检索结果-内蒙古大学图书馆

11th International Conference on Mechatronics and Robotics engineering, ICMRE 2025

作者： Mahmud, Shekhar Kutlu, Mustafa Alan, Alper Turan Military Technological College System Engineering Department Muscat Oman Sakarya University of Applied Sciences Mechatronics Engineering Department Sakarya Turkey International University of Kuwait Computer Science & Cybersecurity Department Kuwait City Kuwait

ISBN: (纸本)9798331509293

Advancements in multi-agent systems (MAS) have enabled swarm-based systems to perform decentralized decision-making and autonomous tasks. However, optimizing their performance while ensuring transparency and interpretability remains a challenge. This paper introduces a framework that combines Bayesian optimization with Explainable Artificial Intelligence (XAI) techniques to enhance both the efficiency and transparency of MAS swarms. The Bayesian optimization framework fine-tunes agent parameters to improve swarm metrics such as energy efficiency, task completion time, and coordination success. The experimental results show significant improvements: a 25% increase in the coordination success rate, a 15% increase in energy efficiency, and a 20 % reduction in task completion time. XAI techniques, including SHAP values, provide interpretable explanations for optimization decisions, improving user trust and understanding. This study demonstrates the efficacy of integrating Bayesian optimization with XAI to create transparent, efficient, and reliable MAS swarms. Future work should address scalability and implications in dynamic environments. © 2025 IEEE.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Bitcoin Price Prediction Using XGBoost Classifier: A Machine Learning Approach 7th

Bitcoin Price Prediction Using XGBoost Classifier: A Machine...

引用

7th International Conference on Soft Computing and Signal Processing, ICSCSP 2024

作者： Sai, P. H. V. Sesha Talpa Acharya, Ganesh Yellappa Pramod, S. Ganesan, Shanmuga Canaraj Bangarraju, Saripelli Chaitanya Tiwari, Kishan Jaswanthi, Katakam Bhaumik, Amiya Department of Mechanical Engineering Malla Reddy College of Engineering and Technology Hyderabad India School of Mechanical Engineering Lincoln University College Petaling Jaya Malaysia Department of Computer Science and Engineering Malla Reddy University Hyderabad India Department of Computer Science and Data Science Engineering Chalapathi Institute of Engineering and Technology Andhra Pradesh Guntur India Lincoln University College Petaling Jaya Malaysia

ISBN: (纸本)9789819609239

Cryptocurrency, particularly Bitcoin, has become a significant component of the financial asset market over the last years with its unstable price. For Traders, investors, and other market participants, the potential movement in Bitcoin’s price is becoming more important. This study focuses on mitigating the unpredictability of Bitcoin prices by using the classifier of XGBoost. This work uses historical data of Bitcoin’s price and data of relevant factors like trading volume, sentiment analysis of the market, and technical indicator. Data pre-processing techniques such as missing value treatment, normalization, and the split of data into training and testing are performed first. XGBoost is then trained in the developing set to identify the patterns in the input variables. The test data is then employed to assess the model with the help of various metrics including accuracy, precision, recall, and F1-score. The XGBoost model has also been compared with the other base models and the traditional forecasting models based on time series. Our results also suggest that the proposed model outperformed the benchmark model and reported 97% accuracy. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Cost estimating

来源：评论

学校读者我要写书评

暂无评论

A Perspective Analysis of Optical Biosensors in Machine Learning Applications 18

A Perspective Analysis of Optical Biosensors in Machine Lear...

引用

18th INDIAcom;11th International Conference on Computing for Sustainable Global Development, INDIACom 2024

作者： Kumar, B. Naveen Panduranga Rao, M.V. Sharan, Preeta Varun, K.R. Kallam, Suresh Kumaresan, M. Faculty of Engineering and Technology Department of Computer Science and Engineering Bengaluru India The Oxford College of Engineering Department of Electronics and Communication Engineering Bengaluru India The Oxford College of Engineering Department of Mechanical Engineering Bengaluru India

ISBN: (纸本)9789380544519

Optical biosensors, a novel invention at the intersection of biotechnology and optics, are revolutionizing the field of biomedical diagnostics. Optical biosensors act by identifying variations in light's wavelength, phase, polarization, or intensity caused by interactions between a sensing element and the target analyte. Optical biosensors outperform other sensor types in sensing applications due to their quick, accurate, and extremely sensitive results. When evaluating optical sensors, total power, core power, efficient area, and indices are the most crucial variables to consider. Recent years have seen notable advancements in machine learning (ML), a branch of artificial intelligence (AI). This review investigates the complementary nature of optical biosensors and machine learning methods. Here, the potential utility of ML for optical biosensors is explored in detail. The advantages and drawbacks of the most popular machine learning methods are listed based on an analysis of the optical biosensing data. It highlights the possible effects of machine learning on improving the sensitivity, selectivity, and adaptability of optical biosensing devices, and it summarizes current advancements in the field. Finally, the study considers the challenges and limitations that associated with current optical biosensing techniques. © 2024 Bharati Vidyapeeth, New Delhi.

