A Hybrid Posture Detection Framework: Integrating Machine Learning and Deep Neural Networks
read more
Citations
Hybrid and Deep Learning Approach for Early Diagnosis of Lower Gastrointestinal Diseases
Classification of Indoor Human Fall Events Using Deep Learning.
Yoga pose classification: a CNN and MediaPipe inspired deep learning approach for real-world application
Convolutional Neural Network-Based Terahertz Spectral Classification of Liquid Contraband for Security Inspection
Data and Decision Level Fusion-Based Crack Detection for Compressor Blade Using Acoustic and Vibration Signal
References
Automatic analysis of affective postures and body motion to detect engagement with a game companion
Multilingual Sentiment Analysis: State of the Art and Independent Comparison of Techniques.
Fine detection of grasp force and posture by amputees via surface electromyography.
eCushion: A Textile Pressure Sensor Array Design and Calibration for Sitting Posture Analysis
An Intelligent Non-Invasive Real-Time Human Activity Recognition System for Next-Generation Healthcare.
Related Papers (5)
Frequently Asked Questions (17)
Q2. What are the different machine learning classifiers used to evaluate the performance of the approach?
After feature extraction, there are different machine learning classifiers, including SVM, logistic regression, KNN, decision tree, naive bayes, random forest, LDA and QDA have been applied in order to evaluate the performance of the approach.
Q3. What are the main features of the proposed hybrid?
In order to classify the posture prediction, standard (logistic regression, random forest, KNN, Naı̈ve Bayes, decision tree, linear discriminant analysis, quadratic discriminant analysis and SVM) and deep learning classifiers such as (1D-CNN, 2D-CNN, LSTM, BiLSTM) are trained.
Q4. What is the purpose of this study?
In this study, the prediction of ML classifiers (logisticregression, random forest, KNN, Naı̈ve Bayes, decision tree, linear discriminant analysis, quadratic discriminant analysis and SVM) and DL classifiers (CNN, LSTM) are used as input of CNN, LSTM architecture.
Q5. What is the main focus of this paper?
In this paper focus is on Indian classical dance, Bharatanatyam, which is driven by music as well as motion for posture recognition.
Q6. What is the method for detecting posture?
A network of sensors is used for data collection using neighbourhood rule (CNN), then data balancing is done with Kennard-stone algorithm and reduction in dimensions via principal component analysis.
Q7. What are the performance metrics used to evaluate the proposed approach?
In order to evaluate the performance of the proposed approach, precision, recall, F-score and accuracy metrics were used:Precision = TPTP + FP (1)Recall = TPTP + FN (2)Precision+Recall(3)Accuracy = TP + TNTP + TN + FP + FN (4)Human Body Posture Detection:
Q8. What is the proposed architecture for long short term memory?
The long short term memory (LSTM) proposed architecture contains input layer, two different stacked LSTM and one output as fully connected layer.
Q9. What is the purpose of the paper?
The deep learning can be used in different various application such as cyber-security, sentiment analysis, speech enhancement and etc. [31, 32, 33, 34, 35, 36, 37, 38] .
Q10. How many people are used in this study?
In order to evaluate the performance of the approach, the data used in their study is collected from five different individuals, the dataset consists of four males and females for different ethnicity, all the bracket of 25 to 30 years of age.
Q11. What is the architecture of the proposed hybrid?
the LSTM architecture consists of two different stacked bidirectional layers (contains 128 cells and 64 cells) with dropout 0.2 and a dense layer with two neurons and softmax activation.
Q12. What are the different methods used to train the classifiers?
The machine learning algorithms are trained based on the 10-fold cross-validation and train/test used Python variables containing the data and comparing the prediction of the data to the actual labels of the data.
Q13. What are the evaluation metrics used to compare the current algorithms?
There are different evaluation metrics such as accuracy, precision, recall and f-measure are used to compare the current algorithms.
Q14. What is the classification of the data?
The data is collected for five different subjects, and it has been classified into three different categories such as standing, sitting and walking.
Q15. What are the main things that are required for the analysis of dance?
For dance analysis few things must be undertaken like segment of the dance video, recognition of the detected action element and recognition of the dance sequences.
Q16. What is the important task for predicting posture?
It is to be noted that, after feature extraction, the most important task is to determines the combination of best features for posture prediction in term of accuracy.
Q17. What is the main topic of the paper?
In next section, the authors discuss their proposed hybrid model which integrates the machine learning and DNN methods including 1D-CNN, 2D-CNN, LSTM and BiLSTM.