检索结果-内蒙古大学图书馆

5th International Conference on Advanced Research in Computing, ICARC 2025

作者： Kariyawasam, K.P.W.D.V. Kahandagamage, P.N. Fernando, M.R.R. Fernandopulle, J.M. Jayasinghearachchi, Vishan Dissanayaka, Kapila Dept. of Software Engineering Sri Lanka Dept. of Information Technology Sri Lanka Dept. of Computer Science Sri Lanka

ISBN: (纸本)9798331530983

In recent years, the Sri Lankan tea industry has fallen behind its competitors in the global tea market. This decline is caused by the challenges in productivity and resource management due to the limitations of traditional crop monitoring methods. This study presents a prototype system architecture that integrates multispectral imagery and IoT technologies to enhance plantation monitoring. The proposed system uses drones to capture high-resolution multispectral images and IoT devices to collect real-time environmental data, providing a comprehensive approach to assessing plant yield and detecting stress. Built on a hexagonal architecture, the system emphasizes modularity, reliability, and scalability by ensuring a clear separation of core functionalities from external components. This design facilitates easy adaptation to various crop types and agricultural contexts, enabling flexibility in deployment and use. This flexible framework can serve as a blueprint for improving decision-making and management practices across diverse plantation environments. © 2025 IEEE.

关键词： Risk perception

来源：评论

学校读者我要写书评

暂无评论

Closed-Loop System Identification of an Unstable Nonlinear System Using Koopman Operator 4

Closed-Loop System Identification of an Unstable Nonlinear S...

引用

4th International Symposium on Instrumentation, control, Artificial Intelligence, and Robotics, ICA-SYMP 2025

作者： Maneeloke, Benjaset Boonto, Sudchai Sanposh, Peerayot Tipsuwan, Yodyium Chinthaned, Natthawut Tanaprasitpattana, Warit Kasetsart University Dept. of Electrical Engineering Bangkok Thailand King Mongkut's University of Technology Thonburi Dept. of Control Systems and Instrumentation Engineering Bangkok Thailand Kasetsart University Dept. of Computer Engineering Bangkok Thailand

ISBN: (纸本)9798331505400

This paper presents a novel methodology for closed-loop system identification of unstable nonlinear systems using the Koopman operator with Extended Dynamic Mode Decomposition with control (EDMDc). The study highlights the critical role of selecting appropriate observable functions to develop accurate and efficient Koopman models. We demonstrate that the resulting Koopman models exhibit excellent fitting and validation properties and retain the stabilizability of the original nonlinear systems. These models are verified through time and frequency responses under closed-loop control using a Linear Quadratic Regulator (LQR), confirming their effectiveness. Future work will extend this framework to more complex systems and incorporate machine learning techniques to refine the selection of observable functions. This approach aims further to enhance the adaptability and robustness of Koopman-based control strategies. © 2025 IEEE.

关键词： Dynamic mode decomposition

来源：评论

学校读者我要写书评

暂无评论

Stabilization Method for DC-bus Oscillation in Dynamic Wireless Power Transfer Systems 14

Stabilization Method for DC-bus Oscillation in Dynamic Wirel...

引用

14th Annual IEEE Applied Power Electronics Conference and Exposition, APEC 2025

作者： Ochiai, Yuki Kusaka, Keisuke Nagaoka University of Technology Dept. of Electrical Electronics and Information Engineering Nagaoka Japan

ISBN: (纸本)9798331516116

Dynamic wireless power transfer systems will have a DC bus, which supplies power to inverters with transmission coils intermittently placed over long distances on the road surface. As the length of the DC bus increases, the wiring inductance also increases. This effect affects inverters that are located far from the power source of the DC bus, requiring them to connect through this increased wiring inductance. When the inverter performs current control on the output side, it may cause negative impedance, resulting in the DC-bus voltage oscillation. This paper proposes a control method to prevent instability of the DC bus voltage by utilizing positive feed-forward (PFF) control. The experimental results with the small-scale prototype show that the proposed control effectively prevents instability. © 2025 IEEE.

关键词： Wireless power transfer

来源：评论

学校读者我要写书评

暂无评论

Retrieval Augmented Generation for Relational Mapping of Resume Data for Improved Analysis 2

Retrieval Augmented Generation for Relational Mapping of Res...

引用

2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025

作者： Manish, Vazzula Manchala, Yugandhar Chopra, Sudeep Banerjee Siddartha, Muddam Reddy, Kothi Yashwanth Vardhaman College of Engineering Dept. of Information Technology Hyderabad India Hyderabad India

ISBN: (纸本)9798331505745

Analysis of resume data is often a critical and time-intensive process that requires extensive metadata. However, a lack of consistency and scalability often leads to inefficiencies and errors in the recruitment process. Tools like Applicant Tracking Systems (ATS) often struggle with the contextual understanding of resume data, as they evaluate each resume in isolation without considering its relations to other similar resumes. We proposes the implementation of a Retrieval-Augmented Generation (RAG) architecture to create a vector relational mapping of resume data based on several curated parameters, such as skills, experiences, and education. This approach enables the system to understand the contextual relations between different resumes, helping the system evaluate them more effectively within a broader context, and improve recruitment outcomes by reducing biases and increasing efficiency. © 2025 IEEE.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Machine Learning Methods in Climate Data Extraction and Forecasting

Comparative Analysis of Machine Learning Methods in Climate ...

