The outstanding comprehensive mechanical properties of newly developed hybrid lattice structures make them useful in engineering applications for bearing multiple mechanical loads. Additive-manufacturing technologies ...
详细信息
Human activity recognition (HAR) is essential for understanding people's habits and behaviors, providing an important data source for precise marketing and research in psychology and sociology. Different approache...
详细信息
Human activity recognition (HAR) is essential for understanding people's habits and behaviors, providing an important data source for precise marketing and research in psychology and sociology. Different approaches have been proposed and applied to HAR. Data segmentation using a sliding window is a basic step during the HAR procedure, wherein the window length directly affects recognition performance. However, the window length is generally randomly selected without systematic study. In this study, we examined the impact of window length on smartphone sensor-based human motion and pose pattern recognition. With data collected from smartphone sensors, we tested a range of window lengths on five popular machine-learning methods: decision tree, support vector machine, K-nearest neighbor, Gaussian naive Bayesian, and adaptive boosting. From the results, we provide recommendations for choosing the appropriate window length. Results corroborate that the influence of window length on the recognition of motion modes is significant but largely limited to pose pattern recognition. For motion mode recognition, a window length between 2.5-3.5 s can provide an optimal tradeoff between recognition performance and speed. Adaptive boosting outperformed the other methods. For pose pattern recognition, 0.5 s was enough to obtain a satisfactory result. In addition, all of the tested methods performed well.
The natural control of robotic prosthetic hands with non-invasive techniques is still a challenge: myoelectric prostheses currently give some control capabilities;the application of pattern recognition techniques is p...
详细信息
ISBN:
(纸本)9781424492701
The natural control of robotic prosthetic hands with non-invasive techniques is still a challenge: myoelectric prostheses currently give some control capabilities;the application of pattern recognition techniques is promising and recently started to be applied in practice but still many questions are open in the field. In particular, the effects of clinical factors on movement classification accuracy and the capability to control myoelectric prosthetic hands are analyzed in very few studies. The effect of regularly using prostheses on movement classification accuracy has been previously studied, showing differences between users of myoelectric and cosmetic prostheses. In this paper we compare users of myoelectric and body-powered prostheses and intact subjects. 36 machine-learning methods are applied on 6 amputees and 40 intact subjects performing 40 movements. Then, statistical analyses are performed in order to highlight significant differences between the groups of subjects. The statistical analyses do not show significant differences between the two groups of amputees, while significant differences are obtained between amputees and intact subjects. These results constitute new information in the field and suggest new interpretations to previous hypotheses, thus adding precious information towards natural control of robotic prosthetic hands.
Gram-negative bacteria have five major subcellular localization sites: the cytoplasm, the periplasm, the inner membrane, the outer membrane, and the extracellular space. The subcellular location of a protein can provi...
详细信息
Gram-negative bacteria have five major subcellular localization sites: the cytoplasm, the periplasm, the inner membrane, the outer membrane, and the extracellular space. The subcellular location of a protein can provide valuable information about its function. With the rapid increase of sequenced genomic data, the need for an automated and accurate to predict subcellular localization becomes increasingly important. We present an approach to predict subcellular localization for Gram-negative bacteria. This method uses the support vector machines trained by multiple feature vectors based on n-peptide compositions. For a standard data set comprising 1443 proteins, the overall prediction accuracy reaches 89%, which, to the best of our knowledge, is the highest prediction rate ever reported. Our prediction is 14% higher than that of the recently developed multimodular PSORT-B. Because of its simplicity, this approach can be easily extended to other organisms and should be a useful tool for the high-throughput and large-scale analysis of proteomic and genomic data.
暂无评论