We focused on the recognition of pedestrian action using motion sensor and machine learning. In this paper, we present our method how to define feature of actions from acquired data, and how to use k nearest neighborhood classifier to data learning and evaluation.

The concept of motion-history image (MHI) is widely adopted by many researchers to solve problems of human actions recognition. An improved MHI with only one parameter is proposed in this paper, it is easier to be implemented and can retain more effective movement information compared with the original...

In order to solve the problem on making full use of RGB+D dataset that includes RGB data, 3D skeletal data, depth map sequences and infrared videos, this paper proposes an action recognition method of RGB+D videos that merges a multi-layer recurrent neural network and two-stream convolutional networks,...

With the development of embedded technology and Internet of things technology, smart home has developed rapidly in recent years. At the same time, deep learning also has brought breakthroughs. The application of deep learning to smart home system can bring a good user experience and increase security....

The finger vein recognition, as a new biometric identification technology, judges the identity of a person by using their finger vein angiography images obtained by near-infrared light, and has recently drawn considerable attention from scientists worldwide. In this work, a novel binary code learning...

Visual SLAM is the process that a camera sensor is used to locate the body of the motion and build a map of the surrounding environment at the same time. First the types of sensors and the framework of visual SLAM are introduced in this article. And then it introduces the word bag model of visual mileage...

With the development of the research of artificial intelligence, image recognition technology has become one of the hot research topics in the modern society, the research results have been widely applied to many fields, which has brought remarkable economic benefits and social benefits. This paper briefly...

Having powerful ability to learn and represent features, deep convolutional neural networks (CNN) can get better results in image super-resolution reconstruction. However, deep networks also exist some problems. For example, the gradient will gradually vanish through the network, which makes the training...

Naïve Bayes classifiers is widely used for text classification because of its simplicity and effectiveness. In this paper, an improved Naïve Bayes classifiers was proposed, using multinomial model to modify its rough parameter estimation and parallel competing with MapReduce to categories to text documents....

Human activities have been a hot research field. Many sensors are embedded in the smartphone, which makes mobile sensor become available. Sensors of smartphone can early get the human activities information, which can analyze the human behaviors and provide the useful information to the human. In this...

BP neural network is a common kind of neural network for recognition and classification, but it is obvious that some difficulties are find during the training process. In this paper, we introduced the basic principle of BP algorithm and propose a parameter adjustment procedure for activation function...

The water distribution system is a spatially large and complex system. Its proper functioning is determined by having been correctly developed in its design and in the hydraulic calculations. The basic purpose of the calculations is the selection of the diameters of the water pipes and the flow of water...

Designing a water distribution system is inherently associated with hydraulic calculations, the primary purpose of which is to select the diameters of water pipelines. Computer programs may choose diameters, but most often, this task is up to the designer. It is necessary to control flow velocity; at...

Welding Procedure for joint has a very important position in the manufacture of all kinds of important products. Application of neural network technology could improve the existing in welding procedure qualification for joint process. It is shown that the yield strength of welded joint could be predicted...

The teeth are natural self-defense weapon of animals. For human, the pronunciation of language is closely related to the upper and lower front teeth (incisors). Furthermore, the cleanliness of the teeth even has an important influence on daily social activities and status of people. Therefore, when the...

The research on robot grasping involves mechanical, control, computer, artificial intelligence and so on. Robot Grasping is also a good emplementation of minimal research to support other related research. Efforts on flexibility and interactivity of robot grasping can promote many related studies. In...

Since the current world is overwhelmed by internet, it becomes important and necessary to find the personalized video information to meet the growing demand for all kinds of users. Video recommendation is a very useful method for getting video data quickly. A personalized video recommendation algorithm...