检索结果-内蒙古大学图书馆

International Conference on Electronics, Materials engineering and Nano-technology (IEMENTech)

作者： V S K V Harish Avijit Routh Department of Electrical Engineering Netaji Subhas University of Technology Dwarka New Delhi Department of Electrical Engineering Haldia Institute of Technology Haldia West Bengal

ISBN: (数字)9798331520762

ISBN: (纸本)9798331520779

Frequency regulation services through demand-side measures such as thermostatically controlled loads have gained popularity in the recent decade. However, there is a significant need for a control strategy that has the capability to provide regulation even under parametric uncertainties. In this paper, a robust PI controller has been designed to homogeneously integrate aggregated Variable Speed Air-Conditioning (VSAC) systems into a Single-Area Power System (SAPS) with a reheat steam turbine. Based on parametric uncertainties, a worst-case model of the VSAC-SAPS system is obtained and its stability margins in terms of Phase and Gain margins are evaluated. Simulation results show that the dynamic responses of the power grid's frequency and power deviation of the grid were steady-state stable. Considering 30,000 homogeneous VSACs with 1.5 tonnes capacity, the rated power of the aggregated VSACs is 59MW (approx.). Simulation results showed that without a robust controller, the uncertain system was stable but sensitive to perturbations due to lower gain and phase margins. Frequency support services were utilized from the grid and aggregated VSAC systems, thereby significantly reducing the strain on the conventional grid. The robust PI controller in the VSAC system enhances transient stability by reducing overshoot and achieving faster damping, complementing the slower grid response.

关键词： PI control Uncertainty Power system stability Stability analysis Regulation Power grids Steady-state Transient analysis Thermal stability Turbines

来源：评论

学校读者我要写书评

暂无评论

Detection of Schizophrenia from Actigraphy Data using UMAP Features

Detection of Schizophrenia from Actigraphy Data using UMAP F...

引用

International Conference on Computing for Sustainable Global Development (INDIACom)

作者： Muzafar Mehraj Misgar M.P.S Bhatia Department of Computer Science & Engineering Netaji Subhas University of Technology New Delhi India

Schizophrenia is a prevalent public health problem that costs both health and the economy. In most cases, there is no straightforward quantitative test for diagnosing mental health issues. Conventional methods based on patient interviews or questionnaires are still used for diagnosing mental health problems like depression and schizophrenia. This paper proposes a new approach to diagnose schizophrenia and related mental health problems by using motor activity data. The proposed framework consists of two parts: feature extraction using UMAP (Uniform Manifold Approximation and Projection) and a Neural network (NN) for classification. The results from using this framework on 24-hour motor activity data (Psykose Dataset) show high accuracy in diagnosing schizophrenia with a score of 93.89%, sensitivity of 89.04%, and specificity of 96.42%. This new approach demonstrates improved results compared to traditional methods of manual feature extraction.

关键词： Manifolds Sensitivity Mental disorders Mental health Artificial neural networks Manuals Machine learning

来源：评论

学校读者我要写书评

暂无评论

Towards Emotion Recognition in Hindi-English Code-Mixed Data: A Transformer Based Approach 11

Towards Emotion Recognition in Hindi-English Code-Mixed Data...

引用

11th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, WASSA 2021

作者： Wadhawan, Anshul Aggarwal, Akshita Department of Computer Engineering Netaji Subhas University of Technology Dwarka New Delhi India

ISBN: (纸本)9781954085183

In the last few years, emotion detection in social-media text has become a popular problem due to its wide ranging application in better understanding the consumers, in psychology, in aiding human interaction with computers, designing smart systems etc. Because of the availability of huge amounts of data from social-media, which is regularly used for expressing sentiments and opinions, this problem has garnered great attention. In this paper, we present a Hinglish dataset labelled for emotion detection. We highlight a deep learning based approach for detecting emotions in Hindi-English code mixed tweets, using bilingual word embeddings derived from FastText and Word2Vec approaches, as well as transformer based models. We experiment with various deep learning models, including CNNs, LSTMs, Bi-directional LSTMs (with and without attention), along with transformers like BERT, RoBERTa, and ALBERT. The transformer based BERT model outperforms all other models giving the best performance with an accuracy of 71.43%. © 2021 Association for Computational Linguistics.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

technology Landscape for Epidemiological Prediction and Diagnosis of COVID-19

引用

computers, Materials & Continua 2021年第5期67卷 1679-1696页

作者： Siddhant Banyal Rinky Dwivedi Koyel Datta Gupta Deepak Kumar Sharma Fadi Al-Turjman Leonardo Mostarda Department of Instrumentation and Control Netaji Subhas University of TechnologyNew Delhi110078India Department of Computer Science&Engineering Maharaja Surajmal Institute of TechnologyNew Delhi110058India Department of Information Technology Netaji Subhas University of TechnologyNew Delhi110078India Research Center for AI and IoT Near East UniversityNicosiaMersin10Turkey Computer Science Department Camerino UniversityCamerino62032Italy

