检索结果-内蒙古大学图书馆

Deep transfer learning technique to detect white blood cell classification in regular clinical practice using histopathological images

引用

Multimedia Tools and Applications 2025年第9期84卷 5699-5723页

作者： Davamani, K. Anita Jawahar, Malathy Anbarasi, L. Jani Ravi, Vinayakumar Al Mazroa, Alanoud Robin, C. R. Rene Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai India Leather Process Technology Division CSIR-Central Leather Research Institute Chennai India School of Computing Science and Engineering Vellore Institute of Technology Vellore India Computer Science and Engineering Sri Sairam Engineering College Sirukalathur India Center for Artificial Intelligence Prince Mohammad Bin Fahd University Khobar Saudi Arabia Department of Information Systems College of Computer and Information Sciences Princess Nourah bint Abdulrahman University Riyadh11671 Saudi Arabia

Leukemia, a malignant disease characterized by the rapid proliferation of specific types of white blood cells (WBC), has prompted increased interest in leveraging automatic WBC classification system. This study presents the design of a robust WBC classification system, integrating deep learning with microscopic image analysis. The proposed classification model is designed to categorize blood cells into four distinct groups: eosinophil, lymphocyte, monocyte, and neutrophil. The study employs a Kaggle image dataset for comprehensive learning. The dataset comprises 12,500 microscopic images used to categorize the four blood cell groups. To enhance performance and reduce the likelihood of overfitting, transfer learning techniques are employed. Six deep transfer learning models namely VGG16, ResNet50, AlexNet, MobileNet, GoogLeNet, and EfficientNetBO are used for feature extraction and classification. The results of the experiments show that VGG16 and MobileNet demonstrated enhancements compared to other pre-trained models when evaluated on both augmented and original datasets. A diverse set of evaluation criteria was employed to thoroughly assess the effectiveness of medical image classification. Notably, the VGG16 and MobileNet models accurately predicted Lymphocytes and Monocytes with a 100% accuracy rate, and Eosinophil and Neutrophil with rates of 99.35% and 99.81%, respectively. This research work empower medical practitioners, particularly in the field of pathology and hematology by providing advanced tools for accurate blood cell classification. The proposed VGG16 and MobileNet models hold promise for simplifying WBC classification, improving decision-making processes, and ultimately advancing patient care in the medical domain. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Data Distribution Valuation 38

Data Distribution Valuation

引用

38th Conference on Neural Information Processing systems, NeurIPS 2024

作者： Xu, Xinyi Wang, Shuaiqi Foo, Chuan-Sheng Low, Bryan Kian Hsiang Fanti, Giulia Department of Computer Science National University of Singapore Singapore Department of Electrical and Computer Engineering Carnegie Mellon University United States Institute for Infocomm Research Agency for Science Technology and Research Singapore

Data valuation is a class of techniques for quantitatively assessing the value of data for applications like pricing in data marketplaces. Existing data valuation methods define a value for a discrete dataset. However, in many use cases, users are interested in not only the value of the dataset, but that of the distribution from which the dataset was sampled. For example, consider a buyer trying to evaluate whether to purchase data from different vendors. The buyer may observe (and compare) only a small preview sample from each vendor, to decide which vendor's data distribution is most useful to the buyer and purchase. The core question is how should we compare the values of data distributions from their samples? Under a Huber characterization of the data heterogeneity across vendors, we propose a maximum mean discrepancy (MMD)-based valuation method which enables theoretically principled and actionable policies for comparing data distributions from samples. We empirically demonstrate that our method is sample-efficient and effective in identifying valuable data distributions against several existing baselines, on multiple real-world datasets (e.g., network intrusion detection, credit card fraud detection) and downstream applications (classification, regression). © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Spatiotemporal Traffic Analysis: Deep Hybrid Approach for Resource and Cyberattacks Prediction 19

Spatiotemporal Traffic Analysis: Deep Hybrid Approach for Re...

