检索结果-内蒙古大学图书馆

2023 IEEE International Conference on electrical, computer and Energy Technologies, ICECET 2023

作者： Adams, Adrian Abu-Mahfouz, Adnan M. Hancke, Gerhard P. University of Pretoria Department: Electrical Electronics and Computer Engineering Pretoria South Africa Pretoria South Africa City University of HongKong Department of Computer Science Kowloon Tong Hong Kong

ISBN: (纸本)9798350327816

Transport systems are fundamental to supporting economic growth, and the need for smarter, safer, more efficient and climate neutral transport systems continues to grow. Maintenance and operation of transport infrastructure is expensive and has many difficulties. In recent years, the application of machine learning to solve problems has been pursued with varying success rates. Many open problems still remain at this stage. This paper provides a review of deep learning applications in transport systems. Multiple deep learning applications are discussed e.g. railway safety, self-driving cars, pedestrian crossing and traffic light detection. Reviewed papers are evaluated in terms of challenges, contribution, weakness, research gaps. Key research questions for future study are proposed: performance optimization, data set improvement and the need for research on real-time performance on edge devices. © 2023 IEEE.

关键词： deep learning edge-devices neural network object detection railway safety self-driving transport systems

来源：评论

学校读者我要写书评

暂无评论

Skeleton-Based Volumetric Parameterizations for Lattice Structures

引用

computer Modeling in engineering & sciences 2023年第4期135卷 687-709页

作者： Long Chen Shuxun Liang Nan Yan Xiangqian Yang Baotong Li School of Mechanical Engineering University of Shanghai for Science and TechnologyShanghai200093China School of Optical-Electrical and Computer Engineering University of Shanghai for Science and TechnologyShanghai200093China Key Laboratory of EducationMinistry for Modern Design&Rotor-Bearing System Xi’an Jiaotong UniversityXi’an710049China

Lattice structures with excellent physical properties have attracted great research *** this paper,a novel volume parametric modeling method based on the skeleton model is proposed for the construction of threedimensional lattice *** skeleton model is divided into three types of *** the corresponding algorithms are utilized to construct diverse types of volume parametric *** unit-cell is assembled with distinct nodes according to the geometric *** final lattice structure is created by the periodic arrangement of *** different types of volume parametric lattice structures are constructed to prove the stability and applicability of the proposed *** quality is assessed in terms of the value of the Jacobian ***,the volume parametric lattice structures are tested with the isogeometric analysis to verify the feasibility of integration of modeling and simulation.

关键词： Lattice structure volumetric parameterization skeleton model node modeling

来源：评论

学校读者我要写书评

暂无评论

Investigation of AI with OpenCV-Python for Detecting Diabetes

Investigation of AI with OpenCV-Python for Detecting Diabete...

引用

Conference of Recent Trends and Applications of Soft Computing in engineering, RTASCE 2024

作者： Mutar, Hussein A. Yalwi, Ilyas Khudhair Mezaal, Yaqeen S. Th. Salim ALRikabi, Haider Alaidi, Abdul Hadi M. Niama ALRubeei, Ibtihal R. Magdy, Ahmed Electrical Engineering Department College of Engineering Wasit University Wasit Iraq College of Computer Science and Information Technology Wasit University Wasit Iraq College of Engineering University of Information Technology and Communications Baghdad Iraq Electrical Engineering Department Faculty of Engineering Suez Canal University Ismailia Egypt

ISBN: (纸本)9783031828805

Plenty of different diagnosing methods have been extensively utilized to identify diabetes accurately;however, an absolutely precise and definitive diagnosis has not yet been attained. Within the context of this research, our primary objective is to leverage the cutting-edge capabilities of Artificial Intelligence (AI) coupled with OpenCV to assist medical professionals, thereby minimizing the rate of misdiagnosis. Specifically, we harness the power of AI to effectively classify diverse images portraying patients afflicted with Non-Proliferative Diabetic Retinopathy (NPDR), with the ultimate goal of determining the severity level at which they are situated. In conjunction with this, Python, with OpenCV, has a crucial role in extracting pertinent features that may be discernible within the given images. Our methodology involves the collection and preprocessing of the Eye PACS Dataset on Kaggle, followed by feature extraction and model training using some machine learning algorithms, including convolutional Neural Network CNN, decision trees, support vector machines SVM, and neural networks. OpenCV is utilized for image processing tasks, enhancing the feature extraction process, certain individual features present within the images are precluded from being considered as contributing factors in the classification process. Some of these features include but not limited to, the measurement of the luminous blobs which are present in the image, the specific area of existence of red lesion. The evaluation of the models includes the analysis of their performance based on the goal of the prediction task, specifically decimal-based accuracy, precision, recall, and F1-score. This research employs a wide-ranging dataset embracing low, medium and high level of image severity. At last, after lots of simulation, it came to a conclusion that the CNN increases its level of classification accuracy up to 98%. These findings show that the proposed application of AI improves the accuracy

