检索结果-内蒙古大学图书馆

2023 International Conference on Sustainable Communication Networks and Application, ICSCNA 2023

作者： Degadwala, Sheshang Vyas, Dhairya Panesar, Sonia Ebenezer, Divya Pandya, Darshanaben D. Shah, Vandita Dipak Sigma University Dept. of Comm. Engg. Gujarat India The Maharaja Sayajirao University of Baroda Gujarat Vadodara India Drs.Kiran and Pallavi Patel Global University Dept. of Comp. Sci & Engg. Kset Gujarat Vadodara India Pes University Department of Computer Science and Engineering EC Campus Karnataka Bengaluru India Scjccs Sankalchand Patel University Dept. of Comp. Sci. Gujarat Visnagar India Shreyarth University Department of Computer Application Gujarat Ahmedabad India

ISBN: (纸本)9798350313987

This research work introduces an innovative approach for the classification of hops plant diseases through the utilization of transfer learning with state-of-the-art Convolutional Neural Networks (CNNs). By leveraging pretrained models on extensive image datasets, this study has developed a customized CNN architecture, which is specifically designed to address the unique challenges posed by hop plant diseases. Their method demonstrates remarkable accuracy in classifying multiple hop plant diseases, offering significant potential for early disease detection and precise management strategies. The paper also provides an insightful comparison of the effectiveness of each CNN architecture within the context of hops plant disease classification. This research has the potential to automate and enhance hops plant disease management, ensuring the sustainability and quality of hop crops for the brewing industry while providing a valuable framework for addressing similar agricultural challenges. © 2023 IEEE.

关键词： Convolutional Neural Network (CNN) Hops Plant Disease Multi-Class Classification Natural Farming Transfer Learning

来源：评论

学校读者我要写书评

暂无评论

Optimization of Hierarchical-QAM based Downlink Multiple Access with Statistical CSI

Optimization of Hierarchical-QAM based Downlink Multiple Acc...

引用

IEEE Workshop on Signal Processing Advances in Wireless Communications (SPAWC)

作者： Jinkang Zhu Shengli Zhou Ming Zhao CAS Key Laboratory of Wireless-Optical Communications University of Sci. and Tech. of China Hefei China Department of Electrical and Computer Engineering University of Connecticut Storrs USA

This paper considers a downlink multiple access scenario with OFDM transmissions in frequency selective channels. The users are assigned with different bit streams from hierarchical quadrature amplitude modulation (QAM) rather than assigned with different subcarriers as in orthogonal frequency division multiple access (OFDMA). Based on statistical channel state information in the form of the average signal-to-noise ratios of the users, we derive a closed-form solution on the hierarchical constellation design. The numerical results demonstrate the performance advantage of the proposed system over OFDMA where power control is also applied based on the same channel feedback.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MLMSA: Multi-Level and Multi-Scale Attention for Lesion Detection in Endoscopy

MLMSA: Multi-Level and Multi-Scale Attention for Lesion Dete...

引用

2023 IEEE International Conference on E-Health Networking, Application and Services, Healthcom 2023

作者： Zhang, Zhang Wang, Xizhe Chen, Shuijiao Liu, Xiaowei Chen, Qilei Zhang, Yizhe Cao, Yu Liu, Benyuan Miner School of Computer and Information Sciences University of Massachusetts Lowell United States Xiangya Hospital of Central South University Department of Gastroenterology China Hunan Intl. Sci. and Technol. Coop. Base of Artif. Intell. Comp. Aided Diagn. and Treatm. for Digest. Dis. China School of Computer Science and Engineering Nanjing University of Science and Technology China

