2023 2nd Edition of IEEE Delhi Section Flagship Conference (DELCON)最新文献_第7页

A Comprehensive Review on Deep Learning Approaches for Question Answering and Machine Reading Comprehension in NLP NLP中用于问答和机器阅读理解的深度学习方法综述

2023 2nd Edition of IEEE Delhi Section Flagship Conference (DELCON) Pub Date : 2023-02-24 DOI: 10.1109/DELCON57910.2023.10127327

R. R., Gnanapriya B, J. J. S.

{"title":"A Comprehensive Review on Deep Learning Approaches for Question Answering and Machine Reading Comprehension in NLP","authors":"R. R., Gnanapriya B, J. J. S.","doi":"10.1109/DELCON57910.2023.10127327","DOIUrl":"https://doi.org/10.1109/DELCON57910.2023.10127327","url":null,"abstract":"Natural Language Processing (NLP) deals with the development of methodologies capable of interacting with computer through human language. NLP improves machine’s comprehension of human language, allowing for human-computer communication based on linguistics. Recent years have seen phenomenal success of NLP models in language and grammatical tasks such as information extraction, translation, classification and reasoning. This accomplishment is mainly due to the influence of transformers, which inspired design ideas such as BERT, SQuAD 2.0 and others. These large-scale models produced unique results, despite the higher computational cost. As a result, current NLP systems use transfer learning, pruning, knowledge filtration and quantization to accomplish reasonable performance. Furthermore, Information Retrievers (IR) are created to extract precise data files from large datasets, addressing the large data assertion made by language models. Major contribution of this study is to understand the application of deep learning methods in NLP for automated question answering and obtaining a comprehension of essay text. Context-based NLP issues that are presented along with existing solutions. The challenges of using NLP in comprehension are examined, as well as research community methods for extracting answers from paragraphs. Further direction of this research is to develop novel deep learning models for QA and text comprehension that can overcome the demerits of existing approaches.","PeriodicalId":193577,"journal":{"name":"2023 2nd Edition of IEEE Delhi Section Flagship Conference (DELCON)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129184511","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Modelling and Simulation of a Bi-Directional DC to DC Converter System 双向DC - DC变换器系统的建模与仿真

2023 2nd Edition of IEEE Delhi Section Flagship Conference (DELCON) Pub Date : 2023-02-24 DOI: 10.1109/DELCON57910.2023.10127485

T. Halder

引用次数: 0

Pramanik Shastra: Blockchain-based Natural User Interfaces and Interaction Approach for Storage and Translation of Sanskrit Scripts Pramanik Shastra:基于区块链的自然用户界面和交互方法，用于梵文的存储和翻译

2023 2nd Edition of IEEE Delhi Section Flagship Conference (DELCON) Pub Date : 2023-02-24 DOI: 10.1109/DELCON57910.2023.10127433

Digvijay Singh, Garvit Vijay, Akanksha Gupta, Manas Yadav, A. Mishra, Kiran Khatter

