检索结果-内蒙古大学图书馆

47th ICT and Electronics Convention, MIPRO 2024

作者： Vulić, Lukrecia Kaučić, Luka Aleksi, Ivan Matić, Tomislav Computer Science And Information Technology Osijek Faculty Of Electrical Engineering Osijek Croatia

ISBN: (纸本)9798350382495

In today's modern world, efficient programming is a necessity. To speed up code generation nowadays, programming code is generated using different graphical tools. Although efficient, this technology is scarcely used in embedded system development. In this paper, we present a procedure for block-based visual programming with applications in embedded systems development. We present several examples of blocks using the Blockly open-source visual programming tool and test the implementation on selected Infineon XMC-based boards. The presented programming solution shows successful implementation of block-based visual programming in embedded systems development. © 2024 IEEE.

关键词： Embedded systems

来源：评论

学校读者我要写书评

暂无评论

2-Step RACH and Unsourced Massive Random Access in Cell-Free User-Centric Networks 58

2-Step RACH and Unsourced Massive Random Access in Cell-Free...

引用

58th Asilomar Conference on Signals, Systems and computers, ACSSC 2024

作者： Gkiouzepi, Eleni Çakmak, Burak Caire, Giuseppe Technische Universität Faculty of Electrical Engineering and Computer Science Berlin Germany

ISBN: (纸本)9798350354058

In this work we consider a scheme for unsourced random access (uRA) in cell free (CF) wireless networks, which is conceptually reminiscent of the 2-step RACH scheme defined in 3GPP for cellular networks. During the designated random access channel (RACH) slots, users engaged in random access transmit codewords drawn from a shared codebook. The distributed and CF nature of the network is adressed by partitioning the network coverage area into zones, referred to as 'locations,' and assigning a location-specific access codebook to each location. We use the recently proposed multisource Approximated Message Passing (AMP) algorithm for joint detection of the access codewords and channel estimation. In particular, AMP generates two outputs:a list of active codewords and an estimate of the corresponding channel vectors. The aforementioned outputs facilitate the formation of a user-centric cluster. The impact of random access users and the overall system performance are assessed based on the sum spectral efficiency for uplink (UL) and downlink (DL) of the data transmission slots, under limited random activity of the users. © 2024 IEEE.

关键词： Channel estimation

来源：评论

学校读者我要写书评

暂无评论

Fast Analysis of Characteristic Modes Using Hybrid Integral Equation Methods

Fast Analysis of Characteristic Modes Using Hybrid Integral ...

引用

2024 International Applied Computational Electromagnetics Society Symposium, ACES-China 2024

作者： He, Yusheng Shao, Hanru Ningbo University Faculty of Electrical Engineering and Computer Science Ningbo315211 China

ISBN: (纸本)9798350355581

To expedite the characteristic mode analysis (CMA) of electromagnetic target structures, this paper combines frequency- and material-independent reactions (FMIR) with characteristic mode analysis using the volume-surface integral equation (VSIE). Although the CMA based on VSIE is not affected by spurious modes when calculating targets containing dielectric, its matrix is high dimensional, resulting in slower calculations. FMIR only needs to store the calculation once for matrices that are independent of frequency and material parameters, which greatly reduces the repetitive operations when calculating multi-frequency impedance matrices. Numerical results show that combining FMIR with the CMA using VSIE can effectively improve the computational speed. © 2024 IEEE.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

Evaluating the Performance of Clinical data using Machine learning Approach- An Ensemble Model 2

Evaluating the Performance of Clinical data using Machine le...

引用

2nd IEEE International Conference on Networks, Multimedia and Information Technology, NMITCON 2024

作者： Abdullah, A. Sheik Vinod, A Aashish Pranav, A G Vishal Govindarajan, Yeshwanth Selvakumar, Subramanian Vellore Institute of Technology School of Computer Science and Engineering Chennai India Bahir Dar University Faculty of Electrical and Computer Engineering Ethiopia

ISBN: (纸本)9798350372892

In the rapidly evolving field of healthcare, accurate clinical predictions are paramount for effective disease management and treatment planning. This paper introduces a novel ensemble machine learning model that utilizes the combined strengths of decision trees, neural networks, random forests, and support vector machines, integrated through a sophisticated linear regression meta-learner. This advanced integration strategy enhances predictive accuracy by optimally weighting the contributions of each base model based on their predictive reliability and effectiveness. The ensemble model amalgamates diverse algorithms with a meta-learning approach to harness a broader spectrum of data insights, thereby overcoming the limitations of traditional single-model approaches. Comparative analysis reveals that the ensemble model significantly outperforms existing methods, achieving superior accuracy in clinical predictions. These results underscore the potential of ensemble approaches in revolutionizing predictive analytics in healthcare, offering a promising tool for improving diagnostic precision and patient outcomes. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Beyond Human Vision: The Role of Large Vision Language Models in Microscope Image Analysis

Beyond Human Vision: The Role of Large Vision Language Model...

