检索结果-内蒙古大学图书馆

2024 International Conference on Artificial Intelligence and Machine Learning Research, CAIMLR 2024

作者： Mahlich, Christopher Vente, Tobias Beel, Joeran University of Siegen Department of Electrical Engineering and Computer Science SiegenD-57076 Germany

ISBN: (纸本)9781510691797

In this paper, we present e-fold cross-validation, an energy-efficient alternative to k-fold, which dynamically adjusts the number of folds to reduce computational resources while ensuring accurate performance estimates. This dynamic adjustment is implemented by a stopping criterion, which checks after each fold whether the standard deviation of the previous evaluated folds has repeatedly decreased or has not changed significantly. Once the stopping criterion is met, the e-fold cross-validation is stopped early. We evaluated e-fold cross-validation on 15 datasets and 10 machine-learning algorithms. Compared to 10-fold cross-validation, e-fold cross-validation needed about 4 folds less for comparable results, resulting in savings of about 40% evaluation time, computational resources and energy consumption. The percentage difference in performance metrics between e-fold and standard 10-fold cross-validation with larger datasets was generally less than 2%. More powerful models show even smaller discrepancies. Statistical significance was confirmed with 96% of iterations falling within the confidence interval for all algorithms tested. Our results indicate that e-fold cross-validation is a robust and efficient alternative to the conventional k-fold cross-validation providing reliable performance evaluation at lower computational costs. © 2025 SPIE.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Digital twin‐based multi‐objective autonomous vehicle navigation approach as applied in infrastructure construction

引用

IET Cyber-Systems and Robotics 2024年第2期6卷 1-19页

作者： Tingjun Lei Timothy Sellers Chaomin Luo Lei Cao Zhuming Bi Department of Electrical and Computer Engineering Mississippi State UniversityMississippi StateMississippiUSA Department of Electrical and Computer Engineering University of MississippiUniversityMississippiUSA Department of Civil and Mechanical Engineering Purdue University Fort WayneFort WayneIndianaUSA

The widespread adoption of autonomous vehicles has generated considerable interest in their autonomous operation,with path planning emerging as a critical ***,existing road infrastructure confronts challenges due to prolonged use and insufficient *** research on autonomous vehicle navigation has focused on determining the trajectory with the shortest distance,while neglecting road construction information,leading to potential time and energy inefficiencies in real-world scenarios involving infrastructure *** address this issue,a digital twin-embedded multi-objective autonomous vehicle navigation is proposed under the condition of infrastructure *** authors propose an image processing algorithm that leverages captured images of the road construction environment to enable road extrac-tion and modelling of the autonomous vehicle ***,a wavelet neural network is developed to predict real-time traffic flow,considering its inherent ***,a multi-objective brainstorm optimisation(BSO)-based method for path planning is introduced,which optimises total time-cost and energy consumption objective *** ensure optimal trajectory planning during infrastructure con-struction,the algorithm incorporates a real-time updated digital twin throughout autonomous vehicle *** effectiveness and robustness of the proposed model are validated through simulation and comparative studies conducted in diverse scenarios involving road *** results highlight the improved performance and reli-ability of the autonomous vehicle system when equipped with the authors’approach,demonstrating its potential for enhancing efficiency and minimising disruptions caused by road infrastructure development.

关键词： autonomous vehicle intelligent robots motion planning navigation path planning robot planning

来源：评论

学校读者我要写书评

暂无评论

Granular Box Regression Using Simulated Annealing and Genetic Algorithm: A Comparative Study

引用

SN computer science 2024年第8期5卷 978页

作者： Chakraborty, Mrittika Maulik, Ujjwal Mukhopadhyay, Anirban Department of Computer Science and Engineering Jadavpur University Kolkata India Department of Computer Science and Engineering University of Kalyani Kalyani India

