technology Roorkee Roorkee India Mehta Family School of Data Science and Artificial Intelligence Indian Institute of Technology Roorkee Roorkee India Civil Engineering Department & Joint Faculty Mehta Family School of Data Science and Artificial Intelligence Indian Institute of Technology Roorkee Roorkee India

To ensure safe and secure coexistence between pedestrians and autonomous vehicles (AVs), AVs must be able to anticipate pedestrian behavior and respond to it. This research gathers video data from real traffic scenes to predict pedestrian crossing intentions at unsignalized crossings. computer vision techniques such as YOLOv4, Deep SORT, and perspective transformation are employed for road user detection, tracking, and mapping image coordinates to world coordinates to prepare trajectory datasets. Using trajectory data, several features influencing pedestrian intention like walking speed, location in the road environment, count and direction of approaching traffic, speed and type of closest approaching vehicle upstream, etc., are extracted. The dataset for this study was obtained by analyzing 1,411 pedestrians, resulting in 223,136 samples. To predict pedestrian crossing intentions, LSTM and Bi-LSTM with an attention mechanism model were built and trained to anticipate the pedestrian crossing intention at unsignalized crossing. The proposed model successfully combined the characteristics and surrounding dynamics of pedestrians to produce accurate predictions, Bi-LSTM with an attention mechanism outperformed LSTM, achieving an AUC of 95.3%, 91.1%, 89.2%, 87.5%, and 84% on the testing dataset at unsignalized crossing on the 0.6 sec, 1.2 s, 1.8 s, 2.4 s, and 3 s time horizons. These outcomes can be used to improve Connected and Autonomous Vehicle (CAV) technologies, infrastructure-to-vehicle (I2V) connectivity, and driver assistance systems to enhance pedestrian safety while navigating through pedestrian crosswalks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Rethinking independent cross-entropy loss for graph-structured data 24

Rethinking independent cross-entropy loss for graph-structur...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Rui Miao Kaixiong Zhou Yili Wang Ninghao Liu Ying Wang Xin Wang School of Artificial Intelligence Jilin University China Institute for Medical Engineering Science Massachusetts Institute of Technology School of Computing University of Georgia College of Computer Science and Technology Jilin University China

Graph neural networks (GNNs) have exhibited prominent performance in learning graph-structured data. Considering node classification task, based on the i.i.d assumption among node labels, the traditional supervised learning simply sums up cross-entropy losses of the independent training nodes and applies the average loss to optimize GNNs' weights. But different from other data formats, the nodes are naturally connected. It is found that the independent distribution modeling of node labels restricts GNNs' capability to generalize over the entire graph and defend adversarial attacks. In this work, we propose a new framework, termed joint-cluster supervised learning, to model the joint distribution of each node with its corresponding cluster. We learn the joint distribution of node and cluster labels conditioned on their representations, and train GNNs with the obtained joint loss. In this way, the data-label reference signals extracted from the local cluster explicitly strengthen the discrimination ability on the target node. The extensive experiments demonstrate that our joint-cluster supervised learning can effectively bolster GNNs' node classification accuracy. Furthermore, being benefited from the reference signals which may be free from spiteful interference, our learning paradigm significantly protects the node classification from being affected by the adversarial attack.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MambaEVT: Event Stream based Visual Object Tracking using State Space Model

arXiv

引用

arXiv 2024年

作者： Wang, Xiao Wang, Chao Wang, Shiao Wang, Xixi Zhao, Zhicheng Zhu, Lin Jiang, Bo School of Computer Science and Technology Anhui University Hefei China School of Artificial Intelligence Anhui University Hefei China Beijing Institute of Technology Beijing China

Event camera-based visual tracking has drawn more and more attention in recent years due to the unique imaging principle and advantages of low energy consumption, high dynamic range, and dense temporal resolution. Current event-based tracking algorithms are gradually hitting their performance bottlenecks, due to the utilization of vision Transformer and the static template for target object localization. In this paper, we propose a novel Mamba-based visual tracking framework that adopts the state space model with linear complexity as a backbone network. The search regions and target template are fed into the vision Mamba network for simultaneous feature extraction and interaction. The output tokens of search regions will be fed into the tracking head for target localization. More importantly, we consider introducing a dynamic template update strategy into the tracking framework using the Memory Mamba network. By considering the diversity of samples in the target template library and making appropriate adjustments to the template memory module, a more effective dynamic template can be integrated. The effective combination of dynamic and static templates allows our Mamba-based tracking algorithm to achieve a good balance between accuracy and computational cost on multiple large-scale datasets, including EventVOT, VisEvent, and FE240hz. Source code of this work will be released. Copyright © 2024, The Authors. All rights reserved.

关键词：

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：