检索结果-内蒙古大学图书馆

Performance Evaluation and Improvement of Shoreline Detection Using Sentinel-1 SAR and DEM Data

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2024年 17卷 8139-8152页

作者： Chang, Lena Chen, Yi-Ting National Taiwan Ocean University Department of Communication Navigation and Control Engineering Keelung202301 Taiwan National Taiwan Ocean University Department of Electrical Engineering Keelung202301 Taiwan

This study improved the shoreline detection performance based on the U-Net model by combining Sentinel-1 synthetic aperture radar (SAR) and digital elevation model (DEM) data. The U-Net network was first modified to enhance feature extraction by using the MobileNetV3 backbone architecture and convolutional block attention module. To alleviate the performance degradation of shoreline detection caused by radar shadow, especially in coastal areas with large terrain undulations, SAR and DEM data were combined as input to U-Net. Furthermore, this study evaluated the shoreline detection performance using the statistical analysis based on the proposed probabilistic model of distance difference between the detected shoreline and reference data which was provided by Construction and Planning Agency Ministry of the Interior, Taiwan government. The experiment was conducted based on two self-built datasets, one containing 4061 SAR images and the other containing 3822 SAR images and corresponding DEM data, both collected in the coastal areas of Taiwan from 2016 to 2019. The experimental results showed that compared with the U-Net network using SAR data, the modified U-Net has achieved superior performance in shoreline detection for various coastal landforms. Moreover, the addition of DEM data reduced the influence of radar shadow, making shoreline detection results more consistent with reference data. Finally, the generalization ability of the modified U-Net in shoreline detection was also verified by testing images from regions not included in the built dataset. © 2008-2012 IEEE.

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Achievable Rates for Finite Alphabet Constellation Over Non-Gaussian Noise Channel

Achievable Rates for Finite Alphabet Constellation Over Non...

引用

International Conference on 6G communications Networking and Signal Processing, SGCNSP 2023

作者： Hussain, Aadil Saqib, Najam-Us Mushtaq, Asrar Mehraj Shah, Shahid Communication Control and Learning Lab Department of Electronics and Communication Engineering National Institute of Technology Srinagar Srinagar India

ISBN: (纸本)9789819778751

Under the assumption of receiver noise characteristics, the Gaussian noise models are well-studied in the literature. There are several scenarios where the Gaussian Noise assumption is not valid;common examples include electromagnetic interference channels, underwater acoustic channels, powerline communication channels, and NAND flash memory channels. In this paper, we study non-Gaussian noise models, specifically Laplacian noise (a well-known model for impulsive noise). Diverting from the usual assumption of Gaussian inputs, we take a more practical approach and consider finite alphabet constellations as input and compute achievable rates (by computing mutual information (MI)) for various modulation schemes. It is a well-known result that MI computed for finite constellation does not have any closed form;hence, we use the famous LogSumExp inequality to find the upper bound for MI. Simulation results are compared with the obtained bound, and remarkable accuracy is found at high SNR. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Gaussian noise (electronic)

来源：评论

学校读者我要写书评

暂无评论

Intelligent Agricultural Drones Utilizing Nano-Fertilizer Dispensation for Precision Farming

Intelligent Agricultural Drones Utilizing Nano-Fertilizer Di...

引用

2024 International Conference on communication, Computing and Internet of Things, IC3IoT 2024

作者： Jayanthi, G. Nancy, W. Umamaheswari, B. Chithrakkannan, R. Sujith, R. Sathya Prasanna, S. Sri Sairam Engineering College Department Of Instrumentation And Control Engineering India Jeppiaar Institute Of Technology Department Of Electronics And Communication Engineering India Sri Sairam Engineering College Department Of Electronics And Communication Engineering India

ISBN: (纸本)9798350352689

An innovative approach to precision agriculture through the integration of artificial intelligence (AI) and nano-fertilizer technology in an agricultural drone system. The proposed system aims to optimize crop yield, reduce environmental impact, and enhance resource efficiency by employing advanced AI algorithms for crop health assessment and nano-fertilizers for targeted nutrient delivery. The drone's real-time decision-making capabilities, coupled with precise dispensation of nano-sized fertilizers, contribute to sustainable farming practices. Field trials demonstrate promising results in terms of improved crop productivity, resource utilization, and minimized environmental footprint. © 2024 IEEE.

