Search results

This paper aims to address the following issues: (1) most existing methods are based on recurrent network, which is time-consuming to train long sequences due to not allowing for full parallelism; (2) personalized preference generally are not considered reasonably; (3) existing methods rarely systematically studied how to efficiently utilize various auxiliary information (e.g. user ID and time stamp) in trajectory data and the spatiotemporal relations among nonconsecutive locations.

The authors propose a novel self-attention network–based model named SanMove to predict the next location via capturing the long- and short-term mobility patterns of users. Specifically, SanMove uses a self-attention module to capture each user's long-term preference, which can represent her personalized location preference. Meanwhile, the authors use a spatial-temporal guided noninvasive self-attention (STNOVA) module to exploit auxiliary information in the trajectory data to learn the user's short-term preference.

The authors evaluate SanMove on two real-world datasets. The experimental results demonstrate that SanMove is not only faster than the state-of-the-art recurrent neural network (RNN) based predict model but also outperforms the baselines for next location prediction.

The authors propose a self-attention-based sequential model named SanMove to predict the user's trajectory, which comprised long-term and short-term preference learning modules. SanMove allows full parallel processing of trajectories to improve processing efficiency. They propose an STNOVA module to capture the sequential transitions of current trajectories. Moreover, the self-attention module is used to process historical trajectory sequences in order to capture the personalized location preference of each user. The authors conduct extensive experiments on two check-in datasets. The experimental results demonstrate that the model has a fast training speed and excellent performance compared with the existing RNN-based methods for next location prediction.

This paper presents a survey of research into interactive robotic systems for the purpose of identifying the state of the art capabilities as well as the extant gaps in this emerging field. Communication is multimodal. Multimodality is a representation of many modes chosen from rhetorical aspects for its communication potentials. The author seeks to define the available automation capabilities in communication using multimodalities that will support a proposed Interactive Robot System (IRS) as an AI mounted robotic platform to advance the speed and quality of military operational and tactical decision making.

This review will begin by presenting key developments in the robotic interaction field with the objective of identifying essential technological developments that set conditions for robotic platforms to function autonomously. After surveying the key aspects in Human Robot Interaction (HRI), Unmanned Autonomous System (UAS), visualization, Virtual Environment (VE) and prediction, the paper then proceeds to describe the gaps in the application areas that will require extension and integration to enable the prototyping of the IRS. A brief examination of other work in HRI-related fields concludes with a recapitulation of the IRS challenge that will set conditions for future success.

Using insights from a balanced cross section of sources from the government, academic, and commercial entities that contribute to HRI a multimodal IRS in military communication is introduced. Multimodal IRS (MIRS) in military communication has yet to be deployed.

Multimodal robotic interface for the MIRS is an interdisciplinary endeavour. This is not realistic that one can comprehend all expert and related knowledge and skills to design and develop such multimodal interactive robotic interface. In this brief preliminary survey, the author has discussed extant AI, robotics, NLP, CV, VDM, and VE applications that is directly related to multimodal interaction. Each mode of this multimodal communication is an active research area. Multimodal human/military robot communication is the ultimate goal of this research.

A multimodal autonomous robot in military communication using speech, images, gestures, VST and VE has yet to be deployed. Autonomous multimodal communication is expected to open wider possibilities for all armed forces. Given the density of the land domain, the army is in a position to exploit the opportunities for human–machine teaming (HMT) exposure. Naval and air forces will adopt platform specific suites for specially selected operators to integrate with and leverage this emerging technology. The possession of a flexible communications means that readily adapts to virtual training will enhance planning and mission rehearsals tremendously.

Interaction, perception, cognition and visualization based multimodal communication system is yet missing. Options to communicate, express and convey information in HMT setting with multiple options, suggestions and recommendations will certainly enhance military communication, strength, engagement, security, cognition, perception as well as the ability to act confidently for a successful mission.

