查看更多>>摘要：Recommendation systems help consumers find useful items of information given a large amount of information while avoiding information overload. Nowadays, in addition to traditional evaluation information (such as individual reviewer ratings), information such as multicriteria ratings are available on the Web. In the work reported here, we investigated whether collaborative filtering methods using multicriteria evaluation data and deep learning are effective for abundant and sparse multicriteria evaluation data. We also investigated whether adaptability can be achieved by predicting aggregated ratings from the evaluations of a few users. Experimental results show that three proposed methods using deep learning are better than traditional methods for both recommendation and rating aggregation.(c) 2022 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).
查看更多>>摘要：Aggregation functions largely determine the convergence and diversity performance of multi-objective algorithms in decomposition methods. Nevertheless, the traditional Tchebycheff function does not consider the matching relationship between the weight vectors and candidate solutions. To deal with this issue, a new multiobjective state transition algorithm based on modified decomposition method (MOSTA/D) is proposed. According to the analysis of the relationship between the weight vectors and candidate solutions under the Tchebycheff decomposition scheme, the concept of matching degree is introduced which employs vectorial angles between weight vectors and candidate solutions. Based on the matching degree, a new modified Tchebycheff aggregation function is proposed in MOSTA/D. It can adaptively select the candidate solutions which are better matched with the weight vectors. This proposed MOSTA/D decomposes a multiobjective optimization problem into a number of scalar optimization subproblems and optimizes them in a collaborative manner. Each individual solution in the population of MOSTA/D is associated with a subproblem. Four mutation operators in STA are adopted to generating candidate solutions on subproblems and maintaining the population diversity. Relevant experimental results show that the proposed algorithm is highly competitive in comparison with other state-of-the-art evolutionary algorithms on tackling a set of benchmark problems with complicated Pareto fronts and a typical engineering optimization problem. (C) 2022 Elsevier B.V. All rights reserved.
查看更多>>摘要：Automatic bayberry picking can substantially reduce labor costs and improve picking efficiency in an orchard management system. Nowadays, an automatic picking system mainly relies on machine vision to segment bayberry fruit from the background. Most existing methods are carried out in an environment where the light intensity is relatively fixed and the bayberries are unobstructed. However, due to the complexity of the growing environment, including variations in lighting and widespread occlusion, segmentation accuracy is quite limited, which affects the large-scale application of automatic picking systems. Aiming at these issues, in this study, a bayberry segmentation method based on a multi-module convolutional neural network is proposed. First, the bayberry images in a real scene were collected and preprocessed to form a dataset. Then, a convolutional neural network was constructed, with an image correction module to improve the network's robustness to natural ambient lighting. Finally, a shape completion module with a puzzle algorithm was utilized to overcome the occlusion in the natural environment. The experimental results show that the average precision of the proposed method for semantic segmentation and instance segmentation of bayberry fruit can reach 0.913 and 0.755, respectively, which outperforms the existing methods and has important significance for automatic picking in orchards. (C) 2022 Elsevier B.V. All rights reserved.
查看更多>>摘要：With the rapid development of network communication technology, identity authentication based on smart cards is one of the most common two-factor authentication schemes. In some real-world applications, timeliness is another challenge besides security and privacy because of the frequent logon and logoff or data updating. Presently, two-factor authentication schemes based on elliptic curve cryptography (ECC) are efficient. They are based on asymmetric encryption algorithms. But the time efficiency can be improved by hash-based methods, such as Negative databases (NDB) inspired by the artificial immune system. A one-time password authentication scheme based on NDBs is efficient, but it does not achieve the functions of mutual authentication and password changing, nor resists stolen-verifier attacks.& nbsp;In this paper, we propose an efficient two-factor authentication scheme based on NDBs. With this scheme, the password changing function is achieved, and the properties of uncertain form of negative databases can reduce the frequency of data updating. As the proposed scheme is a hash function based one, it has fewer calculation steps and higher time efficiency, compared with the authentication schemes based on asymmetric encryption algorithms such as ECC. This scheme also resists the majority of attacking behaviours, such as password-guessing attacks and man-in-the-middle attacks. Experimental results verify the time efficiency of this proposed scheme, and its security is analysed as well. (C)& nbsp;2022 Elsevier B.V. All rights reserved.
查看更多>>摘要：Accurate carbon pricing guidance is of great importance for the inhibition of excessive carbon dioxide emissions. Aiming at improving forecast performance, a number of carbon price forecasting models have been proposed based on the combination or multiscale hybrid frameworks. However, most of these hybrid models cannot easily cast a perfect reflection of erratic fluctuation in carbon trading schemes due to lack of judgment on the trend or inaccurate trend reconstruction. In this study, a novel filter-based modeling with Hodrick-Prescott (HP) filter, that can identify repeated up and down structural features around a certain carbon price, negotiates the obstacle of the parallel-series hybridization concerning the linear and the nonlinear model identification. The residual decomposition scheme with adaptive noise is carried out on the random and nonlinear component for error correction to filter-based models. Moreover, Bayesian optimization adjusts the structure of seven single-hidden layer feedforward neural networks (SLFNs) and the inputs to provide the best generalization performance. The proposed filter-hybrid model using kernel extreme learning machine as the final nonlinear integrator has better stability to the parameters, and has the superiority over the parallel-series and allocation-based models from a statistical perspective. Comparing with existing data-driven models, our proposed model is competitive in view of prediction accuracy and time cost in the majority of carbon futures trading cases.(C) 2022 Elsevier B.V. All rights reserved.
