The processing power of Virtual Reality (VR) devices is constantly growing. However, few applications still take advantage of these capabilities. Machine learning algorithms have shown promise in enabling an immersive and personalized experience for VR device users. Therefore, it is interesting that these algorithms are processed directly on the devices themselves, without needing other external resources. In this work, a Neural Network (NN) is trained for real-time image classification using different VR devices. The results show the feasibility of incorporating VR devices for NN training without compromising the quality of the interaction, simply and saving external resources.
The rate at which the internet is growing is unstoppable due to the large number of connected smart devices. Manufacturers often develop specific protocols for their own devices that do not usually follow any standards. This hinders the interconnection and coordination of devices from different manufacturers, limiting the number of daily activities that can be supported. Some works are proposing different techniques to reduce this barrier and avoid the vendor lock-in issue. Nevertheless, this interconnection should also depend on the context. In this chapter, the authors propose a system to dynamically identify the interconnections required each specific situation depending on the context. This proposal has been tested in case studies focused on elderly people with the aim of automating their daily tasks and improving their quality of life. Further, in a world with an accelerated population aging, there is an increasing interest on developing solutions for the elderly living assistance through IoT systems.
The percentage of elder people in developed countries is increasing rapidly. A high percentage of them usually present multiple and chronic diseases. A patient with several diseases requires specific and coordinated care that is difficult to configure. Different frameworks can evaluate their functional status and identify the required care, together with the associated cost to the health system. Nevertheless, these frameworks are usually questionnaires that have to be periodically performed by the patients with the assistance of already overloaded professionals. In this chapter, the authors make use of mobile technologies to build a system capable of monitoring the activities of the elderly and analysing these data to assess their bio-psycho-social status. The experiments carried out show us that it correctly evaluates these patients and reduces the effort required by health professionals.
In the mobile device market there is a large number of applications to help people monitor intake or provide suggestions to lose weight and manage a healthy diet. However, the vast majority of these apps consume a lot of time by having to introduce food one by one. This paper presents the work to develop and pilot test a new Android application, FoodScan, aimed at people over 70, specially those from rural environments or with limited technical knowledge, to manage their food from the items that appear on their grocery receipts, avoiding the obligation to introduce one by one those foods, and generating recommendations. To achieve this final objective, specific objectives have been completed as indicated in the methods section. We conducted a review of current calorie control applications to learn about their weaknesses and strengths. Different algorithms were tested to expedite the introduction of food into the application and the most suitable for the FoodScan application was selected. Likewise, several options were taken into account to create the knowledge base of food, taking into account dietary recommendations for people over 70 years. Once developed, a pilot evaluation was carried out with a convenience sample of 109 volunteers in rural areas of Caceres and Valladolid (Spain) and Alentejo (Portugal). They tested FoodScan for a month after which they completed a user satisfaction survey. 93 % (101/109) believed that the app was easy to download and install, 66 % (72/109) thought that it was easy to use, 47 % (51/109) noted that the charts with the recommendations helped them with diet control and 49 % (53/109) indicated that FoodScan helped them improve healthy eating habits. One-month pilot evaluation data suggested that most users found the app somewhat helpful for monitoring food intake, easy to download and easy to use.
The high penetration and acceptance of smart devices has encouraged the development of IoT applications. The increase in the capabilities of these final devices has also led to the development of paradigms such as Fog and Edge Computing. Through these new architectural paradigms, developers can exploit the capabilities of the end devices to store, process and provide services, in order to improve the application by reducing the response time and the network overload. Currently, most applications are developed following a Server-Centric architecture because there are a lot of tools facilitating their development. However, these types of tools are not available for these emerging paradigms, which means an extra effort for developers. This paper shows a tool that semi-automatize the generation of applications based on the Edge Computing paradigm, thus reducing the developers' works and the application of these new architectural paradigms.
Dropout prediction is a problem that is being addressed with machine learning algorithms; thus, appropriate approaches to address the dropout rate are needed. The selection of an algorithm to predict the dropout rate is only one problem to be addressed. Other aspects should also be considered, such as which features should be selected and how to measure accuracy while considering whether the features are appropriate according to the business context in which they are employed. To solve these questions, the goal of this paper is to develop a systematic literature review to evaluate the development of existing studies and to predict the dropout rate in contractual settings using machine learning to identify current trends and research opportunities. The results of this study identify trends in the use of machine learning algorithms in different business areas and in the adoption of machine learning algorithms, including which metrics are being adopted and what features are being applied. Finally, some research opportunities and gaps that could be explored in future research are presented.
Abstract There are contexts where communication with TCP/IP protocol is not possible due to the lack of infrastructure or a reliable and continuous data transmission. In this cases, alternatives such as Opportunistic Networks (OPPNets) are valid. Such challenging conditions are common in rural areas and are a significant obstacle for the deployment of eHealth technologies for older adults. Considering this context, the present work introduces Interest-based System for Communication in Isolated Areas (ISCA), an OPPNet architecture for remote monitoring and emergency detection in ageing people who live alone. For this, the energetic requirements are considered, providing efficient and sustainable operation. The proposal makes use of a routing algorithm based on interests which enables asynchronous communication among entities. ISCA is evaluated over a realistic scenario and compared with similar state-of-the-art solutions. Experimental results show that ISCA notably improves the delivery probability with an enhancement of 52.25% in comparison to the second best alternative and provides a suitable average latency. Moreover, it also achieves better performance in terms of overhead and hops number compared to the other studied protocols