检索结果-内蒙古大学图书馆

14th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2023

作者： Kumar, Sunil Rana, K.P.S. Kumar, Vineet Department of Electronics and Communication Engineering J. B. Institute of Technology Uttarakhand Dehradun248197 India Division of Instrumentation and Control Engineering Netaji Subhas University of Technology Sector-3 Dwarka New Delhi110078 India

In the present paper, a step down converter employing combination of Flyback and Forward converters, using a non-cascading scheme, is presented. The voltage conversion ratio in a bi-quadratic converter depends on bi-quadratic power of the duty cycle. Due to this effect, the range of obtainable output voltages has become wider. This means the difference of any two consecutive output realizable voltages becomes narrower than that achieved by using relatively lower power of the duty cycle. Here, for stepping up the output voltage, the outputs of the flyback and forward sub-converters are combined in series with each other. Due to such configuration, a larger output voltage is obtained. A comparison is given to indicate the extension in voltage conversion ratio as the duty cycle is raised to higher power. For validation, a converter of 24 V, 24 W rating is presented. © Grenze Scientific Society, 2023.

关键词： bi-quadratic discontinuous conduction mode intermediate capacitor non-cascading structure switching cycle voltage conversion ratio

来源：评论

学校读者我要写书评

暂无评论

On comparing the performances of MLP and RBFN on sales forecasting problem

引用

International Journal of Information technology (Singapore) 2022年第1期14卷 301-309页

作者： Tiwari, Raman Kumar, Rajesh Gera, Rajat Srivastava, Smriti Faculty of Management Studies Manav Rachna University Faridabad India Department of Electrical and Instrumentation Engineering Thapar Institute of Engineering and Technology Patiala 147004 India Faculty of Management Studies Manav Rachna International Institute of research and studies Faridabad India Division of Instrumentation and Control Netaji Subhas University of Technology (formerly Netaji Subhas Institute of Technology) New Delhi 110078 India

This paper addresses the problem of predicting the sales by developing two sales forecasting models based on multi-layered perceptron (MLP) and radial basis function network (RBFN). The performance of both these models have been thoroughly compared in predicting the sales. To update the parameters in these models we have used dynamic back-propagation (DBP) method. Simulation results obtained shows that MLP has performed better than the RBFN. © 2019, Bharati Vidyapeeth's institute of computer Applications and Management.

关键词： Dynamic back-propagation algorithm MLP prediction RBFN Sales forecasting

来源：评论

学校读者我要写书评

暂无评论

Students’ Performance Prediction Using Feature Selection and Supervised Machine Learning Algorithms 3rd

Students’ Performance Prediction Using Feature Selection an...

引用

3rd International Conference on Innovative Computing and Communication, ICICC 2020

作者： Gajwani, Juhi Chakraborty, Pinaki Division of Computer Engineering Netaji Subhas University of Technology New Delhi India

ISBN: (纸本)9789811551123

Educational data mining involves finding patterns in educational data which can be obtained from various e-learning systems or can be gathered using traditional surveys. In this paper, our focus is to predict the academic performance of a student based on certain attributes of an educational dataset. The attributes can be demographic, behavioural or academic. We propose a method to classify a student’s performance based on a subset of behavioural and academic parameters using feature selection and supervised machine learning algorithms such as logistic regression, decision tree, naïve Bayes classifier and ensemble machine learning algorithms like boosting, bagging, voting and random forest classifier. For selection of the attributes, we plotted various graphs and determined the attributes that were most likely to affect and improve prediction. Experiments with different algorithms show that ensemble machine learning algorithms provide best results with our dataset with an accuracy of up to 75%. This has widespread applications such as assisting students in improving their academic performance, customizing e-learning courses to better suit students’ needs and providing tailor-made solutions for different groups of students. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Self-attention-based Human Activity Detection Using Wearable Sensors 2nd

Self-attention-based Human Activity Detection Using Wearable...

