检索结果-内蒙古大学图书馆

Pothole Detection: A Study of Ensemble Learning and Decision Framework

International Journal of Advanced Computer Science and Applications 2025年第4期16卷 67-79页

作者： Gorro, Ken D. Ranolo, Elmo B. Ilano, Anthony S. Balijon, Deofel P. Center for Cloud Computing Big Data and Artificial Intelligence Philippines College of Computing Artificial Intelligence and Sciences of Cebu Normal University Philippines

This study investigates the potential use of ensemble learning (YOLOv9 and Mask R-CNN) and Multi-Criteria Decision Making for pothole detection system. A series of experiments were conducted, including variations in confidence thresholds, IoU thresholds, dynamic weight configurations, camera angles and MCDM criteria, to assess their effects on detection performance. The YOLOv9 model achieved a mean Average Precision (mAP) of 0.908 at 0.5 IoU and an F1 score of 0.58 at a confidence threshold of 0.282, indicating a strong balance between precision and recall. However, adjusting IoU thresholds showed that lower thresholds improved recall but resulted in false positives, while higher thresholds improved precision but reduced recall. Dynamic weight configurations were explored, with balanced weights (wY = 0.5, wM = 0.5) yielding the best overall performance, while uneven weights allowed trade-offs between precision and recall based on specific application needs. The MCDM framework refined detection outputs by evaluating pothole features such as size, position, depth, and shape. The proposed algorithm has the potential to be widely used in practical applications. Overfitting is the main drawback of the proposed algorithm, but this is dependent on the use case where the pothole detection will be used. © (2025), (Science and Information Organization). All rights reserved.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

IMPRESS: An Importance-Informed Multi-Tier Prefix KV Storage System for Large Language Model Inference 23

IMPRESS: An Importance-Informed Multi-Tier Prefix KV Storage...

引用

23rd USENIX Conference on File and Storage Technologies, FAST 2025

作者： Chen, Weijian He, Shuibing Qu, Haoyang Zhang, Ruidong Yang, Siling Chen, Ping Zheng, Yi Huai, Baoxing Chen, Gang The State Key Laboratory of Blockchain and Data Security Zhejiang University China Institute of Blockchain and Data Security China Zhejiang Key Laboratory of Big Data Intelligent Computing China Huawei Cloud China

ISBN: (纸本)9781939133458

Modern advanced large language model (LLM) applications often prepend long contexts before user queries to improve model output quality. These contexts frequently repeat, either partially or fully, across multiple queries. Existing systems typically store and reuse the keys and values of these contexts (referred to as prefix KVs) to reduce redundant computation and time to first token (TTFT). When prefix KVs need to be stored on disks due to insufficient CPU memory, reusing them does not always reduce TTFT, as disk I/O latency is high. In this paper, we propose IMPRESS, an importance-informed multi-tier prefix KV storage system to reduce I/O delay for LLM inference by only loading important prefix KVs. IMPRESS first leverages the insight that there is significant similarity in important token index sets across attention heads and introduces an I/O-efficient important KV identification algorithm. It then optimizes prefix KV storage and caching through importance-informed KV management, reducing TTFT during model inference. Our experimental results show that IMPRESS can reduce TTFT by up to 2.8× compared to state-of-the-art systems, while maintaining comparable inference accuracy. © 2025 FAST. All Rights Reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

N-Body Simulation Inspired by Metaheuristics Optimization

引用

Computer Systems Science & Engineering 2022年第6期41卷 1143-1155页

作者： Muhammad Ali Ismail Maria Waqas Farah Sadiq National Center in Big Data and Cloud Computing Department of Computer and Info Systems EngineeringNED University of Engineering and TechnologyKarachiPakistan