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Toward Digital-Twin-Assisted Data Acquisition in Underwater Acoustic Sensor Networks

引用

Procedia computer science 2025年 257卷 241-248页

作者： Ivan Spajić Lars Michael Kristensen Volker Stolz Department of Computer Science Electrical Engineering and Mathematical Sciences Western Norway University of Applied Sciences

Data transfer from underwater acoustic sensor networks (UASNs) to cloud services is challenging due to the severe bandwidth constraints of acoustic communication and energy consumption constraints of battery-powered sensor devices. To mitigate this problem, various forms of time series compression algorithms, both lossless and lossy, have been proposed in the literature. These proposals, however, focus on large time series whose in-memory buffering is not feasible in a UASN context. Furthermore, especially in oceanographic data acquisition, buffering large time series sacrifices the Age of Information. To address this gap, we evaluate a modern lossy compression algorithm, Mix-Piece, on small-sized time series. Motivated by our findings, we have developed the Custom-Piece algorithm, an adaptation of Mix-Piece that yields higher data compression at the expense of increased execution times. Our experimental evaluation of the Mix-Piece/Custom-Piece algorithms on real-world oceanographic data shows that compression ratios are highly dependent on the configuration of the algorithms due to the emerging characteristics of the underlying data sets. To facilitate practical use of the Mix-Piece/Custom-Piece algorithms, we outline how a digital twin may dynamically run simulations on available past data to support end-users in developing sensor configurations according to data acquisition requirements.

关键词： emerging networking wireless sensor networks applications optimization for effective communications lossy compression

来源：评论

学校读者我要写书评

暂无评论

High-quality distractor generation framework for English reading comprehension 5

High-quality distractor generation framework for English rea...

引用

5th International Academic Exchange Conference on science and Technology Innovation, IAECST 2023

作者： Guo, Zhengrong Wang, Hui Guo, Gongde Fujian Normal University College of Computer and Cyberspace Security Fujian Fuzhou China Queen's University Belfast School of Electronics Electrical Engineering and Computer Science Belfast United Kingdom

ISBN: (纸本)9798350357738

Distractors are widely used in tasks such as reading comprehension and subject education. Generating high-quality distractors automatically poses a challenging task. Existing frameworks for generating distractors in the context of English reading comprehension primarily rely on training deep neural networks with given passages, questions, and corresponding answers. However, in more difficult questions, these frameworks often produce distractors with low levels of distraction, limiting their practical applications. To address this issue, we propose a framework called 'Generating Distractors Framework with High Distraction' (GDF-HD) that automatically generates high-distraction distractors. The GDF-HD framework categorizes common English reading comprehension questions into three types: detail questions, summary questions, and inference questions. Different question types utilize distinct approaches for generating distractors, and the framework enhances the distraction of these distractors from both syntactic and semantic perspectives. To validate the feasibility and effectiveness of our framework, we conduct experiments and evaluations using the RACE dataset. Additionally, we employ manual assessments to evaluate the quality and distraction levels of the generated distractors. The experimental results demonstrate that the GDF-HD framework is capable of producing high-quality distractors and significantly increasing their distraction levels. © 2023 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A Framework for Cyber-Secure Monitoring and Safe Operation of Solar PV Microgrids

A Framework for Cyber-Secure Monitoring and Safe Operation o...

