检索结果-内蒙古大学图书馆

An Enhancement of deep learning algorithm for Brain Tumor Segmentation Using Kernel Based CNN with M-SVM

JOURNAL OF MEDICAL SYSTEMS 2019年第4期43卷 84-84页

作者： Thillaikkarasi, R. Saravanan, S. Salem Coll Engn & Technol Dept Elect & Commun Engn Salem India Muthayammal Engn Coll Rasipuram Dept Elect & Elect Engn Rasipuram India

The brain tumor can be created by uncontrollable increase of abnormal cells in tissue of brain and it has two kinds of tumors: one is benign and another one is malignant tumor. The benign brain tumor does not affect the adjacent normal and healthy tissue but the malignant tumor can affect the neighboring tissues of brain that can lead to the death of person. An early detection of brain tumor can be required to protect the survival of patients. Usually, the brain tumor is detected using MRI scanning method. However, the radiologists are not providing the effective tumor segmentation in MRI image due to the irregular shape of tumors and position of tumor in the brain. Accurate brain tumor segmentation is needed to locate the tumor and it is used to give the correct treatment for a patient and it provides the key to the doctor who must execute the surgery for patient. In this paper, a novel deep learning algorithm (kernel based CNN) with M-SVM is presented to segment the tumor automatically and efficiently. This presented work contains several steps that are preprocessing, feature extraction, image classification and tumor segmentation of brain. The MRI image is smoothed and enhanced by Laplacian of Gaussian filtering method (LoG) with Contrast Limited Adaptive Histrogram Equalization (CLAHE) and feature can be extracted from it based on tumor shape position, shape and surface features in brain. Consequently, the image classification is done using M-SVM depending on the selected features. From MRI image, the tumor is segmented with help of kernel based CNN method.. Experimental results of proposed method can show that this presented technique can executes brain tumor segmentation accurately reaching almost 84% in evaluation with existing algorithms.

关键词： Brain tumor segmentation deep learning algorithm Kernel based CNN M-SVM Image classification

来源：评论

学校读者我要写书评

暂无评论

News Text Data Classification Method based on deep learning algorithm

International Core Journal of Engineering

引用

International Core Journal of Engineering 2022年第2期8卷 368-374页

作者： Weikun Qiang Ziyuan Jiang Xinkai Zhou Yanyu Zhu Keyu Zhu

News and information app is an important channel for news content distribution. In order to meet the different needs of different groups of people, news classification is crucial. Using automatic classification can reduce a lot of manual operation, which is a core work for the formation of information flow recommendation. This paper proposes CNN (convolutional neural network) to design news classification analysis) to solve this problem. In the daily exposure of people's news content including sports, finance, real estate, home, education, technology, technology, fashion, current politics, games, entertainment, so we decided to experiment with the data of these ten categories of news content. In the method we designed this time, they are mainly divided into four steps: loading data, processing text, text vectorization, and forming text matrix, so that the data are divided into training samples for modeling, evaluating samples for adjusting parameters, and testing samples for evaluating the model. After processing over 650,000 experimental data using python3, we showed that CNN achieved 96% accuracy and RNN achieved 94% accuracy.

关键词： deep learning algorithm Automatic Classification CNN Python3

来源：评论

学校读者我要写书评

暂无评论

Modern Art Design System Based on the deep learning algorithm

引用

JOURNAL OF INTERCONNECTION NETWORKS 2022年第SUPP05期22卷 2147014-2147014页

作者： Zhang, Yinan Shanxi Coll Appl Sci & Technol Acad Fine Taiyuan 030062 Shanxi Peoples R China

Depending on the rapid growth of technology and computer science and globalization, increasing universities and various training programs are expected to achieve increasing lifelong education currently. Based on the increase of visual saturation, one of these programs is undoubtedly visual arts creation. Nowadays, there is a need to reconsider the content of art education and arts programs in the light of modern art productions, changing aesthetic judgments, and social *** of the most challenging tasks an art teacher faces in today's classroom is explaining the meaning behind the art that is sometimes deemed meaningless or shocking. Hence, in this paper, deep learning algorithm (DLA) has been proposed for modern art *** learning outcomes in the art world shifted people's traditional views;more and more people consider that when AI eventually eliminates artists, it is not a long way. To examine the algorithm's performance in practise, experimental assessment exposes it to learning tasks. Such algorithmic features are frequently evaluated independently in terms of performance while learning a model, i.e. at training time, and performance while applying a learnt model, i.e. at test time. This article discusses the implementation of deep learning in drawing, music, literature, and describes the classical models and algorithms in those fields of art. One of the most significant aspects of utilising a deep learning technique is its capacity to perform feature engineering on its own. In this technique, an algorithm searches the data for characteristics that correlate and then combines together to facilitate quicker learning without being expressly directed to provide it. The proposed method supports a comprehensive approach to teaching and learning in the arts and outlines standards and skills for the art teacher in the content of art, knowledge of the students, instruction, curriculum development, and evaluation of student learning outcomes, program

