检索结果-内蒙古大学图书馆

6th International Conference on Sustainable Technologies for Industry 5.0, STI 2024

作者： Al-Muzahid, Muhammad Masud, Md Abdul Samsuzzaman, Md. Islam, Md. Jahidul Patuakhali Science and Technology University Faculty of Computer Science and Engineering Patuakhali Bangladesh

ISBN: (纸本)9798331531973

Class imbalance is a significant and emerging issue in machine learning, which expresses that the number of majority class instances is much greater than the number of minority class instances. In real applications, a large number of imbalanced datasets are available, which is difficult to classify normally. The conventional oversampling technique ADASYN, along with the more recent method RSMOTE, are not able to solve the issue quietly. However, they are prone to outliers and class overlaps. To address this problem, we propose the adaptive density-based synthetic sampling, DASS, technique in this paper. In the DASS technique, we select neighboring instances based on local density estimations to obtain a more accurate sampling of the minority classes. This method reduces overfitting and increases model generalization. In the experimental results, we observe that DASS outperforms baseline approaches using different classifiers in terms of ROC AUC, Fl score, recall, precision, and overall accuracy. This reflects that DASS is an efficient alternative for accurately managing imbalance and significantly contributes to improving prediction power. The proposed technique provides a new perspective on addressing class imbalance more effectively than the baseline resampling methods in machine learning. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Fundamental Limits of Two-Hop MIMO Channels: An Asymptotic Approach

引用

IEEE Transactions on Information Theory 2025年第6期71卷 4069-4111页

作者： Zhuang, Zeyan Zhang, Xin Xu, Dongfang Song, Shenghui The Hong Kong University of Science and Technology Department of Electronic and Computer Engineering Hong Kong Hong Kong The Hong Kong University of Science and Technology Division of Integrative Systems and Design Hong Kong Hong Kong

Multi-antenna relays and intelligent reflecting surfaces (IRSs) have been utilized to construct favorable channels to improve the performance of wireless systems. A common feature between relay systems and IRS-aided systems is the two-hop multiple-input multiple-output (MIMO) channel. As a result, the mutual information (MI) of two-hop MIMO channels has been widely investigated with very engaging results. However, a rigorous investigation on the fundamental limits of two-hop MIMO channels, i.e., the first and second-order analysis, is not yet available in the literature, due to the difficulties caused by the two-hop (product) channel and the noise introduced by the relay (active IRS). In this paper, we employ large random matrix theory, specifically Gaussian tools, to derive the closed form deterministic approximation for the mean and variance of the MI. Additionally, we determine the convergence rate for the mean, variance and the characteristic function of the MI, and prove the asymptotic Gaussianity. Furthermore, we also investigate the analytical properties of the fundamental equations that describe the closed-form approximation and prove the existence and uniqueness of the solution. An iterative algorithm is then proposed to obtain the solutions for the fundamental equations. Numerical results validate the accuracy of the theoretical analysis. © 1963-2012 IEEE.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Comparison of Geographically Weighted Regression (GWR) and Mixed Geographically Weighted Regression (MGWR) Models on the Poverty Levels in Central Java in 2023

引用

IAENG International Journal of Applied Mathematics 2024年第12期54卷 2746-2757页

作者： Alya, Najma Attaqiya Almaulidiyah, Qothrotunnidha Farouk, Bailey Reshad Rantini, Dwi Ramadan, Arip Othman, Fazidah Engineering Department Data Science Technology Study Program Universitas Airlangga Indonesia Engineering Department Data Science Technology Study Program Faculty of Advanced Technology and Multi-discipline Universitas Airlangga Indonesia Information System Study Program Department of Industrial and System Engineering Telkom University Surabaya Campus Indonesia Department of Computer System and Technology Faculty of Computer Science and Information Technology University of Malaya Malaysia

Poverty is considered a serious global issue that must be immediately eradicated by Sustainable Development Goals (SDGs) 1, namely ending poverty anywhere and in any form. As a developing country, poverty is a complex issue faced by Indonesia. Tackling poverty in Indonesia has become a key focus of the government’s strategic priorities. This issue of poverty is experienced by all provinces in Indonesia, including Central Java. The poverty rate in Central Java stands at 10.77% or 3.79 million people. The causes of poverty are explained by several factors. Using these various factors, a mapping model can be conducted to determine the number of poor populations in Central Java. This research employs Geographically Weighted Regression (GWR) and Mixed Geographically Weighted Regression (MGWR) approaches to compare the effectiveness of these models in analyzing the number of poor populations in Central Java in 2023. The kernel function weighting used in this study is Fixed Gaussian. The results showed that the MGWR model outperformed both the OLS regression and GWR models, achieving an Akaike Information Criterion (AIC) of 62.766, an R2 of 82.3%, and a Mean Squared Error (MSE) of 0.177. Consequently, it can be inferred that the MGWR model was more suitable for explaining the poverty levels in Central Java. © (2024), (International Association of Engineers). All Rights Reserved.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

