Search results

Intent detection (ID) and slot filling (SF) are two important tasks in natural language understanding. ID is to identify the main intent of a paragraph of text. The goal of SF is to extract the information that is important to the intent from the input sentence. However, most of the existing methods use sentence-level intention recognition, which has the risk of error propagation, and the relationship between intention recognition and SF is not explicitly modeled. Aiming at this problem, this paper proposes a collaborative model of ID and SF for intelligent spoken language understanding called ID-SF-Fusion.

ID-SF-Fusion uses Bidirectional Encoder Representation from Transformers (BERT) and Bidirectional Long Short-Term Memory (BiLSTM) to extract effective word embedding and context vectors containing the whole sentence information respectively. Fusion layer is used to provide intent–slot fusion information for SF task. In this way, the relationship between ID and SF task is fully explicitly modeled. This layer takes the result of ID and slot context vectors as input to obtain the fusion information which contains both ID result and slot information. Meanwhile, to further reduce error propagation, we use word-level ID for the ID-SF-Fusion model. Finally, two tasks of ID and SF are realized by joint optimization training.

We conducted experiments on two public datasets, Airline Travel Information Systems (ATIS) and Snips. The results show that the Intent ACC score and Slot F1 score of ID-SF-Fusion on ATIS and Snips are 98.0 per cent and 95.8 per cent, respectively, and the two indicators on Snips dataset are 98.6 per cent and 96.7 per cent, respectively. These models are superior to slot-gated, SF-ID NetWork, stack-Prop and other models. In addition, ablation experiments were performed to further analyze and discuss the proposed model.

This paper uses word-level intent recognition and introduces intent information into the SF process, which is a significant improvement on both data sets.

In the COVID-19 era, sign language (SL) translation has gained attention in online learning, which evaluates the physical gestures of each student and bridges the communication gap between dysphonia and hearing people. The purpose of this paper is to devote the alignment between SL sequence and nature language sequence with high translation performance.

SL can be characterized as joint/bone location information in two-dimensional space over time, forming skeleton sequences. To encode joint, bone and their motion information, we propose a multistream hierarchy network (MHN) along with a vocab prediction network (VPN) and a joint network (JN) with the recurrent neural network transducer. The JN is used to concatenate the sequences encoded by the MHN and VPN and learn their sequence alignments.

We verify the effectiveness of the proposed approach and provide experimental results on three large-scale datasets, which show that translation accuracy is 94.96, 54.52, and 92.88 per cent, and the inference time is 18 and 1.7 times faster than listen-attend-spell network (LAS) and visual hierarchy to lexical sequence network (H2SNet) , respectively.

In this paper, we propose a novel framework that can fuse multimodal input (i.e. joint, bone and their motion stream) and align input streams with nature language. Moreover, the provided framework is improved by the different properties of MHN, VPN and JN. Experimental results on the three datasets demonstrate that our approaches outperform the state-of-the-art methods in terms of translation accuracy and speed.

The Chinese housing market has witnessed rapid growth during the past decade and the significance of housing price forecasting has undoubtedly elevated, becoming an important issue to investors and policymakers. This study aims to examine neural networks (NNs) for office property price index forecasting from 10 major Chinese cities for July 2005–April 2021.

The authors aim at building simple and accurate NNs to contribute to pure technical forecasts of the Chinese office property market. To facilitate the analysis, the authors explore different model settings over algorithms, delays, hidden neurons and data-spitting ratios.

The authors reach a simple NN with three delays and three hidden neurons, which leads to stable performance of about 1.45% average relative root mean square error across the 10 cities for the training, validation and testing phases.

The results could be used on a standalone basis or combined with fundamental forecasts to form perspectives of office property price trends and conduct policy analysis.

Based on conservation of resources (COR) theory, this study aims to examine the impact of daily illegitimate tasks on employees' daily silence and daily voice behavior, as well as the mediating role of daily ego depletion and the moderating role of trait mindfulness.

