检索结果-内蒙古大学图书馆

Automatic extraction of lightweight and efficient neural network architecture of heavy convolutional architectures to predict microsatellite instability from hematoxylin and eosin histology in gastric cancer

引用

Neural Computing and Applications 2024年第25期36卷 15295-15321页

作者： Rostami, Habib Ashkpour, Maryam Behzadi-Khormouji, Hamed Mokhtari, Maral Khayati, Armin Keshavarz, Ahmad Talatian Azad, Saeed Tabesh, Yahya Computer Engineering Department Faculty of Intelligent Systems Engineering and Data Science Persian Gulf University Bushehr75168 Iran Artificial Intelligence and Intelligent Healthcare Lab Artificial Intelligence and Data Mining Research Group Faculty of Intelligent Systems Engineering and Data Science ICT Research Institute Persian Gulf University Bushehr75168 Iran Faculty of New Science and Technologies University of Tehran Tehran Iran Department of Computer Science Imec-IDLab University of Antwerp Sint-Pietersvliet 7 Antwerp2000 Belgium Shahid Faghihi Hospital Shiraz University of Medical Sciences Shiraz Iran Department of Computer Science Engineering and IT School of Electrical and Computer Engineering Shiraz University Shiraz Iran Electrical Engineering Department Faculty of Intelligent Systems Engineering and Data Science Persian Gulf University Bushehr75168 Iran IoT and Signal Processing Research Group Faculty of Intelligent Systems Engineering and Data Science ICT Research Institute Persian Gulf University Bushehr75168 Iran Department of Mathematical Sciences Sharif University of Technology Tehran Iran

Cancers have emerged as a significant concern due to their impact on public health and society. The examination and interpretation of tissue sections stained with Hematoxylin and Eosin (H&E) play a crucial role in disease assessment, particularly in cases like gastric cancer. Microsatellite instability (MSI) is suggested to contribute to the carcinogenesis of specific gastrointestinal tumors. However, due to the nonspecific morphology observed in H&E-stained tissue sections, MSI determination often requires costly evaluations through various molecular studies and immunohistochemistry methods in specialized molecular pathology laboratories. Despite the high cost, international guidelines recommend MSI testing for gastrointestinal cancers. Thus, there is a pressing need for a new diagnostic modality with lower costs and widespread applicability for MSI detection. This study aims to detect MSI directly from H&E histology slides in gastric cancer, providing a cost-effective alternative. The performance of well-known deep convolutional neural networks (DCNNs) and a proposed architecture are compared. Medical image datasets are typically smaller than benchmark datasets like ImageNet, necessitating the use of off-the-shelf DCNN architectures developed for large datasets through techniques such as transfer learning. Designing an architecture proportional to a custom dataset can be tedious and may not yield desirable results. In this work, we propose an automatic method to extract a lightweight and efficient architecture from a given heavy architecture (e.g., well-known off-the-shelf DCNNs) proportional to a specific dataset. To predict MSI instability, we extracted the MicroNet architecture from the Xception network using the proposed method and compared its performance with other well-known architectures. The models were trained using tiles extracted from whole-slide images, and two evaluation strategies, tile-based and whole-slide image (WSI)-based, were employed and comp

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

MQTT based monitoring and control system for remote stations in automotive industry

MQTT based monitoring and control system for remote stations...

引用

2023 IEEE Zooming Innovation in Consumer Technologies Conference, ZINC 2023

作者： Ivanovic, Denis Job, Josip Puntaric, Marko Herceg, Marijan TTTech-Auto CX Osijek Croatia Faculty of Electrical Engineering Computer Science and Information Technology Department of Software Engineering Osijek Croatia Faculty of Electrical Engineering Computer Science and Information Technology Department of Communications Osijek Croatia

