检索结果-内蒙古大学图书馆

2023 IEEE Energy Conversion Congress and Exposition, ECCE 2023

作者： Aparo, Michele Giuffrida, Vittorio Chiantello, Massimiliano Rizzo, Santi Agatino Scelba, Giacomo Application Lab STMicroelectronics Power Transistors Sub Group Catania Italy University of Catania Department of Electrical Electronics and Computer Engineering Catania Italy

ISBN: (纸本)9798350316445

This paper presents a compact and cost-effective DC/AC converter solution to test the thermal imbalance of dice placed in parallel in a silicon carbide power module. The analysis is performed in continuous operating mode, by detecting the temperatures directly on each die with an infrared thermal camera. The system validation has been carried out by analysing two traction inverter modules. Each module has been assembled with dice selected according to their gate-source voltage threshold;the final goal being the extraction of a mathematical model, matching experimental data, to be able to predict the thermal imbalance. Input to the model is the Vth selection criteria when the inverter is used in the range of voltage and power typical of the electric vehicle applications. Furthermore, it has been necessary to increase the test time to analyse the dice behaviour when subjected to the current profile typical of the electric cars' lifecycle. The results highlight that the appropriate selection of the dice inside the module, based on the threshold voltage, improves thermal performance, reducing the imbalance. © 2023 IEEE.

关键词： Electric vehicles High power Silicon Carbide Traction invert

来源：评论

学校读者我要写书评

暂无评论

StoryLLaVA: Enhancing Visual Storytelling with Multi-Modal Large Language Models 31

StoryLLaVA: Enhancing Visual Storytelling with Multi-Modal L...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Yang, Li Xiao, Zhiding Huang, Wenxin Zhong, Xian Hubei Key Laboratory of Big Data Intelligent Analysis and Application School of Computer Science and Information Engineering Hubei University China Hubei Key Laboratory of Transportation Internet of Things School of Computer Science and Artificial Intelligence Wuhan University of Technology China

ISBN: (纸本)9798891761964

The rapid development of multi-modal large language models (MLLMs) has positioned visual storytelling as a crucial area in content creation. However, existing models often struggle to maintain temporal, spatial, and narrative coherence across image sequences and frequently lack the depth and engagement of human-authored stories. To address these challenges, we propose Story with Large Language and Vision Assistant (StoryLLaVA), a novel framework for enhancing visual storytelling. Our approach introduces a Topic-Driven Narrative Optimizer (TDNO) that improves both the training data and MLLM models by integrating image descriptions, topic generation, and GPT-4-based refinements. Furthermore, we employ a preference-based ranked story sampling method that aligns model outputs with human storytelling preferences through positive-negative pairing. These two phases of the framework differ in their training methods: the former uses supervised fine-tuning, while the latter incorporates reinforcement learning with positive and negative sample pairs. Experimental results demonstrate that StoryLLaVA outperforms current models in visual relevance, coherence, and fluency, with LLM-based evaluations confirming the generation of richer and more engaging narratives. The enhanced dataset and model are available at https://***/XxxZzD/StoryLLaVA. © 2025 Association for Computational Linguistics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

***: SAR Deforestation Classification of Amazon Forest for Land Use Land Cover application

引用

Journal of computer and Communications 2024年第3期12卷 68-83页

作者： Priyanka Darbari Ankush Agarwal Manoj Kumar Computer Engineering and Application GLA University Mathura India Department of Information Technology GGV Bilaspur India

The process of turning forest area into land is known as deforestation or forest degradation. Reforestation as a fraction of deforestation is extremely low. For improved qualitative and quantitative classification, we used Sentinel-1 dataset of State of Para, Brazil to precisely and closely monitor deforestation between June 2019 and June 2023. This research aimed to find out suitable model for classification called Satellite Imaging analysis by Transpose deep neural transformation network (SIT-net) using mathematical model based on Band math approach to classify deforestation applying transpose deep neural network. The main advantage of proposed model is easy to handle SAR images. The study concludes that SAR satellite gives high-resolution images to improve deforestation monitoring and proposed model takes less computational time compared to other techniques.

