检索结果-内蒙古大学图书馆

1st International Conference on Smart Sustainable Intelligent Computing and Applications, ICITETM 2020

作者： Tiwari, Raman Srivastava, Smriti Gera, Rajat Faculty of Management Studies Manav Rachna University Faridabad121004 India Division of Instrumentation and Control Netaji Subhas Institute of Technology New Delhi110078 India Faculty of Management Studies Manav Rachna International University Faridabad121004 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. © 2020 The Authors. Published by Elsevier B.V.

关键词： Self organizing maps

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 9

Plants stress response detection by selecting minimal bands ...

引用

9th International Conference on Advances in Computing and Communication, ICACC 2019

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

ISBN: (纸本)9781728155234

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. © 2019 IEEE.

关键词： Spectroscopy

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 20

Predictive Maintenance of Air Conditioning Systems Using Sup...

引用

20th International Conference on Intelligent System Application to Power Systems, ISAP 2019

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

ISBN: (纸本)9781728131924

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. © 2019 IEEE.

关键词： Air conditioning

来源：评论

学校读者我要写书评

暂无评论

PHOTOGENIC-A Tool for Best Photo Generation from Multiple Group Photographs 4

PHOTOGENIC-A Tool for Best Photo Generation from Multiple Gr...

引用

4th International Conference on Information Systems and Computer Networks, ISCON 2019

作者： Singh, Karanjot Agarwal, Saurabh Sharma, Deepak Netaji Subhas Institute of Technology Department of Instrumentation and Control Engineering New Delhi India ASET AUUP Department of Computer Science and Engineering Noida India

ISBN: (纸本)9781728136516

Cameras play an important role in capturing precious moments of people's lives in a photograph that can be seen and cherished by them or by their loved ones any time in their lives. This makes it imperative to have a perfect photograph which can describe that moment well. However, it is very difficult to time and capture a group photograph where everyone is looking their best. There are instances when multiple group photos are taken but in one of the photographs a particular person might have his/her eyes open and is smiling whereas someone else's eyes are closed because he/she was blinking. However, in another photograph that person has his/her eyes closed or is not smiling but rest of the people look good. Whatever the case may be, it becomes very difficult to have one perfect group photograph. Thus, if we can pick and blend the good facial features of each person from these multiple photos and merge into a single photo, we can get a better resultant group photograph with the best of their facial features in it. To do this, one could use softwares like Abode Photoshop or other such image editing tools. However, it requires the user to be well versed with that software and demands a lot of effort and user's valuable time to correct the photographs. To make this process easy and better, we have developed a tool that uses OpenCV at its core and follows a sequence of steps for generating the best photograph out of multiple group photographs clicked at a particular instance. By using this tool one can effortlessly get the best group photograph where everyone is smiling with their eyes open. © 2019 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Enhancing Linearity of Voltage controlled Oscillator Thermistor Signal Conditioning Circuit Using Linear Search

引用

Journal of The Institution of Engineers (India): Series B 2018年第3期99卷 263-271页

作者： Rana, K.P.S. Kumar, Vineet Prasad, Tapan Instrumentation and Control Engineering Division Netaji Subhas Institute of Technology Dwarka New Delhi110078 India

Temperature to Frequency Converters (TFCs) are potential signal conditioning circuits (SCCs) usually employed in temperature measurements using thermistors. A NE/SE-566 based SCC has been recently used in several reported works as TFC. Application of NE/SE-566 based SCC requires a mechanism for finding the optimal values of SCC parameters yielding the optimal linearity and desired sensitivity performances. Two classical methods, namely, inflection point and three point have been employed for this task. In this work, the application of these two methods, on NE/SE-566 based SCC in TFC, is investigated in detail and the conditions for its effective usage are developed. Further, since these classical methods offer an approximate linearization of temperature and frequency relationship an application of a linear search based technique is proposed to further enhance the linearity. The implemented linear search method used results obtained from the above mentioned classical methods. The presented simulation studies, for three different industrial grade thermistors, revealed that the linearity enhancements of 21.7, 18.3 and 17.8% can be achieved over the inflection point method and 4.9, 4.7 and 4.7% over the three point method, for an input temperature range of 0–100 °C. © 2018, The Institution of Engineers (India).