引用

2025 International Conference on Emerging Technologies for Intelligent Systems, ETIS 2025

作者： Khajgiwale, Parth Ajit Naveen, Atul Jethani, Nishtha Shitole, Ajitkumar International Institute of Information Technology Dept. of Computer Engineering Hinjewadi Pune India

ISBN: (纸本)9798331507541

Climate forecasting plays a critical role in understanding and mitigating the impacts of climate change. Advances in machine learning (ML) have significantly enhanced the accuracy of climate projections, particularly when dealing with large and complex datasets derived from regional climate models (RCMs) and global climate models (GCMs). This study investigates the application of various ML techniques for predicting precipitation based on temperature data extracted from climate datasets. We evaluate a range of regression models, including linear models and advanced ensemble methods such as Gradient Boosting and XGBoost, along with deep learning approaches like Convolutional Neural Networks (CNNs). Through a rigorous evaluation of these models, we focus on their performance as measured by Mean Squared Error (MSE) to identify the most effective techniques for capturing the intricate relationships within climate data. By analyzing existing studies and performance metrics, we aim to provide insights into the capabilities and limitations of these ML models in improving climate predictions. Furthermore, this research highlights the need for incorporating additional climate variables and optimizing model configurations to enhance predictive accuracy in climate forecasting. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Optimizing Skin Cancer Detection Through Hybrid Convolutional and Ensemble Learning Methods

Optimizing Skin Cancer Detection Through Hybrid Convolutiona...

引用

2025 IEEE International Students' Conference on Electrical, Electronics and Computer Science, SCEECS 2025

作者： Sahithi, Chalamala Teja Basha Shaik, Arif Pandala, Madhavi Latha Dept. of Information Technology Vijayawada India Vit Bhopal School of Computing Science and Engineering Kothrikalan India

ISBN: (纸本)9798331529833

One of the most prevalent types of cancer is skin cancer and millions of people suffer from it across the globe with melanoma being the most dangerous type if not treated at an early stage. Accurate and timely diagnosis is crucial in the management of skin cancer but traditional diagnosis methods like dermoscopy, is largely dependent on the skills of qualified dermatologists which makes it subjective and susceptible to variation among observers. In this sense, deep learning and machine learning approaches have a lot of potential in automating skin cancer classification and enhancing its accuracy for better early intervention and patient outcomes. This paper presents the analysis of the performance of several models, i.e., CNN + Random Forest, DenseNet201, MobileNetV2 and ConvoMixer + CatBoost on HAM10000, ISIC and PAD-UFES-20 datasets. The experimental results indicate that DenseNet201 achieved an accuracy of 91.8%, MobileNetV2 reached 87%, and the combination of ConvoMixer and CatBoost obtained 66% However, the CNN + RF model outperformed all of the other models achieving 96% accuracy revealing the effectiveness of hybrid approaches for skin cancer classification on a reliable and scalable manner. Future work could include investigating transformer-based models, such as Vision Transformers (Suns et al.) and Swin Transformers (Liao et al.), which are able to allow better global context within the data. Also federated learning may be used to enable the use of multi institutional databases without compromising the privacy of patients. In addition, self supervised learning approaches could also help alleviate the reliance in a substantial amount of annotated datasets thereby increasing accuracy and robustness in practical and clinical situations. © 2025 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Silicon nitride photonic beam splitters for O-band power and polarization management 23

Silicon nitride photonic beam splitters for O-band power and...

引用

23rd Slovak-Czech-Polish Optical Conference on Wave and Quantum Aspects of Contemporary Optics

作者： Litvik, Ján Korček, Radovan Benedikovič, Daniel Dept. of Multimedia and Information-Communication Technologies Faculty of Electrical Engineering and Information Technology University of Zilina Univerzitna 1 Zilina01026 Slovakia

ISBN: (数字)9781510688094

ISBN: (纸本)9781510688087

Silicon nitride waveguides play a leading role in photonic system integration. Silicon nitride leverages unique low-loss passive functions, mature deposition techniques of low-pressure chemical vapor deposition and plasma-enhanced chemical vapor deposition, and compatibility with complementary metal-oxide-semiconductor fabrication. So far, a wide variety of photonic devices have been demonstrated in Silicon nitride platforms, including ultra-low-loss waveguides, filters, multiplexers, and grating or edge couplers, to name a few. Among these elements, beam splitters based on multimode interference couplers are key building blocks for complex chip-scale photonic systems, including coherent communications or advanced optical networks. This work is focused on O-band (spectral range between 1260 nm and 1360 nm) multimode interference beam splitters on silicon nitride platform for power and polarization on-chip management. It is used three-dimensional eigenmode expansion and finite difference time domain solvers, respectively. We proposed a 1x2 power and polarization splitters with a compact footprint of 2.6 μm and 5.55 μm and insertion loss as low as 0.3 dB across 400 nm wavelength range. Also, we designed multimode interference power splitters 1:4 and 1:8 with insertion loss as low as 0.5 dB with bandwidth 240 nm and 60 nm, respectively. These results are promising for the development of scalable and high-performance chip-integrated components in power-hungry and polarization-sensitive applications. For effective designing of polarization splitter based on multimode interference it is necessary using apodization techniques to avoid large footprint and very low bandwidth. © 2025 SPIE.