ISBN: (纸本)9798350347722

In this paper is presented implementation of a lightweight supervisory control and data acquisition system for remote test stations as a part of a larger test house in the automotive industry. It is necessary to allow remote set up and monitoring of the test stations, which means defining the structure of a system with numerous test stations as endpoints. The test stations are meant to be virtual machines but can be both virtual and physical machines. A communication protocol must be used that enables this within the organization's network, regardless of actual distance and location. The parameters of the test stations to be monitored can be defined according to the needs and purpose. Even when creating your own tool, this function is not unique, i.e. on one test station parameters of operating system resources such as memory usage can be monitored, while on another test station logged-in users or running programs, reported system errors and others must be monitored. Data storage is one of the mandatory functions of this system. This process allows viewing data throughout history and more detailed analysis of events. There are numerous benefits that can be drawn and used from the data stored in the database. It is necessary to pay attention to the data stored as well as the scope and retention throughout history. The correct and secure setup of a database is one of the prerequisites for any serious system that processes data. Appropriate views should be created for users involved in the data monitoring process using all the elements mentioned so far. Creating a visually acceptable and easy-To-use interface that serves the main purpose is the final presentation of the entire system to users. A complete system leads to higher productivity, profitability and better organization of the company. It also allows project managers to better plan the use and occupancy of test stations. At any time, they have insight into the status of individual test stations, their activitie

关键词： Automotive industry

来源：评论

学校读者我要写书评

暂无评论

High-Boost-Gain Split-Source Inverter With Shared-Ground and No Shoot-Through Issue

引用

IEEE Transactions on Industrial Informatics 2024年第3期20卷 3252-3265页

作者： Ahmed, Hafiz Furqan Moursi, Mohamed Shawky El Hosani, Khalifa Al Alzaabi, Omar Zahawi, Bashar National Sun Yat-sen University Department of Electrical Engineering Kaohsiung804201 Taiwan Khalifa University Advanced Power and Energy Center Department of Electrical Engineering and Computer Science Abu Dhabi127788 United Arab Emirates Mansoura University Faculty of Engineering Mansoura35516 Egypt

In this article, we propose an improved high-boost-gain split-source inverter (SSI) for renewable energy generation. The proposed inverter retains the features of the existing SSIs, such as single-stage boost inversion with a reduced number of passive components and elimination of the inverse modulation-duty relationship constraint of the impedance-source inverters. It also provides additional features that include higher boost inversion ability than existing SSIs to connect low-voltage renewable energy sources to the grid, no voltage-source short-circuit issue, which increases the robustness of the proposed inverter and pulsewidth modulation dead times can be relieved, and the negative input dc-terminal and ac-neutral are electrically connected in the proposed inverter, resulting in a constant common-mode voltage and elimination of leakage ground currents for grid-interfaced PV power systems. A detailed circuit operation and analysis is provided, and experiments are performed on a 400-VA prototype inverter to confirm the working of the proposed topology. © 2005-2012 IEEE.

关键词： Pulse width modulation

来源：评论

学校读者我要写书评

暂无评论

Quality-diversity and Novelty Search for Portfolio Optimization and Beyond

引用

Computational Economics 2025年 1-24页

作者： Gašperov, Bruno Begušić, Stjepan Bauman, Tessa Kostanjčar, Zvonko Faculty of Computer and Information Science University of Ljubljana Večna pot 113 Ljubljana Slovenia Faculty of Electrical Engineering and Computing University of Zagreb Unska 3 Zagreb Croatia