查看更多>>摘要：Sine cosine algorithm (SCA), an emerging metaheuristic method, is usually limited by the local convergence and search stagnation defects in multivariable optimization problems. To improve the SCA performance, this study proposes an enhanced sine cosine algorithm (ESCA) using several modified strategies, including the opposition learning strategy for enlarging search range, the adaptive evolution strategy for improving global exploration, the neighborhood search strategy for increasing population diversity, and the greedy selection strategy for guaranteeing solution quality. ESCA and several meta heuristics methods are used to solve a group of numerical optimization problems. The experimental results indicate that in terms of solution efficiency and convergence rate, ESCA outperforms several traditional methods for multivariable parameter optimization problems. Then, several engineering optimization problems are employed to further test the feasibility of the ESCA method in practical applications. The simulations show that for various performance evaluation indexes, ESCA can produce high-quality solutions with better objective values compared to the control methods. Thus, a simple but powerful tool is developed to address the complex multivariable parameter optimization problems.(c) 2022 Elsevier B.V. All rights reserved.
查看更多>>摘要：A protein is a linear chain containing a set of amino acids, which folds on itself to create a specific native structure, called the minimum energy conformation. It is the native structure that determines the functionality of each protein. The Protein Folding Problem (PFP) remains one of the most strenuous computational and chemical biology. The principal challenge of PFP is to predict the optimal conformation of a given protein by considering only its amino acid sequence. Since the conformational space contains a colossal number of possibilities, even when considering short sequences, different simplified models have been developed and applied to make the PFP less complex. Experimental methods can be used to predict the native structure of small and specific proteins. Given the limitations of experimental methods, in the last few years many computational approaches have been proposed to solve the PFP. Based on the folding process, the PFP was formulated as an optimization problem. They are based on simplified lattice models such as the hydrophobic-polar model. In this paper, we present a new Hybrid Cuckoo Search Algorithm (HCSA) to solve the 3D-HP protein folding optimization problem. Our proposed algorithm consists of combining the Cuckoo Search Algorithm (CSA) with the Hill Climbing (HC) algorithm. Simulation results on different benchmark sequences are presented and compared to the state-of-the-art algorithms. (C)& nbsp;2022 Elsevier B.V. All rights reserved.
查看更多>>摘要：Effective decision support systems are very useful management tools in many applied domains. However, such systems are still scarce or even missing in social and medico-social establishments. This study investigates the personalized user project planning problem in French social and medico-social establishments, whose purpose is to optimize the assignment of multi-featured activities and resources to a group of residents or users subject to complex imperative constraints. We focus on the design and implementation of an innovative multi-neighborhood local optimization algorithm that serves as the key component of a decision support system for these establishments. We assess the effectiveness of the proposed approach on realistic data and show comparisons with other approaches including mathematical programming and greedy search. (c) 2022 Elsevier B.V. All rights reserved.
查看更多>>摘要：This paper firstly introduces the idea of interval-valued hesitant Fermatean fuzzy set (IVHFFS). It is one of the significant theoretical and practical features, which derive from the integration of hesitant Fermatean fuzzy set (HFFSs) and interval number. In this study, we firstly present the basic concept, various operations and distance measures of IVHFFSs. Then, based on the operations of IVHFFSs, some aggregation operators (AOs) are proposed for aggregating the interval-valued hesitant Fermatean fuzzy information. Furthermore, some elegant properties of these operators are discussed in detail. To show the applicability, we discuss a decision analysis process on IVHFFSs environment with the help of conventional complex proportional assessment (COPRAS) methodology. Finally, the selection process of desalination technology for treating the feed water is also taken to validate the developed decision analysis procedure on IVHFFSs. This paper considers various criteria and sub-criteria in the assessment procedure and determines the most significant criteria influencing the desalination technology selection process are technical, social, environment and economic criteria, with significance weights of 0.3972, 0.289, 0.1653 and 0.1486, respectively. The work concludes that the reverse osmosis (RO) is the suitable desalination technology under the considered criteria followed by electrodialysis (ED), and multiple-effect distillation (MED). Moreover, the sensitivity investigation and comparative study are presented to verify the robustness and stability of the proposed method. The findings of this study show that the proposed model can suggest more feasible performance while facing several input uncertainties and influencing factors. (c) 2022 Published by Elsevier B.V.
查看更多>>摘要：In this work, the automated scoring of prognostic marker Human Epidermal Growth Factor Receptor-2 (HER2) stained tissue sample is presented. The HER2 challenge dataset is used for the study to score the sample under observation. Two CNN networks viz. the Xception network in a transfer learning framework and a proposed simpler CNN architecture AutoIHCNet, with three convolution blocks and dense layers, are used in this study considering 228 x 288 x 3 input shape. The training parameters viz. optimizers, learning rate, and the number of epochs are varied to have 48 sets of experiments to choose the best training settings. From the whole slide image, representative region of interest (ROI) images are extracted. One ROI image is divided into eight sub-image patches. 2400 patches from 300 training ROI images were extracted and out of these 2130 patches are used for training based on stained tissue regions available in the patch. Statistical decision fusion using mode is performed for collective voting from eight sub-image patches to label the sample image under observation. 100 test images are used from different cases, to avoid any bias, to assess the models. The proposed deep learning architectures are also compared with the ImmunoMembrane application. Average test accuracy and Pearson's correlation coefficient are used to assess the performance of automated approaches compared to ground truth. The performance is assessed in terms of improvement in accuracy from the patch-based score to ROI image-based score as well as final comparison for image-based comparison with ImmunoMembrane on 100 separate test images. The architectures, Xception network as transfer learning and AutoIHCNet, with statistical decision fusion, improved the accuracy from 95% to 97% and 96% to 98% respectively for the patch-based score to ROI image-based score whereas, the state-of-the-art ImmunoMembrane application shows 87% accuracy for the ROI image-based score. (C)& nbsp;2022 Elsevier B.V. All rights reserved.
NSTL
Elsevier