关键词： Machine learning optical biosensor photonic crystal surface plasmon resonance surface-enhanced Raman scattering

来源：评论

学校读者我要写书评

暂无评论

Leveraging Data Analytics to Enhance Smart Home Efficiency and Security 2

Leveraging Data Analytics to Enhance Smart Home Efficiency a...

引用

2nd IEEE International Conference on Emerging Research in Computational science, ICERCS 2024

作者： Vivekanandan, Karthi Kaleeswari, B. Natchiammai, P.L. Anthonisamy, Arun Vijayabharathi, R. Alagarsamy, Manjunathan Builders Engineering College Department of Electrical and Electronics Engineering Tirupur India Department of Electronics and Communication Engineering Chennai India Mookambigai College of Engineering Department of Electronics and Communication Engineering Pudukkottai India Panimalar Engineering College Department of Computer Science and Business System Chennai India Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Department of Computer Science and Engineering Chennai India K. Ramakrishnan College of Technology Department of Electronics and Communication Engineering Trichy India

ISBN: (纸本)9798331534950

Smart home technology has made daily life easier, automated, and managed. IoT devices like smart speakers, cameras, thermostats, and security systems are increasingly integrated, raising security and privacy concerns. This study examines smart home devices' energy consumption, use trends, device failures, and system efficiency. This research uses smart home devices to identify consumption trends and risks. To better understand smart home ecosystems, the study will evaluate energy consumption, device usage hours, and malfunctions that can affect functionality and security. Using predictive analytics and machine learning, the researchers predict excessive energy usage and device problems. These methods identify trends and irregularities in smart home device operation to improve performance, efficiency, and security. This study investigates how user decisions, usage hours, and device age affect energy consumption, as well as how to identify optimization opportunities. The data analysis study contains statistical summaries and visualisations of device type, usage hours, energy consumption, user preferences, malfunction incidents, and device age. Machine learning algorithms such as linear regression and anomaly detection predict energy usage and locate anomalies. The data illustrate energy and device efficiency trends and recommend improvements to smart home security and effectiveness. This study addresses smart home device vulnerabilities and inefficiencies to improve smart home system optimization. The results offer smart home technology manufacturers and customers ways to improve energy efficiency, device performance, and system security. © 2024 IEEE.

关键词： Smart manufacturing

来源：评论

学校读者我要写书评

暂无评论

Predicting Used Car Prices Employing Data Mining Techniques 3rd

Predicting Used Car Prices Employing Data Mining Techniques

引用

3rd International Conference on Intelligent systems and Sustainable Computing, ICISSC 2023

作者： Sai, P. H. V. Sesha Talpa Bharathi, V. V. Pratibha Lahari, M. L. R. Chaitanya Madalageri, Veeresh P. Marol, Vinodkumar S. Arun, C.K. Tiwari, Kishan Bhaumik, Amiya Department of Mechanical Engineering Malla Reddy College of Engineering and Technology Hyderabad India Department of Mechanical Engineering Mahaveer Institute of Science and Technology Hyderabad India School of Mechanical Engineering Lincoln University College Petaling Jaya Malaysia Department of Computer Science and Engineering Malla Reddy University Hyderabad India Lincoln University College Petaling Jaya Malaysia

ISBN: (纸本)9789819783540

A significant number of cars are purchased and sold annually as a result of the price advantage. Reliable used car price forecasting became essential to understand the vehicle's value and gained popularity. This involves many factors such as make, model, condition, and other features of the used car. These attributes are to be properly processed to get accurate predictions. This work's main goal is to estimate used automobile prices utilizing factors that have a significant impact on the price. Null, redundant, and missing values are found and processed using data mining techniques. These values should be eliminated, and significant qualities should be taken into account. Three regressors—the Random Forest Regressor, the Linear Regression, and the Bagging Regressor—are assessed, trained, and contrasted in this supervised learning study utilizing a benchmark dataset. The Random Forest Regressor scored the highest (95%), followed by the MAE (0.0008), RMSE (0.0378), and MSE (0.025) among all the experiments. Apart from Random Forest Regression, Bagging Regression also fared well, scoring 88%, and Linear Regression, scoring 85%. All studies employed an 80/20 train-test split with 40 random states. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Joint Task Allocation and Resource Optimization for Blockchain Enabled Collaborative Edge Computing

