关键词:
Linguistics;Probabilistic logic;Decision making;Uncertainty;Fuzzy sets;Semantics;Electronic mail;Dual linguistic term set;hesitant fuzzy dual linguistic term set;linguistic probabilities;multicriteria decision making;normal cloud model;score function
摘要:
In recent years, some complex linguistic expression techniques with probabilistic information, such as proportional linguistic terms, probabilistic linguistic term sets, have been proposed to describe the uncertainty of opinions and preferences. However, the probability information is expressed as the crisp numbers, which is usually difficult to be estimated and information losses may exist. To capture the inherent fuzziness and vagueness of decision information more comprehensively and accurately, in this article, we introduce a novel concept named dual linguistic term set (DLTS), which consists of two linguistic variables. The DLTS can allow the decision makers to express the probabilistic information by the means of linguistic variables. To describe the hesitant information of the decision makers, a more general concept named hesitant fuzzy DLTS is developed. Afterwards, a multicriteria decision making method with dual linguistic information is proposed based on the normal cloud model. To do so, the DLTS is first transformed into an equivalent two-tuple consisting of two independent normal clouds. Then, new multiplication operation and power operation of normal clouds are defined to obtain the expectation for each attribute value. After aggregating the evaluation information, we further develop a new score function to rank alternatives reasonably. Finally, an illustrative example is given to verify the effectiveness and feasibility of the proposed method, also some comparisons and analyses are provided to show the advantages of the proposed method.
关键词:
Last mile;Passengers and parcels sharing;Share-a-ride;Genetic algorithm;Vehicles booked on-line
摘要:
With the rapid development of e-commerce, last-mile delivery optimization is important for reduction in logistics cost of e-business enterprises. However, the complex road network structure in various cities makes the last-mile delivery more difficult, which shows high research value. To this end, this paper proposes a special kind of share-a-ride problem (SARP), which uses online car-hailing as a carrier to transport passengers to the distribution centre and courier points to pick up and deliver parcels. The dynamics of the problem is described by designing the key points to update the delivery information; by using an improved genetic algorithm (GA), the problem is solved to realize the goal of minimizing the total cost of three participants (i.e. drivers, passengers and courier companies) and the time penalty costs. Eventually, through simulation example and comparison tests based on three sets of data of different scales, the economic applicability of the problem and the effectiveness of the algorithm are validated.
期刊:
TRANSPORTATION RESEARCH PART A-POLICY AND PRACTICE,2021年153:115-129 ISSN:0965-8564
通讯作者:
Liang, Xiao
作者机构:
[Liang, Xiao; Zhang, Tianyu] Beijing Jiaotong Univ, Key Lab Transport Ind Big Data Applicat Technol C, Minist Transport, Beijing 100044, Peoples R China.;[Xie, Meiquan] Cent South Univ Forestry & Technol, Sch Transportat & Logist, Changsha 410004, Peoples R China.;[Jia, Xudong] Calif State Univ Northridge, Coll Engn & Comp Sci, Northridge, CA 91330 USA.;[Jia, Xudong] Wuyi Univ, Div Intelligent Mfg, Jiangmen 529020, Peoples R China.
通讯机构:
[Liang, Xiao] B;Beijing Jiaotong Univ, Key Lab Transport Ind Big Data Applicat Technol C, Minist Transport, Beijing 100044, Peoples R China.
