To mitigate the negative impact of noise on twin support vector machines (TWSVM), researchers have integrated fuzzy set theory with TWSVM, utilizing fuzzy membership degrees to characterize the influence of various samples in constructing the optimal hyperplane. This approach leads to the development of a fuzzy twin support vector machine (FTSVM). However, existing fuzzy membership degree assignment strategies have several drawbacks: (1) The geometric distance-based assignment strategy exhibits high computational complexity and neglects the surrounding environment of data points. (2) The information entropy-based assignment strategy is sensitive to sample variations and poses challenges in selecting the appropriate membership functions. To address these issues, this study introduces a mass-based dissimilarity measure into the fuzzy membership degree assignment process. The primary factor for assessing the dissimilarity between two instances is the minimum area probability block that encompasses both instances. Then this assignment strategy is integrated with the TWSVM and a novel fuzzy twin support vector machine using mass-based dissimilarity measure (MDFTSVM) is proposed. Additionally, MDFTSVM employs a coordinate descent strategy with shrinking by an active set to reduce computational complexity and significantly improve model training speed. Experimental evaluations are conducted using artificially constructed datasets as well as UCI datasets, which confirm the effectiveness of MDFTSVM in addressing binary classification problems with noise. The results also demonstrate its superior robustness and generalization performance compared to support vector machine, fuzzy support vector machine, TWSVM, FTSVM, twin bounded support vector machine, fuzzy membership assignment strategy based on dissimilarity measure, and fuzzy twin support vector machine based on affinity and class probability models.

Feature selection inherently involves two conflicting objectives: minimizing the number of selected features and maximizing the classification accuracy. The exponential growth of the search space and complex interactions between features make high-dimensional feature selection challenging. Existing multi-objective methods suffer from slow convergence and limited search capabilities. Moreover, there is a lack of efficient methods for identifying feature subsets with equivalent objective values, which could offer diverse options. To address these issues, this paper proposes an evolutionary multitasking algorithm for multi-objective feature selection using dual-perspective reduction, called DREA-FS. First, a dual-perspective dimensionality reduction strategy is designed to generate simplified and complementary tasks through improved filter-based and group-based methods, facilitating the rapid identification of promising regions. To enable effective information sharing, a dual-archive multitasking optimization mechanism is proposed, which incorporates a diversity archive to preserve feature subsets with equivalent performance and maintain diversity. Coupled with an elite archive that offers convergence guidance, this mechanism achieves a balance between convergence and diversity across tasks, thereby enhancing the ability to search for equivalent feature subsets. Experimental results on 21 datasets demonstrate that the proposed method outperforms state-of-the-art multi-objective algorithms in classification performance. Besides, DREA-FS can identify different feature subsets with equivalent objective values, supporting decision-makers with diverse options and better interpretability.

Recently, researchers developed numerous nature-inspired meta-heuristics algorithms, such as particle swarm optimization (PSO), to solve numerical and engineering optimization problems. However, the PSO still suffers from complex optimization problems, such as slow convergence speed and getting stuck in local optima. This paper proposes a Biogeography-based Dual-strategy PSO algorithm (DBPSO). Firstly, a Dual-Strategy Search (DSS) is proposed, which utilizes an improved random learning strategy for global search and a modified quasi-Newton search strategy for local search. The proportion of resources allocated to the modified quasi-Newton search strategy is associated with the inertia weight value of the improved random learning, achieving a balance between exploration and exploitation. Secondly, an improved migration operator of biogeography-based optimization is embedded in DSS. Finally, an iteration-based hybridization strategy that allows one-way information transmission is proposed to fuse the two algorithms effectively. Experiments are conducted on CEC2013 and CEC2017 test suites, and the results show that DBPSO ranks first by comparing it with multiple PSO variants and other meta-heuristics variants. In addition, experiments are conducted on two real-world engineering optimization problems to demonstrate the applicability of DBPSO in solving practical optimization problems, such as the car side impact design problem.