The N-body problem in classical physics, is the calculation of force ofgravitational attraction of heavenly bodies towards each other. Solving this problem for many heavenly bodies has always posed a challenge to physicists andmathematicians. Large number of bodies, huge masses, long distances and exponentially increasing number of equations of motion of the bodies have been themajor hurdles in solving this problem for large and complex galaxies. Adventof high performance computational machines have mitigated the problem to muchextent, but still for large number of bodies it consumes huge amount of resourcesand days for computation. Conventional algorithms have been able to reduce thecomputational complexity from O n2 ð Þ to O nlogn ð Þ by splitting the space into atree or mesh network, researchers are still looking for improvements. In thisresearch work we propose a novel solution to N-body problem inspired by metaheuristics algorithms. The proposed algorithm is simulated for various time periods of selected heavenly bodies and analyzed for speed and accuracy. Theresults are compared with that of conventional algorithms. The outcomes showabout 50% time saving with almost no loss in accuracy. The proposed approachbeing a metaheuristics optimization technique, attempts to find optimal solution tothe problem, searching the entire space in a unique and efficient manner in a verylimited amount of time.

关键词： N-body problem metaheuristics optimization particle swarm optimization heavenly bodies

来源：评论

学校读者我要写书评

暂无评论

Inductive Relation Prediction by Disentangled Subgraph Structure

引用

Tsinghua Science and Technology 2024年第5期29卷 1566-1579页

作者： Guiduo Duan Rui Guo Wenlong Luo Guangchun Luo Tianxi Huang Laboratory of Intelligent Collaborative Computing University of Electronic Science and Technology of ChinaChengdu 611731Chinaand also with Trusted Cloud Computing and Big Data Key Laboratory of Sichuan ProvinceChengdu 611731China School of Computer Science and Engineering University of Electronic Science and Technology of ChinaChengdu 611731China Hangzhou NetEase Cloud Music Technology Co. Ltd.Hangzhou 310052China Department of Fundamental Courses Chengdu Textile CollegeChengdu 611700China

Currently,most existing inductive relation prediction approaches are based on subgraph structures,with subgraph features extracted using graph neural networks to predict ***,subgraphs may contain disconnected regions,which usually represent different semantic *** not all semantic information about the regions is helpful in relation prediction,we propose a relation prediction model based on a disentangled subgraph structure and implement a feature updating approach based on relevant semantic *** indirectly achieve the disentangled subgraph structure from a semantic perspective,the mapping of entity features into different semantic spaces and the aggregation of related semantics on each semantic space are *** disentangled model can focus on features having higher semantic relevance in the prediction,thus addressing a problem with existing approaches,which ignore the semantic differences in different subgraph ***,using a gated recurrent neural network,this model enhances the features of entities by sorting them by distance and extracting the path information in the ***,it is shown that when there are numerous disconnected regions in the subgraph,our model outperforms existing mainstream models in terms of both Area Under the Curve-Precision-Recall(AUC-PR)and Hits@*** prove that semantic differences in the knowledge graph can be effectively distinguished and verify the effectiveness of this method.

关键词： disentangled subgraph structure knowledge graph completion Gated Recurrent Unit(GRU) feature updating

来源：评论

学校读者我要写书评

暂无评论

DeepFake Detection Using Deep Learning 1st

DeepFake Detection Using Deep Learning

引用

1st International Conference on data Science and Artificial Intelligence, DSAI 2023

作者： Rehman, Mariam Rasool, Mehran Safder, Sadaf Government College University Faisalabad Pakistan National Center in Big Data and Cloud Computing University of Agriculture Faisalabad Pakistan

ISBN: (纸本)9789819979684

A deepfake is a computer-generated video or image where one person's face is replaced with another face of a person which uses a generative adversarial network (GAN) to create and alter images that are practically impossible for humans to distinguish from authentic ones. The development of GAN technology has led to significant improvements in image generation. This progress has made it difficult for humans to differentiate between generated images and raised concerns about their misuse and also creating security threats for the society. Deepfake image detection is an essential challenge because the current methods often face inaccuracy and time-consuming issues. The research work employed GAN discriminators to address these issues. The experiment used the CelebA dataset, which contained diverse celebrity images. Moreover, the proposed model consists of components i.e., generator and discriminator. The generator creates fake data from the training images, while the discriminator distinguishes real from the fake images. The result shows that the proposed approach is out-performing with an accuracy of 95.8% in identifying deep fake images, even in the presence of various manipulations. The proposed model is helpful for enhancing trust and security in the society. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2023.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

data Catalogs with Artificial Intelligence and Active Metadata: A Case Study of China Mobile 6

Data Catalogs with Artificial Intelligence and Active Metada...

