检索结果-内蒙古大学图书馆

13th international Winter conference on Brain-Computer Interface, BCI 2025

作者： Yin, Kang Shin, Hye-Bin Li, Dan Lee, Seong-Whan Dept. of Artificial Intelligence Korea University Seoul Korea Republic of Dept. of Brain and Cognitive Engineering Korea University Seoul Korea Republic of

ISBN: (纸本)9798331521929

Multimodal learning has been a popular area of research, yet integrating electroencephalogram (EEG) data poses unique challenges due to its inherent variability and limited availability. In this paper, we introduce a novel multimodal framework that accommodates not only conventional modalities such as video, images, and audio, but also incorporates EEG data. Our framework is designed to flexibly handle varying input sizes, while dynamically adjusting attention to account for feature importance across modalities. We evaluate our approach on a recently introduced emotion recognition dataset that combines data from three modalities, making it an ideal testbed for multimodal learning. The experimental results provide a benchmark for the dataset and demonstrate the effectiveness of the proposed framework. This work highlights the potential of integrating EEG into multimodal systems, paving the way for more robust and comprehensive applications in emotion recognition and beyond. © 2025 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

HybridFL: Hybrid Approach Toward Privacy-Preserving Federated learning 6th

HybridFL: Hybrid Approach Toward Privacy-Preserving Federate...

引用

6th international conference on Security and Privacy in New Computing Environments, SPNCE 2023

作者： Ali, Sheraz Mamoon, Saqib Usman, Areeba Abidin, Zain ul Zhao, Chuan School of Information Science and Engineering University of Jinan Jinan250022 China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China University of Sargodha Sargodha Pakistan Shandong Provincial Key Laboratory of Network-Based Intelligent Computing University of Jinan Jinan250022 China Shandong Provincial Key Laboratory of Software Engineering University of Jinan Jinan250022 China

ISBN: (纸本)9783031736988

In this study, we introduce a novel Hybrid Federated learning (HybridFL) approach aimed at enhancing privacy and accuracy in collaborative machine learning scenarios. Our methodology integrates Differential Privacy (DP) and secret sharing techniques to address inference risks during training and protect against information leakage in the output model. Drawing inspiration from recent advances, we present a HybridFL framework that combines the strengths of Homomorphic Encryption (HE) and Multi-Party Computation (MPC) to achieve secure computation without the computational overhead of pure HE methods. Our contributions include a privacy-preserving design for Federated learning (FL) that ensures local data privacy through secret sharing while leveraging DP mechanisms for noise addition. The system offers resilience against unreliable participants and is evaluated using various machine learning models, including Convolutional Neural Networks (CNN), Multi-Layer Perceptrons (MLP), and linear regression. Furthermore, we address potential external threats by deploying predictive model outputs as robust services against inference attacks. Experimental results demonstrate improved accuracy and convergence speed, establishing the viability of HybridFL as an effective solution for collaborative machine learning with enhanced privacy guarantees. © ICST Institute for Computer Sciences, Social Informatics and Telecommunications engineering 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Autonomous Piloting Algorithms for Drones in Underground Space with No GPS Navigation 30th

Autonomous Piloting Algorithms for Drones in Underground Spa...

引用

30th international conference on Computational and Experimental engineering and Sciences

作者： Zhong, Zicheng Lin, Zhiyan Jiang, Xiangzhou Wang, Chenhao Zhang, Chao Li, Zichang Tsinghua Univ Sichuan Energy Internet Res Inst Chengdu 610213 Peoples R China Beijing Univ Chem Technol Int Educ Coll Beijing 100013 Peoples R China Tsinghua Univ Dept Hydraul Engn Beijing 100084 Peoples R China

ISBN: (纸本)9783031774911;9783031774898;9783031774881

Developing intelligent robotic helpers for underground engineering presents significant hurdles, particularly with regard to autonomous navigation in areas devoid of GPS signals. Although drones using GPS navigation in open areas are sophisticated and widely used, when GPS signals are poor or in areas with subterranean space, drones become blind and lose their benefits. In this study, a thorough foundation for autonomous piloting algorithms was put forward in order to create an autonomous drone, which can pilot autonomously in surroundings without external referrals. The technological framework combines sensor fusion, machine learning, path planning, simultaneous localization and mapping (SLAM), and real-time communication. First, data from LiDAR, ultrasonic sensors, and inertial measurement units (IMUs) are first combined using sensor fusion techniques to generate a 3D virtual model of the surrounding area. Real-time-mapping and locating are facilitated by SLAM algorithms. Second, machine learning models use sensor data to inform piloting decisions, while computer vision algorithms facilitate obstacle detection and recognition. Third, using the virtual model's observed impediments and predetermined mission objectives, path planning algorithms create safe and effective flying routes. Hardware and software were created to accompany a drone for test and demonstration. Through a loop of testing, validation, redundancy, and fail-safes, the autonomous piloting algorithms were integrated and improved. The drone equipped with the autonomous piloting algorithms was able to navigate in subterranean space on its own with no GPS navigation after trial and error. The capability and dependability of autonomous drone systems for inspection support in such conditions are to be improved through ongoing research and development.

