Despite the remarkable progress of semi-supervised learning (SSL), its effectiveness under realistic long-tailed settings remains limited. In such settings, labeled data is severely imbalanced, while the distribution of unlabeled data is unknown and often mismatched. Under these conditions, class imbalance inherently leads to biased decision boundaries during training, and distribution mismatch causes unreliable pseudo-labels that further exacerbate this bias. Moreover, realistic long-tailed semi-supervised learning suffers from representation imbalance in feature learning, where dominant classes occupy large regions of the feature space while minority classes become overly compact. To address these challenges, we propose PRB-SSL, a method for improving pseudo-label reliability and representation balance in realistic long-tailed semi-supervised learning. PRB-SSL is built upon a dual-branch framework. Specifically, a Biased Predictor adapts to the unlabeled data distribution to generate more reliable pseudo-labels under distribution mismatch, while a Balanced Predictor with decision-level rebalancing mitigates class-imbalance-induced boundary bias and enables balanced inference. Furthermore, PRB-SSL introduces learning status, a dynamic class-level measure, to regulate feature diffusion during semi-supervised learning, suppressing excessive expansion of well-learned classes while preserving exploration for under-learned ones, thereby alleviating representation imbalance. Extensive experiments on CIFAR-10-LT, CIFAR-100-LT, and STL-10-LT demonstrate that PRB-SSL consistently outperforms state-of-the-art methods under realistic long-tailed semi-supervised learning settings.

Effective planning of aero-engine washing schedules can significantly reduce operating cost of airlines and greatly extend the engine's service life. The engine exhaust gas temperature margin (EGTM) is a crucial indicator for assessing the health of engine, and developing a reasonable maintenance program. However, the significant nonlinearity of EGTM affected by many factors presents challenges for long-term predictions. Specifically, the aero-engine washing will result in a stepwise jump in EGTM, thus, it is difficult to predict the EGTM evolution using traditional methods. This article proposes a hybrid prediction model that integrates the long short-term memory, the autoregressive integrated moving average, complete ensemble empirical modal decomposition with adaptive noise, and the Markov Chain (Markov) models. An EGTM linear decay model is first constructed to assess the recovery effect of EGTM after washing. Then, a transfer learning model is employed to predict model parameters. Finally, an engine cleaning schedule optimization method is proposed to realize EGTM prediction as well as the washing effect prediction. The effectiveness of the proposed approaches is demonstrated on the real data from the CFM56-7B engine.

Document-level relation extraction aims to extract entity relations that span across multiple sentences. This task faces two critical issues: long dependency and mention selection. Prior works address the above problems from the textual perspective, however, it is hard to handle these problems solely based on text information. In this paper, we leverage video information to provide additional evidence for understanding long dependencies and offer a wider perspective for identifying relevant mentions, thus giving rise to a new task named Multimodal Document-level Relation Extraction (MDocRE). To tackle this new task, we construct a human-annotated dataset including documents and relevant videos, which, to the best of our knowledge, is the first document-level relation extraction dataset equipped with video clips. We also propose a hierarchical framework to learn interactions between different dependency levels and a textual-guided transformer architecture that incorporates both textual and video modalities. In addition, we utilize a mention gate module to address the mention-selection problem in both modalities. Experiments on our proposed dataset show that 1) incorporating video information greatly improves model performance; 2) our hierarchical framework has state-of-the-art results compared with both unimodal and multimodal baselines; 3) through collaborating with video information, our model better solves the long-dependency and mention-selection problems.

Semi-supervised cluster ensemble usually introduces a small amount of supervision in the first stage of cluster ensemble, i.e., ensemble generation, by performing many runs of semi-supervised clustering algorithms. However, it is neither efficient in terms of computational complexity, nor flexible in a dynamic learning environment where limited supervision changes over time. In this article we propose a new framework which generates base partitions in an unsupervised manner and attributes different weights to each cluster of the base partitions. The weighting scheme considers both the internal validation measures of clustering and the degrees of satisfaction of pairwise constraints. A weighted co-association matrix based consensus approach is then applied to achieve a final partition. To handle high-dimensional data, we generate base partitions using k-means with both random sampling and random subspace techniques. The new framework retains a high accuracy, and is efficient since it avoids performing semi-supervised clustering in ensemble generation and the complexity of the weighting scheme is independent of the number of instances in a dynamic environment. It is more adaptive than the traditional approach because it does not require rerunning semi-supervised clustering algorithms when the limited supervision changes. Empirical results on 12 datasets demonstrate that it is also more robust to noisy constraints.