Representation of compound information in a truthful, coarse way forms the layout of the granular computing paradigm. In granular computing, the continuous variables are mapped into intervals to be utilized in the extraction of fuzzy graphs from the given dataset. The objective of Granular Box Regression is to establish a relationship between the predictor and the target variables using multidimensional boxes. However, the traditional box regression technique uses a greedy approach due to which the algorithm tends to converge to some local optima, and optimal box configuration may not be obtained. In this article, we suggest overcoming the problem of getting stuck into local optima using randomized search and optimization techniques of Simulated Annealing and Genetic Algorithms. The major advantage of using Simulated Annealing is that it allows occasional acceptance of poor solutions to avoid getting trapped into some local optima. Genetic Algorithms also provide efficient, robust search optimization techniques that minimize the chances of a local optimum problem. A comparative analysis is conducted while implementing Granular Box Regression using Simulated Annealing and Genetic Algorithm, and the results are demonstrated on some artificial datasets, economic datasets, and some datasets of COVID-19 cases. As per the quantitative analysis of the Granular Box Regression (GBR) methods, both GBR-SA and GBR-GA significantly outperformed the baseline GBR algorithm across various datasets. For instance in the 3DED1 dataset, GBR-SA and GBR-GA showed an improvement of 16.02% while for 2DCD2, they showed an improvement of 22.22%. However, the execution time varied for GBR-GA by 95.4% with the GBR-SA algorithm, which in turn took about 26% average time more than the base algorithm of GBR. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Genetic algorithms Granular box regression Granular computing Regression analysis Simulated annealing

来源：评论

学校读者我要写书评

暂无评论

Proof of Random Leader: A Fast and Manipulation-Resistant Proof-of-Authority Consensus Algorithm for Permissioned Blockchains Using Verifiable Random Function

引用

IEEE Transactions on Services Computing 2025年第3期18卷 1655-1668页

作者： Islam, Md. Mainul Merlec, Mpyana Mwamba In, Hoh Peter Texas A&M University Department of Electrical and Computer Engineering College StationTX77843 United States Korea University Department of Computer Science and Engineering Seoul02841 Korea Republic of DAO Solution Inc. Seoul06247 Korea Republic of

Proof of Authority (PoA) is a widely adopted consensus algorithm for permissioned blockchain networks, where a group of trusted entities governs the network. PoA is known for achieving rapid consensus with minimal computational and energy requirements. However, existing PoA variants such as Aura and Clique suffer from low transaction throughput in high workload conditions and provide limited randomness in leader selection. They are also vulnerable to time and order manipulation attacks. To overcome these limitations, this paper introduces a novel PoA-based consensus algorithm called Proof of Random Leader (PoRL), which utilizes a verifiable random function to enhance transaction throughput, improve scalability, and ensure fair and unpredictable leader selection. The proposed PoRL algorithm was implemented in Python and evaluated using a network of six consensus nodes with varying computational capabilities. The performance of PoRL was assessed based on key metrics, including security, consistency, availability, fault tolerance, block time, and transaction throughput. Experimental results indicate that PoRL achieves lower consensus times and higher transaction throughput compared to Aura and Clique, making it a more efficient solution for permissioned blockchain networks. The findings of this study provide valuable insights for blockchain practitioners in selecting the most suitable PoA implementation based on their specific network requirements. © 2008-2012 IEEE.

关键词： Consensus algorithm

来源：评论

学校读者我要写书评

暂无评论

IVEMPS: IoT-Based Vehicle Emission Monitoring and Prediction System

引用

IEEE Access 2025年 13卷 95628-95646页

作者： Farrag, Omar Mansour, Ahmad Abed, Baraa Abu Alhaj, Amr Landolsi, Taha Al-Ali, A.R. American University of Sharjah Department of Computer Science and Engineering Sharjah United Arab Emirates

Greenhouse gas emissions are a critical issue that can have severe environmental impacts such as global warming and climate change. Gases emitted by road transportation vehicles constitute a significant part of global greenhouse gas emissions. Therefore, this paper proposes an IoT-based real-time vehicle emission monitoring and prediction system to swiftly identify high-emitting vehicles (HEVs). The system consists of an on-board system with wireless networking capabilities housing seven gas sensors (CO, CO2, NO, NO2, H2S, HC, and O2) for real-time data acquisition. It also includes a cloud computing layer for data storage and emission forecasting for predictive maintenance using deep learning time series forecasting techniques. Finally, the system provides visualizations of the collected data through a dedicated web-based dashboard. Trained forecasting models achieved a prediction accuracy of 83% and an F1-score of 0.79. Additionally, real-world on-road test data validated the system’s effectiveness in identifying current and potential HEVs in real-time while generating large datasets to support ongoing research and development aimed at reducing vehicle emissions. © 2013 IEEE.

