Search

This article introduces multiangular imagery into physics-based bathymetry in order to compensate for the shortage of bathymetric spectral bands caused by the low spectral resolution of current high-spatial-resolution satellite multispectral imagery. The focus is to propose a selective bathymetric retrieval method to eliminate the negative effect of nonoptimal image data on depth retrieval in multiangular imagery-based bathymetry. The elimination of the negative effect is implemented by excluding nonoptimal pixels in every individual image from bathymetric retrieval. An empirical criterion is designed for the determination of nonoptimal pixels. The proposed method can use multiangular image data selectively, avoiding situations where bathymetric retrieval results from the whole multiangular imagery are poorer than that from a part of the individual images. The method was tested in two typical areas within the Xisha (Paracel) Islands of the South China Sea using two-angle WorldView-2 multispectral images. The test showed that the derived depths of the method (i.e., depths derived from the selective image data) provided a better fit to the validation depths than those from the entirety of both images. The underestimation of depths derived from the entirety of both images was also improved to some extent.

The log-ratio method (LRM) proposed by Stumpf et al. has been widely used to map bathymetry from multispectral imagery for oligotrophic waters, while the selection criteria of bands for the LRM have been subject to tradeoffs between maximum detectable depth and sensitivity. In this article, we first applied a method for global sensitivity analysis to a semianalytical forward model of optically shallow waters with the WorldView-2 band-set. The results show that the sensitive wavelength band in water-leaving reflectance for water depth varies from the longer wavelength band to the shorter wavelength band with increasing water depth. Then, we developed an adaptive blended algorithm approach (ABAA) to seamlessly map bathymetry from the shallower region to the deeper region. The LRM with different band combinations was selected for the sub-algorithms of the ABAA. The subalgorithms and depth range used for each subalgorithm of the ABAA were automatically determined by the proposed applicable depth range analysis that considers logarithmic regression for the LRM. The ABAA was applied to WorldView-2 and Landsat-8 imagery of the Xisha Qundao. When the in situ bathymetry data are available, compared with the LRM with the blue and green bands, the ABAA significantly improves the accuracy of the estimated depth, especially for waters shallower than 6 m (root–mean- square error (RMSE) = 0.31 to 0.94 m for WorldView-2 data, RMSE= 0.25 to 1.42 m for Landsat-8 data). When the in situ bathymetry data are absent, the ABAA performs better than the LRM with a single band ratio and an optimization-based method overall.

Sequential event prediction is a well-studied area and has been widely used in proactive management, recommender systems and healthcare. One major assumption of the existing sequential event prediction methods is that similar event sequence patterns in the historical record will repeat themselves, enabling us to predict future events. However, in reality, the assumption becomes less convincing when we are trying to predict rare or unique sequences. Furthermore, the representation of the event may be complex with hierarchical structures. In this paper, we aim to solve this issue by taking advantage of the multi-level or hierarchical representation of these rare events. We proposed to build a sequential Encoder-Decoder framework to predict the event sequences. More specifically, in the encoding layer, we built a hierarchical embedding representation for the events. In the decoding layer, we first predict the high-level events and the low-level events are generated according to a hierarchical graphical structure. We propose to link the encoding decoding layers with the temporal models for future event prediction. In this article, we further discussed applying the proposed model into the failure event prediction according to the aviation accident reports and have shown improved accuracy and model interpretability.

The workload of air traffic controllers (ATCs) is increasing due to the growing air traffic. Early alarms of loss of separation (LoS) events between aircraft are critical for ATCs to coordinate intensive traffic safely. The authors studied the time series of traffic densities and numbers of turning aircraft in a given sky section as early indicators of pending LoS. Simulator experiment produced data for comparing the prediction accuracies of the logistic regression models generated from the time series of traffic densities and numbers of turning aircraft, and combinations of these two. We studied different sections of the time series to examine the possibility of early detection and found that 1) the regression model based on the traffic density time series is more accurate than the model using the numbers of turning aircraft; 2) properly combining sections of the time series could produce models that achieve earlier predictions without losing accuracy.

Comprehending how ground incidents and accidents arise and propagate during air traffic control is vital to both the efficiency and safety of air transportation systems. Historical data about airport operational events capture some processes about how improper collaboration among air traffic controllers and pilots result in incidents, accidents, and delays, but could hardly cover all possible air traffic control failures in various environmental conditions. The computational simulation could use historical data to identify repetitive aircraft movement behaviors and air traffic control processes shared in multiple air traffic control sessions and create stochastic models that represent the probabilities of the occurrence of certain aircrafts movements and control events under various contexts. This paper synthesizes four scenarios of aircraft operations around ramp areas during air traffic peak time for supporting the development of a quantitative spatiotemporal simulation that can help predict air traffic control risks based on historical data.

Chromophoric dissolved organic matter (CDOM) retrieval remains to be a challenging task in water color remote sensing research due to its highly spatial and temporal variability. In this paper, we present a novel CDOM retrieval algorithm that takes advantage of the sparse learning, which can simultaneously perform feature selection and parameter estimation. More specifically, by incorporating the band interaction terms into the original spectral matrix and let it be the basis matrix, then the inversion task can be converted to a classical sparse regression problem, namely LASSO, which can be efficiently solved by the coordinate descend algorithm. Experimental results conducted on both simulated and in-situ datasets have demonstrated the efficiency and superiority of the proposed method over some conventional empirical algorithms.

