KNN-Based Machine Learning Classifier Used on Deep Learned Spatial Motion Features for Human Action Recognition

Paramasivam, K.; Sindha, Mohamed Mansoor Roomi; Sarojini, B.

doi:10.3390/e25060844

Cited by 9 publications

(5 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several research articles used this dataset; for example, Paramasivam et al [ 23 ] created a novel solution to address the common obstacles encountered in existing approaches to HAR, which often use computationally intensive networks like 3D CNNs and two-stream networks. This involved developing HARNet, which is a lightweight directed acyclic graph-based residual 2D CNN with reduced parameters.…”

Section: Methodsmentioning

confidence: 99%

Design and Development of an Imitation Detection System for Human Action Recognition Using Deep Learning

Alhakbani,

Alghamdi,

Al-Nafjan

2023

Sensors

View full text Add to dashboard Cite

Human action recognition (HAR) is a rapidly growing field with numerous applications in various domains. HAR involves the development of algorithms and techniques to automatically identify and classify human actions from video data. Accurate recognition of human actions has significant implications in fields such as surveillance and sports analysis and in the health care domain. This paper presents a study on the design and development of an imitation detection system using an HAR algorithm based on deep learning. This study explores the use of deep learning models, such as a single-frame convolutional neural network (CNN) and pretrained VGG-16, for the accurate classification of human actions. The proposed models were evaluated using a benchmark dataset, KTH. The performance of these models was compared with that of classical classifiers, including K-Nearest Neighbors, Support Vector Machine, and Random Forest. The results showed that the VGG-16 model achieved higher accuracy than the single-frame CNN, with a 98% accuracy rate.

show abstract

Section: Methodsmentioning

confidence: 99%

Design and Development of an Imitation Detection System for Human Action Recognition Using Deep Learning

Alhakbani,

Alghamdi,

Al-Nafjan

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…The classifier is then constructed in turn, and finally, the samples are classified into multiple categories. On the other hand, the one-to-one (one-against-one) approach requires the construction of k (k − 1)/2 classifiers [ 25 ]. However, the accuracy does not show significant improvement in the case of existing clustering.…”

Section: Control Methodsmentioning

confidence: 99%

Control Method of Cold and Hot Shock Test of Sensors in Medium

Tian

Zeng

et al. 2023

Sensors

View full text Add to dashboard Cite

In order to meet the latest requirements for sensor quality test in the industry, the sample sensor needs to be placed in the medium for the cold and hot shock test. However, the existing environmental test chamber cannot effectively control the temperature of the sample in the medium. This paper designs a control method based on the support vector machine (SVM) classification algorithm and K-means clustering combined with neural network correction. When testing sensors in a medium, the clustering SVM classification algorithm is used to distribute the control voltage corresponding to temperature conditions. At the same time, the neural network is used to constantly correct the temperature to reduce overshoot during the temperature-holding phase. Eventually, overheating or overcooling of the basket space indirectly controls the rapid rise or decrease in the temperature of the sensor in the medium. The test results show that this method can effectively control the temperature of the sensor in the medium to reach the target temperature within 15 min and stabilize when the target temperature is between 145 °C and −40 °C. The steady-state error is less than 0.31 °C in the high-temperature area and less than 0.39 °C in the low-temperature area, which well solves the dilemma of the current cold and hot shock test.

show abstract

“…KNN belongs to the family of machine learning algorithms, but does not require a learning phase to solve a problem. It is used for both classification and regression problems (Paramasivam et al, 2023). It enables companies to use their appropriate data to train algorithms, in order to better circumvent their consumption requirements.…”

Section: Predictive Modelsmentioning

confidence: 99%

Comparative Machine Learning Models for Predicting Loan Fructification in a Semi-Urban Area

Mpia,

Syasimwa,

Muyisa

2024

AAES

View full text Add to dashboard Cite

The current research proposes a reliable and robust machine learning (ML) model which outperforms among six other models in predicting loan fructification obtained by entrepreneurs in a semi-urban area. The proposed model predicts if an entrepreneur can make grow a loan from a microfinance firm, a bank, a financial company, or an individual. The proposed model uses primary data collected from entrepreneurs residing in Butembo, a semi-urban town located in eastern of the democratic republic of Congo as dataset. This study uses a dataset that contains 5868 records. Seven ML model performances are compared in the loan fructification prediction: support vector machine, random forest, extra-trees, decision tree, naïve bayes, k-nearest neighbors, and logistic regression. Support vector machine reveals to be the best model for predicting loan fructification using features such as age, years of working experience of the entrepreneur, entrepreneur loan repayment conviction, used mean by the lender to recover its loan, entrepreneur opinion on the disadvantage of taking out a loan, capacity of the entrepreneur to invest after obtaining loan, entrepreneur position on the possibility of launching a business without a loan, entrepreneur willingness to apply again for loan in the future, success project after obtaining loan. The study uses accuracy, recall, precision, and f-score as metrics to assess the developed models. The four metrics for support vector machine scored 95%, 95%, 83%, and 83%, respectively. The proposed model confirms the robustness of support vector machine in predicting loan fructification.

show abstract

KNN-Based Machine Learning Classifier Used on Deep Learned Spatial Motion Features for Human Action Recognition

Cited by 9 publications

References 46 publications

Design and Development of an Imitation Detection System for Human Action Recognition Using Deep Learning

Design and Development of an Imitation Detection System for Human Action Recognition Using Deep Learning

Control Method of Cold and Hot Shock Test of Sensors in Medium

Comparative Machine Learning Models for Predicting Loan Fructification in a Semi-Urban Area

Contact Info

Product

Resources

About