Search

Estimation of hand kinematics from surface electromyographic (sEMG) signals provides a non-invasive human-machine interface. This approach is usually subject-specific, so that the training on one individual does not generalise to different subjects. In this paper, we propose a method based on Bidirectional Encoder Representation from Transformers (BERT) structure to predict the movement of hands from the root mean square (RMS) feature of the sEMG signal following $\mu $ -law normalization. The method was tested for within-subject and cross-subject conditions. We trained the model with two hard sample mining methods, Gradient Harmonizing Mechanism (GHM) and Online Hard Sample Mining (OHEM). The proposed method was compared with classic approaches, including long short-term memory (LSTM) and Temporal Convolutional Network (TCN) as well as a recent method called Long Exposure Convolutional Memory Network (LE-ConvMN). Correlation coefficient (CC), normalized root mean square error (NRMSE) and time costs were used as performance metrics. Our method (sBERT-OHEM) achieved state-of-the-art performance in cross-subject evaluation as well as high performance in subject-specific tests on the Ninapro dataset. The above tests are based on the same randomly selected 10 subjects. Generally, in the cross-subject situation, with the increasing of the subjects’ number, it unavoidably leads to the decline of the performance. While the performance of our method on 38 subjects was significantly higher than the other methods on 10 subjects in cross-subject conditions, which further verified the advantage of our methods. [ABSTRACT FROM AUTHOR]

Recurrent neural networks (RNNs) are widely used to process sequence-related tasks such as natural language processing. Edge cloud computing systems are in an asymmetric structure, where task managers allocate tasks to the asymmetric edge and cloud computing systems based on computation requirements. In such a computing system, cloud servers have no energy limitations, since they have unlimited energy resources. Edge computing systems, however, are resource-constrained, and the energy consumption is thus expensive, which requires an energy-efficient method for RNN job processing. In this paper, we propose a low-overhead, energy-aware runtime manager to process tasks in edge cloud computing. The RNN task latency is defined as the quality of service (QoS) requirement. Based on the QoS requirements, the runtime manager dynamically assigns RNN inference tasks to edge and cloud computing systems and performs energy optimization on edge systems using dynamic voltage and frequency scaling (DVFS) techniques. Experimental results on a real edge cloud system indicate that in edge systems, our method can reduce the energy up to 45% compared with the state-of-the-art approach. [ABSTRACT FROM AUTHOR]

To link to full-text access for this article, visit this link: http://dx.doi.org/10.1016/j.jss.2007.02.028 Byline: Hai Zhuge (a)(b)(d), Weiyu Guo (a)(b)(c) Keywords: Knowledge grid; Knowledge service; Knowledge flow network; Reputation; Market; Auction; Bargain Abstract: A knowledge service consists of systematic knowledge and the mechanism of using knowledge to perform a task. The supply of knowledge services forms a knowledge service layer over the knowledge flow network formed by free knowledge sharing. To stimulate the supply of knowledge services, this paper proposes a virtual knowledge service market by establishing reward and reputation mechanisms. Simulations demonstrate that a team with the market mechanism performs better than those without it. The virtual knowledge service market provides an experimental platform for exploring the rules of knowledge service such as the impact of individual behavior on states of individual and team as well as the change of the states. Author Affiliation: (a) China Knowledge Grid Research Group, Key Lab of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China (b) Graduate School of Chinese Academy of Sciences, Beijing, China (c) Shandong Institute of Light Industry, Jinan, Shandong, China (d) Hunan University, Changsha, Hunan, China Article History: Received 9 January 2007; Revised 11 February 2007; Accepted 12 February 2007 Article Note: (footnote) [star] This work was supported by National Basic Research Program of China (973 Project No. 2003CB317001), International Cooperation Project of MOST of China, the EU 6th Framework Project GREDIA (IST-FP6-034363), and the National Science Foundation of China (No. 60503047).

A casual inspection of a graph of volatility indexes indicates that volatility has undergone infrequent, but significant, shifts in its average level. Evidence collected from three distinct periods including pre-1992, 1992-1997, and post-1997 is presented which shows that the mean volatility, as well as its standard deviation, was lowest during 1992-1997.

Since continuous motion control can provide a more natural, fast and accurate man–machine interface than that of discrete motion control, it has been widely used in human–robot cooperation (HRC). Among various biological signals, the surface electromyogram (sEMG)—the signal of actions potential superimposed on the surface of the skin containing the temporal and spatial information—is one of the best signals with which to extract human motion intentions. However, most of the current sEMG control methods can only perform discrete motion estimation, and thus fail to meet the requirements of continuous motion estimation. In this paper, we propose a novel method that applies a temporal convolutional network (TCN) to sEMG-based continuous estimation. After analyzing the relationship between the convolutional kernel's size and the lengths of atomic segments (defined in this paper), we propose a large-scale temporal convolutional network (LS-TCN) to overcome the TCN's problem: that it is difficult to fully extract the sEMG's temporal features. When applying our proposed LS-TCN with a convolutional kernel size of 1 × 31 to continuously estimate the angles of the 10 main joints of fingers (based on the public dataset Ninapro), it can achieve a precision rate of 71.6%. Compared with TCN (kernel size of 1 × 3), LS-TCN (kernel size of 1 × 31) improves the precision rate by 6.6%. [ABSTRACT FROM AUTHOR]

