This paper presents a hybrid grasshopper optimization algorithm using a novel decoder and local search to solve instances of the open vehicle routing problem with capacity and distance constraints. The algorithm’s decoder first defines the number of vehicles to be used and then it partitions the clients, assigning them to the available routes. The algorithm performs a local search in three neighborhoods after decoding. When a new best solution is found, every route is locally optimized by solving a traveling salesman problem, considering the depot and clients in the route. Three sets containing a total of 30 benchmark problems from the literature were used to test the algorithm. The experiments considered two cases of the problem. In the first, the primary objective is to minimize the total number of vehicles and then the total distance to be traveled. In the second case, the total distance traveled by the vehicles is minimized. The obtained results showed the algorithm’s proficient performance. For the first case, the algorithm was able to improve or match the best-known solutions for 21 of the 30 benchmark problems. For the second case, the best-known solutions for 18 of the 30 benchmark problems were found or improved by the algorithm. Finally, a case study from a real-life problem is included.

As the number of older adults increases, and with it the demand for dedicated care, geriatric residences face a shortage of caregivers, who themselves experience work overload, stress, and burden. We conducted a long-term field study in three geriatric residences to understand the work conditions of caregivers with the aim of developing technologies to assist them in their work and help them deal with their burdens. From this study, we obtained relevant requirements and insights to design, implement, and evaluate two prototypes for supporting caregivers’ tasks (e.g., electronic recording and automatic notifications) in order to validate the feasibility of their implementation in situ and their technical requirements. The evaluation in situ of the prototypes was conducted for a period of 4 weeks. The results of the evaluation, together with the data collected from 6 months of use, motivated the design of a predictive schedule, which was iteratively improved and evaluated in participative sessions with caregivers. PRESENCE, the predictive schedule we propose, triggers real-time alerts of risky situations (e.g., falls, entering off-limits areas such as the infirmary or the kitchen) and informs caregivers of routine tasks that need to be performed (e.g., medication administration, diaper change, etc.). Moreover, PRESENCE helps caregivers to record caring tasks (such as diaper changes or medication) and well-being assessments (such as the mood) that are difficult to automate. This facilitates caregiver's shift handover and can help to train new caregivers by suggesting routine tasks and by sending reminders and timely information about residents. It can be seen as a tool to reduce the workload of caregivers and medical staff. Instead of trying to substitute the caregiver with an automatic caring system, as proposed by others, we propose our predictive schedule system that blends caregiver assessments and measurements from sensors. We show the feasibility of predicting caregiver tasks and a formative evaluation with caregivers that provides preliminary evidence of its utility.

The prediction of domestic electricity consumption is relevant because it helps to plan energy production, among many other benefits. In this work a dataset was collected from one house in an urban city of north-east of Mexico. An ad-hoc acquisition system was implemented to collect the data using a smart meter and the open weather API. The data was collected every minute over a period of 14 months since November 5, 2022, to January 5, 2024. The dataset contains 605,260 samples of 19 variables related with energy consumption and weather data. This dataset is specifically tailored for predicting domestic energy consumption and understanding consumption behaviours, filling a void in the existing literature where such datasets for Mexico are scarce. Moreover, the multivariate nature of the dataset allows researchers to investigate and propose new techniques for forecasting or pattern classification using multivariate data collected in a real scenario.

The development of smart cities will require the construction of smart buildings. Smart buildings will demand the incorporation of elements for efficient monitoring and control of electrical consumption. The development of efficient AI algorithms is needed to generate more accurate electricity consumption predictions; therefore; anomaly detection in electricity consumption predictions has become an important research topic. This work focuses on the study of the detection of anomalies in domestic electrical consumption in Mexico. A predictive machine learning model of future electricity consumption was generated to evaluate various anomaly-detection techniques. Their effectiveness in identifying outliers was determined, and their performance was documented. A 30-day forecast of electrical consumption and an anomaly-detection model have been developed using isolation forest. Isolation forest successfully captured up to 75% of the anomalies. Finally, the Shapley values have been used to generate an explanation of the results of a model capable of detecting anomalous data for the Mexican context.