Subset Selection Scheme Research Articles

RBSS: A fast subset selection strategy for multi-objective optimization

Multi-objective optimization problems (MOPs) aim to obtain a set of Pareto-optimal solutions, and as the number of objectives increases, the quantity of these optimal solutions grows exponentially. However, a plethora of optimal solutions can impose significant decision stress on decision-makers. Subset selection, as the extension of a model, can extract a representative set of solutions, thereby alleviating the decision-makers’ choice pressure. In addition, extending a model undoubtedly incurs additional time costs. To cope with the foregoing issues, a fast subset selection method named ranking-based subset selection (RBSS) is proposed in this paper. It can efficiently select a small number of optimal solutions within an unbounded external archive and can be directly applied to any multi-objective evolutionary algorithm. This allows it to maintain good distribution and diversity with very little time investment. We employed a ranking-based approach to map the objective space to a ranking space (an integer space) defined by us and then selected the corresponding subset in the ranking space. The well-behaved mathematical properties of the ranking space and the advantages of using integer calculations accelerated the subset selection process. Experimental results indicate that compared to several state-of-the-art subset selection methods, RBSS is capable of selecting a set of representative and diverse solutions across different types of MOPs, while consuming significantly less time. Specifically, for problems where the Pareto front is a two-dimensional manifold and a one-dimensional manifold, the time consumption of RBSS is approximately only 0.028% to 27.5% and 4.6e−4% to 0.15% of that required by other algorithms, respectively.

Data-driven modeling of multi-stable origami structures: Extracting the global governing equation and exploring the complex dynamics

In recent years, multi-stable origami structures have garnered increasing attention for their applications in dynamic scenarios such as robotic arm motions, impact energy absorption, and spectrum gap regulation. Understanding the intricate working mechanisms and exploring the rich dynamics of these structures necessitate the development of dynamic models. However, existing dynamic modeling methods for origami structures are often cumbersome, and the resulting dynamic models often lack interpretability. To overcome these limitations, we propose a novel data-driven dynamic modeling approach based on B-spline Galerkin method and subset selection strategy. This approach directly captures the dynamics of multi-stable origami structures using measured data, eliminating the need for reliance on empirical or prior knowledge. To validate the effectiveness of the proposed approach, we first evaluate it on the Duffing system, which has explicit expressions, successfully reconstructing the governing equation. Subsequently, we apply this method to the dynamic modeling of the origami ball structure with tri-stability and the multi-cell stacked Miura-origami (SMO) structure with high dimensionality through simulation, showing favorable results. Finally, using experimental data collected from a bi-stable SMO structure prototype, we employ the proposed method to obtain a global model that can accurately predict different dynamic behaviors over a broad range of excitation frequencies, including intra-well periodic vibrations, inter-well periodic vibrations, and inter-well chaotic vibrations. Overall, our method showcases outstanding efficacy in formulating interpretable, manageable, and comprehensive dynamic models. It plays a pivotal role in delving into the intricate dynamics of multi-stable origami structures.

Structure-aware machine learning strategies for antimicrobial peptide discovery

Machine learning models are revolutionizing our approaches to discovering and designing bioactive peptides. These models often need protein structure awareness, as they heavily rely on sequential data. The models excel at identifying sequences of a particular biological nature or activity, but they frequently fail to comprehend their intricate mechanism(s) of action. To solve two problems at once, we studied the mechanisms of action and structural landscape of antimicrobial peptides as (i) membrane-disrupting peptides, (ii) membrane-penetrating peptides, and (iii) protein-binding peptides. By analyzing critical features such as dipeptides and physicochemical descriptors, we developed models with high accuracy (86–88%) in predicting these categories. However, our initial models (1.0 and 2.0) exhibited a bias towards α-helical and coiled structures, influencing predictions. To address this structural bias, we implemented subset selection and data reduction strategies. The former gave three structure-specific models for peptides likely to fold into α-helices (models 1.1 and 2.1), coils (1.3 and 2.3), or mixed structures (1.4 and 2.4). The latter depleted over-represented structures, leading to structure-agnostic predictors 1.5 and 2.5. Additionally, our research highlights the sensitivity of important features to different structure classes across models.

