检索结果-内蒙古大学图书馆

IEEE COMPUTER GRAPHICS AND APPLICATIONS 2024年第5期44卷 40-53页

作者： Debus, Pascal Issel, Sebastian Tscharke, Kilian Fraunhofer Inst Appl & Integrated Secur D-85748 Garching Germany

This article introduces an innovative interactive visualization tool designed to demystify quantum machine learning (QML) algorithms. Our work is inspired by the success of classical machine learning visualization tools, such as TensorFlow Playground, and aims to bridge the gap in visualization resources specifically for the field of QML. The article includes a comprehensive overview of relevant visualization metaphors from both quantum computing and classical machine learning, the development of an algorithm visualization concept, and the design of a concrete implementation as an interactive web application. By combining common visualization metaphors for the so-called data reuploading universal quantum classifier as a representative QML model, this article aims to lower the entry barrier to quantum computing and encourage further innovation in the field. The accompanying interactive application is a proposal for the first version of a QML playground for learning and exploring QML models.

关键词： Quantum computing Logic gates Qubit machine learning Data visualization Quantum entanglement machine learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Incentivizing Socio-Ethical Integrity in Decentralized machine learning Ecosystems for Collaborative Knowledge Sharing

引用

IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS 2024年第6期11卷 7857-7870页

作者： Chi, Yuanfang Zhang, Qiyue Sun, Jiaxiang Cai, Wei Wang, Z. Jane Leung, Victor C. M. Shenzhen Univ Coll Comp Sci & Software Engn Shenzhen 518060 Peoples R China Univ British Columbia Dept Elect & Comp Engn Vancouver BC V6T 1Z4 Canada Chinese Univ Hong Kong Sch Sci & Engn Shenzhen 518172 Peoples R China

To broaden domain knowledge and enable advanced analytics, machine learning (ML) algorithms increasingly utilize comprehensive datasets across diverse sectors. However, these disparate datasets held by various stakeholders raise concerns over data heterogeneity, privacy, and security. Decentralized ML research aims to protect data privacy and integrate knowledge bases, especially knowledge graphs, to address data heterogeneity challenges. Yet, the question of how to foster trustworthy collaborations in decentralized ML ecosystems remains underexplored. This study pioneers two innovative socio-economic mechanisms designed to ensure dependable collaborations with socio-ethical integrity within a decentralized knowledge inference framework, enabling participants to share knowledge while maintaining data privacy and ethical standards. We employ an evolutionary game theory model to analyze the dynamic interactions between requestors and workers, focusing on achieving a stable equilibrium through theoretical and numerical evaluations. Furthermore, we explore how various critical factors, such as incentive schemes and the accuracy of identifying malicious workers, influence the system's equilibrium, providing insights into optimizing collaborative efforts in decentralized ML ecosystems.

关键词： Stakeholders Collaboration Knowledge graphs Cognition machine learning algorithms Socioeconomics Security Decentralized computing evolutionary game theory reputation system

来源：评论

学校读者我要写书评

暂无评论

Image Processing Technology Based on machine learning

引用

IEEE CONSUMER ELECTRONICS MAGAZINE 2024年第4期13卷 90-99页

作者： Qiao, Qiong Commun Univ China Sch Informat & Commun Engn Beijing Peoples R China

machine learning is a relatively new field. With the deepening of people's research in this field, the application of machine learning is increasingly extensive. On the other hand, with the advancement of science and technology, graphics have been an indispensable medium of information transmission, and image processing technology is also booming. However, the traditional image processing technology, more or less has some defects. This article introduces machine learning into image processing, and studies the image processing technology based on machine learning. This article summarizes the current popular image processing technology, compares various image technologies in detail, and explains the limitations of each image processing method. In addition, on the basis of image processing, this article introduces machine learning algorithm, applies convolution neural network to feature extraction of image processing, and carries out simulation test. In the test, we select VOC2007 dataset for image segmentation, ImageNet dataset for target detection, CIFAR100 dataset for image classification, and ROC curve for performance evaluation. The results show that the algorithm based on deep learning can achieve high accuracy in image segmentation, classification, and target detection. The accuracy of image segmentation is 0.984, the accuracy of image classification is 0.987, and the accuracy of target detection is 0.986. Thus, image processing based on machine learning has great advantages.