Imbalanced data widely exist in many high-impact applications. An example is in air traffic control, where among all three types of accident causes, historical accident reports with ‘personnel issues’ are much more than the other two types (‘aircraft issues’ and ‘environmental issues’) combined. Thus, the resulting data set of accident reports is highly imbalanced. On the other hand, this data set can be naturally modeled as a network, with each node representing an accident report, and each edge indicating the similarity of a pair of accident reports. Up until now, most existing work on imbalanced data analysis focused on the classification setting, and very little is devoted to learning the node representations for imbalanced networks. To bridge this gap, in this paper, we first propose Vertex-Diminished Random Walk (VDRW) for imbalanced network analysis. It is significantly different from the existing Vertex Reinforced Random Walk by discouraging the random particle to return to the nodes that have already been visited. This design is particularly suitable for imbalanced networks as the random particle is more likely to visit the nodes from the same class, which is a desired property for learning node representations. Furthermore, based on VDRW, we propose a semi-supervised network representation learning framework named ImVerde for imbalanced networks, where context sampling uses VDRW and the limited label information to create node-context pairs, and balanced-batch sampling adopts a simple under-sampling method to balance these pairs from different classes. Experimental results demonstrate that ImVerde based on VDRW outperforms state-of-the-art algorithms for learning network representations from imbalanced data.

To ensure the audio system has stronger thermal environment adaptability under the harsh environment of heat load and thermal load generate by itself, carry out the thermal simulation analysis research. The thermal simulation analysis model is established by the finite element analysis method. In order to get the audio system temperature distribution and the temperature of components whose temperature rise obviously, complete the thermal simulation calculation. The simulation results show that, the highest temperature is 97 °C of the TFT circuit board, the highest temperature is 92 C of the main circuit board and the highest temperature is 72 C of the AIR circuit board, as the weak positions of the audio system under thermal environment, need to further optimize thermal design, and puts forward suggestions for improvement.

To ensure the audio system has stronger vibrational environment adaptability under the harsh environment of vibrational load, carry out the modal analysis and random vibrational simulation analysis research. The modal analysis and random vibrational simulation analysis model are established by the finite element analysis method. In order to get inherent mode, stress response and displacement response of the audio system, complete the vibrational simulation calculation. The simulation results show that, the first 6 order natural frequencies of the audio system are between 133Hz and 371 Hz. Under the action of random load, the maximum stress is 36MPa, the maximum displacement is 0.19mm, which satisfies the stiffness and strength requirements, and has stronger vibrational environment adaptability.

In order to scientifically and quantitatively allocate the reliability index of a certain polymer processing rheometer, traditional grading method and modified grading method is proposed to establish the reliability of the rheometer allocation model. Based on each subsystem reliability allocation weight and the machine reliability allocation model, each component modified reliability allocation weight and each subsystem reliability allocation model, quantitatively assessment of each subsystem and each component reliability level. At the same time, compared with the result evaluated by traditional grading method, comparison results show that, modified grading method allocation result with the traditional grading method allocation result is very close, because of the modified grading method with the failure rate of similar products as the basis score of individual component reliability allocation, so the modified grading method increase the impact of similar products on the reliability allocation weight, and it has more engineering achievable.

The use of Wireless Sensor Network (WSN) for the prevention of forest fires can greatly reduce the human and financial input, it also can avoid the disadvantage without of manual detection and judge the forest fires all day. The forest environment is so complex that it needs a lot of sensor nodes. The key point to the sensor is the low power and the distribution. So the choice of network protocol is very import. In this paper, we propose an improved protocol BEEM based on HEED routing protocol, BEEM protocol pays more attention to the coverage of the network, so BEEM protocol can prolong the network lifetime, is suitable for forest.

In order to evaluate the reliability of a certain polymer processing rheometer accurately and effectively, and solve the problem of reliability prediction error is bigger which due to ignoring the man-machine interaction existing in the process of reliability prediction, we put forward building a reliability prediction model by using the combination of cognitive load evaluation technique and grading method. Finally, calculated the reliability level based on the corrected failure rate of each component and the reliability relationship of individual components with polymer processing rheometer. The prediction results showed that MTBF of the overall polymer processing rheometer was 2610h, exceeding 2000h which was stipulated in the specification. At the same time, by analyzing the prediction result, it was concluded that main measure and control module was the weak module of the whole polymer processing rheometer, and bracket assembly of main measure and control module and single screw capillary module was the weak component.

In this paper, a new formulation at the small time scale is proposed for multi-scale fatigue crack growth analysis and an in-situ SEM testing methodology is used to verify the basic hypotheses of the model. 12Very high resolution imaging analysis is performed to quantify the crack tip deformation behaviour and crack growth kinetics. In the in-situ SEM testing, the crack closure phenomenon is observed during the crack growth process. It is also observed that crack growth is not uniformly distributed within a loading cycle and only happens during a small portion of loading path. Based on the experimental measurement, the new prognosis model is developed and shows a good agreement with coupon level fatigue crack growth testing data under both constant loading and simple variable loading.