关键词： Modern art education deep learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Optimizing urban water sustainability: Integrating deep learning, genetic algorithm, and CMIP6 GCM for groundwater potential zone prediction within a social-ecological-technological framework

引用

ADVANCES IN SPACE RESEARCH 2024年第12期73卷 5925-5948页

作者： Rahman, Mahfuzur Islam, Md Monirul Kim, Hyeong-Joo Alam, Mehtab Sadiq, Shamsher Rahman, Md Khalilur Hossan, Md Sadir Islam, Md Tariqul Raju, Matiur Rahman Alam, Md Shahrior Ahmad, Syed Ishtiaq Dewan, Ashraf Int Univ Business Agr & Technol IUBAT Dhaka 1230 Bangladesh Kunsan Natl Univ Dept Civil Engn 558 Daehakro Gunsan 54150 Jeollabugdo South Korea Int Univ Business Agr & Technol IUBAT Geomatics & Spatial Analyt Res Lab GSAR Dhaka 1230 Bangladesh Ghulam Ishaq Khan Inst Engn Sci & Technol Dept Civil Engn Topi 23640 Swabi Pakistan LGED Bhaban Local Govt Engn Dept LGED Dhaka 1207 Bangladesh Bangladesh Univ Engn & Technol BUET Dept Civil Engn Dhaka 1000 Bangladesh Curtin Univ Sch Earth & Planetary Sci Bentley WA 6102 Australia Tongji Univ Coll Civil Engn Dept Geotech Engn Shanghai 200092 Peoples R China

This study presents a novel approach to groundwater resource assessment and drought vulnerability, achieved through integrating cutting-edge deep-learning algorithms into a comprehensive framework. In regions susceptible to drought, ensuring groundwater availability is of paramount importance. Addressing this critical need, our research employs an ensemble of advanced algorithms, including long short-term memory, convolutional neural network, deep neural network, and recurrent neural network. These algorithms are further enhanced through optimization using a genetic algorithm to map groundwater potential zones (GWPZ). Leveraging model validation based on the area under the receiver operating characteristic curve (AUCROC), the long short-term memory-genetic algorithm model emerges as the superior algorithm, boasting the highest values of AUCROC: 0.995 for training and 0.996 for testing). Utilizing this optimized model, this study developed the GWPZ map, subsequently overlaying it with established drought maps developed by the Bangladesh Agricultural Research Council across distinct periods-Pre-Kharif, Kharif, and Rabi. The derived baseline GWPZ spatial distribution revealed five categories-very low (34.99%), low (27.67%), moderate (13.26%), high (11.71%), and very high (12.37%)-and their intersection with drought-prone regions, indicative of probabilities of drought occurrence ranging from very severe to low (15.14% to 24.69%). Moreover, employing the best-predicted model, this study projected future GWPZ for 2050 and 2100 using the coupled model intercomparison project 6 general circulation model data under the ambit of three distinct shared socioeconomic pathways (SSPs): SSP1-2.6, SSP2-4.5, and SSP5-8.5. Our findings suggested a contraction in the groundwater potential area by the end of the twenty-first century (2100). This pioneering integration sheds light on the intricate relationship between groundwater availability and drought susceptibility, furnishing inval

关键词： Groundwater Drought deep learning algorithm Optimizer Climate data

来源：评论

学校读者我要写书评

暂无评论

Statistical optimization of supply chain financial credit based on deep learning and fuzzy algorithm

引用

JOURNAL OF INTELLIGENT & FUZZY SYSTEMS 2020年第6期38卷 7191-7202页

作者： Hu, Zijiang Nanjing Univ Finance & Econ Nanjing 210023 Jiangsu Peoples R China

By controlling the transaction background and data of supply chain enterprises, supply chain finance can reduce the degree of information asymmetry in the process of enterprise financing and provide more financing mode options for enterprises. In this paper, the author analyzes the statistical optimization of supply chain financial credit based on deep learning and fuzzy algorithm. We use particle swarm optimization to train BP neural network and improve the previous algorithm. By changing the speed of the particle search in the weight space, that is, updating the weight of the net-work, the mean square error of the network output is gradually reduced. Simulation results show that the model is helpful to analyze the correlation between supply chain finance and economy, compared with the traditional BP neural network, the original data of BP neural network based on particle swarm optimization is better fitted, so it can be used to predict supply chain financial credit level.

关键词： deep learning algorithm supply chain finance credit rating fuzzy algorithm

来源：评论

学校读者我要写书评

暂无评论

Construction of Network Culture Security Indicator System Based on deep learning algorithm

引用

Procedia Computer Science 2023年 228卷 438-445页

作者： Kai Zhao

The Internet has become a key information infrastructure in China. However, in recent years, China's network security incidents have been frequent, thus posing a great threat to relevant software, hardware and other information infrastructure. It is very important to establish a large-scale network security situation analysis system based on existing network security infrastructure and technology to improve the processing capabilities of controlling, analyzing, and predicting network security situations. Network security situation assessment is an emerging research hotspot that has emerged in recent years. This article first defined a series of concepts such as the security indicator ring system, network culture, and deep learning algorithms, and then conducted comparative analysis through experiments. Compared with the original dataset, the classification accuracy after feature selection increased by 33.6%.