Edge computing has emerged as a killer technology for a hyper-connected world due to its distributed architecture and customer-proximity property. Combined edge nodes with the cloud data center, a cloud-edge computing paradigm is formed, whose resource ecosystem calls for competitive pricing and optimal resource allocation. However, it is not feasible to realize global information-based optimization since some information is kept private to their owners. To solve this challenge, this paper develops the user-independent hierarchical reverse game and the user-assisted hierarchical reverse game to depict the relationship among the resource provider, the resource tenant, and the resource user. The aim is to seek the optimal strategies for players without revealing any private information. The common trait of both games is to force the players to report the optimal strategies based on their actual private information. This salient trait can produce privacy-preservation optimization since there is no requirement for the players to release their individual information directly, and the optimal strategies of other players can be deduced naturally. The difference between the user-independent hierarchical reverse game and the user-assisted one is that the game rules are stipulated entirely by the provider and the tenants (edge nodes) in the former, while some game rules can be customized according to the advice of users in the latter. This leads the user-independent hierarchical reverse game is more concise and easy to guarantee the incentive compatibility constraint, while the user-assisted hierarchical reverse game can attract more users since the game rules can adapt to their economic status, requirements, and preferences.

Most existing heuristic optimizers are found to be restricted to problems of moderate dimensionality, and their performance suffers when solving high-dimensional or large-scale optimization tasks. In this paper, we transform the high-dimensional optimization into online decision making problems and propose a stochastic online decisioning hyper-heuristic framework, by considering multi-armed bandits with temporal reward estimation as our essential backbone. The multi-armed bandit problem simulates an agent which tries to balance exploration and exploitation simultaneously. Specifically, we introduce 1) a sliding time window to assign temporal credit for differing heuristics, and 2) boltzmann exploration for balancing the exploration-exploitation tradeoff. The proposed method is well suited for real-world applications, with flexible compatibility for versatile cost definitions, easy interfaces for heuristics as well as fewer hyper-parameters for consistent generalization performance. Experimental studies on the benchmarks results verify the efficacy and significance of the proposed framework, i.e., when considering three differing heuristics, our method reported consistently competitive performance on benchmark problems with a dimensionality up to 10,000.

Currently, strategies for generating multiple choice questions (MCQ) seldom take the analysis of semantic and syntactic dependency features into consideration. A Chinese MCQ generation method is proposed based on the improved TextRank algorithm with semantic similarity and dependency relatedness to

Evolutionary computation has been widely applied in many fields. However, there are several disadvantages when evolutionary computation is applied to the field of path planning: Firstly, the fitness function struggles to discern discontinuous paths. Secondly, in cases of small population sizes, there is a notable tendency for homogenization within the population. Lastly, the reliance on hyperparameters becomes excessive in determining the optimal path. The paper tackles the aforementioned issues by introducing a multi-population genetic algorithm based on lethal chromosomes. Firstly, discontinuous paths are identified as lethal chromosomes and eliminated via a deletion operator. Secondly, the utilization of multi-population addresses the homogenization phenomenon within the population. Finally, adding a fitness evaluation process to the mutation operator promotes positive mutation and reduces reliance on hyperparameters. The paper presents experimental evidence showcasing the algorithm's effectiveness in obstacle avoidance, path smoothness, and path length optimization. This has some instructive significance for mitigating discontinuous paths in path planning challenges using genetic algorithms.

