检索结果-内蒙古大学图书馆

International Conference on Systems, Control and Automation, ICSCA 2023

作者： Yeswanth, P.V. Khera, Ananya Deivalakshmi, S. Department of Electronics and Communication Engineering National Institute of Technology Tiruchirappalli India Department of Electronics and Communication Engineering Government Polytechnic Parvathipuram Andhra Pradesh Nissankapuram India

ISBN: (纸本)9789819773831

Crop diseases caused by a variety of fungi, viruses, bacteria and insects has been a serious problem that requires global attention for generations. Therefore, as soon as crop disease diagnosis should be done to prevent yield loss and increase monetary value. In this paper, the Autonomous Attention Feedback Network (AAFN) model is proposed to produce Super Resolution images. The proposed AAFN model obtained PSNR 30.35, 36.469, 37.846 and SSIM 0.7262, 0.9934, 0.9395 for super-resolution factors 2, 4 and 6 respectively, with classification accuracies of 99.73, 98.62 and 97.18. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Plant diseases

来源：评论

学校读者我要写书评

暂无评论

Glaucoma Detection using HOG based features with Feed-forward Neural Networks and Extreme Learning Machine 2

Glaucoma Detection using HOG based features with Feed-forwar...

引用

2nd IEEE International Conference on Networks, Multimedia and Information technology, NMITCON 2024

作者： Ananya, S. Apoorva, G. Mohan Babu, T.N. Bharath, K.P. Reva University School of Electronics and Communication Engineering Bengaluru India

ISBN: (纸本)9798350372892

Globally, glaucoma is the second most prevalent cause of blindness. It is an eye ailment that doesn't manifest symptoms until there has been a noticeable loss of vision, so early diagnosis is essential to reducing the risk of vision loss. This study assesses the efficacy of deep learning techniques in detecting glaucoma. It looks into feature extraction using the Histogram of Oriented Gradients method and classifies healthy and glaucoma-affected images using two models: Feedforward Neural Network (FNN), and Extreme Learning Machine (ELM). The datasets used to evaluate the HRF and DRISHTI-GS datasets. The study shows that the HOG-ELM provides the accuracy of 84.62% and 93.55% for DRISHTI-GS and HRF dataset respectively. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing Blurred Image Processing with IoT Integration for Improved Clarity 2

Enhancing Blurred Image Processing with IoT Integration for ...

引用

2nd IEEE International Conference on Emerging Research in Computational Science, ICERCS 2024

作者： Tummalapalli, Geetamma Summia Parveen, H. Ramesh, S.M. Monica, P. Santhiya, B. Rajasekaran, Arun Sekar GMR Institute of Technology Department of Electronics and Communication Engineering Rajam India Sri Eshwar College of Engineering Department of Computer Science Engineering Coimbatore India KPR Institute of Engineering and Technology Department of Electronics and Communication Engineering Coimbatore India GITAM Deemed to be University Department of Electronics and Communication Engineering GST Visakhapatnam India Bannari Amman Institute of Technology Department of Information Technology Sathyamangalam India SR University Department of Electronics and Communication Engineering Warangal India

ISBN: (纸本)9798331534950

A blurred image is an image that has undergone a blurring or smoothing effect, resulting in a loss of sharpness and clarity. Blurring is a technique used in image processing to reduce noise, remove unwanted details, or create a visual effect. It involves averaging or blending neighboring pixels to create a smoother appearance. The specific processing techniques and algorithms used will depend on the nature and extent of the blur, the intended outcome, and the available software or programming tools. It's important to experiment with different methods and parameters to achieve the desired result. IoT (Internet of Things) can be used in image processing in several ways to enhance functionality, efficiency, and data processing capabilities enhances image processing by enabling real-time analysis, edge computing capabilities, integration with other IoT devices, and remote monitoring and control. These advancements facilitate applications such as object detection, image recognition, and real-time decision-making, contributing to more efficient and intelligent systems in various domains. Here is a proposed model for blurred image processing with IoT. This proposed model demonstrates the integration of IoT devices, image processing techniques, and cloud-based analytics to address the challenges of blurred image processing. It combines edge processing for real-time analysis and cloud-based processing for more complex algorithms, enabling efficient and intelligent image processing applications in various domains. © 2024 IEEE.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

Harnessing Hierarchical Attention Networks for Effective Document Classification in Handling Long Texts

Harnessing Hierarchical Attention Networks for Effective Doc...

