检索结果-内蒙古大学图书馆

Improving Disease Detection in Tomato Leaves Using Visual Geometry Group 19 Compared to the artificial neural network algorithm 2

Improving Disease Detection in Tomato Leaves Using Visual Ge...

引用

2nd IEEE International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics, ICIITCEE 2024

作者： Jothika, G. Khilar, Rashmita Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Computer Science Engineering Thandalam Chennai India Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Information Technology Thandalam Chennai India

ISBN: (纸本)9798350306415

By comparing the efficiency of the artificial neural network (ANN) technique and the Novel Visual Geometry Group 19 (VGG19) algorithm, this research aimed to enhance the precision of the detection of tomato leaf diseases. Using a dataset consisting of 19,167 photographs, each of which measured 171 rows and 171 columns, the artificial neural network method and Visual Geometry Group 16 were both used in order to identify tomato leaf disease. ClinCalc was used to pick a sample size of ten, providing a pretest power of 0.8 and an alpha of 0.05. This was done in order to assess the effectiveness of each method. Following 10 rounds, the performance of each algorithm was evaluated based on its degrees of accuracy. An average precision of 92.12% was achieved by the Novel Visual Geometry Group 19, which was superior to the mean accuracy of 84.43% that the artificial neural network algorithm achieved. The two algorithms were subjected to a statistical analysis revealing a statistically significant difference. The p-value for the independent sample T-test was 0.014, indicating a difference between the two algorithms. Regarding the detection of tomato leaf disease, the Novel Visual Geometry Group 19 technique performed much better than the artificial neural network approach. Overall, the method achieved a higher average accuracy. © 2024 IEEE.

关键词： artificial neural network algorithm Detection Disease Healthy Novel Visual Geometry Group19 Performance Tomato leaves

来源：评论

学校读者我要写书评

暂无评论

Research on Eliminating Redundancy in Electricity Information Transmission Based on artificial neural network algorithm 6

Research on Eliminating Redundancy in Electricity Informatio...

引用

6th International Conference on Electronics and Communication, network and Computer Technology, ECNCT 2024

作者： Tao, Ligui Zhou, Yuhuai Su, Zhihao Cao, Hanhua Zhang, Huanping Zhujiang College South China Agricultural University Guangzhou510900 China Guangzhou Xinhua University Guangzhou510520 China

ISBN: (纸本)9798350366143

In order to reduce the storage space occupied by the compressed power information and realize the accurate elimination of redundant data, a method of eliminating the redundancy of power information transmission based on artificial neural network algorithm is proposed. According to the principle of artificial neural network, the transmission format of redundant power information is defined, and the redundant power information can be processed on demand according to the numerical level of information repetition rate index. From the perspectives of redundancy strength and aggregation coefficient, calculate the compression level of redundant power information, and complete the design of power information transmission redundancy elimination method based on artificial neural network algorithm. The results show that under the action of artificial neural network algorithm, the storage space occupied by compressed power consumption information is reduced 0.69× 1012 Mb, which can avoid the repetition of information parameters, so as to realize the accurate elimination of redundant data. © 2024 IEEE.

关键词： artificial neural network algorithm compression amount power consumption information redundancy elimination

来源：评论

学校读者我要写书评

暂无评论

Novel intelligent MPP tracker and sliding mode control for decentralized street lighting systems using photovoltaic energy

引用

INTERNATIONAL JOURNAL OF SUSTAINABLE ENGINEERING 2025年第1期18卷

作者： Attia, Hussain Al-Ataby, Ali Takruri, Maen Omar, Amjad Amer Univ Ras Al Khaimah Sch Engn Dept Elect & Elect Engn Ras Al Khaymah U Arab Emirates Amer Univ Middle East Elect Engn Dept Kuwait Kuwait Amer Univ Middle East Coll Engn & Technol Kuwait Kuwait United Arab Emirates Univ Dept Elect & Commun Engn Al Ain U Arab Emirates

