检索结果-内蒙古大学图书馆

Image Fusion Based on NSCT and Sparse Representation for Remote Sensing Data

Computer Systems science & engineering 2023年第9期46卷 3439-3455页

作者： N.A.Lawrance T.S.Shiny Angel Department of Computational Intelligence School of ComputingCollege of Engineering and TechnologySRM Institute of Science and TechnologyChengalpattu603203India

The practice of integrating images from two or more sensors collected from the same area or object is known as image *** goal is to extract more spatial and spectral information from the resulting fused image than from the component *** images must be fused to improve the spatial and spectral quality of both panchromatic and multispectral *** study provides a novel picture fusion technique that employs L0 smoothening Filter,Non-subsampled Contour let Transform(NSCT)and Sparse Representation(SR)followed by the Max absolute rule(MAR).The fusion approach is as follows:first,the multispectral and panchromatic images are divided into lower and higher frequency components using the L0 smoothing *** comes the fusion process,which uses an approach that combines NSCT and SR to fuse low frequency ***,the Max-absolute fusion rule is used to merge high frequency ***,the final image is obtained through the disintegration of fused low and high frequency *** terms of correlation coefficient,Entropy,spatial frequency,and fusion mutual information,our method outperforms other methods in terms of image quality enhancement and visual evaluation.

关键词： Remote sensing multispectral image pan chromatic image L0 smoothening filter non-sub sampled contourlet transform sparse representation

来源：评论

学校读者我要写书评

暂无评论

Enhanced Fruit Fly Optimization Algorithm for Wrapper Based Feature Selection in Cancer Prediction 1

Enhanced Fruit Fly Optimization Algorithm for Wrapper Based ...

引用

1st International Conference on Cognitive, Green and Ubiquitous computing, IC-CGU 2024

作者： Saranya, P. Viji, D. Jangiti, Aditya School of Computing College of Engineering and Technology SRM Institute of Science and Technology Department of Computational Intelligence Tamil Nadu Chennai India School of Computing College of Engineering and Technology SRM Institute of Science and Technology Department of Computing Technologies Tamil Nadu Chennai India

ISBN: (纸本)9798350361780

Nowadays, smart healthcare appliances generate vast amount of medical data. Such huge amount of data requires classification methodologies, through which disease diagnostics can be carried out. Chronic diseases like cancer can be predicted in advance to help the patients to take treatment in initial stages of the disease. This article proposes an improvised feature selection and classification -method for cancer prediction. Here we propose an enhanced fruit fly optimization algorithm in KNN classifier for searching strategy with wrapper methods for feature selection. Lung cancer data set, breast cancer data set and leukemia data set has been taken from the UCI repository for testing the performance of the proposed model. For Lung cancer data set, accuracy, specificity, sensitivity, and fscore value observed are 96.97 %, 96.28 %, 96.35 %, and 96.34% respectively. For breast cancer dataset, accuracy, specificity, sensitivity, and fscore value observed are 99.97 %, 98.2 %, 96.85 %, and 90.35% respectively. For Breast cancer dataset, accuracy, specificity, sensitivity, and fscore value observed are 96.67%, 98.28 %, 95.85 %, and 93.85% respectively. The proposed method works well with various dataset and shows prominent accuracy improvement over the existing systems. © 2024 IEEE.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

POLYIE: A Dataset of Information Extraction from Polymer Material Scientific Literature

POLYIE: A Dataset of Information Extraction from Polymer Mat...

引用

2024 Conference of the North American Chapter of the Association for computational Linguistics: Human Language Technologies, NAACL 2024

作者： Cheung, Jerry Junyang Zhuang, Yuchen Li, Yinghao Shetty, Pranav Zhao, Wantian Grampurohit, Sanjeev Ramprasad, Rampi Zhang, Chao College of Computing United States School of Materials Science and Engineering Georgia Institute of Technology Atlanta United States

ISBN: (纸本)9798891761148

Scientific information extraction (SciIE), which aims to automatically extract information from scientific literature, is becoming more important than ever. However, there are no existing SciIE datasets for polymer materials, which is an important class of materials used ubiquitously in our daily lives. To bridge this gap, we introduce POLYIE, a new SciIE dataset for polymer materials. POLYIE is curated from 146 full-length polymer scholarly articles, which are annotated with different named entities (i.e., materials, properties, values, conditions) as well as their N-ary relations by domain experts. POLYIE presents several unique challenges due to diverse lexical formats of entities, ambiguity between entities, and variable-length relations. We evaluate state-of-the-art named entity extraction and relation extraction models on POLYIE, analyze their strengths and weaknesses, and highlight some difficult cases for these models. To the best of our knowledge, POLYIE is the first SciIE benchmark for polymer materials, and we hope it will lead to more research efforts from the community on this challenging task. Our code and data are available on: https://***/jerry3027/PolyIE. © 2024 Association for computational Linguistics.