Research on moving object tracking with a large number of outliers based on TRESAC++ algorithm

In contrast to the method based on motion equations, image registration proves effective for tracking moving objects in missions where establishing a motion model is unfeasible. However, in cases where the object is captured at varying imaging angles or against a similar background, a large number of outliers may arise during the process of image feature extraction. Consequently, when confronted with a large number of outliers, image registration methods exhibit a drawback in accurate outlier filtering, especially when spatial constraints on feature matching pairs are constrained. Ultimately, these factors can render object tracking inaccurate or even unattainable. In light of the aforementioned circumstances, this paper proposes TRESAC++, which based on a triplet relation feature matching method to effectively filter outliers. To enhance the operational efficiency of the algorithm, Principal Component Analysis is employed for dimensionality reduction, aiming to decrease the incidence of triple matches and subsequently mitigate execution time. To fortify the algorithm's robustness, a triplet relation linked with an initial data subset selection strategy is additionally proposed. Experimental results on five challenging experiments show that TRESAC++ rivals current state-of-the-art techniques in terms of computational cost, while the implementation exhibits better outlier filtering. Additionally, Experiment 4 and Experiment 5 use moving object datasets to confirm TRESAC++'s superior capability in precise object tracking.

A Stochastic Model Based on Optimal Satellite Subset Selection Strategy for Smartphone Pseudorange Relative Positioning.

In order to overcome the limitations of traditional stochastic models for smartphones, we introduce a double-difference code pseudorange residual (DDPR)-dependent stochastic model based on an optimal satellite subset, with the goal of mitigating the constraints imposed by the quality of GNSS observations in smartphones on the accuracy and reliability of phone-based GNSS positioning. In our methodology, the satellite selection process involved considering the integrated carrier-to-noise density ratio (C/N0) index of both the reference station and the smartphone, enabling us to construct a satellite subset characterized by superior observation quality. Furthermore, by leveraging the optimal subset of satellites and incorporating the C/N0-dependent stochastic model, we could determine the approximate location of the terminal through pseudorange differential positioning. Subsequently, we estimated the DDPRs for all satellites and utilized these values as prior information to build a stochastic model of the observations. Our findings indicate that in occluded environments, the DDPR-dependent stochastic model significantly enhances positioning accuracy for both the Huawei Mate40 and P40 terminals compared to the C/N0-dependent model. Numerically, the improvements in the north (N), east (E), and up (U) directions were approximately 30%, 32%, and 34% for the Mate40, and 26%, 33%, and 24% for the P40 terminal. This suggests that the proposed DDPR-dependent stochastic model effectively identifies and mitigates large gross error signals caused by multipath and non-line-of-sight (NLOS) signals, thereby assigning lower weights to these problematic observations and ultimately enhancing positioning accuracy. Moreover, the weighting method involves minimal computations and is straightforward to implement, making it particularly suitable for GNSS positioning applications on smartphones in complex urban environments.

Competitive swarm optimization with subset selection based manifold learning for multimodal multi-objective optimization

There are two major challenges when handling the multimodal multi-objective optimization (MMO) problems. One is the loss of diversity since most of the evolutionary algorithms designed for MMO prefer the base algorithm with rapid convergence. Therefore, the extra niching or other diversity preserving mechanism is inevitable. The other is the distribution of the Pareto optimal solutions with imbalanced density. Since the Pareto optimal sets may show different characteristics in the decision space, it is tough to converge the solutions to the Pareto front uniformly. To address these issues, subset selection and manifold learning based competitive swarm optimization algorithm, namely MMO_CSO, is proposed. Competitive swarm optimizer which has well balance on both diversity and convergence is adopted. Moreover, a subset selection strategy is applied to select diversified individuals for learning the manifold structure of the Pareto set. Thereby, the subset selection based manifold learning mechanism is designed to generate the promising solutions which could approach the real Pareto solutions and fill the sparse Pareto subregion. Compared against six state-of-the-art peer algorithms, the proposed MMO_CSO has a better performance to search for the Pareto optimal solutions both in decision space and objective space on CEC2019 MMO benchmarks.

Dynamic Object Tracking Based on Triplet Relationship Guided Sampling Consensus Algorithm

Compared with the traditional methods based on the prediction of moving object trajectory, the method based on image registration has the advantage of not relying on the object motion equation to track the object. However, in the case of a large number of outliers, the image matching method has the defects of inadequate filtering of outliers or erroneous filtering of incomers due to the limitations of spatial constraints of feature matching pairs, which will make the tracking of flying objects inaccurate or impossible. During the flight, the object may be in a similar background and the image shooting angle is different, which makes the object imaging angle change, resulting in a large number of outlier interference. Because of the above situation, this paper adopted an improved TRESAC algorithm based on RANSAC, which used a feature matching method based on a triplet relationship to effectively filter outliers and then adopted an initial data subset selection strategy to increase its robustness. Experimental results show that the TRESAC algorithm can filter outliers quickly and accurately, and the object is still tracked effectively under the condition of similar background and pose change.

