检索结果-内蒙古大学图书馆

11th International Conference on Machine Intelligence Theory and Applications, MiTA 2024

作者： Zheng, Xin Li, Jian-Yu Yang, Qiang Duan, Dan-Ting Zhan, Zhi-Hui Henan Normal University College of Computer and Information Engineering Xinxiang453000 China Nankai University College of Artificial Intelligence Tianjin300350 China Nanjing University of Information Science and Technology School of Artificial Intelligence Jiangsu China Beijing China

ISBN: (纸本)9798350385670

With the development of information technology, large-scale optimization problem is the core issue in various applications. Due to the high dimension characteristics, large-scale optimization problems are challenging to solve. Therefore, this paper proposes a competition-based stochastic learning particle swarm optimization algorithm (CSLPSO) for solving large-scale optimization problems efficiently, which has two novel designs. First, a competition-based stochastic learning strategy is proposed to improve the exploration ability of PSO. Second, a parameter control mechanism suitable for the CSLPSO algorithm is proposed, so that the algorithm does not require manual parameter selection. In the experiment, the CSLPSO algorithm is applied to 12 large-scale problems with state-of-the-art algorithms as competitors. The experimental results show the effectiveness of the proposed CSLPSO. © 2024 IEEE.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

JPAVE: A Generation and Classification-based Model for Joint Product Attribute Prediction and Value Extraction

JPAVE: A Generation and Classification-based Model for Joint...

引用

2023 IEEE International Conference on Big Data, BigData 2023

作者： Deng, Zhongfen Peng, Hao Zhang, Tao Liu, Shuaiqi Zhao, Wenting Wang, Yibo Yu, Philip S. University of Illinois Chicago Department of Computer Science ChicagoIL60607 United States Beihang University School of Cyber Science and Technology Beijing China The Hong Kong Polytechnic University Department of Computing Hong Kong

ISBN: (纸本)9798350324457

Product attribute value extraction is an important task in e-Commerce which can help several downstream applications such as product search and recommendation. Most previous models handle this task using sequence labeling or question answering method which rely on the sequential position information of values in the product text and are vulnerable to data discrepancy between training and testing. This limits their generalization ability to real-world scenario in which each product can have multiple descriptions across various shopping platforms with different composition of text and style. They also have limited zero-shot ability to new values. In this paper, we propose a multi-task learning model with value generation/classification and attribute prediction called JPAVE to predict values without the necessity of position information of values in the text. Furthermore, the copy mechanism in value generator and the value attention module in value classifier help our model address the data discrepancy issue by only focusing on the relevant part of input text and ignoring other information which causes the discrepancy issue such as sentence structure in the text. Besides, two variants of our model are designed for open-world and closed-world scenarios. In addition, copy mechanism introduced in the first variant based on value generation can improve its zero-shot ability for identifying unseen values. Experimental results on a public dataset demonstrate the superiority of our model compared with strong baselines and its generalization ability of predicting new values. © 2023 IEEE.

关键词： attribute value generation multi-task learning product attribute value extraction value classification

来源：评论

学校读者我要写书评

暂无评论

Enhancing Wireless Sensor Network Efficiency through Al-Biruni Earth Radius Optimization

引用

computers, Materials & Continua 2024年第6期79卷 3549-3568页

作者： Reem Ibrahim Alkanhel Doaa Sami Khafaga Ahmed Mohamed Zaki Marwa M.Eid Abdyalaziz A.Al-Mooneam Abdelhameed Ibrahim S.K.Towfek Department of Information Technology College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Computer Science and Intelligent Systems Research Center BlacksburgVirginia24060USA Delta Higher Institute for Engineering and Technology Mansoura35511Egypt Faculty of Artificial Intelligence Delta University for Science and TechnologyMansoura35712Egypt Artificial Intelligence and Computational Intelligence Research Center MeridenConnecticut06450USA School of ICT Faculty of EngineeringDesign and Information&Communications Technology(EDICT)Bahrain PolytechnicP.O.Box 33349Isa TownBahrain