引用

2024 International Conference on Cybernation and Computation, CYBERCOM 2024

作者： Jemila, S. Jacily Shoba, S.J.Grace Mc, Shanker Sathishkumar, A. Rubitha, K. Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Department of Electronics and Communication Engineering Chennai India Velammal Engineering College Department of Electronics and Communication Engineering Chennai India Saveetha University Department of Electronics and Communication Engineering Chennai India CARE College of Engineering Trichy Department of Electronics and Communication Engineering Tamil Nadu India

ISBN: (纸本)9798331542344

This paper presents a Hierarchical Attention Network (HAN) designed to improve document classification, particularly for long texts. By utilizing both word- and sentence-level attention mechanisms, HAN captures essential local and global contextual information, addressing challenges faced by traditional models such as SVM, CNN, and LSTM. The model was evaluated on three benchmark datasets AG News, IMDB Reviews, and Reuters-21578 where it consistently outperformed these traditional approaches in terms of classification accuracy, precision, recall, and F1-score. Additionally, HAN demonstrated competitive performance compared to the transformer-based BERT model, especially in handling structured, lengthy documents. An ablation study confirmed that both word- and sentence-level attention mechanisms are critical for the model's effectiveness, as removing either led to significant drops in performance. Although HAN requires more computational resources than simpler models, it strikes a balance between efficiency and accuracy, making it suitable for real-world applications such as news categorization, legal document analysis, and opinion mining. The proposed HAN model proves to be a robust solution for document classification, particularly in tasks involving long and complex texts. Its hierarchical structure provides a significant advantage over traditional flat models, enabling more accurate and context-aware classifications. © 2024 IEEE.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Improved Camshift algorithm based on ECA-ResNet model for laser spot tracking in UOWC systems

引用

Optics Letters 2025年第10期50卷 3225-3228页

作者： Chen, Danyang Guo, Xinyu Li, Zhao Hao, Rui Lu, Huimin Jin, Jianli Wang, Jianping School of Computer and Communication Engineering University of Science and Technology Beijing Beijing100083 China

This Letter proposes an improved Camshift algorithm based on the efficient channel attention (ECA)-ResNet model for laser spot tracking in underwater optical wireless communication (UOWC) systems. Experimental results demonstrate that the proposed Cam-ECANet algorithm can maintain the center location error (CLE) within 12 pixels and support a real-time tracking speed of 50 mm/s. In disturbed underwater environments, it achieves 58.5% and 61.6% BER reduction compared to Cam-ResNet and Cam-Kalm algorithms, effectively ensuring the reliability of the wireless laser communication and tracking system. © 2025 Optica Publishing Group. All rights, including for text and data mining (TDM), Artificial Intelligence (AI) training, and similar technologies, are reserved.

关键词： CCD cameras Deep learning Diode lasers Laser beams Laser communications Optical wireless communication

来源：评论

学校读者我要写书评

暂无评论

Deep-Dixon: Deep-Learning frameworks for fusion of MR T1 images for fat and water extraction

引用

Multimedia Tools and Applications 2024年 1-22页

作者： Laddha, Snehal V. Ochawar, Rohini S. Gandhi, Krushna Zhang, Yu-Dong Department of Electronics Engineering School of Electrical and Electronics Engineering Ramdeobaba University Maharashtra Nagpur440013 India Department of Electronics and Communication Engineering School of Electrical and Electronics Engineering Ramdeobaba University Maharashtra Nagpur440013 India M. D. Radiology Gandhi Sonography Clinic Nagpur India Department of Information Technology Faculty of Computing and Information Technology King Abdulaziz University Jeddah21589 Saudi Arabia