{"title":"Pramanik Shastra: Blockchain-based Natural User Interfaces and Interaction Approach for Storage and Translation of Sanskrit Scripts","authors":"Digvijay Singh, Garvit Vijay, Akanksha Gupta, Manas Yadav, A. Mishra, Kiran Khatter","doi":"10.1109/DELCON57910.2023.10127433","DOIUrl":"https://doi.org/10.1109/DELCON57910.2023.10127433","url":null,"abstract":"The holy scriptures are the foundation of religion, civilization, and society. They strengthen a society's ethics and ideals. \"Shastras\" are Indian scriptures. Most of the important Shastras of ancient Indian civilization were destroyed by invaders, and the remaining Shastras are either too complex to understand or have been misinterpreted. Shastras must be preserved for society's ethics and wealth. Using blockchain to store vast volumes of data is efficient since the network grows stretched. Cloud storage uses attribute-based encryption to preserve security. In such systems, a private key generator can decrypt data, which can cause serious issues. The cloud is centralized; therefore, a failure can bring it down, whereas decentralized storage can avoid this. The Interplanetary File System (IPFS) overcomes the restrictions of cloud storage and blockchain when handling sensitive data. In the paper, a solution has been proposed for storing and sharing data in a decentralized way and combining IPFS with the Ethereum blockchain to create a platform where secured storage and translations of Shastras can be provided. The proposed framework is used for storing files to identify text using Web scraping, later translating the text using Natural Language Processing (NLP) and sharing the translated version of the file on the framework so that it can be easily accessed by the user as per the requirement. The proposal is evaluated with the help of IPFS, which provides a platform to store files, generate a hash value, and remove duplication as it uses content-addressing.","PeriodicalId":193577,"journal":{"name":"2023 2nd Edition of IEEE Delhi Section Flagship Conference (DELCON)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116106991","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Lattice Heating Effects on Electric Field and Potential for a Silicon on Insulator (SOI) MOSFET for MIMO Applications 多输入输出(MIMO)用绝缘体上硅(SOI) MOSFET晶格加热对电场和电势的影响

2023 2nd Edition of IEEE Delhi Section Flagship Conference (DELCON) Pub Date : 2023-02-24 DOI: 10.1109/DELCON57910.2023.10127385

Padakanti Kiran Kumar, Kallepelli Srikanth, Naveen Kumar Boddukuri, N. Suresh, B. Vani

引用次数: 0

Effect of Cubic And Quintic Nonlinearities on Spatially Generated Rogue Waves In CQDNLSE CQDNLSE中三次和五次非线性对空间生成异常波的影响

2023 2nd Edition of IEEE Delhi Section Flagship Conference (DELCON) Pub Date : 2023-02-24 DOI: 10.1109/DELCON57910.2023.10127239

Mishu Gupta, Shivani Malhotra, Amit Kumar, Rama Gupta

{"title":"Effect of Cubic And Quintic Nonlinearities on Spatially Generated Rogue Waves In CQDNLSE","authors":"Mishu Gupta, Shivani Malhotra, Amit Kumar, Rama Gupta","doi":"10.1109/DELCON57910.2023.10127239","DOIUrl":"https://doi.org/10.1109/DELCON57910.2023.10127239","url":null,"abstract":"The presence of soliton and multisoliton solutions have been postulated using various functional forms of Discrete nonlinear Schrödinger equation (DNLSE). These functional forms come from the inspiration that various terms represent different kind of nonlinearities in the system, and direct the behavior, characteristics, and propagation of rogue waves. Here cubic-quintic DNLSE (CQDNLSE) has been considered, and rogue waves are produced using various parameter combinations of the coefficients. The simulations consist of spatially discretizing the CQDNLS, put together with periodic boundary conditions, and Akhmediev -type initial conditions for rogue waves. Time propagation is obtained using RK4 method. The results show that the cubic and quintic terms enable the propagation of the rogue waves unidirectionally, but the presence of former leads to higher dissipation of energy along the waveguide. It is observed that rogue waves keep reappearing where the frequency of reappearance is significantly large when quintic terms dominate. Influence of sign dependence has been also observed and is reflected through the structure of the rogue wave, in the sense that the negative sign of the nonlinearities can help produce systems that are able to better control these waves, and as an example, find applications in waveguide design such as optical fibers.","PeriodicalId":193577,"journal":{"name":"2023 2nd Edition of IEEE Delhi Section Flagship Conference (DELCON)","volume":"251 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131844585","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Efficient Prediction and Analysis of Monkeypox Skin Lesion: A Comparative Study for Web based Application 猴痘皮肤病变的有效预测与分析:基于Web应用的比较研究

2023 2nd Edition of IEEE Delhi Section Flagship Conference (DELCON) Pub Date : 2023-02-24 DOI: 10.1109/DELCON57910.2023.10127329