Traditional large-scale multi-objective evolutionary algorithms perform poorly on the large-scale Flexible Job-Shop Scheduling Problems (FJSP), which are characterized by discrete decision variables, large-scale decision space, and sparse non-dominated solutions. In order to improve the sparsity of non-dominated solutions and enhance the diversity as well as convergence of the population, a Large-Scale Multi-Objective Flexible Job-Shop Scheduling Algorithm Based on Differential Evolution and Angle-Based Weight Vector Assignment (MOEA/D-ADE) is proposed. The optimization objectives of this scheduling problem are minimizing the maximum completion time, the total machine energy consumption, and the mean squared error of the machine load. Firstly, an initial population is formed by screening out high-quality individuals from the decision space based on their individual process equilibrium coefficients using a knowledge-based solution filtering approach. Secondly, to obtain non-dominated solutions, the proposed algorithm employs Differential Evolution (DE) to enhance its global search capabilities. Then it calculates the angle between the offspring and the corresponding weight vector of the parent to achieve the reallocation of the offspring. Finally, the algorithm realizes adaptive adjustment of the mutation probability based on the diversity of individuals in the neighborhood. The proposed method is applied to 10 large-scale FJSP and compared with 3 multi-objective evolutionary algorithms, and the effectiveness of the algorithm is finally verified.

IntroductionPoplar is a tree species with important production and application value. The symbiotic relationship between poplar and arbuscular mycorrhizal fungi (AMF) has a key role in ecosystem functioning. However, there remain questions concerning the seasonal dynamics of the AMF community in poplar roots, the relationship between AMF and the soil environment, and its ecological function.MethodPoplar roots and rhizosphere soil were sampled at the end of April and the end of October. The responses of AMF communities to season, host age, and host species were investigated; the soil environmental factors driving community changes were analyzed.ResultsThe diversity and species composition of the AMF community were higher in autumn than in spring. Season, host age, host species, and soil environmental factors affected the formation of the symbiotic mycorrhizal system and the AMF community. Differences in the communities could be explained by soil pH, total nitrogen, total phosphorus, total potassium, available potassium, and glomalin content.DiscussionThe AMF community was sensitive to changes in soil physicochemical properties caused by seasonal dynamics, particularly total potassium. The change in the mycorrhizal symbiotic system was closely related to the growth and development of poplar trees.

The environment friendly Cu2ZnSnSe4 (CZTSe) quantum dot-sensitized solar cells (QDSSCs) has become one of the most promising photovoltaic technologies due to its earth-abundant component and excellent photoelectric properties. However, the power conversion efficiency (PCE) is far behind other high-efficiency chalcogenide sensitizer systems and the main obstacle can be attributed to the inappropriate conduction band position relative to the TiO2 films. Herein, we developed a partial substitution approach to transform CZTSe QDs to Cu2Zn(SnxGe1−x)Se4 (CZTGSe) QDs to resolve the CBM mismatch problem in QDSSCs. The CZTGSe QDs with narrow size distribution were synthesized via one-step method and Ge/(Ge+Sn) ratios were prepared. It is found that the introduction of Ge upshifts the CBM and broadens the band gap of CZTGSe QDs. Benefiting from the enhanced driving force of photoelectron injection and depressed charge recombination at TiO2/QDs/electrolyte interface, the short-circuit current (Jsc) and open-circuit voltage (Voc) of Ge-substituted QDSSCs are synchronously improved and the PCE of the 30

When solving large-scale many-objective optimization problems (LMaOPs), due to the large number of variables and objectives involved, the algorithm is faced with a very high-dimensional and complex search space, which is difficult to be explored with limited resources. To address these issues, this paper proposes a universal large-scale many-objective optimization framework based on cultural learning (UCLMO). First, a universal framework is proposed, and multi-objective optimizers can be embedded into the framework to accelerate the convergence. Moreover, inspired by cultural learning, an individual selection strategy based on historical knowledge is proposed to promote the diversity of the population, and an assisted evolution strategy based on normative knowledge is presented to accelerate the convergence of the algorithm. Experiments have been conducted on multi-objective knapsack problems and LMaOPs with decision variables ranging from 500 to 1500, and the number of objectives ranging from 5 to 15. The experimental results verify the superiority and competitiveness of the proposed UCLMO framework in solving LMaOPs compared with state-of-the-art algorithms.