In this paper, we provide an overview of exploration algorithms, a novel class of evolutionary computation approaches encompassing novelty search and quality-diversity, as they may be applied to portfolio optimization and related problems in quantitative finance. These algorithms rely on the idea of divergent search, prioritizing the discovery of novel, unexplored solutions over maximizing a classical objective (fitness) function. Their favorable exploration properties make them particularly valuable in evolutionary reinforcement learning, where they have been successfully applied to diverse practical domains such as procedural generation of video game content and robotics. However, their application in portfolio optimization (PO) and quantitative finance in general, remains largely unexplored. We posit that this gap presents significant untapped potential, given the natural connections between divergent search principles and key concepts in PO, including diversification, inter-individual variety of risk preferences, and sensitivity to market regimes. Following an introduction to exploration algorithms, we delve into existing research on their applications in PO, outlining their advantages and shortcomings. Moreover, we propose several research directions that are expected to pave the way for more substantial leverage of such algorithms in decision-making processes in PO and beyond, while emphasizing challenges that stand in the way of their realization. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Evolutionary computation Exploration algorithms Novelty search Portfolio optimization Quality-diversity Quantitative finance

来源：评论

学校读者我要写书评

暂无评论

Elliptic Localization With Imperfect Clock Synchronization for Known and Unknown Propagation Speed Scenarios

Elliptic Localization With Imperfect Clock Synchronization f...

引用

作者： Xiao, Yudong Wang, Gang Ho, K.C. Ningbo University Faculty of Electrical Engineering and Computer Science Ningbo315211 China University of Missouri Electrical Engineering and Computer Science Department ColumbiaMO65211 United States

In this article, we address the elliptic localization problem in the presence of clock synchronization errors at the receivers and transmitters, when the propagation speed is known as well as not known. For the known propagation speed scenario, we first show that the clock synchronization errors, when modeled as Gaussian random variables, can be treated as part of the composite noise in the measurement model without incurring performance loss in localization. Motivated by this result, we propose a generalized trust region subproblem solution for estimating the object position. For the unknown propagation speed scenario, we first formulate a nonconvex weighted least-squares problem. Such a nonconvex problem is solved by either one of the two proposed methods, semidefinite relaxation or grid search, to jointly estimate the object position and the propagation speed. Furthermore, we conduct the mean square error analysis to show that the proposed methods are able to reach the Cramer-Rao lower bound accuracy under Gaussian noise, which is validated by using simulated and semireal data. © 1965-2011 IEEE.

关键词： Synchronization

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Two-Step Methodology for Automated Segmentation of Architectural Distortion in Mammograms 6

A Comprehensive Two-Step Methodology for Automated Segmentat...

引用

6th IEEE Novel Intelligent and Leading Emerging sciences Conference, NILES 2024

作者： Ibrahim, Sameh E. Elnokrashy, Ahmed F. Mohamed, Wael A. Benha University Benha Faculty of Engineering Department of Electrical Engineering Benha Egypt Benha University Electrical Engineering Benha Egypt Nile University Computer Science Giza Egypt

ISBN: (纸本)9798350378511

Breast cancer is one of the most prevalent forms of cancer worldwide and a leading cause of mortality among women. Early detection of breast cancer is crucial for effective treatment. Architectural distortion (AD) is an early sign of breast cancer, characterized by a subtle contraction of breast tissue that often goes unnoticed. Traditional methods of detection heavily rely on the expertise of radiologists, making the process more difficult. To address this, we propose a deep learning approach to automate precise and efficient AD segmentation. Our approach involves a two-step process. In the first step, we utilize a Mask R-CNN Detectron2 model to perform AD segmentation across the entire set of mammography images. This initial segmentation provides a baseline for identifying AD regions. The ResNet-18 patch model is incorporated into the Mask R-CNN model's segmentation pipeline in the second stage. The purpose of this combination is to improve AD area localization and precision. By combining the strengths of both models, we achieve improved accuracy in AD segmentation. The evaluation of our fully automated method yielded remarkable outcomes on a diverse test set consisting of private datasets, including the Baheya dataset and the NCI dataset, as well as the publicly available Digital Database for Screening Mammography (DDSM). The results showed a Segmentation Accuracy of 0.852, Classification Accuracy of 0.915, and Mean Average Precision (mAP) of 0.894. These findings demonstrate potential to enhance the efficiency and accuracy of AD detection and segmentation in mammogram images, contributing to early diagnosis and treatment planning for patients at risk of breast cancer. © 2024 IEEE.