P. Gupta, Uday Mittal, Tushar Jha, Mini Agarwal, A. Tiwari

{"title":"Efficient Prediction and Analysis of Monkeypox Skin Lesion: A Comparative Study for Web based Application","authors":"P. Gupta, Uday Mittal, Tushar Jha, Mini Agarwal, A. Tiwari","doi":"10.1109/DELCON57910.2023.10127329","DOIUrl":"https://doi.org/10.1109/DELCON57910.2023.10127329","url":null,"abstract":"After the coronavirus pandemic, another deadly disease, known as monkeypox, began to spread. This was so alarming that the World Health Organization declared it a global public health emergency. As of 31st January 2023, there have been 85449 cases of monkeypox reported in 110 countries worldwide. It is difficult to diagnose because its symptoms resemble those of chicken pox, small-pox, etc. The clinical diagnosis of monkeypox is performed using the Polymerase chain reaction (PCR) test, which takes a considerable amount of time to determine the result. Any non-clinical test that could aid in identifying monkeypox in suspected patients would be advantageous. Various deep learning models were found to be useful for this purpose, provided sufficient training data is available. We’ve used already existing datasets and extended them to have a sufficiently large dataset. This dataset is then fed to pre-trained deep-learning models, including ResNet50, EfficientNetB3, InceptionV3, and MobileNetV2. It has aided in comparing the accuracy of these models. Based on our analysis, we have employed best performing model i.e., EfficientNetB3 in a web application with a user-friendly interface to interact with it.","PeriodicalId":193577,"journal":{"name":"2023 2nd Edition of IEEE Delhi Section Flagship Conference (DELCON)","volume":"287 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131846790","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Sound AI Engine for Detection and Classification of Overlapping Sounds in Home Environment 用于家庭环境中重叠声音检测与分类的声音AI引擎

2023 2nd Edition of IEEE Delhi Section Flagship Conference (DELCON) Pub Date : 2023-02-24 DOI: 10.1109/DELCON57910.2023.10127311

Saroj Anand Tripathy, Adeel Abdul Sakkeer, Utkarsh Utkarsh, Deepanshu Saini, S. Narayanan, Sourabh Tiwari, Kalyanaraman Pattabiraman, Rashmi T. Shankarappa

{"title":"Sound AI Engine for Detection and Classification of Overlapping Sounds in Home Environment","authors":"Saroj Anand Tripathy, Adeel Abdul Sakkeer, Utkarsh Utkarsh, Deepanshu Saini, S. Narayanan, Sourabh Tiwari, Kalyanaraman Pattabiraman, Rashmi T. Shankarappa","doi":"10.1109/DELCON57910.2023.10127311","DOIUrl":"https://doi.org/10.1109/DELCON57910.2023.10127311","url":null,"abstract":"Classification of sounds present in the environment is a major issue in the field of audio pattern recognition and classification. For gaining insights into the frequency and time features of Log-Mel Spectrogram with higher efficiency, the Neural Network model is implemented to give the classified audio output which can be further used for various use cases. In this research work, we have considered, both overlapping and non-overlapping audio data, and considered generic input features such as MFCC, bit depth, sampling rate etc. We conducted experiments with various deep learning models based on variants of Convolutional Neural Networks (CNN). Performance evaluation is carried out on the most popular datasets such as UrbanSound8k, DCASE, and AudioSet. Our proposed model using 13-layered CNN has achieved a mean Average Precision (mAP) of up to 0.42. In this paper we have shown the significance of our model using overlapping sounds compared to the state-of-the-art models.","PeriodicalId":193577,"journal":{"name":"2023 2nd Edition of IEEE Delhi Section Flagship Conference (DELCON)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134258081","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Performance Analysis of Knowledge-Based Optimization Algorithm for Effective Resource Allocation 基于知识的资源有效分配优化算法性能分析

2023 2nd Edition of IEEE Delhi Section Flagship Conference (DELCON) Pub Date : 2023-02-24 DOI: 10.1109/DELCON57910.2023.10127543