Infrared (IR) images containing rich spectral information are essential in many fields. Most RGB-IR transfer work currently relies on conditional generative models to learn and train IR images for specific devices and scenes. However, these models only establish an empirical mapping relationship between RGB and IR images in a single dataset, which cannot achieve the multi-scene and multi-band (0.7–3 μm and 8–15 μm) transfer task. To address this challenge, we propose VQ-InfraTrans, a comprehensive framework for transferring images from the visible spectrum to the infrared spectrum. Our framework incorporates a multi-mode approach to RGB-IR image transferring, encompassing both unconditional and conditional transfers, achieving diverse and flexible image transformations. Instead of training individual models for each specific condition or dataset, we propose a two-stage transfer framework that integrates diverse requirements into a unified model that utilizes a composite encoder–decoder based on VQ-GAN, and a multi-path transformer to translate multi-modal images from RGB to infrared. To address the issue of significant errors in transferring specific targets due to their radiance, we have developed a hybrid editing module to precisely map spectral transfer information for specific local targets. The qualitative and quantitative comparisons conducted in this work reveal substantial enhancements compared to prior algorithms, as the objective evaluation metric SSIM (structural similarity index) was improved by 2.24% and the PSNR (peak signal-to-noise ratio) was improved by 2.71%.

Line crossing detection is to check whether people or objects go across a given barrier line, which is quite common and important in our daily life, such as the electronic article surveillance (EAS) checkpoint in a retail store or the finish line in track and field. Although existing solutions to line crossing detection have achieved great advancement, they do not function well when multiple objects or people cross the line at the same time. In this paper, we propose a new radio frequency identification (RFID)-based solution called RF-Line to line crossing detection, especially for multiobject scenarios. The biggest challenge is that the RFID reader’s coverage zone is invisible and irregular; we cannot roughly take the time when a tag is seen by the reader for the first time as the time when line crossing occurs. In RF-Line, we deploy two antennas opposite to each other and collect the RF phase profiles of two antennas at the same time. By a series of geometric transformations and mathematical derivations, we find that summing up the two phase profiles will get a new phase curve, in which the inflection point of the curve is the time of line crossing. In addition, we address the problem of turning back or long stay on the barrier line. We implement RF-Line with commodity RFID systems. Extensive experiments show that RF-Line can achieve accurate line crossing detection with a small error of 6.1 cm, with no need for any system calibration or complicated deployment.

The imaging and tracking of moving objects through scattering media is a challenge due to the serious degradation of optical information. However, the reconstruction fidelity for non-sparse objects is inadequate and the displacement information lack the quantitative description of moving objects. In this study, we propose a deep learning method to decode the shape and displacement information of moving objects on the plane perpendicular to the system's optical axis from one-frame speckle difference pattern. The proposed method was verified via experiments and it was found to be viable for imaging moving objects with different complexity and sparsity. The superiority of the method was demonstrated via comparison experiments. Moreover, it accurately tracked moving objects at a pixel level.

High-order problems pose significant challenges for evolutionary algorithms (EAs) to optimize. To mitigate this, a deep hybrid transfer learning EA (DHTL-EA) is proposed. DHTL-EA works by transferring both the model and the optima from a corresponding low-order problem. Here, a deep neural network is adopted to model both the low-order and high-order problems, and the training data are derived from historical evolutionary data. The theoretical basis of DHTL-EA is well-supported by the transferability of solutions among domination-landscape-equivalent problems. The transfer to high-order problem is achieved by retraining the last fully connected layer of the deep neural network model for the target problem. Experiments on two groups of problems validated that DHTL-EA is effective on high-order problems. Further testing on other benchmark functions demonstrated its competitive performance.