关键词： Autonomous piloting underground space LiDAR sensor fusion machine learning path planning

来源：评论

学校读者我要写书评

暂无评论

Research on data-driven Virtual Experimental Framework 24

Research on Data-driven Virtual Experimental Framework

引用

7th international conference on Educational Technology Management, ICETM 2024

作者： Li, Miaomiao He, Xiangchun College of Educational Technology Northwest Normal University Gansu Lanzhou China

ISBN: (纸本)9798400717468

With the rapid development of computing technology, data-driven method has become an indispensable part of scientific research and engineering design. Aiming at the problems of high cost and long cycle of traditional experimental methods, a data-driven virtual experimental framework is proposed. The framework utilizes advanced data analysis techniques and machine learning algorithms to predict and simulate the behavior of complex systems without the need for physical experiments. Based on the research of virtual experiment literature, this paper understands the current status of virtual experiment research, summarizes the key elements of virtual experiment, and proposes a virtual experiment framework including data layer, service layer and user layer by using design-based research method. The framework includes knowledge graph construction of data layer and behavior data construction based on xAPI. Service layer data collection, analysis and application and other basic functions;The design of specific virtual experiments in the application layer and the feedback of experiment reports, and the data collection, analysis and application methods for the overall experiment design through the experiment link. In the part of result report, it not only gives the overall results of the data analysis of the whole experiment process, but also gives the personalized resources and intelligent assistant database resources to provide data feedback for the improvement of the virtual experiment. © 2024 Copyright held by the owner/author(s).

关键词： data driven

来源：评论

学校读者我要写书评

暂无评论

Digital twin enhanced with machine learning Algorithms for Irrigation Management Using Sensor data 6

Digital twin enhanced with Machine Learning Algorithms for I...

引用

6th international conference on Industry 4.0 and Smart Manufacturing, ISM 2024

作者： Carlo Tancredi, Giovanni Paolo Preite, Luca Vignali, Giuseppe CIPACK Center Parco Area delle Scienze 181/A Parma43124 Italy Department of Engineering for Industrial Systems and Technologies Parco Area delle Scienze 181/A Parma43124 Italy

Efficient irrigation management is critical for maximizing agricultural output while minimizing water waste. This study investigates the effectiveness of machine learning (ML) for data-driven irrigation decision support systems (DSS) to address the scalability issue in artificial intelligence applications. Therefore, the scientific literature highlights how scalability is the main issue that needs to be investigated. In this framework, a living lab focused on an olive cultivation in a greenhouse has been developed to train and test a digital twin application enhanced with machine learning algorithms. Specifically, the algorithm classifies the irrigation status by assessing soil and environmental sensor data. The integration between the physical and the virtual counterparts has been implemented exploiting a Message Queuing Telemetry Transport (MQTT) communication protocol, where soil and environmental data have been treated as input topics. The model performance has been evaluated by calculating accuracy, precision, recall, F1-score, and confusion matrices, which highlight the effectiveness of the model in managing irrigation by assessing no-crop specific features with the aim of improving the scalability in greenhouse applications. © 2024 The Authors. Published by Elsevier B.V.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Using machine learning to Assess the Impact of Harsh Violent Discipline on Children and Adolescents in Lowand Middle-Income Countries: A Comparative Analysis Focusing on Its Relationship with Disabilities

Using Machine Learning to Assess the Impact of Harsh Violent...