关键词： Brazilian Amazon Sentinel-1 Band Math Transpose CNN Transformation Network

来源：评论

学校读者我要写书评

暂无评论

Accelerating local SGD for non-IID data using variance reduction

引用

Frontiers of computer Science 2023年第2期17卷 73-89页

作者： Xianfeng LIANG Shuheng SHEN Enhong CHEN Jinchang LIU Qi LIU Yifei CHENG Zhen PAN Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of ChinaHefei 230027China Ant Financial Services Group Hangzhou 310000China Department of Computer Science and Engineering Hong Kong University of Science and TechnologyHong Kong 999077China

Distributed stochastic gradient descent and its variants have been widely adopted in the training of machine learning models,which apply multiple workers in *** them,local-based algorithms,including Local SGD and FedAvg,have gained much attention due to their superior properties,such as low communication cost and ***,when the data distribution on workers is non-identical,local-based algorithms would encounter a significant degradation in the convergence *** this paper,we propose Variance Reduced Local SGD(VRL-SGD)to deal with the heterogeneous *** extra communication cost,VRL-SGD can reduce the gradient variance among workers caused by the heterogeneous data,and thus it prevents local-based algorithms from slow convergence ***,we present VRL-SGD-W with an effectivewarm-up mechanism for the scenarios,where the data among workers are quite *** from eliminating the impact of such heterogeneous data,we theoretically prove that VRL-SGD achieves a linear iteration speedup with lower communication complexity even if workers access non-identical *** conduct experiments on three machine learning *** experimental results demonstrate that VRL-SGD performs impressively better than Local SGD for the heterogeneous data and VRL-SGD-W is much robust under high data variance among workers.

关键词： distributed optimization variance reduction local SGD federated learning non-IID data

来源：评论

学校读者我要写书评

暂无评论

Enhanced SMOTE Strategy for Handling Imbalanced Data in Machine Learning Classification

Enhanced SMOTE Strategy for Handling Imbalanced Data in Mach...

引用

2023 IEEE International Conference on Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication engineering, RMKMATE 2023

作者： Tiwari, Shivam Bhardwaj, Barkha Rathore, Yogesh Singh Vats, Satvik Vishwakarma, Pramod Department of Computer Science & Engineering Sharda University Greater Noida India Department of Computer Science and Engineering NIET Greater Noida India Computer Science and Application Sharda University Greater Noida India Computer Science & Engineering Graphic Era Hill University Dehradun India Chandigarh University Gharuan Punjab Mohali India

ISBN: (纸本)9798350305708

Most real-time datasets have class instances scattered across the data in a non-uniform fashion. Certain classes have an abnormally high number of instances when compared to the rest of the classes. The term "class imbalance problem" is used to describe this occurrence (CIP). Due to its inaccuracy in projecting weak class data samples, this skewed information impacts the reliability of forecasts as a whole. Many businesses make use of CIP's data mining experts who employ CIP. Both ML and deep learning have substantial difficulties with the classification of skewed data (DL). Several researchers are curious in how to overcome the major hurdle presented by the widespread adoption of sample techniques to improve classifier performance. In this research, we provide a survey of state-of-the-art approaches currently being used in studies of data classification, and we contrast and compare the numerous algorithms used at each stage of the process. Talk about the challenges and limitations that come up in investigations of imbalanced data classification. Taken as a whole, this work not only provides an in-depth analysis of the uneven data categorization industry but also inspires more study in this space. © 2023 IEEE.