The rapid development of pay-as-you-go cloud services motivates the increasing number of cloud resource demands. However, the volatile demands bring new challenges for current techniques to minimize the cost of cloud capacity planning and VM provisioning while satisfying the customer demands. The service vendors will incur enormous revenue loss within the long-term inappropriate planning, especially when the demands fluctuate abruptly and frequently. In this paper, we cast the cloud capacity planning as a classification problem and propose an integrated framework, which effectively predicts the abrupt changing demands, to reduce the cost of cloud resource provisioning. In this framework, we first apply Piecewise Linear Representation to segment the time series of cloud resource demands for labeling the changing trend of each period. Second, Weighted SVM is leveraged to fit the statistical information and the label of each period and predict the changing trend of the following period. Finally, an incremental learning strategy is utilized to ensure the low cost of updating the model using the upcoming requests. We evaluate our framework on the IBM Smart Cloud Enterprise (SCE) trace data and the experimental results show the effectiveness of our proposed framework.

As a state-of-the-art ensemble method, random forest which exhibits a good ability to predict and generalize on various dataset is often composed of a large number of trees. Redundancy of ensemble and connotative decision rules result in expensive operational costs as well as difficulties in comprehension. In this paper, novel leaf node-level pruning methods for random forest are proposed. Each leaf node extracted from a random forest model is regarded as a singe classifier or classification rule, and is then evaluated for pruning. Different from traditional tree-level pruning and rule pruning methods, the idea is to evaluate and extract rules according to node-sample correlation rather than eliminate trees from the ensemble or integrate rules themselves. Experiment results show that the proposed methods can efficiently reduce the size of rule set, and the resulted rules based ensemble achieves better interpretability without significant loss of accuracy.

3D container loading problem (3D-CLP) is a classic NP-hard optimization problem. Although computer scientists and discrete mathematicians have studied this problem for decades, there are still some unsolved puzzles, such as multi-constrained 3D container loading optimization. Moreover, with the rapid development of modern logistics, several new 3D container-loading related problems emerged, such as containers with various sizes, considering different orientations of boxes, and two-step 3D container loading with pallets. From the perspective of practical applications, this paper proposes a new heuristic algorithm for emerged 3D container loading problems. Our proposed algorithm regards the loading arrangement as the position of an individual in the swarm, and by the interactions of the individuals with each other and with loading constraints, most of them will gather to the good ones and finally stop at the best position, which is the loading arrangement of boxes. The proposed algorithm can solve both the 3D container loading problem with pallets or without pallets. Experimental results show significant performance improvements over other state-of-the-art approaches.

Several factors (e.g., balancedness, good correlation immunity) are considered as important properties of Boolean functions for using in cryptographic primitives. A Boolean function is perfect algebraic immune if it is with perfect immunity against algebraic and fast algebraic attacks. There is an increasing interest in construction of Boolean function that is perfect algebraic immune combined with other characteristics, like resiliency. A resilient function is a balanced correlation-immune function. This paper uses bivariate representation of Boolean function and theory of finite field to construct a generalized and new class of Boolean functions on even variables by extending the Carlet-Feng functions. We show that the functions generated by this construction support cryptographic properties of 1-resiliency and (sub)optimal algebraic immunity and further propose the sufficient condition of achieving optimal algebraic immunity. Compared experimentally with Carlet-Feng functions and the functions constructed by the method of first-order concatenation existing in the literature on even (from 6 to 16) variables, these functions have better immunity against fast algebraic attacks. Implementation results also show that they are almost perfect algebraic immune functions.

In disaster management, people are interested in the development and the evolution of the disasters. If they intend to track the information of the disaster, they will be overwhelmed by the large number of disaster-related documents, microblogs, and news, etc. To support disaster management and minimize the loss during the disaster, it is necessary to efficiently and effectively collect, deliver, summarize, and analyze the disaster information, letting people in affected area quickly gain an overview of the disaster situation and improve their situational awareness.

Matrix factorization (MF) is a major technique for collaborative filtering of recommender systems. However, in the traditional MF model, it is difficult to tune the regularization parameter, and the predicted ratings may not lie within the given range. In this paper, we propose a new MF approach, in which MF is modeled as a constrained optimization problem and the constraint conditions are given in terms of the range of the factorization matrices. Under the new model, the regularization parameter is not needed and the predicted ratings are limited in the given range. We further provide a feasible direction method to solve the new model. Experimental results demonstrate that our approach outperforms the traditional MF.

A novel model of support vector classification with partial empirical risks given (P-SVC) is proposed. A sequential minimal optimization for P-SVC is also provided. P-SVC is an extension of the classical support vector classification (C-SVC) and can be used in the case where partial empirical risks are requested. The experiments on some artificial and benchmark datasets show P-SVC obtains a better classification accuracy and a more stable classification result than C-SVC does when partial empirical risks are known.

