检索结果-内蒙古大学图书馆

A Deep Recurrent Neural Network for Plant Disease Classification

SN computer science 2024年第8期5卷 1053页

作者： Singh, Divya Kumar, Ashish School of Computer Science Engineering and Technology Bennett University Greater Noida India

Agriculture is important in emerging nations like India, but food security is still a serious problem. Plant diseases, inadequate storage facilities, and poor transportation cause the majority of harvests to be squandered. Since illnesses cause almost 15% of India’s crop yield to be lost, this is a big issue that needs to be addressed. This proposed model is an automated system that can identify the diseases and assist farmers to take the necessary action to cure the crop losses. Farmers have been using the traditional method of using their own eyes to detect plant illnesses, but not all farmers can detect these diseases in the same way. computer vision capabilities must be incorporated into agriculture given the advancements in artificial intelligence. The proposed model uses a convolutional neural network (CNN) with Recurrent Neural Network (RNN) for PlantVillage dataset, the greatest publicly accessible dataset. The proposed model has a 99.37% prediction accuracy for the condition. The proposed approach can identify 14 different plant classes out of the 38 and other moderate in the Plant Village dataset shows how versatile it is. Farmers may decrease crop loss and enhance crop quality and output using this automated and user-friendly technique. In this study, we present the use of a deep recurrent neural network to automatically detect plant diseases. The resulting algorithm is used to identify the bacterial blight of rice during the growing season with a detection accuracy of 99.16%, a classification accuracy of 99.17%, and a sensor-based detection accuracy of 98.98%. Recurrent networks have made great advances in various sequence modeling, such as speech recognition, language modeling, image captioning, and many other applications in recent years. We detect the bacterial blight of rice leaves in this study with a deep recurrent network. We use a stacked LSTM-CNN network to train representations for the radio signal data collected during the lifespan of the rice

关键词： Convolutional neural network Plant disease detection Recurrent neural network Smart agriculture

来源：评论

学校读者我要写书评

暂无评论

Reset-Free Reinforcement Learning via Multi-State Recovery and Failure Prevention for Autonomous Robots

引用

Tsinghua science and technology 2024年第5期29卷 1481-1494页

作者： Xu Zhou Benlian Xu Zhengqiang Jiang Jun Li Brett Nener School of Mechanical Engineering Changshu Institute of TechnologyChangshu 215500China School of Automation Nanjing University of Science and TechnologyNanjing 210094China School of Electronic and Information Engineering Suzhou University of Science and TechnologySuzhou 215009China Faculty of Medicine and Health The University of SydneySydney 2006Australia Department of Electrical Electronic and Computer EngineeringThe University of Western AustraliaPerth 6009Australia

Reinforcement learning holds promise in enabling robotic tasks as it can learn optimal policies via trial and ***,the practical deployment of reinforcement learning usually requires human intervention to provide episodic resets when a failure *** manual resets are generally unavailable in autonomous robots,we propose a reset-free reinforcement learning algorithm based on multi-state recovery and failure prevention to avoid failure-induced *** multi-state recovery provides robots with the capability of recovering from failures by self-correcting its behavior in the problematic state and,more importantly,deciding which previous state is the best to return to for efficient *** failure prevention reduces potential failures by predicting and excluding possible unsafe actions in specific *** simulations and real-world experiments are used to validate our algorithm with the results showing a significant reduction in the number of resets and failures during the learning.

关键词： reinforcement learning manual reset multi-state recovery failure prediction

来源：评论

学校读者我要写书评

暂无评论

Elevating IDS Capabilities: The Convergence of SVM, Deep Learning, and RFECV in Network Security 2

Elevating IDS Capabilities: The Convergence of SVM, Deep Lea...

