检索结果-内蒙古大学图书馆

Canadian Conference on Electrical and computer engineering (CCECE)

作者： Jiehan Zhou Yang Zhao Jiahong Liu Peijun Dong Xiaoyu Luo Hang Tao Shi Chang Hanjiang Luo Shandong University of Science and Technology Qingdao China Faculty of Information Technology and Electrical Engineering University of Oulu Oulu Finland Kyung Hee University Seoul South Korea Department of Computer Science University of Western Ontario London Canada

ISBN: (数字)9798350371628

ISBN: (纸本)9798350371635

Integrating large language models (LLMs) into reinforcement learning (RL) promises to enhance the learning performance. Traditional RL faces challenges in industrial settings, including complex environments, safety concerns, and multimodal data. As powerful tools for contextual learning and reasoning, LLMs can address issues inherent in traditional RL. This paper introduces a generic LLM4RL framework, and investigates how LLM4RL can improve learning performance in autonomous driving.

关键词： Analytical models Large language models Computational modeling Reinforcement learning Cognition Safety Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Improving Lithium-Ion Battery Life Prediction using CEEMDAN Decomposition and Machine Learning

Improving Lithium-Ion Battery Life Prediction using CEEMDAN ...

引用

computer engineering and Intelligent Communications (ISCEIC), International Symposium on

作者： Xinxin Li Kun Xie Ziliang An Yiwen Zuo School of Rail Transportation Shanghai Institute of Technology Shanghai Faculty of Urban Operations and Management Shanghai Urban Construction Vocational College Shanghai School of computer and Information Engineering Shanghai Polytechnic University Shanghai

ISBN: (数字)9798331518677

ISBN: (纸本)9798331518684

The remaining useful life (RUL) of lithium-ion batteries is a key indicator for the optimal design of battery management systems and ensuring equipment safety. Most existing RUL prediction methods retain only the trend term of the capacity curve, neglecting the potential information in high-frequency fluctuations. Therefore, this paper presents a combined model based on adaptive white noise complete integrated empirical mode decomposition (CEEMDAN), gradient boosted decision tree (GBDT), and long-short-term memory neural network (LSTM). CEEMDAN is employed to reduce noise and extract fluctuation components at different frequencies. GBDT assigns weights to each component to assess its contribution to the interpretation of the original data. The final prediction is obtained by weighted reconstruction of the LSTM prediction results for each component. The experimental results show that using the NASA lithium battery dataset, the CEEMDAN-GBDT-LSTM model significantly improves RUL prediction accuracy and outperforms single models in predictive performance.

关键词： Lithium-ion batteries Fluctuations Accuracy Neural networks NASA Time series analysis Predictive models White noise Lithium batteries Long short term memory

来源：评论

学校读者我要写书评

暂无评论

JAX-CNV:A Whole-genome Sequencing-based Algorithm for Copy Number Detection at Clinical Grade Level

引用

Genomics, Proteomics & Bioinformatics 2022年第6期20卷 1197-1206页

作者： Wan-Ping Lee Qihui Zhu Xiaofei Yang Silvia Liu Eliza Cerveira Mallory Ryan Adam Mil-Homens Lauren Bellfy Kai Ye Charles Lee Chengsheng Zhang Precision Medicine Center The First Affiliated Hospital of Xi’an Jiaotong UniversityXi’an 710061China The Jackson Laboratory for Genomic Medicine FarmingtonCT 06032USA School of Cyber Science and Engineering Xi’an Jiaotong UniversityXi’an 710049China Department of Pathology and Laboratory Medicine Perelman School of MedicineUniversity of PennsylvaniaPhiladelphiaPA 19104USA School of Computer Science and Technology Faculty of Electronic and Information EngineeringXi’an Jiaotong UniversityXi’an 710049China MOE Key Lab for Intelligent Networks&Networks Security Faculty of Electronic and Information EngineeringXi’an Jiaotong UniversityXi’an 710049China Department of Life Sciences Ewha Womans UniversitySeoul 03760South Korea