引用

2024 IEEE International Conference on Big Data, BigData 2024

作者： Verma, Prateek Van, Minh-Hao Wu, Xintao University of Arkansas Department of Electrical Engineering and Computer Science Fayetteville United States

ISBN: (纸本)9798350362480

Vision language models (VLMs) such as LLaVA, ChatGPT-4, and Gemini have recently emerged and gained the spotlight for their ability to comprehend the dual modality of image and textual data showing impressive performance on tasks such as natural image captioning, visual question answering, and spatial reasoning. Additionally, a universal segmentation model by Meta AI, Segment Anything Model (SAM) shows unprecedented performance at isolating objects from unforeseen images. Because medical experts, biologists, and materials scientists routinely examine microscopy or medical images in conjunction with textual information in the form of captions, literature, or reports, and draw conclusions of great importance and merit, it is essential to evaluate their performance on these images. In this study, we charge ChatGPT, LLaVA, Gemini, and SAM quantitatively with classification, segmentation and counting tasks. We observed that ChatGPT and Gemini were impressively able to comprehend the visual features in microscopy images, while SAM was quite capable at isolating artifacts in a general sense. However, the performance was not close to that of a domain expert - the models were readily encumbered by the introduction of impurities, defects, object overlaps and diversity present in the images. © 2024 IEEE.

关键词： biology electron microscopy images materials science vision language models zero-shot evaluation

来源：评论

学校读者我要写书评

暂无评论

Measurement of acceleration and angular velocity of particles during a 3D silo discharge

引用

Particuology 2024年第9期92卷 61-71页

作者： Tongtong Mu Yiming Li Quan Chen Ran Li Hui Yang College of Medical Instrument Shanghai University of Medicine and Health SciencesShanghai201318China School of Optical-Electrical and Computer Engineering University of Shanghai for Science and TechnologyShanghai200093China

Accurate measurement of the three-dimensional(3D)movement of discrete particles is crucial for comprehending complex granular rheology in *** this paper,the acceleration and angular velocity of particles in 3D silos are measured by using a spherical detector based on inertial technology and magnetic positioning *** acceleration of particles is the largest in the center of silos,which suggest that the resistance generated by friction and extrusion is the ***,the angular velocity distribution follows lognormal function except for particles near the *** correlation between acceleration and angular velocity is opposite in different flow *** reveals for the first time that the extent to which the resultant force on the particles affects their rotational motion is related to the flow *** results have practical significance for regulating the granular flow pattern and optimizing the structural design of silos.

关键词： Granularflow Silo Angular velocity Acceleration

来源：评论

学校读者我要写书评

暂无评论

Benchmarking Machine Learning based Intrusion Detection for IoT Edge Devices 12

Benchmarking Machine Learning based Intrusion Detection for ...

引用

12th IEEE International Conference on Identification, Information and Knowledge in the Internet of Things, IIKI 2024

作者： Alsharif, Maram Rawat, Danda B. Department of Electrical Engineering & Computer Science WashingtonDC20059 United States

ISBN: (纸本)9798331510633

Machine learning-based Intrusion detection (ML-IDS) gained a lot of interest from the research community as security threats facing the IoT are on the rise. Researchers focused on improving intrusion detection efficiency based on machine learning. However, the feasibility of applying proposed ML algorithms to resource limited IoT devices limited. We present a proof of concepts (POC) for ML-IDS for IoT edge device using actual devices. Furthermore, we envisage the lack of virtual environments that mimics the realistic IoT world, puts research completeness on bay. In this paper, we extend the benchmarks of intrusion detection, applied to IoT edge devices of a varying of computing resources. The benchmarks are based on machine learning techniques endorsed by the research community, and adopt popular intrusion datasets for training and testing models. We also utilize the benchmarks to calibrate Virtual-box environment in a novel way to produce virtual machines that closely mimic realistic IoT edge devices. Thus accurate virtualization would become a reliable tool available to researchers to test their approaches. © 2024 IEEE.

