检索结果-内蒙古大学图书馆

An Improved Hybrid Switching Scheme for UAV-to-Ground ACM FSO System

An Improved Hybrid Switching Scheme for UAV-to-Ground ACM FS...

2023 Asia communications and Photonics Conference/2023 International Photonics and Optoelectronics Meetings, ACP/POEM 2023

作者： Zhang, Qianwu Liu, Boyang Chen, Guanwen Zhan, Shucheng Li, Zhiyu Zhang, Jing Jiang, Ning Cao, Bingyao Li, Zhengxuan Shanghai Institute for Advanced Communication and Data Science Shanghai University Key Laboratory of Specialty Optics and Optical Access Networks Shanghai200072 China School of Information and Communication Engineering University of Electronic Science and Technology of China Sichuan Chengdu611731 China

ISBN: (纸本)9798350312614

关键词： ACM FSO UAV

来源：评论

学校读者我要写书评

暂无评论

An Autoencoder-based Transceiver for UAV-to-Ground Free Space Optical communication

An Autoencoder-based Transceiver for UAV-to-Ground Free Spac...

引用

2023 Opto-Electronics and communications Conference, OECC 2023

作者： Zhang, Qianwu Chen, Guanwen Liu, Boyang Zhi, Xuzhuang Zhan, Shucheng Zhang, Jing Jiang, Ning Cao, Bingyao Li, Zhengxuan Shanghai Institute for Advanced Communication and Data Science Key Laboratory of Specialty Optics and Optical Access Networks Shanghai University Shanghai200072 China University of Electronic Science and Technology of China School of Information and Communication Engineering Sichuan Chengdu611731 China

An end-to-end autoencoder-based transceiver for UAV-to-ground free space optical communication is proposed. Simulation results show ∼ 12dB improvement compared to the PPM transmitter and ∼ 51.3% reduction of decoder... 详细信息

ISBN: (纸本)9781665462136

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Efficient Canine Vision: Accurate Dog Breed Classification with EfficientNet 2

Efficient Canine Vision: Accurate Dog Breed Classification w...

引用

2nd IEEE International Conference on Trends in Quantum Computing and Emerging Business Technologies, TQCEBT 2024

作者： Godwin James, T. Prabahar Poonguzhali, C. Selvakumaran, S. Malathi, G. Kaliappan, S. Venu, Nookala Department of Computer Science and Engineering Sri Sairam Institute of Technology India Department of Electronics and Communication Engineering S.A. Engineering College Chennai India Department of Artificial Intelligence and Data Science Rajalakshmi Institute of Technology Chennai India Department of Electrical and Electronics Engineering Kumaraguru College of Technology Saravanampatti Coimbatore India Madhya Pradesh Gwalior India

ISBN: (纸本)9798350384277

Understanding and classifying dog breeds is a fascinating yet challenging task due to the vast diversity within the canine species. In this project, we present a novel approach to dog breed classification utilizing the state-of-the-art Efficient Net architecture. Leveraging a comprehensive dataset comprising 133 distinct breeds, our method aims to accurately identify and categorize each breed with high precision. Efficient Net's innovative scaling method allows us to strike a balance between model complexity and computational efficiency, enabling robust classification performance even with limited computational resources. Through meticulous preprocessing techniques and data augmentation strategies, we enhance the model's ability to generalize across diverse breed characteristics, minimizing the risk of overfitting. Our experimental results demonstrate the efficacy of the proposed approach, achieving impressive classification accuracy on the challenging dog breed dataset. We conduct extensive evaluations and comparisons with existing methodologies, showcasing the superiority of Efficient Net in handling complex classification tasks with large-scale image datasets. Furthermore, we provide insights into the interpretability of the model's predictions, shedding light on the learned representations and key features contributing to breed classification. This project not only advances the state-of-the-art in dog breed classification but also contributes to our understanding of deep learning techniques applied to animal recognition tasks. In sum up, our work highlights the potential of leveraging advanced neural network architectures like Efficient Net for comprehensive and accurate dog breed classification, paving the way for applications in veterinary medicine, pet care, and animal welfare. © 2024 IEEE.

