检索结果-内蒙古大学图书馆

Investigation of Artificial Intelligence Techniques in Finance and Marketing

Procedia Computer Science 2020年 173卷 149-157页

作者： Raman Tiwari Smriti Srivastava Rajat Gera Faculty of Management Studies Manav Rachna University Faridabad - 121004 India Division of Instrumentation and Control Netaji Subhas Institute of Technology New Delhi-110078 India Faculty of Management Studies Manav Rachna International University Faridabad - 121004 India

The paper presents the application of artificial intelligence techniques-artificial neural network (ANN) and fuzzy logic to the problems of stock market prediction, sales forecasting and market segmentation. Back propagation algorithm has been used to train the neural network for the first two problems, while Self-Organizing Maps (SOM) have been employed for the clustering problem that Market Segmentation presents. The Fuzzy model discussed in the paper uses the state values or the input-output data pairs. Mean Square Error has been used as the performance index to compare ANN and Fuzzy logic for stock prediction and sales forecasting.

关键词： Artificial neural network Fuzzy logic Stock market prediction Sales forecasting Market segmentation Back propagation algorithm Self-organizing maps

来源：评论

学校读者我要写书评

暂无评论

Whale Optimization Algorithm (WOA) Based control Of Nonlinear Systems

Whale Optimization Algorithm (WOA) Based Control Of Nonlinea...

引用

International Conference on Power Energy, Environment and Intelligent control (PEEIC)

作者： Vishal Srivastava Smriti Srivastava Instrumentation & Control Division Netaji Subhas Institute of Technology New Delhi India

An efficient optimization technique based controller is proposed, for non-linear systems like inverted pendulum and robotic arm manipulator which are bench mark problems in control engineering. The optimization based controller is optimizing the gain parameters by using the Whale optimization algorithm (WOA). WOA is applied on Conventional PID controller to optimize their parameters i.e. Kp, Ki and Kd. Mean Square Error (MSE) is taken as the objective function. The Simulation results show substantial improvement in the performance of the nonlinear systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Pitch angle control of variable speed wind turbine by using fuzzy logic 2

Pitch angle control of variable speed wind turbine by using ...

引用

2nd IEEE International Conference on Power Electronics, Intelligent control and Energy Systems, ICPEICES 2018

作者： Kumar, Akshiv Kumar, Bhavnesh Netaji Subhas Institute of Technology Division of Instrumentation Control Engineering New Delhi India

ISBN: (纸本)9781538666258

Wind energy conversion systems have to handle the variations in the wind speed for efficient energy conversion. This paper presents an analysis made on the controller effectiveness system for pitch angle control of a wind turbine which changes performance of the wind energy conversion system. A fuzzy logic controller is proposed in place of classical PI controller for controlling the pitch angle to have maximum available power from the wind energy conversion system and the comparisons are made between PI controller, fractional order PI controller and fuzzy logic controller. The system is tested for different realistic environmental conditions using MATLAB/Simulink Software. © 2018 IEEE.

关键词： Fuzzy logic

来源：评论

学校读者我要写书评

暂无评论

Hyper Smoothing Function based Edge Detection for Prediction of Fat Content in Marble Meat

Hyper Smoothing Function based Edge Detection for Prediction...

引用

International Conference on Computing, Power and Communication Technologies (GUCON)

作者： Navdeep Navdeep Vijander Singh Asha Rani Sonal Goyal Department of Instrumentation and Control Engineering Netaji Subhas Institute of Technology Delhi University Delhi India

Intramuscular fat is one of the crucial quality indices in meat grading. The traditional intramuscular fat detection methods like chemical, visual, nuclear magnetic resonance etc. are tedious, costly and time-consuming whereas edge detection techniques are fast and non-destructive testing methods. In this paper hyper smoothing function-based edge detection technique is proposed for intramuscular fat detection. The proposed method utilizes an improved counting scheme and the relationship between surrounding pixels and centric pixel. The scheme calculates fat percentage, fat fleck size distribution and homogeneity. The quantitative analysis of results shows that the fat percentage measured by HLBP is more accurate as compared to black and white method and energy and skewness based fat detection method.

