The functioning of flight test sensors is crucial for aviation safety, but previous methods often overlooked the impact of data imbalance on model performance while exploring anomalies in aviation data. Imbalances in ...
详细信息
The functioning of flight test sensors is crucial for aviation safety, but previous methods often overlooked the impact of data imbalance on model performance while exploring anomalies in aviation data. Imbalances in aviation time-series data can lead to the following issues: 1) Varying sizes of feature spaces lead to the majority class overshadowing the minority class;2) small interclass differences in the model result in a bias toward predicting the majority class;and 3) imbalanced algorithms causes the model to lack learning of general features. To alleviate these problems, this article proposes the imbalanced flight test sensor temporal data anomaly detection (IFAD) model. First, a dual-branch network is designed where one branch is trained on original data distribution for general feature learning, and the other on resampled data to enhance learning of anomalous aviation data features. Second, a normalization module is introduced to standardize feature and weight vectors for a quantifiable decision boundary, along with an angle constraint for greater class differentiation. Finally, an adaptive reweighting algorithm (cosine-variance-aware loss reweighting algorithm) is implemented to balance the loss between different categories using cosine sample variance. Extensive ablation studies demonstrate that each proposed module enhances model performance. The IFAD model, when benchmarked against the baseline network, notably excels in the flights dataset, achieving improvements in accuracy, recall, and F1 score by 18.93%, 27.16%, and 12.43%, respectively, affirming its efficacy and superiority in detecting anomalies in flight test data.
We present a forward-backward-based algorithm to minimize a sum of a differentiable function and a nonsmooth function, both being possibly nonconvex. The main contribution of this work is to consider the challenging c...
详细信息
We present a forward-backward-based algorithm to minimize a sum of a differentiable function and a nonsmooth function, both being possibly nonconvex. The main contribution of this work is to consider the challenging case where the nonsmooth function corresponds to a sum of nonconvex functions, resulting from composition between a strictly increasing, concave, differentiable function and a convex nonsmooth function. The proposed variable metric composite function forward-backward (C2FB) algorithm circumvents the explicit, and often challenging, computation of the proximity operator of the composite functions through a majorize-minimize approach. Precisely, each composite function is majorized using a linear approximation of the differentiable function, which allows one to apply the proximity step only to the sum of the nonsmooth functions. We prove the convergence of the algorithm iterates to a critical point of the objective function leveraging the Kurdyka-Lojasiewicz inequality. The convergence is guaranteed even if the proximity operators are computed inexactly, considering relative errors. We show that the proposed approach is a generalization of reweighting methods, with convergence guarantees. In particular, applied to the log-sum function, our algorithm reduces to a generalized version of the celebrated reweighted l(1) method. Finally, we show through simulations on an image processing problem that the proposed C2FB algorithm necessitates fewer iterations to converge and leads to better critical points compared with traditional reweighting methods and classic forward-backward algorithms.
An exhaustive description of the molecular recognition mechanism between a ligand and its biological target is of great value because it provides the opportunity for an exogenous control of the related process. Very o...
详细信息
An exhaustive description of the molecular recognition mechanism between a ligand and its biological target is of great value because it provides the opportunity for an exogenous control of the related process. Very often this aim can be pursued using high resolution structures of the complex in combination with inexpensive computational protocols such as docking algorithms. Unfortunately, in many other cases a number of factors, like protein flexibility or solvent effects, increase the degree of complexity of ligand/protein interaction and these standard techniques are no longer sufficient to describe the binding event. We have experienced and tested these limits in the present study in which we have developed and revealed the mechanism of binding of a new series of potent inhibitors of Adenosine Deaminase. We have first performed a large number of docking calculations, which unfortunately failed to yield reliable results due to the dynamical character of the enzyme and the complex role of the solvent. Thus, we have stepped up the computational strategy using a protocol based on metadynamics. Our approach has allowed dealing with protein motion and solvation during ligand binding and finally identifying the lowest energy binding modes of the most potent compound of the series, 4-decyl-pyrazolo[1,5-a]pyrimidin-7-one.
暂无评论