检索结果-内蒙古大学图书馆

11th International Conference on Soft Computing and Machine Intelligence, ISCMI 2024

作者： Afifi, Shereen Moataz Kaur, Ranpreet Gholamhosseini, Hamid Azzam, Omar Taha, Radwa German University in Cairo Cairo Egypt Software Engineering & AI Media Design School Auckland New Zealand Auckland University of Technology School of Engineering Auckland New Zealand

ISBN: (纸本)9798331518127

This research work presents the development and implementation of a skin scan app utilizing deep learning technologies. The aim is to provide users with a convenient and accessible tool for skin analysis to reduce the reliance on traditional dermatological solutions. After extensive exploration of different deep learning techniques, an efficient and accurate model, EffecientNetB0V2 was identified as the most suitable model and trained using the HAM10000 skin cancer dataset. The developed models were then integrated into a user-friendly flutter application called 'SkinKo' that is fully developed from scratch, and designed to offer an intuitive and seamless experience for users. This research not only showcases the technical aspects of developing such an application but also focuses on the potential impact on the healthcare community. By offering an 'in-pocket dermatologist' This application has the potential to empower users to monitor their skin health more effectively and seek timely medical attention when necessary. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Reduced Order Modeling of an Entry Capsule from Simulated Ballistic Range Trajectories

Reduced Order Modeling of an Entry Capsule from Simulated Ba...

引用

AIAA Science and technology Forum and Exposition, AIAA SciTech Forum 2025

作者： Dean, Hayden V. Perron, Christian Robertson, Bradford E. Mavris, Dimitri N. School of Aerospace Engineering Aerospace Systems Design Laboratory Georgia Institute of Technology AtlantaGA30332 United States Aerospace Systems Design Laboratory Georgia Institute of Technology AtlantaGA30332 United States

ISBN: (数字)9781624107238

ISBN: (纸本)9781624107238

Entry, Descent, and Landing (EDL) relies on blunt-body entry vehicles, or entry capsules, to survive atmospheric entry to enable successful planetary missions. In the supersonic through the transonic flight regime, these entry capsules can display dynamic instabilities. While research is ongoing to leverage non-linear functional fits to determine dynamic stability coefficients, these research efforts omit the rich data produced from Computational Fluid Dynamics (CFD) simulations, that might aid researchers in understanding and quantifying dynamic stability characteristics of these capsules. The objective of this paper is to build upon previous work that developed an aerodynamic ROM to predict forced rotational oscillation trajectories, addressing key limitations. A Reduced Order Model (ROM) is a form of field-based surrogate model capable of efficiently leveraging high-fidelity aerodynamic data to mimic the results of CFD simulations. The previous limitations included a lack of exploration of skin friction ROMs, utilization of a coarse grid, scalability issues when using a Kriging regression, and leveraging data from an unrealistic motion caused by forced oscillation simulations. These limitations were addressed, and results showed success at predicting the mean aerodynamic trends of a free-flight validation trajectory for Cp and Cf data for both the heatshield and back shell regions using a ROM methodology. © 2025, American Institute of Aeronautics and Astronautics Inc, AIAA. All rights reserved.

关键词： Skin friction

来源：评论

学校读者我要写书评

暂无评论

Uncertain Reduced Order Model Predictions of an Unsteady Field

Uncertain Reduced Order Model Predictions of an Unsteady Fie...

引用

AIAA Science and technology Forum and Exposition, AIAA SciTech Forum 2025

作者： Willier, Brenton J. Perron, Christian Robertson, Bradford E. Mavris, Dimitri N. Aerospace Systems Design Laboratory Georgia Institute of Technology School of Aerospace Engineering AtlantaGA30332 United States Aerospace Systems Design Laboratory Georgia Institute of Technology AtlantaGA30332 United States

