Static and Dynamic Human Activity Detection Using Multi CNN-ELM Approach

Ankalaki, Shilpa; Thippeswamy, M. N.

doi:10.1007/978-981-16-1338-8_18

Cited by 6 publications

(7 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The UniMiB SHAR dataset comprises of movement traces from both falls and typical ADL activity. Public access to the raw data, which is free of gravitational constant influence and noise (such as EMG noise), is provided 20) . Because it only includes accelerator data, the UniMiB SHAR dataset was gathered from a real-time environment with little power consumption.…”

Section: Resultsmentioning

confidence: 99%

“…A stack of deep learning layers of varying depths is used to categorize the signal properties as proposed in 20) . The paper used a conventional CNN method to categorize the signals as either stationary or active.…”

Section: Resultsmentioning

confidence: 99%

“…Despite strides in generalization techniques, the task of creating models with strong generalization capabilities across diverse individuals, environments, and sensor setups remains an ongoing research focus. Transfer learning approaches hold promise, but further exploration is essential to enhance their transferability and adaptability to different domains 20) . Another persistent challenge in human activity recognition revolves around imbalanced datasets.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Advancing Human Activity Recognition: A Novel WAECN-BO Approach for Distinguishing Highly Correlated Actions

Ghalan,

Rajesh Kumar Aggarwal

2023

Evergreen

View full text Add to dashboard Cite

Human actions, when gauged through the lens of Human Activity Recognition (HAR), find numerous applications across healthcare, sports, and security sectors. Nonetheless, the intricacy of HAR becomes apparent when distinguishing akin actions poses a challenge. To tackle this issue, the present article introduces a pioneering method known as the Weighted Average Ensemble of Convolutional Neural Networks with Bayesian Optimization (WAECN-BO), which amalgamates five distinct Convolutional Neural Network (CNN) layer configurations. Notably, this method incorporates a fresh CNN layer designed to enable more intricate abstraction and optimizes its hyperparameters through Bayesian optimization. The evaluation of this method transpires on the UniMiB SHAR Database, a well-recognized benchmark dataset for HAR, focusing on actions with considerable resemblance. The findings reveal a remarkable accuracy rate of 99.98% across the entire dataset, surpassing established state-of-the-art approaches. Additionally, an analysis of the individual contributions made by each CNN layer configuration to the model's performance is conducted. This method, poised to enhance the accuracy of HAR systems across diverse domains, especially those dealing with actions that closely resemble each other, emerges as a promising advancement.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Advancing Human Activity Recognition: A Novel WAECN-BO Approach for Distinguishing Highly Correlated Actions

Ghalan,

Rajesh Kumar Aggarwal

2023

Evergreen

View full text Add to dashboard Cite

show abstract

“…Figure 2 shows, human activities can be divided into three basic types: static activities [17], dynamic activities [18] and activities with posture transitions [4]. Static activities generally refer to activities, such as Sitting and Standing, which basically do not involve human movement.…”

Section: Methodsmentioning

confidence: 99%

A Radar-Based Human Activity Recognition Using a Novel 3-D Point Cloud Classifier

Taha

Taylor

et al. 2022

IEEE Sensors J.

View full text Add to dashboard Cite

This article provides a new benchmark dataset for 3D point cloud classification in which the manually labelled human activity data exceeds 100 point clouds per frame and is capable of meeting the training needs for data-intensive learning approaches. In this study, a case study is considered for evaluating the benchmark using a deep LSTM neural network, which demonstrated a significant performance improvement over the state-of-the-art human activity recognition area. To date, numerous types of collection devices have been used in the recognition of human activities. However, due to the scarcity of training data, the task of 3D point cloud labelling has not yet made significant progress. To overcome this challenge, it is aimed to deduce this data requirements gap, allowing deep learning methods to reach their full potential in 3D point cloud tasks. The dataset used for this process is comprised of dense point clouds acquired with the static ground sensor by the NodeNs company supported MIMO radar (NodeNs ZERO 60 GHz IQ radar). It contains multiple types of human being data ranging from one to four individuals and encompasses a range of human action scenarios, including standing, sitting, picking up, falling, and walking. Furthermore, it also investigated sensor locations and requirements for human being data collection that is from a single subject to multiple subjects, as well as identified and analysed various sensing devices and applications that collect activity data. In this regard, a thorough study is conducted on several benchmark datasets, examining sensors, characteristics, activity categories, and other data. Finally, it compares and analyses the activity recognition methods used in several benchmark datasets based on the current study. Unlike existing devices, the new NodeNs sensor provides more accessible and straightforward point cloud data to capture human movement information. Depending on an advanced detection algorithm to process point cloud data it achieved more than 95% accuracy on the benchmark dataset.

show abstract

“…Firstly, advanced deep learning architectures, like deep neural networks (DNNs), can utilize a large number of variables and features, including laboratory measurements and diagnoses, to improve prediction accuracy [18]. Secondly, CNN models can effectively identify and diagnose diseases in plants by analyzing leaf images, achieving high accuracy rates and reducing training time [19], [20] Thirdly, deep learning techniques, like CNN-ELM, can classify human activities accurately without the need for handcrafted features, enhancing the performance of human activity recognition systems [21]. Additionally, deep CNN models, combined with ensemble learning, have shown robustness and better performance in crack detection, surpassing traditional image processing methods [22].…”

Section: Introductionmentioning

confidence: 99%

Enhancing cirrhosis detection: A deep learning approach with convolutional neural networks

Endah H,

Wijaya,

Khotibul Ahsan

2023

J. Soft Comput. Explor.

View full text Add to dashboard Cite

Cirrhosis, a prevalent and life-threatening liver condition, demands early detection for effective intervention. This study investigates the potential of machine learning algorithms, including Convolutional Neural Networks (CNN), Support Vector Machines (SVM), Decision Trees, K-Nearest Neighbors (KNN), Gaussian Naive Bayes (GNB), and Gradient Boosting (GBoost), in cirrhosis prediction using a dataset from Kaggle containing 418 observations and 20 attributes. Performance evaluation involves metrics like accuracy, precision, recall, and F1-score, revealing CNN's superior performance with an 84% accuracy rate. The study highlights the importance of algorithm selection and feature engineering in medical diagnosis. Moreover, a comparison with traditional machine learning techniques underscores CNN's prowess in this domain. Beyond cirrhosis, CNNs offer promise for automating feature extraction from medical imagery and recognizing complex patterns, potentially transforming diagnostic accuracy in healthcare.

show abstract

Static and Dynamic Human Activity Detection Using Multi CNN-ELM Approach

Cited by 6 publications

References 14 publications

Advancing Human Activity Recognition: A Novel WAECN-BO Approach for Distinguishing Highly Correlated Actions

Advancing Human Activity Recognition: A Novel WAECN-BO Approach for Distinguishing Highly Correlated Actions

A Radar-Based Human Activity Recognition Using a Novel 3-D Point Cloud Classifier

Enhancing cirrhosis detection: A deep learning approach with convolutional neural networks

Contact Info

Product

Resources

About