引用

2nd International Conference on Emerging Trends in Information technology and engineering, ic-ETITE 2024

作者： Kumar, G Aditya Katiyar, Aditi Srinivasan, Kathiravan Computer Science Engineering Vellore Institute of Technology Vellore India School of Computer Science and Engineering Vellore Institute of Technology Vellore India

ISBN: (纸本)9798350328202

By presenting an improved Intrusion Detection System (IDS) that combines deep learning with support vector machines (SVM), this research increases network security. The main goal is to increase the accuracy of SVM detection by using a methodical feature selection and optimization technique that is tailored to the complexity of network intrusions. 35 out of the 42 features were chosen for feature selection using RFECV, an algorithmic feature selection technique in machine learning. To ensure that the features preserved are those that contribute most to the model's predictive capacity and that the redundant features are deleted, techniques such as RFECV and feature priority ranking using ExtraTreesClassifier take the model's performance into account during the feature selection process. To improve classifier performance, optimization strategies such as hyperparameter tuning are used, focusing on important data and cutting down on redundancies. The performance of several SVM kernel functions, including linear, polynomial, RBF, and sigmoid, is compared in the study. The Linear model combined with the deep learning model was shown to perform the best. Our model outperforms current IDS frameworks, as demonstrated by comparative analysis, confirming the efficacy of integrating SVMs with deep learning for real-time threat detection. The KDD Cup 99 dataset, which has been widely used as a benchmark for assessing the performance of different IDS models, was used for the work. It offers a consistent, varied, and large dataset so that researchers may evaluate and contrast their methods. Researchers can experiment with feature selection and reduction strategies to enhance IDS performance because of the dataset's broad set of features. © 2024 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Deep ensemble model for skin cancer classification with improved feature set

引用

Multimedia Tools and Applications 2025年第10期84卷 7599-7626页

作者： Burada, Sreedhar Manjunathswamy, B.E. Kumar, M. Sunil Department of Computer Science and Engineering Don Bosco Institute of Technology Karnataka Bengaluru560074 India Department of Computer Science and Engineering School of Computing Mohan Babu University Sree Vidyanikethan Engineering College Andhra Pradesh Tirupati517102 India

Early identification of skin cancer is mandatory to minimize the worldwide death rate as this disease is covering more than 30% of mortality rates in young and adults. Researchers are in the move of proposing advanced models for the accurate classification of skin disease. This paper introduces a novel skin cancer detection model under the stages of preprocessing, feature extraction, classification as well as segmentation. The given input is first preprocessed via Gaussian filtering. Subsequently, the Deep learning model termed as ‘U-net’ is used for the segmentation process. Afterward, the extraction of the feature set including features like Improved Center symmetric Local Binary Pattern (ICS-LBP), Local Gradient Pattern (LGP), Median binary pattern (MBP) is performed. Classification takes place using Deep Ensemble Model based on the extracted features, that includes BiGRU, Deep Maxout, and Improved Deep Convolutional Neural Network (CNN), respectively. Also, as the hyperparameter tuning of the classification model enhances the performance, this work introduces a new Hybrid Atom and Arithmetic Operation Algorithm (HAAOA) algorithm for tuning the optimal weights of the Bi-GRU (Bi-directional Gated Recurrent Unit) and Deep Maxout model. At last, the validation of the proposed work is performed through different performance measures by comparing it with different algorithms. Accordingly, accuracy of the adopted method at 90th learning percentage is 93.56%, which is (~) 82.63%, 85.15%, 84.98%, 83.66% and 83.42% better than AOA, ASO, BWO, BMO and DO, respectively. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Leakage Localization of Gas Pipelines Based on Modal Acoustic Emission and Cross-Power Spectrum Peak Optimization

引用

IEEE Sensors Journal 2025年第11期25卷 19982-19992页

作者： Zhang, Wenbiao Gong, Kezheng Cui, Xiwang North China Electric Power University School of Control and Computer Engineering Beijing102206 China Beijing Information Science and Technology University School of Instrument Science and Opto-Electronics Engineering Beijing100192 China

Leakage accidents in natural gas pipelines bring huge property losses and pose serious safety risks. Therefore, faster and more accurate leakage localization is of great significance. In this article, a new method based on modal acoustic emission (MAE) and peak optimization of cross-power spectrum is proposed to enhance the performance of leakage localization. When a pipeline leakage occurs, the sensors installed on the pipelines receive acoustic emission (AE) signals, which have various modes. Instead of extracting a single mode through complex algorithms, the proposed method directly extracts the cross-power spectrum of a specified mode by choosing the appropriate window function and window parameters to locate the leakage with velocity information from dispersion curves. Gaussian, Hamming, and Blackman window functions are compared in the extraction of the cross-power spectrum of L(0, 1) mode, among which the Blackman window function is found to be the most effective. The artificial fish swarm algorithm combined with the iteration criterion for peak optimization is used to obtain suitable window parameters. Finally, the localization error of the above method is less than 5.2%. In addition, the performance of the iteration criterion for peak optimization of cross-power spectrum combined with other intelligent swarm algorithms is investigated. The results show that the maximum errors of other intelligent methods are still less than 9%, demonstrating the great compatibility of the proposed method. © 2001-2012 IEEE.

