This study presents an innovative extension to Home Healthcare Scheduling and Routing Problem (HHCRSP), introducing an Optional Starting Point (OSP) that allows for personalization of routes from the caregivers’ homes directly to patients. We developed a model using Mixed Integer Linear Programming (MILP) and a metaheuristic method inspired by the Greedy Randomized Adaptive Search Procedure (GRASP). This combination aims to make scheduling and routing more efficient, saving time and improving the quality of care for patients at home. Our results show that this new method can significantly enhance how home healthcare is delivered, making it more flexible and effective for both caregivers and patients.

Sleep disorders caused by snoring are a common problem that negatively affect the individual’s daily quality of life. For instance, poor sleep caused by snoring will induce important physical and mental issues. Given the fact that finding common criteria for all snoring sounds is very tough, this study aims to propose two models for snoring classification using AI-based learning methods. The first model is a Machine Learning (ML)-based built by stacking two classifiers namely, the SVM and KNN, that will learn the features extracted by applying the MFCC as a feature extraction technique. The second model is a Deep Learning (DL)-based where RNN and LSTM classifiers are stacked and where three feature extraction techniques (i.e. MFCC, STFT, ZCR) are applied. An online dataset consisting of .wav audio signals is used to implement the two models. Results show that the first and second models have achieved high accuracy scores of 98.5% and 80.8% respectively.

This article formulates a multi-day home care assignment scheduling and routing problem in which workload and distances are balanced between the employees. Additionally, constraints such as lunch breaks, maximum daily working hours, the maximum number of overtime hours, and the amplitude of the day are considered when solving the problem. The objective is to satisfy the clients' preferences, minimize the total distance traveled and the number of wasted and overtime hours, and balance the workload and the distance traveled between the employees. Since the proposed model is an NP-Hard problem, for solving large-scale problems, two resolution methods, a genetic algorithm approach, and a discrete invasive weed optimization with a greedy heuristic hybridization are presented. To validate the efficiency of the two approaches in solving the Home Care Multi-day Assignment, Scheduling, and Routing Problems, instances inspired by a real-life example of a home care center were tested. Moreover, they were compared to an exact mixed-integer linear programming method. The optimal results show the efficiency of our resolution methods; the solutions perform well as the multi-day home care assignment, scheduling, and routing problem can be solved in a reasonable time.

Home health care optimization is a trending research topic in the recent years since the demand for home health care rises. An important aspect of the problem is the workload balancing among caregivers that must be fair. However, the workload can be defined differently since the work of a caregiver can be composed of different activities: traveling time, time spent providing cares and idle time. Moreover, the home health care routing and scheduling problem with workload balancing is a multi-objective problem leading the working time balancing to increase the value of the total working time and soft patients time window and shared visits non-satisfaction. In order to obtain a good balance between all objectives, we perform an impact analysis of the caregivers activities balancing in order to identify the appropriate activities to balance instead of the whole working time. A mixed-integer programming representation of the problem is proposed and a memetic algorithm is used to evaluate the model on literature instances. An analysis of the results reveals the importance of the choice of the balanced activities in order to obtain an acceptable balance between workload balancing and the other objectives according to decision-makers strategy.

As people age, they become more fragile and exhibit difficulties in maintaining their gait and balance. Their state of fragility increases their vulnerability to fall incidents. Various analysis methods were developed to detect the abnormality of human gait and balance, and estimate the risk of falling. In this paper, we present a method to estimate the falling risk and alert the patient when a fall is about to happen. The proposed method consists in monitoring and analyzing the amount of sway of the center of mass in the medial-lateral plane by computing the center of pressure displacement at the foot plantar surface. Our proposed method uses the spatio-temporal sliding window processing to generate fall alarms and estimate the falling risk. The method was validated via a two-phase experimental protocol with five young adults who performed a walk of 20 stances with simulated sways using an instrumented shoe with resistive pressure sensors. The threshold of the normal walk THNand the risk level RLof the altered walk are determined as well as the risk of falling. The method can be applied in real-life and clinical settings with real-time processing.

Falls are events that affect almost every aging human being above the age of 65. These incidents can have major consequences on the physiological, psychological and socio-economical levels. In this paper, a simple smart carpet design is developed to detect falls using a novel sensing technique. Conventional sensing methods use either inertial measurement sensors (accelerometers, gyroscopes) or environmental sensors (infrared, force, vibration, acoustic, etc.). The proposed technique employs differential piezoresistive pressure sensors. The prototype of the system is implemented and tested using statistical methods. Experimental results show the sensitivity and the specificity of the system to be 88.8% and 94.9% respectively. The system could be deployed in home care environment as a final product. Our proposed sensing technique can be also integrated in beds to alert patients from falling during sleep.

In most developed countries, life expectancy has been increasing steadily and burden of chronic disease continues to grow. The chronic diseases are responsible for increasingly growing health spending. Telemonitoring systems provide a way to monitor patients and their needs within the comfort of their own homes. In the first systems, the data were sent directly to the medical experts to be interpreted. With technological advancements, software and applications have been developed to process the data. In this paper, we will focus on e-Care platform that combines the semantic web and artificial intelligence, for telemonitoring. e-Care is based on generic ontologies to accommodate different conditions and types of sensors and data. A decision support is bases on an inference engine, this engine is used for following up the health of the patient and the detection of abnormal situations and react accordingly, by providing recommendations and informing his physician with alerts.