关键词： Greenhouse gas emissions

来源：评论

学校读者我要写书评

暂无评论

ElectroBlock: Reinforcement Learning and Blockchain-based Energy Trade to Optimize Tariffs 7

ElectroBlock: Reinforcement Learning and Blockchain-based En...

引用

7th Conference on Cloud and Internet of Things, CIoT 2024

作者： Islam, Ridwan Arefin Rezwan-Ul-Islam Shatabda, Swakkhar Islam, Salekul McGill University School of Computer Science Montréal Canada United International University Department of Computer Science and Engineering Dhaka Bangladesh Brac University Department of Computer Science and Engineering Dhaka Bangladesh North South University Department of Electrical and Computer Engineering Dhaka Bangladesh

ISBN: (纸本)9798350356717

Energy prices have increased by more than 62% globally on average, while power companies are trying to provide more affordable energy with different options: fixed-rate, slab-based tariffs, and Time-of-Use pricing. This article aims to combine blockchains, smart contracts, smart grids, energy forecasting through reinforcement learning, and energy trading between closed communities, bringing consumer savings. Our proposed model, ElectroBlock, uses the first 25 days of each month's energy usage history along with seasonal and exogenous factors to forecast the final end-of-month usage. Then with the forecast we can predict which customers are the most likely to be pushed to the next energy consumption slab and be charged at a higher rate for the remaining month. This allows these customers to be buyers, and seamlessly buy energy units from users who would sell, the energy units they are predicted to leave unused by the end of the month. Moreover, trading is done with WalletCoins, at a coin per kilowatt hour, but could also be traded directly for fiat currency. Furthermore, the power company makes a profit on every trade through transaction fees. Hence there is great incentive for both customers and power companies to adopt our proposed model. We integrated Hyperledger Fabric into our ElectroBlock prototype to store all customer data and prevent tampering with WalletCoin and consumption records. Finally, we did a performance analysis, on the actual cost savings based on a real-world dataset;and a scalability test for concurrency and customer bases on our prototype. © 2024 IEEE.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

DisP+V: A Unified Framework for Disentangling Prototype and Variation From Single Sample per Person

引用

IEEE Transactions on Neural Networks and Learning Systems 2023年第2期34卷 867-881页

作者： Pang, Meng Wang, Binghui Ye, Mang Cheung, Yiu-Ming Chen, Yiran Wen, Bihan Nanyang Technological University School of Electrical and Electronic Engineering 639798 Singapore Illinois Institute of Technology Department of Computer Science ChicagoIL60616 United States Wuhan University School of Computer Science Wuhan430072 China Hong Kong Baptist University Department of Computer Science Kowloon Hong Kong Duke University Department of Electrical and Computer Engineering DurhamNC27708 United States

Single sample per person face recognition (SSPP FR) is one of the most challenging problems in FR due to the extreme lack of enrolment data. To date, the most popular SSPP FR methods are the generic learning methods, which recognize query face images based on the so-called prototype plus variation (i.e., P+V) model. However, the classic P+V model suffers from two major limitations: 1) it linearly combines the prototype and variation images in the observational pixel-spatial space and cannot generalize to multiple nonlinear variations, e.g., poses, which are common in face images and 2) it would be severely impaired once the enrolment face images are contaminated by nuisance variations. To address the two limitations, it is desirable to disentangle the prototype and variation in a latent feature space and to manipulate the images in a semantic manner. To this end, we propose a novel disentangled prototype plus variation model, dubbed DisP+V, which consists of an encoder-decoder generator and two discriminators. The generator and discriminators play two adversarial games such that the generator nonlinearly encodes the images into a latent semantic space, where the more discriminative prototype feature and the less discriminative variation feature are disentangled. Meanwhile, the prototype and variation features can guide the generator to generate an identity-preserved prototype and the corresponding variation, respectively. Experiments on various real-world face datasets demonstrate the superiority of our DisP+V model over the classic P+V model for SSPP FR. Furthermore, DisP+V demonstrates its unique characteristics in both prototype recovery and face editing/interpolation. © 2020 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Designing a novel network anomaly detection framework using multi-serial stacked network with optimal feature selection procedures over DDOS attacks

引用

International Journal of Intelligent Networks 2025年第1期6卷 1-13页

作者： Pradeep, K. Jeevan Shukla, Prashanth Kumar Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram AP India