关键词： Fats Image edge detection Chemicals Smoothing methods Muscles Visualization

来源：评论

学校读者我要写书评

暂无评论

Effect of Higher Order DC-DC Converter on Solar fed BLDC Motor Driven Water Pumping System

Effect of Higher Order DC-DC Converter on Solar fed BLDC Mot...

引用

Students Conference on engineering and Systems (SCES)

作者： Mohd Juned Manisha Prerna Gaur Instrumentation and Control Engineering Netaji Subhas Institute of Technology (NSIT) New Delhi INDIA Instrumentaion and Control Engineering Netaji Subhas University of Technology (formerly NSIT) New Delhi INDIA

ISBN: (纸本)9781728105789

Standalone BLDC motor system for applications such as household water pumping, irrigation, electric vehicle etc has been commercialized. In this system, closed loop power electronic converters control the speed of BLDC motor and track maximum power drawn from solar panel. Zeta converter with inductor on the load side is used to track maximum power. This paper presents design of power electronic converters for driving BLDC motor using solar PV source. Design of converters is done according to the ratings of BLDC motor and required solar PV array. The performance of Zeta converter is shown through simulated results of 2. S9kW, 3000 rpm BLDC motor. The effect of higher order converter is shown in terms of comparison with second order buck boost converter.

关键词： brushless DC motors DC motor drives maximum power point trackers photovoltaic power systems pumps solar cell arrays brushless direct current motor maximum power point trackers Solar cell arrays DC motor drives photovoltaic power systems Converters Pumps load side Maximum power

来源：评论

学校读者我要写书评

暂无评论

AlexaPi3-An economical Smart Speaker 1

AlexaPi3-An economical Smart Speaker

引用

1st International Conference on Data Science and Analytics, PuneCon 2018

作者： Kumar, Archiev Instrumentation and Control Engineering Netaji Subhas Institute of Technology New Delhi India

ISBN: (纸本)9781538672785

In the recent years, smart electronics have seen a rapid rise in the field of home automation and wireless digital technology. But the high costs of these devices restrict many people to use the features of these technologies. In this paper, I present an economical solution for a smart speaker such as Amazon Echo Dot. The Alexa AWS is used and incorporated with Raspberry Pi 3 with a Bluetooth speaker (Logitech X100). Anyone with an internet connection can make their own Amazon Echo Dot with any speaker. This is significantly cheaper than buying the commercially available products. Moreover, this device can be interfaced with almost any electrical equipment to make a voice controlled home automation system. This paper helps readers to explore the Internet of Things without spending much money. © 2018 IEEE.

关键词： Bluetooth

来源：评论

学校读者我要写书评

暂无评论

Plants Stress Response Detection by Selecting Minimal Bands of Hyperspectral Images

Plants Stress Response Detection by Selecting Minimal Bands ...

引用

International Conference on Advanced Computer control, ICACC

作者： Milton Mondal Manish Edida Naman Sharma Brejesh Lall Dhandapani Raju Department of Electrical Engineering Indian Institute of Technology Delhi Instrumentation and Control Engineering Netaji Subhas Institute of Technology Delhi Plant Physiology Division Indian Agricultural Research Institute

It is an important task in the agricultural domain to determine the stress levels in plants. Drought conditions can have an adverse effect on crop yield. Hyperspectral Imaging (HSI) combined with classical Machine Learning algorithms are in current use to determine the stress levels. Every spectral band in an HSI does not contain useful information regarding the stress levels. For this reason, some vegetation indices are selected by agricultural researchers, based on reflectance ratios where a significant change in reflectance was observed because of stress. These indices do not always contain significant information because of changes in temperature, humidity or other atmospheric variations in different trials. There is no fixed set of vegetation indices which can be used to estimate stress levels accurately. In this paper, we demonstrated the working of Conditional Covariance Operator (CCM) which is used to select the most significant spectral bands from the collected Hyperspectral data itself. CCM is the most recent of the feature selection methods. This efficient feature selection method is used for the first time in this paper for plant stress analysis in rapid manner. It selects consistent discriminative spectral bands even when training examples per class are less than what other feature selection methods need. It can be seen that the Random Forest classifier model can classify the stress level into three categories (i) normal (ii) mild and (iii) severe stress with an accuracy of 99.7% when only 10 spectral bands are selected.

关键词： crops feature selection geophysical image processing hyperspectral imaging image classification random forests remote sensing vegetation

来源：评论

学校读者我要写书评

暂无评论

Application of Newton iterative process in approximation of fractional differentiator and integrator

Application of Newton iterative process in approximation of ...

