检索结果-内蒙古大学图书馆

13th International Symposium on Image and Signal Processing and Analysis, ISPA 2023

作者： Litsas, Anastasis Fraggelakis, Fotis Tsibidis, George D. Stratakis, Emmanuel Pantazis, Yannis University of Crete Computer Science Department Heraklion Crete Greece Institute of Electronic Structure and Laser Foundation for Research and Technology - Hellas Heraklion Crete Greece Institute of Applied and Computational Mathematics Foundation for Research and Technology - Hellas Heraklion Crete Greece

ISBN: (纸本)9798350315363

In this paper, we explore the potential of deep learning techniques in the field of ultra-fast laser processing. More specifically, we trained convolutional neural networks on an in-house dataset with the aim of predicting the laser parameters from images which capture the morphological characteristics of the material surface after being laser fabricated. There are several challenges related with the collected dataset stemming from stochastic variations of the material and the laser, the sampling scheme and the overall low sample size. Therefore, to further test our models we additionally construct a synthetic dataset. The results on the synthetic dataset are almost perfect showing that the proposed predictive models have the capacity to learn the assigned tasks. As expected, the predictive performance decreases when the real dataset is utilized. Nevertheless, we show that both the accuracy in the classification task and the mean square error in the majority of the regression tasks are satisfactory (e.g., classification accuracy drops from 99.9% to 94.8%). © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Classifying Activities of Electrical Line Workers Based on Deep Learning Approaches Using Wrist-Worn Sensor 20

Classifying Activities of Electrical Line Workers Based on D...

引用

20th International Joint Conference on computer science and Software Engineering, JCSSE 2023

作者： Mekruksavanich, Sakorn Jitpattanakul, Anuchit School of Information and Communication Technology University of Phayao Department of Computer Engineering Thailand King Mongkut's University of Technology North Bangkok Intelligent and Nonlinear Dynamic Innovations Research Center Faculty of Applied Science Department of Mathematics Bangkok Thailand

ISBN: (纸本)9798350300505

The field o f human activity recognition (HAR) is a priority for cutting-edge study because of its potential to revolutionize the way we understand and improve our everyday lives. A large variety of ordinary, everyday tasks has been classified using H AR. Nevertheless, inc ontrast to basic human actions, the increasing demands of numerous real-world applications have attracted the interest of the HAR area of study. Electrical line workers (ELWs) face a variety of challenges, including long hours, working in isolated locations, and performing particularly hazardous tasks. Wearable sensor-based HAR allows for unobtrusive tracking of ELW efficiency and security. This study explores deep learning strategies for automatically categorizing ELWs' complicated actions through sensor data collected through a wrist-worn device. We propose ResNeXt, a deep residual neural network, and evaluate it with other deep learning networks for their ability to categorize ELW activities effectively. We employ a publicly available benchmark dataset that includes 10 ELW tasks. The results of the experiment demonstrate that the proposed ResNeXt achieved the highest accuracy (98.74%) and F1-score (98.81%) compared to other deep learning networks studied. © 2023 IEEE.

关键词： Wearable sensors

来源：评论

学校读者我要写书评

暂无评论

ARWeather: Weather Forecasting and Visualization using Augmented Reality

ARWeather: Weather Forecasting and Visualization using Augme...

引用

Intelligent Systems for Communication, IoT and Security (ICISCoIS), International Conference on

作者： R Manimegalai S Arawind G V Sri Rajiv Jegan B Gomathi Department of Computer Science and Engineering PSG Institute of Technology and Applied Research Coimbatore India

Weather Forecasting is the application of AI to predict the state of the atmosphere for a given location. Earlier, weather forecasting methods usually relied on observed patterns of events. Our ancestors predicted the next day weather based on the happenings of the previous day evening. However, those intuitive methods and predictions are not reliable. This paper depicts the design and implementation of an application for weather forecasting and visualization using Augmented Reality (AR), which can forecast climatic conditions, namely, such as rain, snow, sun, wind, and hail. This work deals with various real-world weather types and how they could be simulated using a mobile augmented reality system. Users can move freely inside the real world without limitations, experiencing the developed augmented objects. A visual change of the augmented reality weather conditions can be used as a supplement to train the simulations for search and rescue teams during catastrophic disasters.