We aimed to develop a whole-genome sequencing(WGS)-based copy number variant(CNV)calling algorithm with the potential of replacing chromosomal microarray assay(CMA)for clinical ***-CNV is thus developed for CNV detection from WGS *** performance of this CNV calling algorithm was evaluated in a blinded manner on 31 samples and compared to the 112 CNVs reported by clinically validated CMAs for these 31 *** result showed that JAX-CNV recalled 100%of these ***,JAX-CNV identified an average of 30 CNVs per individual,representing an approximately seven-fold increase compared to calls of clinically validated *** validation of 24 randomly selected CNVs showed one false positive,i.e.,a false discovery rate(FDR)of 4.17%.A robustness test on lowercoverage data revealed a 100%sensitivity for CNVs larger than 300 kb(the current threshold for College of American Pathologists)down to 10×*** CNVs larger than 50 kb,sensitivities were 100%for coverages deeper than 20×,97%for 15×,and 95%for 10×.We developed a WGS-based CNV pipeline,including this newly developed CNV caller JAX-CNV,and found it capable of detecting CMA-reported CNVs at a sensitivity of 100%with about a FDR of 4%.We propose that JAX-CNV could be further examined in a multi-institutional study to justify the transition of first-tier genetic testing from CMAs to ***-CNV is available at https://***/TheJacksonLaboratory/JAX-CNV.

关键词： Copy number variant Chromosomal microarray assay Whole-genome sequencing JAX-CNV Genetic testing

来源：评论

学校读者我要写书评

暂无评论

A Conceptual Framework for Multidisciplinary Data Science Education Based on IoT Projects

A Conceptual Framework for Multidisciplinary Data Science Ed...

引用

Artificial Intelligence and Education (WAIE), International Workshop on

作者： Daniel Moritz Marutschke Atanas Kirjakovski Fitra A. Bachtiar Valentinus Roby Hananto Mate Kovacs Patricia Brockmann Victor V. Kryssanov Faculty of Economics and Business Administration Kyoto University of Advanced Science Kyoto Japan Department of Psychology International Balkan University Skopje North Macedonia Faculty of Computer Science Universitas Brawijaya Malang Indonesia College of Information Science and Engineering Ritsumeikan University Osaka Japan Faculty of Computer Science Nuremberg Institute of Technology Nuremberg Germany

ISBN: (数字)9798350378894

ISBN: (纸本)9798350378900

The necessity for professionals to make predictions using digital data has been recognized for many decades. With its roots in statistical analysis and later implemented as data analytics, Data Science emerged as a widely accepted discipline. The data science life cycle begins by setting a goal and ends with reporting/reflecting on the gained results. It incorporates known analytical techniques, including modern artificial intelligence and machine learning techniques. While often considered an independent discipline, both engineering and liberal arts colleges have recognized the need for an understanding of data science in the general workforce. The literature still suggests a disconnect between the study fields and how the Internet of Things could be leveraged in Project-Based Learning (PBL) style data science education. In this paper, the authors propose a conceptual framework to teach multidisciplinary data science at university level to engineering and liberal arts students using data from real-world Internet of Things (IoT) projects.

关键词： Smart agriculture Art Statistical analysis Smart cities Education Software algorithms Refining Data science Internet of Things Software engineering

来源：评论

学校读者我要写书评

暂无评论

Ethics of AI: A Systematic Literature Review of Principles and Challenges 22

Ethics of AI: A Systematic Literature Review of Principles a...

引用

26th ACM International Conference on Evaluation and Assessment in Software engineering, EASE 2022

作者： Khan, Arif Ali Badshah, Sher Liang, Peng Waseem, Muhammad Khan, Bilal Ahmad, Aakash Fahmideh, Mahdi Niazi, Mahmood Akbar, Muhammad Azeem M3S Empirical Software Engineering Research Unit University of Oulu Finland Faculty of Computer Science Dalhousie University Canada School of Computer Science Wuhan University China Department of Computer Science University of Loralai Pakistan College of Computer Science and Engineering University of Hail Saudi Arabia School of Business University of Southern Queensland Australia Department of Information and Computer Science King Fahd University of Petroleum and Minerals Finland Software Engineering Department Lappeenranta-Lahti University of Technology Finland

ISBN: (纸本)9781450396134

Ethics in AI becomes a global topic of interest for both policymakers and academic researchers. In the last few years, various research organizations, lawyers, think tankers, and regulatory bodies get involved in developing AI ethics guidelines and principles. However, there is still debate about the implications of these principles. We conducted a systematic literature review (SLR) study to investigate the agreement on the significance of AI principles and identify the challenging factors that could negatively impact the adoption of AI ethics principles. The results reveal that the global convergence set consists of 22 ethical principles and 15 challenges. Transparency, privacy, accountability and fairness are identified as the most common AI ethics principles. Similarly, lack of ethical knowledge and vague principles are reported as the significant challenges for considering ethics in AI. The findings of this study are the preliminary inputs for proposing a maturity model that assesses the ethical capabilities of AI systems and provides best practices for further improvements. © 2022 ACM.

