scholarly journals Characterizing Tourism Destination Image Using Photos’ Visual Content

2020 ◽  
Vol 9 (12) ◽  
pp. 730
Author(s):  
Xin Xiao ◽  
Chaoyang Fang ◽  
Hui Lin
Keyword(s):  
Deep Learning ◽  
Visual Information ◽  
Latent Dirichlet Allocation ◽  
Hot Spot ◽  
Small Sample Size ◽  
Small Sample ◽  
Destination Image ◽  
Learning Technology ◽  
Visual Content ◽  
Tourism Destination

“A picture is worth a thousand words”. Analysis of the visual content of tourist photos is an effective way to explore the image of tourist destinations. With the development of computer deep learning and big data mining technology, identifying the content of massive numbers of tourist photos by convolutional neural network (CNN) approaches breaks through the limitations of manual approaches of identifying photos’ visual information, e.g., small sample size, complex identification process, and results deviation. In this study, 531,629 travel photos of Jiangxi were identified as 365 scenes through deep learning technology. Through the latent Dirichlet allocation (LDA) model, five major tourism topics are found and visualized by map. Then, we explored the spatial and temporal distribution characteristics of different tourism scenes based on hot spot analysis technology and the seasonal evaluation index. Our research shows that the visual content mining on travel photos makes it possible to understand the tourism destination image and to reveal the temporal and spatial heterogeneity of the image, thereby providing an important reference for tourism marketing.

Exploring destination image through online reviews: an augmented mining model using latent Dirichlet allocation combined with probabilistic hesitant fuzzy algorithm

Kybernetes ◽  
2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Yuyan Luo ◽  
Tao Tong ◽  
Xiaoxu Zhang ◽  
Zheng Yang ◽  
Ling Li
Keyword(s):  
Machine Learning ◽  
Decision Making ◽  
Latent Dirichlet Allocation ◽  
Online Reviews ◽  
Small Sample ◽  
Destination Image ◽  
Tourism Destination ◽  
Fuzzy Algorithm ◽  
Content Type ◽  
Dirichlet Allocation

PurposeIn the era of information overload, the density of tourism information and the increasingly sophisticated information needs of consumers have created information confusion for tourists and scenic-area managers. The study aims to help scenic-area managers determine the strengths and weaknesses in the development process of scenic areas and to solve the practical problem of tourists' difficulty in quickly and accurately obtaining the destination image of a scenic area and finding a scenic area that meets their needs.Design/methodology/approachThe study uses a variety of machine learning methods, namely, the latent Dirichlet allocation (LDA) theme extraction model, term frequency-inverse document frequency (TF-IDF) weighting method and sentiment analysis. This work also incorporates probabilistic hesitant fuzzy algorithm (PHFA) in multi-attribute decision-making to form an enhanced tourism destination image mining and analysis model based on visitor expression information. The model is intended to help managers and visitors identify the strengths and weaknesses in the development of scenic areas. Jiuzhaigou is used as an example for empirical analysis.FindingsIn the study, a complete model for the mining analysis of tourism destination image was constructed, and 24,222 online reviews on Jiuzhaigou, China were analyzed in text. The results revealed a total of 10 attributes and 100 attribute elements. From the identified attributes, three negative attributes were identified, namely, crowdedness, tourism cost and accommodation environment. The study provides suggestions for tourists to select attractions and offers recommendations and improvement measures for Jiuzhaigou in terms of crowd control and post-disaster reconstruction.Originality/valuePrevious research in this area has used small sample data for qualitative analysis. Thus, the current study fills this gap in the literature by proposing a machine learning method that incorporates PHFA through the combination of the ideas of management and multi-attribute decision theory. In addition, the study considers visitors' emotions and thematic preferences from the perspective of their expressed information, based on which the tourism destination image is analyzed. Optimization strategies are provided to help managers of scenic spots in their decision-making.

scholarly journals Application of Data-Driven Iterative Learning Algorithm in Transmission Line Defect Detection

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Yuquan Chen ◽  
Hongxing Wang ◽  
Jie Shen ◽  
Xingwei Zhang ◽  
Xiaowei Gao
Keyword(s):  
Deep Learning ◽  
Transmission Line ◽  
Target Detection ◽  
Defect Detection ◽  
Learning Algorithm ◽  
Small Sample ◽  
Iterative Learning ◽  
Data Driven ◽  
Learning Technology ◽  
Line Defect

Deep learning technology has received extensive consideration in recent years, and its application value in target detection is also increasing day by day. In order to accelerate the practical process of deep learning technology in electric transmission line defect detection, the current work used the improved Faster R-CNN algorithm to achieve data-driven iterative training and defect detection functions for typical transmission line defect targets. Based on Faster R-CNN, we proposed an improved network that combines deformable convolution and feature pyramid modules and combined it with a data-driven iterative learning algorithm; it achieves extremely automated and intelligent transmission line defect target detection, forming an intelligent closed-loop image processing. The experimental results show that the increase of the recognition of improved Faster R-CNN network combined with data-driven iterative learning algorithm for the pin defect target is 31.7% more than Faster R-CNN. In the future, the proposed method can quickly improve the accuracy of transmission line defect target detection in a small sample and save manpower. It also provides some theoretical guidance for the practical work of transmission line defect target detection.

scholarly journals Improving the Efficacy of Deep-Learning Models for Heart Beat Detection on Heterogeneous Datasets

2021 ◽  
Vol 8 (12) ◽  
pp. 193
Author(s):  
Andrea Bizzego ◽  
Giulio Gabrieli ◽  
Michelle Jin Yee Neoh ◽  
Gianluca Esposito
Keyword(s):  
Deep Learning ◽  
Small Sample Size ◽  
Classification Performance ◽  
Heart Beat ◽  
Small Sample ◽  
Electrocardiogram Signals ◽  
Heterogeneous Datasets ◽  
Beat Detection ◽  
Physiological Markers ◽  
Bioelectric Signals

Deep learning (DL) has greatly contributed to bioelectric signal processing, in particular to extract physiological markers. However, the efficacy and applicability of the results proposed in the literature is often constrained to the population represented by the data used to train the models. In this study, we investigate the issues related to applying a DL model on heterogeneous datasets. In particular, by focusing on heart beat detection from electrocardiogram signals (ECG), we show that the performance of a model trained on data from healthy subjects decreases when applied to patients with cardiac conditions and to signals collected with different devices. We then evaluate the use of transfer learning (TL) to adapt the model to the different datasets. In particular, we show that the classification performance is improved, even with datasets with a small sample size. These results suggest that a greater effort should be made towards the generalizability of DL models applied on bioelectric signals, in particular, by retrieving more representative datasets.

What travel motivational factors influence Muslim tourists towards MMITD?

2017 ◽  
Vol 8 (1) ◽  
pp. 48-73 ◽  
Author(s):  
Muhammad Khalilur Rahman ◽  
Suhaiza Zailani ◽  
Ghazali Musa
Keyword(s):  
Structural Equation ◽  
Small Sample Size ◽  
Self Esteem ◽  
Small Sample ◽  
Motivational Factors ◽  
Equation Modeling ◽  
Tourism Destination ◽  
Content Type ◽  
The World ◽  
Managerial Implications

Purpose The World Islamic Tourism Mart in Malaysia has been attracting Muslim tourists from all over the world to choose Malaysia as their Islamic tourism destination. This paper aims to implement the concept of the travel career ladder (TCL) with the main purpose of the antecedents of travel motivation toward Malaysia for Islamic tourism destination (MMITD). Design/methodology/approach The theoretical model was tested using the structural equation modeling technique with partial least squares. A self-administered questionnaire was designed, distributed and collected from 180 effective participants who had visited Malaysia. Findings The findings revealed that the Islamic compliance with self-esteem needs, the Islamic compliance with relationship needs and the Islamic compliance with physiological needs have significant effects on Malaysia My Islamic tourism destination. Research limitations/implications The scope of this research paper is limited to TCL including the Islamic compliance issues with self-fulfillment, self-esteem, relationship, safety and physiological needs. A small sample size was obtained with participants from the Muslim countries. A future study should be comprehensively conducted on larger and diverse sampling methods with participants from the Muslim and the non-Muslim major countries, as this paper particularly discusses the theoretical and managerial implications for the anticipated future studies. Originality/value The study yet attempts on the part of academicians in Malaysia, what travel motivational factors influence Islamic tourists to travel MMITD. Based on the previous literature and researcher’s experience, it is a new phenomenon and investigation on MMITD.

scholarly journals Unravelling Small Sample Size Problems in the Deep Learning World

2020 ◽  
Author(s):  
Rohit Keshari ◽  
Soumyadeep Ghosh ◽  
Saheb Chhabra ◽  
Mayank Vatsa ◽  
Richa Singh
Keyword(s):  
Deep Learning ◽  
Sample Size ◽  
Small Sample Size ◽  
Small Sample

A deep learning approach to injury forecasting in NBA basketball

2021 ◽  
pp. 1-12
Author(s):  
Alexander Cohan ◽  
Jake Schuster ◽  
Jose Fernandez
Keyword(s):  
Deep Learning ◽  
Sports Medicine ◽  
Injury Risk ◽  
Small Sample Size ◽  
Model Performance ◽  
Imbalanced Data ◽  
Feature Learning ◽  
Small Sample ◽  
Injury Incidence ◽  
Learning Approaches

Predicting athlete injury risk has been a holy grail in sports medicine with little progress to date due to a variety of factors such as small sample sizes, significantly imbalanced data, and inadequate statistical approaches. Modeling approaches which are not able to account for the multiple interactions across factors can be misleading. We address the small sample size by collecting longitudinal data of NBA player injuries using publicly available data sources and develop a state of the art deep learning model, METIC, to predict future injuries based on past injuries, game activity, and player statistics. We evaluate model performance using metrics appropriate for imbalanced data and find that METIC performs significantly better than other traditional machine learning approaches. METIC uses feature learning to create interactive features which become meaningful in combination with each other. METIC can be used by practitioners and front offices to improve athlete management and reduce injury incidence, potentially saving sports teams millions in revenue due to reduced athlete injuries.

scholarly journals Development and Validation of Suspicious Liver Lesion Deep Learning Algorithm for Computed Tomography

2021 ◽  
Author(s):  
Jacob Johnson ◽  
Kaneel Senevirathne ◽  
Lawrence Ngo
Keyword(s):  
Deep Learning ◽  
Learning Algorithm ◽  
Small Sample Size ◽  
Liver Lesion ◽  
The United States ◽  
Detection Algorithm ◽  
Small Sample ◽  
Lesion Detection ◽  
Liver Lesions ◽  
Deep Learning Algorithm

In this work, we report the results of a deep-learning based liver lesion detection algorithm. While several liver lesion segmentation and classification algorithms have been developed, none of the previous work has focused on detecting suspicious liver lesions. Furthermore, their generalizability remains a pitfall due to their small sample size and sample homogeneity. Here, we developed and validated a highly generalizable deep-learning algorithm for detection of suspicious liver lesions. The algorithm was trained and tested on a diverse dataset containing CT exams from over 2,000 hospital sites in the United States. Our final model achieved an AUROC of 0.84 with a specificity of 0.99 while maintaining a sensitivity of 0.33.

Mapping the concepts evoked by a destination: an approach to the study of a holistic destination image

2021 ◽  
Vol 12 (2) ◽  
pp. 324-340
Author(s):  
Vanesa F. Guzman-Parra ◽  
Juan Trespalacios Gutierrez ◽  
José Roberto Vila-Oblitas
Keyword(s):  
Small Sample Size ◽  
Small Sample ◽  
Marketing Strategies ◽  
Rural Tourism ◽  
Destination Image ◽  
Tourist Destination ◽  
New Approach ◽  
Content Type ◽  
Target Segment ◽  
Practical Implications

Purpose This study aims to demonstrate the application of computer-aided text analysis (CATA) software in identifying primary associations and impressions of a specified tourist destination. Design/methodology/approach The Leximancer software is applied on primary information to analyze the concepts evoked by a destination. Because no specific planning has been done for destination image marketing strategies for rural tourism in Andalusia, this study visualizes and determines clusters of the main attributes associated with this destination. Findings The analysis identifies the main clusters among associations and impressions of the destination that can be useful in developing strategies. Research limitations/implications Only a target segment is studied, with a relatively small sample size. Practical implications Leximancer can not only be applied to online user-generated content, but primary information can also be mapped to generate a holistic destination image. Furthermore, identification of the relevant attributes and impressions can serve to identify unique assets to help tourism organizations develop a destination. Social implications Several implications concerning destination marketing are outlined. Originality/value Although previous studies have applied Leximancer and other CATA software, the present research uses a new approach. Deriving the primary information on destination image using an unstructured methodology, the concepts evoked by a destination are mapped. Because there is a lack of research on rural tourism in Andalusia and its destination image, its associated attributes are studied.

Sign in / Sign up

Export Citation Format

Share Document