The P300 potential is a positive peak of an event- related potential (ERP) that happens at 300 ms after a stimulus. In this study, both offline and online stages were carried out in the experiment. The ...
详细信息
The P300 potential is a positive peak of an event- related potential (ERP) that happens at 300 ms after a stimulus. In this study, both offline and online stages were carried out in the experiment. The motivation of this paper is to compare two different P300 brain-computer interfaces (BCIs) which were evoked by random stimulus and non-random stimulus respectively. The offiine data demonstrated that the random stimulus induced a higher P300 amplitude and classification accuracy than the non-random stimulus. The offline data were used to train the Bayesian linear discriminate analysis (BLDA), which was used in offline experiment. The online results further proved that random stimulus P300 BCI yields better performance than non- random stimulus P300 BCI.
Workflow mining is a concept in early era, it analyzes the workflow log in the control flow dimensions, to mining the actual process model, but ignores relationships among executors in workflow, hence it fails to effe...
详细信息
ISBN:
(纸本)9781457713811
Workflow mining is a concept in early era, it analyzes the workflow log in the control flow dimensions, to mining the actual process model, but ignores relationships among executors in workflow, hence it fails to effectively excavate the workflow log to find the implicit structure. In this paper, the organizational dimensions of workflow log will be the main focuses to be researched. The paper introduces executor similarity metrics and grid clustering to demonstrate the methods of the organizational structure mining based on executor similarity and organization mining based on grid clustering. Both of them are effective to extract the actual organizational structure from the workflow logs.
The key link of constructing a virtual enterprise is to choose a cooperation partner who has the characteristics of sensitive, competitive and compatible. To solve the large scale partner selection under the environme...
详细信息
In order to solve the problem of high dimension in text classification, the paper proposes a method based on manifold learning and Bagging for text classification which imports manifold learning algorithm for dimensio...
详细信息
In order to solve the problem of high dimension in text classification, the paper proposes a method based on manifold learning and Bagging for text classification which imports manifold learning algorithm for dimension reduction. And Bagging algorithm is introduced when training classifier to improve the accuracy of text classification. Experimental results demonstrate that effect of text dimension reduction by manifold learning algorithm in the pretreatment of text classification is better, and the performance of the classifier has improved significantly.
The day time nap sleep has the significant prophylactic function to our health and working efficiency. In this study, the prediction of sleep level for day time short nap was investigated. The ultimate purpose was to ...
详细信息
The day time nap sleep has the significant prophylactic function to our health and working efficiency. In this study, the prediction of sleep level for day time short nap was investigated. The ultimate purpose was to develop the automatic analysis technique for nap sleep interpretation. Firstly, the conditional probabilities of sleep stage awake, stage 1 and stage 2 were calculated for the consecutive data segments based on a set of parameters. Secondly, the sleep level of next data segment was predicted according to the obtained conditional probabilities. The prediction of sleep level reflected the future sleep tendency and was helpful for automatic nap sleep interpretation.
This paper investigates the problem of non-fragile static output feedback control (SOF) design for discrete-time linear systems. Interval type of additive gain variations to reflect imprecision in controller implement...
详细信息
This paper investigates the problem of non-fragile static output feedback control (SOF) design for discrete-time linear systems. Interval type of additive gain variations to reflect imprecision in controller implementation is considered. The non-fragile SOF controller design is firstly formulated as a robust convex problem. Then a deterministic algorithm and a randomized one are proposed to solve the obtained robust convex problem. These two algorithms complements each other. The deterministic algorithm is suitable for systems with low dimensions, while the randomized one is applicable for systems with high dimensions. In addition, the randomized algorithm can alleviate the conservatism of the deterministic one. Two examples are given to show the effectiveness of the proposed method.
Traditional Modbus/TCP server-side protocol includes in many inappropriate blocking I/O operations. These operations frequently lead to receiving thread blockage in the communication. To solve this problem, some impro...
详细信息
Currently, the earlier detection, diagnosis and treatment to breast cancer still mainly depend on physicians' experience and knowledge. Case-Based Reasoning(CBR) mimics oncologists' real thinking process and t...
详细信息
ISBN:
(纸本)9783037851555
Currently, the earlier detection, diagnosis and treatment to breast cancer still mainly depend on physicians' experience and knowledge. Case-Based Reasoning(CBR) mimics oncologists' real thinking process and therefore is appropriate to the diagnosis decision making. In CBR, weight derivation as a key step is commonly conducted by expert score approaches using Delphi method. The accuracy of case matching largely changes with the selection and experience of experts. In this paper, information entropy for weight determination is introduced into the CBR. We conduct experimental studies to compare the performance of Delphi method and information entropy. The results suggest that: generally, information entropy is a better approach to weight derivation.
Security assessment of Thermal Power Plants (TPPs) is one of the important means to guarantee the safety of production in thermal power production enterprises. Essentially, the evaluation of power plant systems relies...
详细信息
Parameters of ball mill load (ML) affects production capacity and energy consumption of the grinding process, which have stronger correlation with shell vibration spectrum. A novel spectral features extraction and sel...
详细信息
暂无评论