关键词： Crops

来源：评论

学校读者我要写书评

暂无评论

AI Based on Inception v3 Architecture for Fault Diagnosis in paddy crop using image recognition and Transfer Learning 4

AI Based on Inception v3 Architecture for Fault Diagnosis in...

引用

4th International Conference on Power, Energy, control and Transmission Systems, ICPECTS 2024

作者： Jayanthi, G. Brindha, S. Sri Sairam Engineering College Department of Instrumentation and Control Engineering India Sri Sairam Engineering College Department of Electronics and Communication Engineering India

ISBN: (数字)9798331508845

ISBN: (纸本)9798331508845

Plant diseases is a serious effect that greatly affects crop yield due to these diseases. The optimal diagnosis of this plant disease will prevent us from the loss in crop yield. In analyzing automatic diagnosis of the plant, disease by implementing a smartphone application established. Artificial intelligence is used is machine learning framework to detect the plant disease in time. The basic preventive measure taken using machine learning algorithms that works on an example model in which the module integrated to predict the plant diseases. The proposed structure uses a tuned Inception v3 architecture, which is a typical deep convolutional neural network with multiple convolution layers, consisting of nearly 6 convolution layers. This architecture, which use for classifying the plant disease, supports nearly 12 layers whose performance is an outstanding one for image network. The result shows that this model built using this Framework works very well in timely diagnosis of the plant diseases. Places like the learning rate position f- measure recall and disease recognition with accuracy performances investigated. Total accuracy attained using the built model is 76.56 % with maximum area of the curve. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Tomato Leaf Disease Detection Using Machine Learning

Tomato Leaf Disease Detection Using Machine Learning

引用

2024 International Conference on communication, Computing and Internet of Things, IC3IoT 2024

作者： Jayanthi, G. Brindha, S. Vijayalakshmi, S. Dharshini, V. Angelin Freeda, J. Sahana, S. Sri Sairam Engineering College Department Of Instrumentation And Control Engineering India Sri Sairam Engineering College Department Of Electronics And Communication Engineering India R.M.K Engineering College Department Of Electronics And Communication Engineering India

ISBN: (纸本)9798350352689

Leaf diseases are a major danger to the world's food security and have a substantial impact on crop productivity. Effective plant disease management depends on the early identification and precise diagnosis of these illnesses. Recent developments in computer vision techniques and the accessibility of inexpensive hardware, such the Raspberry Pi, have created new avenues for the development of portable and reasonably priced leaf disease detection devices. An innovative Raspberry Pi method for leaf disease detection is shown in this abstract. The proposed approach automatically detects and classifies various leaf diseases using machine learning and image processing techniques. For on-site disease detection in agricultural settings, the Raspberry Pi platform is a perfect fit because of its small size, low power consumption, and computational capacity. © 2024 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Advancing Underwater Object Identification Using Aerial Hyperspectral Imaging 4

Advancing Underwater Object Identification Using Aerial Hype...

引用

4th International Conference on Power, Energy, control and Transmission Systems, ICPECTS 2024

作者： Sujith, R. Ganapathy, V.S. Sathya Prasanna, S. Mohanraj, K. Balaji, N. Vignesh, A. Sri Sairam Engineering College Department of Instrumentation and Control Engineering India Sri Sairam Engineering College Department of Instumentation and Control Engineering India Sri Sairam Engineering College Department of Electronics and Communication Enginnering India Sri Sairam Engineering College Department of Electronics and Control Enginnering India