引用

18th international Joint conference on Biomedical engineering Systems and Technologies, BIOSTEC 2025

作者： Barreira, Milena S. Da Silva, Ariane C. B. Mannani, Hasheem Nobre, Cristiane N. Institute of Exact Sciences and Informatics Pontifical Catholic University of Minas Gerais Belo Horizonte Dom José Gaspar Brazil University College Dublin Ireland

Children’s exposure to violence has long been a social and cultural concern, manifesting in various forms across societies. According to UNICEF, approximately 300 million children worldwide, aged 2 to 4, experience regular violent discipline from caregivers, with around 250 million subjected to physical punishment. This study leverages data from the Multiple Indicator Cluster Survey to investigate the prevalence of severe violent discipline among children with and without disabilities in 54 lowand middle-income countries. Using machine learning algorithms, including Decision Tree, Random Forest, XGBoost, Support Vector machine (SVM), and Neural Networks, the analysis revealed that SVM outperformed other models, achieving the highest precision, recall, and F1-score (with values of 78% and 80% for the violence and non-violence classes, respectively). The results highlighted an increase in severe disciplinary violence correlated with the presence of disabilities, particularly in contexts involving the domain of ‘controlling behavior’. © 2025 by SCITEPRESS – Science and Technology Publications, Lda.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Autonomous international Classification of Diseases Coding Using Pretrained Language Models and Advanced Prompt learning Techniques: Evaluation of an Automated Analysis System Using Medical Text

引用

JMIR MEDICAL INFORMATICS 2025年 13卷 e63020页

作者： Zhuang, Yan Zhang, Junyan Li, Xiuxing Liu, Chao Yu, Yue Dong, Wei He, Kunlun Chinese Peoples Liberat Army Gen Hosp Med Big Data Res Ctr 28 Fuxing Rd Beijing 100853 Peoples R China Beijing Inst Technol Sch Comp Sci & Technol Beijing Peoples R China Digital Hlth China Technol Co LTD Beijing Peoples R China Peoples Liberat Army Gen Hosp Med Ctr 6 Sr Dept Cardiol Beijing Peoples R China

Background: machine learning models can reduce the burden on doctors by converting medical records into international Classification of Diseases (ICD) codes in real time, thereby enhancing the efficiency of diagnosis and treatment. However, it faces challenges such as small datasets, diverse writing styles, unstructured records, and the need for semimanual preprocessing. Existing approaches, such as naive Bayes, Word2Vec, and convolutional neural networks, have limitations in handling missing values and understanding the context of medical texts, leading to a high error rate. We developed a fully automated pipeline based on the Key-bidirectional encoder representations from transformers (BERT) approach and large-scale medical records for continued pretraining, which effectively converts long free text into standard ICD codes. By adjusting parameter settings, such as mixed templates and soft verbalizers, the model can adapt flexibly to different requirements, enabling task-specific prompt learning. Objective: This study aims to propose a prompt learning real-time framework based on pretrained language models that can automatically label long free-text data with ICD-10 codes for cardiovascular diseases without the need for semiautomatic preprocessing. Methods: We integrated 4 components into our framework: a medical pretrained BERT, a keyword filtration BERT in a functional order, a fine-tuning phase, and task-specific prompt learning utilizing mixed templates and soft verbalizers. This framework was validated on a multicenter medical dataset for the automated ICD coding of 13 common cardiovascular diseases (584,969 records). Its performance was compared against robustly optimized BERT pretraining approach, extreme language network, and various BERT-based fine-tuning pipelines. Additionally, we evaluated the framework's performance under different prompt learning and fine-tuning settings. Furthermore, few-shot learning experiments were conducted to assess the feasibil

关键词： BERT bidirectional encoder representations from transformers pretrained language models prompt learning ICD international Classification of Diseases cardiovascular disease few-shot learning multicenter medical data

来源：评论

学校读者我要写书评

暂无评论

Mitigating urban pollution: A comparative life cycle assessment of hydrogen, electric, and diesel buses for urban transportation

引用

international JOURNAL OF HYDROGEN ENERGY 2025年 125卷 333-353页

作者： Mahmoudi, Ali Afshari, Hamid Sarhadi, Hassan Jabbarzadeh, Armin Dalhousie Univ Dept Ind Engn 5269 Morris St Halifax NS B3H4R2 Canada Acadia Univ FC Manning Sch Business Wolfville NS Canada Univ Quebec Ecole Technol Super Dept Syst Engn Montreal PQ Canada

Urban transportation systems, particularly public buses, contribute significantly to global pollution, creating an urgent need for sustainable solutions. Alternative fuel buses and other disruptive technological advancements in this field are essential to resolve these problems. The absence of studies on the life cycle assessment (LCA) of hydrogen-fueled buses, along with comparative analyses of alternative-fueled buses, makes this research particularly timely. This study develops a comprehensive LCA framework to measure the economic and environmental impact of using different technologies (i.e., hydrogen-fueled, electric, and diesel buses). Different fuel production methods were examined, considering operational factors such as energy consumption across various routes. This study contributes to enhancing the LCA methodology for public bus operations by using machine learning algorithms to cluster routes and identify optimal demonstration routes for analysis. The results highlight the impact of fuel production methods for hydrogen-fueled buses in the significant pollutant reductions (e.g., CO2 and NOx), despite their high life cycle costs. The proposed framework is validated with real data from Halifax, Canada, and expanded to assess public bus networks in cities with varying routes, topology, and population levels. The paper's analyses consider future technological advances to lower costs, aligning them with electric buses over time. This study helps policymakers choose the best public bus alternatives to improve the economic, environmental, and social sustainability of urban transportation.