ISBN: (数字)9781624107238

ISBN: (纸本)9781624107238

The design of blunt-body entry vehicles balances atmospheric heating and drag to ensure payload safety during entry, descent, and landing. Their blunt shape creates turbulent, recirculating wakes, leading to uncertain flight paths and challenging mitigation strategies. Traditionally, uncertainties are managed using conservative scalars and multipliers, resulting in over-engineered designs with reduced payload capacity and less accurate landings. While advances in computational fluid dynamics (CFD) enable high-fidelity analysis, the cost of extensive simulations remains prohibitive. Surrogate models, such as reduced-order models (ROMs), offer a faster alternative but must address the uncertainty introduced by unsteady aerodynamic training data. This paper presents a methodology to capture, encode, and propagate uncertainty in unsteady high-dimensional fields using parametric ROMs. The approach employs a Lorenz modeltoemulate unsteady fields and applies replication sampling to capture full-order model (FOM) nonparametric uncertainty. Proper orthogonal decomposition (POD) reduces dimensionality, and sparse Kriging regression predicts latent space mean and variance. A linear covariance back-mapping technique is applied to propagate uncertainty from the latent coordinates to integrated scalar coefficients. Results demonstrate the ROM accurately predicts scalar uncertainties consistent with FOM validation, supporting future application to more complex problems, such as entry vehicles in unsteady free-flight simulations. © 2025, American Institute of Aeronautics and Astronautics Inc, AIAA. All rights reserved.

关键词： Flight paths

来源：评论

学校读者我要写书评

暂无评论

A Generalized Perturbation Matrix-Based Fractional-Order Optimization Method of GM(r,2) for Inferring Driving Intention

引用

IEEE Transactions on Transportation Electrification 2025年第3期11卷 8561-8572页

作者： Lian, Yufeng Xu, Jianqiang Luo, Jun Nie, Zhigen Liu, Shuaishi Sun, Zhongbo Changchun University of Technology School of Electrical and Electronic Engineering Changchun130012 China Chongqing SERES New Energy Vehicle Design Institute Company Ltd. Vehicle Test Center Chongqing401135 China Kunming University of Science and Technology Faculty of Transportation Engineering Yunnan Kunming650500 China

A fractional-order optimization method based on generalized perturbation matrix of GM(r,2) is proposed in this article. The smaller the perturbation bound, the more stable the model. By minimizing perturbation bound, a generalized perturbation matrix is given, which is the solving equation of the optimized fractional order. With different coefficients δ, different fractional orders can be calculated by a linear equation in one variable. Maximum relative error (RE) eM and mean absolute percentage error (MAPE) with different fractional orders can be obtained. Based on the smallest eM and the MAPE, the optimized fractional order of GM(r,2) can be determined. Compared with particle swarm optimization (PSO) and long short-term memory (LSTM) network transfer learning optimization methods, the MAPE of the proposed method is much smaller than that of PSO and slightly greater than LSTM network transfer learning optimization. The proposed method is superior to others without iteration calculation, and the convergence problem of PSO and the computational burden problem of transfer learning based on LSTM network optimization can be further improved. A GM(r,2) with optimized fractional order ropt is evaluated in inferring driving intention of an active collision avoidance system for electric vehicles. Car-following simulations are performed to demonstrate the effectiveness of the proposed fractional-order optimization method with simple structure and flexible implementation. © 2015 IEEE.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

design of companion aging and early warning service system based on speech emotion recognition

Design of companion aging and early warning service system b...

引用

2024 International Conference on Computer Application and Information Security, ICCAIS 2024

作者： Xu, Yue Gao, Sheng Zhang, Jiande School of Art and Design Nanjing Institute of Technology Jiangsu Nanjing211167 China School of Computer Engineering Nanjing Institute of Technology Jiangsu Nanjing211167 China

ISBN: (纸本)9781510689312

This study proposes a speech emotion recognition-based system to meet the growing demand for intelligent elderly care in China. The system creates an architecture for emotion recognition, companionship, and risk alerts by integrating deep learning and intelligent dialog. The research results show that it can demonstrate good performance in key indicators such as emotion recognition accuracy, interaction naturalness, and warning timeliness, and provide feasible technical solutions to improve the quality of life of the elderly. © The Authors.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Speech Method for Caregiving Robots Considering Uncertainty 16th