引用

6th International Conference on Next Generation data-Driven Networks, NGDN 2024

作者： Wang, Jibin Guo, Yanmei Jiang, Yong Shang, Jing Chen, Zhuo Liu, Yu Hu, Qingyuan Yin, Zheng China Mobile Information Technology Center Beijing China Cloud Computing and Big Data Research Institute China Academy of Information and Communications Technology Beijing China

ISBN: (纸本)9798350388374

In the context of the rapid development of artificial intelligence, telecommunications operators have accumulated an increasing amount of data. China Mobile has developed a set of practical methods of enhanced data catalog in response to current issues such as difficulties in scheduling heterogeneous data from multiple sources, lack of macroscopic views of data usage, unintelligent data operation methods, and high risk of data leakage. By leveraging data virtualization, active metadata management, machine learning, along with other large-scale model technologies, China Mobile has crafted an enhanced data catalog, improving the data management efficiency and business decision-making process, further strengthening its competitiveness in the telecommunication industry. © 2024 IEEE.

关键词： Information leakage

来源：评论

学校读者我要写书评

暂无评论

Research on Blockchain-based Decentralized Federated Learning

Research on Blockchain-based Decentralized Federated Learnin...

引用

2023 International Conference on Computer Applications Technology, CCAT 2023

作者： Han, Boyuan Liang, Zhihong Qin, Mingming Jiang, Rongxin Dai, Wei Southwest Forestry University School of Big Data and Intelligent Engineering Kunming China Southwest Forestry University Big Data and Cloud Computing Center Kunming China Yunnan Pu'er Technical School Yunnan Pu'er Technical School Kunming China

ISBN: (纸本)9798350301540

The integration of blockchain and federated learning exhibits a highly synergistic relationship. Blockchain, with its assurance of trustworthiness in computational processes and data, combined with federated learning's ability to make data available yet invisible, mutually complement each other and have shown initial advancements across various domains. Consequently, research and analysis of blockchain-based federated learning technology have garnered considerable *** blockchain enhances the federated learning process, it also poses a number of problems, such as increased communication overhead and lack of computational *** article aims to provide a comprehensive examination of the subject. Firstly, it introduces the fundamental concept of federated learning technology, along with privacy protection techniques and the existing threat landscape. Secondly, it analyzes the core principles of blockchain-based federated learning technology, delving into current research status, progress, and outlining the various research directions involved. Furthermore, it conducts an in-depth analysis and summarization of the integration between federated learning and blockchain technology, identifying numerous challenges that need to be addressed within the relevant domains. Finally, it recognizes and analyzes the future development of this combination, emphasizing the need to overcome existing *** summary, this article highlights the amalgamation of federated learning and blockchain technology. It identifies and analyzes the many challenges that require resolution within the pertinent fields, while also offering insights into the future development of this integration. © 2023 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

A numerical magnitude aware multi-channel hierarchical encoding network for math word problem solving

引用

Neural computing and Applications 2025年第3期37卷 1651-1672页

作者： Xu, Junjie Chen, Yuzhong Xiao, Lingsheng Liao, Hongmiao Zhong, Jiayuan Dong, Chen College of Computer and Data Science Fuzhou University Fujian Province Fuzhou350108 China Engineering Research Center of Big Data Intelligence Ministry of Education Fuzhou China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fujian Province Fuzhou350108 China

