The design of Domain-Specific Languages (DSLs) plays a key role in improving productivity and usability in software engineering tools. This paper empirically evaluates a DSL developed to optimize periodic maintenance scheduling, which is crucial for efficiently managing vehicle fleets. Optimizing this process can significantly reduce costs by ensuring that only the required maintenance is performed, preventing bottlenecks and other problems derived from inefficient resource management, especially when faced with restrictions such as limited maintenance facility capacity. Most current tools for planning maintenance, such as Computerized Maintenance Management Systems (CMMS), fail to optimize their schedules, requiring custom implementations to achieve better results and being overwhelming to use due to complex navigation and repetitive procedures. In this paper, we propose a Domain-Specific Language that simplifies the maintenance scheduling process through the centralization of all the functionality in a single program, following Model-Driven Engineering principles. This DSL enables the optimization of maintenance schedules by defining constraints directly within the language. Usability tests and user surveys demonstrate a reduction in the time and effort required for maintenance scheduling and an increased satisfaction rate compared to CMMS.

Robotics applications to healthcare have become more prominent in the last few years. With the advances in technology, robots have become more sophisticated at doing what humans do in healthcare. The potential of robotics in healthcare is vast. Its applications range from patient care to personal medical assistants. In addition, there is no doubt that the automation driven in healthcare by robotics often paves the way for healthcare systems' long-term sustainability and profitability. The use of robotics takes care of various tasks performed by the healthcare workforce, which is complex and repetitive. Some of the many robotics applications in healthcare include surgical robots, pharmacy robots, robotic telemedicine, robotics-assisted infectious disease management, robotics rehabilitation medicine and many more. As technology continues to advance, healthcare systems have started to embrace robotics applications. They are mainly used to simplify the tasks performed by human resources. However, research in this stream is still in its infancy and requires greater improvement. This special issue aims to bring together researchers in related fields to explore and present various aspects of robotics applications to healthcare systems. It has provided an excellent opportunity for researchers and practitioners working in this field to transfer their knowledge and new ideas. This special issue includes a collection of seven articles, and they have been reviewed and accepted for publication after a careful review from an expert team. The major contributions of the accepted articles are highlighted in the following: The first article is entitled ‘Fetal health classification from cardiotocographic data using machine learning.’ The authors propose a machine-learning algorithm to make remarkable progress in foetal health treatment, diagnosis and prognosis. The results are evaluated using regression correlation analysis. The results of this approach are comparatively better than the existing methods. The second article is entitled ‘Study on the effect of mental health nursing intervention after gynecological tumour operation based on clustering model.’ The authors make use of robotics for mental health intervention. They have presented a clustering method to analyse the nursing data. The focus is on the analysis of mental health after gynaecological tumour operation. This approach provides significantly better performance than existing methods. The third article is entitled ‘Improved grey-level correlation feature and neural network model for medical resource requirement prediction.’ The authors propose a grey-level correlation algorithm using neural networks to efficiently solve medical resource management problems. This algorithm provides strong robustness and stability measures. It also provides efficient predictive models. The fourth article is entitled ‘A deep learning semantic segmentation architecture for COVID-19 lesions discovery in limited chest CT datasets.’ The authors propose a semantic segmentation architecture for COVID-19 lesion detection from the CT scan data. A deep learning-based semantic segmentation algorithm is used for this purpose. The results are evaluated using the IoU metric and various performance-related factors. It shows significantly improved results. The fifth article is entitled ‘Hybrid intelligent framework for automated medical learning.’ A hybrid automated medical learning algorithm is proposed to learn and predict healthcare data. Deep learning and knowledge graphs are used for this process. They help to recognize the various activities of the patients. The sixth article is entitled ‘Detection of neurodegenerative disease in brain using region splitting based segmentation with deep unsupervised neural networks.’ The authors propose a RSS-DUNN algorithm to deal with neurodegenerative diseases. The accuracy, precision and recall measures are found to be comparatively better than conventional approaches. We thank all the authors and reviewers for their valuable contributions. A special thanks to the Editor-in-Chief of this journal for offering us the privilege to edit a special in this reputed journal. The research works presented in this special issue will add significant opportunities to the research community.