The COVID-19 outbreak initiated from the Chinese city of Wuhanand eventually affected almost every nation around the globe. From China,the disease started spreading to the rest of the world. After China, Italybecame the next epicentre of the virus and witnessed a very high death *** nations like the USA became severely hit by SARS-CoV-2 virus. TheWorld Health Organisation, on 11th March 2020, declared COVID-19 a pandemic. To combat the epidemic, the nations from every corner of the worldhas instituted various policies like physical distancing, isolation of infectedpopulation and researching on the potential vaccine of SARS-CoV-2. Toidentify the impact of various policies implemented by the affected countrieson the pandemic spread, a myriad of AI-based models have been presented toanalyse and predict the epidemiological trends of COVID-19. In this work, theauthors present a detailed study of different articial intelligence frameworksapplied for predictive analysis of COVID-19 patient record. The forecastingmodels acquire information from records to detect the pandemic spreadingand thus enabling an opportunity to take immediate actions to reduce thespread of the virus. This paper addresses the research issues and correspondingsolutions associated with the prediction and detection of infectious diseaseslike COVID-19. It further focuses on the study of vaccinations to cope withthe pandemic. Finally, the research challenges in terms of data availability,reliability, the accuracy of the existing prediction models and other open issuesare discussed to outline the future course of this study.

关键词： COVID-19 diagnosis deep learning forecasting models machine learning metaheuristics prediction big data pandemic

来源：评论

学校读者我要写书评

暂无评论

An Energy Efficient Artificial Neural Network based Clustering Protocol for Wireless Sensor Network 7

An Energy Efficient Artificial Neural Network based Clusteri...

引用

7th International Conference on Contemporary Computing and Informatics, IC3I 2024

作者： Kaushal, Rajanish Kumar Tiwari, Sourabh Laxmi Charan, Piyush Chandra, K. Ramesh Manchanda, Rachit Chandigarh University Department of Electrical Engineering Punjab Mohali India Chandigarh University Department of Cse Punjab Mohali India Netaji Subhas Institute of Technology Department of Ece Bihta Bihar Patna India Manav Rachna University Department of Ece Haryana Faridabad India Vishnu Institute of Technology Department of Ece Andhra Pradesh Kovvada India

ISBN: (纸本)9798350350067

Wireless sensor nodes are equipped with compact batteries that supply the necessary energy for a several operational tasks in a wireless sensor network (WSNs). During the execution of these tasks, significant power is depleted from the sensor nodes (SNs). Nonetheless, given the restricted battery capacity of these SNs, they eventually become depleted, leading to the failure of individual nodes and compromising the integrity of the entire network. An essential aspect of addressing the challenge of energy depletion is the choice of the most suitable cluster head (CH). In this research paper, we proposed a model that employs an Artificial Neural Network (ANN) to designate a single node within each cluster as the CH. This approach has resulted in the development of an energy-efficient clustering protocol, referred to as the Energy-Efficient Artificial Neural Network-Based Clustering Protocol (EEANNCP), tailored specifically for WSNs. Through extensive simulations, we have demonstrated that our proposed approach substantially enhances energy conservation and extends the network's lifespan. © 2024 IEEE.

关键词： Artificial Neural Network Base Station Cluster head Compressive sensing Sensor node Wireless sensor network

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

Multi-class Regret Detection in Hindi Devanagari Script

arXiv

引用

arXiv 2024年

作者： Sharma, Renuka Nagpal, Sushama Sabharwal, Sangeeta Butt, Sabur Department of Computer Science and Engineering Netaji Subhas University of Technology India Institute for the Future of Education Tecnológico de Monterrey 64849 Mexico