引用

19th International Conference on Ubiquitous Information Management and Communication, IMCOM 2025

作者： Lee, Hyeonmin Kim, Dongchan Beom, Donggyu Byun, Gyurin Vo, Van-Vi Choo, Hyunseung Department of AI Systems Engineering Sungkyunkwan University Suwon16419 Korea Republic of Department of Electrical and Computer Engineering Sungkyunkwan University Suwon16419 Korea Republic of Convergence Research Institute Sungkyunkwan University Suwon16419 Korea Republic of Department of Computer Science and Engineering Sungkyunkwan University Suwon16419 Korea Republic of

ISBN: (纸本)9798331507817

This study proposes a hybrid deep learning approach to address the complexity and dynamic characteristics of modern network environments. The research integrates Graph Neural Networks (GNNs) and Convolutional Long and Short-Term Memory (ConvLSTM) networks to predict future network traffic and detect cyberattacks. The model was trained and evaluated on the CICIDS 2018 dataset which includes various types of normal and malicious traffic. Grid-based representations were created from the dataset. The attack type of each timestamp were visualized using distinct colors to the grid images. These images are sued as input of ConvLSTM model. Protocol and destination port are modeled as nodes in a graph, with volume of data flow represented as weighted edges. This graph-based representation is designed to capture unique traffic patterns of specific services and enhance the analysis of spatial and temporal features. Experimental results show a 13% increase in macro F1 score and a 4% increase in weighted F1 score, highlighting the effectiveness of the proposed method. This research highlights its potential to enable proactive responses through the prediction of potential cyberattack occurrences. © 2025 IEEE.

关键词： Convolutional Long Short-Term Memory Cyberattack Detection Deep Learning Graph Neural Networks Network Traffic Prediction

来源：评论

学校读者我要写书评

暂无评论

A cadaveric breast cancer tissue phantom for phase-contrast X-ray imaging applications

引用

Animal Models and Experimental Medicine 2023年第5期6卷 427-432页

作者： Cody C.Rounds Chengyue Li Wei Zhou Kenneth M.Tichauer Jovan G.Brankov Biomedical Engineering Illinois Institute of TechnologyChicagoIllinoisUSA Medical Imaging Research Center Illinois Institute of TechnologyChicagoIllinoisUSA Electrical and Computer Engineering Illinois Institute of TechnologyChicagoIllinoisUSA

Background:As mammography X-ray imaging technologies advance and provide elevated contrast in soft tissues,a need has developed for reliable imaging phantoms for use in system design and component *** advanced imaging modalities such as refraction-based methods,it is critical that developed phantoms capture the biological details seen in clinical precancerous and cancerous cases while minimizing artifacts that may be caused due to phantom *** work presents the fabrication of a breast tissue imaging phantom from cadaveric breast tissue suitable for use in both transmission and refraction-enhanced imaging ***:Human cancer cell tumors were grown orthotopically in nude athymic mice and implanted into the fixed tissue while maintaining the native tumor/adipose tissue ***:The resulting human–murine tissue hybrid phantom was mounted on a clear acrylic housing for absorption and refraction X-ray *** breast tomosynthesis was also ***:Both attenuation-based imaging and refraction-based imaging of the phantom are presented to confirm the suitability of this phantom's use in both imaging modalities.

关键词： breast tumors digital mammography imaging phantoms orthotopic animal models phasecontrast X-ray imaging

来源：评论

学校读者我要写书评

暂无评论

Simulation and Analysis of a MEMS based Micromirror System for Deployment in Optical Beam Steering systems Used in Experimental Quantum Computing 4

Simulation and Analysis of a MEMS based Micromirror System f...