关键词： Acoustic emissions

来源：评论

学校读者我要写书评

暂无评论

Hannan Quinn Quantum Grasshopper Optimization and Attention Deep Intelligent Train Status Prediction

引用

Multimedia Tools and Applications 2024年 1-26页

作者： Singh, Ajay Dhanaraj, Rajesh Kumar Kumar, Santosh Abraham, Ajith School of Computer Science and Engineering Galgotias University Greater Noida India Pune India Department School of Computer Science Engineering & amp Technology Bennett University Uttar Pradesh Greater Noida India

Providing accurate and timely traffic information such as arriving time of train plays a significant part in intelligent train status prediction. Maximum-speed train status forecast is a significant topic as far as railway dispatching. In this paper proposes a novel train status prediction method based on the Hannan Quinn Quantum Grasshopper Optimized Attention Deep Learning (HQQGO-ADL) method introduced for accurate train status prediction. The proposed HQQGO-ADL is designed with three different processes namely preprocessing, feature selection, and prediction. This method can well capture the influence of discrete and continuous features in addition to spatiotemporal characteristics, therefore modeling train status prediction. At first, Mid-hinge Inter-Quartile Interpolation is utilized to perform preprocessing for eradicating or discarding the outliers with less train status identification time. Second, HannanQuinn Quantum Grasshopper Optimization is employed to capture the influence of discrete and continuous features on spatiotemporal characteristics, therefore modeling train status prediction. Besides, the maximum log likelihood discrete feature fine tuned to obtain continuous features. Finally, the Attention Deep Neural Train Status Prediction model is utilized for improved latency train status prediction. The overall analysis of HQQGO-ADL has better performance of higher train status prediction accuracy by 32% and lower train status prediction time, overhead, and error rate by 32%, 32%, and 27%as compared to existing techniques. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Optimizing CNN Performance for Heart Attack Detection through Grey Wolf Algorithm

Optimizing CNN Performance for Heart Attack Detection throug...

引用

2024 Asia Pacific Conference on Innovation in technology, APCIT 2024

作者： Aditya Kumar, G. Katiyar, Aditi Kannan, A. Vellore Institute of Technology Computer Science Engineering Vellore India Vellore Institute of Technology School of Computer Science and Engineering Vellore India

ISBN: (纸本)9798350361537

Better patient outcomes and prompt care depend on early detection of heart attacks. In this current work, we use the infamous MIT-BIH Arrhythmia Dataset, a reference resource for cardiac abnormality recognition, to train and validate our models. We propose an improved method for heart attack diagnosis and detection which includes a CNN model that is optimized with the help of the Grey Wolf Optimization (GWO) technique. This novel integration aims to enhance feature extraction and classification processes by tackling the drawbacks of traditional deep learning methods. A comprehensive testing process has been conducted on the proposed CNN-GWO model versus well-known deep learning models, such as Artificial Neural Networks also known as ANN, as well as many state-of-the-art machine learning models used for heart attack detection such as SVM, Decision Tree, and other ensemble learning models such as XG Boost. Our findings demonstrate a significant increase in detection accuracy and efficiency when comparing the CNN-GWO model to its rivals. This work not only demonstrates the effectiveness of combining CNN with GWO, but also demonstrates how well the proposed model performs in detecting heart attacks. This work contributes to the advancement of medical diagnostic technology by offering a more reliable and accurate diagnostic instrument. It also opens new options for algorithmic advancements in the future that forecast heart attacks. © 2024 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Towards Blockchain-Based Secure BGP Routing,Challenges and Future Research Directions

引用

computers, Materials & Continua 2024年第5期79卷 2035-2062页

作者： Qiong Yang Li Ma Shanshan Tu Sami Ullah MuhammadWaqas Hisham Alasmary Faculty of Information Technology Beijing University of TechnologyBeijing100124China School of Information Science and Technology North China University of TechnologyBeijing100144China Department of Computer Science Shaheed Benazir Bhutto UniversitySheringal18050Pakistan School of Computing and Mathematical Science Faculty of Engineering and ScienceUniversity of GreenwichLondonSE109LSUK School of Engineering Edith Cowan UniversityPerth6027Australia Department of Computer Science King Khalid UniversityAbha61421Saudi Arabia