The networks of wireless sensors provide the ground for a range of applications,including environmental moni-toring and industrial *** the networks can overcome obstacles like power and communication reliability and sensor coverage is the crux of network *** infrastructure planning should be focused on increasing performance,and it should be affected by the detailed data about node *** work recommends the creation of each sensor’s specs and radius of influence based on a particular geographical location,which will contribute to better network planning and *** using the ARIMA model for time series forecasting and the Al-Biruni Earth Radius algorithm for optimization,our approach bridges the gap between successive terrains while seeking the equilibrium between exploration and *** implementing adaptive protocols according to varying environments and sensor constraints,our study aspires to improve overall network *** compare the Al-Biruni Earth Radius algorithm along with Gray Wolf Optimization,Particle Swarm Optimization,Genetic Algorithms,and Whale Optimization about performance on real-world *** the most efficient in the optimization process,Biruni displays the lowest error rate at *** two other statistical techniques,like ANOVA,are also useful in discovering the factors influencing the nature of sensor data and network-specific *** to the multi-faceted support the comprehensive approach promotes,there is a chance to understand the dynamics that affect the optimization outcomes better so decisions about network design can be *** delivering better performance and reliability for various in-situ applications,this research leads to a fusion of time series forecasters and a customized optimizer algorithm.

关键词： Wireless sensor networks optimization ARIMA model BER algorithm metaheuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

An Ensemble Learning Approach for Wind Power Forecasting 3

An Ensemble Learning Approach for Wind Power Forecasting

引用

3rd International Conference on Electronic Information Engineering and computer, EIECT 2023

作者： Huang, Yuesheng Chen, Sida Wu, Qiling Xiao, Jiapeng Ren, Yongqi Wang, Leijun Chen, Rongjun Li, Jiawen Guangdong Polytechnic Normal University School of Computer Science Guangzhou China Wuhan University of Science and Technology Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan China

ISBN: (纸本)9798350357707

With the growing global energy demand and requirement for environmental protection, renewable energy is attracting attention as a vital development direction. Particularly, wind power is rapidly developing as a clean and sustainable form of energy. Nonetheless, wind speed uncertainty and system dynamics make wind power prediction and optimization complex and challenging. Accurate wind power prediction is essential to improve system reliability and performance. In this regard, traditional forecasting methods have limitations in some cases. In this study, based on XGBoost and decision tree with Bagging methods in ensemble learning, wind power data is predicted. The results indicated that better performances than the traditional linear regression and ordinary decision tree models are achieved, revealing the efficiency of the proposed approach. © 2023 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Time-Sensitive Local Differential Privacy-Based Federated Learning for Vehicular Digital Twin Networks 1st

Time-Sensitive Local Differential Privacy-Based Federated Le...

引用

1st International Symposium on Intelligent Computing and Networking, ISICN 2024

作者： Sun, Kangkang Xu, Hansong Zhang, Xiaojin Hua, Kun Li, Jianhua Shanghai Key Laboratory of Integrated Administration Technologies for Information Security School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China Department of Electrical Engineering California Polytechnic State University San Luis ObispoCA93407 United States

ISBN: (纸本)9783031674464

The Vehicular Digital Twin Network (VDTN) integrates digital twin (DT) models of connected and autonomous vehicles (CAVs) to facilitate smart sensing, management, and collaboration in the physical realm. VDTN synchronizes extensive data on roads, vehicles, and operators, including sensitive information like user location and driving habits. To address these privacy concerns and enhance model efficiency, we introduce a time-sensitive local differential privacy-based federated learning framework (FedTS) tailored for VDTN. This framework assigns varying privacy levels to DT models during model-sharing intervals, considering the time sensitivity of VDTNs. Comparative analysis with state-of-the-art algorithms, such as differentially-private stochastic gradient descent (DP-SGD), demonstrates significant improvements in both security and model performance. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Credit Approval Decision using Machine Learning Algorithms 10

Credit Approval Decision using Machine Learning Algorithms

引用

10th International Conference on Reliability, Infocom Technologies and Optimization ,Trends and Future Directions, ICRITO 2022