关键词： Linearization

来源：评论

学校读者我要写书评

暂无评论

Preface

Lecture Notes in Electrical Engineering

引用

Lecture Notes in Electrical engineering 2023年 1023 LNEE卷 v页

作者： Rani, Asha Kumar, Bhavnesh Shrivastava, Vivek Bansal, Ramesh C. Department of Instrumentation and Control Engineering Netaji Subhas University of Technology Delhi New Delhi India Department of Electrical Engineering National Institute of Technology Delhi Delhi New Delhi India Department of Electrical Engineering University of Sharjah Sharjah United Arab Emirates

来源：评论

学校读者我要写书评

暂无评论

Novel ubiquitous configuration algorithm for power enhancement of PV array operating under partial shading conditions

引用

Computers and Electrical engineering 2025年 126卷

作者： Rahul Anand Bhavnesh Kumar Swaroop D Arjun Tyagi Data & AI Division Telstra Global Business Services LLP Bangalore India Department of Instrumentation and Control Engineering Netaji Subhas University of Technology New Delhi 110078 India Department of Studies in Computer Science University of Mysore Mysuru 570006 Karnataka India Department of Electrical Engineering Faculty of Technology University of Delhi Delhi 110007 India

The power-generating capacity of a photovoltaic (PV) array decreases dramatically under partial shade. Operating conditions reduce the power-generating capacity of the array and complicate MPP tracking. Reconfiguring the PV array can mitigate the partial shading effect. This paper presents a Novel Ubiquitous Configuration Algorithm (NUCA) for dynamically reconfiguring the PV array. Efficacy of the proposed algorithm has been tested on a PV array of 7 × 5 modules for mismatch in power loss, performance ratio, and fill factor. A relative comparison has also been made of the proposed configuration to the benchmark configurations, namely SP-TCT, TCT, BLHC, and BL-TCT. The PV array under NUCA has achieved a 10.8 % higher global maximum power point (GMPP) and 15.3 % lower power loss than the best-performing configuration. This completed research has been conducted in the MATLAB/Simulink environment.

关键词：

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 2

Application of Newton iterative process in approximation of ...

引用

2nd International Conference on Intelligent Computing, instrumentation and control Technologies, ICICICT 2019

作者： Shrivastava, Nitisha Varshney, Pragya Inderprastha Engineering College NCR-Delhi Department of Electrical and Electronics Engineering Ghaziabad201010 India Netaji Subhas University of Technology Division of Instrumentation and Control Engineering New Delhi110078 India

ISBN: (纸本)9781728102832

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. © 2019 IEEE.

关键词： Transfer functions

来源：评论

学校读者我要写书评

暂无评论

An efficient load flow solution for distribution system with addition of distributed generation using improved harmony search algorithms

引用

Journal of Electrical Systems and Information technology 2020年第1期7卷 1-16页

作者： Tyagi, Arjun Kumar, Krishan Ansari, M. A. Kumar, Bhavnesh School of Electrical Engineering Shri Mata Vaishno Devi University Katra India Department of Electrical Engineering School of Engineering Gautam Buddha University Greater Noida India Division of Instrumentation and Control Engineering Netaji Subhas University of Technology New Delhi India

The distribution system analysis is very important to know the system condition at any given point of time. This distribution power flow plays an important role. Many power flow techniques have been proposed in the past for distribution power flow (DPF). The implicit Z-bus Gauss–Seidel (GS) method is good when dispersed generations are modelled as PQ nodes in the distribution system but, when dispersed generations are modelled as PV nodes, it leads to divergence problems. In a Newton-like method, a slight change in the execution of the bus-type switching logic leads to an unlike convergence characteristic. Though backward/forward (BW/FW) method is effective and efficient, it slows down under heavy-load condition. Now, with the addition of distributed generation (wind/solar, etc.) at the distribution level, the classical configuration of the distribution system is also changed. This poses a need for more robust and efficient technique. This paper investigates the application of a new algorithm known as improved harmony search (IHS) for DPF. The IHS can determine multiple power flow solutions which fix the limitations of other methods while determining a solution for the highly stressed condition. The results for a standard test system are taken with IHS, Newton–Raphson (NR) and BW/FW method without and with the impact of the wind energy system, to show the potential of the proposed algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Investigation of Artificial Intelligence Techniques in Finance and Marketing

引用

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

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

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：