引用

2nd International Conference on Signals, machines, and Automation, SIGMA 2022

作者： Diwakar, Shivin Dwivedi, Dhirendra Singh, Satya P. Sharma, Madan Center of Excellence in Artificial Intelligence and Division of Electronics and Communication Netaji Subhas Institute of Technology University of Delhi New Delhi India Department of Information and Communication Engineering College of Engineering University of Buraimi Al Buraimi Governorate Oman

ISBN: (纸本)9789819909681

Analyzing human activity through wearable sensors can assist applications connected to context—vigilance and health care. The proposed approach utilizes convolutional and recurrent modeling to express the space–time-dependent constraints from information provided by numerous sensors. We construct a neural network layout, a combination of convolutional neural network and recurrent neural network, which focuses on spatiotemporal characteristics provided by sensor time series data with short listing and learning crucial points by executing a self-attentive procedure. We exhibit validation of our designed strategy on the WISDM dataset and indicate that the self-attention technique achieves a remarkable amendment in presentation over deep neural networks through the union consisting of convolutional and recurrent network architectures. We also present that our designed algorithm offers a statistic performance improvement over other designed approaches for the information (dataset) under consideration. The presented technique allows precise interpretation of activity from numerous body part sensors through various time intervals. We evaluated our technique through various classification methods namely: MLP Classifier, gradient boosting, Random Forest Classifier, Conv2D–LSTM, and self-attention mechanism (proposed). The simulation results show that our proposed method achieved the highest accuracy of 89.58% out of all other methods. We compared the effects of the designed architecture scheme with a baseline constructed through ConvNN and RecNN models, and with earlier designed approaches. We figured out that our self-attention model outperformed the baseline model with high difference among all the considered metrics. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Wearable sensors

来源：评论

学校读者我要写书评

暂无评论

Output power control of wind energy system by tip speed ratio control using fractional PI^βD^α controller

引用

International Journal of Information technology (Singapore) 2021年第1期13卷 299-305页

作者： Pathak, Diwaker Gaur, Prerna Division of Instrumentation and Control Engineering Netaji Subhas Institute of Technology University of Delhi Delhi India

Various non-linear systems are well designed using a non-integer order mathematical model based differential and integral components. The fractional-order concept provides an effective method for turning the technology robust in various industry applications. This paper presents a fractional proportional-integral-derivative (FPID) controller and its benefits in variable speed wind turbine (WT) application. The FPID controller improves the operational environment of WT from the initiation of two more tuning parameters i.e., the fractional-order integral and derivative gains. These gains are well-tuned using the manual tuning method. For analysis of the effectiveness of the FPID controller, a comparison has been carried out between FPID and conventional PID controllers. The overshoot, rise time and settling time in various parameter responses like rotor speed, electromagnetic torque, and load power are considered for comparison of effectiveness of both the controllers. Performance indexes are also calculated and compared for both the controllers. © 2020, Bharati Vidyapeeth's institute of computer Applications and Management.

关键词： Fractional PID controller PID controller Renewable energy Wind turbine

来源：评论

学校读者我要写书评

暂无评论

Image Analysis for E-Healthcare Systems using Multi-Biometric Recognition Model

Image Analysis for E-Healthcare Systems using Multi-Biometri...

引用

2023 International Conference on Advancement in Computation and computer Technologies, InCACCT 2023

作者： Bansal, Naman Arora, Pranav Sharma, Deepak Kumar Gupta, Koyel Datta Kuntala, Chandana Netaji Subhas Institute of Technology University of Delhi Department of Instrumentation and Control Engineering New Delhi India Indira Gandhi Delhi Technical University for Women Department of Information Technology New Delhi India Maharaja Surajmal Institute of Technology Department of Computer Science and Engineering New Delhi India

ISBN: (纸本)9798350396485

With the dawn of e-Healthcare systems, Medical Record Management has become an important research problem. The storage and organization of medical records have made relatively little progress in a world of constantly emerging new technologies and continuous innovation. Many hospitals keep the records on paper, which raises many challenges, including but not limited to a significant amount of time for searching and retrieving a specific record, high maintenance costs, lack of backup, and limited security. Although the inclusion of technology has made this task far more efficient and secure, there is still much that can be done to improve it. This paper proposes a double index-based approach for mapping medical records directly to a patient's biometrics which would take advantage of the uniqueness of biometrics to identify a patient. The proposed multi-biometric model achieves an accuracy of 97% and an F 1 score of 0.9814. © 2023 IEEE.