ISBN: (数字)9798331508845

ISBN: (纸本)9798331508845

This This paper proposes a novel approach of Underwater object identification is a critical aspect of marine exploration, environmental monitoring, and underwater resource management. However, traditional methods face challenges such as limited visibility and time-consuming manual processes. This paper proposes an innovative approach to enhance underwater object identification using aerial hyperspectral imaging coupled with artificial intelligence (AI) techniques. Leveraging the advantages of aerial platforms equipped with hyperspectral sensors, this research aims to improve the efficiency and accuracy of underwater object detection and classification. The methodology involves data acquisition through aerial platforms, preprocessing of hyperspectral data to enhance quality, and the application of AI algorithms for automated object identification. An experimental study is conducted to evaluate the proposed approach, demonstrating its effectiveness in accurately identifying underwater objects across different environments. The results highlight significant advancements over conventional methods, showcasing the potential of aerial hyperspectral imaging and AI for underwater applications. This research contributes to the advancement of underwater sensing technologies and underscores the importance of integrating aerial platforms and AI for improved underwater object identification. © 2024 IEEE.

关键词： Underwater imaging

来源：评论

学校读者我要写书评

暂无评论

Seamless Integration of Legacy Industrial Systems with OPC UA for Enhanced Digital Transformation 4

Seamless Integration of Legacy Industrial Systems with OPC U...

引用

4th International Conference on Power, Energy, control and Transmission Systems, ICPECTS 2024

作者： Sujith, R. Ganapathy, V.S. Ilayaraja, R. Durgadevi, K. Balaji, N. Vignesh, A. Sri Sairam Engineering College Department of Instrumentation & Control Engineering Chennai India Sri Sairam Engineering College Department of Electronics & Communication Engineering Chennai India

ISBN: (数字)9798331508845

ISBN: (纸本)9798331508845

The integration of legacy systems with modern control technologies is a significant challenge in the digital transformation of industrial environments. Many facilities still rely on outdated equipment that lacks compatibility with contemporary communication standards like OPC UA (Open Platform communications Unified Architecture). This paper proposes a comprehensive solution to bridge this gap by developing OPC UA wrappers and adapters that facilitate communication between legacy systems and modern control infrastructures. The approach involves translating data from various legacy protocols into the OPC UA format, enabling seamless data exchange and interoperability. A central OPC UA server is implemented to aggregate and normalize data, providing a unified and secure platform for real-time monitoring and control. The proposed solution was evaluated in a simulated industrial environment, demonstrating effective data integration, enhanced performance, robust security, and high operator satisfaction. The results validate the feasibility of using OPC UA to integrate legacy systems, supporting digital transformation and fostering a more connected industrial ecosystem. © 2024 IEEE.

关键词： Interoperability

来源：评论

学校读者我要写书评

暂无评论

Smart Assistive E-Vehicle for Enhanced Mobility of Physically Challenged Individuals 4

Smart Assistive E-Vehicle for Enhanced Mobility of Physicall...

引用

4th International Conference on Power, Energy, control and Transmission Systems, ICPECTS 2024

作者： Jayanthi, G. Ganapathy, V.S. Vijayalakshmi, S. Sujith, R. Vallarasu, M. Vignesh, A. Sri Sairam Engineering College Department of Instrumentation and Control Engineering India R.M.K Engineering College Department of Electronics and Communication Engineering India

ISBN: (数字)9798331508845

ISBN: (纸本)9798331508845

Mobility is essential to freedom and a high quality of life in the fast-paced world of today, especially for those with physical disabilities. Even while they work well, traditional cars frequently fall short of meeting the unique requirements of this population, which makes navigation and autonomy challenging. In order to tackle this issue, we suggest creating a Smart Assistive E-Vehicle that is intended to improve mobility for those with physical disabilities. This cutting-edge car is an electric four-wheel drive vehicle with cutting-edge technology that offers convenient, safe, and effective transportation. The YOLO (You Only Look Once) algorithm, a cutting-edge deep learning model that enables real-time traffic light monitoring, is the brains behind this system. Because of the great efficiency of the YOLO algorithm, the car can recognize traffic lights and signals with great speed and accuracy, which is essential for safe urban navigation. Because of the great efficiency of the YOLO algorithm, the car can recognize traffic lights and signals with great speed and accuracy, which is essential for safe urban navigation. © 2024 IEEE.

