![]() ![]() Most of the preceeding travel recommendation methodologies are capable of recommending a personalized travel by considering the POIs. The travel recommender a system is based on Points Of Interests (POIs) of user’s emerge in many studies and enterprise applications. Leveraging community-contributed information such as blogs, Global Positioning System, and images that are geographically tagged for suggestions on navigation with mobile based communication is becoming a research area. It contributes to knowledge by adding new moderator, new paths as well as integrating personal characteristics (e.g. The study will succor different tourism firms, restaurants and SNSs service providers to maximise the adoption of geotagging technology use. Geotagg’s use frequency strongly moderated the different relationships in the integrated UTAUT model. All constructs of UTAUT except effort expectancy have substantial positive effect on SNSs users’ intention to adopt geotagging technology. facilitating condition to effort expectancy and effort expectancy to performance expectancy) are statistically significant. Two new paths among the predictor variables (e.g. PIIT has impact on all UTAUT exogenous constructs except effort expectancy as well as on behavioural intention. Interestingly, PIIT properly explains the personal characteristics of SNSs users in UTAUT framework. Integrated UTAUT fulfills all criterion of model fitness. Statistical analysis techniques, such as SPSS AMOS and partial least square method, based on structural equation modeling (SEM), were used to analyse the collected data. By using structured questionnaire survey, 390 data were collected. This study explores the factors that affect the adoption of geotagging technology among the SNSs users integrating personal innovativeness in IT (PIIT) with UTAUT. Many scholars focused on geotagged photography in various contexts such as the potential to encourage post-¯eldwork of students (Welsh et al., 2012), demographics and motivations for volunteered geographic information in location-based social media (Ha®ner et al., 2018), geotagging tweeted pictures for disaster management (Chong et al., 2018), adoption of geotagging in tourism sectors (Chung et al., 2017), attitude towards location data in everyday life (Rzeszewski and Luczys, 2018), role in the acquisition of geographic knowledge and behaviour (Tussyadiah and Zach, 2012), geotagged web photos-based tourism recommendation system (Cao et al., 2010), tourist activities measurement in cities (Kader, 2014), digital photography and community photo sharing (Luo, 2011), location and activity recommendation by using GPS data (Zheng et al., 2010), and divisions of gender in the production of user-generated geotagged information (Stephens, 2013), developing travel route recommendations and travel planning systems (Kurashima et al., 2013), studying the travel behaviour of tourists (Vu et al., 2015) and determinants of photo tagging on social networking sites (see Table 1).ĭue to the outstanding growth of geotagging technology usage among the social networking sites (SNSs) users, research is needed to better understand how SNSs users accept and use this technology. Because of new technology, many information systems and geographical studies are investigating this issue. Moreover, outstanding results are obtained for the Corel-1000 dataset in comparison with state-of-the-art methods. The proposed method reports significant results on Cifar-10 and Cifar-100 benchmarks. ![]() The presented method shows remarkable results on texture datasets ALOT with 250 categories and fashion (15). The proposed method is experimentally applied on challenging datasets including Cifar-100 (10), Cifar-10 (10), ALOT (250), Corel-10000 (10), Corel-1000 (10) and Fashion (15). Spatial color coordinates are integrated with convolutional neural network (CNN) extracted features to comprehensively represent the color channels. The principal component analysis (PCA) reduced feature vectors are combined with the ResNet generated feature. The resulting feature sets are scaled at various levels with parameterized smoothened images. ![]() Box filtering adjusts the results of approximation of Gaussian with standard deviation to the lowest scale and suppressed by non-maximal technique. These values of smoothed intensity are calculated as per local gradients. Thereafter, the rotated sampling patterns and pairwise comparisons are performed, which return image smoothing by applying standard deviation. In the first step, symmetric sampling is performed on the images from the neighborhood key points. For this, fusion of ResNet generated signatures is performed with the innovative image features. This article presents symmetry of sampling, scoring, scaling, filtering and suppression over deep convolutional neural networks in combination with a novel content-based image retrieval scheme to retrieve highly accurate results. ![]()
0 Comments
Leave a Reply.AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |