Weight convergence analysis of DV-hop localization algorithm with GA

Gesture recognition has always been a research hotspot in the field of human-computer interaction. Its purpose is to realize the natural interaction with the machine by recognizing the semantics expressed by gesture. In the process of gesture recognition, the occlusion of gesture is an inevitable problem. In the process of gesture recognition, some or even all of the gesture features will be lost due to the occlusion of the gesture, resulting in the wrong recognition or even unrecognizability of the gesture. Therefore, it is of great significance to study gesture recognition under occlusion. The single shot multibox detector (SSD) algorithm is analyzed, and the front-end network is compared. Mobilenets is selected as the front-end network, and the Mobilenets-SSD network is improved. In tensorflow environment, based on the improved network model, the self-occlusion gesture and object occluding gesture are trained in color map, depth map, and color and depth fusion respectively. The recognition models of self-occlusion gestures and object-occlusion gestures in color map, depth map, and color and depth fusion are obtained. And compare and analyze the learning rate, loss function, and average accuracy of various models obtained for occlusion gesture recognition.

Section: Gesture Databasementioning

confidence: 99%

Section: Gesture Database and Gesture Preprocessingmentioning

confidence: 99%

Occlusion gesture recognition based on improvedSSD

Liao

et al. 2020

“…29,30 The performance of the algorithm is different because of the different selection operators in the algorithm, which makes it show different advantages in dealing with optimization problems with certain characteristics. 31,32 Therefore, there are some common selection operators are described in detail as follows.…”

Section: The Related Workmentioning

confidence: 99%

“…Among these many‐objective optimization algorithms, the key is how to keep the balance between the convergence of solution set (i.e., the distance from the obtained solution to the real PF) and the diversity (i.e., the distribution of the obtained solution in the approximate PF) to get the best comprehensive performance 29,30 . The performance of the algorithm is different because of the different selection operators in the algorithm, which makes it show different advantages in dealing with optimization problems with certain characteristics 31,32 . Therefore, there are some common selection operators are described in detail as follows.…”

Section: The Related Workmentioning

confidence: 99%

A hybrid many‐objective optimization algorithm for coal green production problem

Cui

Zhang

2020

Self Cite

The problem of convergence and diversity in the course of population evolution is difficult to be balanced for solving the many-objective optimization problem (MaOP). To track with the problem, a many-objective optimization algorithm is designed. In the algorithm, a hybrid selection mechanism under the concurrent integration strategy is built to improve algorithm performance by employing the different selection operators. The concurrent integration strategy can select the suitable operator to balance the convergence and diversity of the solution in the course of the population evolutionary. To verify the effectiveness of the algorithm, the designed algorithm is compared with other five excellent many-objective algorithms on DTLZ and WFG test problem. What is more, the designed algorithm is applied to solve the coal green production optimization problem. The simulation results show that the performance of designed algorithm is superior to whether the DTLZ and WFG test problem or the application problem.

“…8 In order to lift the speed of the clustering algorithm, Maji et al proposed the concept of inhibitors. 9 Clustering algorithms have also begun to be applied in different fields, 10 such as the field of image segmentation, 11 data analysis, [12][13][14] and medicine. [15][16][17] Since the complete information of a given set of patterns is often not obtained in practical applications, the uncertainty arises in various pattern recognitions.…”

Section: Related Workmentioning

confidence: 99%

A novel fuzzy clustering algorithm based on rough set and inhibitive factor

Tang

Wang

et al. 2020

As an important data analysis method, rough set theory can be used to analyze data with uncertainties. Rough set is able to acquire knowledge by the indistinguishable relationship among data objects without any prior knowledge. Rough set theory provides a new theoretical means for solving soft computing problems and has a wide application space in data mining. Meanwhile, the fuzzy C-means clustering algorithm is sensitive to noisy points and has low convergence speed. In order to deal with the above problems, a novel fuzzy clustering algorithm based on rough set and inhibitive factor is proposed. According to the related concepts of rough set theory, the membership model of fuzzy C-means algorithm is redefined. Besides, an inhibitive factor is set to improve the convergence speed of the algorithm under the premise of guaranteeing the clustering effect. K E Y W O R D S fuzzy clustering, inhibitive factor, membership degree, rough set 1 INTRODUCTION There are many cluster analysis approaches in the data clustering field. From the view of the membership degrees of data sample, cluster analysis can be divided into two categories. One is the hard clustering analysis, the other is the soft clustering analysis, also known as fuzzy clustering analysis. 1 Hard clustering is a kind of strict division, which aims to divide every data sample into a specific cluster. Its division mechanism is very clear with only two membership degrees: 0 and 1, which means a sample can only belong to a certain class or not at all. This clustering method is too strict to deal with some data at the boundary, which could easily cause errors. Soft clustering is more tolerant for the division of data and divides them into different clusters according to their membership degree. The traditional fuzzy clustering method is sensitive to noise data, and the accuracy of clustering is often not good enough when dealing with complex data sets. Although some data objects are divided into a certain cluster, it is not obvious that they belong to that one. Rough set theory can deal with the fuzzy and uncertain problems. The idea of inhibitive factor comes from the suppressed fuzzy C-means clustering algorithm (S-FCM). 2 The essence of S-FCM is prizing the biggest membership and suppressing the others. By choosing the reasonable a parameter, S-FCM converges faster than FCM under the precondition of not decreasing clustering performance. In this article, the related work about fuzzy clustering algorithm based on rough set is overviewed in Section 2. In Section 3 the related concepts of rough set theory and fuzzy method are introduced. Section 4 designs a new calculation method of fuzzy membership degree. At the same time, an inhibitive factor is used to improve the convergence speed of the algorithm, and then a fuzzy clustering algorithm based on rough set and the inhibitive factor is proposed. The experimental results and analysis are given in Section 6. Section 6 gives the conclusion of this article.