检索结果-内蒙古大学图书馆

3rd International Conference on Intelligent Systems and Sustainable Computing, ICISSC 2023

作者： Sudhane, G. Sai Rao, G. Venkateswara Vani, V. Karthik, N. Department of Electrical and Electronics Engineering Puducherry India Department of Computer Science and Engineering National Institute of Technology Puducherry Puducherry Karaikal609609 India

ISBN: (纸本)9789819783540

Post-pandemic, with the advent of many OTT platforms, there are a number of different movies and web series available which makes it difficult for the users to find a suitable movie to watch. So the movie recommendation system helps the users by recommending some movies based on their past search history, their interests and also considering the movie genre, actors, director and movie ratings. Our system uses a hybrid filtering technique which makes the system suitable for new users as well by considering the interests of various other users using SVD. Sentimental Analysis is done using a Sentiment Intensity Analyzer (SIA). Since it uses the most accurate methods, it makes the system a robust one. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Advancing Liver Cancer Diagnosis: Innovative Deep Learning Algorithms for Segmentation and Classification

Advancing Liver Cancer Diagnosis: Innovative Deep Learning A...

引用

2024 International Conference on Integration of Emerging Technologies for the Digital World, ICIETDW 2024

作者： Suganthi, B. Vidhya, U. Dhanalakshmi Srinivasan University School of Engineering and Technology Department of Electronics and Communication Engineering Trichy India Dhanalakshmi Srinivasan University School of Engineering and Technology Department of Computer Science and Engineering Trichy India

ISBN: (纸本)9798331541170

Liver cancer is a significant worldwide health issue that requires precise diagnosis techniques and efficient treatment options. This paper presents sophisticated deep learning (DL) algorithms for the segmentation and classification of liver cancers, providing a thorough comparative comparison. The advancements in DL have led to significant progress in other domains. As a result, there is a rising excitement for using DL techniques in liver research to aid clinicians in diagnosing and treating medical conditions. The Improved Fully Convolutional Neural Network (IFCNN) has been introduced in this study as a solution to the problem of liver tumor segmentation in cases of liver cancer. The IFCNN has been mathematically designed to address this issue. Transfer learning improves the ability to apply knowledge gained from one patient group to other patient groups with different characteristics. Comparative studies performed against ResNet and VGG16 demonstrate higher sensitivity, specificity, and overall classification metrics. The algorithms' efficacy and real-time processing capabilities have been extensively validated on multiple datasets, including different kinds and stages of liver cancer. This paves the way for eventual incorporation into clinical processes. These advanced algorithms exhibit superior precision and efficiency compared to current models, offering significant potential for improving clinical practice. They provide more dependable tools for precise diagnosis and informed treatment planning in the fight against liver cancer. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

ForeScanGuard: Proactive Monitoring and Detection for Sustainable Forest Conservation 7

ForeScanGuard: Proactive Monitoring and Detection for Sustai...

引用

7th International Conference on Inventive Computation Technologies, ICICT 2024

作者： Krishnan, R. Santhana Balamurugan, S. Rekha, M. Jose, R. Arul Haribabu, K. Muthu, A. Essaki Scad College of Engineering And Technology Department of Electronics And Communication Engineering Cheranmahadevi India Velammal College of Engineering And Technology Department of Mathematics Madurai India P.S.R.R College of Engineering Department of Computer Science And Engineering Sivakasi India RajaRajeswari College of Engineering Department of Electrical And Electronics Engineering Bangalore India Scad College of Engineering And Technology Department of Mechanical Engineering Cheranmahadevi India Scad College of Engineering And Technology Department of Computer Science And Engineering Cheranmahadevi India

ISBN: (纸本)9798350359299

In response to the increasing environmental threats, ForeScanGuard emerges as a vital forest monitoring system. Integrating advanced sensors and a proactive anomaly detection algorithm, it employs a 5-channel fire sensor for early fire detection, ultrasonic and vibration sensors for identifying tree cutting activities, and a BMP120 sensor to confirm tree falls. GPS modules attached to trees allow real-time location tracking, transmitted via Wi-Fi to a cloud server. The ForeScanGuard Algorithm analyzes sensor data for anomalies like fire outbreaks, illegal logging, and tree falls. Its proactive alerts facilitate rapid responses from forest officials, ensuring effective forest management. ForeScanGuard, with multiple sensors and cloud-based analytics, represents a significant advancement in smart forest monitoring, promoting conservation efforts through real-time anomaly detection and informed decision-making. This comprehensive solution enhances ecosystem protection, fostering a sustainable and proactive approach to forest conservation. © 2024 IEEE.