This paper proposes a solution for powering an unlimited number of streetlight poles systems. Firstly, an intelligent MPPT battery charger incorporates battery state of charge monitoring and an artificial neural network algorithm is incorporated to ensure optimal system performance. Secondly, an effective DC driver is proposed using a buck converter supported by a Sliding Mode Controller to achieve a smooth response under different loading conditions. Unlike traditional decentralised street lighting solutions, which focus mainly on LED dimming based on motion detection or basic MPPT algorithms, this paper proposes a hybrid approach that integrates an intelligent ANN-based MPPT battery charger with a robust SMC for load driving. The collected testing data are analysed to show effective MPPT battery charger and load driver using MATLAB/Simulink software. Simulation results demonstrate high performance of the proposed system, with accurate MPP location tracking by the ANN algorithm, achieving a Mean Square Error of 7.9467 x 10-5 and battery charging up to 80 % of SOC. The results also confirm an accurate controlling response of load driver with minimal voltage fluctuation of 0.25 mV and a low overshoot of 50 mV. The approach proposed enhances energy efficiency, making it ideal for large-scale, sustainable urban infrastructure.

关键词： artificial neural network algorithm MPPT battery charger sliding mode controller street light dimming motion sensor

来源：评论

学校读者我要写书评

暂无评论

Analysis of treatment effect of acupuncture on cervical spondylosis and neck pain with the data mining technology under deep learning

引用

JOURNAL OF SUPERCOMPUTING 2022年第4期78卷 5547-5564页

作者： Huo, Huaying Chang, Yigang Tang, Yu Shanxi Prov Peoples Hosp Taiyuan Peoples R China

This study was to explore the value of data mining model in evaluating the treatment effect of acupuncture on patients with cervical spondylosis (CS) and neck pain. A total of 270 patients with CS and neck pain recruited in the acupuncture clinic of Shanxi Provincial People's Hospital were selected as the research objects in this study and were divided into an acupuncture needle group (group A), an acupoint latent acupuncture group (group B), and a puncture bloodletting group (group C) randomly, with 90 cases in each group. The Northwick Park Questionnaire (NPQ), McGill Pain Questionnaire (MPQ), and Role-Physical (RP), Physiological Function (PF), General Health (GH), and Body Pain (BP) of all patients were recorded before treatment, at the completion of the fifth acupuncture, at the end of treatment, one-month follow-up, two-month follow-up, and three-month follow-up to analyse the clinical treatment effect. Based on the artificial neural network (ANN) algorithm, a curative effect evaluation method and data mining model was further established to compare the accuracy rate of data processing by different data models, and the data processed by the data mining model were compared with the clinical data to analyse the feasibility of the data mining model. The test results found that the NPQ and MPQ values of patients in group B were significantly lower than those in groups A and C (P < 0.05). At the end of treatment, the PF and BP values of patients in groups B and C were significantly higher than those of group A (P < 0.05). The RP value of patients in group B was significantly higher than that in groups A and C after treatment and during follow-up (P < 0.05). The GH value of patients in group B was significantly higher than that in groups A and C (P < 0.05). The clinical treatment efficiency in group B was significantly higher than that in the other two groups (P < 0.05). Different sample sizes of decision tree (DT-1), clustering algorithm (CA-1), and support vector

关键词： artificial neural network algorithm Data mining technology Cervical spondylosis and neck pain Evaluation of clinical treatment efficiency Acupuncture

来源：评论

学校读者我要写书评

暂无评论

Internal combustion engine fuel synthesis, suitability, physical property evaluation using mixing models and backpropagation ANN algorithm

引用

ENGINEERING APPLICATIONS OF artificial INTELLIGENCE 2024年 132卷

作者： Rahiman, M. Kalil Santhoshkumar, S. Rex, Prathiba Thirumurugaveerakumar, S. Khan, S. Sudheer Saveetha Univ Inst Agr Engn Saveetha Inst Med & Tech Sci SIMATS Saveetha Sch Engn Chennai 602105 India Bannari Amman Inst Technol Dept Automobile Engn Sathyamangalam 638401 India Kumaraguru Coll Technol Dept Mech Engn Coimbatore 641049 India Saveetha Univ Saveetha Dent Coll & Hosp Saveetha Inst Med & Tech Sci SIMATS Dept Oral Med & Radiol Chennai 600077 India

