检索结果-内蒙古大学图书馆

2025 International Conference on Artificial Intelligence and Data engineering, AIDE 2025

作者： Ruparelia, Vidhi Shah, Sneh Pathak, Lakshin Gupta, Rajesh Tanwar, Sudeep Sawhney, Sahil Gupta, Ankur Nirma University Inst. of Technology Department of Electronics and Communication Engineering Ahmedabad India Nirma University Institute of Technology Department of Computer Science and Engineering Ahmedabad India Model Institute of Engineering & Technology Department of Computer Science & Engineering Jammu & Kashmir India

ISBN: (纸本)9798331527518

The application of Unmanned Aerial Vehicles (UAVs) for securely delivering essential items during extreme conditions includes numerous challenges, particularly in ensuring identification of potential threats. To solve this challenge, we propose a strong framework that makes use of Boosting algorithms, with a particular focus on XGBoost to enhance attack classification in UAV-based delivery systems. The XGBoost model achieved an accuracy of 93%, a precision of 0.9312, a recall of 0.9311, and an F1 score of 0.9283 , which makes it a highly suitable model for security of UAVs. Explainable AI (XAI) is used to further enhance classification including SHAP and LIME to identify the most influential features, such as the barometer and battery levels. Our framework provides a comprehensive solution for secure UAV-based deliveries. The experimental results proves the effectiveness of the proposed model which shows its potential for real-life applications. © 2025 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Enhancing Hyperspectral Image Compression Through Stacked Autoencoder Approach 6

Enhancing Hyperspectral Image Compression Through Stacked Au...

引用

6th International Conference on Electrical engineering and Information and Communication technology, ICEEICT 2024

作者： Afrin, Afsana Haque, Md. Rakibul Mamun, Md. Al Inst. of Information and Communication Technology Rajshahi University of Engineering Technology Rajshahi6204 Bangladesh Rajshahi University of Engineering & Technology Dept. of Computer Science & Engineering Rajshahi6204 Bangladesh

ISBN: (纸本)9798350385779

Hyperspectral Image (HSI) consisting of numerous high-resolution spectral bands creates challenges of the high dimensionality problem in HSI classification which hinder real-life applications despite their abundance of information. We present a lossy compression approach using stacked autoencoders to reduce high dimensionality problem in this paper. The pro-posed method utilizes stacked autoencoders to extract features from HSIs, allowing compression and subsequent reconstruction. The study demonstrates improved Peak Signal-to-Noise Ratio (PSNR) of 70.43, 60.87 and 61.36 on three distinct HSI datasets-Salinas, Botswana, and KSC respectively compared to previous autoencoder-based compression method. Additionally, the impact of compression on classification accuracy is assessed using a 3D-2D CNN model, achieving an average accuracy of 99 % across the datasets. Improved compression along with high classification accuracy shows our proposed method's usefulness. © 2024 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Decoding the Skin with AI: A Review of Cutting-Edge Technologies and Applications 2

Decoding the Skin with AI: A Review of Cutting-Edge Technolo...

引用

2nd International Conference on Disruptive Technologies, ICDT 2024

作者： Kumari, Sejal Umrao, Sandhya Kushwaha, Dileep Noida Inst. of Engg. and Technology Computer Science & Engineering Greater Noida India Greater Noida India

ISBN: (纸本)9798350371055

The skin of humans can tell stories through its textures and colors, providing insights into both health and disease. Dermatologists have been interpreting these stories for years, using their expertise to diagnose and treat conditions. They have an ally in this pursuit: artificial intelligence and machine learning (AI/ML). In this review, we will delve into the meeting point of AI/ML and dermatology, exploring the applications, challenges and the promising future. Looking ahead, we can imagine a future where emerging technologies drive advancements. In this future, AI will work hand in hand with dermatologists in procedures guided by images, speed up the process of discovering drugs, and empower individuals to keep track of their skin health using AI-powered sensors. This goes beyond upgrading technology. It signifies a revolution in how we perceive and approach skin health. It promises a future where early detection, personalized treatment and preventive measures become the standard. Join us on our journey at the intersection of skin and technology as we witness the beginning of an era in dermatology. With AI shedding light on the secrets of our skin we pave the way for a healthier tomorrow. © 2024 IEEE.

关键词： Artificial intelligence Derma-tology Diagnosis Machine learning Personalized medicine Skin cancer Treatment Wearable sensors

来源：评论

学校读者我要写书评

暂无评论

BER Analysis of Cross-QAM Uncoded Space-Time Labeling Diversity with Three Transmit Antennas in Nakagami-m Fading Channels 22

BER Analysis of Cross-QAM Uncoded Space-Time Labeling Divers...

