In agriculture, crop yield and quality are critical for global food supply and human survival. Challenges such as plant leaf diseases necessitate a fast, automatic, economical, and accurate method. This paper utilizes deep learning, transfer learning, and specific feature learning modules (CBAM, Inception-ResNet) for their outstanding performance in image processing and classification. The ResNet model, pretrained on ImageNet, serves as the cornerstone, with introduced feature learning modules in our IRCResNet model. Experimental results show our model achieves an average prediction accuracy of 96.8574% on public datasets, thoroughly validating our approach and significantly enhancing plant leaf disease identification.

This research presents a novel approach utilizing a self-enhanced chimp optimization algorithm (COA) for feature selection in crowdfunding success prediction models, which offers significant improvements over existing methods. By focusing on reducing feature redundancy and improving prediction accuracy, this study introduces an innovative technique that enhances the efficiency of machine learning models used in crowdfunding. The results from this study could have a meaningful impact on how crowdfunding campaigns are designed and evaluated, offering new strategies for creators and investors to increase the likelihood of campaign success in a rapidly evolving digital funding landscape.

Given the large amount of railway maintenance work in China, whereas the maintenance time window is continuously compressed, this paper proposes a novel network model-based maintenance planning and optimization method, transforming maintenance planning and optimization into an integer linear programming problem. Based on the dynamic inspection data of track geometry, the evaluation index of maintenance benefit and the model of the decay and recovery of the track geometry are constructed. The optimization objective is to maximize the railway network’s overall performance index, considering budget constraint, maximum length constraint, maximum number of maintenance activities within one single period constraint, and continuity constraint. Using this method, the track units are divided into several maintenance activities at one time. The combination of surrounding track units can be considered for each maintenance activity, and the specific location, measure, time, cost, and benefit can be determined. Finally, a 100 km high-speed railway network case study is conducted to verify the model’s effectiveness in complex optimization scenarios. The results show that this method can output an objective maintenance plan; the combination of unit track sections can be considered to expand the scope of maintenance, share the maintenance cost and improve efficiency; the spatial-temporal integrated maintenance planning and optimization can be achieved to obtain the optimal global solution.

PPGIS platforms have been widely used to map social actors since the emergence of open access webGIS platforms. This identification of citizen initiatives is based on the physical location, but is rarely combined with social networking. This research seeks to close that gap by using the platIC web-based mapping tool for citizen initiatives, together with their interrelationships. Therefore, a methodical procedure has been defined to construct a geolocalised graph by identifying and categorising linked nodes. Method steps have been tested in three case studies in the Malaga region: Malaga city, Benalmadena, and Valle del Genal. They were selected for a comparative analysis in three different urban and socio-economic scenarios, namely: a tourist destination with a high density of Spanish population and floating city users; a sun-and-beach destination with a significant presence of resident foreign population; and a rural area suffering from depopulation, respectively. Mapping reveals a higher density of citizen initiatives in central urban areas and with social conflicts. Social graphs show a wider interconnection of nodes in rural areas, but isolated nodes are spread more widely there. Monitoring active citizen initiatives could serve as a basis for local administration to involve the citizenry in the management of current issues in the urban and rural context. Future research may promote new plugins to improve participatory process through webGIS platforms.

This research presents a comprehensive model for enhancing the road network in Thailand to achieve high efficiency in transportation. The objective is to develop a systematic approach for categorizing roads that aligns with usage demands and responsible agencies. This alignment facilitates the creation of interconnected routes, which ensure clear responsibility demarcation and foster efficient budget allocation for road maintenance. The findings suggest that a well-structured road network, combined with advanced information and communication technology, can significantly enhance the economic competitiveness of Thailand. This model not only proposes a framework for effective road classification but also outlines strategic initiatives for leveraging technology to achieve transportation efficiency and safety.

Accurate drug-drug interaction (DDI) prediction is essential to prevent adverse effects, especially with the increased use of multiple medications during the COVID-19 pandemic. Traditional machine learning methods often miss the complex relationships necessary for effective DDI prediction. This study introduces a deep learning-based classification framework to assess adverse effects from interactions between Fluvoxamine and Curcumin. Our model integrates a wide range of drug-related data (e.g., molecular structures, targets, side effects) and synthesizes them into high-level features through a specialized deep neural network (DNN). This approach significantly outperforms traditional classifiers in accuracy, precision, recall, and F1-score. Additionally, our framework enables real-time DDI monitoring, which is particularly valuable in COVID-19 patient care. The model’s success in accurately predicting adverse effects demonstrates the potential of deep learning to enhance drug safety and support personalized medicine, paving the way for safer, data-driven treatment strategies.