关键词： Challenges AI Ethics Machine Ethics Systematic Literature Review Principles

来源：评论

学校读者我要写书评

暂无评论

Psychological Assessment Data Analysis Based on Particle Swarm Algorithm

Psychological Assessment Data Analysis Based on Particle Swa...

引用

2023 IEEE International Conference on Paradigm Shift in information Technologies with Innovative Applications in Global Scenario, ICPSITIAGS 2023

作者： Chen, Yuxi Wang, Houbin Zhang, Zanglong Ren, Yunying Deng, Zetao Tu, Jinxia Sino-German College of Intelligent Manufacturing Shenzhen Technology University Guangdong Shenzhen China School of Resources and Environmental Engineering Ludong University Shandong Yantai China Shandong University of Traditional Chinese Medicine Faculty of Intelligence and Information Engineering Shandong Jinan China School of Computer Engineering Chongqing College of Humanities Science & Technology Chongqing China Modern Industry School of Virtual Reality of Jufe Jiangxi University of Finance and Economics Jiangxi Nanchang China School of Business Chongqing College of Humanities Science & Technology Chongqing China

ISBN: (纸本)9798350329773

Research has found a close connection between a mother's mental health and an infant's physiological, cognitive, emotional, and social development. This paper delves into the impact of maternal physical and psychological health on infant growth using various academic research methods, providing theoretical guidance for promoting infant development. Firstly, a canonical correlation analysis is employed to explore the specific relationship between maternal physical and psychological indicators and infant behavioral characteristics and sleep quality. The conclusion is that maternal psychological indicators largely account for variations in infant sleep quality and behavioral characteristics. Secondly, a multivariate linear regression model, combining stepwise regression and ridge regression, is used to analyze the relationship between maternal and infant indicators and make predictions. The result indicates that the 391st infant is of the contradictory type, among others. Subsequently, an objective planning model incorporating particle swarm optimization algorithm reveals that the behavioral characteristics of the 238th infant can shift from contradictory to moderate type, requiring a treatment cost of $9577.01. Finally, based on principal component analysis, the 391st infant's sleep quality is assessed as moderate. © 2023 IEEE.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Label-free Identification of Nonelectrogenic Cancer Cells using Adhesion Noise

Label-free Identification of Nonelectrogenic Cancer Cells us...

引用

BioSensors Conference (BioSensors), IEEE

作者： Maximilian Ell Ralf Zeitler Roland Thewes Günther Zeck TU Wien Faculty of Electrical Engineering and Information Technology Institute of Biomedical Electronics Vienna Austria zerodev Stuttgart Germany TU Berlin Faculty of Electrical Engineering and Computer Science Chair of Sensor and Actuator Systems Berlin Germany

Time-continuous detection of cells on substrates without the need of optical microscopic imaging is of broad interest in biotechnological applications. We present a method how to detect cancer cells using voltage noise caused by cell adhesion which is recorded by high-density CMOS-based microelectrode arrays. We analyze our data in terms of spectral power density for two different types of arrays, each of them being optimized in a different working regime.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Blockchain-based Security Framework for Metaverse: A Decentralized Approach 15

Blockchain-based Security Framework for Metaverse: A Decentr...

引用

15th International Conference on Electronics, computers and Artificial Intelligence, ECAI 2023

作者： Rajawat, Anand Singh Goyal, S.B. Solanki, RamKumar Raboaca, Maria Simona Mihaltan, Traian Candin Illes, Zoltan Verma, Chaman School of Computer Science & Engineering Sandip University Nashik India City University Faculty of Information Technology Petaling Jaya Malaysia Research and Development Institute for Cryogenics and Isotopic Technologies Ramnicu Icsi Energy Department National Valcea Romania Technical University of Cluj-Napoca Faculty of Building Services Cluj-Napoca40033 Romania Eötvös Loránd University Faculty of Informatics Department of Media and Educational Informatics Budapest Hungary

