For any organization, personnel selection is regarded as one of the most critical and complex issues in human resource management. Due to the fuzziness and ambiguity in personnel selection, it was ...usually tackled by utilizing multi-criteria decision-making (MCDM) methods. Previously developed MCDM methods for personnel selection have principally depended on experts’ preferences, which may lead to the bias and deviation caused by human cognitive limitations. With the development of information technology, many human resource (HR) data have accumulated within some organizations, making it possible to discover meaningful patterns in HR data based on data analytics algorithms (DAAs). These patterns do not depend on experts’ judgement and can objectively reflect the performance of personnel in several aspects. Thus, it is promising that integrating objective patterns obtained from HR data and experts’ judgement can make personnel selection more systematic and scientific. To tackle this complex scenario, we propose a data-driven decision-making framework that combines DAAs and MCDM method. The proposed framework can explore the underlying patterns in HR data and also consider experts’ judgement during the selection process. In this framework, a data-driven competency-based method is designed to mine out valuable information in HR data. In addition, for assisting multiple experts, a linear group best–worst method (LGBWM) is proposed to calculate the weights of criteria, and intuitionistic fuzzy numbers (IFNs) are used to help experts express their preferences. A personnel evaluation and selection (PLEAS) decision support system is also designed and developed to implement the framework better. In order to illustrate the effectiveness of the proposed framework, a real-world case is conducted in a Chinese state-owned company, and the results demonstrate that our proposed framework is valid for solving data-driven personnel selection problems.
•In this paper, a three-stage decision-making framework which combines data analytics algorithms (DAAs) and multi-criteria decision-making (MCDM) method is proposed to solve data-driven personnel selection problem.•In the first stage, in order to discover the behavior patterns of employees and determine the evaluation criteria in personnel selection, a data-driven competency-based method is designed.•In the second stage, for the preliminary screening of candidates, an improved ranking aggregation algorithm based on graph is proposed.•In the last stage, an integrated MCDM method based on linear group best–worst method (LGBWM) and intuitionistic fuzzy numbers (IFNs) is designed to help decision-makers express their preferences in group decision-making.•A decision support system named PLEAS is developed for the implementation of our methodology, and a case of personnel selection is also conducted to verify the proposed framework.
Single image dehazing is a difficult problem because of its ill-posed nature. Increasing attention has been paid recently as its high potential applications in many visual tasks. Although single ...image dehazing has made remarkable progress in recent years, they are mainly designed for haze removal in daytime. In nighttime, dehazing is more challenging where most daytime dehazing methods become invalid due to multiple scattering phenomena, and non-uniformly distributed dim ambient illumination. While a few approaches have been proposed for nighttime image dehazing, low ambient light is actually ignored. In this paper, we propose a novel unified nighttime hazy image enhancement framework to address the problems of both haze removal and illumination enhancement simultaneously. Specifically, both halo artifacts caused by multiple scattering and non-uniformly distributed ambient illumination existing in low-light hazy conditions are considered for the first time in our approach. More importantly, most current daytime dehazing methods can be effectively incorporated into nighttime dehazing task based on our framework. Firstly, we decompose the observed hazy image into a halo layer and a scene layer to remove the influence of multiple scattering. After that, we estimate the spatially varying ambient illumination based on the Retinex theory. We then employ the classic daytime dehazing methods to recover the scene radiance. Finally, we generate the dehazing result by combining the adjusted ambient illumination and the scene radiance. Compared with various daytime dehazing methods and the state-of-the-art nighttime dehazing methods, both quantitative and qualitative experimental results on both real-world and synthetic hazy image datasets demonstrate the superiority of our framework in terms of halo mitigation, visibility improvement and color preservation.