The objective is to develop a multimodal autonomous interactive robot for military communications. This survey reports the state of the art, what exists and what is missing, what can be done and possibilities of extension that support the military in maintaining effective communication using multimodalities. There are some separate ongoing progresses, such as in machine-enabled speech, image recognition, tracking, visualizations for situational awareness, and virtual environments. At this time, there is no integrated approach for multimodal human robot interaction that proposes a flexible and agile communication. The report briefly introduces the research proposal about multimodal interactive robot in military communication.

Background: The annual average daily traffic (AADT) data from road segments are critical for roadway projects, especially with the decision-making processes about operations, travel demand, safety-performance evaluation, and maintenance. Regular updates help to determine traffic patterns for decision-making. Unfortunately, the luxury of having permanent recorders on all road segments, especially low-volume roads, is virtually impossible. Consequently, insufficient AADT information is acquired for planning and new developments. A growing number of statistical, mathematical, and machine-learning algorithms have helped estimate AADT data values accurately, to some extent, at both sampled and unsampled locations on low-volume roadways. In some cases, roads with no representative AADT data are resolved with information from roadways with similar traffic patterns.

Methods: This study adopted an integrative approach with a combined systematic literature review (SLR) and meta-analysis (MA) to identify and to evaluate the performance, the sources of error, and possible advantages and disadvantages of the techniques utilized most for estimating AADT data. As a result, an SLR of various peer-reviewed articles and reports was completed to answer four research questions.

Results: The study showed that the most frequent techniques utilized to estimate AADT data on low-volume roadways were regression, artificial neural-network techniques, travel-demand models, the traditional factor approach, and spatial interpolation techniques. These AADT data-estimating methods' performance was subjected to meta-analysis. Three studies were completed: R squared, root means square error, and mean absolute percentage error. The meta-analysis results indicated a mixed summary effect: 1. all studies were equal; 2. all studies were not comparable. However, the integrated qualitative and quantitative approach indicated that spatial-interpolation (Kriging) methods outperformed the others.

Conclusions: Spatial-interpolation methods may be selected over others to generate accurate AADT data by practitioners at all levels for decision making. Besides, the resulting cross-validation statistics give statistics like the other methods' performance measures.

The study is carried out to analytically reconnoiter geotechnical index properties of subgrade soils as key variables that shape the cost profile of road infrastructure projects in a tropical geographic setting with starkly heterogenous ground conditions.

Using the Niger Delta region, as a point of reference, data on geotechnical index properties of subgrade soils at spatially dispersed locations for 61 completed highway projects are collated. Exploratory statistical tests were carried out to infer significant associations with final project costs before regression analysis. Regression analysis is principally deployed as an explanatory analytical tool, relevant to quantify the sensitivity of highway project costs to the individual and collective impact of geotechnical variables.

Several parameters of expansivity and compressibility exhibited significantly strong associations with the final costs recorded on the highway projects. The statistical analysis further established a cause-effect relationship, whereby small changes in the geotechnical properties of sub-grade soils at project locations, would result in disproportionately large changes in the cost of road construction.

The study findings provide insight into the sensitivity of road construction costs to geotechnical variables, which can serve as a useful input in financial risk analysis for development appraisal and the generation of location adjustment factors.

The study statistically demonstrates location-induced construction cost profiles, triggered in response to the spatial geotechnical variability and occurrence of problem subgrade soils in the humid tropics, which may be different from those traditionally established in studies of cold and temperate climate soils.

The multisource uncertainties, including material dispersion, load fluctuation and geometrical tolerance, have crucial effects on fatigue performance of turbine bladed disks. In view of the aim of this paper, it is essential to develop an advanced approach to efficiently quantify their influences and evaluate the fatigue life of turbine bladed disks.

In this study, a novel combined machine learning strategy is performed to fatigue assessment of turbine bladed disks. Proposed model consists of two modeling phases in terms of response surface method (RSM) and support vector regression (SVR), namely RSM-SVR. Two different input sets obtained from basic variables were used as the inputs of RSM, then the predicted results by RSM in first phase is used as inputs of SVR model by using a group data-handling strategy. By this way, the nonlinear flexibility of SVR inputs is improved and RSM-SVR model presents the high-tendency and efficiency characteristics.