An experimental analysis comprising pongamia, soyabean, and corn biodiesel was selected and mixed with diesel and di-butyl ether at different proportions for its viability and phase separation. The test samples were experimentally confirmed for their density, sound speed, and refractive index characteristics by varying the temperatures between 298 K and 343 K. The mixing models, namely the Lorentz-Lorenz (L-L) and Gladstone-Dale (G-D) methods, were tested for the uncertainty of experimental results. The use of artificial neural networks (ANN) was made as an attempt to characterize the backpropagation algorithm's gradient to pursue the minimum error function of experimental and mixing models. The L-L and G-D with and without ANN equations were used to compare the different proportions and temperatures for the fuel blends of D50PD50, D50PD45DBE05, and D50PD25DBE25, and so on. Furthermore, each sample has been computed for the excess molar volume, and interactions between the liquids have been verified. The exergy analysis for PD, SB, and CB biodiesel under ambient conditions and the experimental and predicted results of energy destruction can be narrowed. The use of ternary fuel in place of diesel shows significant improvements in terms of energy annihilation and homogeneity, which have a lesser impact on emissions and the environment.

关键词： Ternary blends Refractive index Error analysis artificial neural network algorithm Molar volume Exergy

来源：评论

学校读者我要写书评

暂无评论

Machine learning model for predicting threshold voltage by taper angle variation and word line position in 3D NAND flash memory

引用

IEICE ELECTRONICS EXPRESS 2020年第22期17卷 20200345-20200345页

作者： Lee, Dong Chan Lee, Jang Kyu Shin, Hyungcheol Seoul Natl Univ Interuniv Semicond Res Ctr ISRC Seoul 151747 South Korea Seoul Natl Univ Sch Elect Engn & Comp Sci Seoul 151747 South Korea

In this letter, a machine learning (ML) model is presented to predict the variation of the threshold voltage (V-th) according to the taper angle and target word line (WLT) position in 3D NAND flash memory. Through Technology Computer-Aided Design (TCAD) simulation, V-th is extracted according to taper angle and WLT position. TCAD data is used as the training data set required for learning by an artificial neural network algorithm (NNA). The completed ML model is then used to predict V-th for each word line (WL). It was also confirmed that the ML model predicted well even for TCAD data that was not used as a training data set.

关键词： 3D NAND flash memory taper angle artificial neural network algorithm machine learning

来源：评论

学校读者我要写书评

暂无评论

Wear morphology analysis and structural optimization of cone bit bearing seals

引用

INDUSTRIAL LUBRICATION AND TRIBOLOGY 2018年第1期70卷 59-67页

作者： Zhang Yi Zhang Xiaodong Chang Xueping Wu Qian Southwest Petr Univ Sch Mechatron Engn Chengdu Sichuan Peoples R China

Purpose This paper aims to clarify the relationship between the cone bit seal failure and the down-hole drilling fluid pressure and high temperature that occur during ultra-deep well drilling. It proposes that the contact pressure distribution under low pressure conditions is favourable for lubrication and the seal inner wear is serious under high pressure conditions. Furthermore, the more reliable cone bit seal can be obtained using the back propagation (BP) neural network and genetic algorithm (GA) to reduce the drilling cost. Design/methodology/approach The wear morphologies of the seal surface were analyzed using Contour GT-K to determine the seal contact pressure distribution. Then, the influences of the drilling fluid pressure and high temperature on the metal seal interface were analyzed using finite element method. The structural parameters of the seal under high pressure were optimized based on the BP neural network and GA. Findings This paper proposes that the inner seal contact pressure increases rapidly with an increase in the drilling fluid pressure. The design parameters of the seal components should be adjusted reasonably to ensure that the outer contact pressure is greater than the inner contact pressure, which is advantageous for forming a lubricant film on the inner side of the seal. The uneven temperature distribution of the seal surface will further aggravate seal failure. Originality/value Study on the bit seal with good property is significant in drilling application, and the optimized seal can prolong the cone bit life.