关键词： Mammography

来源：评论

学校读者我要写书评

暂无评论

Improved Layered Architecture: Integration of IoT with Blockchain for Increased Security and Scalability 5

Improved Layered Architecture: Integration of IoT with Block...

引用

5th International Conference on Artificial Intelligence and Data sciences, AiDAS 2024

作者： Jahangir, Muhammad Lee, Ming Jie Kwan, Ban-Hoe Kamal, Tariq Chai, Tong-Yuen Loh, Wing Son Lee Kong Chian Faculty of Engineering and Science Universiti Tunku Abdul Rahman Kajang Malaysia Dhanani School of Science & Engineering Electrical and Computer Engineering Karachi Pakistan

ISBN: (纸本)9798331528553

Most of the existing Internet of Things (IoT) applications are built upon the conventional three-layered architecture that possesses several issues in terms of security, privacy and scalability. In this paper, we propose a five-layer architecture to mitigate the issues faced by the three-layered IoT applications. In particular, two layers: (i) data-link layer and (ii) IoT-Blockchaln layer were introduced. The data-link layer authenticates the legitimate device during the data transmission;while the IoT-Blockchain utilizes the distributed storage to prevent the data from being tampered. To testify the performance of the proposed method in terms of publishing time, experiments were conducted based on two setups: (i) single node setup and (ii) dual node setup. The results suggested the proposed method is highly scalable where the single node setup required an average of 9.4 seconds and dual node setup required 8.66 seconds. Future research will explore various network configurations and the integration of the Internet of Things Application (IOTA), a feeless and lightweight blockchain, to further optimize scalability and efficiency. © 2024 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Development of Automotive-mobility Training in the TRIREME project 30

Development of Automotive-mobility Training in the TRIREME p...

引用

30th IEEE International Symposium for Design and Technology in Electronic Packaging, SIITME 2024

作者： Medgyes, Balint Farkas, Csaba Spanyik, Marek Danieli, Stefano Cantiani, Elena Stolfa, Jakub Budapest University of Technology and Economics Faculty of Electrical Engineering and Informatics Department of Electronics Technology Budapest Hungary VSB-Technical University of Ostrava Faculty of Electrical Engineering and Computer Science Department of Computer Science Ostrava Czech Republic Mylia-Adecco Formazione Milan Italy

ISBN: (纸本)9798331539511

To achieve climate neutrality by 2050, the consistent transformation of the mobility sector is one of the most important pillars of the European Green deal. As a result of green and sustainable approaches, novel automotive concepts and massive digitalisation in the mobility ecosystem is undergoing a continuous development towards eco-friendly solutions and novel business models, and the changing landscape of automotive industry comes with a significant social impact as well. The overall horizontal collaboration on skills agenda in the Automotive-Mobility Ecosystem is assured throughout the Automotive Skills Alliance (ASA) [1], which is the Large-scale Pact for Skills Partnership. The latest strategic project of the partnership to support its activities is the Digital & Green Skills Towards Future of the Mobility Ecosystem (TRIREME) which promotes a collaboration between industry stakeholders and training providers including Vocational education Trainings (VETs), Higher Educations (HEs) and universities), moreover, also emphasizing the widespread public representation of different project segments and evaluating the social impacts and regional impact of the changes in the Automotive-Mobility Ecosystem. In parallel to the development of sectoral skills strategy, our department (Department of Electronics Technology-ETT) is contributing to deliver specific training materials and courses within Work Package 4 (WP4), which is based on the gathered and processed intelligence from previous desk research, survey activity and participation in professional events. The methodology of course development relies on the concept of modularity, our professional competences in the field of Automotive-mobility, and the fulfillment of requirements to cover the needed skills, the competence and the occupational profile subsets. © 2024 IEEE.