Through daily diary approach, 81 employees were followed for 10 consecutive workdays. Multilevel analysis was employed to examine the hypothesized relationships.

The results showed that daily illegitimate tasks are positively related to daily silence behavior and negatively related to daily voice behavior; daily ego depletion plays a mediating role in these relationships. Trait mindfulness moderates the effect of daily illegitimate tasks on daily ego depletion and the indirect effect of daily illegitimate tasks on daily silence and daily voice.

Managers should be mindful of minimizing the assignment of illegitimate tasks. Additionally, it is recommended that the organization provide training courses for employees to help them reduce ego depletion. Finally, organizations should focus on fostering high levels of mindfulness among their employees.

This study contributes to the existing literature by investigating the immediate impact of illegitimate tasks on employee voice and silence at within-person level. By doing so, it enhances comprehension of the consequences associated with illegitimate tasks. Meanwhile, this study offers additional insights into the underlying mechanisms and boundary conditions of the effect of illegitimate tasks from a resource perspective.

The purpose of this paper is to develop a coupled lattice Boltzmann model for the simulation of the freezing process in unsaturated porous media.

In the developed model, the porous structure with complexity and disorder was generated by using a stochastic growth method, and then the Shan-Chen multiphase model and enthalpy-based phase change model were coupled by introducing a freezing interface force to describe the variation of phase interface. The pore size of porous media in freezing process was considered as an influential factor to phase transition temperature, and the variation of the interfacial force formed with phase change on the interface was described.

The larger porosity (0.2 and 0.8) will enlarge the unfrozen area from 42 mm to 70 mm, and the rest space of porous medium was occupied by the solid particles. The larger specific surface area (0.168 and 0.315) has a more fluctuated volume fraction distribution.

The concept of interfacial force was first introduced in the solid–liquid phase transition to describe the freezing process of frozen soil, enabling the formulation of a distribution equation based on enthalpy to depict the changes in the water film. The increased interfacial force serves to diminish ice formation and effectively absorb air during the freezing process. A greater surface area enhances the ability to counteract liquid migration.

This study aims to investigate consumers’ intention to use onsite restaurant interactive self-service technology (ORISST) using a modified value attitude-behavior model. To extend the understanding of how consumers’ dining value focus could influence their intention to use ORISST, this study examines the conditional indirect effects of restaurant type (quick-service vs fine-dining) within the proposed model.

An online survey was developed and distributed to randomly selected respondents in the USA. A total of 588 (quick-service: 295; fine-dining: 293) responses were used for the data analysis. Structural equation modeling with a robust maximum likelihood method was used to examine the proposed model. To investigate the moderated effects of restaurant type, a latent moderated mediation model was used.

The results showed that consumers’ value perceptions toward technology use in restaurants influenced their intention to use ORISST via both hedonic and utilitarian expectations. Latent moderated mediation analyzes revealed that the mediation effect of hedonic expectation between perceived value and the intention was stronger in fine-dining than in quick-service restaurants.

This study extends the understanding of consumer intentions to use interactive self-service technology in restaurants by building on a model that is customer-oriented instead of tech-specific. Furthermore, the conditional effects of restaurant type are investigated using the latent moderated structural equation method. The findings of this study provide guidelines for managers of quick-service and fine-dining restaurants to better incorporate ORISST in their restaurants, to boost customer experiences and to increase operational efficiency.

The coupling process between the loading mechanism and the tank car mouth is a crucial step in the tank car loading process. The purpose of this paper is to design a method to accurately measure the pose of the tanker car.

The collected image is first subjected to a gray enhancement operation, and the black parts of the image are extracted using Otsu’s threshold segmentation and morphological processing. The edge pixels are then filtered to remove outliers and noise, and the remaining effective points are used to fit the contour information of the tank car mouth. Using the successfully extracted contour information, the pose information of the tank car mouth in the camera coordinate system is obtained by establishing a binocular projection elliptical cone model, and the pixel position of the real circle center is obtained through the projection section. Finally, the binocular triangulation method is used to determine the position information of the tank car mouth in space.