关键词： balanced data classification deep learning each sampling method has a connection to the issue of class imbalance Machine learning

来源：评论

学校读者我要写书评

暂无评论

Surface flashover in 50 years:*** modification,structureoptimisation,and characteristics enhancement

引用

High Voltage 2025年第2期10卷 243-278页

作者： Zhen Li Ji Liu Yoshimichi Ohki George Chen Shengtao Li Key Laboratory of Engineering Dielectrics and Its Application Ministry of EducationHarbin University of Science and TechnologyHarbinHeilongjiangChina State Key Laboratory of Electrical Insulation and Power Equipment Xi'an Jiaotong UniversityXi'anShaanxiChina Research Institute for Materials Science and Technology Waseda UniversityShinjukuJapan School of Electronics and Computer Science University of SouthamptonSouthamptonUK

Surface flashover is a gas-solid interface insulation failure that significantly jeopardises the secure operation of advanced electronic,electrical,and spacecraft *** the widespread application of numerous material modification and structure optimisation technologies aimed at enhancing surface flashover performance,the influence mechanisms of the present technologies have yet to be systematically discussed and *** review aims to introduce various material modification technologies while demonstrating their influence mechanisms on flashover performances by establishing relationships among‘microscopic structure-mesoscopic charge transport-macroscopic insulation failure’.Moreover,it elucidates the effects of chemical structure on surface trap parameters and surface charge transport concerning flashover *** review categorises and presents structure optimisation technologies that govern electric field *** identified technologies highlight that achieving a uniform tangential electric field and reducing the normal electric field can effectively enhance flashover ***,this review proposes recommendations encompassing mathematical,chemical,evaluation,and manufacturing *** systematic summary of current technologies,their influence mechanisms,and associated advantages and disadvantages in improving surface insulation performance is anticipated to be a pivotal component in flashover and future dielectric theory.

关键词： material modification structure optimization surface flashover structure optimisation technologies chemical structure charge transport insulation failure

来源：评论

学校读者我要写书评

暂无评论

Grey Markov model based horizontal scaling strategy for Kubernetes

Grey Markov model based horizontal scaling strategy for Kube...

引用

IEEE Advanced Information Management,Communicates,Electronic and Automation Control Conference (IMCEC)

作者： Pengxiang Gao Han Wang Ziyang Meng Yakun Zhang Institute of Computer Application China Academy of Engineering Physics Mianyang China

ISBN: (数字)9798350316537

ISBN: (纸本)9798350316544

With the rapid development and wide application of cloud computing technology, Kubernetes has attracted much attention as the most mainstream container cluster management tool. Aiming at the shortcomings of the horizontal auto-scaling strategy of Kubernetes itself, this paper proposes a horizontal auto-scaling optimization strategy based on the grey Markov model, which can effectively achieve fast scaling up to meet the sudden task requests and slow scaling down to reduce the SLA violation rate. Finally, the effectiveness of the algorithm is verified through experiments.

关键词： computers Cloud computing Computational modeling Predictive models Containers Prediction algorithms Information management

来源：评论

学校读者我要写书评

暂无评论

DnnARs: An Artificial Intelligence Technique for Prediction of Antimicrobial Resistant Strains in E. coli Bacteria Causing Urine Tract Infection

引用

SN computer Science 2024年第8期5卷 1091页

作者： Nayak, Debasish Swapnesh Kumar Priyadarshini, Arpita Mahanta, Pabani Das, Tejaswini Sahoo, Santanu Kumar Swarnkar, Tripti Department of Computer Science and Engineering FET-ITER Siksha ‘O’ Anusandhan (Deemed to Be) University Bhubaneswar India Department of Computer Science and Engineering SOET Centurion University of Technology and Management Odisha Bhubaneswar India Department of Statistics Utkal University Bhubaneswar India Department of Electronics and Communication Engineering FET-ITER Siksha ‘O’ Anusandhan (Deemed to Be) University Bhubaneswar India Department of Computer Application National Institute of Technology Raipur India