关键词： Drilling Finite element analysis Parameter optimizing artificial neural network algorithm Sealing performance Wear and friction

来源：评论

学校读者我要写书评

暂无评论

Determining phase diagrams of tetrahydrofuran plus methane, carbon dioxide or nitrogen clathrate hydrates using an artificial neural network algorithm

引用

CHEMICAL ENGINEERING SCIENCE 2010年第22期65卷 6059-6063页

作者： Mohammadi, Amir H. Martinez-Lopez, Jose F. Richon, Dominique CEP TEP Ctr Energet & Procedes MINES ParisTech F-77305 Fontainebleau France Univ Zaragoza Dept Quim Organ & Quim Fis Fac Ciencias Edificio D E-50009 Zaragoza Spain

In this communication, we have developed a feed-forward artificial neural network algorithm for estimating dissociation pressures of the binary clathrate hydrates of tetrahydrofuran+methane, carbon dioxide or nitrogen as a function of temperature and concentration of tetrahydrofuran in the aqueous solution below/equal its stoichiometric concentration (i.e., 0.056 mole fraction). In order to develop this algorithm, the most reliable experimental data reported in the literature on the dissociation pressures of the aforementioned binary hydrates have been used. Moreover, we report few experimental data on the dissociation pressures of the binary hydrates of tetrahydrofuran+carbon dioxide or nitrogen at 0.011 mole fraction of tetrahydrofuran in aqueous solution, which were measured using an isochoric pressure-search method. The latter experimental data are used to verify the reliability of the corresponding experimental data reported in the literature. (C) 2010 Elsevier Ltd. All rights reserved.

关键词： Gas hydrate Tetrahydrofuran Methane Carbon dioxide Nitrogen artificial neural network algorithm

来源：评论

学校读者我要写书评

暂无评论

Nonparametric Structural Damage Detection algorithm for Ambient Vibration Response: Utilizing artificial neural networks and Self-Organizing Maps

引用

JOURNAL OF ARCHITECTURAL ENGINEERING 2016年第2期22卷 1-14页

作者： Abdeljaber, Osama Avci, Onur Qatar Univ Coll Engn Dept Civil & Architectural Engn POB 2713 Doha Qatar

This study presentes a new nonparametric structural damage detection algorithm that integrates self-organizing maps with a pattern-recognition neural network to quantify and locate structural damage. In this algorithm, self-organizing maps are used to extract a number of damage indices from the ambient vibration response of the monitored structure. The presented study is unique because it demonstrates the development of a nonparametric vibration-based damage detection algorithm that utilizes self-organizing maps to extract meaningful damage indices from ambient vibration signals in the time domain. The ability of the algorithm to identify damage was demonstrated analytically using a finite-element model of a hot-rolled steel grid structure. The algorithm successfully located the structural damage under several damage cases, including damage resulting from local stiffness loss in members and damage resulting from changes in boundary conditions. A sensitivity study was also conducted to evaluate the effects of noise on the computed damage indices. The algorithm was proved to be successful even when the signals are noise-contaminated. (C) 2016 American Society of Civil Engineers.

关键词： Self-organizing maps artificial neural network algorithm Nonparametric damage detection Structural health monitoring

来源：评论

学校读者我要写书评

暂无评论

Vectorized Code Implementation of Logistic Regression and artificial neural networks to Recognize Handwritten Digit 1

Vectorized Code Implementation of Logistic Regression and Ar...

引用

1st IEEE International Conference on Power Electronics, Intelligent Control, and Energy Systems (ICPEICES)

作者： Farooq, Faizan Tandon, Siddhant Parashar, Pankaj Sengar, Prateek Amity Univ Dept Elect & Commun Engn Noida Uttar Pradesh India

ISBN: (纸本)9781467385879

This paper presents the development of a Machine learning model through implementation of two algorithms namely Logistic Regression and artificial neural networks to recognize handwritten digits from 0 to 9. The Training efficiency of both the algorithms is compared at the end of implementation. Logistic Regression is generally used for binary classification however;multiclass classification has been achieved by using One-vs-AII approach. artificial neural networks are used for feed forward propagation to build the hypothesis function and back propagation is used for calculation of weights. The weights for both the models are minimized using advanced optimization algorithm such as fmiunc and fmincg. The formulas are implemented in vectorized format that is the formulas are solely expressed in matrix form and nowhere for loops are required. Vectorization does involve a lot of formulations to be done on paper beforehand but it ultimately serves the optimization purpose because higher programming languages such as MATLAB are very efficient to implement vectorized codes and this property should be exploited. The database consists of five thousand handwritten digits. The final result shows the program predicting the number on the display. The system is well trained and effective in recognizing the number.

关键词： Recognition artificial neural network algorithm Logistic Regression algorithm One-vs-All

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：