关键词： Silicon nitride

来源：评论

学校读者我要写书评

暂无评论

Quantum Resistance Blockchain Algorithm using QHF and Novel Consensus Mechanism

Quantum Resistance Blockchain Algorithm using QHF and Novel ...

引用

2025 IEEE International Students' Conference on Electrical, Electronics and Computer Science, SCEECS 2025

作者： Paul, Soumyadip Mazumdar, Mausumi Maitra Chakraborty, Sarit Government College of Engineering & Ceramic Technology Dept. of Information Technology Kolkata700010 India Government College of Engineering and Leather Technology Department of Computer Science and Engineering Kolkata700106 India

ISBN: (纸本)9798331529833

The emergence of quantum computing poses a significant threat to the security of traditional blockchain systems, which rely heavily on classical cryptographic algorithms. To safeguard the integrity and reliability of blockchain technology in the upcoming era, this work proposes a novel quantum-resistant blockchain architecture. This approach integrates a robust consensus mechanism, with advanced quantum cryptographic primitives, including quantum digital signatures based on a Quantum Hash Function (QHF). Incorporating a quantum hash function enhances the blockchain resistance, providing an additional layer of security against quantum attacks. By combining these elements, our method creates a blockchain system fortified against the potential vulnerabilities introduced by quantum computers. The proposed solution leverages the power of QHFs to safeguard transaction integrity, while the consensus mechanism ensures the reliability and decentralization of the network. This paper also delves into the theoretical underpinnings of quantum blockchains, exploring their design, feasibility, and potential applications, emphasizing their promising future, particularly in areas such as decentralized identity authentication. Finally, it contributes to the development of a secure and resilient blockchain ecosystem capable of thriving in the coming era. © 2025 IEEE.

关键词： Quantum computers

来源：评论

学校读者我要写书评

暂无评论

High Voltage and High Frequency DC Power Supply with Ultra High Voltage SiC Schottky Barrier Diode Modules

引用

Journal of Japan Institute of Electronics Packaging 2025年第1期28卷 123-131页

作者： Nomura, Yuki Funaki, Tsuyoshi Research Dept. NexFi Technology Inc. 2-1 Yamadaoka Suita-shi Osaka565-0871 Japan Dept. of Electronic and Information Engineering Osaka University 2-1 Yamadaoka Suita-shi Osaka565-0871 Japan

A high-voltage (HV) DC power supply typically consists of an inverter, a transformer and a Cockcroft-Walton (CW) voltage multiplier. High-frequency operation of the inverter can reduce the required capacitance of HV capacitors in the CW circuits, allowing miniaturization of HV DC power supplies. High voltage rectifying diodes used in high frequency CW circuits can reduce switching losses by using SiC Schottky barrier diodes (SBD). In this study, we developed an ultra-high voltage SiC SBD module connected in series. However, an increase in the number of SBD modules connected in series results in increased conduction loss, indicating a limitation in the high-voltage blocking capability. This paper proposes an effective circuit configuration required to improve the efficiency of an HV DC power supply by considering the number of series-connected SBDs in the module along with the number of stages in the CW circuit. © The Japan Institute of Electronics Packaging.

关键词： Schottky barrier diodes

来源：评论

学校读者我要写书评

暂无评论

Multi-Objective Cooperative control of Vehicle Platoon Based on Fuzzy MPC

Multi-Objective Cooperative Control of Vehicle Platoon Based...

引用

IEEE International Conference on Industrial technology (ICIT)

作者： Wanying Zhu Yunfei Yin Zhanguo Xu Yuanlong Wei Shenjun Zeng Dept. of Traffic Information and Control Engineering Harbin Institute of Technology Harbin China Dept. of Traffic Information and Control Engineering Jilin University Changchun China

ISBN: (数字)9798331521950

ISBN: (纸本)9798331521967

To simultaneously optimize multiple performances of the cooperative adaptive cruise control (CACC) system, a fuzzy MPC control strategy is proposed to achieve multi-objective cooperative control for electric vehicle platoons. The longitudinal kinematic analysis of the vehicle platoon is conducted to establish the platoon model. Based on the analysis of system performance, safety, comfort, and following performance are selected as the system's performance indexes, and a comprehensive performance function for the MPC is constructed. Fuzzy control theory is employed to optimize the weight parameters, enabling the CACC system to adapt to different conditions. The effectiveness and reliability of the fuzzy MPC control strategy are verified through co-simulation using Carsim and Simulink.

关键词： Wireless communication Fuzzy control Adaptation models Software packages System performance Reliability theory Electric vehicles Safety Vehicle dynamics Cruise control

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：