Human action recognition targets recognising different actions from a sequence of observations and different environmental conditions. A wide different applications is applicable to vision based action recognition research. This can include video surveillance, tracking, health care, and human–computer interaction. However, accurate and effective vision based recognition systems continue to be a big challenging area of research in the field of computer vision. This review introduces the most recent human action recognition systems and provides the advances of state-of-the-art methods. To this end, the direction of this research is sorted out from hand-crafted representation based methods including holistic and local representation methods with various sources of data, to a deep learning technology including discriminative and generative models and multi-modality based methods. Next, the most common datasets of human action recognition are presented. This review introduces several analyses, comparisons and recommendations that help to find out the direction of future research.
A wide range of techniques exist to help control the thermal comfort of an occupant in indoor environments. A novel technique is presented here to adaptively estimate the occupant’s metabolic rate. This is performed by utilising occupant’s actions using computer vision system to identify the activity of an occupant. Recognized actions are then translated into metabolic rates. The widely used Predicted Mean Vote (PMV) thermal comfort index is computed using the adaptivey estimated metabolic rate value. The PMV is then used as an input to a fuzzy control system. The performance of the proposed system is evaluated using simulations of various activities. The integration of PMV thermal comfort index and action recognition system gives the opportunity to adaptively control occupant’s thermal comfort without the need to attach a sensor on an occupant all the time. The obtained results are compared with the results for the case of using one or two fixed metabolic rates. The included results appear to show improved performance, even in the presence of errors in the action recognition system.
Human action recognition (HAR) is an important yet challenging task. This paper presents a novel method. First, fuzzy weight functions are used in computations of depth motion maps (DMMs). Multiple length motion information is also used. These features are referred to as fuzzy weighted multi-resolution DMMs (FWMDMMs). This formulation allows for various aspects of individual actions to be emphasized. It also helps to characterise the importance of the temporal dimension. This is important to help overcome, e.g., variations in time over which a single type of action might be performed. A deep convolutional neural network (CNN) motion model is created and trained to extract discriminative and compact features. Transfer learning is also used to extract spatial information from RGB and depth data using the AlexNet network. Different late fusion techniques are then investigated to fuse the deep motion model with the spatial network. The result is a spatial temporal HAR model. The developed approach is capable of recognising both human action and human–object interaction. Three public domain datasets are used to evaluate the proposed solution. The experimental results demonstrate the robustness of this approach compared with state-of-the art algorithms.
The dense deployment of small cells in the existing 5G networks is a proper solution to enhance the capacity and extend the coverage of the cellular network. However, the service quality is expected to be weak as a result of unnecessary handover, which is caused by dense small cell deployment. This work presents a velocity-based handover hysteresis margin method for outdoor small cells to reduce frequent handovers in 5G network. The mobility information of the user, velocity and direction, are deployed to optimize the list of candidate small cells and to manage the handover, in addition to the distance from the user's location to the small cell center and the small cell radius. The handover hysteresis margin is derived according to the velocity of the user so that the unnecessary handover is reduced. Results show that our method outperformed the conventional one in terms of the total number of handovers, unnecessary handover probability and network throughput for different velocities.
Speech and image processing are fundamental components of artificial intelligence technology. Speech processing can be deployed to acquire unique features of a person's voice. These can then be used for speaker identification as well as gender and age classification. This paper studies the effect of the relative degree of correlation in speech features on gender classification. To this end, gender classification performance is evaluated using orthogonally transformed speech features. The performance is then compared to the case when speech features are used without transformation. Two machine learning approaches are used in the evaluation. One of them primarily depends on Gaussian Mixture Models (GMM) and the other one uses Support Vector Machines (SVM). The results show that less correlated speech features, obtained after the orthogonal transformation, provides better classification performance.