Over the past decade, deep learning techniques have significantly advanced the field of building change detection in remote sensing imagery. However, existing deep learning-based approaches often ...encounter limitations in complex remote sensing scenarios, resulting in false detections and detail loss. This paper introduces EFP-Net, a novel building change detection approach that resolves the mentioned issues by utilizing effective feature fusion and foreground perception. EFP-Net comprises three main modules, the feature extraction module (FEM), the spatial–temporal correlation module (STCM), and the residual guidance module (RGM), which jointly enhance the fusion of bi-temporal features and hierarchical features. Specifically, the STCM utilizes the temporal change duality prior and multi-scale perception to augment the 3D convolution modeling capability for bi-temporal feature variations. Additionally, the RGM employs the higher-layer prediction map to guide shallow layer features, reducing the introduction of noise during the hierarchical feature fusion process. Furthermore, a dynamic Focal loss with foreground awareness is developed to mitigate the class imbalance problem. Extensive experiments on the widely adopted WHU-BCD, LEVIR-CD, and CDD datasets demonstrate that the proposed EFP-Net is capable of significantly improving accuracy in building change detection.
Autonomy increases the ability of earth observing satellites by allowing them to acquire more images. This is enabled by an efficient planning and scheduling algorithm which is able to make quick ...decisions onboard. Due to the NP-hardness of the agile earth observing satellite (AEOS) onboard scheduling problem, heuristic and metaheuristic algorithms seem to be appropriate to cope with increasingly enlarged problems. Also, the algorithms need to be intelligent enough to deal with dynamically changing situations onboard. Such algorithms are missing in the literature and we make the first attempt to propose a learning-based approach (LBA) for the AEOS onboard scheduling problem. LBA adopts an offline training - onboard scheduling paradigm where it trains a classifier using massive historical data offline on the ground and embeds this classifier to an onboard greedy construction algorithm. At each construction step, the greedy algorithm uses the classifier to test the potential of a task and arranges its observation time if it is accepted by the classifier. Extensive experimental results show that the proposed LBA is highly suitable for onboard use in terms of both solution quality and response time. In particular, LBA easily dominates state-of-the-art algorithms by producing very high quality solutions for large-size problems (with over 100 tasks) in seconds.
Despite wide‐temperature tolerance and high‐voltage compatibility, employing propylene carbonate (PC) as electrolyte in lithium‐ion batteries (LIBs) is hampered by solvent co‐intercalation and ...graphite exfoliation due to incompetent solvent‐derived solid electrolyte interphase (SEI). Herein, trifluoromethylbenzene (PhCF3), featuring both specific adsorption and anion attraction, is utilized to regulate the interfacial behaviors and construct anion‐induced SEI at low Li salts’ concentration (<1 m). The adsorbed PhCF3, showing surfactant effect on graphite surface, induces preferential accumulation and facilitated decomposition of bis(fluorosulfonyl)imide anions (FSI−) based on the adsorption–attraction–reduction mechanism. As a result, PhCF3 successfully ameliorates graphite exfoliation‐induced cell failure in PC‐based electrolyte and enables the practical operation of NCM613/graphite pouch cell with high reversibility at 4.35 V (96% capacity retention over 300 cycles at 0.5 C). This work constructs stable anion‐derived SEI at low concentration of Li salt by regulating anions–co‐solvents interaction and electrode/electrolyte interfacial chemistries.
Trifluoromethylbenzene (PhCF3), as surfactant, is introduced into propylene carbonate (PC)‐based electrolyte to regulate interfacial behaviors in lithium‐ion batteries. The adsorbed PhCF3 on graphite surface facilitates bis(fluorosulfonyl)imide anions’ (FSI−) accumulation and decomposition at graphite/electrolyte interface through the adsorption–attraction–reduction mechanism. As a result, the graphite is kinetically stabilized in medium‐concentrated PC electrolyte with high reversibility.