引用

22nd Annual Wireless Telecommunications Symposium (WTS) - Global Wireless Communications - Now and in the Future

作者： Ayanda, Dauda Costa, Marcello Da Silva, Bruno S. Mate, Dercio Solwa, Shaheen Sidia Inst. of Science & Technology Manaus Brazil School of Engineering University of KwaZulu-Natal Durban South Africa

ISBN: (纸本)9781665490924

This paper presents a new cross quadrature amplitude modulation (XQAM) technique for three transmit antennas uncoded space-time labeling diversity (USTLD) over Nakagamim fading channels. A heuristic algorithm is employed in designing the second and third optimized mapper for 32-XQAM and 128-XQAM. The study exploits an approximate analytical expression to derive bit error rate (BER). The average BER is obtained by applying probability density function and moment generating functions. Monte carlo simulation results show a tight fit with the theoretical approximate analysis in the high signal-to-noise ratio (SNR). The BER performance comparison of XQAM USTLD is carried out based on rate one with the existing two transmit antennas XQAM USTLD for link reliability which shows significant improvement. In addition, frame error rate (FER) performance analysis is carried out for real-world wireless communication where the degradation of error performance due to dropped frames is the same for one or many bit errors within a frame. Finally, XQAM transmission performance evaluation is carried out with rectangular QAM (RQAM), amplitude phase-shift scheme (APSK) and phase-shift scheme (PSK) transmission schemes.

关键词： Cross QAM heuristic algorithm labeling mapper Nakagami-m fading channels wireless communications

来源：评论

学校读者我要写书评

暂无评论

Fluid and kinetic modeling of runaway electron generation from tritium beta decay and Compton scattering 50

Fluid and kinetic modeling of runaway electron generation fr...

引用

50th EPS Conference on Plasma Physics, EPS 2024

作者： Ekmark, I. Hoppe, M. Fülöp, T. Tinguely, R.A. Sweeney, R. Jansson, P. Antonsson, L. Vallhagen, O. Pusztai, I. Department of Physics Chalmers University of Technology Göteborg Sweden Department of Electrical Engineering KTH Royal Inst. Technology Stockholm Sweden Plasma Science and Fusion Center Massachusetts Inst. Technology CambridgeMA United States Commonwealth Fusion Systems DevensMA United States Department of Computer Science and Engineering Chalmers Univ. Technology Göteborg Sweden

ISBN: (纸本)9798331305239

We derived kinetic sources of energetic electrons generated by tritium beta decay and Compton scattering and compared them to the corresponding fluid RE generation rates [2]. In the SPARC example considered, using kinetic (as opposed to fluid) sources yielded 25 % higher RE current. The reason for this is that energetic electrons generated by the kinetic sources with p c can run away since collisions for these electrons are kinetically resolved. © 2024 50th EPS Conference on Plasma Physics, EPS 2024. All rights reserved.

关键词： Compton scattering

来源：评论

学校读者我要写书评

暂无评论

Ion Bombardment-Induced Stress Mechanism for the Formation of Ag Nanotwinned Films on Si Substrates

引用

Journal of Electronic Materials 2024年第5期53卷 2583-2590页

作者： Chuang, Tung-Han Lin, Ang-Ying Chen, Yen-Ting Chen, Yin-Hsuan Yang, Zi-Hong Wu, Po-Ching Institute of Materials Science and Engineering National Taiwan University Taipei106 Taiwan Ag Materials Technology Co. LTD Hsinchu Science Park Hsinchu30078 Taiwan Inst. Optoelectronics Industrial Technology Research Institute Hsinchu Taiwan Taiwan Semiconductor Manufacturing Co. TSMC Hsinchu Science Park Hsinchu30078 Taiwan

Nanotwinned face-centered-cubic (FCC) metals have gained significant attention recently due to their exceptional mechanical and electrical properties. Among all the FCC metals, Ag has the lowest stacking fault energy, which allows twin formation to easily occur. In this study, Ag films with a thickness of 4 µm were deposited on Si (100) substrates pre-coated with Ti adhesion layers by electron beam evaporation. With ion beam assistance during the evaporation process, highly (111)-textured and high-density nanotwinned Ag films with excellent properties were produced. Both x-ray diffraction (XRD) and electron backscatter diffraction (EBSD) analyses indicate that the Ag film possesses a strong (111) preferred orientation. In addition, statistical measurements from transmission electron microscopy (TEM) images show that the average twin spacing in nanotwinned Ag films with a deposition rate of 1.8 nm/s is only 6.1 nm. However, conventional models based on thermodynamics are insufficient to describe the formation of growth twins in an ion beam-assisted deposition system. Therefore, an ion bombardment stress model is introduced in this work. The results of the mechanism of deformation twinning are also discussed. © The Minerals, Metals & Materials Society 2024.

关键词： Ion beams

来源：评论

学校读者我要写书评

暂无评论

How to Construct Pseudorandom Bit Sequences from Mazes by a Method Digging Out Walls

How to Construct Pseudorandom Bit Sequences from Mazes by a ...