Speech Method for Caregiving Robots Considering Uncertainty

引用

16th International Conference on Social Robotics, ICSR + AI 2024

作者： Shindo, Arisa Kawasaki, Yosuke Takahashi, Masaki School of Science for Open and Environmental Systems Graduate School of Science and Technology Keio University Kanagawa Japan Department of System Design Engineering Faculty of Science and Technology Keio University Kanagawa Japan

ISBN: (纸本)9789819635214

Recent studies have explored the integration of large language models (LLMs) into caregiving robots. The use of LLMs facilitates the generation of human-like natural dialogues and diverse, varied expressions. However, in case of a lack of direct and specific instructions from a user, gaining an accurate understanding of the user's intent is challenging, which may result in miscommunication. Thus, this study proposed a method to achieve robust communication even in the absence of direct instructions by considering the uncertainty in destination prediction probabilities. The proposed system leveraged GPT-4 to generate various Japanese speech content candidates and employed neighborhood components analysis to facilitate dimensionality reduction. Consequently, notable features of the rich linguistic embeddings were preserved while transforming them into manageable data. The system selected appropriate utterances based on the destination prediction probabilities. Furthermore, this study investigated changes in the speech content according to the variations in these probabilities, and the incorporation of uncertainty in communication was validated. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Dimensionality reduction

来源：评论

学校读者我要写书评

暂无评论

EXPERIMENTAL STUDIES ON LOAD-SETTLEMENT RELATION OF INTERMEDIATE BELL AND EFFECT OF BELL SPACING ON BEARING CAPACITY IN MULTI-BELLED CAST-IN-PLACE PILE

Journal of Structural and Construction Engineering

引用

Journal of Structural and Construction engineering 2024年第816期89卷 157-167页

作者： Hama, Kentaro Abe, Ton Wat An Horii, Yoshihiro Nagao, Toshiaki Muramatsu, Akitsugu Nakanishi, Yoshitaka Mukai, Yoichi Taisei Advanced Center of Technology Taisei Corporation Japan Design Division Taisei Corporation Japan Building Construction Division Taisei Corporation Japan Graduate School of Engineering Kobe University Japan

Aiming for accurate evaluation of bearing capacity and settlement behavior of multi-belled cast-in-place piles in sand, the characteristics of load-settlement relations and the effect of bell spacing on bearing capacity were investigated by experimental techniques. The findings are summarized as follows^ l) The average curves of the load-settlement relations of intermediate bells based on six full-scale load tests showed larger initial stiffness and curvature than the recommended curve for a pile tip by AIJ. 2) The results of centrifuge modelling tests indicated that smaller bell spacing brought lower resistance of an intermediate bell and the change of ground failure mechanism. © 2024 Architectural Institute of Japan. All rights reserved.

关键词： Bells

来源：评论

学校读者我要写书评

暂无评论

Hierarchy-Aware and Channel-Adaptive Semantic Communication for Bandwidth-Limited Data Fusion

引用

IEEE Wireless Communications Letters 2025年第6期14卷 1748-1752页

作者： Guo, Lei Chen, Wei Sun, Yuxuan Ai, Bo Pappas, Nikolaos Quek, Tony Beijing Jiaotong University State Key Laboratory of Advanced Rail Autonomous Operation China Beijing Jiaotong University School of Electronic and Information Engineering Beijing China Linköping University Department of Computer and Information Science Linköping Sweden Singapore University of Technology and Design Information Systems Technology and Design Singapore

Obtaining high-resolution hyperspectral images (HR-HSI) is costly and data-intensive, making it necessary to fuse low-resolution hyperspectral images (LR-HSI) with high-resolution RGB images (HR-RGB) for practical applications. However, traditional fusion techniques, which integrate detailed information into the reconstruction, significantly increase bandwidth consumption compared to directly transmitting raw data. To overcome these challenges, we propose a hierarchy-aware and channel-adaptive semantic communication approach for bandwidth-limited data fusion. A hierarchical correlation module is proposed to preserve both the overall structural information and the details of the image required for super-resolution. This module efficiently combines deep semantic and shallow features from LR-HSI and HR-RGB. To further reduce bandwidth usage while preserving reconstruction quality, a channel-adaptive attention mechanism based on Transformer is proposed to dynamically integrate and transmit the deep and shallow features, enabling efficient data transmission and high-quality HR-HSI reconstruction. Experimental results on the CAVE and Washington DC Mall datasets demonstrate that our method outperforms single-source transmission, achieving up to a 2 dB improvement in peak signal-to-noise ratio (PSNR). Additionally, it reduces bandwidth consumption by two-thirds, confirming its effectiveness in bandwidth-constrained environments for HR-HSI reconstruction tasks. © 2012 IEEE.

