This regular issue of JAISE is composed of six articles. The review process for the manuscripts in this issue was supervised by our editors (in alphabetical order): George Baryannis, Andreas Braun, Jeannette Chin, Lukas Esterle, Andres Muñoz Ortega, and Ping Wang, whom we thank for their service. The first article in this issue is selected as editor’s choice to be available as open access.
AgriTech: Prospects and Challenges of Robotics, AI & 5G technologies in Agriculture, by M. Abdulraheem et al., is a survey article examining the potential benefits and risks of robotics, artificial intelligence, and 5G technology applications in agriculture. It focuses on precision agriculture, crop monitoring, autonomous agriculture, live-stock monitoring and farm-to-table logistics. It identifies a number of issues on infrastructure, data management and regulations.
Interpretable Rules for Wildfire Risk Prediction Using the Binary Golden Ratio Optimization Method, by A. Bekhouche et al., explores a prediction model using a hybrid model that combines the a priori association rule mining algorithm with the binary golden ratio optimization method (BGROM) to improve accuracy of forest fire predictions. Experimental results based on a dataset representing three regions from Algeria, outperformed existing prediction methods, improving early forest fire detection and consequently risk management.
Deep Learning-Based Forecasting of Temperature and Humidity in Footwear Using Multi-Sensor Data, by C. Yardimci et al. makes a comparison of various Deep Learning strategies against a Hybrid Model when used to forecast temperature and humidity inside various types of footwear based on multi-sensor data. The author explains the conditions in which the Hybrid Model approach outperforms the other models and achieves the highest predictive accuracy across all tested footwear conditions.
A Scalable Deep Learning Framework for Evapotranspiration Estimation Using Open-Access Climate Services and Remote Sensing, by V. Casino Sánchez et al., proposes a deep learning (DL) framework for estimating reference evapotranspiration (ET0) by combining open-access climate services and remote sensing (RS) data. The proposed approach is benchmarked against traditional machine learning (ML) models, while multiple deep neural network (DNN) architectures are also evaluated. Experiments conducted on three agricultural plots in south eastern Spain, indicate in those specific conditions RNNs achieve better performance. The proposed methodology illustrates the feasibility of AI-driven irrigation management across diverse climates and highlights its potential to advance sustainable water use in agriculture.
An auto-scaling approach for serverless environments based on a multi-expert consensus mechanism, by M. Kashaniyan et al., presents a dependency-aware autoscaling framework that improves robustness and cost efficiency in Serverless computing. Experiments on real workload traces show improved prediction accuracy and more stable scaling decisions than representative baselines; and shows better results for supervised forecasting than unsupervised clustering for generating autoscaling actions.
Video-based contactless detection of task-related concentration using advanced machine learning techniques, by X. Li et al., explains a test of accuracy when applying machine learning to a novel contactless video-based approach in detecting task-related concentration. Applying machine learning to physiological signals from video photoplethysmography enable contactless detection of task-related concentration. The experiment conducted with thirty adults showed detection based on video photoplethysmography signals to outperform more typical approaches with ECG signals.
Upcoming issues
The following is a list of upcoming issues of JAISE:
November 2026: Regular Issue
February 2027: Regular Issue.
May 2027: Regular Issue.
August 2027: Thematic Issue on " Robust and Responsible Intelligent Systems for Human-Centred Smart Environments"