Math word problem (MWP) represents a critical research area within reading comprehension, where accurate comprehension of math problem text is crucial for generating math expressions. However, current approaches still grapple with unresolved challenges in grasping the sensitivity of math problem text and delineating distinct roles across various clause types, and enhancing numerical representation. To address these challenges, this paper proposes a Numerical Magnitude Aware Multi-Channel Hierarchical Encoding Network (NMA-MHEA) for math expression generation. Firstly, NMA-MHEA implements a multi-channel hierarchical context encoding module to learn context representations at three different channels: intra-clause channel, inter-clause channel, and context-question interaction channel. NMA-MHEA constructs hierarchical constituent-dependency graphs for different levels of sentences and employs a Hierarchical Graph Attention Neural Network (HGAT) to learn syntactic and semantic information within these graphs at the intra-clause and inter-clause channels. NMA-MHEA then refines context clauses using question information at the context-question interaction channel. Secondly, NMA-MHEA designs a number encoding module to enhance the relative magnitude information among numerical values and type information of numerical values. Experimental results on two public benchmark datasets demonstrate that NMA-MHEA outperforms other state-of-the-art models. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

An insider user authentication method based on improved temporal convolutional network

引用

High-Confidence computing 2023年第4期3卷 87-95页

作者： Xiaoling Tao Yuelin Yu Lianyou Fu Jianxiang Liu Yunhao Zhang Guangxi Key Laboratory of Cryptography and Information Security Guilin University of Electronic TechnologyGuilin 541004China Guangxi Cooperative Innovation Center of Cloud Computing and Big Data Guilin University of Electronic TechnologyGuilin 541004China

With the rapid development of information technology,information system security and insider threat detection have become important topics for organizational *** the current network environment,user behavioral bio-data presents the characteristics of nonlinearity and temporal *** of the existing research on authentication based on user behavioral biometrics adopts the method of manual feature *** do not adequately capture the nonlinear and time-sequential dependencies of behavioral bio-data,and also do not adequately reflect the personalized usage characteristics of users,leading to bottlenecks in the performance of the authentication *** order to solve the above problems,this paper proposes a Temporal Convolutional Network method based on an Efficient Channel Attention mechanism(ECA-TCN)to extract user mouse dynamics features and constructs an one-class Support Vector Machine(OCSVM)for each user for *** results show that compared with four existing deep learning algorithms,the method retains more adequate key information and improves the classification performance of the neural *** the final authentication,the Area Under the Curve(AUC)can reach 96%.

关键词： Insider users Mouse dynamics Feature extraction Temporal convolutional network Efficient channel attention mechanism Authentication

来源：评论

学校读者我要写书评

暂无评论

IGED:Towards intelligent DDoS Detection Model Using Improved Generalized Entropy and DNN

引用

Computers, Materials & Continua 2024年第8期80卷 1851-1866页

作者： Yanhua Liu Yuting Han HuiChen Baokang Zhao XiaofengWang Ximeng Liu College of Computer and Data Science Fuzhou UniversityFuzhou350108China Engineering Research Center of Big Data Intelligence Ministry of EducationFuzhou350108China Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou UniversityFuzhou350108China College of Computer National University of Defense TechnologyChangsha410073China

As the scale of the networks continually expands,the detection of distributed denial of service(DDoS)attacks has become increasingly *** propose an intelligent detection model named IGED by using improved generalized entropy and deep neural network(DNN).The initial detection is based on improved generalized entropy to filter out as much normal traffic as possible,thereby reducing data *** the fine detection is based on DNN to perform precise DDoS detection on the filtered suspicious traffic,enhancing the neural network’s generalization *** results show that the proposed method can efficiently distinguish normal traffic from DDoS *** with the benchmark methods,our method reaches 99.9%on low-rate DDoS(LDDoS),flooded DDoS and CICDDoS2019 datasets in terms of both accuracy and efficiency in identifying attack flows while reducing the time by 17%,31%and 8%.

关键词： DDoS real-time improved generalized entropy DNN

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：