引用

2023 International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2023

作者： Miyazaki, Takeru Araki, Shunsuke Uehara, Satoshi Kyushu Inst. of Information Sciences Faculity of Management and Information Sciences Fukuoka Japan Kyushu Inst. of Technology Faculty of Computer Science and Systems Engineering Fukuoka Japan The Univ. of Kitakyushu Faculty of Environmental Engineering Fukuoka Japan

ISBN: (纸本)9798350324174

In this paper, we propose a new pseudorandom bit sequence generator, which is based on a method digging out walls. Although each of these sequences lacks enough randomness, synthesized sequences of them can pass all of the NIST statistical test suite. We also describe a conjectural relation between the number of types on the square mazes and their sizes. © 2023 IEEE.

关键词： Digging Out the Walls Maze Generator Pseudorandom Bit Sequence

来源：评论

学校读者我要写书评

暂无评论

Prediction of Heart Diseases using Nonlinear Techniques and Machine Learning 10

Prediction of Heart Diseases using Nonlinear Techniques and ...

引用

17th INDIACom;2023 10th International Conference on Computing for Sustainable Global Development, INDIACom 2023

作者： Tiwari, Shashi Kant Sinha, Shweta Kaur, Karamjit Singh, Ram Sewak Amity School of Engineering and Technology Amity University Haryana Gurugram India Fairfield Inst. of Mgmt. and Technology New Delhi India School of Electrical and Computing Engineering Adama Science and Technology University Adama Ethiopia

ISBN: (纸本)9789380544472

This study proposes a new method for predicting cardiac diseases using spectral, nonlinear techniques, ranking methods, generalized discriminant analysis (GDA), and classification algorithm as a 1-Norm linear extreme learning machine (1-NLELM). The accessible thirty features from heart rate variability (HRV) data were extracted using spectral techniques and ten features from nonlinear techniques. For the classification model of coronary and congestive heart diseases, the top ten attributes acquired from ranking methods were applied to suggested GDA + 1-NLELM model. For all of this, the HRV databases of healthy young (YNG) and Elderly (ELY) coronary artery disease (CAD) and congestive heart failure (CHF) were taken from PhysioNet ATM. The experiments were carried on the grouping of record sets as YNG-ELY, CHF-CAD, YNG-CAD, YNG-CHF, ELY-CAD, and ELY-CHF subjects. The numerical results have shown that ranked nonlinear attributes have 100% test accuracy using the proposed GDA + 1-NLELM binary classifier and do not depend on ranking methods. © 2023 Bharati Vidyapeeth, New Delhi.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Chinese Medical Record Entity Recognition Based on Lexicon and Self-attention

Chinese Medical Record Entity Recognition Based on Lexicon a...

引用

2023 IEEE International Conference on Sensors, Electronics and Computer engineering, ICSECE 2023

作者： Wang, Le Zhao, Yahui Cui, Rongyi Jin, Guozhe Wang, Jinxiang Yanbian University Inst. of Intelligent Information Processing Yanji133002 China Yanbian University Computer Science and Technology College of Engineering Yanji China

ISBN: (纸本)9798350313734

Named Entity Recognition (NER) is a pivotal challenge in the field of natural language processing. In the medical field, NER plays a crucial role in identifying medical entities, such as diagnoses and drugs, from electronic medical records. To address the issue of incomplete and inaccurate word recognition in Chinese electronic medical records, we propose a BERT-BiLSTM-CRF model that incorporates both a lexicon and self-attention *** our approach, we first utilize the BERT model for preprocessing to generate word vectors. These vectors capture important semantic information about the words. Next, we employ a BiLSTM network to further capture contextual information from the input sequence. This helps to enhance the understanding of the text's meaning. To reinforce the significance of the sequence information, we introduce a self-attention layer that learns to prioritize relevant contextual details. Subsequently,the extracted features are fed into a CRF model for final training. The CRF layer takes into account the dependencies among the labels and improves the overall sequence labeling accuracy. Given the specialized nature of the medical domain, we integrate a medical lexicon, incorporating external knowledge features into the model. This inclusion enables better recognition of medical terms and enhances performance on medical-related *** extensive experiments on the CCKS2019 dataset, our proposed model demonstrates favorable performance. It get relatively excellent results in identifying medical entities accurately and effectively from Chinese electronic medical records. © 2023 IEEE.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Bayesian optimization of disruption scenarios with fluid-kinetic models 49

Bayesian optimization of disruption scenarios with fluid-kin...

引用

49th EPS Conference on Plasma Physics, EPS 2023

作者： Ekmark, I. Pusztai, I. Hoppe, M. Jansson, P. Fülöp, T. Department of Physics Chalmers Univ. Technology Göteborg Sweden Department of Electrical Engineering KTH Royal Inst. Technology Stockholm Sweden Department of Computer Science and Engineering Chalmers Univ. Technology Göteborg Sweden

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：