Learning Compact Features for Human Activity Recognition Via Probabilistic First-Take-All

Ye, Jun; Qi, Guo-Jun; Zhuang, Naifan; Hu, Hao; Hua, Kien A.

doi:10.1109/tpami.2018.2874455

Cited by 43 publications

(15 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep learning algorithms may also be applied to increase accuracy compared to simpler RF or k-NN algorithms [23], [30]. However, deep learning algorithms require more time to train models, which can impact usability and device adoption.…”

Section: Discussionmentioning

confidence: 99%

“…However, deep learning algorithms require more time to train models, which can impact usability and device adoption. A new method of learning features called probabilistic First-Take-All could be applied to accelerate the training and testing speeds in deep learning models with marginal changes to accuracy [30]. Notably, the sample size of this study (i.e.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Evaluation of Machine Learning Models for Classifying Upper Extremity Exercises Using Inertial Measurement Unit-Based Kinematic Data

Hua

Chaudhari

Johnson

et al. 2020

IEEE J. Biomed. Health Inform.

View full text Add to dashboard Cite

The amount of home-based exercise prescribed by a physical therapist is difficult to monitor. However, the integration of wearable inertial measurement unit (IMU) devices can aid in monitoring home exercise by analyzing exercise biomechanics. The objective of this study is to evaluate machine learning models for classifying nine different upper extremity exercises, based upon kinematic data captured from an IMU-based device. Fifty participants performed one compound and eight isolation exercises with their right arm. Each exercise was performed ten times for a total of 4500 trials. Joint angles were calculated using IMUs that were placed on the hand, forearm, upper arm, and torso. Various machine learning models were developed with different algorithms and train-test splits. Random forest models with flattened kinematic data as a feature had the greatest accuracy (98.6%). Using triaxial joint range of motion as the feature set resulted in decreased accuracy (91.9%) with faster speeds. Accuracy did not decrease below 90% until training size was decreased to 5% from 50%. Accuracy decreased (88.7%) when splitting data by participant. Upper extremity exercises can be classified accurately using kinematic data from a wearable IMU device. A random forest classification model was developed that quickly and accurately classified exercises. Sampling frequency and lower training splits had a modest effect on Manuscript

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Evaluation of Machine Learning Models for Classifying Upper Extremity Exercises Using Inertial Measurement Unit-Based Kinematic Data

Hua

Chaudhari

Johnson

et al. 2020

IEEE J. Biomed. Health Inform.

View full text Add to dashboard Cite

show abstract

“…According to summarised performance in Table 3, the proposed FR-DL method helped us in recognising complex actions using spatio-temporal information, which were hidden in sequential patterns and features. We initialised the weights randomly and trained all the networks by reiterating the training stage until getting the minimum errors [37], [58], [59], [60], [61]. In addition to Softmax, the KNN is used for classification.…”

Section: Discussionmentioning

confidence: 99%

Complex Human Action Recognition in Live Videos Using Hybrid FR-DL Method

Serpush¹,

Rezaei²

2020

Preprint

View full text Add to dashboard Cite

Automated human action recognition is one of the most attractive and practical research fields in computer vision, in spite of its high computational costs. In such systems, the human action labelling is based on the appearance and patterns of the motions in the video sequences; however, the conventional methodologies and classic neural networks cannot use temporal information for action recognition prediction in the upcoming frames in a video sequence. On the other hand, the computational cost of the preprocessing stage is high. In this paper, we address challenges of the preprocessing phase, by an automated selection of representative frames among the input sequences. Furthermore, we extract the key features of the representative frame rather than the entire features. We propose a hybrid technique using background subtraction and HOG, followed by application of a deep neural network and skeletal modelling method. The combination of a CNN and the LSTM recursive network is considered for feature selection and maintaining the previous information, and finally, a Softmax-KNN classifier is used for labelling human activities. We name our model as "Feature Reduction \& Deep Learning" based action recognition method, or FR-DL in short. To evaluate the proposed method, we use the UCF dataset for the benchmarking which is widely-used among researchers in action recognition research. The dataset includes 101 complicated activities in the wild. Experimental results show a significant improvement in terms of accuracy and speed in comparison with six state-of-the-art articles.

show abstract

“…Having this in mind, some authors measured energy efficiency of HAR approaches with wearables [8,10,14,30,31,32]. Some authors analyzed the energy consumption of activity recognition of smartphones [45,111,112]. Data segmentation stage: Segmentation approaches also affect energy consumption, which is calculated through the computational complexity of a segmentation algorithm.…”

Section: Impact Of Human Activity Recognition (Har) Stages On Enermentioning

confidence: 99%

“…Energy consumption can be improved by reducing the number of sensors [61], reducing the amount of data on the sensor node [8,32], reducing the sampling rate [14,30,61,82,111,124,125], using a dynamically adjusted sampling rate [124] and Kinetic Energy Harvesting (KEH) supporting devices, as well as adaptive selection of sensors in real-time data acquisition [61] in the Data collection and filtering stage of HAR. The impact of some of these mechanisms is verified in practice and listed in Table 6.…”

Section: The Optimization Of Energy Consumption and Latency In Harmentioning

confidence: 99%

Step by Step Towards Effective Human Activity Recognition: A Balance between Energy Consumption and Latency in Health and Wellbeing Applications

Dinarevic

Husić

Baraković

2019

Sensors

View full text Add to dashboard Cite

Human activity recognition (HAR) is a classification process that is used for recognizing human motions. A comprehensive review of currently considered approaches in each stage of HAR, as well as the influence of each HAR stage on energy consumption and latency is presented in this paper. It highlights various methods for the optimization of energy consumption and latency in each stage of HAR that has been used in literature and was analyzed in order to provide direction for the implementation of HAR in health and wellbeing applications. This paper analyses if and how each stage of the HAR process affects energy consumption and latency. It shows that data collection and filtering and data segmentation and classification stand out as key stages in achieving a balance between energy consumption and latency. Since latency is only critical for real-time HAR applications, the energy consumption of sensors and devices stands out as a key challenge for HAR implementation in health and wellbeing applications. Most of the approaches in overcoming challenges related to HAR implementation take place in the data collection, filtering and classification stages, while the data segmentation stage needs further exploration. Finally, this paper recommends a balance between energy consumption and latency for HAR in health and wellbeing applications, which takes into account the context and health of the target population.

show abstract

Learning Compact Features for Human Activity Recognition Via Probabilistic First-Take-All

Cited by 43 publications

References 26 publications

Evaluation of Machine Learning Models for Classifying Upper Extremity Exercises Using Inertial Measurement Unit-Based Kinematic Data

Evaluation of Machine Learning Models for Classifying Upper Extremity Exercises Using Inertial Measurement Unit-Based Kinematic Data

Complex Human Action Recognition in Live Videos Using Hybrid FR-DL Method

Step by Step Towards Effective Human Activity Recognition: A Balance between Energy Consumption and Latency in Health and Wellbeing Applications

Contact Info

Product

Resources

About