引用

4th International Conference for Emerging Technology, INCET 2023

作者： Abani, Rita Indian Institute of Science Education and Research Bhopal Department of Electrical Engineering and Computer Science Bhopal India

ISBN: (纸本)9798350335750

The aim of this study is to highlight the utility and applicability of Microelectromechanical systems (MEMS) technology in addressing the existing challenges of precision control of beams in performing manipulation of two-dimensional atomic systems or states of a qubit in Quantum Optics setups. This study specifically focuses on the utility of a controllable MEMS based Micromirror that maneuvers a laser source to access multiple positions of a qubit in a two-dimensional trapped lattice;an application of pertinent interest to Experimental Quantum Computation. This paper focuses on simulating a MEMS based micromirror system proposed by (Knoernschild et al. [1]) in COMSOL and analyzing its architecture. © 2023 IEEE.

关键词： MEMS

来源：评论

学校读者我要写书评

暂无评论

Investigation of Scalable Approximation of the Minimum Variance Distortionless Response Beamformer

Investigation of Scalable Approximation of the Minimum Varia...

引用

2024 IEEE International Symposium on Phased Array systems and Technology, ARRAY 2024

作者： Park, Jung-Jin Rodriguez-Martinez, Gumer Bolding, Mark M. Westafer, Ryan S. Sathe, Visvesh S. School of Electrical and Computer Engineering Georgia Institute of Technology United States Georgia Tech Research Institute Georgia Institute of Technology Information and Communications Laboratory United States

ISBN: (纸本)9798350392142

The minimum variance distortionless response (MVDR) beamformer is commonly used with phased arrays to perform adaptive spatial filtering - preserving array gain in a desired direction while minimizing in-band interference from other directions. This constrained optimization problem is traditionally solved by regularly constructing and inverting the array covariance matrix, resulting in computational complexity of order O(N3), where N is the number of elements in the array. This paper explores a beamspace approximation, using a combination of the spatial fast Fourier transform (FFT) and iterative search, to achieve linear-logarithmic complexity. We investigate the signal to interference-plus-noise ratio (SINR) and complexity tradeoffs associated with this approach to examine its suitability for large array systems, © 2024 IEEE.

关键词： Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

Development of a Medium-Voltage Transformerless Multilevel Inductive Power Transfer System

Development of a Medium-Voltage Transformerless Multilevel I...

引用

2024 IEEE Energy Conversion Congress and Exposition, ECCE 2024

作者： Hwang, Hyeonji Park, Sumi Kim, Myung-Yong Lee, Jaehong Lee, Seung-Hwan University of Seoul School of Electrical and Computer Engineering Seoul Korea Republic of Korea Railroad Research Institute Smart Electrical & Signaling Division Uiwang16105 Korea Republic of

ISBN: (纸本)9798350376067

A transformerless multilevel inductive power transfer (IPT) system converts medium-voltage (MV, 6.6 ~ 25 kV) by employing a multilevel converter and excitation coils. To deliver outputs of N number of inverters with MV-level isolation, N:1 coupled excitation coils and a transmitter coil are investigated. The transmitter coil augments magnetic fields generated by the multiple excitation coils. Then, receiver coils can collect power from the transmitter coil via inductive couplings. Applications of the proposed IPT system are MV online IPT systems for trains and large-scale wireless charging stations for electric vehicles. This paper addresses key technical challenges in realizing the MV transformerless multilevel IPT system, such as the multilevel converter, its controllers, and the resonant tank design. In addition, the MV isolation strategy of the excitation coil and the impact of the reinforced concrete on the IPT system are discussed. For evaluation, a 6-level IPT system was fabricated in the PLECS simulation tool. The multi-load charging capacity of the proposed IPT system was evaluated as well. © 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

Innovative Prompting Strategies and Holistic Evaluation of LLM Movie Recommender 3

Innovative Prompting Strategies and Holistic Evaluation of L...

