Revistas y Patentes
Proyecto 01
Identificación humana mediante análisis de marcha y red convolucional 3D Bajo supervisión deDr. P. Supraja.
Este proyecto trata sobre human recognition by its gait i.e. estilo de caminar analizando sus características de marcha. Incluye detección de objetos, extracción de siluetas, esqueletización, CNN 3D, reconocimiento.
Tomó un día preprocesar los 18000 videos de 181 objetos desde 11 ángulos diferentes y 8 días entrenar la red para reconocer el objeto, es decir, humano por sus gait features.
Trabajo de investigación:Aplicado.
Patente: Publicado enIPindia 01/2020,1, Pg- 208
Proyecto 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
Subtítulos de video usando Módulo codificador y decodificador Bajo supervisión de Dr.P.Supraja
yoEn este proyecto, usamos CNN 3D con LSTM para entrenar la red neuronal para generar el título sobre la base de las características presentes en los marcos. Incrustamos palabras y vectorizamos para desinfectar los subtítulos en los que entrenamos nuestra red neuronal.
Después de entrenar durante cinco días continuos, obtuvimos los subtítulos que eran relevantes en un 92 % para los fotogramas del video.
Patente: Publicado enIPindia 51/2019,1, Pg- 61314
Proyecto 03
Silhoutte of human waliking
Trainning Epochs of Model
Graph of trained model
Silhoutte of human waliking
Predicción mejorada de la marcha humana bajo supervisión deDr.P.Supraja
yoEn esto, hemos utilizado 2D CNN para reconocer al ser humano por sus características de marcha mediante el análisis de su patrón de marcha.
Trabajo de investigación: Aceptado en Journal of Physics and Nanotechnology.
Proyecto 04
Model Evaluation Chapter Published in Book
Model Evaluation Chapter Published in Book
Evaluación del modelo(Capítulo) enPublicación Scrivener
Este es un capítulo publicado en el libro de Fundamentos y métodos de aprendizaje automático y profundo: algoritmos, herramientas y aplicaciones. En este capítulo, he explicado cómo podemos evaluar diferentes tipos de modelos, como visión por computadora, NLP, regresión, clasificación. y varios otros tipos de modelo. En este capítulo se analizan los pasos teóricos y matemáticos para evaluar el modelo entrenado.
Enlace del capítulo:Enlace
DOI(Libro) : 10.1002/9781119821908
Proyecto 05
Paper Published in Springer Journal
Paper Published in Springer Journal
Aprendizaje de similitud basado en canales utilizando una red neuronal convolucional basada en canales 2D
Documento de investigación denominado as Aprendizaje de similitud basado en canales mediante red neuronal convolucional basada en canales 2D publicado en Springer - Inteligencia artificial en datos médicos, Apuntes de clase en visión computacional y biomecánica serie de libros (LNCVB, volumen 37)
Trabajo de investigación :Enlace
Proyecto 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
Proyecto 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
Proyecto 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
Proyecto 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
Proyecto 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
Proyecto 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
Proyecto 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
Proyecto 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
Proyecto 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
Proyecto 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