引用

China Communications 2024年第12期21卷 218-229页

作者： Xu Wenjing Wang Wei Li Zuguang Wu Qihui Wang Xianbin College of Electronic and Information Engineering Nanjing University of Aeronautics and AstronauticsNanjing 211106China Key Laboratory of Dynamic Cognitive System of Electromagnetic Spectrum Space Ministry of Industry and Information TechnologyNanjing 211106China Department of Electrical and Computer Engineering Western UniversityCanada

Collaborative edge computing is a promising direction to handle the computation intensive tasks in B5G wireless ***,edge computing servers(ECSs)from different operators may not trust each other,and thus the incentives for collaboration cannot be *** this paper,we propose a consortium blockchain enabled collaborative edge computing framework,where users can offload computing tasks to ECSs from different *** minimize the total delay of users,we formulate a joint task offloading and resource optimization problem,under the constraint of the computing capability of each *** apply the Tammer decomposition method and heuristic optimization algorithms to obtain the optimal ***,we propose a reputation based node selection approach to facilitate the consensus process,and also consider a completion time based primary node selection to avoid monopolization of certain edge node and enhance the security of the *** results validate the effectiveness of the proposed algorithm,and the total delay can be reduced by up to 40%compared with the non-cooperative case.

关键词： blockchain collaborative edge computing resource optimization task allocation

来源：评论

学校读者我要写书评

暂无评论

Knowledge‐based deep learning system for classifying Alzheimer's disease for multi‐task learning

引用

CAAI Transactions on Intelligence Technology 2024年第4期9卷 805-820页

作者： Amol Dattatray Dhaygude Gaurav Kumar Ameta Ihtiram Raza Khan Pavitar Parkash Singh Renato R.Maaliw III Natrayan Lakshmaiya Mohammad Shabaz Muhammad Attique Khan Hany S.Hussein Hammam Alshazly Department of Data Science University of WashingtonSeattleWashingtonUSA Department of Computer Science&Engineering Parul Institute of TechnologyParul UniversityVadodaraGujaratIndia Department of Computer Science Jamia HamdardDelhiIndia Department of Management Lovely Professional UniversityPhagwaraIndia 5 College of Engineering Southern Luzon State UniversityLucbanQuezonPhilippines Department of Mechanical Engineering Saveetha School of EngineeringSIMATSChennaiTamil NaduIndia Model Institute of Engineering and Technology JammuJ&KIndia Department of Computer Science HITEC UniversityTaxilaPakistan Department of Computer Science and Mathematics Lebanese American UniversityBeirutLebanon Electrical Engineering Department College of EngineeringKing Khalid UniversityAbhaSaudi Arabia Electrical Engineering Department Aswan UniversityAswanEgypt Faculty of Computers and Information South Valley UniversityQenaEgypt

Deep learning has recently become a viable approach for classifying Alzheimer's disease(AD)in medical ***,existing models struggle to efficiently extract features from medical images and may squander additional information resources for illness *** address these issues,a deep three‐dimensional convolutional neural network incorporating multi‐task learning and attention mechanisms is *** upgraded primary C3D network is utilised to create rougher low‐level feature *** introduces a new convolution block that focuses on the structural aspects of the magnetORCID:ic resonance imaging image and another block that extracts attention weights unique to certain pixel positions in the feature map and multiplies them with the feature map ***,several fully connected layers are used to achieve multi‐task learning,generating three outputs,including the primary classification *** other two outputs employ backpropagation during training to improve the primary classification *** findings show that the authors’proposed method outperforms current approaches for classifying AD,achieving enhanced classification accuracy and other in-dicators on the Alzheimer's disease Neuroimaging Initiative *** authors demonstrate promise for future disease classification studies.

关键词： classification deep learning

来源：评论

学校读者我要写书评

暂无评论

Integrating Machine Learning (ML) and Deep Learning (DL) Methods to Produce Reliable Wind Power Predictions 2

Integrating Machine Learning (ML) and Deep Learning (DL) Met...