关键词： Information retrieval

来源：评论

学校读者我要写书评

暂无评论

A Fertilizer Recommendation System for Rice Leaf Plant 9

A Fertilizer Recommendation System for Rice Leaf Plant

引用

9th International Conference on Communication and Electronics Systems, ICCES 2024

作者： Murugan, Subhiksha Manikandan, A. Hariprasad, S. College of Engineering and Technology Srm Institute of Science and Technology Department of Electronics and Communication Engineering Kattankulathur Chennai603203 India School of Computing College of Engineering and Technology Srm Institute of Science and Technology Department of Computational Intelligence Kattankulathur Chennai603203 India

ISBN: (纸本)9798350377972

The secret to increasing crop productivity and sustainability is precision farming. Optimizing fertilizer use is essential in rice cultivation to satisfy the unique nutrient requirements of crops while reducing environmental effect. Conventional techniques focus on general principles, which frequently result in reduced yields, deteriorated soil, and inefficient nutrient usage. The AI-based fertilizer recommendation system RiceFert, created for rice leaf plants, is presented in this work. The system examines crop-specific information, soil characteristics (such as type and nutrient levels), and environmental data (temperature, humidity, and wetness) using a Random Forest (RF) model and deep learning techniques. Data preparation, feature extraction, and model training are all part of the process, which compares classifiers such as Random Forest, SVM, Gradient Boosting, and Naive Bayes. The Random Forest model is superior at recommending fertilizer based on performance criteria like accuracy, precision, recall, and F1-score. This focused strategy reduces excessive or inadequate fertilizer use, increasing rice output and promoting sustainable farming. RiceFert demonstrates the potential of AI in precision agriculture by offering farmers personalized guidance that improves crop output, lowers costs, encourages environmental conservation, and helps farmers make better decisions. © 2024 IEEE.

关键词： Deep Learning Fertilizer Recommendation Precision Agriculture Rice Crop

来源：评论

学校读者我要写书评

暂无评论

Learned multiphysics inversion with differentiable programming and machine learning

引用

Leading Edge 2023年第7期42卷 474-486页

作者： Louboutin, Mathias Yin, Ziyi Orozco, Rafael Grady, Thomas J. Siahkoohi, Ali Rizzuti, Gabrio Witte, Philipp A. Møyner, Olav Gorman, Gerard J. Herrmann, Felix J. Georgia Institute of Technology School of Earth and Atmospheric Sciences AtlantaGA United States Georgia Insitute of Technology School of Computational Science and Engineering AtlantaGA United States Georgia Institute of Technology College of Computing GA Atlanta United States Utrecht University Utrecht Netherlands Microsoft Corp. RedmondWA United States SINTEF Trondheim Norway Imperial College London Department of Earth Science and Engineering London United Kingdom

We present the Seismic Laboratory for Imaging and Modeling/Monitoring open-source software framework for computational geophysics and, more generally, inverse problems involving the wave equation (e.g., seismic and medical ultrasound), regularization with learned priors, and learned neural surrogates for multiphase flow simulations. By integrating multiple layers of abstraction, the software is designed to be both readable and scalable, allowing researchers to easily formulate problems in an abstract fashion while exploiting the latest developments in high-performance computing. The design principles and their benefits are illustrated and demonstrated by means of building a scalable prototype for permeability inversion from time-lapse crosswell seismic data, which, aside from coupling of wave physics and multiphase flow, involves machine learning. © 2023 The Authors. Published by the Society of Exploration Geophysicists. All article content, except where otherwise noted (including republished material), is licensed under a Creative Commons Attribution 4.0 Unported License (CC BY). See.

关键词： Multiphysics

来源：评论

学校读者我要写书评

暂无评论

Gaussian weighting—based random walk segmentation and DCNN method for brain tumor detection and classification

引用

Multimedia Tools and Applications 2025年第8期84卷 4675-4702页

作者： Rani, K. Vijila Sumathy, G. Shoba, L.K. Sivalakshmi, P. Department of ECE Udaya School of Engineering Tamil Nadu Nagercoil India Department of Computational Intelligence SRM Institute Of Science and Technology Kattankulathur CampusChengalpattu Dt Tamil Nadu India Department of Computing Technologies SRM Institute of Science and Technology Chennai India Department of ECE R.M.K College of Engineering and Technology Tamil Nadu Chennai India