The rise of antimicrobial resistance (AMR) in bacteria that cause infectious diseases poses a significant global health challenge, necessitating advanced prediction technology for effective management and response. This study aims to evaluate the predictive capabilities of several machine learning (ML) and deep learning (DL) models in identifying patterns of antibiotic resistance. We have proposed a comprehensive experimental framework that combines multiple machine learning algorithms and deep learning architectures to evaluate their efficacy and accuracy in predicting antibiotic resistance. We have developed DnnARs, an artificial intelligence pipeline designed to identify antibiotic-resistant strains of E. coli bacteria, which are mostly responsible for urinary tract infections (UTIs). DnnARs utilizes Synthetic Minority Over-sampling Technique (SMOTE) and applies feature engineering using principal component analysis (PCA) and t-distributed Stochastic neighbor embedding (t-SNE) on our dataset to evaluate the effectiveness of various AI models. Our model comparison demonstrates that DL models outperform ML models when the dataset is fine-tuned using SMOTE and feature engineering. Our DnnARs achieve a classification accuracy of 97%, a specificity of 91%, and a remarkable sensitivity of 100%. The DL models that were examined exhibit an average classification accuracy that is 3.66% higher than that of the ML models. The findings demonstrate the capability of deep learning methodology to enhance predictive analytics for antimicrobial resistance, offering a robust and efficient alternative to traditional machine learning techniques. This research aims to enhance diagnostic tools and medications, improve the management of infectious diseases, reduce antibiotic resistance, and integrate deep learning models into clinical workflows to enable immediate decision-making. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Antimicrobial resistance Artificial intelligence Deep learning Infectious disease Machine learning Urine tract infections

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Model for Classification of COVID-19 Related Fake News 2nd

A Deep Learning Model for Classification of COVID-19 Related...

引用

2nd International Conference on Electronic Systems and Intelligent Computing, ESIC 2021

作者： Dutta, Rakesh Das Adhikary, Dibya Ranjan Majumder, Mukta Department of Computer Science & Application Hijli College Kharagpur India Department of Computer Science & Engineering Siksha ‘O’ Anusandhan Deemed to be University Bhubaneswar India Department of Computer Science & Application University of North Bengal Siliguri India

ISBN: (纸本)9789811694875

The health crisis caused by COVID-19 throws the whole world into the biggest emergency of the century. Moreover, the pandemic has become awful because of the spread of inadequate and fake news or information among common people. Fake news, gossip and misleading information are on the rise due to the popularity of web-based information sources among people, such as social media, news feeds, online blogs and e-news articles. Monitoring and identifying such fake stories is a prerequisite to cease unwanted panic in this pandemic. But carrying out this task manually is challenging and labour intensive. computer-assisted pattern recognition can now be used to replace human contact thanks to developments in machine learning, deep learning models and natural language processing. This is also essential for accurately distinguishing between true and false information automatically. A hybrid deep learning classification model has been proposed here to identify and classify the fake news and misleading information on the ‘COVID-19 Fake News Dataset’ (taken from Mendeley) which is a collection of news or web article related to COVID-19. The proposed classification model has achieved an accuracy of 75.34% and outperforms the existing LSTM and BiLSTM techniques. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

A SSCPS safety assessment method based on mission risk

A SSCPS safety assessment method based on mission risk

引用

IEEE International Conference on Software Quality, Reliability and Security Companion (QRS-C)

作者： Yafeng Shen Lianzhi Qi Shiyong Li Siyou Ma Fei Deng Institute of Computer Application China Academy of Engineering Physics Mianyang China

ISBN: (数字)9798350365658

ISBN: (纸本)9798350365665

Cyber physical system (CPS) is a complex system that deeply integrates computing, network communication and control equipment. It has broad application prospects in aerospace, industrial production, transportation and other fields, and it also faces very severe security challenges. Especially for some safety-critical CPS (SSCPS), security issues will have serious consequences. How to carry out security assessment for safety-critical CPS systems has always been a hot issue in CPS research. This paper proposes a task risk-based SSCPS security assessment method. By decomposing the key tasks of the SSCPS system, identifying system risk elements based on task characteristics, and establishing the impact relationship between tasks and risk factors such as assets, vulnerabilities, and threats, construct a security assessment index system based on mission risk, and propose a security fusion method to achieve multilevel and multidimensional security assessment of SSCPS.

关键词： Transportation Software quality Time measurement Software reliability Safety Security Indexes Data mining Software measurement Standards

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：