EFS-XGBoost: A robust framework for precision classification of COVID-19 cases

引用

Intelligent Data Analysis 2025年第1期29卷 171-185页

作者： Abidi, Mustufa Haider Khare, Neelu D, Preethi Alkhalefah, Hisham Umer, Usama Advanced Manufacturing Institute King Saud University Riyadh Saudi Arabia School of Computer Science Engineering and Information Systems Vellore Institute of Technology Tamil Nadu Vellore India Department of Computer Science and Engineering Faculty of Engineering and Technology SRM Institute of Science and Technology Ramapuram Chennai India

The emergence of the novel COVID-19 virus has had a profound impact on global healthcare systems and economies, underscoring the imperative need for the development of precise and expeditious diagnostic tools. Machine learning techniques have emerged as a promising avenue for augmenting the capabilities of medical professionals in disease diagnosis and classification. In this research, the EFS-XGBoost classifier model, a robust approach for the classification of patients afflicted with COVID-19 is proposed. The key innovation in the proposed model lies in the Ensemble-based Feature Selection (EFS) strategy, which enables the judicious selection of relevant features from the expansive COVID-19 dataset. Subsequently, the power of the eXtreme Gradient Boosting (XGBoost) classifier to make precise distinctions among COVID-19-infected patients is *** EFS methodology amalgamates five distinctive feature selection techniques, encompassing correlation-based, chi-squared, information gain, symmetric uncertainty-based, and gain ratio approaches. To evaluate the effectiveness of the model, comprehensive experiments were conducted using a COVID-19 dataset procured from Kaggle, and the implementation was executed using Python programming. The performance of the proposed EFS-XGBoost model was gauged by employing well-established metrics that measure classification accuracy, including accuracy, precision, recall, and the F1-Score. Furthermore, an in-depth comparative analysis was conducted by considering the performance of the XGBoost classifier under various scenarios: employing all features within the dataset without any feature selection technique, and utilizing each feature selection technique in isolation. The meticulous evaluation reveals that the proposed EFS-XGBoost model excels in performance, achieving an astounding accuracy rate of 99.8%, surpassing the efficacy of other prevailing feature selection techniques. This research not only advances the field of COVI

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Combining Deep Learning with Knowledge Graph for design Knowledge Acquisition in Conceptual Product design

引用

computer Modeling in engineering & sciences 2024年第1期138卷 167-200页

作者： Yuexin Huang Suihuai Yu Jianjie Chu Zhaojing Su Yangfan Cong Hanyu Wang Hao Fan Key Laboratory of Industrial Design and Ergonomics Ministry of Industry and Information TechnologyNorthwestern Polytechnical UniversityXi’an710072China School of Industrial Design Engineering Delft University of TechnologyDelft2628 CEThe Netherlands Department of Industrial Design College of ArtsShandong University of Science and TechnologyTsingtao266590China College of Computer Science and Technology Zhejiang UniversityHangzhou310027China

The acquisition of valuable design knowledge from massive fragmentary data is challenging for designers in conceptual product *** study proposes a novel method for acquiring design knowledge by combining deep learning with knowledge ***,the design knowledge acquisition method utilises the knowledge extraction model to extract design-related entities and relations from fragmentary data,and further constructs the knowledge graph to support design knowledge acquisition for conceptual product ***,the knowledge extraction model introduces ALBERT to solve memory limitation and communication overhead in the entity extraction module,and uses multi-granularity information to overcome segmentation errors and polysemy ambiguity in the relation extraction *** comparison verified the effectiveness and accuracy of the proposed knowledge extraction *** case study demonstrated the feasibility of the knowledge graph construction with real fragmentary porcelain data and showed the capability to provide designers with interconnected and visualised design knowledge.