关键词： Life cycle assessment Sustainability Hydrogen energy machine learning Public transportation

来源：评论

学校读者我要写书评

暂无评论

Research on Fracture Propagation of Fractured Shale Reservoirs by Supercritical CO2 Fracturing Based on Numerical Simulation and machine learning Tools 30th

Research on Fracture Propagation of Fractured Shale Reservoi...

引用

30th international conference on Computational and Experimental engineering and Sciences

作者： Han, Lei Shi, Xian Ni, Hongjian Zhang, Weidong Ge, Xiaoxin China Univ Petr East China Coll Petr Engn Qingdao 266580 Peoples R China China Univ Petr East China State Key Lab Deep Oil & Gas Qingdao 266580 Peoples R China

ISBN: (纸本)9783031774911;9783031774898;9783031774881

Understanding the interaction between fracturing fractures and natural fractures (NF) is crucial for estimating fracture complexity and simulated reservoir volume (SRV). For the simulation of complex network models, the general time cost is enormous, therefore, it is very meaningful to consider using machine learning algorithms to predict fracture propagation. On the basis of establishing a fluid structure coupling model using the Cohesive module of ABAQUS and completing indoor experimental verification, this article introduces the global embedded cohesion zone model (CZM) combined with the natural fracture (NF) model (generated in Python) to establish a dispersed mesh model. Based on this model, compare the fracture propagation patterns of hydraulic fracturing and supercritical CO2 fracturing. Design experimental schemes to study the problem of fracture propagation under different engineering and geological conditions. Using machine learning (LSTM-Long Short-Term Memory algorithm) to predict the changes in fracture length under different time and conditions, and comparing it with actual simulation results to optimize the algorithm. The results indicate that supercritical CO2 is more inclined to penetrate natural fractures, leading to the expansion of fractures within the rock matrix. Hydraulic fracturing fractures combine well with natural fractures. The established prediction model can effectively predict the state of fracture propagation. This study combines numerical simulation and machine learning, which is of great significance for enriching the theory of supercritical CO2 fracturing.

关键词： Shale reservoir Natural fracture Supercritical CO2 Cohesion zone model LSTM model

来源：评论

学校读者我要写书评

暂无评论

Study on State-of-the-Art machine learning Algorithms Efficiency for CO2 Emissions Prediction in Fleet Management Optimization 18th

Study on State-of-the-Art Machine Learning Algorithms Effici...

引用

18th international conference on Interdisciplinarity in engineering, INTER-ENG 2024

作者： Muraru, Mădălina Maria Simó, Zsuzsa Iantovics, László Barna Pharmacy Science and Technology of Targu Mures George Emil Palade University of Medicine Targu Mures540142 Romania

ISBN: (纸本)9783031816840

Global carbon dioxide emissions from fossil fuels and industry reached a record in 2022, emphasizing the importance of reducing pollution from the automotive sector. Vehicles represent a significant source of CO₂ emissions, and large fleets are a major challenge in managing the carbon footprint. Although there are strict regulations and initiatives to reduce emissions, companies that manage large fleets face difficulties in collecting and reporting accurate data on vehicle emissions. The lack of uniformity in the provision of data by car manufacturers and the difficulties associated with manual retrieval of information from vehicle documents complicate this process. To address these challenges and with the aim of selecting the best algorithm to integrate into a decision support system, the following machine learning algorithms were involved in the research: Random Forest, XGBoost, and a Feed-Forward Neural Network, to predict CO₂ emissions based on vehicle characteristics from a fleet of over 26,500 records. The models were trained using numerical and categorical data, properly preprocessed, providing a good solution for emissions prediction in the absence of real measured data for newly ordered vehicles. Based on these findings, all of them can be integrated into a complex decision support system, enabling more effective and informed decision-making. The results indicate that the Random Forest algorithm is the most effective for predicting CO2 emissions in this context, as it captures complex relationships between features and the target variable delivering accurate predictions. In this context, the use of machine learning models for large vehicle fleets not only ensures CO2 emission predictions but also contributes to sustainable fleet management and compliance with environmental regulations. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Low emission

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：