Inventory forecasting aims to predict the demand of a specific item in the future and reserve the amount of item based on the forecasting results. An accurate and reliable inventory prediction can avoid product overstock and greatly reduce the maintenance cost. Inventory data is a kind of time series data, which has its own characteristics of large volume, long time span, wide covering range and poor regularity. The existing inventory forecasting methods usually only consider the contemporary data or similar goods historical data and achieve the prediction by calculating past average, which cannot capture the complex characteristics, such as long term trend, periodic, and special events. In this work, we treat inventory management as a data mining problem and propose a two-step dynamic prediction model, which first adopts six machine learning techniques and combines them with time series analysis methods to obtain a forecasting basis, then takes into account multiple factors of inventory to fulfill a dynamic inventory forecasting. Moreover, our proposed dynamic forecasting model, as one of core algorithms, is incorporated into an intelligent inventory management system. The experimental results and practical application demonstrate the effectiveness and efficiency of our proposed method.

Gridding is the first and most important step to separate the spots into distinct areas in microarray image analysis. Human intervention is necessary for most gridding methods, even if some so-called fully automatic approaches also need preset parameters. The applicability of these methods is limited in certain domains and will cause variations in the gene expression results. In addition, improper gridding, which is influenced by both the misalignment and high noise level, will affect the high throughput analysis. In this paper, we have presented a fully automatic gridding technique to break through the limitation of traditional mathematical morphology gridding methods. First, a preprocessing algorithm was applied for noise reduction. Subsequently, the optimal threshold was gained by using the improved Otsu method to actually locate each spot. In order to diminish the error, the original gridding result was optimized according to the heuristic techniques by estimating the distribution of the spots. Intensive experiments on six different data sets indicate that our method is superior to the traditional morphology one and is robust in the presence of noise. More importantly, the algorithm involved in our method is simple. Furthermore, human intervention and parameters presetting are unnecessary when the algorithm is applied in different types of microarray images.

The gene expression data are usually provided with a large number of genes and a relatively small number of samples, which brings a lot of new challenges. Selecting those informative genes becomes the main issue in microarray data analysis. Recursive cluster elimination based on support vector machine (SVM-RCE) has shown the better classification accuracy on some microarray data sets than recursive feature elimination based on support vector machine (SVM-RFE). However, SVM-RCE is extremely time-consuming. In this paper, we propose an improved method of SVM-RCE called ISVM-RCE. ISVM-RCE first trains a SVM model with all clusters, then applies the infinite norm of weight coefficient vector in each cluster to score the cluster, finally eliminates the gene clusters with the lowest score. In addition, ISVM-RCE eliminates genes within the clusters instead of removing a cluster of genes when the number of clusters is small. We have tested ISVM-RCE on six gene expression data sets and compared their performances with SVM-RCE and linear-discriminant-analysis-based RFE (LDA-RFE). The experiment results on these data sets show that ISVM-RCE greatly reduces the time cost of SVM-RCE, meanwhile obtains comparable classification performance as SVM-RCE, while LDA-RFE is not stable.

In smooth support vector machine (SSVM), the plus function must be approximated by some smooth function, and the approximate error will affect the classification ability. This paper studies the smooth approximation to the plus function by piecewise polynomials. First, some standard piecewise polynomial smooth approximation problems are formulated. Then, the existence and uniqueness of solution for these problems are proved and the analytic solutions are achieved. The comparison between the results in this paper and the previous ones shows that the piecewise polynomial functions in this paper achieve better approximation to the plus function

This paper discusses the strategies of maximizing the sum of margins for ranking multi classification problem. First, the strategy of maximizing the sum of margins (MSM) is extended to maximizing the sum of weighted margins (MSWM). Using MSWM, a mathematical model is established to deal with the ranking multi classification problems where the importance of margins between classes is different, and its dual model is deduced. Then, by introducing the concept of algebraic margin, which is a generalization of geometric margin, the MSWM is further extended to maximizing the sum of weighed algebraic margins (MSWAM). Based on the MSWAM, the deduced mathematical model of the ranking multi classification problem not only has positive generalization ability, but is also a simple linear programming model

Credit risk assessment plays an important role in banks credit risk management. The objective of credit assessment is to decide credit ranks, which denote the capacity of enterprises to meet their financial commitments. Traditional "one-versus-one" approach has been commonly used in the multi-classification method based on support vector machine (SVM). Since SVM for pattern recognition is based on binary classification, there will be unclassifiable regions when extended to multi-classification problems. Focus on this problem, a new credit risk assessment model based on fuzzy SVM is introduced in this paper that can give a reasonable classification for unclassifiable examples. Experiment results show that the fuzzy SVM method provides a better performance in generalization ability and assessment accuracy than conventional one-versus-one multi-classification approach