In this digitized world, data has become an integral part in any domain, including healthcare. The healthcare industry produces a huge amount of digital data, by utilizing information from all sources of healthcare, including the patients' demographics, medications, vital signs, physician's observations, laboratory data, billing data, data from various wearable sensors, etc. With the rapid growth of the wireless technology applications, there has also been a significant increase in the digital health data. New medical discoveries and new eHealth-related technologies, such as mobile apps, novel sensors, and wearable technology have contributed as important data sources for healthcare data. Nowadays, there is a huge potential to improve the healthcare quality and customer satisfaction with the help of machine learning (ML) algorithms applied on time-domain and frequency-domain healthcare data obtained from wearables and sensors. This systematic literature review examines in depth how health data from sensors can be processed and analyzed using ML techniques. The review focuses on the following diseases for obtaining the eHealth data: diabetes mellitus type 1 and type 2, hypertension and hypotension, atrial fibrillation, bradykinesia, dyskinesia, and fever related diseases. The data for the systematic literature review was collected from four databases, Medline, Proquest, Scopus, and Web of Science. We selected 67 studies for the final in-depth review out of the initial pre-selected papers. Our study identified that the major part of eHealth data is obtained from the sensors such as accelerometer, gyroscopes, ECG (Electrocardiogram), EEG (Electroencephalogram ) monitors, and blood glucose sensors. This study also examines the different feature types, feature extraction methods, and ML algorithms used for eHealth data analysis. Our review also shows that neural network (NN) algorithms and support vector machines (SVM) have shown so far the best performance for analyzing the healthcare data among other ML algorithms studied in the literature.

As an inevitable process, the number of older adults is increasing in many countries worldwide. Two of the main problems that society is being confronted with more and more, in this respect, are the inter-related aspects of feelings of loneliness and social isolation among older adults. In particular, the ongoing COVID-19 crisis and its associated restrictions have exacerbated the loneliness and social-isolation problems. This paper is first and foremost a comprehensive survey of loneliness monitoring and management solutions, from the multidisciplinary perspective of technology, gerontology, socio-psychology, and urban built environment. In addition, our paper also investigates machine learning-based technological solutions with wearable-sensor data, suitable to measure, monitor, manage, and/or diminish the levels of loneliness and social isolation, when one also considers the constraints and characteristics coming from social science, gerontology, and architecture/urban built environments points of view. Compared to the existing state of the art, our work is unique from the cross-disciplinary point of view, because our authors’ team combines the expertise from four distinct domains, i.e., gerontology, social psychology, architecture, and wireless technology in addressing the two inter-related problems of loneliness and social isolation in older adults. This work combines a cross-disciplinary survey of the literature in the four aforementioned domains with a proposed wearable-based technological solution, introduced first as a generic framework and, then, exemplified through a simple proof of concept with dummy data. As the main findings, we provide a comprehensive view on challenges and solutions in utilizing various technologies, particularly those carried by users, also known as wearables, to measure, manage, and/or diminish the social isolation and the perceived loneliness among older adults. In addition, we also summarize the identified solutions which can be used for measuring and monitoring various loneliness- and social isolation-related metrics, and we present and validate, through a simple proof-of-concept mechanism, an approach based on machine learning for predicting and estimating loneliness levels. Open research issues in this field are also discussed.

Loneliness and social isolation are subjective measures associated with the feeling of discomfort and distress. Various factors associated with the feeling of loneliness or social isolation are: the built environment, long-term illnesses, the presence of disabilities or health problems, etc. One of the most important aspect which could impact feelings of loneliness is mobility. In this paper, we present a machine-learning based approach to classify the user loneliness levels using their indoor and outdoor mobility patterns. User mobility data has been collected based on indoor and outdoor sensors carried on by volunteers frequenting an elderly nursing house in Tampere region, Finland. The data was collected using Pozyx sensor for indoor data and Pico minifinder sensor for outdoor data. Mobility patterns such as the distance traveled indoors and outdoors, indoor and outdoor estimated speed, and frequently visited clusters were the most relevant features for classifying the user’s perceived loneliness levels.Three types of data used for classification task were indoor data, outdoor data and combined indoor-outdoor data. Indoor data consisted of indoor mobility data and statistical features from accelerometer data, outdoor data consisted of outdoor mobility data and other parameters such as speed recorded from sensors and course of a person whereas combined indoor-outdoor data had common mobility features from both indoor and outdoor data. We found that the machine-learning model based on XGBoost algorithm achieved the highest performance with accuracy between 90% and 98% for indoor, outdoor, and combined indoor-outdoor data. We also found that Lubben-scale based labelling of perceived loneliness works better for both indoor and outdoor data, whereas UCLA scale-based labelling works better with combined indoor-outdoor data.

This paper addresses the issue of generating the frequent closed Itemset in distributed environment. Some algorithms have been proposed earlier there but they are suffering from the drawbacks like: Increasing communication load or frequent communication between the nodes for transferring information. So some algorithm need to be proposed which could solve these two drawbacks simultaneously and this paper have propose one such algorithm so that the mining of the datasets present in the distributed environment could be done effectively and with less theoretical complexity.