ISBN: (纸本)9798350302301

The advancement of deep learning techniques has significantly improved abnormality detection in gastrointestinal (GI) endoscopy. However, this imaging process comes with challenges due to the complex nature of GI abnormalities. The wide variety of abnormalities in terms of type, color, texture, shape, and scale of lesions makes it difficult to accurately detect them in different scenarios. Furthermore, the presence of multiple types of lesions within the same region create complex scenarios that complicate abnormality detection. Additionally, differentiating early-stage cancers from non-cancerous lesions is a significant challenge even for experienced professionals. The simultaneous identification of cancers, particularly early-stage ones, and non-cancerous lesions within the same region remains a challenging issue in GI endoscopy imaging. In this study, we discover that multiple types of lesions exhibit a scale-sensitive characteristic that can be leveraged by multi-level feature-based deep learning models. Hence, we propose the use of a multi-level and multi-scale attention (MLMSA) neck module in a deep learning network. The MLMSA module utilizes multiple levels of features extracted from the backbone network to generate processed multi-level features that assist the detection head. By integrating the MLMSA module into the deep learning framework, our goal is to enhance the detection and differentiation of lesions, particularly the early-stage cancer, thereby advancing the capabilities of GI endoscopy imaging. Our experiment results show that integrating the MLMSA module leads to a significant improvement in the detection of GI abnormalities, providing compelling evidence for the enhanced performance achieved through the utilization of the MLMSA module in our approach. © 2023 IEEE.

关键词： Endoscopy

来源：评论

学校读者我要写书评

暂无评论

A Systematic Approach for Object Detection in Unconstrained Environments

A Systematic Approach for Object Detection in Unconstrained ...

引用

International Conference on Industrial and Information Systems, ICIIS

作者： K. Thiruthanigesan Ruwan D. Nawarathna Roshan G. Ragel Postgraduate Institute of Science University of Peradeniya Sri Lanka Department of Stat. and Comp. Sci. University of Peradeniya Sri Lanka Department of Computer Engineering University of Peradeniya Sri Lanka

Object detection in unconstrained environments could be defined as identifying objects captured in challenging environments like smoky, wild, and cloudy environments. Object detection is widely used in computer vision applications. It also has many applications in security surveillance, where we often have to deal with unconstrained environments. Several algorithms and techniques have been developed for object detection over the past years. Overall, object detection approaches can be divided into two main types: conventional computer vision-based approaches and modern deep learning-based computer vision approaches. This study reviews different methods and algorithms developed in recent years for object detection in constrained environments. Most object detection methods in constrained environments produce good performance. However, object detection in unconstrained environments is still an open problem that requires unique methods. So far, only a handful of approaches have been proposed. This study also presents future development trends and research directions for object detection in unconstrained environments to produce automated intelligence security surveillance. This review's main conclusion is that object detection in unconstrained environments needs to be improved and well-established using unique computer vision methods based on modern machine learning and deep learning technologies.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhanced YOLOv4 for Facilitating Public Safety Management amidst Protests and Riots

Enhanced YOLOv4 for Facilitating Public Safety Management am...

引用

International Conference on Industrial and Information Systems, ICIIS

Public safety management during protests is a critical issue requiring effective and efficient measures to minimise harm to law enforcement personnel and protesters. Our research introduces a faster variant of the You Only Look Once version 4 (YOLOv4) algorithm, specifically designed to identify objects frequently employed as weapons or for starting fires in public demonstrations and riots. We also developed a new dataset containing knives, swords, axes, stones, sticks, and objects commonly associated with arson. The proposed Accelerated YOLOv4 algorithm was trained and tested using the developed dataset. Its performance was compared to the standard YOLOv4 algorithm. The performance evaluation of the detection models showed that the Accelerated YOLOv4 model achieved higher precision scores than the YOLOv4 model for most objects. The mean average precision (mAP) of the Accelerated YOLOv4 model was 86%, which is higher than the mAP of the YOLOv4 model, which was 72%. These results indicate that the proposed Accelerated YOLOv4 algorithm can improve the effective management of public safety during protests.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Neural Signal Compression System with Spike Detection Using Compressed Sensing

Neural Signal Compression System with Spike Detection Using ...

