Novel features for intensive human activity recognition based on wearable and smartphone sensors

Nandy, Asmita; Saha, Jayita; Chowdhury, Chandreyee

doi:10.1007/s00542-019-04738-z

Cited by 27 publications

(22 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, an increased DR1 can result in a reduced cross-sectional area of the fiber sheath (A). Therefore, according to equation (2), for the fibers with the same lengths, it can be found that an increased DR1 leads to an increased resistance of the fiber. Figure 6(a,b) show the effects of the CB concentration in the sheath material and DR1 on the breaking tenacity and breaking strain of the fibers, respectively.…”

Section: Resultsmentioning

confidence: 99%

“…In recent years, real-time monitoring and data management of human physiological signals have been in urgent need, which has greatly stimulated the development of wearable technologies, especially wearable sensing technologies. [1][2][3] Fabric sensors are fabricated by embedding or integrating sensing materials into fabrics, [4][5][6] which are characterized by features including softness, flexibility, lightweight, permeability, and durability. These features give the fabric sensors the capability of being compliant to the wearer's body and offer next-to-the-skin wearability, as well as good reliability when the sensors are used for monitoring physiological signals of the human body.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Strain-sensing fiber with a core–sheath structure based on carbon black/polyurethane composites for smart textiles

Pei

2021

Textile Research Journal

View full text Add to dashboard Cite

Fiber-shaped sensors have great potential for real-time monitoring of human physiological signals thanks to the merging of electronic and textile technologies. This work reports on the fabrication of a core–sheath structured strain-sensing fiber based on the wet-spinning method. The sensing fiber is composed of a core of non-conducting polyurethane and a conducting sheath of carbon black in a polyurethane matrix. Microscopic observation reveals the irregular shape or scattered appearance of the core as well as the porous structure of the fiber, the diameter of which is in the range 200–500 μm. The electro-mechanical properties and their dependence on carbon black concentration in the sheath and draw ratio between the spinneret and first drafting roller are experimentally investigated. It has been found that the percolation threshold of the fiber is in the range 15–16 wt%. The resistance of the fiber rises stably as the fiber is stretched up to a strain of 120% and increases with the increase of draw ratio between the spinneret and first drafting roller. In the cyclic tensile tests, the resistance of the fiber exhibits good repeatability in subsequent loading–unloading cycles after pre-stretching, despite partial recovery of the resistance in the first few cycles. The integration of the strain-sensing fiber into textiles is demonstrated by the core-spun yarn fabricated based on a modified vortex spinning method. The results of this study indicate the fiber could be a promising candidate for a sensor for smart textiles.

show abstract

Section: Resultsmentioning

confidence: 99%

mentioning

confidence: 99%

Strain-sensing fiber with a core–sheath structure based on carbon black/polyurethane composites for smart textiles

Pei

2021

Textile Research Journal

View full text Add to dashboard Cite

show abstract

“…Achieved accuracy for HAR tasks is 0.95. Similarly, the authors propose a stacked ensemble model for human activity recognition in [20]. A neural network is used as a meta learner while latent Dirichlet allocation, decision tree, Gaussian naive Bayes, k nearest neighbor, SVM, and multi-layered perceptron are used as the base learners for the proposed approach.…”

Section: Related Workmentioning

confidence: 99%

“…Table 11 contains the results and the models of the above-mentioned studies. [44] Deep CNN 0.946 [45] Deep CNN 0.951 [46] Deep CNN 0.947 [47] Deep CNN 0.900 [48] Deep ConvLSTM 0.958 [16] Residual Bi LSTM 0.905 [17] Multiview stacking 0.925 [18] Stacked LSTM 0.930 [19] SDAE+GBM 0.959 [20] Stacked ensemble 0.960 [21] Stacked ensemble 0.968 DS-MLP Deep Stacked Ensemble 0.973 Performance analysis suggests that the approaches based on deep CNN have an accuracy between 0.90 to 0.95. Ensemble approaches, on the other hand, tend to have higher accuracy than that of simple deep learning approaches.…”

Section: Performance Comparison With State-of-the-art Studiesmentioning

confidence: 99%

Sensor-Based Human Activity Recognition Using Deep Stacked Multilayered Perceptron Model

et al. 2020

View full text Add to dashboard Cite

The recent development of machines exhibiting intelligent characteristics involves numerous techniques including computer hardware and software architecture development. Many different hardware devices, wearable sensors, machine learning, and deep learning model implementations are being applied in human activity recognition (HAR) applications in recent times. However, to develop high accuracy classification systems for activity recognition using low-cost hardware technology is of significant importance. To achieve this goal this study uses sensor data from two low-cost sensors, gyroscope and accelerometer along with the implementation of an Artificial Neural Network (ANN) based deep learning model for HAR. In particular, Deep Stacked Multilayered Perceptron (DS-MLP) has been proposed. In the implementation of DS-MLP, an ANN model has been used as a meta-learner while five MLP models have been used as base-learners. In this study, these base-learners and meta-learner have been combined using a stack ensemble technique. The performance evaluations have been done first on the applicability of individual base-models followed by the application of DS-MLP, the results prove the high accuracy of 97.3% and 99.4% for heterogeneous datasets used for testing. The performance of the proposed DS-MLP models has been compared to some existing machine learning classifiers and several state-of-the-art activity recognition systems. The comparative result analysis also proves that the proposed system performed better than these classification approaches in terms of important performance metrics such as accuracy, precision, recall, F-score, Cohen's Kappa, and Mathew correlation coefficient.

show abstract

“…In previous studies, human activity recognition systems can be categorized into four classes: wearable-based [4], vision-based [5], ambient devices-based [6], and wirelessbased. Wearable sensor devices are widely used for human activity recognition especially in elder healthcare.…”

Section: Introductionmentioning

confidence: 99%

A Framework for Human Activity Recognition Based on WiFi CSI Signal Enhancement

Yang

Liu

et al. 2021

International Journal of Antennas and Propagation

View full text Add to dashboard Cite

With the advancement of wireless technologies and sensing methodologies, many studies have shown that wireless signals can sense human behaviors. Human activity recognition using channel state information (CSI) in commercial WiFi devices plays an important role in many applications. In this paper, a framework for human activity recognition was constructed based on WiFi CSI signal enhancement. Firstly, the sensitivity of different antennas to human activity was studied. An antenna selection algorithm was proposed, which can make a choice of the antenna automatically based on their sensitivity in accordance with different activities. Secondly, two signal enhancement approaches, which can strengthen the active signals and weaken the inactive signals, were proposed to extract the active interval caused by human activity. Finally, an activity segmentation algorithm was proposed to detect the start and end time of activity. In order to verify and evaluate the methods, extensive experiments have been conducted in real indoor environments. The experimental results have demonstrated that our solutions can eliminate a large number of redundant information brought by insensitive and inactive signals. Our research results can be put into use to improve recognition accuracy significantly and decrease the cost of recognition time.

show abstract

Novel features for intensive human activity recognition based on wearable and smartphone sensors

Cited by 27 publications

References 18 publications

Strain-sensing fiber with a core–sheath structure based on carbon black/polyurethane composites for smart textiles

Strain-sensing fiber with a core–sheath structure based on carbon black/polyurethane composites for smart textiles

Sensor-Based Human Activity Recognition Using Deep Stacked Multilayered Perceptron Model

A Framework for Human Activity Recognition Based on WiFi CSI Signal Enhancement

Contact Info

Product

Resources

About