Medical image fusion plays a crucial role in understanding the necessity of medical procedures and it also assists radiologists in decision-making for surgical operations. Dixon has mathematically described a fat suppression technique that differentiates between fat and water signals by utilizing in-phase and out-of-phase MR imaging. The fusion of MR T1 images can be performed by adding or subtracting in-phase and out-phase images, respectively. The dataset used in this study was collected from the CHAOS grand challenge, comprising DICOM data sets from two different MRI sequences (T1 in-phase and out-phase). Our methodology involved training of deep learning models;VGG 19 and RESNET18 to extract features from this dataset to implement the Dixon technique, effectively separating the water and fat components. Using VGG19 and ResNet18 models, we were able to accomplish the image fusion accuracy for water-only images with EN as high as 5.70, 4.72, MI as 2.26, 2.21;SSIM as 0.97, 0.81;Qabf as 0.73, 0.72;Nabf as low as 0.18, 0.19 using VGG19 and ResNet18 models respectively. For fat-only images we have achieved EN as 4.17, 4.06;MI as 0.80, 0.77;SSIM as 0.45, 0.39;Qabf as 0.53, 0.48;Nabf as low as 0.22, 0.27. The experimental findings demonstrated the superior performance of our proposed method in terms of the enhanced accuracy and visual quality of water-only and fat-only images using several quantitative assessment parameters over other models experimented by various researchers. Our models are the stand-alone models for the implementation of the Dixon methodology using deep learning techniques. This model has experienced an improvement of 0.62 in EN, and 0.29 in Qabf compared to existing fusion models for different image modalities. Also, it can better assist radiologists in identifying tissues and blood vessels of abdominal organs that are rich in protein and understanding the fat content in lesions. © The Author(s), under exclusive licence to Springer Science+Business

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Self Sufficient Charging Control System for Electric Bicycle Application 5

Self Sufficient Charging Control System for Electric Bicycle...

引用

5th International Conference on Intelligent communication Technologies and Virtual Mobile Networks, ICICV 2024

作者： Pradheep, K. Prakash, N. Gowrishankar, R. Keerthivel, P. Rahul, K. Siddiq, M. Kit - Kalaignarkarunanidhi Institute of Technology Department of Electrical and Electronics Engineering Department of Electronics and Communication Engineering Coimbatore India

ISBN: (纸本)9798350385649

Electric bicycles are currently a global trend, and our project aims to be at the forefront of pioneering this technology. The establishment of an electric bicycle system is our initial focus, with a commitment to simplicity and independence. Central to this initiative is the integration of a Brushless Direct Current BLDC motor seamlessly into the front wheel, serving as into electrical energy through a voltage booster circuit, efficiently meeting the battery's requirements. This innovative power regeneration system not only amplifies efficiency but also extends the bicycle's range, positioning it as a sustainable mode of transport. Our ongoing focus revolves around optimizing the front wheel setup with a generator, aiming for seamless integration to further enhance the overall riding experience. The implementation of Blynk Internet of Things (IoT) technology for real- time monitoring of energy generation through mobile devices completes our vision of promoting a greener urban transit system. a core component to enhance energy efficiency and extend the bicycle's range while maintaining aerodynamic integrity. The primary rear- wheel motor serves a dual purpose by propelling the electric bicycle and charging the battery. Simultaneously, the front wheel contributes by generating power and converting kinetic energy © 2024 IEEE.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Optimizing Energy-Efficient Routing in Wireless Sensor Networks via Genetic Algorithm for Enhanced Performance

Optimizing Energy-Efficient Routing in Wireless Sensor Netwo...

引用

2024 International Conference on Cybernation and Computation, CYBERCOM 2024

作者： Mc, Shanker Saraswathi, D. Deepalakshmi, R. Jemila, S. Jacily Sathishkumar, A. Saveetha University Department of Electronics and Communication Engineering Chennai India Sri Krishna College of Engineering Department of Electronics and Communication Engineering Arakkonam India CARE College of Engineering Department of Electronics and Communication Engineering Tamil Nadu Trichy India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Department of Electronics and Communication Engineering Chennai India

