Newly deployed trains have massive normal data and scarce faulty data for training, which limits the diagnosis accuracy with class imbalance problem of small samples. Considering that there are a lot unutilized information hidden in the abundant unlabeled monitoring data, this paper proposes a novel method named manifold-contrastive broad learning system, which utilizes the online updating approach for dealing with the class imbalance problem of small samples. This method constructs a novel one-class broad-learning classifier based on an inherency-guided comparison mechanism, which can classify and annotate unlabeled data online. This classifier employs contrastive manifold matrices to maintain the inherent structures, which is not affected to the overfitting caused by imbalanced samples. Secondly, inspired by the active learning, this classifier proposes the minimum-error strategy to annotate the samples by classifying the modes, which solves the problem of insufficient training data. Thirdly, this method applies an incremental learning strategy that continuously absorbs the newly annotated data to update the model online, which improves the model accuracy under the data imbalanced condition. Finally, the feasibility and effectiveness of the proposed method are verified by wheelset bearing data collected from a test rig of a Chinese rolling stock company.

MOTIVATION: Cyclization is a common strategy to enhance the therapeutic potential of peptides. Many cyclic peptide drugs have been approved for clinical use, in which the disulfide-driven cyclic peptide is one of the most prevalent categories. Molecular docking is a powerful computational method to predict the binding modes of molecules. For protein-cyclic peptide docking, a big challenge is considering the flexibility of peptides with conformers constrained by cyclization. RESULTS: Integrating our efficient peptide 3D conformation sampling algorithm MODPEP2.0 and knowledge-based scoring function ITScorePP, we have proposed an extended version of our hierarchical peptide docking algorithm, named HPEPDOCK2.0, to predict the binding modes of the peptide cyclized through a disulfide against a protein. Our HPEPDOCK2.0 approach was extensively evaluated on diverse test sets and compared with the state-of-the-art cyclic peptide docking program AutoDock CrankPep (ADCP). On a benchmark dataset of 18 cyclic peptide-protein complexes, HPEPDOCK2.0 obtained a native contact fraction of above 0.5 for 61% of the cases when the top prediction was considered, compared with 39% for ADCP. On a larger test set of 25 cyclic peptide-protein complexes, HPEPDOCK2.0 yielded a success rate of 44% for the top prediction, compared with 20% for ADCP. In addition, HPEPDOCK2.0 was also validated on two other test sets of 10 and 11 complexes with apo and predicted receptor structures, respectively. HPEPDOCK2.0 is computationally efficient and the average running time for docking a cyclic peptide is about 34 min on a single CPU core, compared with 496 min for ADCP. HPEPDOCK2.0 will facilitate the study of the interaction between cyclic peptides and proteins and the development of therapeutic cyclic peptide drugs. AVAILABILITY AND IMPLEMENTATION: http://huanglab.phys.hust.edu.cn/hpepdock/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

The successful deployment of artificial intelligence (AI) in many domains from healthcare to hiring requires their responsible use, particularly in model explanations and privacy. Explainable artificial intelligence (XAI) provides more information to help users to understand model decisions, yet this additional knowledge exposes additional risks for privacy attacks. Hence, providing explanation harms privacy. We study this risk for image-based model inversion attacks and identified several attack architectures with increasing performance to reconstruct private image data from model explanations. We have developed several multi-modal transposed CNN architectures that achieve significantly higher inversion performance than using the target model prediction only. These XAI-aware inversion models were designed to exploit the spatial knowledge in image explanations. To understand which explanations have higher privacy risk, we analyzed how various explanation types and factors influence inversion performance. In spite of some models not providing explanations, we further demonstrate increased inversion performance even for non-explainable target models by exploiting explanations of surrogate models through attention transfer. This method first inverts an explanation from the target prediction, then reconstructs the target image. These threats highlight the urgent and significant privacy risks of explanations and calls attention for new privacy preservation techniques that balance the dual-requirement for AI explainability and privacy.

The classification of binary [n,k,d] codes withdgess2k-1 and without zero coordinates is reduced to the classification of binary [(2k-1)c(k,s,t)+t,k,d] code forn=(2k-1)s+t,sges 1 and 1 lestles 2k-2, wherec(k,s,t) les min{s,t} is a function ofk,s, andt. Binary [15s+t, 4] optimal self-orthogonal codes are characterized by systems of linear equations. Based on these two results, the complete classification of [15s+t,4] optimal self-orthogonal codes fortisin {1,2,6,7,8,9,13,14} andsges 1 is obtained, and the generator matrices and weight polynomials of these 4-dimensional optimal self-orthogonal codes are also given.

This paper proposes an improved fine granular scalable (FGS) coding method with interlayer prediction. There are two important aspects to improving FGS coding efficiency. One is a low bit-rate video coding method and the other is interlayer prediction with enhancement layer reference at base-layer coding. The whole scalable coding performance with the proposed method is greatly enhanced over a wide bandwidth. New spatial and temporal prediction methods are investigated in order to increase FGS base-layer low bit-rate coding efficiency. There are nine kinds of spatial prediction modes for intra coding to exploit the pixels' spatial correlation, including DC and eight directional predictions, and multiple model-based motion prediction is utilized to predict a large irregular motion for inter coding, including a 6-parameter affine model. The reference for motion compensation is adaptively selected from base layer or enhancement layer according to their prediction error. The references are reconstructed at two layers. The references for prediction and reconstruction can be different in order to decrease drifting error due to bit-stream truncation. The coding efficiency of our base layer coding can be comparable with that of latest draft H.26L and holds a compelling improvement compared to MPEG-4. With our proposed scalable coding scheme, the whole FGS coding efficiency can be improved by about 2.0 dB at low bit-rate and 3.0-4.0 dB at medium or high bit-rate. The visual quality of the decoded video is also impressively improved at all decoded bit-rates.

The paper aims at online recognition of handwritten mathematical symbols. It analyses the structures of 94 opt used mathematical symbols and concludes that all of them consist of 10 basic elements. It proposes a new method of basic element ordering and reduces the number of standard symbols by extracting three primary features of mathematical symbols, namely, basic element vector, relative positions between basic elements and basic element length vector. The traditional dynamic programming method is improved by means of classifying roughly 94 mathematical symbols, considering matching and unmatching value, adding geometric restraints and solving matching problem, through improved Kohn-Munkres algorithm. Correctness rate reaches 90.52%, incorrectness rate 5.03% and refusal rate 4.45%.