作者： Mridha, Krishna Barua, Dipayan Shorna, Meghla Monir Nouman, Hasan Nouman Kabir, Md Hasanul Singh, Ajay Vikram Marwadi University Computer Engineering Rajkot India Marwadi Univeristy Informaation Technology Rajkot India Daffodil International University Computer Science and Engineering Dhaka Bangladesh Henan Polytechnic University Computer Science & Technology China Aiit Amity University Uttar Pradesh Noida India

ISBN: (数字)9781665474337

ISBN: (纸本)9781665474337

The credit approval process for customers seeking a loan has been an important and risky full decision to take for banking institutions. The standard procedure involves a host of information regarding the customer based on what the bankers decide whether to grant a loan which often is time-taking and exhaustive. Therefore, this paper proposes a solution based on machine learning algorithms that reduce risk factors associated with the customer's behaviors that could suggest selecting a trusted person to save the bank's effort and assets. The method utilizes customer information such as monthly income, prior loan history, investment, education, gender, etc., up to twelve attributes that are further used to construct a machine learning model of the decision-making on credit approval. Five different machine learning algorithms named Gradient Booster (GB), Support Vector Machine (SVM), Random Forest (RF), K-Nearest Neighbor (K-NN), and Gradient Booster Classification (GB) are built with a 90% training dataset. Among these, LR has reported the best accuracy as much as 80.43% for the available dataset. We applied these methods to a dataset collected from Kaggle, which contains 615 rows and 13 columns where rows represent customers and columns feature and decisions on credit in 'yes' or 'no'. Future work includes the attempt to improve prediction accuracy with the application deep learning algorithm. © 2022 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Visual Fileless Malware Classification via Few-shot Learning

Visual Fileless Malware Classification via Few-shot Learning

引用

2023 International Conference on Cyber Security, Artificial Intelligence, and Digital Economy, CSAIDE 2023

作者： Jiang, Liyan Zhang, Yu Shi, Yuanquan School of Information Science and Technology Hainan Normal University Haikou571158 China School of Cybersecurity Guangdong Polytechnic Normal University Guangzhou510665 China School of Computer and Artificial Intelligence Huaihua University Hunan Huaihua418000 China

ISBN: (纸本)9781510666597

The use of fileless technologies in malware continues to grow and fileless malware becomes more dangerous and difficult to detect. To address this challenge, we propose a novel visual method for classifying fileless malware based on few-shot learning. First, we built a fileless malware dataset, which is executed through a local virtual environment to collect malware memory dumps. Secondly, memory dumps are clipped and visualized. We developed a new memory dumps trimming method and a novel binary file visualization technique, which can remove redundant data from memory dumps, significantly compress the file size, and then represent the trimmed memory dumps as RGB images. Finally, we propose a few-shot learning framework, namely MMEL (MAML + Mean_subtraction + Euclidean_normalization + Label_Smothing), to improve the performance of the classification method. Experimental results show that our visualization technique and framework outperform other state-of-the-art few-shot learning methods. © 2023 SPIE.

关键词： Malware

来源：评论

学校读者我要写书评

暂无评论

Locality sensitive hashing-driven multifactorial evolutionary algorithms for multitask optimization

引用

Applied Soft Computing 2023年 132卷

作者： Yu, Tuo-Bin Zhang, Yu-Hui Gong, Yue-Jiao Li, Yuan School of Computer Science and Engineering South China University of Technology Guangzhou China School of Computer Science and Technology Dongguan University of Technology Dongguan China School of Computer and Information Engineering Henan Normal University Xinxiang China

