The technological development and growth of the telecommunications industry have had a great positive impact on the education, health, and economic sectors, among others. However, they have also increased rivalry between companies in the market to keep and acquire new customers. A lower level of market concentration is related to a higher level of competitiveness among companies in the sector that drives a country’s socioeconomic development. To guarantee and improve the level of competition, it is necessary to monitor the concentration level in the telecommunications market to plan and develop appropriate strategies by governments. With this in mind, the present work aims to analyze the concentration prediction in the telecommunications market through recurrent neural networks and the Herfindahl-Hirschman index. The results show a slight gradual increase in competition in terms of traffic and access, while a more stable concentration level is observed in revenues.

Aiming at the problem of road network multi-scale matching, a multi-scale road matching method under the constraint of road mesh of small-scale data has been proposed. First, two road meshes with different scale data are constructed; Secondly, under the constraint of the small-scale road mesh, the composite mesh composed of several road meshes in the large-scale road is extracted, and the mesh matching with the small-scale road mesh is completed; Then, many-to-many matching of road meshes with different scales is realized; finally, the matching relationship between composite mesh and small-scale road mesh is transformed into the matching between multi-scale road mesh boundary roads and internal roads, and the matching of the whole road network is completed. The experimental results show that this method can better realize the matching of multi-scale road network.

The study aims to investigate and analyse the social media, precisely the Instagram activity of several hotels in the city of Yogyakarta, Indonesia. Having been the second most popular destination besides Bali, it is mainly dominated by domestic tourism. Although several governmental institutions exist, the study focuses on the hotel’s activity only. The main purpose was to find, that after the classification of the posts, whether there is a more positive effect of one as opposed to the other type of posts. In addition, it was also important to see if with the time advancing positive effect of likes and comments appear and the relation of hashtags, likes and comments. Data was collected between 1st of January 2023. and 15th of July 2024. The first step was to collect posts done by the suppliers and then the posts were classified. Also, the number of hashtags used were collected. Second step was to collect the response from the demand side by gathering their likes and comments. Data then was analysed with SPSS 24 and JASP program. Results show that while there is no significance on increasing likes and comments with the months advancing, but in terms of the type of the posts there is. Promotional posts with other suppliers tend to bring a lot more comments and likes than self-promotional posts. This study’s main purpose to analyse through social media posts to enhance online networking by local suppliers promoting each other’s products.

In view of the fact that the convolution neural network segmentation method lacks to capture the global dependency of infected areas in COVID-19 images, which is not conducive to the complete segmentation of scattered lesion areas, this paper proposes a COVID-19 lesion segmentation method UniUNet based on UniFormer with its strong ability to capture global dependency. Firstly, a U-shaped encoder-decoder structure based on UniFormer is designed, which can enhance the cooperation ability of local and global relations. Secondly, Swin spatial pyramid pooling module is introduced to compensate the influence of spatial resolution reduction in the encoder process and generate multi-scale representation. Multi-scale attention gate is introduced at the skip connection to suppress redundant features and enhance important features. Experiment results show that, compared with the other four methods, the proposed model achieves better results in Dice, loU and Recall on COVID-19-CT-Seg and CC-CCIII dataset, and achieves a more complete segmentation of the lesion area.

The destructive geohazard of landslides produces significant economic and environmental damages and social effects. State-of-the-art advances in landslide detection and monitoring are made possible through the integration of increased Earth Observation (EO) technologies and Deep Learning (DL) methods with traditional mapping methods. This assessment examines the EO and DL union for landslide detection by summarizing knowledge from more than 500 scholarly works. The research included examinations of studies that combined satellite remote sensing information, including Synthetic Aperture Radar (SAR) and multispectral imaging, with up-to-date Deep Learning models, particularly Convolutional Neural Networks (CNNs) and their U-Net versions. The research categorizes the examined studies into groups based on their methodological development, spatial extent, and validation techniques. Real-time EO data monitoring capabilities become more extensive through their use, but DL models perform automated feature recognition, which enhances accuracy in detection tasks. The research faces three critical problems: the deficiency of training data quantity for building stable models, the need to improve understanding of AI’s predictions, and its capacity to function across diverse geographical landscapes. We introduce a combined approach that uses multi-source EO data alongside DL models incorporating physical laws to improve the evaluation and transferability between different platforms. Incorporating explainable AI (XAI) technology and active learning methods reduces the uninterpretable aspects of deep learning models, thereby improving the trustworthiness of automated landslide maps. The review highlights the need for a common agreement on datasets, benchmark standards, and interdisciplinary team efforts to advance the research topic. Research efforts in the future must combine semi-supervised learning approaches with synthetic data creation and real-time hazardous event predictions to optimise EO-DL framework deployments regarding landslide danger management. This study integrates EO and AI analysis methods to develop future landslide surveillance systems that aid in reducing disasters amid the current acceleration of climate change.

The Huaiyang Canal, a significant section of the Grand Canal, boasts representative tourist attractions. This study analysis of online reviews from Ctrip and Mahive using R language, Gephi, ROST CM, and SPSS has provided insights into tourists’ perceptions of the Huaiyang Canal’s image. Key findings include: (1) Dominant landscape images encompass gardens, canals, and buildings, emphasizing the historical and cultural assets. Both cultural and natural landscapes equally captivate tourists. (2) The canal’s tourism image perception follows a “garden-history-canal” hierarchy with the canal as the central space and history expanding its tourism features. (3) The perceptions can be categorized into historical and cultural landscapes, man-made projects, and attraction perception. Despite varying tourist numbers in Huaian and Yangzhou, scenic spot experiences are similar. The overall perception of tourists is largely positive, but some express concerns about service attitudes and travel time planning.