The accuracy and tendency of the RSM-SVR model, applied to the fatigue life estimation of turbine bladed disks, are validated. The results indicate that the proposed model is capable of accurately simulating the nonlinear response of turbine bladed disks under multisource uncertainties, and SVR-RSM model provides an accurate prediction strategy compared to RSM and SVR for fatigue analysis of complex structures.

The results indicate that the proposed model is capable of accurately simulate the nonlinear response of turbine bladed disks under multisource uncertainties, and SVR-RSM model provides an accurate prediction compared to RSM and SVRE for fatigue analysis of turbine bladed disk.

This study aims to investigate the current state of research using deep learning methods for text classification in the tourism and hospitality field and to propose specific guidelines for future research.

This study undertakes a qualitative and critical review of studies that use deep learning methods for text classification in research fields of tourism and hospitality and computer science. The data was collected from the Web of Science database and included studies published until February 2022.

Findings show that current research has mainly focused on text feature classification, text rating classification and text sentiment classification. Most of the deep learning methods used are relatively old, proposed in the 20th century, including feed-forward neural networks and artificial neural networks, among others. Deep learning algorithms proposed in recent years in the field of computer science with better classification performance have not been introduced to tourism and hospitality for large-scale dissemination and use. In addition, most of the data the studies used were from publicly available rating data sets; only two studies manually annotated data collected from online tourism websites.

The applications of deep learning algorithms and data in the tourism and hospitality field are discussed, laying the foundation for future text mining research. The findings also hold implications for managers regarding the use of deep learning in tourism and hospitality. Researchers and practitioners can use methodological frameworks and recommendations proposed in this study to perform more effective classifications such as for quality assessment or service feature extraction purposes.

The paper provides an integrative review of research in text classification using deep learning methods in the tourism and hospitality field, points out newer deep learning methods that are suitable for classification and identifies how to develop different annotated data sets applicable to the field. Furthermore, foundations and directions for future text classification research are set.

The goal of this work is to create a computational finite element model to perform thermoelastic stress analysis (TSA) with the usage of a non-ideal load frequency, containing the effects of the material thermal properties.

Throughout this document, the methodology of the model is presented first, followed by the procedure and results. The last part is reserved to results, discussion and conclusions.

This work had the main goal to create a model to perform TSA with the usage of non-ideal loading frequencies, considering the materials’ thermal properties. Loading frequencies out of the ideal range were applied and the model showed capable of good results. The created model reproduced acceptably the TSA, with the desired conditions.

This work creates a model to perform TSA with the usage of non-ideal loading frequencies, considering the materials’ thermal properties.

In a boundary layer ingestion (BLI) propulsion system, the fan operates continuously under distorted inflow conditions, leading to an increment of aerodynamic loss and in turn impacting the potential fuel burn reduction of the aircraft. Usually, in the preliminary design stage of a BLI propulsion system, it is essential to assess the impact of fuselage boundary layer fluids on fan aerodynamic performances under various flight conditions. However, the hub region flow loss is one of the major loss sources in a fan and would greatly influence the fan performances. Moreover, the inflow distortion also results in a complex and highly nonlinear mapping relation between loss and local physical parameters. It will diminish the prediction accuracy of the commonly used low-fidelity computational approaches which often incorporate traditional physics-based loss models, reducing the reliability of these approaches in evaluating fan performances. Meanwhile, the high-fidelity full-annulus unsteady Reynolds-averaged Navier–Stokes (URANS) approach, even though it can give rather accurate loss predictions, is extremely time-consuming. This study aims to develop a fast and accurate hub loss prediction method for a BLI fan under distorted inflow conditions.