A pointwise optimal subset selection strategy assisted by shape functions in digital image correlation algorithm

A pointwise optimal subset selection strategy assisted by shape functions in digital image correlation algorithm

Feature subset selection in data-stream environments using asymmetric hidden Markov models and novelty detection

With the increase of computational power and memory capacity, it is possible to record and analyse lots of features of different nature in real time or in a data stream manner. Nonetheless, in many applications, not all variables may be relevant to explain the nature of the data. Feature subset selection strategies are therefore required to extract the relevant features to understand the data generating process. Much work has been performed in the area of supervised classification problems regarding feature selection, whereas for unsupervised environments, scarce studies have been conducted. In current feature subset selection methodologies for unsupervised data streams, the set of relevant variables are reevaluated or forgotten whenever a new instance or chunk of data arrives: this approach can be computationally expensive or unnecessary. Therefore, in this article, we provide a method to perform feature subset selection in unsupervised data streams. An embedded feature subset selection methodology based on asymmetric hidden Markov models and novel concept discovery strategies is used. This methodology can be used to detect novel concepts in data, and update the set of relevant features when a drift in the data stream is detected. Thus, the relevant variables are updated only when needed. To make this possible, we provide a model for batch and online problems, that is capable of dynamically determining the relevant variables to address feature selection in data streams. Additionally, the model provides domain insights using context-specific Bayesian networks which can be helpful to understand the dynamic process. To validate the proposed methodology, synthetic and real data from ball-bearings are used. Additionally, the proposed methodology is compared with other state of the art methodologies. The proposed method can be used to update the relevant features when needed and is more stable than its competitors.

TFSFB: Two-stage feature selection via fusing fuzzy multi-neighborhood rough set with binary whale optimization for imbalanced data

Obtaining informative features is crucial in imbalanced classification. However, existing neighborhood rough set-based feature selection approaches easily overlook the diversity and complexity of data distributions, and it is difficult to obtain this global optimal feature subset from imbalanced and high-dimensional datasets. To tackle these limitations, we construct a new two-stage feature subset selection scheme by fusing the fuzzy multi-neighborhood rough set (FMRS) with the binary whale optimization algorithm (BWOA) for imbalanced data. First, to evaluate those distributions of different features, this standard deviation coefficient is introduced to construct a fuzzy multi-neighborhood radius set. Then, the fuzzy multi-neighborhood granule and fuzzy membership degree are presented to establish the novel FMRS, and the feature significance measure in the view of algebra is developed to balance the approximate properties and influences of different features in the negative and positive classes. Second, fuzzy multi-neighborhood conditional entropy is defined to maximize information quantity of class- imbalanced data from the information view, and then by fusing the two evaluation perspectives above, this mixed metric is provided to fully assess this uncertainty of class-imbalanced datasets. These internal and external significant metrics are designed to obtain this preselected candidate set of features based on the filter FMRS model at this first stage. Third, a control factor can be developed to dominate the whale position update, and a novel fitness function will be constructed when fusing the dependency degree and entropy measure with the reduction ratio to evaluate this optimal subset of features. Adopting population partitioning and local interference schemes can prevent the BWOA from becoming trapped within a local optimum. To reduce this search space of evolution, the dynamic bitmask is used to improve the BWOA, and then an optimal subset of features is acquired through continuous iterations of this wrapper BWOA at this second stage. Finally, a new two-stage algorithm for feature subset selection by fusing FMRS and BWOA is provided to process class-imbalanced data, where this particle swarm optimization algorithm confirms those optimized parameters. Experiments on 31 datasets show that our algorithm is efficient and can achieve excellent classification efficiency for binary and multiclass imbalanced data.

Self-Attentive Subset Learning over a Set-Based Preference in Recommendation

Recommender systems that learn user preference from item-level feedback (provided to individual items) have been extensively studied. Considering the risk of privacy exposure, learning from set-level feedback (provided to sets of items) has been demonstrated to be a better way, since set-level feedback reveals user preferences while to some extent, hiding his/her privacy. Since only set-level feedback is provided as a supervision signal, different methods are being investigated to build connections between set-based preferences and item-based preferences. However, they overlook the complexity of user behavior in real-world applications. Instead, we observe that users’ set-level preference can be better modeled based on a subset of items in the original set. To this end, we propose to tackle the problem of identifying subsets from sets of items for set-based preference learning. We propose a policy network to explicitly learn a personalized subset selection strategy for users. Given the complex correlation between items in the set-rating process, we introduce a self-attention module to make sure all set members are considered in subset selecting process. Furthermore, we introduce gumble softmax to avoid gradient vanishing caused by binary selection in model learning. Finally the selected items are aggregated by user-specific personalized positional weights. Empirical evaluation with real-world datasets verifies the superiority of the proposed model over the state-of-the-art.