关键词： Automotive Mobility Modular Courses Skills Training Development

来源：评论

学校读者我要写书评

暂无评论

Intelligent wearable vision systems for the visually impaired in Saudi Arabia

引用

Neural Computing and Applications 2025年第14期37卷 8571-8591页

作者： Talaat, Fatma M. El-Shafai, Walid Soliman, Naglaa F. Algarni, Abeer D. El-Samie, Fathi E. Abd Faculty of Artificial Intelligence Kafrelsheikh University Kafrelsheikh33516 Egypt Faculty of Computer Science and Engineering New Mansoura University Gamasa35712 Egypt Security Engineering Lab Computer Science Department Prince Sultan University Riyadh11586 Saudi Arabia Department Electronics and Electrical Communications Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt Department of Information Technology College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia

Navigating the world with visual impairments presents unique challenges, often limiting independence and safety. This research introduces SafeStride, a novel algorithm designed to empower visually impaired individuals through real-time obstacle detection and navigation assistance. SafeStride functions through five interconnected phases: sensor data acquisition, data preprocessing, obstacle detection, path planning, and feedback and guidance. A combination of ultrasonic sensors, cameras, and inertial measurement units (IMUs) feed comprehensive environmental data into the system, enabling accurate obstacle detection and safe path planning. Evaluating SafeStride's performance involved the MNIST dataset for image recognition and a dedicated indoor object detection dataset. Additionally, comparisons were made against three deep learning models—convolutional neural network (CNN), long short-term memory (LSTM), and gated recurrent unit (GRU). The results showcased SafeStride's high accuracy and effectiveness in both obstacle detection and classification. Beyond its impressive performance, SafeStride represents a significant leap forward in navigation aids for the visually impaired. By offering a comprehensive solution that enhances safety and independence in diverse environments, it holds immense potential to improve the lives of countless individuals. Future efforts will focus on further optimizing the algorithm and testing its real-world capabilities, paving the way for a future where safe and independent navigation becomes a reality for all. All three deep learning models (CNN, LSTM, GRU) excelled in the experiment, achieving high accuracy above 0.98, strong recall and F1-scores near 0.99, and exceptional AUC-ROC scores exceeding 0.9998. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Paths, Proofs, and Perfection: Developing a Human-Interpretable Proof System for Constrained Shortest Paths 38

Paths, Proofs, and Perfection: Developing a Human-Interpreta...

引用

38th AAAI Conference on Artificial Intelligence, AAAI 2024

作者： Sidorov, Konstantin de Almeida Correia, Gonçalo Homem de Weerdt, Mathijs Demirović, Emir Algorithmics Group Faculty of Electrical Engineering Mathematics and Computer Science Delft University of Technology Netherlands Faculty of Civil Engineering and Geosciences Delft University of Technology Netherlands

ISBN: (纸本)1577358872

People want to rely on optimization algorithms for complex decisions but verifying the optimality of the solutions can then become a valid concern, particularly for critical decisions taken by non-experts in optimization. One example is the shortest-path problem on a network, occurring in many contexts from transportation to logistics to telecommunications. While the standard shortest-path problem is both solvable in polynomial time and certifiable by duality, introducing side constraints makes solving and certifying the solutions much harder. We propose a proof system for constrained shortest-path problems, which gives a set of logical rules to derive new facts about feasible solutions. The key trait of the proposed proof system is that it specifically includes high-level graph concepts within its reasoning steps (such as connectivity or path structure), in contrast to using linear combinations of model constraints. Using our proof system, we can provide a step-by-step, human-auditable explanation showing that the path given by an external solver cannot be improved. Additionally, to maximize the advantages of this setup, we propose a proof search procedure that specifically aims to find small proofs of this form using a procedure similar to A* search. We evaluate our proof system on constrained shortest path instances generated from real-world road networks and experimentally show that we may indeed derive more interpretable proofs compared to an integer programming approach, in some cases leading to much smaller proofs. Copyright © 2024, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Integer programming

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：