关键词： Traffic signals

来源：评论

学校读者我要写书评

暂无评论

KERNEL DENSITY-BASED STATISTICAL TEXTURAL FEATURE ANALYSIS AND CLASSIFICATION OF VAGINOSCOPIC IMAGES TO DETECT ESTROUS CYCLE IN FEMALE CANINES

Biomedical Sciences Instrumentation

引用

Biomedical Sciences Instrumentation 2024年第1期60卷 66-77页

作者： Rajan, Bindhu K. Venugopal, G. Department of Instrumentation and Control Engineering N. S. S. College of Engineering Palakkad Affiliated to A. P. J. Abdul Kalam Technological University Kerala India Jyothi Engineering College Electronics and Communication Engineering Department Kerala Thrissur India

Effective breeding management allows breeders to preserve and improve desirable traits within specific dog breeds. Knowing the optimal mating period in canines earlier allows for efficient breeding planning, maximizing the chances of successful conception while reducing the need for repeated attempts. It is possible to detect the mating period of canines by classifying the features corresponding to the variations in the reproductive stages. The kernel density estimation (KDE) technique is employed in this paper to analyze the textural variations in the vaginoscopic images of female canines. The pre-processed images are subjected to kernel density estimation techniques, and the texture features are extracted for three different kernels: Gaussian, triangle, and Epanechinknv. These features are used to differentiate various stages in the reproductive cycle of female canines. The average values of six statistical features such as entropy, energy, kurtosis, mean, median and skewness are 1.47, 1.2, 0.54, 1.59, 0.69, and 2.8 respectively. There are notable differences in KDE characteristics observed during different stages of the reproductive cycle. By employing different classifiers like K- nearest neighbor (KNN), support vector machine, and K-Star, the features undergo classification, revealing that KNN achieves remarkable accuracy, specificity, and sensitivity of 82.1%, 76.5 % and 69.8% respectively, effectively distinguishing all the stages. The highest accuracy is obtained for the bandwidth 0.2 for all the classifiers. This automated system showcases its potential as a valuable tool for predicting the optimum mating period for effective reproductive management and canine breeding programs. © 2024 IAE All rights reserved.

关键词： Classification Kernel density estimators Textural features Vaginoscopy

来源：评论

学校读者我要写书评

暂无评论

A Method for Filtering Data-Driven Predictive control Aimed at Vehicle Lateral Stabilization in Compacted-Snow Rutted Road Conditions 8

A Method for Filtering Data-Driven Predictive Control Aimed ...

引用

8th CAA International Conference on Vehicular control and Intelligence, CVCI 2024

作者： Zhao, Xu Guo, Hongyan Shi, Wanqing College of Communication Engineering Jilin University Changchun China Jilin Institute of Chemical Technology Department of Aircraft Control and Information Engineering Changchun China College of Communication Engineering Jilin University State Key Laboratory of Automotive Simulation and Control Changchun China

ISBN: (纸本)9798331504892

Designing a data-driven predictive controller for lateral stability of vehicles on compacted-snow rutted roads, especially when the data is subjected to non-stationary noise disturbances, is a significant challenge. This paper introduces a novel subspace predictive equation construction method that incorporates filtering using the inverse of a first-order disturbance model. Based on this, a filtering data-driven predictive controller is designed. The proposed method is tested through numerical simulations and MATLAB/CarSim co-simulation. Simulation results show that the proposed subspace predictive equation with filtering effectively mitigates the variance and bias introduced by non-stationary noise. The co-simulation results demonstrate that the controller ensures the stability and robustness of the vehicle system. © 2024 IEEE.

关键词： Predictive control systems

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：