Experimental results have shown that this method for measuring the position and orientation of the tank car mouth is highly accurate and can meet the requirements for industrial loading accuracy.

A method for extracting the contours of various types of complex tanker mouth is proposed. This method can accurately extract the contour of the tanker mouth when the contour is occluded or disturbed. Based on the binocular elliptic conical model and perspective projection theory, an innovative method for measuring the pose of the tanker mouth is proposed, and according to the space characteristics of the tanker mouth itself, the ambiguity of understanding is removed. This provides a new idea for the automatic loading of ash tank cars.

The purpose of this paper is to describe the design and development of “Pylon-Climber II”, a 5-DOF biped climbing robot (degree of freedom – DOF) for moving on the external surface of a tower and assisting the electricians to complete some maintenance tasks.

The paper introduces a pole-climbing robot, which consists of a 5-DOF mechanical arm and two novel grippers. The gripper is composed of a two-finger clamping module and a retractable L-shaped hook module. The robot is symmetrical in structure, and the rotary joint for connecting two arms is driven by a linear drive mechanism.

The developed prototype proved a new approach for the inspection and maintenance of the electricity pylon. The gripper can reliably grasp the angle bars with different specifications by using combined movement of the two-finger clamping module and the retractable L-shaped hook module and provide sufficient adhesion force for the Pylon-Climber II.

The clamping experiments of the gripper and the climbing experiments of the robot were carried out on a test tower composed of some angle bars with different specification.

This paper includes the design and development of a 5-DOF biped climbing robot for electricity pylon maintenance. The climbing robot can move on the external surface of the electric power tower through grasping the angle bar alternatively. The gripper that is composed of a two-finger gripping module and a retractable L-shaped hook module is very compact and can provide reliable adhesion force for the climbing robot.

The coal-fired power plants have been confronted with new operation challenge since the unified carbon trading market was launched in China. To make the optimal decision for the carbon emissions and power production has already been an important subject for the plants. Most of the previous studies only considered the market prices of electricity and coal to optimize the generation plan. However, with the opening of the carbon trading market, carbon emission has become a restrictive factor for power generation. By introducing the carbon-reduction target in the production decision, this study aims to achieve both the environmental and economic benefits for the coal-fired power plants to positively deal with the operational pressure.

A dynamic optimization approach with both long- and short-term decisions was proposed in this study to control the carbon emissions and power production. First, the operation rules of carbon, electricity and coal markets are analyzed, and a two-step decision-making algorithm for annual and weekly production is presented. Second, a production profit model based on engineering constraints is established, and a greedy heuristics algorithm is applied in the Gurobi solver to obtain the amounts of weekly carbon emission, power generation and coal purchasing. Finally, an example analysis is carried out with five generators of a coal-fired power plant for illustration.

The results show that the joint information of the multiple markets of carbon, electricity and coal determines the real profitability of power production, which can assist the plants to optimize their production and increase the profits. The case analyses demonstrate that the carbon emission is reduced by 2.89% according to the authors’ method, while the annual profit is improved by 1.55%.

As an important power producer and high carbon emitter, coal-fired power plants should actively participate in the carbon market. Rather than trade blindly at the end of the agreement period, they should deeply associate the prices of carbon, electricity and coal together and realize optimal management of carbon emission and production decision efficiently.

This paper offers an effective method for the coal-fired power plant, which is struggling to survive, to manage its carbon emission and power production optimally.

Despite the importance of tourism ethnocentrism in emerging tourism destinations, there is limited, but growing, research interest in this area. This study aims to respond to current calls for investigating mechanisms that can promote tourism ethnocentrism in both emerging and developed tourism destinations.