Two-Stage Human Activity Recognition Using 2D-ConvNet

Verma, Kamal Kant; Singh, Brij Mohan; Mandoria, Hardwari Lal; Chauhan, Prachi

doi:10.9781/ijimai.2020.04.002

Cited by 19 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DNN (Ding and Fan, 2015), BLSTM, CNN and CNN-LSTM (Li, 2018; Kästner, 2013) are used as learning algorithms for the classification models. Verma (2020) has presented two-stage HAR using 2D-ConvNet, and various other researchers have presented the computational model for HAR (Siirtola and Röning, 2012; Herrera, 2020). The DNN takes an input of 80 × 3 Numpy array, and output is simply a one-hot vector containing seven binary values according to the activities classified.…”

Section: Proposed Methodology and Trajectories Generationmentioning

confidence: 99%

Wearable sensor-based pattern mining for human activity recognition: deep learning approach

Bijalwan¹,

Semwal

Gupta

2021

View full text Add to dashboard Cite

Purpose This paper aims to deal with the human activity recognition using human gait pattern. The paper has considered the experiment results of seven different activities: normal walk, jogging, walking on toe, walking on heel, upstairs, downstairs and sit-ups. Design/methodology/approach In this current research, the data is collected for different activities using tri-axial inertial measurement unit (IMU) sensor enabled with three-axis accelerometer to capture the spatial data, three-axis gyroscopes to capture the orientation around axis and 3° magnetometer. It was wirelessly connected to the receiver. The IMU sensor is placed at the centre of mass position of each subject. The data is collected for 30 subjects including 11 females and 19 males of different age groups between 10 and 45 years. The captured data is pre-processed using different filters and cubic spline techniques. After processing, the data are labelled into seven activities. For data acquisition, a Python-based GUI has been designed to analyse and display the processed data. The data is further classified using four different deep learning model: deep neural network, bidirectional-long short-term memory (BLSTM), convolution neural network (CNN) and CNN-LSTM. The model classification accuracy of different classifiers is reported to be 58%, 84%, 86% and 90%. Findings The activities recognition using gait was obtained in an open environment. All data is collected using an IMU sensor enabled with gyroscope, accelerometer and magnetometer in both offline and real-time activity recognition using gait. Both sensors showed their usefulness in empirical capability to capture a precised data during all seven activities. The inverse kinematics algorithm is solved to calculate the joint angle from spatial data for all six joints hip, knee, ankle of left and right leg. Practical implications This work helps to recognize the walking activity using gait pattern analysis. Further, it helps to understand the different joint angle patterns during different activities. A system is designed for real-time analysis of human walking activity using gait. A standalone real-time system has been designed and realized for analysis of these seven different activities. Originality/value The data is collected through IMU sensors for seven activities with equal timestamp without noise and data loss using wirelessly. The setup is useful for the data collection in an open environment outside the laboratory environment for activity recognition. The paper also presents the analysis of all seven different activity trajectories patterns.

show abstract

Section: Proposed Methodology and Trajectories Generationmentioning

confidence: 99%

Wearable sensor-based pattern mining for human activity recognition: deep learning approach

Bijalwan¹,

Semwal

Gupta

2021

View full text Add to dashboard Cite

show abstract

“…Vision based human activity recognition has four basic steps, that is, activity sequence recording, feature extraction, model implementation and training and finally recognition. RGB‐D camera is extensively used for human activity recognition (Verma et al, 2020; Ye et al, 2013) due to its low complexity, ease of doing, higher accuracy rate and cost effectiveness in nature. Shotton et al (2013) proposed a method to quickly and accurately predict human pose, the 3D positions of body joints using single depth image and then calculate skeleton using proposed algorithm.…”

Section: Literature Reviewmentioning

confidence: 99%

Heterogeneous computing model for post‐injury walking pattern restoration and postural stability rehabilitation exercise recognition