引用

International Conference on Intelligent Computing, instrumentation and control Technologies (ICICICT)

作者： Nitisha Shrivastava Pragya Varshney Inderprastha Engineering College NCR-Delhi Ghaziabad India Division of Instrumentation and Control Engineering Netaji Subhas University of Technology New Delhi India

The band specific realization of fractional order controllers and filters find its way into implementation through the approximated value as its realization in the original form is very difficult. The integer-order passive structure of the fractional operator is built based upon its approximated integer-order transfer function. Therefore, approximation is an essential part of fractional order elements which are ideally characterized by constant phase and constant slope in the entire frequency range. The realizable approximated solutions are obtained by either finding alternate placement of real poles and zeros on the left half of s-plane, so that the slope of the approximated transfer function remains constant or by performing iterations and using continued fraction expansion. In this paper the authors have studied two techniques of approximation viz. Carlson and NPC techniques, both of which are based on Newton iterations. All the mathematical steps involved in each of the method to obtain the solution is presented in detail. A comparison of the two methods is also presented. Two fractional operators, one-fourth differentiator and nine-tenth integrator are chosen for simulation purpose. The results obtained in terms of frequency response are compared with the ideal response using MATLAB.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Predictive Maintenance of Air Conditioning Systems Using Supervised Machine Learning

Predictive Maintenance of Air Conditioning Systems Using Sup...

引用

International Conference on Intelligent Systems Applications to Power Systems (ISAP)

作者： Shrishti Trivedi Sahil Bhola Archit Talegaonkar Prerna Gaur Shreya Sharma Instrumentation and Control Engineering Netaji Subhas University of Technology New Delhi India Computer Science Engineering Indraprastha Institute of Information Technology New Delhi India

ISBN: (数字)9781728131924

ISBN: (纸本)9781728131931

Various types of faults can occur in an air conditioner resulting in a decrease in efficiency, a rise in energy consumption, and increasing maintenance costs. Hence predictive maintenance becomes important. In this paper, the two most common types of faults - gas leakage and capacitor malfunction have been detected using the decision tree machine learning algorithm. The data for faulty and operating air conditioners have been collected using distributed sensors, microcontroller, and dedicated circuitry and analyzed using MATLAB Classification App Learner Toolbox. The results obtained by the decision tree for fault detection and diagnosis and load monitoring were then compared with results obtained by support vector machine and the prediction accuracy for the decision tree was found to be higher. The presented research work can identify the air conditioner which is faulty as well as predicts the type of fault at an early stage to do maintenance beforehand.

关键词： Circuit faults Decision trees Machine learning algorithms Intelligent sensors Air conditioning Fault detection

来源：评论

学校读者我要写书评

暂无评论

Development of a smart identification and sorting system

Development of a smart identification and sorting system

引用

2018 World Congress on engineering and Computer Science, WCECS 2018

作者： Kumar, Shubham Ashi Khanna, Pradeep Department of Instrumentation and Control Netaji Subhas Institute of Technology New Delhi India Department of Manufacturing Process and Automation Engineering South Africa

ISBN: (纸本)9789881404909

Sorting of the components on the basis of their features is an important process extensively required in industries mainly on assembly and production lines. Such systems are of significant importance in selective assembly processes where the part to be delivered is decided on the basis of real time requirements. This not only does away with the requirement of manual labor, but also addresses the issue of mistakes arising from fatigue and negligence of human worker, plus there is definitely an increase in productivity by the use of such systems as they offer the advantage of complete automation of the process. The present system has been developed with a view to provide an effective, simple and low cost solution to identification and sorting system applications. The system has been developed by using less costly and robust sensors and actuators such that the electronic circuitry involved is also simple and can meet the demands where flexibility of a concern because the present system can quickly be reprogrammed to meet any changed circumstance within the operating range of the system. System presently developed is based on sorting on the basis of component color. The system does not need to hit its home position each time it makes a delivery, rather it takes its present position as the reference and can make a quick move to the next delivery, saving a significant time. The system has successfully been tested and is found to give an error less than 1% in total number of trials conducted. © 2018 Newswood Limited. All rights reserved.

关键词： Real time systems

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：