关键词： Veterinary medicine

来源：评论

学校读者我要写书评

暂无评论

Total Variation Denoising for Graph Signals Enhanced with Moreau Envelope

引用

Circuits, Systems, and Signal Processing 2025年 1-32页

作者： Jia, Zihao He, Yangfan Zhang, Zhichao School of Communication and Artificial Intelligence School of Integrated Circuits Nanjing Institute of Technology Nanjing 211167 China School of Mathematics and Statistics The Center for Applied Mathematics of Jiangsu Province The Jiangsu International Joint Laboratory on System Modeling and Data Analysis Nanjing University of Information Science and Technology Nanjing 210044 China

Graph signal denoising plays a crucial role in processing complex network data. However, traditional Total variation (TV) denoising methods often suffer from excessive smoothing and high computational cost. In this paper, we propose an Moreau-enhanced TV (MTV) denoising method for graph signals, based on the Moreau envelope. By introducing a non-convex regularization term, this method improves the conventional -norm model, effectively reducing edge information loss caused by over-smoothing and preserving the structural features of graph signals. Compared to the traditional TV approach, the MTV method strikes a better balance between noise suppression and signal feature preservation. It excels in capturing signal jumps and mitigating error accumulation, particularly for periodic cyclic and complex random graph signals. Additionally, the proposed method demonstrates strong robustness to changes in graph density, maintaining stable denoising performance even as edge probabilities increase, thus overcoming the instability commonly observed in traditional methods on complex topologies. Experimental results validate that the MTV method outperforms existing techniques across various graph topologies and signal distributions, especially in high-dimensional and complex signal scenarios, highlighting its theoretical and practical significance in graph signal processing. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Complex networks Graph Laplacian Graph signal denoising Moreau envelope Non-convex regularization Optimization algorithm Signal Recovery Total variation

来源：评论

学校读者我要写书评

暂无评论

An Empirical Analysis and Challenging Era of Blockchain in Green Society 1

引用

4th International Conference on communication and Intelligent Systems, ICCIS 2022

作者： Senthil, G.A. Prabha, R. Divya, B. Sathya, A. Department of Information Technology Agni College of Technology Chennai India Department of Electronics and Communication Engineering Sri Sai Ram Institute of Technology Chennai India Department of Computer Science and Engineering Sri Sai Ram Institute of Technology Chennai India Department of Artificial Intelligence and Data Science Sri Sai Ram Institute of Technology Chennai India

ISBN: (数字)9789819923229

ISBN: (纸本)9789819923212

Blockchain is one of the new inventions that can help develop sustainable and sustainable solutions as it is able to provide accountability, transparency, online tracking and robustness, and improve the efficiency of global collaboration. A massive increase in electricity demand has created a new dilemma. Power businesses, startups, commercial banks, policymakers, and researchers are all interested in blockchain technology, which has become the most generally acknowledged IoT technology. Therefore, blockchain technology efforts from both industry and education have been included in the study. Recently, the blockchain has been employed as a new approach for developing and enhancing green societies. A full examination of all the constraints and potential of the blockchain through technological ideas is required. In this article, tremendous attempts are underway to thoroughly investigate the complete foundation of the green community and how the blockchain contributes to the green community. Finally, this article also highlights the applications and challenges of the green chain-driven community. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Automatic Road Extraction using Scale Invariant Feature Transform-based Random Forest in Satellite Images 1

Automatic Road Extraction using Scale Invariant Feature Tran...

引用

1st International Conference on Software, Systems and Information technology, SSITCON 2024

作者： Rajesh, N. Alzubaidi, Laith H. Shivaprasad Yadav, S.G. Chembian, W.T. Prameela, Boddepalli Nitte Meenakshi Institute of Technology Department of Electronics and Communication Engineering Bengaluru India The Islamic University of Babylon Department of Computers Techniques Babylon Iraq Ramaiah Institute of Technology Department of Electronics and Telecommunication Engineering Bengaluru India Department of Computer Science and Engineering Chennai India Vignan's Institute of Information and Technology Department of Artificial Intelligence and Data Science Andhra Pradesh India

ISBN: (纸本)9798350352931

Road Extraction from High-Resolution Satellite Images (HRSI) plays a significant role in the analysis of the remote sensor image field. The extraction of road automatically labels a road's pixels in a satellite image with semantic features depending on topographical meaningful features. However, manual road extraction inaccurately extracts road networks from satellite images which has significant difficulties like complex urban environments, varying road types, and diverse image conditions. Therefore, the Scale Invariant Feature Transform-based Random Forest(SIFT-RF) is proposed for automatic road extraction in satellite images. First, the image is obtained from DeepGlobe dataset and Z-score normalization is employed to maximize model performance. Then, SIFT is established to extract the road network in satellite images. Finally, the RF is utilized to extract and classify roads as road or non-road using Machine Learning (ML). The SIFT-RF achieves a greater f1-score of 98.24% compared to existing methods like Dual-Attention Road extraction Network (DA-RoadNet), High-Resolution U-Net architecture (HRU-Net), and Global Context-aware and Batch-independent Network (GCBNet) respectively. © 2024 IEEE.

