This paper proposes an importance weighted adversarial nets-based method for unsupervised domain adaptation, specific for partial domain adaptation where the target domain has less number of classes compared to the source domain. Previous domain adaptation methods generally assume the identical label spaces, such that reducing the distribution divergence leads to feasible knowledge transfer. However, such an assumption is no longer valid in a more realistic scenario that requires adaptation from a larger and more diverse source domain to a smaller target domain with less number of classes. This paper extends the adversarial nets-based domain adaptation and proposes a novel adversarial nets-based partial domain adaptation method to identify the source samples that are potentially from the outlier classes and, at the same time, reduce the shift of shared classes between domains.
The grasshopper optimization algorithm (GOA) is a metaheuristic algorithm that mathematically models and simulates the behavior of the grasshopper swarm. Based on its flexible, adaptive search system, the innovative algorithm has an excellent potential to resolve optimization problems. This paper introduces an enhanced GOA, which overcomes the deficiencies in convergence speed and precision of the initial GOA. The improved algorithm is named MOLGOA, which combines various optimization strategies. Firstly, a probabilistic mutation mechanism is introduced into the basic GOA, which makes full use of the strong searchability of Cauchy mutation and the diversity of genetic mutation. Then, the effective factors of grasshopper swarm are strengthened by an orthogonal learning mechanism to improve the convergence speed of the algorithm. Moreover, the application of probability in this paper greatly balances the advantages of each strategy and improves the comprehensive ability of the original GOA. Note that several representative benchmark functions are used to evaluate and validate the proposed MOLGOA. Experimental results demonstrate the superiority of MOLGOA over other well-known methods both on the unconstrained problems and constrained engineering design problems.
This paper presents a new vision-based method for real-time assessment of upper-body postures of a subject who is sitting in front of a desk studying or operating a computer. Unlike most existing vision-based methods that perform offline assessment from human skeletons extracted from RGB video or depth maps, the proposed method analyses directly single images captured by a webcam in front of the subject without the prone-to-error process of extracting the skeleton data from the images or depth maps. To this end, this paper proposes to assess postures by classifying them into predefined classes, without explicitly measuring the variables required for calculating risk scores. Each class of postures is associated with a configuration of the upper body, and an ergonomics risk score is assigned by following one of the scoring methods, e.g. Rapid Upper Limb Assessment (RULA). A data set of upper-body postures that cover the various scenarios when a subject is sitting in front of a desk as well as some extreme cases when the subject turns away from the desk is collected for evaluating the proposed method quantitatively. The proposed method achieved an on-average accuracy of 99.5% for binary classification (low-vs. high-risk postures), 88.2% for classification of 19 risk levels and 81.5% for classification of 30 risk levels on the data set, and the demo developed based on the method runs in real time on a regular computer. Keywords Posture assessment • Upper body • HOG • SVM • RULA 1 Introduction Posture refers to the arrangement of body segments/parts at a particular time [18], and it can be healthy (good) or harmful (poor). Poor posture increases the risk of work-related musculoskeletal disorders (WMSDs), such as carpal tunnel syndrome (CTS), back injury and back pain, and arthritis. WMSDs are associated with high costs to both employers and the whole society and are more severe than the average non-fatal injury or illness: nearly, one in every two Americans B Zewei Ding
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.