关键词： Visualization Rain Snow Atmosphere Security Reliability Wind forecasting

来源：评论

学校读者我要写书评

暂无评论

Breast Cancer Histopathology Image Classification Using Frequency Attention Convolution Network 9th

Breast Cancer Histopathology Image Classification Using Freq...

引用

19th International Conference on Advanced Data Mining and Applications, ADMA 2023

作者： Lu, Ruidong Sun, Qiule Ding, Xueyan Zhang, Jianxin School of Computer Science and Engineering Dalian Minzu University Dalian China School of Information and Communication Engineering Dalian University of Technology Dalian China SEAC Key Laboratory of Big Data Applied Technology Dalian Minzu University Dalian China

ISBN: (纸本)9783031466632

The existing deep learning works mainly capture breast cancer histopathology image features in the spatial domain, and they rarely consider the frequency domain feature representation of histopathology images. According to the classical digital signal processing theory, frequency domain features may outperform spatial domain features in analyzing texture images. Motivated by this, we attempt to mine frequency domain features for the breast cancer histopathology image classification application, and further propose a novel frequency-attention convolutional network called SeFFT-Net by combining the Fourier transform with the channel attention mechanism. The core of SeFFT-Net consists of a newly constructed frequency-based squeeze and excitation (SeFFT) module, which first performs Fourier transform with residual construction to capture deep features in the frequency domain of histopathology images, followed by a squeeze-and-excitation attention operator to further enhance important frequency features. We extensively evaluate the proposed SeFFT-Net model on the public BreakHis breast cancer histopathology dataset, and it achieves the optimal image-level and patient-level classification accuracy of 98.67% and 98.16%, respectively. Meanwhile, ablation studies also well demonstrate the effectiveness of introducing frequency transforms for this medical image application. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Integrating Object Detection and Wide Area Network Infrastructure for Sustainable Ferry Operation

Integrating Object Detection and Wide Area Network Infrastru...

引用

IEEE International Workshop on Imaging Systems and Techniques (IST)

作者： Arslan Musaddiq David Mozart Neda Maleki Tobias Olsson Fredrik Ahlgren Department of Computer Science and Media Technology Applied IoT Lab Linnaeus University Sweden

Low-Power Wide-Area Network (LPWAN) technologies offer new opportunities for data collection, transmission, and decision-making optimization. Similarly, a wide range of use cases of computer vision and object detection algorithms can be found across different industries. This paper presents a case study focusing on the utilization of LPWAN infrastructure, specifically the Helium network, coupled with computer vision and object detection algorithms, to optimize passenger ferry operation. The passenger ferry called M/S Dessi operates between Kalmar and Färjestaden in Sweden during the summer season. By implementing an Edge-computing solution, real-time data collection and communication are achieved, enabling accurate measurement of passenger flow. This approach is superior to traditional methods of collecting passenger data, such as manual counting or CCTV surveillance. Real-time passenger data is invaluable for traffic planning, crowd prediction, revenue enhancement, and speed and fuel optimization. The utilization of the Helium network ensures reliable and long-distance data transmission, extending the system’s applicability to multiple ferries and distant locations. The proposed approach can be utilized to integrate passenger ferries that operate in close proximity to urban areas into society’s digital transformation efforts. This study highlights the potential of LPWAN, computer vision, and object detection in enhancing passenger ferry operations, contributing to enhanced efficiency and sustainability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Robust and Reliable Liveness Detection Models for Facial Recognition Systems 20

Robust and Reliable Liveness Detection Models for Facial Rec...

引用

20th International Conference on Frontiers of Information technology, FIT 2023

作者： Anjum, Haris Arshad, Usama Ali, Raja Hashim Ul Abideen, Zain Shah, Muhammad Huzaifa Khan, Talha Ali Ijaz, Ali Zeeshan Siddique, Abu Bakar Imad, Muhammad Gik Institute of Engg. Sciences & Technology Faculty of Computer Science & Engineering Topi Pakistan University of Europe for Applied Sciences Dept. of Technology & Software Engineering Berlin Germany BCMaterials Basque Center for Materials Applications & Nanostructure Spain