In recent years, evolutionary multitasking optimization (EMTO) has attracted considerable attention. Different from the traditional algorithms that solve one optimization problem at a time, EMTO aims at solving multiple problems simultaneously, through transferring useful information among individuals. The most well-known algorithm in this area is the multifactorial evolutionary algorithm (MFEA). However, when designing the information sharing mechanism, MFEA and its variants focus solely on the properties of individuals in the objective space, while neglecting the valuable information in the decision space. To make full use of the inherent knowledge of the evolving population, this paper presents a novel EMTO framework by using the locality sensitive hashing (LSH) method to analyze the population distribution in the decision space and then guide the information sharing. Specifically, LSH uses hash functions to map the individuals in the decision space into hash codes, ensuring that similar individuals have a higher probability to be mapped into the same code. Then, based on the matching relationships of the hash codes and skill factors between individuals, different reproduction and evaluation strategies are exerted to satisfy the specific requirements under different conditions. This way, the knowledge from both the decision space and the objective space are utilized for the purpose of better manipulating the individuals. Additionally, an opposition-based learning method is integrated in this algorithm to enhance exploration. The comprehensive experimental studies confirm the efficacy and efficiency of the proposed method on both single-objective multitask benchmarks and multi-objective multitask benchmarks. According to the statistic tests, the proposed single-objective and multi-objective algorithms significantly outperform their best competitors on 14/18 and 12/18 tasks, respectively. © 2022 Elsevier B.V.

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Transforming Diabetes Care: A Review of IoT-Based Mobile Health Systems 10th

Transforming Diabetes Care: A Review of IoT-Based Mobile He...

引用

10th EAI International Conference on IoT Technologies for Health-Care, HealthyIoT 2023, and 4th EAI International Conference on Wearables in Healthcare, HealthWear 2023

作者： Ashfaq, Fiza Ahad, Abdul Hussain, Mudassar Madeira, Filipe Department of Computer Science University of Management and Technology Sialkot51040 Pakistan School of Software Northwestern Polytechnical University Shaanxi Xian China Istanbul34467 Turkey /Pole of Digital Literacy and Social Inclusion Polytechnic Institute of Santarem Santarem2001-904 Portugal Department of Computer Science and Creative Technologies Global College of Engineering and Technology Muscat Oman

ISBN: (纸本)9783031719103

Diabetes, a chronic ailment requiring ongoing care and monitoring, has undergone a healthcare shift thanks to the Internet of Things (IoT). Real-time monitoring, individualized treatment plans, and improved patient-provider communication are all features of IoT-based mobile health solutions. This study explores the components, functionalities, benefits, and disadvantages of IoT-based mobile health systems for the management of diabetes. It investigates wearable sensors, smartphone apps, and linked devices like glucose meter and monitors, placing a focus on their precision, dependability, and usability. The study explores data analytics techniques that allow for customized advice and actions. Patients can effectively control their diabetes with the use of individualized treatments and real-time monitoring. The research also looks into the data analytical methods used in IoT-based mobile health systems for the treatment of diabetes. IoT-based mobile health system issues and implications are also covered. These include issues with data security and privacy, platform and device compatibility, standardization of data formats, and ensuring that all people with diabetes have equal access to technology. Healthcare workers, academics, and policymakers may learn more about the potential of IoT-based mobile health systems to revolutionize diabetes treatment through this thorough assessment. © ICST Institute for computer sciences, Social Informatics and Telecommunications Engineering 2024.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Proportional Feature Pyramid Network for Lane Detection 4

Proportional Feature Pyramid Network for Lane Detection

引用

4th International Conference on computer, Big Data and Artificial Intelligence, ICCBD+AI 2023

作者： Hui, Jiapeng Lian, Guoyun Wu, Jiansheng Ge, Shuting Yang, Jinfeng Shenzhen Polytechnic University Institute of Applied Artificial Intelligence of the Guangdong-Hong Kong-Macao Greater Bay Area Shenzhen China University of Science and Technology School of Computer Science and Software Engineering Anshan China

ISBN: (纸本)9798350373233

Lane detection under extreme conditions presents a highly challenging task that requires capturing each crucial pixel to predict the complex topology of lane lines and differentiate the various lane types. Existing methods predominantly rely on deep feature extraction networks with substantial parameters or the fusion of multiple prediction modules, resulting in large model sizes, embedding difficulties, and slow detection speeds. This paper proposes a Proportional Feature Pyramid Network(P-FPN) through fusing the weights into the FPN for lane detection. In our method, the high-level features are explored to predict lanes coarsely while local- detailed features are leveraged to improve localization accuracy. Extensive experiments on the widely used lane detection dataset, CULane dataset, demonstrate that the proposed method achieves the competitive results compared with several state-of-the-art approaches. © 2023 IEEE.

关键词： Feature extraction

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：