The number of Hindi speakers on social media has increased dramatically in recent years. Regret is a common emotional experience in our everyday life. Many speakers on social media, share their regretful experiences and opinions regularly. It might cause a re-evaluation of one’s choices and a desire to make a different option if given the chance. As a result, knowing the source of regret is critical for investigating its impact on behavior and decision-making. This study focuses on regret and how it is expressed, specifically in Hindi, on various social media platforms. In our study, we present a novel dataset from three different sources, where each sentence has been manually classified into one of three classes "Regret by action", "Regret by inaction", and "No regret". Next, we use this dataset to investigate the linguistic expressions of regret in Hindi text and also identify the textual domains that are most frequently associated with regret. Our findings indicate that individuals on social media platforms frequently express regret for both past inactions and actions, particularly within the domain of interpersonal relationships. We use a pre-trained BERT model to generate word embeddings for the Hindi dataset and also compare deep learning models with conventional machine learning models in order to demonstrate accuracy. Our results show that BERT embedding with CNN consistently surpassed other models. This described the effectiveness of BERT for conveying the context and meaning of words in the regret domain. © 2024, CC BY-NC-SA.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Modelling of a Non-Linear Dynamic System Using Long Short-Term Memory

Modelling of a Non-Linear Dynamic System Using Long Short-Te...

引用

International Conference on Computing, Communication, and Intelligent Systems (ICCCIS)

作者： Richa Sahu Smriti Srivastava Rajesh Kumar Department of Electrical Engineering Netaji Subhas University of Technology Delhi India Department of Control and Instrumentation Engineering Netaji Subhas University of Technology Delhi India Department of Electrical Engineering National Institute of Technology Kurukshetra India

Long Short-Term Memory (LSTM) is a Recurrent Neural Network (RNN) that overcomes typical neural network constraints. Because of its ability to record temporal dependencies and solve nonlinear equations, long-term data can be simply managed. LSTM is intended to alleviate the problems of RNN's vanishing gradient and exploding gradient difficulties. In this paper, we used LSTM to solve nonlinear plant equations with a gradient descent-based back propagation approach and retrieved the plant's output as well as other performance measures including Average Mean Square Error (AMSE) and Total Mean Average Error (TMAE). When the output of an LSTM is compared to that of a feed-forward Neural Network (FFNN), the LSTM outshines the FFNN. All the parameters of both models, such as iteration count and learning rate are kept constant.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An experimental analysis of state-of-the-art Time Series Prediction models 2

An experimental analysis of state-of-the-art Time Series Pre...

引用

2nd International Conference on Advance Computing and Innovative Technologies in engineering, ICACITE 2022

作者： Gupta, Kavya Tayal, Devendra Kumar Jain, Aarti Indira Gandhi Delhi Technical University for Women Department of Computer Science and Engineering Delhi India Netaji Subhas University of Technology Department OfElectronics and Communication Engineering Delhi India

ISBN: (纸本)9781665437899

Various prediction problems encompass a time element and consequently entail extrapolating data or prediction. Time series prediction is one of the most employed data mining models in business, finance, weather forecasting, and pattern recognition. Prediction comprises selecting models to fit historical data and utilizing them to foretell future reflections. The future is predicted or established on whatever has previously occurred. Time series appends a time-order dependency amongst observations. This dependency is both a constriction and construction that offers a basis of added intelligence. In this paper, an experimental analysis of various state-of-the-art time series prediction models has been presented. The analysis has been done for three datasets, and results have been evaluated based on MAE, MSE, RMSE, R2, and Average time per data point. © 2022 IEEE.

关键词： Weather forecasting

来源：评论

学校读者我要写书评

暂无评论

Modelling of a MIMO Non-Linear System using a Double Internal Loop Recurrent Neural Network

Modelling of a MIMO Non-Linear System using a Double Interna...

引用

Recent Advances in Electrical, Electronics & Digital Healthcare Technologies (REEDCON), International Conference on

A Double Internal Loop Recurrent Neural Network (DILRNN) model is proposed for Multiple Input Multiple Output (MIMO) system to obtain improved output using Gradient Descent based Back Propagation Algorithm. In the modelling of DILRNN, three feedback loops are taken i.e., the first feedback is taken from the unit delay of the output to the hidden layer, the second feedback is taken from the previous value of hidden layer to itself and the last feedback is taken from the previous value of output to output. The weight is updated with the help of the algorithm after every iteration. The output of the proposed DILRNN model reduces error significantly vis-à-vis other Recurrent Neural Network (RNN) models for constant value of iterations and epochs. The statistical parameters such as RMSE and TMAE for the proposed model are greatly in comparison to other models and thereby enhances the accuracy of the model.

关键词：

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：