Nidhi Chauhan, Navneet Kaur, K. S. Saini

{"title":"Performance Analysis of Knowledge-Based Optimization Algorithm for Effective Resource Allocation","authors":"Nidhi Chauhan, Navneet Kaur, K. S. Saini","doi":"10.1109/DELCON57910.2023.10127543","DOIUrl":"https://doi.org/10.1109/DELCON57910.2023.10127543","url":null,"abstract":"The word \"adaptability\" refers to the process of continuously adjusting the resources to meet the changing demands of the application or service. The cloud must be able to quickly scale up or down to meet the current demands of the application or service. This is important to maintain the performance and quality of service as the workload changes. Cloud computing also requires the use of automation to ensure that resources are allocated and utilized most efficiently. Automation also contributes to the adaptability of the cloud as it allows for the rapid deployment and configuration of applications and services. Knowledge-based optimization algorithms (KBO) are widely used for resource allocation in many areas such as transportation, scheduling, and energy management. KBO algorithms are a powerful tool for solving challenging optimization problems. They can quickly and accurately identify the best solution to complex problems. The effectiveness of the KBO algorithm in solving two resource allocation problems, the knapsack problem and the minimum cost flow problem, has been examined in this paper. The algorithm was evaluated based on its ability to find the optimal solution and its running time. The results indicate that the KBO algorithm can solve both problems quickly and accurately. In comparison to other algorithms such as heuristic algorithms, the running time of the KBO algorithm is significantly lower. Additionally, the KBO algorithm can find the optimal solution with a high degree of accuracy.","PeriodicalId":193577,"journal":{"name":"2023 2nd Edition of IEEE Delhi Section Flagship Conference (DELCON)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115391751","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Virtual Reality Based Attention Simulator using EEG Signals 基于脑电图信号的虚拟现实注意力模拟器

2023 2nd Edition of IEEE Delhi Section Flagship Conference (DELCON) Pub Date : 2023-02-24 DOI: 10.1109/DELCON57910.2023.10127358

V. Khemchandani, Kartik Goswani, Meghansh Pankaj Teotia, Sushil Chandra, N. M. Wadalkar

引用次数: 0

Data Analytics of Online Education during Pandemic Health Crisis: A Case Study 流行病健康危机期间在线教育的数据分析:一个案例研究

2023 2nd Edition of IEEE Delhi Section Flagship Conference (DELCON) Pub Date : 2023-02-24 DOI: 10.1109/DELCON57910.2023.10127423

Ishteyaaq Ahmad, Sonal Sharma, Rajiv Kumar, Saurabh Dhyani, Ankur Dumka

{"title":"Data Analytics of Online Education during Pandemic Health Crisis: A Case Study","authors":"Ishteyaaq Ahmad, Sonal Sharma, Rajiv Kumar, Saurabh Dhyani, Ankur Dumka","doi":"10.1109/DELCON57910.2023.10127423","DOIUrl":"https://doi.org/10.1109/DELCON57910.2023.10127423","url":null,"abstract":"There was a rise in the popularity of online education as a means of continuing education during the COVID-19 pandemic, as it enabled students to finish their education while staying safe in their homes. The downsides were a lack of personal connection, limited access to technology, and difficulty engaging students. This article aims to assess whether students regard online learning to be acceptable by considering several aspects, like the degree of difficulty, and the amount of mental stress involved, among others. An online survey was used for this research, the respondents were students from India’s Uttaranchal University. The data was analyzed using Python, findings suggest that students responded well to technology-aided learning. The students also adapted and accepted the online learning mode. The current work was completed after the third wave of the pandemic ended in India. An overwhelming 66.9% of the students believe that in the new normal after the COVID pandemic higher education requires a new approach that combines offline and online learning and recommends a mixture of the two. This paper recommends a \"Hybrid Learning Approach\" that uses Industry 4.0 Technologies and humanitarian AI Chatbots to promote comprehension and creativity in young brains, preparing them for lifelong learning and the future.","PeriodicalId":193577,"journal":{"name":"2023 2nd Edition of IEEE Delhi Section Flagship Conference (DELCON)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124980177","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1