关键词： Random forests

来源：评论

学校读者我要写书评

暂无评论

Real Time Crop Health Monitoring Through Convolution Neural Networks 4

Real Time Crop Health Monitoring Through Convolution Neural ...

引用

4th International Conference on Ubiquitous Computing and Intelligent Information Systems, ICUIS 2024

作者： Sridevi, Bommagani Padma, Nanda Manjusha, Puram Tirunagari, Sharanya Hariharan, Shanmugasundaram Famila, S. Vardhaman College of Engineering Department of Artificial Intelligence and Data Science Hyderabad India Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Electronics & Communication Engineering Tamil Nadu Chennai602001 India

ISBN: (纸本)9798331529635

The agriculture sector, also known as the primary sector in India, is currently facing significant challenges due to the increasing number of pests and insects. These pests can cause serious damage to crop fields, negatively affect crop health, reduce yields, and lead to substantial economic losses for farmers. Early detection of crop diseases can help minimize yield losses by 20-40%, depending on the specific crop type and its various growth stages. The paper discusses the important use of deep learning algorithms in agriculture, specifically focusing on developing an effective approach for the automatic detection of crop diseases through advanced image analysis techniques. The proposed Convolutional Neural Network (CNN) model architecture consists of multiple layers that extract meaningful features from images using convolution and pooling operations. After the feature extraction process, additional layers are used for accurately classifying the images into different disease categories. This model is trained using the Adam optimizer, which is known for its efficiency in handling large datasets and improving the overall training speed. It employs sparse categorical cross-entropy loss over 50 epochs, with a batch size of 32, to effectively optimize the learning process. During the training phase, the model's accuracy is continuously monitored to assess its performance and make any necessary adjustments to enhance its effectiveness. One of the key innovations of this approach is the ability to perform real-time crop disease detection using a camera. This advancement eliminates the need for manual picture collection from the fields, making the entire process faster and much more efficient. By enabling farmers to quickly identify diseases, this cutting-edge technology can significantly help improve crop management practices and increase overall agricultural productivity. Ultimately, the goal is to enhance food security and reduce economic losses in the agriculture sect

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Oppositional Harris Hawks Optimization with Deep Learning-Based Image Captioning

引用

Computer Systems science & Engineering 2023年第1期44卷 579-593页

作者： V.R.Kavitha K.Nimala A.Beno K.C.Ramya Seifedine Kadry Byeong-Gwon Kang Yunyoung Nam Department of Computer Science and Engineering Prathyusha Engineering CollegeThiruvallur602025India Department of Networking and Communications SRM Institute of Science and TechnologyChennaiIndia Department of Electronics and Communication Engineering Dr.Sivanthi Aditanar College of EngineeringTiruchendur628215India Department of Electrical and Electronics Engineering Sri Krishna College of Engineering and TechnologyCoimbatore641008India Deparmtent of Applied Data Science Noroff University CollegeKristiansandNorway Department of Information and Communication Engineering Soonchunhyang UniversityAsanKorea Department of Computer Science and Engineering Soonchunhyang UniversityAsanKorea

Image Captioning is an emergent topic of research in the domain of artificial intelligence(AI).It utilizes an integration of Computer Vision(CV)and Natural Language Processing(NLP)for generating the image *** use in several application areas namely recommendation in editing applications,utilization in virtual assistance,*** development of NLP and deep learning(DL)modelsfind useful to derive a bridge among the visual details and textual *** this view,this paper introduces an Oppositional Harris Hawks Optimization with Deep Learning based Image Captioning(OHHO-DLIC)*** OHHO-DLIC technique involves the design of distinct levels of ***,the feature extraction of the images is carried out by the use of EfficientNet ***,the image captioning is performed by bidirectional long short term memory(BiLSTM)model,comprising encoder as well as *** last,the oppositional Harris Hawks optimization(OHHO)based hyperparameter tuning process is performed for effectively adjusting the hyperparameter of the EfficientNet and BiLSTM *** experimental analysis of the OHHO-DLIC technique is carried out on the Flickr 8k dataset and a comprehensive comparative analysis highlighted the better performance over the recent approaches.