ISBN: (纸本)9798350321388

People can act out fake social exchanges in the Metaverse, which is an online community. Security has become a problem in the Metaverse because there are so many online transactions and digital assets. In this thesis, a Blockchain-based security system for the Metaverse is proposed. This would be a decentralised way to keep the virtual world safe. Our system uses Blockchain's autonomous structure to make sure that all financial transactions in the Metaverse are safe, anonymous, and true. We suggest a new consensus process that combines Proof of Stake (PoS) and Proof of Authority (PoA) to make networks safer and allow them to grow. We also have a user-focused, decentralised identity management system that keeps their information safe. We also suggest a way to process Metaverse transactions safely that is based on smart contracts. Our method makes sure that transactional proof, recording, and validation are done in a safe and reliable way. We also show a reputation system that benefits people who follow the law and punishes people who break the law. Lastly, we test how well our suggested structure works with simulations and real-world tests. The results show that our way works to reduce possible security risks in the Metaverse and create a safe, scalable environment for online business. Overall, our Blockchain-based Security Framework for Metaverse: A Decentralised Approach is a good way to keep the security and privacy of digital activities in Metaverse. © 2023 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

A Method for Evaluating Expressive Power and Semantic Capacity of Metamodel in Conceptual Data Modeling 17th

A Method for Evaluating Expressive Power and Semantic Capa...

引用

17th Asian Conference on Intelligent information and Database Systems, ACIIDS 2025

作者： Jodlowiec, Marcin Krótkiewicz, Marek Faculty of Information and Communication Technology Wroclaw University of Science and Technology Wroclaw Poland School of Computer Science and Engineering International University Ho Chi Minh City Viet Nam Vietnam National University Ho Chi Minh City Viet Nam

ISBN: (纸本)9789819660070

The paper introduces a method for quantitatively analyzing the expressive power and semantic capacity of metamodels in the context of conceptual data modeling. The method leverages a formal semantic representation of metamodels, based on the Conceptual Layer of Metamodels (CLoM) and expressed using an ontological system of concepts. By extracting semantic constructs, such as concepts, semantic atoms, and semantic particles, the approach allows for a structured evaluation of metamodels’ abilities to express semantic complexity. The proposed method is applied to selected conceptual metamodels, including AOM, EER, ORM, and a reference graph metamodel, providing insights into their semantic capabilities. Results demonstrate alignment with expert intuition and reveal differences in semantic richness and complexity. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： conceptual modeling expressive power metamodel semantics semantic capacity semantics of metamodels

来源：评论

学校读者我要写书评

暂无评论

Novel Deep Learning Network Architectures for Time Series Forecasting

Novel Deep Learning Network Architectures for Time Series Fo...

引用

Paradigm Shift in information Technologies with Innovative Applications in Global Scenario (ICPSITIAGS), IEEE International Conference on

作者： Jitendra Kumar Katariya Dhananjay Yadav Gayathri C Vikas K. Kolekar Umesh M. Daivagna V. Pushparajesh Department of Computer Science & Application Vivekananda Global University Jaipur India Maharishi School of Engineering and Technology Maharishi University of Information Technology UP India Department of Science and Humanities Prince Shri Venkateshwara Padmavathy Engineering College Chennai Department of Computer Engineering Vishwakarma Institute of Information Technology Pune INDIA Department of uGDX ATLAS SkillTech University Mumbai Maharastra India Department of Electrical and Electronics Engineering Faculty of Engineering and Technology Bangalore Karnataka

ISBN: (数字)9798350329773

ISBN: (纸本)9798350329780

This paper presents novel deep-learning network architectures for time series forecasting. First, a singular deep gaining knowledge of network architecture is proposed and tested for the usage of the Google tendencies dataset as a benchmark. The proposed structure combines 1-dimensional convolution neural networks, recurrent neural networks, and long-term cells to seize and study lengthy-term styles in the time series information. The structure is compared to current deep getting-to-know architectures and is shown to outperform them in phrases of accuracy. Moreover, the proposed structure is applied to a secondary time collection dataset, the COVID-19 confirmed infection dataset, to attain compelling effects. Eventually, an open-source implementation of the proposed architecture is made available for use in addition to research.

关键词： Knowledge engineering Deep learning Recurrent neural networks Time series analysis Network architecture Internet Forecasting

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：