A simplified machine learning approach for recognizing human activity

S, Abdul Lateef Haroon P; Eranna, U.

doi:10.11591/ijece.v9i5.pp3465-3473

Cited by 6 publications

(3 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…9 shows the Receiver Operating Characteristics (ROC) for AB-J48 which is calculated to be 0.9538. Several studies have utilized machine learning classifiers in their work such as network anomaly detection [27], breast cancer [28], aerobic granular sludge [29], acute kidney disease [30], student's performance [31], melanoma detection [32], recognizing human activity [33], regression-based model [34], Sentiment Analysis [35], predicting chronic kidney disease [36], Soybean leaf disease detection [37], investigating dengue outbreak [38], sentiment of mobile unboxing [39,40].…”

Section: Resultsmentioning

confidence: 99%

An Efficient Approach for Malarial Epidemic Prognosis Using Machine Learning Classifiers

Kumar¹,

Sikamani²

2022

INDJCSE

View full text Add to dashboard Cite

Malaria is an acute infectious disease, which affects nearly two-thirds of the global population. Annually, the deaths due to malaria have crossed millions, the countries with fewer medical facilities are the ones which are most affected, thus the prediction of its outbreak at early stages will reduce the intense diminishing of human lives. This systematic investigation deals with the analysis and prediction of the malarial epidemic outbreak by investigating several factors such as climate, global warming, human activities, mosquitoes, sewage, etc., with malarial incidence. The first stage includes data collection by the passive surveillance system; the second stage includes establishing relationships among the climatic factors with malarial incidence and finally predicting using machine learning classifiers. In the analysis, the adaptive boosted J48 (AB-J48) decision tree machine learning classifier outperformed other classifiers under the study with an accuracy of 95% in establishing a relationship among climatic factors with malarial incidence. The inferred results from the investigation are found to be stupendous which helps the public health authorities and medical practitioners to take precautionary steps to avoid more deaths.

show abstract

Section: Resultsmentioning

confidence: 99%

An Efficient Approach for Malarial Epidemic Prognosis Using Machine Learning Classifiers

Kumar¹,

Sikamani²

2022

INDJCSE

View full text Add to dashboard Cite

show abstract

“…Haroon and Eranna [20] posit that real-time event streams can present variability, especially when digital image processing is employed for activity identification. Many contemporary techniques fall short when dealing with real-world events, rendering them suboptimal.…”

Section: Literature Surveymentioning

confidence: 99%

Activity recognition based on spatio-temporal features with transfer learning

Hiremath

et al. 2024

IJ-AI

View full text Add to dashboard Cite

<span lang="EN-US">Human action recognition (HAR) has gathered significant attention recently due to its high demand in various application domains. We explore different CNN architectures for extracting Spatio-Temporal features. In addition to spatial correlation in 2D images, video actions also own the temporal domain attributes. Many research attempts addressed simple activity recognition, but complex activity recognition is still challenging. In the proposed work, the concept of transfer learning consists of two pre-trained networks, ResNet50 and VGG16, which are used to extract Spatiotemporal features and are later fused using the averaging method. Pre-processed frames are considered for the pre-trained network, the pre-processing consists of frame extraction, resizing, and contrast enhancement. The fused features are trained using a multiclass non-linear SVM classifier that achieved an accuracy of 89.71% on the UCF-101 database.</span>

show abstract

“…It is a type of statistical learning in which each item of the database is described by several characteristics or attributes. Machine learning models have been applied in many areas of research [5]- [9]. In contrast, the other category of AI claims deep learning, which is also a type of statistical learning but extracts feature from input data.…”

Section: Introductionmentioning

confidence: 99%

A survey of deepfakes in terms of deep learning and multimedia forensics

Hadi

Kadhem²,

Abbas³

2022

IJECE

View full text Add to dashboard Cite

Artificial intelligence techniques are reaching us in several forms, some of which are useful but can be exploited in a way that harms us. One of these forms is called deepfakes. Deepfakes is used to completely modify video (or image) content to display something that was not in it originally. The danger of deepfake technology impact on society through the loss of confidence in everything is published. Therefore, in this paper, we focus on deepfakedetection technology from the view of two concepts which are deep learning and forensic tools. The purpose of this survey is to give the reader a deeper overview of i) the environment of deepfake creation and detection, ii) how deep learning and forensic tools contributed to the detection of deepfakes, and iii) finally how in the future incorporating both deep learning technology and tools for forensics can increase the efficiency of deepfakes detection.

show abstract

A simplified machine learning approach for recognizing human activity

Cited by 6 publications

References 26 publications

An Efficient Approach for Malarial Epidemic Prognosis Using Machine Learning Classifiers

An Efficient Approach for Malarial Epidemic Prognosis Using Machine Learning Classifiers

Activity recognition based on spatio-temporal features with transfer learning

A survey of deepfakes in terms of deep learning and multimedia forensics

Contact Info

Product

Resources

About