The narrow therapeutic time window and risk of intracranial hemorrhage largely restrict the clinical application of thrombolysis in acute ischemic stroke. Adjunctive treatments added to rt-PA may be beneficial to improve the capacity of neural cell to withstand ischemia, and to reduce the hemorrhage risk as well. This review aims to evaluate the neuroprotective effects of adjunctive treatments in combination with thrombolytic therapy for acute ischemic stroke. Relevant studies were searched in the PubMed, Web of Science and EMBASE database. In this review, we first interpret the potential role of adjunctive treatments to thrombolytic therapy in acute ischemic stroke. Furthermore, we summarize the current clinical evidence for the combination of intravenous recombinant tissue plasminogen activator and various adjunctive therapies in acute ischemic stroke, either pharmacological or non-pharmacological therapy, and discuss the mechanisms of some promising treatments, including uric acid, fingolimod, minocycline, remote ischemic conditioning, hypothermia and transcranial laser therapy. Even though fingolimod, minocycline, hypothermia and remote ischemic conditioning have yielded promising results, they still need to be rigorously investigated in further clinical trials. Further trials should also focus on neuroprotective approach with pleiotropic effects or combined agents with multiple protective mechanisms. [ABSTRACT FROM AUTHOR]

Deep Neural Networks (DNNs) have powerful learning abilities on high-rank and non-linear features, and thus have been applied to various fields, exhibiting higher discrimination performance than conventional methods. However, their applications in enterprise credit rating tasks are rare, as most DNNs employ the "end-to-end" learning paradigm, producing high-rank representations of objects or predictive results without any explanations. This "black box" approach makes it difficult for users in the financial industry to understand how these predictive results are generated, or what correlations exist with the raw inputs, leading to a lack of trust to the predictions. To address this issue, this paper proposes a novel network to explicitly model the enterprise credit rating problem using DNNs and attention mechanisms, allowing for explainable enterprise credit ratings. Experiments conducted on real-world enterprise datasets show that the proposed approach achieves higher performance than conventional methods, while also providing insights into individual rating results and the reliability of model training. The code is provided on. [ABSTRACT FROM AUTHOR]

Pairwise learning is a vital technique for personalized ranking with implicit feedback. Given the assumption that each user is more interested in items which have been previously selected by the user than the remaining ones, pairwise learning algorithms can well learn users’ preference, from not only the observed user feedbacks but also the underlying interactions between users and items. However, a mass of training instances are randomly derived according to such assumption, which makes the learning procedure often converge slowly and even result in poor predictive models. In addition, the cold start problem often perplexes pairwise learning methods, since most of traditional methods in personalized ranking only take explicit ratings or implicit feedbacks into consideration. For dealing with the above issues, this work proposes a novel personalized ranking model which incorporates implicit feedback with content information by making use of Factorization Machines. For efficiently estimating the parameters of the proposed model, we develop an adaptive sampler to draw informative training instances based on content information of users and items. The experimental results show that our adaptive item sampler indeed can speed up our model, and our model outperforms advanced methods in personalized ranking. [ABSTRACT FROM AUTHOR]

A knowledge flow is invisible but it plays an important role in ordering knowledge exchange when working in a team. It can help achieve effective team knowledge management by modeling, optimizing, monitoring, and controlling the operation of knowledge flow processes. This paper proposes the notion of knowledge energy as the driving force behind the formation of an autonomous knowledge flow network, and explores the underlying principles. Knowing these principles helps teams and the support systems improve cooperation by monitoring the knowledge energy of nodes, by evaluating and adjusting knowledge flows, and by adopting appropriate strategies. A knowledge flow network management mechanism can help improve the efficiency of knowledge-intensive distributed teamwork. Copyright © 2006 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

We use a simultaneous equation model which treats firm value, investments and management ownership as endogenous to the firm. Our results show a feedback relation between corporate value and management ownership, i.e., corporate value is positively impacted by management ownership, which in turn is positively impacted by corporate value. Corporate value also affects investments made by the firm. We also find that the effect of the main bank on corporate value is positive but only up to a certain point; then, it turns negative. Supporting the argument that keiretsu firms have lower agency cost, we find that firms belonging to a keiretsu have higher valuations during the sample period. Finally, we find that management ownership increases as the ownership of the main bank, ownership of institutional holders and cross-holdings decreases, suggesting a substitution effect among these monitoring forces. Our results indicate that ignoring the web of these relationships leads to incorrect inferences. [ABSTRACT FROM AUTHOR]

The employment of surface electromyographic (sEMG) signals in the estimation of hand kinematics represents a promising non-invasive methodology for the advancement of human-machine interfaces. However, the limitations of existing subject-specific methods are obvious as they confine the application to individual models that are custom-tailored for specific subjects, thereby reducing the potential for broader applicability. In addition, current cross-subject methods are challenged in their ability to simultaneously cater to the needs of both new and existing users effectively. To overcome these challenges, we propose the Cross-Subject Lifelong Network (CSLN). CSLN incorporates a novel lifelong learning approach, maintaining the patterns of sEMG signals across a varied user population and across different temporal scales. Our method enhances the generalization of acquired patterns, making it applicable to various individuals and temporal contexts. Our experimental investigations, encompassing both joint and sequential training approaches, demonstrate that the CSLN model not only attains enhanced performance in cross-subject scenarios but also effectively addresses the issue of catastrophic forgetting, thereby augmenting training efficacy.