引用

2024 IEEE Energy Conversion Congress and Exposition, ECCE 2024

作者： Kim, Jaewon Ilic, Marija Xie, Le Massachusetts Institute of Technology Laboratory for Information & Decision Systems CambridgeMA02139 United States Massachusetts Institute of Technology Department of Electrical Engineering and Computer Science CambridgeMA02139 United States Texas A&m University Department of Electrical & Computer Engineering College StationTX77843 United States

ISBN: (纸本)9798350376067

In this paper, we introduce a systematic design of an end-to-end cyber-secure monitoring and safe operation framework for solar photovoltaic (PV)-rich microgrids, by focusing on the use of on-line attack detector for defending against potential cyber-physical attacks and sensor measurement data processing for operational safety. The proposed approach is based on: 1) identifying component models using their input and output measurements;2) dynamic watermarking (DW) methodology for on-line cyber-attack detection and its timing;and 3) an adaptive event-driven safe shutdown procedure after attack detection. It is shown how these three components interactive steps jointly to ensure safe operation under both normal operational scenarios and compromised operational scenarios with some malicious sensors caused by cyber-attacks on solar PV microgrids. Through this on-line integration, the proposed framework dynamically adapts to varying solar irradiance, load demands, operating conditions, and potential cyber-physical attacks. This forms a cyber-physical system which can pro-actively detect and mitigate potential cyber-physical attacks on solar PV microgrids. We describe its proof-of-concept implementation using real-world industrial solar farm data provided by the CenterPoint Energy. This study contributes to enhancing the cyber-security and safe operation of solar PVrich power systems, offering a scalable solution to other types of emerging renewable-rich energy distribution systems. © 2024 IEEE.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

Improving Accuracy of Object Detection in Autonomous Drones with Convolutional Neural Networks

Improving Accuracy of Object Detection in Autonomous Drones ...

引用

2025 IEEE International Conference on Computational, Communication and Information Technology, ICCCIT 2025

作者： Goyal, Himanshu Rai Shrivastava, Anurag Dixit, Krishna Kant Nagpal, Amandeep Reddy, B. Ravali Kumar, Jaysheel Graphic Era Deemed to Be University Department of Computer Science & Engineering Dehradun India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Tamilnadu Chennai India GLA Universit Department of Electrical Engineering Mathura India Lovely Professional University Phagwara India MLR Institute of Technology Department of Computer Science and Engineering Telangana Hyderabad India New Horizon College of Engineering Bangalore India

ISBN: (纸本)9798331512965

Increasing use of autonomous drones in such areas as agriculture, disaster response and surveillance means that an effective and precise method of object recognition is becoming more important. In this study, we use Convolutional Neural Networks (CNNs) to bring additional precision to autonomous drone object detecting systems. While conventional machine learning approaches fail miserably in having complicated contexts and real time processing, CNN have sucessfully handles visual identification task. Based on state of the art methods being data augmentation and transfer learning, plus being real time with data augmentation of the raw data on the edge processor, this research introduces a convolutional neural network (CNN) model which has been fine-tuned and can be used for drones. The model is trained and tested on a big dataset of aerial photos acquired by drones. The item classification on this dataset varies from lighting conditions, to weather variables, etc. A considerable increase in the object detection accuracy is found from experimental findings in reducing false positives and improving resilience in dynamic contexts. Furthermore, the suggested model allows for detection with little latency, making it a good model for drones that must be deployed in real-time. Not only does this work contribute to bolstering rapidly growing autonomous drone navigation, it has great promise in environmental monitoring, SAR, and precision agriculture, and other applications. The components of the models are being researched on how scalable they are and how do they scale up on hardware that has limited resources. © 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

Enhanced Adaptive Brain-computer Interface Approach for Intelligent Assistance to Disabled Peoples

引用

computer Systems science & engineering 2023年第8期46卷 1355-1369页

作者： Ali Usman Javed Ferzund Ahmad Shaf Muhammad Aamir Samar Alqhtani Khlood M.Mehdar Hanan Talal Halawani Hassan A.Alshamrani Abdullah A.Asiri Muhammad Irfan Department of Computer Science COMSATS University IslamabadSahiwal CampusSahiwal57000Pakistan Department of Information Systems College of Computer Science and Information SystemsNajran UniversityNajran61441Saudi Arabia Anatomy Department Medicine CollegeNajran UniversityNajran61441Saudi Arabia Computer Science Department College of Computer Science and Information SystemsNajran UniversityNajran61441Saudi Arabia Radiological Sciences Department College of Applied Medical Sciences and Information SystemsNajran UniversityNajran61441Kingdom of Saudi Arabia Electrical Engineering Department College of EngineeringNajran UniversityNajran61441Saudi Arabia