ISBN: (纸本)9798350395785

Facial Liveness Detection is instrumental in combating fraudulent practices and identity theft by differentiating genuine faces from forgeries. Given that facial recognition is now an integral part of many sectors like banking and law enforcement, liveness detection has become a vital aspect for maintaining the trustworthiness of these applications. Unfortunately, the utility of prevalent facial liveness detection models is constrained by their lack of generalizability to novel, unseen data, which presents a substantial impediment to practical applications. To mitigate this issue, our research endeavored to construct a reliable and precise facial liveness detection model that can effectively navigate this challenge and ensure consistent performance across diverse datasets. The devised model exhibited excellent accuracy, which attests to its robustness. This research underscores the advantages of employing deep learning methods such as Convolutional Neural Networks (CNNs) as they significantly enhance the model's accuracy. We intend for our findings to drive further research and progress in this critical field, by laying the groundwork for future work that integrates multiple liveness detection methods and collects more varied training data to develop an even more resilient and efficient system. © 2023 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

DeltaBin: An Efficient Binary Data Format for Low Power IoT Devices

DeltaBin: An Efficient Binary Data Format for Low Power IoT ...

引用

International Conference on computer, Information and Telecommunication Systems (CITS)

作者： Neda Maleki Arslan Musaddiq David Mozart Tobias Olsson Mustafa Omareen Fredrik Ahlgren Department of Computer Science and Media Technology Applied IoT Lab Linnaeus University Sweden

The Internet of Things (IoT) notion is quickly influencing t he architectures of data-driven systems d ue to the ever-increasing rapid technological progress in all sectors. The IoT involves the collection and exchange of data from a large number of interconnected devices or sensors. The collected data is structured and transmitted in a variety of different data formats such as JSON, CBOR, BSON, or simply a binary format. The data format used by an IoT device can have a significant i mpact on t he efficiency of its data transmission. In general, using a more compact and efficient data format can help to reduce t he amount of data that needs to be transmitted, which can improve the overall speed and performance of the device. For example, using a binary data format rather than a text-based format can often result in smaller data sizes and faster transmission times. Similarly, using a binary format in a more compressed form can further help to reduce the size of the data being transmitted, which can further improve the efficiency of the transmission. In this paper, we propose Delta Binary (i.e., DeltaBin) to reduce the binary data format by transmitting only changed data. We assess DeltaBin using a real IoT deployment scenario.

关键词：

来源：评论

学校读者我要写书评

暂无评论

COVID-19 Infection Detection in X-Ray Images Using Enhanced Image Segmentation and Machine Learning Models 25

COVID-19 Infection Detection in X-Ray Images Using Enhanced ...

引用

25th International Arab Conference on Information technology, ACIT 2024

作者： Nahar, Khalid M.O. Ebrahim Megdad, Mohammad Al Mamlook, Rabia Emhamed Aljaidi, Mohammad Nahar, Besan K.M. Nahar, Mohammad K. M. Anbarkhan, Samar Hussni Khafajeh, Hayel Amer, Waleed Arab Open University Faculty of Computer Studies P.O. Box 84901 Riyadh11681 Saudi Arabia Yarmouk University Computer Science Department Irbid21163 Jordan University of Zawia Dept. of Mechanical and Industrial Engineering Zawia Libya Zarqa University Faculty of Information Technology Department of Computer Science Zarqa13110 Jordan University of Business and Technology College of Engineering Jeddah21448 Saudi Arabia Yarmouk University Faculty of Medicine Irbid Jordan Jordan University of Science and Technology Faculty of Applied Medical Science Irbid21163 Jordan Northern Border University Information Systems Department Rafha76322 Saudi Arabia Zarqa University Faculty of Information Technology Department of Artificial Intelligence Zarqa13110 Jordan Zarqa University Faculty of Information Technology Department of Cybersecurity Zarqa13110 Jordan