引用

3rd International Conference on Intelligent Computing and Next Generation Networks, ICNGN 2024

作者： Zhu, Yuanjing Liu, Yunan Social Science Research Institute Duke University Durham United States Electrical & Computer Engineering Duke University Durham United States

ISBN: (纸本)9798331529222

Recommendation systems play a crucial role in today’s digital environment, and the rise of Large Language Models (LLMs) has created new opportunities to enhance their effectiveness. LLMs have shown great promise in improving recommendation systems by better understanding user preferences and generating personalized suggestions. However, zero-shot in-context learning often yields suboptimal performance, while fine-tuning requires significant resources. This study creatively develops four distinct prompting strategies: Basic, Context-based, Personalized, and Chain-of-Thought. Each strategy takes advantage of LLMs for movie recommendations, integrating collaborative filtering techniques with reasoning methods. Our innovative approach outperforms traditional deep learning methods without the need for fine-tuning. Unlike previous research that focused solely on recommendation accuracy, we use a comprehensive evaluation framework that includes accuracy, diversity, and novelty metrics. This holistic analysis highlights the specific strengths of each prompting strategy across different LLM architectures, providing valuable insights into balancing recommendation quality with user experience. ©2024 IEEE.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Design of high-efficiency and large-angle homo-metagratings for light source integration

引用

Optics Express 2023年第15期31卷 24404-24411页

作者： Tsai, Wei-Cheng Hong, Yu-Heng Kuo, Hao-Chung Huang, Yao-Wei Department of Photonics College of Electrical and Computer Engineering National Yang Ming Chiao Tung University Hsinchu30010 Taiwan Semiconductor Research Center Hon Hai Research Institute Taipei11492 Taiwan

Meta-optics integrated with light sources has gained significant attention. However, most focused on the efficiency of metasurfaces themselves, rather than the efficiency of integration. To design highly efficient beam deflection, we develop a scheme of homo-metagrating, involving the same material for meta-atoms, substrate, and top layer of the laser, to achieve near-unity power from light-emitting to metasurfaces. We utilize three degrees of freedom: overall add-on phase, parameters of meta-atoms in a period, and lattice arrangement. The overall efficiency of homo-metagratings is higher than that of hetero-metagratings. We believe our approach is capable of being implemented in various ultracompact optic systems. © 2023 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Robust Load Frequency Control of Two-Area Interconnected Power System Using Fuzzy-I Controller

Robust Load Frequency Control of Two-Area Interconnected Pow...

引用

2023 IEEE IAS Global Conference on Emerging Technologies, GlobConET 2023

作者： Wazir, Awadh Ba Alhussainy, Abdullah Ali Alghamdi, Sultan Rawa, Muhyaddin Sindi, Hatem F. King Abdulaziz University K. A. CARE Energy Research and Innovation Center Smart Grids Research Group Center of Research Excellence in Renewable Energy and Power Systems Department of Electrical and Computer Engineering Jeddah Saudi Arabia King Abdulaziz University Smart Grids Research Group Center of Research Excellence in Renewable Energy and Power Systems Department of Electrical and Computer Engineering Jeddah Saudi Arabia King Abdulaziz University Electrical and Computer Engineering Jeddah Saudi Arabia

ISBN: (纸本)9798350331790

The paper proposes a Fuzzy-I controller for optimal load frequency control (LFC) in a two-area interconnected power system. The proposed controller is composed of a fuzzy logic controller (FLC) and an integral (I) controller. To achieve a better dynamic response for the LFC, the integral controller and frequency bias parameters of the secondary loop are tuned using the Particle Swarm Optimization (PSO) technique. To boost the efficiency of the optimization, a proposed objective function using the integral of squared error (ISE) and settling time is used. A comparative study and analysis are conducted between the base system controller, optimized I controller, and the proposed controller under three different scenarios of load disturbances. The robustness of the proposed controller is shown by performing a sensitivity analysis for various system parameters and operating conditions. Moreover, the performance of the proposed controller was compared with the previous LFC approaches published in the literature. The simulation outcomes demonstrate that the proposed method has an outstanding performance. The work results are presented as time-domain simulations using MATLAB/SIMULINK tool. © 2023 IEEE.

关键词： Controllers

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：