This paper develops a data-driven hub loss prediction method for a BLI fan under distorted inflows. To improve the prediction accuracy and applicability, physical understandings of hub flow features are integrated into the modeling process. Then, the key physical parameters related to flow loss are screened by conducting a sensitivity analysis of influencing parameters. Next, a quasi-steady assumption of flow is made to generate a training sample database, reducing the computational time by acquiring one single sample from the highly time-consuming full-annulus URANS approach to a cost-efficient single-blade-passage approach. Finally, a radial basis function neural network is used to establish a surrogate model that correlates the input parameters and the output loss.

The data-driven hub loss model shows higher prediction accuracy than the traditional physics-based loss models. It can accurately capture the circumferentially and radially nonuniform variation trends of the losses and the associated absolute magnitudes in a BLI fan under different blade load, inlet distortion intensity and rotating speed conditions. Compared with the high-fidelity full-annulus URANS results, the averaged relative prediction errors of the data-driven hub loss model are kept less than 10%.

The originality of this paper lies in developing a new method for predicting flow loss in a BLI fan rotor blade hub region. This method offers higher prediction accuracy than the traditional loss models and lower computational time cost than the full-annulus URANS approach, which could realize fast evaluations of fan aerodynamic performances and provide technical support for designing high-performance BLI fans.

The purpose is twofold. First, this study aims to establish that black box tree-based machine learning (ML) models have better predictive performance than a standard linear regression (LR) hedonic model for rent prediction. Second, it shows the added value of analyzing tree-based ML models with interpretable machine learning (IML) techniques.

Data on Belgian residential rental properties were collected. Tree-based ML models, random forest regression and eXtreme gradient boosting regression were applied to derive rent prediction models to compare predictive performance with a LR model. Interpretations of the tree-based models regarding important factors in predicting rent were made using SHapley Additive exPlanations (SHAP) feature importance (FI) plots and SHAP summary plots.

Results indicate that tree-based models perform better than a LR model for Belgian residential rent prediction. The SHAP FI plots agree that asking price, cadastral income, surface livable, number of bedrooms, number of bathrooms and variables measuring the proximity to points of interest are dominant predictors. The direction of relationships between rent and its factors is determined with SHAP summary plots. In addition to linear relationships, it emerges that nonlinear relationships exist.

Rent prediction using ML is relatively less studied than house price prediction. In addition, studying prediction models using IML techniques is relatively new in real estate economics. Moreover, to the best of the authors’ knowledge, this study is the first to derive insights of driving determinants of predicted rents from SHAP FI and SHAP summary plots.

Internet of things (IoT) is essential in technical, social and economic domains, but there are many challenges that researchers are continuously trying to solve. Traditional resource allocation methods in IoT focused on the optimal resource selection process, but the energy consumption for allocating resources is not considered sufficiently. This paper aims to propose a resource allocation technique aiming at energy and delay reduction in resource allocation. Because of the non-deterministic polynomial-time hard nature of the resource allocation issue and the forest optimization algorithm’s success in complex problems, the authors used this algorithm to allocate resources in IoT.

For the vast majority of IoT applications, energy-efficient communications, sustainable energy supply and reduction of latency have been major goals in resource allocation, making operating systems and applications more efficient. One of the most critical challenges in this field is efficient resource allocation. This paper has provided a new technique to solve the mentioned problem using the forest optimization algorithm. To simulate and analyze the proposed technique, the MATLAB software environment has been used. The results obtained from implementing the proposed method have been compared to the particle swarm optimization (PSO), genetic algorithm (GA) and distance-based algorithm.

Simulation results show that the proper performance of the proposed technique. The proposed method, in terms of “energy” and “delay,” is better than other ones (GA, PSO and distance-based algorithm).

The paper presents a useful method for improving resource allocation methods. The proposed method has higher efficiency compared to the previous methods. The MATLAB-based simulation results have indicated that energy consumption and delay have been improved compared to other algorithms, which causes the high application of this method in practical projects. In the future, the focus will be on resource failure and reducing the service level agreement violation rate concerning the number of resources.

The proposed technique can solve the mentioned problem in the IoT with the best resource utilization, low delay and reduced energy consumption. The proposed forest optimization-based algorithm is a promising technique to help enterprises participate in IoT initiatives and develop their business.