In electrical impedance tomography (EIT), the uncertainty of conductivity distribution may cause the uncertainty in the forward calculation and further affect the inverse problem. In this paper, an ...improved univariate dimension reduction method based on deep neural network (DNN-UDR) is proposed for the high-dimensional uncertainty quantification in EIT forward problem. Firstly, DNN is studied to build a substitute model for EIT forward problem in order to solve the high-dimensional problem. Three normalized circular finite element models are established with random uniform conductivity distribution. Then UDR is used to analyze and quantify the uncertainty in the simulation with the form of probability. Compared with Monte Carlo simulation (MCS), the probability distribution of voltage is fitted, and the quantification indicators such as mean, variance, variation coefficient and covariance, are also consistent. On the other hand, with the increase of parameter dimensions, DNN-UDR accelerates the computations obviously. This indicates that DNN-UDR is effective and has high structural stability, accurate prediction results and high computational efficiency.
Earth observation satellites (EOSs) are taking a large number of pictures with increasing resolution which produce massive image data. Satellite data transmission becomes the bottleneck part in the ...process of EOS resource management. In this paper, we study the earth observation satellite integrated scheduling problem (EOSIS) where the imaging activities and download activities are considered integratively. We propose an integer linear programming model to formulate the problem. Due to the NP-hardness of the problem, we propose an efficient local search heuristic (ELSH) to solve problems of large size. ELSH uses a dedicated local search method to guarantee algorithm performance and efficient constraint handling mechanisms to guarantee algorithm efficiency. Numerical experimental results show that the algorithm demonstrates excellent performance on a set of benchmark instances. The ELSH achieves optimal results for all small-size instances (with 50 targets, two satellites, and three ground stations), and is very robust for large instances with up to 2000 targets. Moreover, the proposed ELSH easily dominates the state-of-the-art algorithm.
A sub-regional and multilevel ceramic valve spool (CVS) surface defects algorithm is proposed to improve the adaptation of the existing surface defect detection algorithm and reduce missing rate. ...According to the different reflectivities in CVS surface, the surface was divided into two regions: polished surface (P) and non-polished surface (Non P), by the characteristics of CVS surface defect, it was divided into two types of defect: G defects and C defects. The P region and Non P region are extracted by searching template image pyramid information, adjusting the target grey-scale image position and posture, regional registration. The defects of the P region and Non P region are extracted by blob detection and crack detection. Through experimental research, the feasibility and applicability of the detection algorithm were verified. The experimental results showed that the detection algorithm was suitable for different types of CVS surface defects, and the missing rate was low, and it can improve the detection efficiency through the reasonable setting of priority.
Most early research on route choice behavior analysis relied on the data collected from the stated preference survey or through small-scale experiments. This manuscript focused on the understanding ...of commuters’ route choice behavior based on the massive amount of trajectory data collected from occupied taxicabs. The underlying assumption was that travel behavior of occupied taxi drivers can be considered as no different than the well-experienced commuters. To this end, the DBSCAN algorithm and Akaike information criterion (AIC) were first used to classify trips into different categories based on the trip length. Next, a total of 9 explanatory variables were defined to describe the route choice behavior, and and the path size (PS) logit model was then built, which avoided the invalid assumption of independence of irrelevant alternatives (IIA) in the commonly seen multinomial logit (MNL) model. The taxi trajectory data from over 11,000 taxicabs in Xi’an, China, with 40 million trajectory records each day were used in the case study. The results confirmed that commuters’ route choice behavior are heterogenous for trips with varying distances and that considering such heterogeneity in the modeling process would better explain commuters’ route choice behaviors, when compared with the traditional MNL model.
In the past few decades, applications of geostationary orbit (GEO) satellites have attracted increasing attention, and with the development of optical technologies, GEO optical satellites have become ...popular worldwide. This paper proposes a general working pattern for a GEO optical satellite, as well as a target observation mission planning model. After analyzing the requirements of users and satellite control agencies, two objectives are simultaneously considered: maximization of total profit and minimization of satellite attitude maneuver angle. An NSGA-II based multi-objective optimization algorithm is proposed, which contains some heuristic principles in the initialization phase and mutation operator, and is embedded with a traveling salesman problem (TSP) optimization. The validity and performance of the proposed method are verified by extensive numerical simulations that include several types of point target distributions.