GENEREIT: generating multi-talented reinforcement learning agents

Creating an intelligent system that is able to generalize and reach human or above-human performance in a variety of tasks will be part of the crowning achievement of Artificial General Intelligence. However, even though many steps have been taken towards this direction, they have critical shortcomings that prevent the research community from drawing a clear path towards that goal, such as limited learning capacity of a model, sample-inefficiency or low overall performance. In this paper, we propose GENEREIT, a meta-Reinforcement Learning model in which a single Deep Reinforcement Learning agent (meta-learner) is able to produce high-performance agents (inner-learners) for solving different environments under a single training session, in a sample-efficient way, as shown by primary results in a set of various toy-like environments. This is partially due to the fixed subset selection strategy implementation that allows the meta-learner to focus on tuning specific traits of the generated agents rather than tuning them completely. This, combined with our system’s modular design for introducing higher levels in the meta-learning hierarchy, can also be potentially immune to catastrophic forgetting and provide ample learning capacity.

Subset Selection Strategies Based on Target Positioning Characteristics for Anti-Jamming Technology

For the discrimination of false targets, the discrimination probability can be improved by increasing the number of radar stations. However, that may result in a serious waste of equipment resources when too many radars are involved. An asymptotic subset selection strategy based on target positioning characteristics is proposed to address the above issues. Several effective strategies are considered to select some transmitters and receivers to form a radar subset, such as the rapid shrinkage method, global shrinkage method, and predetermined size method, which can guarantee the preset discrimination performance of limited equipment resources and reduce the waste of resources. All of the selected stations have good spatial distribution or strong discrimination capacity in multistatic radar system. Compared with the exhaustive search, the proposed subset selection strategy affords a significant reduction in terms of time complexity. The simulation results show that the radar subset can maintain approximate discrimination performance with the original multistatic radar systems. At the same time, the proposed method optimizes the number of radar stations and reduces data processing time and required communication links, thus effectively saving operating costs.

A feature selection model for software defect prediction using binary Rao optimization algorithm

In this digital world, using software has become an important part of daily life and business. The software must be rigorously tested in order to avert a financial crisis. The defect-free software enhances the functionality of the business. Predicting software defects in advance is a crucial task in the software industry. The aim of Software Defect Prediction (SDP) is to locate the possible software bugs. This paper proposes a hybrid feature selection (filter–wrapper) approach based on the multi-criteria decision making (MCDM) method and the Rao optimization method for selecting the more informative features to improve the software defect prediction rate. The proposed work measures the fitness of the candidate solution by using the defect prediction rate and the feature selection ratio. The performance of the proposed method is evaluated using three popular benchmark NASA datasets (PC5, JM1, and KC1) and compared with the state-of-the-art methods. The proposed feature subset selection scheme identifies the most significant feature subset for defect prediction with an average accuracy of 95% on the benchmark datasets. According to the experimental results, the proposed hybrid approach outperforms the standard strategy in terms of defect prediction rate.

A subset-selection-based derivative-free optimization algorithm for dynamic operation optimization in a steel-making process

ABSTRACT Steel-making production is a dynamic process that has the characteristics of high temperature and heat, and a complex reaction mechanism that causes the mechanism model possibly to be unavailable and the system to be a black box. In this article, a dynamic operation optimization (DOO) problem is refined from the basic oxygen furnace (BOF) steel-making process, and the system model is formulated by a data analytics method. This prevents to solve the optimization problem with derivative-based optimization methods. To circumvent these difficulties, a surrogate-model-based derivative-free optimization algorithm is proposed for solving the DOO problem. In order to establish the surrogate model with the least number of function evaluations, a subset selection strategy is designed to find a sparse structure for the optimization problem, based on which a set of simple bases is determined to establish the surrogate model. Moreover, this also reduces the scale of the parameter optimization problem. Numerical experiments on actual production data verify the applicability and effectiveness of the proposed method.