关键词： Deforestation

来源：评论

学校读者我要写书评

暂无评论

Open-Source Visual Target-Tracking System Both on Simulation Environment and Real Unmanned Aerial Vehicles 2nd

Open-Source Visual Target-Tracking System Both on Simulation...

引用

2nd International Congress of Electrical and computer engineering, ICECENG 2023

作者： Yılmaz, Celil Ozgun, Abdulkadir Erol, Berat Alper Gumus, Abdurrahman Electrical and Electronics Engineering Izmir Institute of Technology Izmir Turkey Computer Engineering Izmir Institute of Technology Izmir Turkey Meshine Swarm Technologies Izmir Turkey

ISBN: (纸本)9783031527593

This work presents an investigation into the domain of dynamic target tracking through object detection, particularly emphasizing the context of open-source applications like PX4, ROS, and YOLO. Over the years, achieving real-time object tracking on UAVs in dynamic environments has been a formidable challenge, necessitating offline computations or substantial onboard processing resources. However, contemporary UAVs are now equipped with advanced edge embedded devices, sensors, and cameras, enabling the integration of deep learning-based vision applications. This advancement offers the prospect of directly deploying cutting-edge applications onto UAVs, thereby expanding their utility in areas such as surveillance, search and rescue, and videography. To fully harness the potential of these vision applications, a communication infrastructure interfacing with the UAV’s underneath closed controllers becomes imperative. We’ve developed an integrated visual target-tracking system that connects a flight controller unit with a graphical unit by leveraging ROS tools and open-source deep learning packages. The overall integrated system based on ROS, deep learning applications, and custom PID controllers is shared on GitHub as open-source software package in a way that benefits everyone interested: https://***/miralab-ai/vision-ROS. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Multi-scale network for single image deblurring based on ensemble learning module

引用

Multimedia Tools and Applications 2025年第11期84卷 9045-9064页

作者： Wu, WenBo Pan, Yun Su, Na Wang, JingTao Wu, ShaoChuan Xu, ZeKun Yu, YouJian Liu, YaPeng State Key Laboratory of Media Convergence and Communication Communication University of China Beijing100024 China School of Computer and Cyberspace Security Communication University of China Beijing100024 China School of Electronics and Information Engineering Harbin Institute of Technology Harbin150080 China College of Computer and Control Engineering Northeast Forestry University Harbin150040 China School of Computer and Information Engineering Tianjin Chengjian University Tianjin300384 China School of Computer Science and Technology Anhui University Hefei230601 China

In this paper, we have identified two primary issues with current multi-scale image deblurring methods. On the one hand, the blurring scale is ignored. On the other hand, the context information of images is not fully utilized, and the spatial detail information of images is lost. To better solve the above problems, on top of that, this paper proposes a multi-scale network for single image deblurring. The designed network contains two parts: 1) Ensemble Learning Model: The Weak Learning Model in this module connects multiple weak learners in series to increase network depth. Moreover, through multi-scale feature ensemble module, the output features and intermediate features of different weak learner are integrated, and finally strong learner is used to enhance the features with semantic information at different scales;2) Spatial Feature Enhancement Module: This module can preserve spatial detail information of images and compensate for the disadvantages of losing image spatial details due to continuous downsampling in the Ensemble Learning Model structure. Our proposed deblurring model has been extensively evaluated on several benchmark datasets, and the model achieves superior performance compared to the most advanced deblurring methods. In particular, the peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM) values are 33.57 dB and 0.965 on the GoPro dataset, respectively, with PSNR and SSIM improving by 0.49 dB and 0.002 over NAFNet, and 0.65 dB and 0.004 over Restormer. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

AquaVision Dehaze and Enhancement: A Robust Algorithm for Improving Underwater Image Quality in Aquatic Environments 2

AquaVision Dehaze and Enhancement: A Robust Algorithm for Im...