- Distributed denial-of-service (DDoS) attacks are the major threat that disrupts the services in the computer system and networks using traffic and targeted sources. So, real-world attack detection techniques are considered an important element in executing cybersecurity tasks. The present DDoS techniques are prone to False Positive Rates (FPR) and also it didn't acquire the complicated patterns presented in the attack traffic. Internet of Things (IoT) is a complicated network with resource-constrained devices and networks that are prone to different security threats like DDoS attacks. Later, the Software Defined Networking (SDN) with IoT models is used to enhance the access control techniques and security models. DDoS attacks are considered as an important threat in the IoT networks. Hence, it is important to construct a novel network anomaly detection model with a deep learning mechanism to resolve the limitations of the existing techniques. Initially, essential data required for the validation are gathered from the IDS ISCX 2012 dataset. The optimal features are selected from input data using the Predefined-Mud Ring Algorithm (P-MRA). The optimally selected features are provided to the Multi-Serial Stacked Networks (Multi-SSN), which is the fusion of Convolutional Autoencoder (CAE), Gated Recurrent Unit (GRU), and Bayesian Learning (BL) networks. Here, the essential features for the validation are acquired from the CAE and GRU. Then, these features are stacked and given to the BL mechanism for detecting the anomalies in the network. Further, several experimental validations are performed in the developed framework over traditional network anomaly detection mechanism. © 2024 The Authors

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Cellular shape micromachined actuator ribbons

引用

Microsystems & Nanoengineering 2022年第4期8卷 209-220页

作者： Amin Abbasalipour Prithviraj Palit Sepehr Sheikhlari Siavash Pakdelian Siavash Pourkamali Department of Electrical and Computer Engineering University of Texas at DallasRichardsonTXUSA Department of Electrical and Computer Engineering University of MassachusettsLowellMAUSA

This work presents a new class of micromachined electrostatic actuators capable of producing output force and displacement unprecedented for MEMS electrostatic *** actuators feature submicron high aspect ratio transduction gaps lined up in two-dimensional *** an arrangement of microscale actuator cells allows the addition of force and displacements of a large number of cells(up to 7600 in one demonstrated array),leading to displacements ranging in the hundreds of microns and several gram forces of axial *** 50μm thick actuators with horizontal dimensions in the 1-4 millimeter range,an out-of-plane displacement of up to 678μm at 46 V,a bending moment of up to 2.0μNm,i.e.,0.08 N(~8 gram-force)of axial force over a 50μm by 2 mm cross-sectional area of the actuator(800 kPa of electrostatically generated stress),and an energy density(mechanical work output per stroke per volume)up to 1.42 mJ/cm3 was demonstrated for the actuators.

关键词： electrostatic displacement shape

来源：评论

学校读者我要写书评

暂无评论

MMHBC-Net: a multi-modal hybrid approach for breast cancer classification

引用

Neural Computing and Applications 2025年 1-31页

作者： Deb, Dipti Dash, Ratnakar Mohapatra, Durga Prasad Department of Computer Science and Engineering National Institute of Technology Rourkela Odisha Rourkela India

Early detection of breast cancer is crucial for improving survival rates. Many computer-aided diagnosis (CAD) models have been proposed in the past for the detection of breast cancer. However, analyzing breast cancer across multiple imaging modalities remains a challenge. Different imaging modalities provide complimentary information on the lesion and help in detecting the abnormalities at an early stage. Our study introduces a MMHBC-Net model that utilizes mammogram, ultrasound, and histopathology images to enhance detection accuracy. Pre-processing and augmentation of the images are performed for better accuracy. For extracting features from mammogram and ultrasound images, a deep learning model that includes four convolutional layers followed by a dense layer. For histopathology, handcrafted techniques based on texture and color feature extraction are employed. Data-level fusion is performed among the image modalities and passed through various classifiers, including RF, BAG, DT, ADA, NB, LGBM, XGB, GBC, kNN SVM, and GCN. Based on the classifier’s performance, the top five classifiers for each modality are selected to construct a stacking ensemble classifier for the final classification. Experimentation involves datasets such as DDSM, MIAS, INbreast for mammograms, BUS and MBU for ultrasounds, and BreakHis for histopathology images. The results reveal that the multi-modal CAD system outperforms uni-modal CAD systems by obtaining test accuracy of 99.96, 88.16, 95.33, and 91.79% for combined, mammogram, ultrasound, and histopathology images. This highlights the effectiveness of the multi-modal approach for breast cancer detection. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Image coding

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：