Bijalwan¹,

Semwal

Singh

et al. 2021

Expert Systems

View full text Add to dashboard Cite

The research paper presents the heterogeneous computing model for analysis & restoration of human walking deformity and posture instability. Gait‐related walking activities are very important for the analysis of postural instability, repairment of gait abnormality, diagnosis of cognitive declination, enhance the cognitive ability of human‐centered humanoid robot system, and many clinical diagnoses, for example, Parkinson, pathological gait, freezing of gait, etc. at an early stage. For experiment analysis, 10 different lower limb activities are being considered of healthy and crouch walking subjects. A total of 25 healthy and 10 crouch walk subjects are considered for experiment purposes of different age groups, sex, and mental status. To achieve this objective the pattern of 10 different rehabilitation activities are captured using RGB‐Depth (RGB‐D) camera and classified using heterogeneous deep learning models. Different deep learning models Convolutional Neural Network (CNN) and CNN‐LSTM (CNN‐Long Short Term Memory) are used for the classification of these rehabilitation exercises. The RGB‐D data is obtained using a Microsoft Kinect v2 sensor on a 100 Hz sampling frequency. Experimental results have shown significant activity recognition accuracy with 96% and 98% for CNN and CNN‐LSTM models respectively.

show abstract

“…Amongst the DL techniques, Convolutional Neural Networks (CNN) [3,4] have been having the greatest influence on practical machine learning. Due to high capability of DL, a variety of complicated tasks have been carried out by the help of DL-based technieques like face classification by using deep belief networks [5], human sentiment classification [6], human consumption behavior forcasting [7], human activity recognition [8], hand gesture recognition [9], plannar pressure segmentation [10], driving behavior recognition [11], finally even in the case of recent COVID-19 detection from chest X-ray images [12][13][14], etc. One of the CNN-based systems widely used is deep face recognition system which due to its implementation on cloud level it can be targeted by privacy cyber-attackers.…”

Section: Introductionmentioning

confidence: 99%

Model Inversion Attack: Analysis under Gray-box Scenario on Deep Learning based Face Recognition System

2021

KSII TIIS

View full text Add to dashboard Cite

In a wide range of ML applications, the training data contains privacy-sensitive information that should be kept secure. Training the ML systems by privacy-sensitive data makes the ML model inherent to the data. As the structure of the model has been fine-tuned by training data, the model can be abused for accessing the data by the estimation in a reverse process called model inversion attack (MIA). Although, MIA has been applied to shallow neural network models of recognizers in literature and its threat in privacy violation has been approved, in the case of a deep learning (DL) model, its efficiency was under question. It was due to the complexity of a DL model structure, big number of DL model parameters, the huge size of training data, big number of registered users to a DL model and thereof big number of class labels. This research work first analyses the possibility of MIA on a deep learning model of a recognition system, namely a face recognizer. Second, despite the conventional MIA under the white box scenario of having partial access to the users' non-sensitive information in addition to the model structure, the MIA is implemented on a deep face recognition system by just having the model structure and parameters but not any user information. In this aspect, it is under a semi-white box scenario or in other words a gray-box scenario. The experimental results in targeting five registered users of a CNN-based face recognition system approve the possibility of regeneration of users' face images even for a deep model by MIA under a gray box scenario. Although, for some images the evaluation recognition score is low and the generated images are not easily recognizable, but for some other images the score is high and facial features of the targeted identities are observable. The objective and subjective evaluations demonstrate that privacy cyber-attack by MIA on a deep recognition system not only is feasible but also is a serious threat with increasing alert state in the future as there is considerable potential for integration more advanced ML techniques to MIA.

show abstract

Two-Stage Human Activity Recognition Using 2D-ConvNet

Cited by 19 publications

References 0 publications

Wearable sensor-based pattern mining for human activity recognition: deep learning approach

Wearable sensor-based pattern mining for human activity recognition: deep learning approach

Heterogeneous computing model for post‐injury walking pattern restoration and postural stability rehabilitation exercise recognition

Model Inversion Attack: Analysis under Gray-box Scenario on Deep Learning based Face Recognition System

Contact Info

Product

Resources

About