Papers by Keyword: Incomplete Data

Abstract: Spectrum prediction is a technology to estimate the channel status by mining and using the correlation of the spectrum data. Using a reliable prediction scheme, the performance of opportunity spectrum access can be more effective. However, the traditional study on the spectrum prediction methods only use the correlation of the historical data in time domain, and on the basis of the spectrum historical data is complete. In reality, the historical data are often incomplete. The reality calls for a deeper understanding of the correlation of current spectrum data. In this paper, we present a correlation study, with data collected by measure both on the time domain and spectrum domain. Main findings include that the channel status information has correlation not only in the time domain, but also in the spectrum domain. We then exploit such time and spectrum correlation to develop a matrix completion based spectrum prediction scheme under the incomplete data that can predict channel availability based on past observations with considerable accuracy.

Abstract: Partially missing data sets are a prevailing problem in pattern recognition. In this paper, the problem of clustering incomplete data sets is considered, and missing attribute values are imputed by the centers of corresponding nearest-neighbor intervals. Firstly, the algorithm estimates the nearest-neighbor intervals of missing attribute values by using the attribute distribution information of the data sets sufficiently. Secondly, the missing attribute values are imputed by the center of the intervals so as to clustering incomplete data sets. The proposed algorithm introduces the nearest neighbor information into incomplete data clustering, and the comparisons of the experimental results for two UCI data sets demonstrate the capability of the proposed algorithm.

Abstract: With the development of the Internet of Things, collected data from the Internet of Things include more and more incomplete data because of the network fault or the sensing terminal breakdown. A lot of incomplete data do harm to the IoT application and decision. For filling the incomplete data in IoT effectively, this paper presents a new method based on power graph, which first uses the graph power to abstract the important attributes of the objects. Then the proposed method fills the important attributes using improved method based on similarity. Experimental results show the effectiveness of our method, especially for filling the massive incomplete data in IoT.

Abstract: The pressure information collection of bridge buildings is important to monitor the healthy status of the bridge buildings. For the defects of traditional pressure information collection system, the paper designs a system for collecting the pressure information of bridges based on the IoT. To meet the demand of real time, the system sends the pressure information collected by pressure sensors to the data processing center through the CAN bus. Before storing the pressure information into the database, the system will fill the incomplete pressure information to provide the bridge experts with useful information. Simulation experiments show the system can collect the pressure information of bridges in real time and meet the demand of bridge experts.

Abstract: This paper outlines a new technique to address the paucity of data in determining fatigue life and performance based on reliability concepts. Two new randomized models are presented for estimating the safe life and pS-N curve, by using the standard procedure for statistical analysis and dealing with small sample numbers of incomplete data. The confidence level formulations for the safe and p-S-N curve are also given. The concepts are then applied for the determination of the safe life and p-S-N curve. Two sets of fatigue tests for the safe life and p-S-N curve are conducted to validate the presented method, demonstrating the practical use of the proposed technique.

Abstract: Many data in practical projects belong to incomplete data distribution. An approach for treat the data is investigated from chi-square optimization to measure the parameters. The statistical reference is also performed in the measuring process. Availability has been indicated by an example.

Abstract: In the field of experimental mechanics, there exist some circumstances when only data at the boundary can be obtained while the internal data are unavailable, or when some data are missed due to shadow, illumination saturation and other reasons. Thus it would be helpful if a reasonable estimation of the unavailable or missed data can be obtained. In this study, an algorithm is developed to reconstruct the missed data from the existing ones by generating a series of equations about the missed data and solving for an optimal solution using least-squares approach. Results based on both simulation data and real incomplete experimental data obtained by shearography and fringe projection show the usefulness and potential of the algorithm for experimental mechanics applications.