引用

2nd International Conference on computer Vision and Internet of Things, ICCVIoT 2024

作者： Vijayalakshmi, M. Sasithradevi, A. Spoorthi, J.S. Prakash, P. School of Electronics Engineering Vellore Institute of Technology Chennai India Centre for Advanced Data Science Vellore Institute of Technology Chennai India School of Computer Science and Engineering Vellore Institute of Technology Chennai India Department of Electronics Engineering Madras Institute of Technology Chennai India

ISBN: (数字)9781837242535

ISBN: (纸本)9781837242672

Underwater imaging is frequently challenged by light scattering, leading to haze, color distortion, and visibility loss. To address these issues, we introduce the AquaVision Dehaze and Enhancement algorithm to improve underwater image quality. Extensive testing on a dataset from an aquaculture environment demonstrates that the algorithm significantly enhances image clarity. Quantitative evaluations reveal high performance across various image quality metrics, with scores of UICM (19.6463), UISM (18.1490), UIConM (26.7463), and UIQM (13.3312). Furthermore, the algorithm delivers competitive results in no-reference image quality metrics, including NIQE (3.6780), Entropy (7.5942), PIQE (52.1444), and BRISQUE (35.9847). These results highlight the algorithm's effectiveness in addressing the challenges of underwater imaging and illustrate the effectiveness through an ablation study. The AquaVision Dehaze and Enhancement algorithm offers a robust solution for improving the quality making it a valuable tool for advancing research in aquatic environments. © The Institution of engineering & technology 2024.

关键词： Aquaculture

来源：评论

学校读者我要写书评

暂无评论

Hybrid hesitant fuzzy linguistic bi-objective binary coyote clustering based segmentation and classification for land use land cover in hyperspectral image

引用

International Journal of Information technology (Singapore) 2024年第1期16卷 525-534页

作者： Yele, Vijaykumar P. Alegavi, Sujata Sedamkar, R.R. Department of Electronics and Telecommunication Engineering Thakur College of Engineering and Technology Maharashtra Mumbai 400101 India Department of Internet of Things Thakur College of Engineering and Technology Maharashtra Mumbai 400101 India Department of Computer Engineering Thakur College of Engineering and Technology Maharashtra Mumbai 400101 India

Land use and land cover segmentation and classification from hyperspectral image is significant in many land use inventories. Though several techniques have been proposed for classification of land use and land cover, the classification accuracy is low in the prevailing approaches. This manuscript offers Auto-Metric Graph Neural Network to improve the Land Use/Land Cover (AMGNN-LU/LC) classification. Land use and land cover classification is assessed with the help of EuroSAT dataset. The input image is enhanced with preprocessing method called Anisotropic Diffusion Kuwahara Filtering (ADKF). After preprocessing, Hesitant Fuzzy Linguistic Bi-objective Clustering (HFLBC) technique is utilized for segmentation. The Binary Coyote Optimization Algorithm (BCOA) is used for optimizing hesitant fuzzy linguistic bi-objective clustering. The segmented image is classified into land use/ land cover with the help of auto-metric graph neural network. The introduced method is implemented in PYTHON. The proposed approach attains 99% precision, 98.30% accuracy, 99% F1-score, 99.2% recall, 98.1% sensitivity, 99% specificity, 98% Structural Similarity Index Measure (SSIM), 44 dB Peak Signal-to-Noise Ratio (PSNR) and 2.7 s computational time and 0.12% loss. The AMGNN-LU/LC’s efficiency is compared to the prevailing approaches. © 2023, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of computer Applications and Management.

关键词： Anisotropic diffusion Kuwahara filtering Binary coyote optimization algorithm Hyperspectral image Land use and land cover classification Land use and land cover segmentation

来源：评论

学校读者我要写书评

暂无评论

Effective segmentation of land-use and land-cover from hyperspectral remote sensing image

引用

International Journal of Information technology (Singapore) 2024年第4期16卷 2395-2412页

Hyperspectral images (HSI) provide valuable data for Land-Use and Land-Cover (LU/LC) segmentation. Detecting buildings, roads, and LU/LC labels in satellite images is crucial for various applications. This research introduces a method combining Hybrid Dynamic Arithmetic Edge Detection with Bi-directional Long Short-Term Memory UNet (BiLSTMUNet) for segmentation. Initially, enhance the image quality with an Approximate Adaptive Noise Variance Wiener filtering technique (AANVW), and perform dynamic spatial-spectral feature extraction on pre-processed images. The proposed segmentation system is a hybrid of Arithmetic Optimization (AO) and BiLSTMUNet, reducing the entropy loss function. Then, processed a substantial amount of remote sensing images to achieve improved LU/LC segmentation. Results show the effectiveness of BiLSTMUNet with an accuracy of 98.5% on EuroSAT and 97.5% on DeepGlobe datasets. This approach holds promise for accurate and efficient high-resolution remote sensing image analysis. © 2024, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of computer Applications and Management.