Border Gateway Protocol(BGP)is a standard inter-domain routing protocol for the Internet that conveys network layer reachability information and establishes routes to different *** BGP protocol exhibits security design defects,such as an unconditional trust mechanism and the default acceptance of BGP route announcements from peers by BGP neighboring nodes,easily triggering prefix hijacking,path forgery,route leakage,and other BGP security ***,the traditional BGP security mechanism,relying on a public key infrastructure,faces issues like a single point of failure and a single point of *** decentralization,anti-tampering,and traceability advantages of blockchain offer new solution ideas for constructing secure and trusted inter-domain routing *** this paper,we summarize the characteristics of BGP protocol in detail,sort out the BGP security threats and their ***,we analyze the shortcomings of the traditional BGP security mechanism and comprehensively evaluate existing blockchain-based solutions to address the above problems and validate the reliability and effectiveness of blockchain-based BGP security methods in mitigating BGP security ***,we discuss the challenges posed by BGP security problems and outline prospects for future research.

关键词： BGP security blockchain prefix hijacking trust model secure routing

来源：评论

学校读者我要写书评

暂无评论

FAME: Towards Factual Multi-Task Model Editing

FAME: Towards Factual Multi-Task Model Editing

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Zeng, Li Shan, Yingyu Liu, Zeming Yao, Jiashu Guo, Yuhang School of Computer Science and Technology Beijing Institute of Technology Beijing China School of Computer Science and Engineering Beihang University Beijing China

ISBN: (纸本)9798891761643

Large language models (LLMs) embed extensive knowledge and utilize it to perform exceptionally well across various tasks. Nevertheless, outdated knowledge or factual errors within LLMs can lead to misleading or incorrect responses, causing significant issues in practical applications. To rectify the fatal flaw without the necessity for costly model retraining, various model editing approaches have been proposed to correct inaccurate knowledge within LLMs in a cost-efficient way. To evaluate these model editing methods, previous work introduced a series of datasets. However, most of the previous datasets only contain fabricated data in a single format, which diverges from real-world model editing scenarios, raising doubts about their usability in practice. To facilitate the application of model editing in real-world scenarios, we propose the challenge of practicality. To resolve such challenges and effectively enhance the capabilities of LLMs, we present FAME, an factual, comprehensive, and multi-task dataset, which is designed to enhance the practicality of model editing. We then propose SKEME, a model editing method that uses a novel caching mechanism to ensure synchronization with the real world. The experiments demonstrate that SKEME performs excellently across various tasks and scenarios, confirming its practicality. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

High-speed encrypted traffic classification by using payload features

引用

Digital Communications and Networks 2025年第2期11卷 412-423页

作者： Xinge Yan Liukun He Yifan Xu Jiuxin Cao Liangmin Wang Guyang Xie School of Cyber Science and Engineering Southeast UniversityNanjing 211189China Nanjing Huafei Data Technology Co. Ltd.Nanjing 210019China School of Computer Science and Communication Engineering Jiangsu UniversityZhenjiang 212013China

Traffic encryption techniques facilitate cyberattackers to hide their presence and *** classification is an important method to prevent network ***,due to the tremendous traffic volume and limitations of computing,most existing traffic classification techniques are inapplicable to the high-speed network *** this paper,we propose a High-speed Encrypted Traffic Classification(HETC)method containing two ***,to efficiently detect whether traffic is encrypted,HETC focuses on randomly sampled short flows and extracts aggregation entropies with chi-square test features to measure the different patterns of the byte composition and distribution between encrypted and unencrypted ***,HETC introduces binary features upon the previous features and performs fine-grained traffic classification by combining these payload features with a Random Forest *** experimental results show that HETC can achieve a 94%F-measure in detecting encrypted flows and a 85%–93%F-measure in classifying fine-grained flows for a 1-KB flow-length dataset,outperforming the state-of-the-art comparison ***,HETC does not need to wait for the end of the flow and can extract mass computing *** average time for HETC to process each flow is only 2 or 16 ms,which is lower than the flow duration in most cases,making it a good candidate for high-speed traffic classification.

关键词： Traffic classification Flow analysis Information entropy Machine learning Randomness test

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：