关键词： Feature extraction Image processing Image enhancement Histograms Laplace equations Convolution machine learning algorithms machine learning Image Processing Convolution Neural Network Feature Extraction

来源：评论

学校读者我要写书评

暂无评论

In-Situ Dynamic Modulus Prediction for Asphalt Pavement Combining machine learning Algorithm and Sensing Technology

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2024年第8期25卷 8695-8704页

作者： Zhang, Cheng Shen, Shihui Huang, Hai Yu, Shuai Penn State Civil & Environm Engn Dept State Coll PA 16801 USA Penn State Altoona Dept Engn Altoona PA 16601 USA

The in-situ dynamic modulus property of asphalt mixtures is critical to aiding the decision-making of pavement maintenance and rehabilitation. With the recent advancement in data science and sensing technologies, embedded sensors have been applied to collect the in-situ signal induced by traffic loading and estimate the traffic information. However, very limited studies have focused on evaluating the mechanical properties of pavement materials and structures using embedded sensors. This paper aims to present a practical approach to performing the in-situ dynamic modulus test and develop an in-situ dynamic modulus predictive model using Artificial Neural Network (ANN) based on real-time sensing data. Particle-size wireless sensors were implemented in several pavement sections to collect data under vehicular loading. An empirical mode decomposition (EMD) method was introduced to calculate the intrinsic modes of the collected data as the ANN model inputs. Laboratory dynamic modulus tests using the same material as the paving projects were also performed with embedded wireless sensors. Those laboratory data, combined with the field sensing data, were used as the training and testing dataset for developing the ANN model. The results show that the developed ANN model, when adequately trained with particle-level sensing data, is feasible and robust for predicting the in-situ dynamic modulus of asphalt pavement.

关键词： Vehicle dynamics Artificial neural networks Predictive models Feature extraction Mechanical sensors Load modeling machine learning algorithms Artificial neural network (ANN) asphalt mixture empirical mode decomposition (EMD) in-situ dynamic modulus wireless sensor

来源：评论

学校读者我要写书评

暂无评论

Improving electric vehicles sustainability: Accurate forecasting of lithium-ion battery health using machine learning models

引用

JOURNAL OF ENERGY STORAGE 2024年 103卷

作者： Yang, Chao Ye, Zhihao Xiong, Xin Su, Chang Xie, Mengli Naval Univ Engn Sch Elect Engn Wuhan 430000 Hubei Peoples R China Guangdong Univ Technol Sch Adv Mfg Jieyang 522000 Guangdong Peoples R China

Electric vehicles are increasingly acknowledged as a promising solution for addressing global warming and climate change, with their effectiveness greatly influenced by the attributes of energy storage systems. Although lithium-ion batteries are presently the primary choice for electric vehicle energy storage, their deterioration over time poses challenges in maintaining performance. This research introduces a technique for accurately forecasting battery health, which is crucial for ensuring safety and gaining consumer trust. By utilizing various machine learning algorithms such as Random Forest Regression, Light Gradient Boosting Regression, Support Vector Regression, and Stacked Regressor, this study investigates advancements in estimating the state of health of batteries. Feature extraction and selection, and Pearson correlation analysis, play a significant role, with seven key variables identified as inputs for prediction models, categorically capturing essential aspects of battery performance. The characteristics categorized within class A comprised the Voltage-time graph first turning point, Voltage-time graph second turning point, two turning point slop, and turning points in the voltage-time graph yielding superior outcomes compared to other categorized features. The study illustrates the effectiveness of the proposed method using the experimental battery dataset, achieving an impressive SOH prediction accuracy of 99.36 % with the Stacked regression model. This multi-feature model signifies a substantial progression in addressing existing limitations in lithium-ion batteries' SOH estimation, offering potential avenues for enhancing electric vehicle performance and sustainability.

关键词： Electric vehicles Lithium-ion batteries State of health Energy storage systems machine learning algorithms Stacked regressor

来源：评论

学校读者我要写书评

暂无评论

Survey on limitations, applications and challenges for machine learning aided hybrid FSO/RF systems under fog and smog influence

引用

JOURNAL OF MODERN OPTICS 2024年第4-6期71卷 101-125页

作者： Khalid, Hira Sajid, Sheikh Muhammad Nistazakis, Hector E. Ijaz, Muhammad Natl Univ Comp & Emerging Sci Dept Elect Engn Lahore Pakistan Natl & Kapodistrian Univ Athens Dept Phys Sect Elect Phys & Syst Panepistimiopolis 15784 Zografou Greece Manchester Metropolitan Univ Fac Sci & Engn Dept Engn Manchester England