引用

2023 Cross Strait Radio sci.nce and Wireless Technology Conference, CSRSWTC 2023

作者： Zheng, Ruihan Xia, Yu Li, Dongming Wang, Liyang Li, Hung Chun Mak, Peng Un Vai, Mang I. Pun, Sio Hang State Key Laboratory of Analog and Mixed-Signal VLSL University of Macau Macau China Institution of Microelectronics University of Macau Macau China Jt. Lab. of Zhuhai UM Sci. and Technol. Research Institution - Lingyange Semiconductor Incorporated Zhuhai China University of Macau Faculty of Science and Technology Department of Electrical and Computer Engineering Macau China

ISBN: (纸本)9798350358971

This article aims to demonstrate a signal compression method for the wireless invasive neural recording system. A compression system with spike detection for neural signals is proposed. The input signal is firstly detected in the spike detection part and then the intercepted spike segments are sent to the compression part. A compressed sensing technique is applied in the compression part, and the Minimum Euclidean or Manhattan Distance Cluster-based (MDC) matrix is adopted for compressing neural spike segments. During simulation, the compression rate can surpass 99% and the signal-to-noise distortion ratio is around 37 dB. Moreover, the proposed method is also contrasted with the direct compression of input neural signals. When the input neural signal is directly compressed, the compression ratio is 98%, and the signal-to-noise ratio distortion rate is about 28 dB. By employing spike detection and utilizing this MDC matrix, it becomes possible to compress non-sparse spike segments in the time domain, resulting in a higher compression rate and improved reconstruction performance. © 2023 IEEE.

关键词： compressed sensing neural signal compression spike detection

来源：评论

学校读者我要写书评

暂无评论

Fault-Tolerant Data Aggregation with Error-Checking for Smart Grids

Fault-Tolerant Data Aggregation with Error-Checking for Smar...

引用

IEEE International Symposium on Dependable, Autonomic and Secure Computing (DASC)

作者： Congcong Wang Chen Wang Jian Shen Pandi Vijayakumar Zakirul Alam Bhuiyan School of Software Nanjing University of Information Science & Technology Nanjing China School of Information Science and Engineering Zhejiang Sci-Tech University Hangzhou China Department of Computer Science and Engineering University College of Engineering Tindivanam Tamilnadu India Department of Computer and Information Sciences Fordham University New York USA

With the rapid development of smart grid technology, a new challenge has been brought about by the massive data generated from distributed devices. Data aggregation technology plays a crucial role in smart grid schemes, in terms of energy data statistics and resource allocation. However, achieving fast error-checking and improving device fault-tolerance are still open issues in the smart grid data aggregation. To address these issues, this paper proposes an error-tolerant data aggregation scheme integrated with error-checking mechanisms. The scheme proposes a tree-based aggregation structure, facilitating swift error-checking of data. We combine masking values with user anonymity in the ElGamal cryptographic scheme to ensure the security of sensitive data and resist collusion attacks. Both theoretical and experimental analyses demonstrate that this scheme enables a lightweight, secure data aggregation, ensuring enhanced reliability and error-checking.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Combined Machine Learning-Inversion Scheme for Super-Resolution 3-Dimensional Microwave Human Brain Imaging

Combined Machine Learning-Inversion Scheme for Super-Resolut...

引用

2022 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio sci.nce Meeting, AP-S/URSI 2022

作者： Zhao, Le-Yi Xiao, Li-Ye Cheng, Yu Liu, Qing Huo Xiamen University Inst. of Electromagnetics and Acoust. and Fujian Prov. Key Lab. of Electromagnetic Wave Sci. and Detection Technol. Xiamen361005 China Duke University Department of Electrical and Computer Engineering DurhamNC27708 United States