Introduction to the Special Issue on Artificial Intelligence for Underwater Sensor NetworksIn recent years, significant growth in Artificial Intelligence (AI) applications has been observed in several fields, mainly due to growing technological advancements and ever-increasing demand for modern computing systems.Currently, research on underwater sensor networks has acquired greater importance.This instance makes essential factors such as connectivity, security, power, cost, size, and interoperability the most critical aspects to be considered while coming up with innovative solutions for underwater sensor networks.However, although conventional approaches in underwater sensor networks achieve significant performance measures, efficient monitoring of the aquatic ecosystem is crucial for the transition toward sustainable underwater systems.This special issue of the Transactions on Sensor Networks journal on underwater sensors systems, entitled "Artificial Intelligence for Underwater Sensor Networks," mainly focuses on new paradigms and developmental trends of intelligent techniques for underwater sensor networks.The series of research articles presented in this special issue emphasizes several aspects of this domain, including exploring innovative tools, algorithms, hierarchies, power management, and control of underwater sensors.The call for papers resulted in the acceptance of ten articles for publication.For every submitted article, the editorial team has followed a strict evaluation process to examine the quality of the articles.The article entitled "Minimizing Latency for Data Aggregation in Wireless Sensor Networks: An Algorithm Approach" presents an innovative approach for reducing latency in underwater sensor networks through AI-based algorithmic approaches.The authors mainly focus on the problem of reporting data to the sink node in underwater sensor networks.The conventional approaches make use of data segregation methods to communicate with the sink node.But with the evolution in sensor networks, different kinds of data require varied aggregation functions.At the same time, they are reporting multiple data types to the sink node.The major problem that occurs often is increased latency measures.The authors have explored an innovative AI algorithm with minimum latency to report data across the sink nodes to effectively address this concern.It works on the basis of the Relative Collision Graph-based algorithm, and this work provides improved performance with better results.The next article presents efficient routing of data in underwater sensor networks.In the article, entitled "Traffic Classification in Underwater Networks using SDN and Data-Driven Hybrid Metaheuristics," the authors have presented an interesting approach to directing the traffic rate in underwater sensor networks based on data-driven hybrid metaheuristics.The authors mainly focus on solving the drawbacks associated with the application-centric nature of traditional approaches.The authors have enhanced the SDN controllers decision-making capability with machine learning approaches.They have used three classifiers, namely, logistics

Monte-Carlo methods are the basis for solving many computational problems using repeated random sampling in scenarios that may have a deterministic but very complex solution from a computational point of view. In recent years, researchers are using the same idea to solve many problems through the so-called Monte-Carlo Tree Search family of algorithms, which provide the possibility of storing and reusing previously calculated results to improve precision in the calculation of future outcomes. However, developers and researchers working in this area tend to have to carry out software developments from scratch to use their designs or improve designs previously created by other researchers. This makes it difficult to see improvements in current algorithms as it takes a lot of hard work. This work presents JGraphs, a toolset implemented in the Java programming language that will allow researchers to avoid having to reinvent the wheel when working with Monte-Carlo Tree Search. In addition, it will allow testing experiments carried out by others in a simple way, reusing previous knowledge.

Intelligent security systems have evolved enormously in the last few years. Most of these security systems use a group of physics sensors and algorithms for data analysis and communication systems to notify security alarms. Many security systems that are included in doors can detect intruders when they have already opened the door, but not while intruders are forcing upon the door. However, some security systems include preventive systems, which can detect intruders before they open the door. These preventive systems are usually based on video cameras (image processing) or in-presence sensors, which can generate many false positives, for instance, when a person is next to the door for a few seconds, even if this person is not manipulating the door. This research work proposes a novel force door detection system. The system includes a specific device for monitoring door small vibrations and movements; it analyzes these data using neural networks to detect accurately if someone is forcing upon the door. Artificial intelligence must be able to categorize data records without confusing when someone is forcing upon the door with other actions, like knocking on the door.

People rely on other people's opinions to make decisions, especially if they belong to their circle of trust. In addition, there are lots of websites of recognized prestige that provide people opinions about different products and services, which are read by millions of people before making a decision. That is why systems for sentiment analysis are becoming increasingly important to automatically process the information and determine feelings of users. They analyze their written words, usually conditioned by the characteristics of microblogging platforms, in which a large number of messages are published every day, providing a great source of information, impossible to be managed manually. In this work, we show a proposal to analyze the feeling that Twitter users have towards different hotels or hotel chains through a platform that could be easily adapted to other contexts. The goal is to create q a structure based on independent and interchangeable components that will make it possible to conduct studies in a more uniform, open and transparent way.