关键词： Biometrics

来源：评论

学校读者我要写书评

暂无评论

A survey of tools for social network analysis

引用

International Journal of Web engineering and technology 2021年第3期16卷 189-216页

作者： Rani, Poonam Shokeen, Jyoti Department of Computer Engineering Netaji Subhas University of Technology Delhi India Department of CSE University Institute of Engineering and Technology Maharshi Dayanand University Haryana Rohtak India

Social networking sites contain large amounts of data about users and their relationship with each other. This data is huge, noisy and unstructured, due to which it is necessary to mine the data to extract useful information. To interpret various network features and analyse the results visually or numerically, there are many tools for social network analysis and visualisation. The selection of a suitable tool to perform a specific work is an arduous task. This paper discusses various tools used in the analysis of social networks. It also gives a brief overview of few popular languages for social network analysis. We give a comprehensive comparison of social network analysis tools based on different parameters. We also perform experiments on these tools to evaluate their computational speed and scalability. Copyright © 2021 Inderscience Enterprises Ltd.

关键词： Visualization

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Techniques for Disease Prediction in Rice Plant

Machine Learning Techniques for Disease Prediction in Rice P...

引用

Self Sustainable Artificial Intelligence Systems (ICSSAS), International Conference on

作者： Nikunj Madan Umang Soni Computer Science Thapar Institute of Engineering and Technology New Delhi India Mechanical Engineering Netaji Subhas University of Technology New Delhi India

ISBN: (数字)9798350368413

ISBN: (纸本)9798350368420

It is essential to identify diseases in plants to increase crop production and yield. Therefore, prediction of these diseases at an early stage is important to avoid or minimize crop losses. In this paper we have taken the use case of rice crop and predicting diseases namely leaf smut, brown spots and bacterial leaf blight using machine learning techniques. Labeled image dataset of these three diseases in rice plants is used and several machine learning algorithms (DT, RF, KNN, GBM, LR, NB, and MobileNet) are applied on it. To compare performance of different models, calculations and analysis of confusion matrix, recall, precision and f1-score have been used.

关键词： Accuracy Microorganisms Crops Machine learning Nearest neighbor methods Predictive models Data models Classification algorithms Diseases Classification tree analysis

来源：评论

学校读者我要写书评

暂无评论

Fiberless optical communication: Issues and challenges

引用

Journal of Optical Communications 2024年第0期45卷 s1179-s1200页

作者： Singh, Shree Prakash Shrivastava, Shreesh Kumar Sengar, Sujata Nath, Soyinka Division of Electronics and Communication Engineering Netaji Subhas University of Technology Sector-3 Dwarka New Delhi110078 India Department of ECE GLA University Mathura India Department of ECE Netaji Subhas Institute of Technology Faculty of Technology University of Delhi New Delhi India

To fulfill the requirement of high data rate with variable quality of service, optical wireless communication is a better option in comparison to existing RF system and is a favorable technological candidate for future optical communication. In wireless optical communication, information is transmitted by propagation of optical wave through the atmosphere. The detrimental effects of channel parameters can acutely limit the utility of an optical wireless communication system. The paper first reviews different channel models in the context to outdoor wireless communication. Different impairments that affect the performance of outdoor optical communication systems and different techniques to mitigate these impairments are then investigated. The upper layer protocols for free space optical communication are also discussed. © 2023 Walter de Gruyter GmbH, Berlin/Boston.

关键词： Atmospheric turbulence

来源：评论

学校读者我要写书评

暂无评论

A novel approach to predict stock market price using radial basis function network

引用

International Journal of Information technology (Singapore) 2021年第6期13卷 2277-2285页

作者： Kumar, Rajesh Srivastava, Shefali Dass, Anuli Srivastava, Smriti Department of Electrical and Instrumentation Engineering Thapar Institute of Engineering and Technology (Deemed to be University) Patiala 147004 India Division of Information Technology Netaji Subhas Institute of Technology New Delhi 110078 India Division of Instrumentation and Control Netaji Subhas Institute of Technology New Delhi 110078 India

In the financial sector, the sales price forecasting is a hot issue. Since the indices associated with the stock are nonlinear and are affected by various internal and external factors, they are very difficult to model and pose a difficult problem to be solved by the researchers. This paper is devoted in designing an intelligent prediction model based on the radial basis function network (RBFN). To tune its parameters a learning algorithm is developed using the back-propagation (BP) method. The performance of the proposed method is also compared with that of the multi-layered feed-forward neural network (MLFFNN) containing only single hidden layer and the results obtained from the simulation study indicate that the performance of RBFN is better as compared to the MLFFNN model. © 2019, Bharati Vidyapeeth's institute of computer Applications and Management.

关键词： Back-propagation Multilayer feed forward neural network Prediction Radial basis function network Stock market data

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：