This paper provides a concise overview of hybrid Free Space Optical (FSO)/Radio Frequency (RF) systems operating under fog and smog channels. With the rapid growth of wireless communication and the emergence of the Internet of Things (IoT) have brought about unprecedented connectivity and transformed various aspects of our daily lives. However, certain environmental conditions pose significant challenges to wireless communication systems like FSO and RF technologies. Fog and smog with its dense moisture-laden atmosphere and presence of particulate matter cause absorption and scattering of light, leading to reduced link quality and limited range for FSO communication system. Whereas, RF systems are although less affected by fog/smog as compared to rain but still have inherent limitations in terms of bandwidth and capacity. To overcome these challenges and ensure reliable communication, researchers have turned their attention to hybrid FSO/RF systems which can combine the strengths of FSO and RF technologies and mitigate the limitations of each technology. This work summarizes and explores the hybrid system architecture and machine learning techniques used to enhance the performance and adaptability of wireless communication systems. Additionally, we present the existing experimental research on hybrid FSO/RF systems, performance evaluation metrics, and future research directions to pave the way for further *** FSO: Free Space Optical;RF: Radio Frequency;IoT: Internet-of-Things;OS: Operating Systems;OWC: Optical Wireless Communication;LOS: Line-of-Sight;LPF: Low Pass Filter;AM: Amplitude Modulation;FM: Frequency Modulation;PSK:Phase Shift key;QAM: Quadrature Amplitude Modulation;OFDM: OrthogonalFrequency Division Multiplexing;LF: Low frequency;M-L: Medium frequency;UHF:Ultra High Frequency;SHF: Super High Frequency;EHF: Extremely High frequency;PM: Phase Modulation;QPSK: Quadrature Phase Shift Key;DSSS: Direct SequenceSpread Spectrum;FHSS: Frequen

关键词： Free space optical communication fog and smog attenuation hybrid FSO/RF machine learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Detection of disease-specific signatures in B cell repertoires of lymphomas using machine learning

引用

PLOS COMPUTATIONAL BIOLOGY 2024年第7期20卷 e1011570页

作者： Schmidt-Barbo, Paul Kalweit, Gabriel Naouar, Mehdi Paschold, Lisa Willscher, Edith Schultheiss, Christoph Maerkl, Bruno Dirnhofer, Stefan Tzankov, Alexandar Binder, Mascha Kalweit, Maria Univ Hosp Basel Dept Biomed Translat Immunooncol Basel Switzerland Collaborat Res Inst Intelligent Oncol CRIION Freiburg Germany Univ Freiburg Neurorobot Lab D-79110 Freiburg Germany Martin Luther Univ Halle Wittenberg Internal Med Oncol Hematol 4 Halle Saale Germany Univ Hosp Augsburg Pathol Augsburg Germany Univ Hosp Basel Pathol Basel Switzerland Univ Hosp Basel Med Oncol Basel Switzerland

The classification of B cell lymphomas-mainly based on light microscopy evaluation by a pathologist-requires many years of training. Since the B cell receptor (BCR) of the lymphoma clonotype and the microenvironmental immune architecture are important features discriminating different lymphoma subsets, we asked whether BCR repertoire next-generation sequencing (NGS) of lymphoma-infiltrated tissues in conjunction with machine learning algorithms could have diagnostic utility in the subclassification of these cancers. We trained a random forest and a linear classifier via logistic regression based on patterns of clonal distribution, VDJ gene usage and physico-chemical properties of the top-n most frequently represented clonotypes in the BCR repertoires of 620 paradigmatic lymphoma samples-nodular lymphocyte predominant B cell lymphoma (NLPBL), diffuse large B cell lymphoma (DLBCL) and chronic lymphocytic leukemia (CLL)-alongside with 291 control samples. With regard to DLBCL and CLL, the models demonstrated optimal performance when utilizing only the most prevalent clonotype for classification, while in NLPBL-that has a dominant background of non-malignant bystander cells-a broader array of clonotypes enhanced model accuracy. Surprisingly, the straightforward logistic regression model performed best in this seemingly complex classification problem, suggesting linear separability in our chosen dimensions. It achieved a weighted F1-score of 0.84 on a test cohort including 125 samples from all three lymphoma entities and 58 samples from healthy individuals. Together, we provide proof-of-concept that at least the 3 studied lymphoma entities can be differentiated from each other using BCR repertoire NGS on lymphoma-infiltrated tissues by a trained machine learning model. Lymphoma, a complex group of malignant blood cancers, poses a significant diagnostic challenge due to its diverse subtypes. Yet, precise classification is crucial for tailored treatment. In our research, w

关键词： Lymphoma B cells machine learning Cancer detection and diagnosis machine learning algorithms Malignant tumors Antibodies Neoplastic transformation

来源：评论

学校读者我要写书评

暂无评论

Predicting human trust in human-robot collaborations using machine learning and psychophysiological responses

引用

ADVANCED ENGINEERING INFORMATICS 2024年 62卷

作者： Chauhan, Hardik Jang, Youjin Jeong, Inbae North Dakota State Univ Dept Civil Construct & Environm Engn Fargo ND 58105 USA North Dakota State Univ Dept Mech Engn Fargo ND USA

In the ever-evolving construction industry, grappling with challenges such as labor shortages and workplace hazards, human-robot collaboration (HRC) has emerged as a transformative solution. However, the industry faces hurdles in comprehending the intricacies of trust dynamics within the domain of HRC. It exerts considerable influence on both productivity and safety within the construction sector. To address this issue, the paper proposes machine learning-based models to predict and enhance human trust in construction robots using psychophysiological data. Through a virtual reality bricklaying task across varied construction settings, this study collected psychophysiological data from participants and predicted trust score. Results indicated that electrodermal activity and skin temperature were two significant standalone variables for trust prediction. With similar R squared value of 0.98, the XG boost, and random forest models displayed superior predictive accuracy, with minor standard deviations of 0.003 and 0.004, respectively. This study contributes valuable insights into trust dynamics, paving the way for more dependable and secure HRC in construction, optimizing workflows and ensuring industry-wide advancements.