Cancer is a disease that develops when cells divide abnormally. Cancerous cells can spread to surrounding organ tissues, the bloodstream, and the lymphatic system. This process is known as metastasis, and it shortens the patients' lives. Brain cancer is a type of cancer that develops in the brain and nervous system. Typically, MR (Magnetic Resonance) scan images are used by doctors to assess the condition of tissues that have grown abnormally within the human body. A novel segmentation method with classification is specifically suggested here for assessing the tumor site. To improve the quality of an image, it first uses top hat filtering to perform the morphological process. The brain tumor region is subsequently extracted from the morphologically filtered output using the Gaussian Weighted-Based Random Walk (GWBRW) segmentation technique. Lastly, a classification operation is carried out by the Deep Convolutional Neural Network (DCNN) classifier. Five performance measures are then used to compare the segmented output with the original images. The segmentation-based assessment estimations show that the segmentation achieves higher results, with average values of 22.8160, 0.2133, and 0.9704 for PSNR, Dice, and SSIM, respectively, and lower results, with average values of 19.3997 and 422.0844 for RMSE and MSE. The segmentation results show that the suggested computation enhances the tumor region's characteristics. Eventually, the Deep Convolutional Neural Network classifier successfully classifies 96.1% of the predictions. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

A hybrid Improved Fully Homomorphic Encryption with AES to provide high security in Cloud computing

A hybrid Improved Fully Homomorphic Encryption with AES to p...

引用

2023 International Conference on Innovative computing, Intelligent Communication and Smart Electrical Systems, ICSES 2023

作者： Ravindran, K. Prabhu, S. Nagendra Easwari Engineering College SRM Institute of Science and Technology Department of Information Technology Chennai India SRM Institute of Science and Technology Department of Computational Intelligence School of Computing India

ISBN: (纸本)9798350319200

Since this information may be accessible by a third party and could compromise the client's information's confidentiality, there is a barrier between the customer and the true location of his information. The most often used approach to bridging this security gap has been to first encrypt online data using traditional methods before sending it to the cloud service provider. But to decrypt the information and complete the calculations that are required, the customer must give the server a secret key. Using homomorphic encryption, mathematical calculations can be made on encrypted information without having to first decode it. The electrocardiogram (ECG) measures and finds arrhythmias in the circulatory system. It differ from individual to individual, these characteristics are now employed for identification. So it's crucial to secure an ECG signal. A safety method known as Homomorphic Encryption (HE) handles encrypted information without the need for *** identical initial information findings are provided by HE. In this research, an Improved Fully Homomorphic Encryption (IFHE) technique using Advanced Encryption Standard (AES) is proposed for encoding the ECG measures to enhance safety while safeguarding the confidentiality of information while removing sharing key limitations. The information of the customer is encrypted in the cloud server discussed in this work, so required computations can be performed on the encrypted information. To do this, it is proposed that the method of assessment be added as a further layer of security to the AES technique, which then executes several homomorphic mathematical computations on the encrypted information in place of the initial information. To increase safety, a linear polynomial equation with changeable values is proposed for the assessment ***, the IFHEAES method has a 100% success rate in decryption (recovering the original signal) and 95.8% efficiency in categorization. Its decryption and enc

关键词： Advanced Encryption Standard Cloud computing Improved Fully Homomorphic Encryption Performance Measures Security

来源：评论

学校读者我要写书评

暂无评论

Graph Neural Networks for Optimizing Reliability in Vehicle-to-Infrastructure Communication in Autonomous Systems 9

Graph Neural Networks for Optimizing Reliability in Vehicle-...

引用

9th International Conference on Communication and Electronics Systems, ICCES 2024

作者： Neelamegam, G. Revathy, J. Kannukkiniyal, M. Devendran, M. Akshya, J. Choudhry, Mani Deepak Vsb College of Engineering and Technology Department of Computer Science and Engineering Coimbatore India Christ the King Engineering College Department of Artificial Intelligence and Data Science Coimbatore India Kongu Engineering College Department of Computer Science and Engineering Erode India Hindustan institute of technology Department of Computer Science and Engineering Coimbatore India Srm Institute of Science and Technology Department of Computational Intelligence Chennai India Srm Institute of Science and Technology Department of Computing Technologies Chennai India