ISBN: (数字)9781665496582

ISBN: (纸本)9781665496582

To realize three-dimensional (3-D) super-resolution whole brain imaging with a low high efficiency and computational cost, a new machine learning based-inversion method with the resolution enhancement technique is proposed in this work. This method consists three parts: a parallel semi-connected back-propagation neural network (SJ-BPNN) scheme, a U-Net scheme and a modified Akima segmented cubic Hermite interpolation (MASCHI) scheme. The parallel SJ-BPNN scheme is employed to map the measured scattering field data to the initial electrical properties distribution of human brain, firstly. Then, U-Net is used to improve the quality of preliminary reconstruction results obtained from SJ-BPNN. Finally, MASCHI scheme is adopted to greatly improve the resolution of reconstruction results with a very low computational cost. Numerical examples of normal human brain and human brain with abnormal scatterers show that the proposed model can achieve accurate human brain imaging with 1024×1024×1024 voxels resolution with a very low computational cost. © 2022 IEEE.

关键词： Brain mapping

来源：评论

学校读者我要写书评

暂无评论

Suspicious Object Detection in Environments with Tear Gas 16

Suspicious Object Detection in Environments with Tear Gas

引用

16th IEEE International Conference on Industrial and Information Systems, ICIIS 2021

作者： Thiruthanigesan, K. Nawarathna, Ruwan D. Ragel, Roshan G. Postgraduate Institute of Science University of Peradeniya Sri Lanka University of Peradeniya Department of Stat. and Comp. Sci. Sri Lanka University of Peradeniya Department of Computer Engineering Sri Lanka

ISBN: (纸本)9781665426374

In a digital security surveillance system, detecting suspicious objects is paramount to identifying criminals and thereby reducing the crime rate. At present most of the security surveillance systems are based on automated CCTV cameras. Usually, it is highly challenging to detect objects in environments covered with smoke, water, and dark clouds. One of the main intentions of security surveillance is detecting harmful objects such as guns, knives, axes, and iron rods. Digital surveillance in a situation where the police have used tear gas and water is even more challenging since the background could contain many artefacts. This paper aims to develop a model to detect suspicious objects in footage of protests or riots where the environment encompasses tear gas. The proposed method uses a YOLOv4 object detection framework along with Roboflow. All the fully connected dense layers of the YOLOv4 model were trained with a newly created dataset with different images captured in environments where tear gas is present and containing dangerous objects. Also, the developed dataset uses several Bags of Freebies to improve the detection rate. The model achieved a mean average precision (mAP) of 82% for the test dataset when trained for 105 epochs. Overall, the proposed method could solve problems in suspicious object detection in public security surveillance under challenging environments. © 2021 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Trustworthy Federated Learning: Privacy, Security, and Beyond

arXiv

引用

arXiv 2024年

作者： Chen, Chunlu Liu, Ji Tan, Haowen Li, Xingjian Wang, Kevin I-Kai Li, Peng Sakurai, Kouichi Dou, Dejing HiThink Research Hangzhou China Carnegie Mellon University Pittsburgh United States Information Science and Electrical Engineering Department Kyushu University Fukuoka Japan Electrical Computer and Software Engineering Department The University of Auckland Auckland New Zealand Computer Science and Engineering Department The University of Aizu Aizuwakamatsu Japan Information Science and Technology Department Zhejiang Sci-Tech University Hangzhou China Fudan University Shanghai and BEDI Cloud Beijing China

While recent years have witnessed the advancement in big data and Artificial Intelligence (AI), it is of much importance to safeguard data privacy and security. As an innovative approach, Federated Learning (FL) addresses these concerns by facilitating collaborative model training across distributed data sources without transferring raw data. However, the challenges of robust security and privacy across decentralized networks catch significant attention in dealing with the distributed data in FL. In this paper, we conduct an extensive survey of the security and privacy issues prevalent in FL, underscoring the vulnerability of communication links and the potential for cyber threats. We delve into various defensive strategies to mitigate these risks, explore the applications of FL across different sectors, and propose research directions. We identify the intricate security challenges that arise within the FL frameworks, aiming to contribute to the development of secure and efficient FL systems. © 2024, CC BY-NC-SA.

关键词： Differential privacy

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：