关键词： Conceptual product design design knowledge acquisition knowledge graph entity extraction relation extraction

来源：评论

学校读者我要写书评

暂无评论

REDUCTION OF CO2 EMISSION AS A RESULT OF THE USE OF 48-VOLT ELECTRICAL INSTALLATIONS IN PASSENGER CARS

引用

Archives of Transport 2023年第2期66卷 7-20页

作者： Kozyra, Jacek Lukasik, Zbigniew Kuśmińska-Fijalkowska, Aldona Janota, Aleš Faculty of Transport Electrical Engineering and Computer Science University of Technology and Humanities Radom Poland Faculty of Electrical Engineering and Information Technology University of Žilina Žilina Slovakia

The introduction of a new standard of 48-volt electrical systems in cars comes at an additional cost to the vehicle. Acceptance of these costs is justified because it becomes a way to achieve lower CO2 emissions and lower fuel consumption. An important factor in favor of adopting 48-volt systems is the reduction in CO2 due to the use of a highly efficient 48-volt motor-generator unit coupled to a DC/DC converter. A methodology for testing new solutions to quantify CO2 savings and reductions therefore becomes crucial. This methodology must be capable of demonstrating the CO2 benefits primarily of the innovative technology proven in real-world driving conditions and with a large amount of realistic statistical data. The introduction of new eco-innovations must take into account the linkage and impact on other environmentally oriented ecoinnovative solutions. When implementing new technical solutions, a necessary aspect is the interaction with other innovations installed in vehicles with new electrical installation standards. Therefore, for the expected synergy of solutions to occur, two or more innovative technologies must be installed. Then the combined savings from one of them will affect the performance of the other technologies, and vice versa. The new technology of a high-efficiency 48-volt motor-generator unit cooperating with a 48V/12V DC/DC converter fits very well in creating interactions with other implemented solutions aimed at reducing CO2 emissions. The article discusses the problems of the introduced new technology of a high-efficiency 48-volt motor-generator unit cooperating with a 48V/12V DC/DC converter. The publication analyzes the impact of increasing the voltage rating of current passenger car installations to 48V. Based on the methodology for determining the reduction of CO2 emissions of a vehicle with a 48V/12V DC/DC voltage converter installed, the mass of fuel per unit of engine operation time was determined. The amount of fuel saved was determ

关键词： Carbon dioxide

来源：评论

学校读者我要写书评

暂无评论

QuakeGuard Insight: An IoT-Enabled Machine Learning System 4

QuakeGuard Insight: An IoT-Enabled Machine Learning System

引用

4th IEEE International Conference on Data engineering and Communication Systems, ICDECS 2024

作者： Amat, Kapileshwor Ray Baitha, Aashutosh Adhikarichhetri, Bhabishya Bohara, Neha Bista, Chirayou Shreenidhi, H.S. University Computer Science and Engineering-IOT Faculty of Engineering and Technology Bangalore India

ISBN: (纸本)9798350393354

In this work, an earthquake prediction system utilizing machine learning (ML) techniques and Internet of Things (IoT) technologies is presented, using accelerometer data from the ADXL335 sensor. In order to analyze seismic patterns, the system records multi-axis accelerations. Various machine learning models are then used for predictive analytics. This technology seeks to predict probable seismic events by combining sensor data with sophisticated algorithms, assisting early warning systems for disaster readiness. The ADXL335 accelerometer is the central component of the Earthquake Prediction System described in this work. It records accelerations on the X, Y, and Z axes and converts them into analogue signals for further processing. These data streams are transmitted for feature extraction by utilizing IoT infrastructure, with an emphasis on seismic patterns that may indicate future earthquake events. To evaluate the accelerometer data and produce predicted insights, the system incorporates a variety of machine learning models, such as decision trees and support vector machines. The goal is to support disaster management plans by enabling early detection and warning of seismic activity through this combination of sensor technology and advanced analytics. A wide variety of machine learning models, such as decision trees, support vector machines, and recurrent neural networks, are used to derive actionable insights. These algorithms produce predictive analytics to support catastrophe management methods by carefully analyzing accelerometer data. The ultimate objective is to enable more proactive disaster mitigation planning by facilitating early detection and alerts of seismic activity. This system, which combines advanced analytics with sensor technology, is a critical step in strengthening disaster management systems. Its capacity to predict seismic events may help minimize the effects of earthquakes on impacted areas, help with evacuation plans, and provide timely a

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of the Machine Learning Algorithms for the Early Detection of Breast Carcinoma 2

Performance Analysis of the Machine Learning Algorithms for ...