关键词： Safety Indicators Network Culture deep learning algorithm System Construction

来源：评论

学校读者我要写书评

暂无评论

Building loss assessment using deep learning algorithm from typhoon Rusa

引用

HELIYON 2024年第1期10卷 e23324页

作者： Kim, Ji-Myong Bae, Junseo Das Adhikari, Manik Yum, Sang-Guk Mokpo Natl Univ Dept Architectural Engn Mokpo 58554 South Korea Korea Univ Div Smart Cities Sejong 30019 South Korea Gangneung Wonju Natl Univ Dept Civil Engn Gangwon 25457 South Korea

Climate crises such as extreme weather events, natural disasters and climate change caused by climate transformations are causing much damage worldwide enough to be called a climate catastrophe. The private sector and the government across industries are making every effort to prevent and limit the increasing damage, but the results have yet to meet market demand. Therefore, this study proposes a method that uses a deep learning algorithm to predict the damage caused by typhoons. Model development is based on a deep Neural Network (DNN) algorithm, and learning data is obtained by fine-tuning the network structure and hyperparameters;the amount of damage caused by Typhoon Rusa was known as training data. The constructed DNN model underwent evaluation and validation by computation of mean absolute error (MAE) and root mean square error (RMSE). Furthermore, a comparative analysis was conducted to confirm the applicability of the proposed framework against a traditional multiregression model to ensure the model's accuracy and resilience. Finally, this study offers a novel approach to predicting typhoon damage using advanced deep-learning techniques. Subsequently, government disaster management officials, facility managers, and insurance companies can utilize this method to accurately predict the extent of damage caused by typhoons. Preventive actions such as improved risk assessment, expanded insurance companies, and enhanced disaster responses plans can be implemented using these outcomes. Ultimately, the proposed model will help to reduce typhoon damage and strengthen general resilience to climate crises.

关键词： Climate change Extreme weather events Typhoon Rusa Wet typhoon deep learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Optimizing Screening Frequency and Interval Using a deep learning algorithm

引用

JOURNAL OF THORACIC ONCOLOGY 2022年第9期17卷 S101-S101页

作者： Lam, S. Mayo, J. Myers, R. Yee, J. Atkar-Khattra, S. English, J. Yuan, R. Wu, M. Huang, P. BC Canc Res Inst Vancouver BC Canada Univ British Columbia Vancouver BC Canada Johns Hopkins Univ Balitmore MD USA

P1.04-02

关键词： Screening Interval deep learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Research on Image Processing Optimization Technology Based on deep learning algorithm of Big Data Processing Technology

Research on Image Processing Optimization Technology Based o...

引用

作者： Weijun Wang Junquan Wang Zhiqiang Zhang Da Shi School of Information Science and Engineering Chengdu University

In the context of the era of big data, the application of deep learning algorithms in the field of machine learning has gradually expanded, and has achieved great achievements in image recognition, online recommendation and speech recognition. Applying the deep learning algorithm to the image processing process has a very good application effect and is beneficial to improve image quality. Therefore, based on big data processing technology, this paper deeply studies the image processing optimization technology of deep learning algorithm, which is beneficial to break the technical barriers of related industries and improve image processing efficiency.

关键词： Big data deep learning algorithm Image processing Optimization Technology

来源：评论

学校读者我要写书评

暂无评论

Integrating Unmanned Aerial Vehicle and deep learning algorithm for Pipeline Monitoring and Inspection in the Oil and Gas Sector 21

Integrating Unmanned Aerial Vehicle and Deep Learning Algori...

引用

Proceedings of the International Conference on Artificial Intelligence and its Applications

作者： Uchechi F. Ukaegbu Lagouge K. Tartibu Modestus O. Okwu Isaac O. Olayode Department of Mechanical & Industrial Engineering University of Johannesburg Johannesburg South Africa Department of Mechanical & Industrial Engineering Technology University of Johannesburg Johannesburg South Africa

ISBN: (纸本)9781450385756

Organizations invest heavily during the installation of pipeline facilities which spans across extensive geographical linkage. Also, the issue of pipeline protection and safety must be taken into consideration to have a free flow of oil and gas at inbound and outbound locations. This has necessitated the need for routine inspection and monitoring of pipelines for structural integrity, continued safe operations, and also to monitor intruders/potential trespassers at such locations. This research is focused on the elucidation of a modular unmanned aerial vehicle (UAV) integrated with deep learning algorithms for monitoring and security response to obtain very useful information around the oil and gas facility. The deep learning model employed in this study had training, validation and testing accuracies of 88.3%, 87.5%, and 83.3% respectively. Also, training and validation losses of 0.3583 and 0.3649 were obtained. The suggested integrated UAV has a low maintenance requirement, high endurance, and is cost-effective. It has a superior advantage over the manned aerial vehicles (MAV) currently in use since safety is greatly improved, the cost is reduced, adequate information is obtained and communication is enhanced.

关键词： Unmanned aerial vehicle deep learning algorithm Monitoring Pipeline Inspection

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：