期刊和专利
项目 01
使用步态分析和 3D 卷积网络进行人体识别 在监督下P.Supraja 博士。
这个项目是关于human recognition by their gait i.e.通过分析他们的步态特征来确定行走方式。它包括对象检测、轮廓提取、骨架化、3D CNN、识别。
从 11 个不同角度预处理 181 个对象的 18000 个视频花了 1 天时间，训练网络通过 his/her gait features 识别物体即人类花了 8 天时间。
研究论文：应用。
专利： 出版于印地亚 01/2020,1, Pg- 208
项目 02
This is the caption generated by Encoder and Decoder module of Video Captioning
Video frames as input given to the model
Graph obtain on training video captioning model
This is the caption generated by Encoder and Decoder module of Video Captioning
视频字幕使用 Encoder and Decoder Module 在监督下 苏普拉亚博士
我在这个项目中，我们使用带有 LSTM 的 3D CNN 来训练神经网络，以基于帧中存在的特征的 basic 生成标题。我们使用词嵌入和矢量化来净化我们训练神经网络的字幕。
经过连续五天的训练，我们得到了与视频帧有 92% 相关性的字幕。
专利： 出版于印地亚 51/2019,1, Pg- 61314
项目 03
Silhoutte of human waliking
Trainning Epochs of Model
Graph of trained model
Silhoutte of human waliking
增强的人类步态预测 监督下苏普拉亚博士
我在此，我们使用 2D CNN 通过分析人的步行模式，通过他们的步态特征来识别人。
研究论文： 在物理学和纳米技术杂志上接受。
项目 04
Model Evaluation Chapter Published in Book
Model Evaluation Chapter Published in Book
模型评估(章节） 在书记员出版
这是在《机器和深度学习的基础和方法：算法、工具和应用》一书中发表的一章。在本章中，我解释了我们如何评估不同类型的模型，例如计算机视觉、NLP、回归、分类。和各种其他类型的模型。本章讨论了评估训练模型的理论和数学步骤。
章节链接：关联
DOI(书) : 10.1002/9781119821908
项目 05
Paper Published in Springer Journal
Paper Published in Springer Journal
使用基于 2D 通道的卷积神经网络的基于通道的相似性学习
研究论文名为 as Channel-Based Similarity Learning Using 2D Channel-Based Convolutional Neural Network 发表在 Springer - 医学数据上的人工智能， 计算视觉和生物力学讲义 book 系列（LNCVB，第 37 卷）
研究论文 ：关联
项目 05
Conceptualizing a Channel-based overlapping CNN tower architechture for COVID-19 identification from CT-scan Images
A Research Paper named Conceptualizing a Channel-based Overlapping CNN tower architecture for COVID-19 Identification from CT-scan Images published in Scientific Reports.
Research Paper: Link
DOI: 10.1038/s41598-022-21700-8
项目 05
Futuristic Trends in Artificial Intelligence
Edited Book named Futuristic Trends in Artificial Intelligence published in Iterative International Publishers (IIP), Selfypage Developers Pvt Ltd with ISBN: 978-93-95632-81-2
Book : Link
项目 05
Explainable AI (EXAI) for Sustainable Development: Trends and Applications
Edited Book named as Explainable AI (EXAI) for Sustainable Development: Trends and Applications will be published in CRC Press Taylor & Francis Group.
Book: Link
ISBN: 9781032598864
项目 05
Futuristic Trends in IOT
Edited Book named as Futuristic Trends in IOT published in Iterative International Publishers (IIP), Selfypage Developers Pvt Ltd
Reviewer ID: IIPER1655553093
项目 05
Privacy Preservation and Secured Data Storage in Cloud Computing
Privacy Preservation and Secured Data Storage in Cloud Computing
Privacy Preservation and Secured Data Storage in Cloud Computing
Edited Book named Privacy Preservation and Secured Data Storage in Cloud Computing published in IGI Global Publisher
Book: Link
ISBN: 9798369305935
DOI: 10.4018/979-8-3693-0593-5
项目 05
3D convolution neural network-based person identification using gait cycles
3D convolution neural network-based person identification using gait cycles
3D convolution neural network-based person identification using gait cycles
Human identification plays a prominent role in terms of security. In modern times security is becoming the key term for an individual or a country, especially for countries that are facing internal or external threats. Gait analysis is interpreted as the systematic study of the locomotive in humans.The steps involve object detection, background subtraction, silhouette extraction, skeletonization, and training 3D Convolution Neural Network (3D-CNN) on these gait features.
Research Paper : Link
DOI: 10.1007/s12530-021-09397-y
项目 05
Comparative Study on Forecasting of Schedule Generation in Delhi Region for the Resilient Power Grid Using Machine Learning
Comparative Study on Forecasting of Schedule Generation in Delhi Region for the Resilient Power Grid Using Machine Learning
Comparative Study on Forecasting of Schedule Generation in Delhi Region for the Resilient Power Grid Using Machine Learning
In this proposed work, the focus is on Short-Term Load Forecasting (STLF) in the Delhi metropolis for the upcoming twelve months of 2020. The transformation of the conventional electrical grid into a more adaptable and interactive system due to the increasing use of Renewable Energy Resources (RES) has made accurate load prediction crucial for smart grid operation, including planning, scheduling, management, and electricity trading.
Research Paper: Link
项目 05
Explainable AI (XAI) for Sustainable Development Trends and Applications
Explainable AI (XAI) for Sustainable Development Trends and Applications
Libraries for Explainable Artificial Intelligence (EXAI): Python (Chapter) in Explainable AI (XAI) for Sustainable DevelopmentTrends and Applications
This is a chapter published in the book Explainable AI (XAI) for Sustainable Development Trends and Applications. In this chapter, I have explained how we can use different libraries to explain the output of the Artificial Intelligence model to the end user to increase the trustworthiness of the AI model. by implementing Explainable Artificial Intelligence (XAI). This chapter discusses theoretical as well as mathematical steps to evaluate the trained model.
Book Link : Link
Book ISBN : 9781032598864
项目 05
Cloud-Based Quad Deep Ensemble Framework for the Detection of COVID-19 Omicron and Delta Variants
Cloud-Based Quad Deep Ensemble Framework for the Detection of COVID-19 Omicron and Delta Variants
Cloud-Based Quad Deep Ensemble Framework for the Detection of COVID-19 Omicron and Delta Variants
We have developed a unique ensemble model for detecting COVID-19 Omicron and Delta variants from lung CT-scan images. The ensemble model combines the Capsule Network (CapsNet) with pre-trained architectures including VGG-16, DenseNet-121, and Inception-v3. This approach aims to enhance reliability and robustness in diagnosing the variants.
Research Paper: Link
项目 05
Computational Intelligence Methods for Sentiment Analysis in Natural Language Processing
Computational Intelligence Methods for Sentiment Analysis in Natural Language Processing
Hate Speech Detection Using LSTM (Chapter) in Computational Intelligence Methods for Sentiment Analysis in Natural Language Processing
This is a chapter published in the book Computational Intelligence Methods for Sentiment Analysis in Natural Language Processing. In this chapter, I have explained how we can use LSTM to detect hate speech and explain the model output to the user by implementing Explainable Artificial Intelligence (XAI). This chapter discusses theoretical as well as mathematical steps to evaluate the trained model.
Book Link : Link