引用

2nd IEEE International Conference on Interdisciplinary Approaches in technology and Management for Social Innovation, IATMSI 2024

作者： Vanitha, K. Karpagavalli, S.M. Mahesh, T.R. Ali, A. Althaf Sridhar, T. Anitha, K. Faculty of Engineering Department of Computer Science and Engineering Coimbatore India Al Ameen Engineering College Department of Computer Science and Engg Tamilnadu Erode India Faculty of Engineering and Technology Department of Computer Science and Engineering Bangalore India Madanapalle Institute of Technology & Science Department of Computer Applications Andhra Pradesh India Alliance University Alliance College of Engineering and Design Bangalore India Csi College of Engineering Department of Information Technology Tamilnadu Ooty India

ISBN: (纸本)9798350360523

Breast Carcinoma, generally known as breast cancer, primarily affects women, though men can develop it as well. Because of the existence of breast tissue and exposure to female hormones, notably oestrogen, women are at a higher risk It's critical to diagnose breast tumors early. Several techniques based on machine learning (ML were used in this study to classify breast cancer using a dataset that was made available to the public. F-score, recall, precision, preciseness, and other performance metrics were used to evaluate these ML algorithms. Previous research and experimental findings indicate that Random Forest achieved the highest accuracy, with a remarkable accuracy rate of 99.12%. © 2024 IEEE.

关键词： Hormones

来源：评论

学校读者我要写书评

暂无评论

Novel soft robotic finger model driven by electrohydrodynamic(EHD)pump

引用

Journal of Zhejiang University-science A(Applied Physics & engineering) 2024年第7期25卷 596-604页

作者： Xuehang BAI Yanhong PENG Dongze LI Zhuochao LIU Zebing MAO Department of Mechanical Automotive and Materials EngineeringFaculty of EngineeringUniversity of WindsorWindsorN9B 3P4Canada Department of Information and Communication Engineering Graduate School of EngineeringNagoya UniversityNagoya464-8601Japan Department of Intelligent Science and Technology College of Computer Science and TechnologyQingdao UniversityQingdao266071China Design and Research Institute of University of Science and Technology Beijing Co.Ltd. Beijing100083China Faculty of Engineering Yamaguchi UniversityYamaguchi755-8611Japan

1Introduction In the field of robotic-human interactions,soft robotics offers enhanced safety and adaptability.A major challenge in this area is the integration of soft actuators with pump systems,which often increases the system volume and *** study presents the development and testing of a robotic finger powered by electrohydrodynamic(EHD)*** leveraging the electric field-induced flow of dielectric fluids.

关键词： robotic complexity. pump

来源：评论

学校读者我要写书评

暂无评论

Smoke detection in foggy surveillance environment using parallel vision transformer network

引用

Neural Computing and Applications 2024年第31期36卷 19499-19514页

作者： Chaturvedi, Shubhangi Thakur, Poornima Singh Khanna, Pritee Ojha, Aparajita Computer Science and Engineering Department PDPM Indian Institute of Information Technology Design and Manufacturing Dumna Road Madhya Pradesh Jabalpur482005 India

Recent years have seen an unprecedented increase in fire incidents, resulting in severe damage to forest regions, loss of human and animal lives, and unwarranted displacement of people. Owing to these issues, artificial intelligence-based fire detection systems have been developed. These systems mostly work with camera-based inputs for fire detection and alarm generation. As fire-smoke can be seen from a distance, methods for smoke detection have also been deployed for identifying fire incidents. But detecting smoke in an outdoor environment can be challenging due to weather conditions such as haze, fog, or clouds. These challenges have led to advancements in the field, and various deep learning architectures have been suggested over the years for fire-smoke detection in normal and foggy or cloudy weather conditions. Many existing methods are either computationally expensive and demand high memory, or if they are lightweight, they suffer from lower smoke detection accuracy and high false alarms. In the present paper, a dual-channel vision transformer model ‘SmokeViT’ is proposed for detecting fire-smoke in an outdoor environment. These channels are interlaced with a convolutional neural network to improve the feature learning capability of the model. ‘SmokeViT’ shows a remarkable accuracy of more than 99% and false alarm rate below 0.20% on two publicly available smoke datasets, outperforming six state-of-the-art methods. The model architecture has only 0.4 million parameters and 0.17 giga floating-point operations, making it suitable for deployment on resource-constrained surveillance devices. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Smoke

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：