关键词： Hyperspectral imaging Land cover Land use Segmentation Spatial features

来源：评论

学校读者我要写书评

暂无评论

Hybrid CNN-LSTM Model for Enhanced Weather Forecasting: Leveraging Spatial and Temporal Dependencies 4

Hybrid CNN-LSTM Model for Enhanced Weather Forecasting: Leve...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Vallileka, N. Rajkumar, G.Vinoth Krishnan, R. Santhana Shankar, S. Vijay Francis Raj, J. Relin Karthikeyan, M. Saravana Psna College of Engineering and Technology Department of Computer Applications Dindigul India J. P. College of Engineering Department of Electronics and Communication Engineering Tenkasi India Scad College of Engineering and Technology Department of Electronics and Communication Engineering Cheranmahadevi India Sona College of Technology Department of Electrical and Electronics Engineering Salem India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Electronics and Communication Engineering Chennai India Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Avadi Chennai India

ISBN: (纸本)9798331523923

Accurate weather forecasting is critical for decision-making in agriculture, disaster management, urban planning, and numerous other domains. Traditional forecasting methods often struggle to capture the intricate spatial and temporal dependencies in weather data. This work proposes a hybrid deep learning model that integrates Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks to address these challenges. The CNN component efficiently extracts spatial features from satellite images, such as cloud formations and precipitation zones, while the LSTM network models the temporal dependencies inherent in meteorological data, such as temperature, humidity, and wind speed. The model is trained on a dataset comprising historical weather records and satellite imagery, spanning several years. PyTorch, a dynamic deep learning framework, is used to implement and train the hybrid architecture. Data preprocessing involves normalization, image augmentation, and sequence structuring to prepare inputs for the model. The CNN layers, built with convolutional and pooling operations, extract spatial features, which are combined with temporal weather data and passed to the LSTM network. The LSTM layers capture long-term dependencies and trends in weather patterns. Fully connected layers map the learned features to final predictions, including temperature, rainfall, and other key weather parameters. The hybrid model is evaluated using metrics such as Root Mean Square Error (RMSE) for numerical predictions and accuracy for classification tasks. Results indicate that the proposed hybrid CNN-LSTM model outperforms standalone models and traditional statistical approaches, demonstrating its ability to leverage spatial and temporal dependencies for accurate weather forecasting. This work highlights the potential of hybrid deep learning models in advancing weather forecasting capabilities, offering a scalable and reliable solution for real-world applications such as e

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

DEFECTED GROUND SQUARE PATCH EDGE TRUNCATED POLARIZATION RECONFIGURABLE ANTENNA

引用

Telecommunications and Radio engineering (English translation of Elektrosvyaz and Radiotekhnika) 2024年第5期83卷 11-24页

作者： Nikam, Pritam B. Kumar, Jayendra Baidya, Achinta Bhosale, Akshay Hake, Shahadev School of Electrical & Electronics Engineering SGU Maharashtra 416118 India School of Electronics Engineering VIT-AP University Andhra Pradesh 522237 India Department of Electronics and Communication Mizoram University Aizawl796004 India Department of E&Tc SCTR's Pune Institute of Computer Technology Pune411043 India

In this paper, a polarization reconfigurable antenna is reported. The proposed antenna operates in linear and circular polarization. Linear polarization is obtained using a square patch antenna and circular polarization is realized by truncating the diagonal corners of the square patch. Wideband circular polarization is obtained using two triangular defects to the ground plane beneath the truncated edge. To implement polarization reconfigurability, two pin diodes are placed on the truncated edges. These pin diodes electronically transform the proposed structure into square or truncated square patches resulting in linear or circular polarizations respectively. The proposed antenna operates in the 4.75 to 3 GHz band with circular polarization and the 4.75 to 1 GHz band with linear polarization. The antenna exhibits a higher peak gain of 7.7 dBi due to a low-loss foam substrate with the main lobe at 0°. A prototype of the antenna is developed and tested. © 2024 by Begell House, Inc.

关键词： Circular polarization

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：