In RFID systems, the privacy problem has attracted increasing attention as the tags have extremely limited on-chip resources and may blindly respond to unauthorized readers. To protect the privacy, one widely used solution is to deploy one or more blocker tags to collide the RF signal sent from protected tags all the time. In this paper, we investigate the problem of tag identification in privacy-sensitive RFID systems when we have the authorized reader(s). Due to the presence of blocker tags, the tag identification becomes more challenging since the protected tags and blocker tags will always respond concurrently, leading to unreconciled collisions. To overcome this challenge, we in this paper propose two efficient tag identification protocols IIP and SIP, which meet three application requirements: privacy, accuracy, and efficiency. IIP iteratively deactivates blocking tags as well as labeling genuine tags, and finally identifies tags by avoiding all the unreconciled collisions. On top of IIP, SIP further avoids the slot waste by carrying out a filter to separate genuine tags from others in advance. Simulation results demonstrate that our protocols are able to guarantee any identification accuracy in a time-efficient and privacy-protected way.

Herein, a CuSCN/Ga2O3 heterojunction device was fabricated by spin-coating and metal-organic chemical vapor deposition (MOCVD) methods. Under the irradiation of 254 nm deep ultraviolet (DUV) light with an intensity of 1000 mu W/cm(2) , the device shown high sensitivity and favorable self-powered performances with photo-to-dark current ratio (PDCR) of 1.29 x 10(4) , photo responsivity (R) of 5.5 mA/W, rejection ratio (R-270nm/R-600nm) of 4.33 x 10(3) , and specific detectivity (D*) of 3.8 x 10(11) cm Hz(1/2)W(-1) (Jones) at -5 V. In addition, the device has a rise time of 0.45 s and 3.80 s, and a decay time of 0.26 s and 0.26 s. In general, the CuSCN/Ga2O3 heterojunction prepared in this work may well be a potential candidate for achieving a self-powered and high-performance DUV photodetector.

Person re-identification (ReID) arises in many applications, such as video surveillance and intelligent security. A challenge of cross-domain person ReID is the notorious distribution drift problem. Improving the accuracy of pseudo labels can promote the model to fit the target domain, so it is crucial to extract discriminative person features. The transformer can extract discriminative person features due to its ability to capture long distance depen-dencies, but its poor generalization ability may aggravate the influence of noise pseudo labels. The isolation between local information modeling and global information modeling further prevents the extraction of the discriminative person features. Therefore, this paper proposes an interactive cascade transformer framework. Firstly, a lightweight transformer structure (microformer) with better generalization is proposed. It maintains the advan-tages of traditional transformers on extracting discriminative features, and avoids the aggravation of the influence of noise labels. Secondly, an interactive cascade microformer framework (ICMiF) is proposed, which promotes the interaction between local information modeling and global information modeling to enhance the person feature representation. Local information facilitates mining global attribute dependencies, and global information improves the accuracy of local information. The experimental results demonstrate that the proposed ICMiF outperforms state-of-the-art methods for the cross-domain person ReID tasks.(c) 2022 Elsevier Inc. All rights reserved.

Line crossing detection is to check whether people or objects go across a given barrier line, which is quite common and important in our daily life, such as the EAS checkpoint in a retail store or the finish line in track and field. Although existing solutions to line crossing detection have achieved great advancement, they do not function well when multiple objects or people cross the line at the same time. In this paper, we propose a new RFID-based solution called RF-Line to the problem of line crossing detection, especially for multi-object scenarios. The biggest challenge is that the RFID reader’s coverage zone is invisible and irregular; we cannot roughly take the time when a tag is seen by the reader for the first time as the time when line crossing occurs. In RF-Line, we deploy two antennas opposite each other and collect the RF phase profiles of two antennas at the same time. By a series of geometric transformations and mathematical derivations, we find that summing up the two phase profiles will get a new phase curve, in which the inflection point of the curve is the time of line crossing. We implement RF-Line with commodity RFID systems. Extensive experiments show that RF-Line can achieve accurate line crossing detection with a small error of 6.1 cm, with no need for any system calibration or complicated deployment.