关键词： Intrusion Detection IoT Security Machine Learning

来源：评论

学校读者我要写书评

暂无评论

Fault Detection and Diagnostics of Air Handling Unit in Hospital Building Using Machine Learning 15

Fault Detection and Diagnostics of Air Handling Unit in Hosp...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Islam, Md. Mazharul Ahmed, Mubasshir Khan, Niaz Ashraf North South University Electrical and Computer Engineering Dhaka Bangladesh University of Liberal Arts Bangladesh Computer Science and Engineering Dhaka Bangladesh

ISBN: (纸本)9798350370249

Fault Detection and Diagnostics (FDD) in Air Handling Units (AHUs) are vital for ensuring optimal indoor air quality and operational efficiency in hospital buildings. AHUs play a critical role in regulating temperature and humidity, which directly impacts patient care and staff comfort. Effective FDD can prevent system malfunctions that lead to increased energy consumption, higher operational costs, and potential health risks due to poor air quality. This study explores the application of machine learning techniques for FDD in hospital HVAC systems. Utilizing comprehensive datasets from the Lawrence Berkeley National Laboratory (LBNL), we focused on various classifiers, including Random Forest and K-Nearest Neighbors, which achieved accuracies of 99.85% and 99.77%, respectively, in fault identification. These models demonstrated exceptional precision, highlighting their suitability for complex environments where accurate diagnostics are essential. Our findings emphasize the importance of integrating machine learning into building management systems. By enabling early fault detection, these advanced models significantly reduce operational costs and enhance system reliability. This approach not only improves indoor air quality but also supports sustainable healthcare environments by minimizing energy waste. The research contributes to the development of smarter, more efficient building management solutions, paving the way for real-world applications of data-driven FDD methods. The insights gained provide a strong foundation for future implementations, promoting safer and more sustainable healthcare facilities through enhanced HVAC system performance and fault management. This study underscores the potential of machine learning in revolutionizing building management and improving the overall hospital environment. © 2024 IEEE.

关键词： Air handling units ahus Building management systems Fault detection and diagnostics Hospital building Machine learning Real time monitoring

来源：评论

学校读者我要写书评

暂无评论

Face frontalization GAN with self-supervised learning for pose-invariant facial recognition 11

Face frontalization GAN with self-supervised learning for po...

引用

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

作者： Alhlffee, Mahmood H.B. Chung Hua University College of Computer Science and Electrical Engineering Hsinchu Taiwan

ISBN: (纸本)9798331518127

Despite impressive milestones achieved by generative models such as Generative Adversarial Network (GAN) in synthesizing faces, maintaining face identity remains a major challenge for most face recognition system. In this paper, we propose a Self-supervised Face Frontalization GAN (SF-GAN), which produces a frontal face image from a profile image. We designed a profile method to preserve identity information and fine details in high-resolution that focus on pose feature space, which helps SF-GAN reconstruct high-frequency face texture details. SF-GAN switches key facial regions between the input image and its reconstructed version to produce more realistic images. Furthermore, we introduce an orthogonal constraint to our generator that penalizes redundant latent representations, resulting in a more diverse pose appearance details. While the discriminator is designed with a mechanism of facial awareness for each facial region to improve overall model performance. FaceNet and MTCNN are then used to extract correlated face features in order to determine the accuracy of face recognition. Our evaluations are based on the Multi-PIE and CAS-PEAL datasets. Results showed that SF-GAN achieved a better face quality visualization and rank-1 face identification. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Optimization of Transmission Distance in Symmetric Wireless Power Transfer Topology 47

Optimization of Transmission Distance in Symmetric Wireless ...

引用

47th ICT and Electronics Convention, MIPRO 2024

作者： Vinko, Davor Srnović, Mario Bilandžija, Domagoj Filipović, Luka Faculty Of Electrical Engineering Computer Science And Information Technology Osijek Osijek Croatia

ISBN: (纸本)9798350382495

Inductive wireless power transfer (WPT) system uses alternating magnetic field to transmit power from the transmitter to the receiver. To confine the magnetic field, WPT coils are realized with high permeability substrate material that ensures shielding. Aside from shielding, high permeability substrate also increases the coil inductance. When transmitter and receiver coils are placed in close proximity, high permeability substrate of transmitter coil increases the inductance of the receiver coil, and vice versa. This additional inductance increase is a function of the substrate material type and the distance between the coils. To achieve high efficiency and low losses of the WPT system, a capacitor network is added to both transmitter and receiver coil. In a common serial-serial (S-S) WPT system topology, the capacitor networks are asymmetric, i.e. the capacitor network of the transmitter and the receiver are not identical. The efficiency of asymmetric S-S topology is significantly impaired due to variable coil inductance. To attain high efficiency in such operating conditions, this paper proposes symmetric S-S WPT topology with emphasis on transmission distance optimization. © 2024 IEEE.

关键词： Inductive power transmission

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：