ISBN: (纸本)9798350377972

High reliance on autonomous systems necessitates efficient and reliable data exchange through Vehicle-to-Infrastructure (V2I) communication to have appropriate and stable network performance in dynamic vehicular environments. With heuristic approaches, Dijkstra's algorithm, and Deep Q-Networks (DQN), several methods are proposed for optimizing latency reduction, packet delivery rate improvement, and power efficiency in the direction of V2I communications. However, these approaches suffer from important challenges: low adaptability of the network to real-time dynamics, suboptimal resource usage, and difficulties in scalability towards complex large-scale networks. In this scenario, we propose a framework that incorporates a GNN inside autonomous systems for V2I communication to optimize performance. The GNN will process real-time graph features, including signal strength, packet loss, and mobility speed, as it dynamically changes in adaptation to the evolution of network behaviour and other functions. This work shows the superiority of the proposed GNN model for the efficiency of experimentally conducted simulations compared to the current models;it achieved latency reduced by up to 28%, 5-10% PDR, and 20% energy efficiency across the various scenarios with urban, rural, highway, and suburban networks. The results validate robustness and scalability for practical implementations by the proposed approach in real-world autonomous systems. Further development is possible with this framework: for example, the use of multi-agent reinforcement learning techniques within cooperative decision-making and the enhancement through blockchain-based security mechanisms to ensure the integrity of the data. © 2024 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Leveraging Instruction-based Learning for Effective UAV Traffic Management in Dynamic Environment

Leveraging Instruction-based Learning for Effective UAV Traf...

引用

2025 International Conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Ramya, R.S. Daniel, Keren Lois Rajkumar, S. Madhavan, Sruthi S. Akshya, J. Choudhry, Mani Deepak Sri Ramakrishna Engineering College Department of Computer Science and Engineering Coimbatore India KGiSL Institute of Technology Department of Computer Science and Business Systems Coimbatore India Sona College of Technology Department of Information Technology Salem India Nehru Institute of Engineering and Technology Department of Artificial Intelligence and Data Science Coimbatore India Srm Institute of Science and Technology Department of Computational Intelligence Chennai India Srm Institute of Science and Technology Department of Computing Technologies Chennai India

ISBN: (纸本)9798331509828

With the popularization of UAVs (Unmanned Aerial Vehicles) in surveillance, delivery services, environmental monitoring, and increasingly other operational aspects, besides the need to take off and land, efficient traffic management becomes integral for assuring and securing further development and exploitation. Most of the existing traffic management systems for UAVs depend on traditional rule-based algorithms or simpler machine learning techniques, such as DQN or PPO. However, these systems also have enormous challenges: dynamic environments, high-density traffic, and robust decision-making over unpredictable weather and network conditions. In addition, the above traditional models usually experience difficulties in balancing exploration and exploitation, leading to suboptimal routing and enlarged collision risks in complicated urban airspaces. These challenges have driven us to develop a new proposal: a UA V traffic management framework based on Double Deep Q-Network (DDQN) combined with Instruction-Based Learning. In this approach, advanced learning for DDQN optimizes processes at decision-making points for UAVs. The model proposed herein, along with comprehensive simulations and quantitative analyses, demonstrated higher performance in terms of leadership and cumulative rewards while keeping lower training loss compared to the classical algorithms such as DQN, A3C, and PPO. At the same time, the DDQN model presented a better success rate (95%), as also reflected in the balanced precision-recall curve showing an area under the curve of 0.90, over others in the on-point prediction of UAVstate and safety margin of collision. Our experimental results demonstrate that the proposed DDQN-based framework significantly enhances UA V traffic management by optimizing energy consumption in complex airspaces and reducing the risk of collision. © 2025 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Design of Approximate Multiplier using Highly Compressed 5_2 Counter 6

Design of Approximate Multiplier using Highly Compressed 5_2...

引用

6th International Conference on Mobile computing and Sustainable Informatics, ICMCSI 2025

作者： Nelmin, Bathlin N. Shaji, R.S. Hariprasad, S. Shettygari, Sudeshna Vasan, J.K. Vijayan, V. Department of Electronics and Communication Engineering University College of Engineering Nagercoil India Department of Computer Science and Engineering St. Xavier’s Catholic College of Engineering Nagercoil India Department of Computational Intelligence School of Computing SRM Institute of Science and Technology Kattankulathur Chennai India Department of Electronics and Communication Engineering SRM Institute of Science and Technology Kattankulathur Chennai India

ISBN: (纸本)9798331522667

Approximate computing effectively impacts low-power VLSI circuits by reducing circuit overhead. It introduces minimal error in the output, which does not significantly affect the application. This paper proposes an approximate multiplier constructed using 5_3 and 5_2 counters. The proposed 5_2 counter delivers two outputs instead of three, thereby achieving 60% compression. The overhead of the 5_2 counter circuit is reduced, achieving a power delay product (PDP) improvement of 18%. This reduction comes with an addition of an 6% error rate. The newly designed multiplier has less delay, where the Mean error distance (MED) is kept as low as possible. The complexity of the 5_2 counter is also reduced since the counter uses only a full adder and three gates. This is achieved by applying various error optimization mechanisms. The error parameters, (i) Error Distance (ED), and (ii) Mean Error Distance (MED) are analyzed and compared with existing works. The proposed multipliers are involved in image contrast application with better Peak Signal to Noise Ratio (PSNR) value. © 2025 IEEE.

关键词： Delay circuits

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：