ISBN: (纸本)9798331540012

The COVID-19 pandemic has shown a significant challenge to healthcare associations worldwide demanding the progress of reliable diagnostic techniques. Chest X-ray imaging is an easily available and cost-effective tool for evaluating lung defects combined with COVID-19. This study aims to introduce a novel COVID-19 infection detection and recognition method in X-ray images through image segmentation. By employing machine learning (ML) methods, particularly CNN-based U-Net architectures, the lung sections are accurately segmented, and infection sections are classified based on specific radiological features. The model was trained on a large dataset of annotated X-ray images assisting it to distinguish between healthy lungs, COVID-19-affected lungs, and other lung pathologies. The proposed method apprehended a segmentation accuracy of 96.6% with a Dice coefficient of 94.36% offering a potential solution for mechanical detection and 98.4% with KNN analysis of COVID-19 infection in chest X-rays in that way assisting radiologists in making faster and more accurate diagnoses. © 2024 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Influence of agglomerations on magnetic properties of polymer matrices filled with magnetic nanoparticles

引用

Materials Today: Proceedings 2022年 67卷 792-796页

作者： Blachowicz, Tomasz Grzybowski, Jacek Ehrmann, Andrea Institute of Physics – Centre for Science and Education Silesian University of Technology Gliwice 44-100 Poland Faculty of Automatic Control Electronics and Computer Science Silesian University of Technology Gliwice 44-100 Poland Faculty of Engineering and Mathematics Bielefeld University of Applied Sciences Bielefeld 33619 Germany

Magnetic nanoparticles can be embedded in electrospun nanofibers and other polymeric matrices to prepare magnetic composites with defined magnetic and mechanical properties. Metal-oxide nanoparticles, such as magnetite or nickel-ferrite, are of special interest since they do not need a coating to avoid oxidation. Like other nanoparticles, these metal-oxide nanoparticles tend to form agglomerations, in this way modifying the magnetic properties of the composites. After studying this effect for the magnetic elements Co, Fe, Ni as well as permalloy (Py) in a previous study, defining a new method to quantify the nanoparticle distribution in a polymer, here we concentrate on the influence of agglomerations on the magnetic properties of metal-oxide nanoparticles with different diameters in non-magnetic matrices. © 2022

关键词： Magnetite

来源：评论

学校读者我要写书评

暂无评论

Bridging the Climate Gap: Multimodel Framework With Explainable Decision-Making for IOD and ENSO Forecasting

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第3期6卷 661-675页

作者： Tiwari, Harshit Kumar, Prashant Prasad, Ramakant Saha, Kamlesh Kumar Singh, Anurag Cherifi, Hocine Rajni National Institute of Technology Delhi Department of Applied Sciences New Delhi110036 India Centre Tecnológic de Telecomunicacions de Catalunya Barcelona08860 Spain National Institute of Technology Delhi Department of Computer Science and Engineering New Delhi110036 India University of Burgundy ICB UMR 6303 CNRS Dijon21078 France O P Jindal Global University Jindal Global Business School Haryana Sonipat131001 India

Accurate forecasting of the Indian Ocean Dipole (IOD) and El- Niño-Southern Oscillation (NINO3.4) is crucial for understanding regional weather patterns in the Indian subcontinent. Addressing the challenges associated with IOD and NINO3.4 prediction, a robust multitask autoregressive deep learning (DL) model is introduced for precise forecasting of these indices and key grid projections sea surface temperature (SST), surface-level pressure gradient (SLG), and horizontal wind velocity (U-Comp) over a short to mid-term window (20 months). Utilizing spatiotemporal (SST, SLG, U-Comp) and temporal (IOD and NINO3.4) modalities, the proposed model predicts future IOD and NINO3.4, as well as SST, SLG, and U-Comp, in an autoregressive scheme. The multitask learning component regularizes the model, effectively capturing the evolving dynamics of global patterns conditioned on IOD and NINO3.4. The comprehensive evaluation explores various task settings, including a duo-setting that predicts IOD or NINO3.4 with spatiotemporal information, showcasing notable proficiency. In a multitask environment, where both temporal IOD, NINO3.4, and spatiotemporal SST, SLG, U-Comp are predicted, the model successfully forecasts IOD and NINO3.4 indices alongside grid projections with modest accuracy in root mean square error (RMSE). To enhance the model's interpretability regarding spatiotemporal dynamics, a tailored version of Grad-CAM is employed, providing critical insights for climate prediction. This research advances climate prediction models, offering a comprehensive framework with significant implications for informed decision-making in the Indian subcontinent's climatic context. © 2024 IEEE.

关键词： Deep 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：