Assistive devices for disabled people with the help of Brain-computer Interaction(BCI)technology are becoming vital bio-medical *** with physical disabilities need some assistive devices to perform their daily *** these devices,higher latency factors need to be addressed ***,the main goal of this research is to implement a real-time BCI architecture with minimum latency for command *** proposed architecture is capable to communicate between different modules of the system by adopting an automotive,intelligent data processing and classification ***-sky mind wave device has been used to transfer the data to our implemented server for command ***-Net Convolutional Neural Network(TN-CNN)architecture has been proposed to recognize the brain signals and classify them into six primary mental states for data *** collection and processing are the responsibility of the central integrated server for system load *** of implemented architecture and deep learning model shows excellent *** proposed system integrity level was the minimum data loss and the accurate commands processing *** training and testing results are 99%and 93%for custom model implementation based on *** proposed real-time architecture is capable of intelligent data processing unit with fewer errors,and it will benefit assistive devices working on the local server and cloud server.

关键词： Disable person electroencephalogram convolutional neural network brain signal classification

来源：评论

学校读者我要写书评

暂无评论

Guest Editorial: Special Issue on Knowledge-Infused Learning for Computational Social Systems

引用

IEEE Transactions on Computational Social Systems 2024年第3期11卷 3045-3048页

作者： Nguyen, Tu Piuri, Vincenzo Rodrigues, Joel Qi, Lianyong Mumtaz, Shahid Lee, Warren Huang-Chen Kennesaw State University Department of Computer Science MariettaGA30060 United States University of Milan MI Milano20122 Italy Piauí Teresina64049-550 Brazil Qufu Normal University School of Computer Science Shandong273165 China Instituto de Telecomunicações Aveiro3810-164 Portugal National Chung Cheng University Department of Communications Engineering & Electrical Engineering Chiayi County621301 Taiwan

This special issue comprises 12 articles, showcasing the latest advances in computational social systems research.

关键词： Special issues and sections Computational cultural modeling Social factors Learning systems Knowledge based systems Behavioral sciences Economics Social factors

来源：评论

学校读者我要写书评

暂无评论

SLA$^{{\text{2}}}$2P: Self-Supervised Anomaly Detection With Adversarial Perturbation

引用

IEEE Transactions on Knowledge and Data engineering 2024年第12期36卷 9282-9293页

作者： Yizhou Wang Can Qin Rongzhe Wei Yi Xu Yue Bai Yun Fu Department of Electrical and Computer Engineering Northeastern University Boston MA USA Georgia Institute of Technology Atlanta GA USA Department of Electrical and Computer Engineering Khoury College of Computer Science Northeastern University Boston MA USA

Anomaly detection is a foundational yet difficult problem in machine learning. In this work, we propose a new and effective framework, dubbed as SLA 2 P, for unsupervised anomaly detection. Following the extraction of delegate embeddings from raw data, we implement random projections on the features and consider features transformed by disparate projections as being associated with separate pseudo-classes. We then train a neural network for classification on these transformed features to conduct self-supervised learning. Subsequently, we introduce adversarial disturbances to the modified attributes, and we develop anomaly scores built on the classifier's predictive uncertainties concerning these disrupted features. Our approach is motivated by the fact that as anomalies are relatively rare and decentralized, 1) the training of the pseudo-label classifier concentrates more on acquiring the semantic knowledge of regular data instead of anomalous data; 2) the altered attributes of the normal data exhibit greater resilience to disturbances compared to those of the anomalous data. Therefore, the disrupted modified attributes of anomalies can not be well classified and correspondingly tend to attain lesser anomaly scores. The results of experiments on various benchmark datasets for images, text, and inherently tabular data demonstrate that SLA 2 P achieves state-of-the-art performance consistently.

关键词： Feature extraction Anomaly detection Perturbation methods Task analysis Training Uncertainty Unsupervised learning

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：