Cyber security for federated learning environment using AI technique

AbstractA cyber‐security threat in the Android environment is seen as malicious code. Due to the rapid development of Android malware deployments, manually detecting malicious apps inside the Android environment is almost impossible. In the end of an outcome, machine learning has emerged as a promising method for detecting malware. Because the increasing accessibility and appropriate attributes have a significant impact on machine learning performance, selecting features becomes more critical in malware detection using the machine learning. In the existing system, a filter‐based feature selection method was used. The filter‐based feature subset selection strategies are mathematically efficient for computation. But they refuse to address concerns including such multicollinearity, which impacts the filter methods' accuracy. To overcome this issue, this research develops a hybrid method that combines the findings of both static and dynamic malware examination. This method tackles the issue of more effectively analysing, identifying, and classifying Android malware. Many feature selection approaches are compared and contrasted based on a variety of parameters, such as the composition of important extracted features. By using extracted features, whilst completing static and dynamic malware examinations, several machine learning methods are used to identify and characterize malware. The experimental result shows the evaluation of the feature selection method which is varied from other algorithms. It enhances the accuracy and minimizes the run time of the learning models.

Multiple imputation method of missing credit risk assessment data based on generative adversarial networks

Credit risk assessment is critical for loan approval and risk management of banks. However, the problem of missing credit risk data may greatly reduce the effectiveness of the assessment model. Therefore, constructing a data imputation method for accurate missing data prediction is quite beneficial. Typically, building an effective imputation model is very challenging due to the high missing rate and complex arbitrary missing pattern of datasets in credit risk assessment. In this paper, a novel imputation method named as Multiple Generative Adversarial Imputation Networks (MGAIN) is proposed. Specifically, we first randomly select multiple attribute subsets instead of the whole attributes such that more complete samples can be generated. Then, the missing data in each attribute are imputed by using generative adversarial imputation networks (GAIN) which fully considers the relationships among missing values by combining neural network and adversarial learning. The proposed subset selection and multiple imputation strategy not only simplify the network structure of GAIN but also reduce the demand for data. Finally, a weighted average method is presented to synthesize multiple results of each missing attribute value to further improve the accuracy. The experimental results on real-world data demonstrate that the proposed method is superior to other popular imputation methods.

Improved UWB TDoA-Based Positioning Using a Single Hotspot for Industrial IoT Applications

The goal of this article is to investigate ultra wideband localization with time difference of arrival processing at the anchors. We consider scenarios where the anchors are placed very close to each other and the target to be localized is around the group of anchors. All target–anchor communications are assumed to be in line-of-sight. Since our analysis shows that symmetries in anchors’ placement, with respect to the target position, degrade the positioning accuracy of standard algorithms, we propose to use a subset selection strategy, where position estimates obtained with properly selected subsets of asymmetric anchors are fused together to get the final localization output. Our results show improved localization accuracy with respect to the use of all anchors, especially in estimating the angle of arrival. Finally, we analyze the impact of an inaccurate time synchronization among the anchors, deriving guidelines for hardware implementation.

Novel Receive Antenna Selection Scheme for Precoding-Aided Spatial Modulation with Lattice Reduction.

In this paper, a new receive antenna subset (RAS) selection scheme is proposed for precoding-aided spatial modulation (PSM). First, a lattice reduction (LR)-based precoder is employed instead of a conventional zero-forcing (ZF) precoder. It is analytically shown that a full diversity gain can be achieved by the LR-based ZF precoder without RAS selection. Then, an optimal LR-based RAS selection criterion is derived for the over-determined LR-based PSM systems, and a suboptimal selection algorithm is additionally presented. It is also shown that optimal and suboptimal RAS selection algorithms based on LR improve the BER performance of the LR-based PSM system. Further, the overall diversity order of the over-determined LR-based PSM systems with optimal LR-based RAS selection is analyzed. Finally, diversity analysis and simulation results show that the LR-ZF-based PSM system with optimal LR-based RAS selection outperforms the conventional ZF-based PSM system with conventional optimal RAS selection.

A hybrid feature selection scheme for high-dimensional data

There is a growing interest in developing feature subset selection schemes for high-dimensional datasets by filter, wrapper, embedded, and hybrid manners. In this paper, we propose a new hybrid (filter-wrapper) feature selection approach. At first, in the filter step, we rank input features according to their relevance with the class label. Afterwards, we apply different clustering methods for the classification of the selected features. We perform an inner and outer cluster ranking based on the primary feature ranking in the next step. Then, different search strategies are performed on the best cluster of features in the wrapper phase. Moreover, we add some of them to the feature set based on the classifiers (nearest neighbor, decision tree, support vector machine, and random forests) feedback. Then, the algorithm goes to the next cluster, and this process is continued till all clusters are met. Finally, we compare the results of the proposed method to the state-of-the-art schemes. Comparison results imply the superiority of the proposed method to the counterparts on eight high-dimensional datasets in terms of accuracy and computational complexity.