Search

There are two main contributions in this article. One is that an extraction means of dominant frequencies is proposed for the first time. The footstep events (FEs) from diverse subjects are analyzed comparatively in frequency domain. Besides the extraction of dominant frequencies containing rich feature information is successfully accomplished after numerous experiments. The other is novel footstep features. Seven simple but effective features are developed and assessed based on dominant frequencies. A SVM is utilized as classifier, exactly identifying which person a FE belongs to. 92.41% precision, 91.3% recall and 91.85% ${F}_{1}$ on average are obtained in personal recognition experiment. Moreover, our seven features show a best performance in the comparison about our features and some features studied previously, even under various SNR. It is worth mentioning that our original signals are collected in noisy environment to approach real application scenarios, without any polishing such as filtering, amplifying. Good classification results could be acquired with poor signal, which is enough to demonstrate that our features are robust and preferable. Our human recognition scheme only involves a microphone to collect footstep sounds and easy classification method, with the characteristics of small calculation and low experimental cost. [ABSTRACT FROM AUTHOR]

E-commerce is the main means of commodity circulation in the future, and its development model needs to establish a product recommendation network for different customer groups. Under the unified mode of global market, accurately grasping the appearance requirements of customers’ products is the prerequisite for the development of e-commerce enterprises. Based on the improved 3D block matching algorithm, this study identified and analyzed the internationalized commodity images of e-commerce networks, and combined customer actual operations to conduct customer clustering to accurately grasp customer demand information, realized e-commerce customer segmentation, and laid the foundation for personalized recommendation. In addition, this paper constructed an e-commerce customer segmentation model based on improved three-dimensional block matching algorithm and performed performance analysis on the improved algorithm and system model of this study through experimental verification. The research shows that the algorithm and model of this study have certain practical effects and can provide theoretical reference for subsequent related research. [ABSTRACT FROM AUTHOR]

We reported in this paper the tooth-whitening effect by a direct-current cold atmospheric-pressure air plasma microjet (PMJ) and saline solution (0.9%). All teeth were randomly divided into three groups, treated for 20 min with an air blow and saline solution, a PMJ and saline solution, and 35% hydrogen peroxide gel, respectively. Compared with the other groups, the teeth treated with the PMJ and saline solution showed the best tooth-whitening effect. The microhardness of the tooth enamel measurement showed no apparent differences among the three groups. A minor enamel surface morphological change was observed via SEM but was considered acceptable. Singlet oxygen (^1\O2) and hydroxyl (^\bullet\OH) radicals were detected by electron spin resonance spectroscopy. Atomic oxygen (O) was observed in the optical emission spectra of the PMJ. ^1 \O2, ^\bullet\OH, and O were considered to be the key agents during the tooth-whitening process. This novel method of tooth whitening has the potential to revolutionize the clinical tooth-whitening procedure. [ABSTRACT FROM PUBLISHER]