关键词:
Bicycle traffic;Bicycle Level of Service (BLOS);Virtual Reality (VR) method;Symbolic regression;LOS criteria
摘要:
Bicycle Level of Service (BLOS) provides an essential tool for evaluating the operations of low-carbon bicycle facilities and prioritizing investment in new bicycle facilities under various constraints. This study aimed at developing a LOS method for assessing bicycle facilities in the metropolitan areas of China. Using this method, we addressed major challenges in obtaining user ratings of bicycle facilities and captured senses of satisfaction of bike users riding on bicycle facilities. Virtual Reality (VR) technique was introduced to obtain data by creating 120 immersive settings or scenarios for participants. A hundred of bicyclists or participants with a wide range of characters were recruited. These participants were asked to express their senses of satisfaction under predefined physical conditions of bike facilities and traffic conditions. Their Satisfaction Rating Scores (SRS) were documented. The statistical relationships between rider’s feelings and bike facilities/traffic conditions were modeled and verified through a symbolic regression (or an effective deep learning) approach. The model is demonstrated to be reliable in predicting SRS of bicyclists with a high correlation coefficient. This study also developed a set of LOS criteria based on the cumulative distribution of satisfaction scores. These LOS criteria are simple to use and effective in assessing operational performance of existing bicycle facilities and providing decision makers with insightful guidance for planning, designing, and operating new active transportation facilities.
期刊:
Multimedia Tools and Applications,2021年80(7):11291-11312 ISSN:1380-7501
通讯作者:
Wei, Zhanguo
作者机构:
[Li, Meilin; Wei, Zhanguo; Cai, Weiwei] Cent South Univ Forestry & Technol, Sch Logist & Transportat, Changsha 410004, Peoples R China.;[Cai, Weiwei] Changsha Astra Informat Technol Co Ltd, Changsha 410219, Peoples R China.;[Liu, Botao] Cent South Univ, Changsha 410083, Peoples R China.;[Kan, Jiangming] Beijing Forestry Univ, Beijing 100083, Peoples R China.
通讯机构:
[Wei, Zhanguo] C;Cent South Univ Forestry & Technol, Sch Logist & Transportat, Changsha 410004, Peoples R China.
关键词:
Triple-attention mechanism;Hyperspectral image;Residual and dense networks;Bi-directional long-short term memory networks
摘要:
AbstractEach sample in the hyperspectral remote sensing image has high-dimensional features and contains rich spatial and spectral information, which greatly increases the difficulty of feature selection and mining. In view of these difficulties, we propose a novel Triple-attention Guided Residual Dense and BiLSTM networks(TARDB-Net) to reduce redundant features while increasing feature fusion capabilities, which ultimately improves the ability to classify hyperspectral images. First, a novel Triple-attention mechanism is proposed to assign different weights to each feature. Then, the residual network is used to perform the residual operation on the features, and the initial features of the multiple residual blocks and the generated deep residual features are intensively fused, retaining a host number of prior features. And use the bidirectional long short-term memory network to integrate the contextual semantics of deep fusion features. Finally, the classification task is completed by Softmax classifier. Experiments on three hyperspectral datasets—Indian Pines, University of Pavia, and Salinas—show that under 10% of the training samples, the overall accuracy of our method is 87%, 96% and 96%, which is superior to several well-known methods.
关键词:
face emotion;emotion recognition;Multi-layer Interactive;Feature fusion;deep learning;neural networks
摘要:
Understanding human emotions and psychology is a critical step toward realizing artificial intelligence, and correct recognition of facial expressions is essential for judging emotions. However, the differences caused by changes in facial expression are very subtle, and different expression features are less distinguishable, making it difficult for computers to recognize human facial emotions accurately. Therefore, this paper proposes a novel multi-layer interactive feature fusion network model with angular distance loss. To begin, a multi-layer and multi-scale module is designed to extract global and local features of facial emotions in order to capture part of the feature relationships between different scales, thereby improving the model's ability to discriminate subtle features of facial emotions. Second, a hierarchical interactive feature fusion module is designed to address the issue of loss of useful feature information caused by layer-by-layer convolution and pooling of convolutional neural networks. In addition, the attention mechanism is also used between convolutional layers at different levels. Improve the neural network's discriminative ability by increasing the saliency of information about different features on the layers and suppressing irrelevant information. Finally, we use the angular distance loss function to improve the proposed model's inter-class feature separation and intra-class feature clustering capabilities, addressing the issues of large intra-class differences and high inter-class similarity in facial emotion recognition. We conducted comparison and ablation experiments on the FER2013 dataset. The results illustrate that the performance of the proposed MIFAD-Net is 1.02-4.53% better than the compared methods, and it has strong competitiveness.</p>