Human Activity Recognition Based on Weighted Sum Method and Combination of Feature Extraction Methods

Nguyen, Nang Hung Van; Pham, Minh Tuan; Ung, Nho Dai; Tachibana, Kanta

doi:10.11648/j.ijiis.20180701.13

Cited by 5 publications

(5 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…La etapa de extracción de características se utiliza para encontrar una alta resolución de representación de datos para cada segmento (Van Nguyen, et al, 2018), este es un paso crucial en el procesamiento de datos.…”

Section: Extracción De Característicasunclassified

Clasificación de actividad física mediante señales de acelerometría

Cavita-Huerta,

Reyes-Reyes

2024

ICBI

View full text Add to dashboard Cite

El presente trabajo aborda la problemática asociada con el reconocimiento de patrones de señales provenientes de acelerómetros para identificar y clasificar un grupo de 12 actividades físicas, las señales se recolectaron mediante acelerómetros colocados en tres posiciones antropométricas distintas: pecho, muñeca derecha, tobillo izquierdo. Se desarrolló un modelo de Redes Neuronales Artificiales (ANN) que clasifica este conjunto de actividades utilizando únicamente señales de acelerometría como entrada. Se presenta una comparativa del rendimiento de la red neuronal tipo feedforward (RNAf). La evaluación se realizó en cuatro escenarios de clasificación diferentes, concluyendo que el pecho fue la posición más efectiva para la clasificación, logrando un 77% de precisión. Sin embargo, al adoptar un enfoque integral que considera las señales de los tres sensores, la precisión aumentó significativamente, alcanzando un 90%.

show abstract

Section: Extracción De Característicasunclassified

Clasificación de actividad física mediante señales de acelerometría

Cavita-Huerta,

Reyes-Reyes

2024

ICBI

View full text Add to dashboard Cite

show abstract

“…Allah Bux Sargano et al [28] propose an innovative approach for human activity identification using the pre-trained structure of deep CNN for mining of features and depiction pursued by a fused SVM KNN categorizer for activity recognition. Additionally, there exists plenty of tasks in human acknowledgment with an essential job in motion recognition [29,30]. A strategy for recognizing complex human exercises is proposed, including different people with intellectual insight into the computer.…”

Section: Literature Reviewmentioning

confidence: 99%

Suspicious Activity Recognition Using Proposed Deep L4-Branched-Actionnet With Entropy Coded Ant Colony System Optimization

et al. 2021

View full text Add to dashboard Cite

Intelligent visual surveillance systems are attracting much attention from research and industry. The invention of smart surveillance cameras with greater processing power has now been the leading stakeholder, making it conceivable to design intelligent visual surveillance systems. It is possible to assure the safety of people in both homes and public places. This work aims to distinguish the suspicious activities for surveillance environments. For this, a 63 layers deep CNN model is suggested and named "L4-Branched-ActionNet". The suggested CNN structure is centered on the alteration of AlexNet with added four blanched sub-structures. The developed framework is first transformed into a pre-trained framework by conducting its training on an object detection dataset called CIFAR-100 with the SoftMax function. The dataset for suspicious activity recognition is then forwarded to this pretrained model for feature acquisition. The acquired deep features are subjected to feature subset optimization. These extracted features are first coded by applying entropy and then an ant colony system (ACS) is utilized on the entropy-based coded features for optimization. The configured features are then fed into numerous SVM and KNN based classification models. The cubic SVM has the highest efficiency scores, with a performance of 0.9924 in terms of accuracy. The proposed model is also validated on the Weizmann action dataset and attained an accuracy of 0.9796. The successful findings indicate the suggested work's soundness.

show abstract

“…Sliding window techniques are the common example of the segmentation stage [30]. Feature extraction stage [31][32][33][34] is used to find a high resolution of data representation for each segment. Extracted features can be divided into four main categories: time domain, frequency domain, learning techniques, and other techniques.…”

Section: Human Activity Recognitionmentioning

confidence: 99%

A Review of Physical Human Activity Recognition Chain Using Sensors

AlShorman¹,

Alshorman²,

Masadeh³

2020

IJEEI

View full text Add to dashboard Cite

In the era of Internet of Medical Things (IoMT), healthcare monitoring has gained a vital role nowadays. Moreover, improving lifestyle, encouraging healthy behaviours, and decreasing the chronic diseases are urgently required. However, tracking and monitoring critical cases/conditions of elderly and patients is a great challenge. Healthcare services for those people are crucial in order to achieve high safety consideration. Physical human activity recognition using wearable devices is used to monitor and recognize human activities for elderly and patient. The main aim of this review study is to highlight the human activity recognition chain, which includes, sensing technologies, preprocessing and segmentation, feature extractions methods, and classification techniques. Challenges and future trends are also highlighted.

show abstract

Human Activity Recognition Based on Weighted Sum Method and Combination of Feature Extraction Methods

Cited by 5 publications

References 5 publications

Clasificación de actividad física mediante señales de acelerometría

Clasificación de actividad física mediante señales de acelerometría

Suspicious Activity Recognition Using Proposed Deep L4-Branched-Actionnet With Entropy Coded Ant Colony System Optimization

A Review of Physical Human Activity Recognition Chain Using Sensors

Contact Info

Product

Resources

About