关键词： Image captioning natural language processing artificial intelligence machine learning deep learning

来源：评论

学校读者我要写书评

暂无评论

Simulation on Natural Disaster Fire Accident Evacuation Using Augmented Virtual Reality 7th

Simulation on Natural Disaster Fire Accident Evacuation Usin...

引用

7th International Conference on Inventive communication and Computaional Technologies, ICICCT 2023

作者： Senthil, G.A. Mathumitha, V. Prabha, R. Suganthi, Su. Alagarsamy, Manjunathan Department of Information Technology Agni College of Technology Chennai India Deptartment of Electronics and Communication Engineering Sri Sai Ram Institute of Technology Chennai India Department of Artificial Intelligence and Data Science Sri Sai Ram Institute of Technology Chennai India Department of Electronics and Communication Engineering K. Ramakrishnan College of Technology Trichy India

ISBN: (纸本)9789819951659

Disaster situations are dangerous, highly dynamic, and unpredictable. Human behavior after a disaster is difficult to predict because it is influenced by unknown and irrational factors. Unpredictable behavior deviates from what science refers to as "ration al choice." Creating awareness without entering disaster situations does not provide a realistic sense of the situation. It is advised to use immersive simulators to enter artificial yet authentic world’s. It is difficult to have a sense of realistic disaster scenarios when raising awareness without actually experiencing them. It is advised to use immersive simulators to enter artificial yet authentic worlds. It is difficult to have a sense of realistic disaster scenarios when raising awareness without actually experiencing them. Immersive simulations are advised since they will enable users to enter virtual yet accurate environments of natural fire disaster. Simulations can depict dangerous and novel or unique circumstances without having to deal with the severe repercussions of an emergency or actual tragedy. Immersive learning opportunities like medical simulators are excellent teaching aids. Since they allow participants to experience emergency circumstances in a safe and engaging manner, simulations can help us plan for emergencies and manage crises. The research proposal of this work is simulation of Mixed Reality (MR) is Integrated Augmented Virtual Reality (AVR). © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Mixed reality

来源：评论

学校读者我要写书评

暂无评论

Optimising IoT-Healthcare Systems with Deep Learning: Sensors data Fusion, Prognostic Modelling, and Smart Management 2

Optimising IoT-Healthcare Systems with Deep Learning: Sensor...

引用

2nd International Conference Computational and Characterization Techniques in Engineering and sciences, IC3TES 2024

作者： Veerabomma, Supraja Sika, K. Rajeswari, G. Murthy, B Satyanarayana Selvan, R. Senthamil G Pullaiah College Of Engineering and Technology Department of Ece Kurnool India Nehru Institute of Engineering And Technology Department of Artificial Intelligence and Data Science Coimbatore India India Department of Cse Odalarevu India Department of Electronics and Communication Engineering Tirupati India

ISBN: (纸本)9798350364699

Internet of Things (IoT) technologies allow real-time patient monitoring and data collection, changing healthcare. Deep learning has the potential to improve IoT-enabled medical facilities by combining sensor data, making predictions, and developing techniques to assist. The integration of sensor data is crucial for amalgamating medical, intelligent, and electronic medical record data. CNNs and RNNs excel at processing various data streams. This provides a complete patient health picture. Combining physical indications, activity levels, and outside elements may provide doctors with an accurate assessment of a patient's health. Based on historical data, predictive modelling employs deep learning to predict future health outcomes. Using LSTM networks and attention processes, IoT healthcare systems may predict illness progression, identify risk factors, and recommend early treatment. These prediction models enable fast therapies, preventative care, and resource optimization, improving patient outcomes and lowering healthcare expenditures. Deep learning helps to create patient-specific smart management approaches. Using real-time monitoring data and previous patient information, machine learning algorithms may create customized treatment regimens. These therapies may involve lifestyle modifications, pharmaceutical adjustments, or medical worker advice. These enlighten patients and healthcare providers to help them manage chronic diseases and make better decisions. When coupled, IoT and deep learning may transform healthcare. IoT-enabled healthcare systems may enhance patient surveillance, analysis, and treatment with improved information from sensor fusion, forecasting algorithms, and intelligent actions. This improves treatment and health outcomes. © 2024 IEEE.

关键词： Electronic health record

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：