关键词： Bandwidth

来源：评论

学校读者我要写书评

暂无评论

A novel approach to simulate ortho-para conversion in hydrogen liquefaction based on the van't Hoff equation

引用

International Journal of Hydrogen Energy 2025年 140卷 870-880页

作者： Kanz, Benjamin Tafone, Alessio Stops, Laura Massier, Tobias Klein, Harald Technical University of Munich TUM School of Engineering and Design Department of Energy and Process Engineering Institute of Plant and Process Technology Boltzmannstr. 15 Bavaria Garching85748 Germany TUMCREATE Ltd. 1 Create Way Singapore138602 Singapore

Liquid hydrogen (LH2) is a promising solution to transport green hydrogen to countries lacking domestic energy resources. One challenge in simulating the liquefaction process is the exothermic ortho-para conversion (OPC). Orthohydrogen is converted to parahydrogen during the process to prevent the liquid hydrogen from evaporating due to the exothermic conversion in the LH2 tank. This paper introduces a new method to simulate the OPC based on the van't Hoff equation and provides an analytical expression for the molar heat of conversion. This van't Hoff approach is assessed by comparing its results to literature data and an existing equilibrium reactor approach. Both approaches are validated against an existing industrial plant. Both methods show good agreement with the literature data with relative errors of 0.5 % and 0.4 %, respectively. After successfully validating both approaches, these methods enable dynamic simulations of hydrogen liquefaction as they can simulate the OPC across the entire temperature range. © 2025 The Authors

关键词： Hydrogen liquefaction Ortho-para conversion Simulation methodology Equation of state REFPROP Modified Benedict-Webb-Rubin (MBWR)

来源：评论

学校读者我要写书评

暂无评论

Detection of viral messages in twitter using context-based sentiment analysis framework

引用

International Journal of Information technology (Singapore) 2024年第8期16卷 5069-5075页

作者： Marriwala, Nikhil Kumar Shukla, Vinod Kumar William, P. Guleria, Kalpna Sobti, Rajni Sharma, Shagun Electronics and Communication Engineering Department University Institute of Engineering and Technology Kurukshetra University Information Technology Head of Academics School of Engineering Architecture Interior Design Amity University Dubai Dubai International Academic City Department of Information Technology Sanjivani College of Engineering SPPU Chitkara University Institute of Engineering and Technology Chitkara University University Institute of Engineering and Technology Panjab University

The prevalence of social media sites like Twitter has made it simpler for individuals and organizations to disseminate incorrect facts or misinformation that can sway public opinion and behavior. It is crucial to create a trustworthy system that can recognize the sentiment of tweets in their context, analyze that sentiment, and pinpoint those that are spreading quickly and could be potentially damaging or deceptive. Hence, to identify viral tweets on Twitter, we suggest a new remora-optimized twofold gated attention neural network (RO-TGANN). This research’s word representation also creates weighted word vectors by including sentiment data in the term frequency-inverse document frequency (TF-IDF) algorithm. The resulting vectors are entered into RO-TGANN to better represent the comment vectors and efficiently collect context information. Multi-layer perceptron (MLP) classification is also employed to determine the sentiment pattern of the message. The proposed technique is contrasted with the current sentiment analytical techniques under comparable circumstances. According to the empirical results, the suggested analytical approach for sentiment classification has a greater accuracy, f-score, precision, and recall. The creation of such a technique can aid in the drive to encourage ethical social networking usage and limit the transmission of dangerous posts on social networking sites. © Bharati Vidyapeeth's Institute of Computer Applications and Management 2024.

关键词： Context information Multi-layer perceptron (MLP) Remora optimized context-sensitive twofold gated attention neural network (RO-TGANN) Social media Twitter Viral message

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：