Current Issue : July - September Volume : 2018 Issue Number : 3 Articles : 5 Articles
Over the last years deep learning methods have been shown to outperform previous state-of-the-art machine learning techniques\nin several fields, with computer vision being one of the most prominent cases. This review paper provides a brief overview of some\nof the most significant deep learning schemes used in computer vision problems, that is, Convolutional Neural Networks, Deep\nBoltzmann Machines and Deep Belief Networks, and Stacked Denoising Autoencoders. A brief account of their history, structure,\nadvantages, and limitations is given, followed by a description of their applications in various computer vision tasks, such as object\ndetection, face recognition, action and activity recognition, and human pose estimation. Finally, a brief overview is given of future\ndirections in designing deep learning schemes for computer vision problems and the challenges involved therein....
Frailty and senility are syndromes that affect elderly people. The ageing process involves a decay of cognitive and motor functions which\noften produce an impact on the quality of life of elderly people. Some studies have linked this deterioration of cognitive and motor function\nto gait patterns. Thus, gait analysis can be a powerful tool to assess frailty and senility syndromes. In this paper, we propose a vision-based\ngait analysis approach performed on a smartphone with cloud computing assistance. Gait sequences recorded by a smartphone camera are\nprocessed by the smartphone itself to obtain spatiotemporal features. These features are uploaded onto the cloud in order to analyse and\ncompare them to a stored database to render a diagnostic. The feature extraction method presented can work with both frontal and sagittal\ngait sequences although the sagittal view provides a better classification since an accuracy of 95% can be obtained....
Visual prosthesis applying electrical stimulation to restore visual function for the blind has promising prospects. However, due\nto the low resolution, limited visual field, and the low dynamic range of the visual perception, huge loss of information occurred\nwhen presenting daily scenes. The ability of object recognition in real-life scenarios is severely restricted for prosthetic users. To\novercome the limitations, optimizing the visual information in the simulated prosthetic vision has been the focus of research.This\npaper proposes two image processing strategies based on a salient object detection technique. The two processing strategies enable\nthe prosthetic implants to focus on the object of interest and suppress the background clutter. Psychophysical experiments show\nthat techniques such as foreground zooming with background clutter removal and foreground edge detection with background\nreduction have positive impacts on the task of object recognition in simulated prosthetic vision. By using edge detection and\nzooming technique, the two processing strategies significantly improve the recognition accuracy of objects.We can conclude that\nthe visual prosthesis using our proposed strategy can assist the blind to improve their ability to recognize objects. The results will\nprovide effective solutions for the further development of visual prosthesis...
Aiming at howto achieve optimal control of joint pitch angles in the process of the robot surmounting obstacle, taking the developed\ncoal mine rescue snake robot as an experimental platform, a pose control algorithm based on particle swarm optimization weight\ncoefficient of extreme learning machine (PSOELM) is proposed. In order to obtain the optimized hidden layer matrix of the\nextreme learning machine (ELM), particle swarm optimization (PSO) is applied to optimize the weight coefficient of hidden layer\nmatrix.The simulation and experiment results prove that, compared with the ELMalgorithm, the smallermean square error (MSE)\nbetween the joint pitch angles of robot and the expected values is acquired by the PSOELM, which overcomes the shortcoming that\ntraditional extreme learning machine cannot reach the best performance because of the random selection of the parameters of the\nhidden layer nodes. PSOELM is superior to ELM algorithm in control accuracy, fast searching for the optimal and stability.Optimal\ncontrol of robot�s joint pitch angles is achieved. Thealgorithm is applied to the surmounting obstacle control of the developed snake\nrobot, and it lays the foundation for further implement of the coal mine rescue....
CPS is potential application in various fields, such as medical, healthcare, energy, transportation, and defense, as well as Industry 4.0\nin Germany. Although studies on the equipment aging and prediction of problemhave been done by combining CPSwith Industry\n4.0, such studies were based on small numbers and majority of the papers focused primarily on CPS methodology. Therefore, it is\nnecessary to study active self-protection to enable self-management functions, such as self-healing by applying CPS in shop-floor.\nIn this paper, we have proposedmodeling of shop-floor and a dynamic reconfigurable CPS scheme that can predict the occurrence\nof anomalies and self-protection in the model. For this purpose, SVMwas used as a machine learning technology and it was possible\nto restrain overloading in manufacturing process. In addition, we design CPS framework based on machine learning for Industry\n4.0, simulate it, and perform. Simulation results show the simulation model autonomously detects the abnormal situation and it is\ndynamically reconfigured through self-healing....
Loading....