Technologies for Managing the Health of Older Adults with Multiple Chronic Conditions: A Systematic Literature Review.

Multimorbidity is defined as the presence of two or more chronic medical conditions in a person, whether physical, mental or long-term infectious diseases. This is especially common in older populations, affecting their quality of life and emotionally impacting their caregivers and family. Technology can allow for monitoring, managing, and motivating older adults in their self-care, as well as supporting their caregivers. However, when several conditions are present at once, it may be necessary to manage several types of technologies, or for technology to manage the interaction between conditions. This work aims to understand and describe the technologies that are used to support the management of multimorbidity for older adults. We conducted a systematic review of ten years of scientific literature from four online databases. We reviewed a corpus of 681 research papers, finally including 25 in our review. The technologies used most frequently by older adults with multimorbidity are mobile applications and websites, and they are mostly focused on communication and connectivity. We then propose opportunities for future research on addressing the challenges in the management of several simultaneous health conditions, potentially creating a better approach than managing each condition as if it were independent.

Creativity in Generative Musical Networks: Evidence From Two Case Studies.

Deep learning, one of the fastest-growing branches of artificial intelligence, has become one of the most relevant research and development areas of the last years, especially since 2012, when a neural network surpassed the most advanced image classification techniques of the time. This spectacular development has not been alien to the world of the arts, as recent advances in generative networks have made possible the artificial creation of high-quality content such as images, movies or music. We believe that these novel generative models propose a great challenge to our current understanding of computational creativity. If a robot can now create music that an expert cannot distinguish from music composed by a human, or create novel musical entities that were not known at training time, or exhibit conceptual leaps, does it mean that the machine is then creative? We believe that the emergence of these generative models clearly signals that much more research needs to be done in this area. We would like to contribute to this debate with two case studies of our own: TimbreNet, a variational auto-encoder network trained to generate audio-based musical chords, and StyleGAN Pianorolls, a generative adversarial network capable of creating short musical excerpts, despite the fact that it was trained with images and not musical data. We discuss and assess these generative models in terms of their creativity and we show that they are in practice capable of learning musical concepts that are not obvious based on the training data, and we hypothesize that these deep models, based on our current understanding of creativity in robots and machines, can be considered, in fact, creative.

Creating Music With Fuzzy Logic.

Fuzzy logic is an artificial intelligence technique that has applications in many areas, due to its importance in handling uncertain inputs. Despite the great recent success of other branches of AI, such as deep neural networks, fuzzy logic is still a very powerful machine learning technique, based on expert reasoning, that can be of help in many areas of musical creativity, such as composing music, synthesizing sounds, gestural mappings in electronic instruments, parametric control of sound synthesis, audiovisual content generation or sonification. We propose that fuzzy logic is a very suitable framework for thinking and operating not only with sound and acoustic signals but also with symbolic representations of music. In this article, we discuss the application of fuzzy logic ideas to music, introduce the Fuzzy Logic Control Toolkit, a set of tools to use fuzzy logic inside the MaxMSP real-time sound synthesis environment, and show how some fuzzy logic concepts can be used and incorporated into fields, such as algorithmic composition, sound synthesis and parametric control of computer music. Finally, we discuss the composition of Incerta, an acousmatic multichannel composition as a concrete example of the application of fuzzy concepts to musical creation.

Volume visualization using a spatially aware mobile display device.

Volume visualization is a difficult three-dimensional task and a significant amount of research is devoted to the development of a suitable computer input device for it. Most of the proposed models use fixed displays, thus rendering extracted slices in orientations unrelated to their real locations within the volume. We present a new device which takes a different approach, as it leaves the volume in a fixed location and demands the user to change his or her posture to explore it from different angles. To implement this, we built a prototype based on a mobile display equipped with sensors that allows it to track its position, which is related to the location of the slice plane within the volume. Therefore, the user can manipulate this plane by displacing and rotating the display, which is a very intuitive method with minimum learning time. Furthermore, the postural changes required to use the device add a new channel of feedback, which effectively helps to reduce the cognitive load imposed on the user. We built a prototype device and tested it with two groups of volunteers who were asked to use it in a medical imaging application. Statistical analysis of the results shows that explorations made with the proposed device were considerably faster with no penalty in precision. We believe that, with further work, the proposed device can be developed into an useful tool for radiology and neurosurgery.