ISBN: (纸本)9798331542344

Wireless Sensor Networks (WSNs) are employed in various fields like environment monitoring and smart cities in which well-defined routing with less energy consumption for path discovery is a major area of concern for longer network lifetime and better efficiency. This work focuses on energy efficiency in WSNs with an emphasis on routing optimization through Genetic Algorithms (GAs). The above approach therefore uses GAs to search for the best route plan that will help transfer data at high rates while, at the same time causing low energy utilization. Specifically, the routing paths are encoded as chromosomes, and crossover and mutation operations are performed on these chromosomes;the fitness estimation of the solutions is made based on the energy and network performance functions. The proposed GA-based routing protocol is analyzed and compared with LEACH and Direct Transmission and the congestion control and average energy consumption proves that the protocol has an improved network lifetime, less packet delivery ratio. A closer look at the results show that population size if increased and the mutant rate if optimised improves the performance of the algorithm. Moreover, there are numerous integration of GA with other Algorithms such as Particle Swarm Optimization (PSO), Ant Colony Optimization (ACO) and so on. Thus, the obtained results reveal the effectiveness of the GA-based methods for designing efficient and power-aware routing algorithms in WSNs, which will help to design more effective and resource-saving networks in the future. It will be of future work to improve these algorithms and to investigate on how to apply it in dynamic and real-life conditions. © 2024 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

A novel fractional uplink power control framework for self-organizing networks

引用

Digital communications and Networks 2023年第6期9卷 1434-1440页

作者： Zezhou Luo Hongcheng Zhuang Wireless Technology Innovation Center Guangdong Communications and Networks InstituteShenzhen510663China School of Electronics and Communication Engineering SUN YAT-SEN UniversityShenzhen518107China

Internet of things and network densification bring significant challenges to uplink *** depending on optimization algorithm enhancements is not enough for uplink *** control intercell interference,Fractional Uplink Power Control(FUPC)should be optimized from network-wide perspective,which has to find a better traffic distribution ***,traffic distribution is geographic-based,and ineffective due to tricky locating *** paper proposes a novel uplink power management framework for Self-Organizing Networks(SON),which firstly builds up pathloss-based traffic distribution model and then makes the decision of FUPC based on the ***-based Traffic Distribution(PLTD)aggregates traffic based on the propagation condition of traffic that is defined as the pathloss between the position generating the traffic and surrounding *** show that the improvement in optimization efficiency of FUPC with PLTD can be up to 40%compared to conventional GeoGraphic-based Traffic Distribution(GGTD).

关键词： 5G and beyond Self-organizing networks Uplink power control Optimization efficiency Traffic distribution

来源：评论

学校读者我要写书评

暂无评论

An efficient Dense-Resnet for multimodal image fusion using medical image

引用

Multimedia Tools and Applications 2024年第26期83卷 68181-68208页

作者： Ghosh, Tanima Jayanthi, N. Electronics and Communication Engineering Department Delhi Technological University Bawana Road 42 Delhi India Bhagwan Parshuram Institute of Technology Affiliated to GGSIPU Delhi India Electronics and Communication Engineering Delhi Technological University Bawana Road 42 Delhi India

Nowadays, the visual content of various medical images is increased through multimodal image fusion to gather more information from medical images. The complementary information available in various modalities is merged to increase the visual content of the image for quick medical diagnosis. However, the resultant fused multi-modality images suffered from different issues, like texture distortion and gradient, mainly for the affected region. Thus, a hybrid deep learning model, Dense-ResNet is designed for the fusing of multimodal medical images from different modalities in this research work. The images from three different modalities are collected initially, which are individually pre-processed by using a median filter. The pre-processed image of the spatial domain is transformed into a spectral domain by applying Dual-Tree Complex Wavelet Transform (DTCWT), and the transformed image is segmented using Edge-Attention Guidance Network (ET-Net). Finally, the multimodal fusion of medical images is performed on the segmented images using the designed Dense-ResNet model. Moreover, the superiority of the designed model is validated, which shows that the designed Dense-ResNet model outperforms as compared with other existing multimodal medical image fusion approaches. The Dense-ResNet model achieved 0.402 Mean Square Error (MSE), 0.634 Root Mean Square Error (RMSE), and 47.136 dB Peak Signal to Noise Ratio (PSNR). © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Mean square error

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：