关键词： Human-robot collaboration Trust prediction machine learning algorithms Construction robots

来源：评论

学校读者我要写书评

暂无评论

Modelling of soft fiber-reinforced bending actuators through transfer learning from a machine learning algorithm trained from FEM data

引用

SENSORS AND ACTUATORS A-PHYSICAL 2024年 368卷

作者： Ye, Yongkai Scharff, Rob B. N. Long, Sifang Han, Chaoyue Du, Dongdong Zhejiang Univ Coll Biosyst Engn & Food Sci Hangzhou 310058 Zhejiang Peoples R China Hong Kong Univ Sci & Technol Div Integrat Syst & Design Hong Kong Peoples R China Key Lab Intelligent Equipment & Robot Agr Zhejiang Hangzhou 310058 Peoples R China

A soft fiber-reinforced bending actuator (SFRBA) is a multi-material system that plays a crucial role in robotics applications due to its high output force and robust bending motion. However, the multi-material composition of SFRBAs causes significant structural nonlinearity. This nonlinear behavior is difficult to capture using traditional analytical models. This study presents a method for modeling the SFRBA using finite element method (FEM) and nonlinear machine learning algorithms (MLAs). First, the key structural parameters of the SFRBA are defined and selected as input variables for the method. An accurate FEM, considering varying actuation pressure, is then employed to generate a simulation training dataset. Subsequently, three nonlinear MLAs, including polynomial regression (PLR), extreme gradient boosting regression (XGBoostR), and normalized multilayer perceptron regression (NMLPR), are developed to model the bending angle of the SFRBA. Moreover, transfer learning is deployed to improve the accuracy and convergence speed of the optimal NMLPR. Experimental measurements are conducted to validate the established MLAs, and the results demonstrate that the refined NMLPR outperforms the other models, yielding an average Root Mean Square Error (RMSE) of 7.935 (degrees) and Mean Absolute Percentage Error (MAPE) of 6.45%. Furthermore, the refined NMLPR is implemented in a feedback control loop to showcase its real-time ability to convert actuation pressure information into bending angles. The results exhibit excellent control performance, with an average MAPE of less than 6% and a low time delay of 0.0875 s. This work exemplifies a methodology that combines FEM and MLAs for modeling SFRBAs, paving the way for their further development and practical application.

关键词： Soft fiber -reinforced bending actuators Nonlinear modeling Finite element method machine learning algorithms Transfer learning

来源：评论

学校读者我要写书评

暂无评论

A Novel Dynamic Model for Ranking Cryptocurrencies in Different Time Horizons Based on Deep learning and Sentiment Analysis

引用

IEEE ACCESS 2024年 12卷 83022-83042页

作者： Mohagheghzadeh, Aida Amiri, Babak Makui, Ahmad Iran Univ Sci & Technol Sch Ind Engn Tehran *** Iran

This paper addresses the imperative task of assessing and ranking cryptocurrencies, particularly pertinent in the context of the burgeoning popularity of public blockchains. The proliferation of available options necessitates a rigorous evaluation, prompting the formulation of a novel model grounded in both objective and subjective criteria. To contend with the challenge posed by the expanding landscape of public blockchains, ten discerning criteria are delineated, encompassing facets such as Technology, TPS, Market capitalization, GitHub fork, GitHub stars, Twitter followers, Twitter hashtags, trading volume, sentiment score, and the price range differential. Leveraging expert opinions, the pairwise impact of these criteria is ascertained, and the DEMATEL method is judiciously employed to derive their respective weights. Subsequently, the PROMETHEE method is harnessed to effectuate the ranking of 20 cryptocurrencies predicated on the identified criteria. Furthermore, the integration of LSTM enables the prediction of values for four predictable criteria, seamlessly incorporated into the PROMETHEE model to furnish rankings across diverse temporal intervals. The proposed model, thus, presents a holistic and pragmatic approach to inform investment decision-making within the dynamic cryptocurrency market. By embracing a comprehensive set of criteria and integrating predictive analytics, this model stands as a valuable contribution to the field, offering nuanced insights to stakeholders navigating the complexities of cryptocurrency investment.

关键词： Cryptocurrency Bitcoin Predictive models Measurement machine learning Analytical models machine learning algorithms LSTM PROMETHEE ranking sentimental analysis

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：