引用

2nd International Conference Computational and Characterization Techniques in engineering and sciences, IC3TES 2024

作者： Birudaraju, Hyma Sailaja, K. Sreedevi, Vaitla Viswanathan, R. Vandaarkuzhali, S. Guru Nanak Institutions Technical Campus Department Computer Science and Engineering Hyderabad India Gurunanak Institutional Technical Campus Department Computer Science and Engineering Hyderabad India Department Computer Science and Engineering Secunderabad India Kongu Engineering College Department of Mathematics Erode India Mailam Engineering College Department of Mechanical Engineering Mailam India

ISBN: (纸本)9798350364699

Wind energy forecasting is crucial for effective implementation due to weather instability and unpredictability. Seamless incorporation into contemporary electricity systems. Various methodologies and strategies have been used and utilized to achieve precise wind power prediction over a wide range of timeframes. Every approach has advantages and disadvantages. This study first examines the current uses of Machine Learning and Deep Learning methods in wind power and wind speed predictions. An extensive examination and classification of the most significant forecasting techniques has been conducted. Simultaneously, thought-provoking conversations are offered to facilitate the examination of all the topics presented. Two algorithms, one from machine learning (ML) and the other from deep learning (DL), have been chosen and used to anticipate wind power. The findings have shown the strong capacity of both algorithms to accurately capture the characteristics of the produced power. Additional analyses of the outcomes about their correctness and prospects are being contemplated. © 2024 IEEE.

关键词： Wind forecasting

来源：评论

学校读者我要写书评

暂无评论

Analysis of performance, combustion, and emission parameters in a reactivity-controlled combustion ignition (RCCI) engine–an intensive review

引用

International Journal of Ambient Energy 2022年第1期43卷 6839-6848页

作者： Elumalai, P.V. Pradeepkumar, A.R. Murugan, M. Saravanan, A. Sreenivasa Reddy, M. Rama Sree, S. Meenakshi Sundaram, G. Department of Mechanical Engineering Aditya Engineering College Surampalem India Department of Mechanical Engineering Dhanalashmi College of Engineering Chennai India Department of Mechanical Engineering Aditya College of Engineering and Technology Surampalem India Department of Computer Science Engineering Aditya Engineering College Surampalem India Department of Electronics and Communication Engineering Aditya College of Engineering Surampalem India

The new diversion of research in the field of engine modification is reactivity-induced compression ignition (RCCI). Researchers recommend that RCCI is the solution for regulating pre-mixed combustion, thereby promoting lean air–fuel mixture combustion. It is also suitable for low-temperature operations. The combination of lean mixture and low-temperature operations leads to a reduction of the oxides of nitrogen and particles of soot production during combustion. This paper analyses the principle and methodology of RCCI and compares its performance with homogeneous controlled compression ignition (HCCI). An intensive literature review is done and a concluding report is compiled. This will be an essential content for researchers who pursue their experimental and analytical work in RCCI. The future scope of RCCI can be extended to alternate fuel sources such as biodiesel ethanol and natural gas by adopting HCCI concepts. However, there are a few limitations in this, such as higher HC and CO emissions, which may necessitate oxidation catalysts. © 2022 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Biodiesel

来源：评论

学校读者我要写书评

暂无评论

Adaptive Confidence Threshold for ByteTrack in Multi-Object Tracking 12

Adaptive Confidence Threshold for ByteTrack in Multi-Object ...

引用

12th IEEE International Conference on Control, Automation and Information sciences, ICCAIS 2023

作者： Ma, Linh Van Hussain, Muhammad Ishfaq Park, JongHyun Kim, Jeongbae Jeon, Moongu Gwangju Institute of Science and Technology School of Electrical Engineering and Computer Science Korea Republic of Pusan National University Department of Mechanical-IT Convergence System Engineering Busan Korea Republic of

ISBN: (纸本)9798350328783

We investigate the application of ByteTrack in the realm of multiple object tracking. ByteTrack, a simple tracking algorithm, enables the simultaneous tracking of multiple objects by strategically incorporating detections with a low confidence threshold. Conventionally, objects are initially associated with high confidence threshold detections. When the association between objects and detections becomes ambiguous, ByteTrack extends the association to lower confidence threshold detections. One notable drawback of the existing ByteTrack approach is its reliance on a fixed threshold to differentiate between high and low-confidence detections. In response to this limitation, we introduce a novel and adaptive approach. Our proposed method entails a dynamic adjustment of the confidence threshold, leveraging insights derived from overall detections. Through experimentation, we demonstrate the effectiveness of our adaptive confidence threshold technique while maintaining running time compared to ByteTrack. © 2023 IEEE.

关键词： Object detection

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：