Selected papers from the 16th International Conference on Intelligent Environments (IE2020)

University campuses are normally constituted of large buildings responsible for high energy demand, and are also important as demonstration sites for new technologies and systems. This paper presents the results of achieving energy sustainability in a testbed composed of a set of four buildings that constitute the Telecommunications Engineering School of the Universidad Politécnica de Madrid. In the paper, after characterizing the consumption of university buildings for a complete year, different options to achieve more sustainable use of energy are presented, considering the integration of renewable generation sources, namely photovoltaic generation, and monitoring and controlling electricity demand. To ensure the implementation of the desired monitoring and control, an internet of things (IoT) platform based on wireless sensor network (WSN) infrastructure was designed and installed. Such a platform supports a smart system to control the heating, ventilation, and air conditioning (HVAC) and lighting systems in buildings. Furthermore, the paper presents the developed IoT-based platform, as well as the implemented services. As a result, the paper illustrates how providing old existing buildings with the appropriate technology can contribute to the objective of transforming such buildings into nearly zero-energy buildings (nZEB) at a low cost. Full article

In this work, a novel current metering device was presented. This device was intended to bring current metering capabilities to a wide variety of scenarios: Developing countries, rural areas, or any situation with technological constraints. The device was designed to provide a straightforward installation with no intrusion in the electrical panels. This was achieved by applying energy harvesting techniques and wireless communication technology for data transmission. The device was able to exploit the magnetic field inducted around a wire carrying electricity as energy harvesting, thus acquiring the power it needed to work. Since very low power was harvested, an efficient treatment for the incoming power and a minimal power consumption system were essential. Although exploiting the magnetic fields inducted around a wire has been used for years, the combination of this technology for both energy harvesting and current metering in an end-user device was off-center. To work in a wide variety of scenarios, it used Sigfox for communications as this brought wide coverage and out-of-the-box functioning. The theoretical design of the device was validated by verification assessments for the joint performance of the individual parts compounding the device, including metering capabilities and wireless communication test-bench. Finally, the metering device was tested under three distinct real-world scenarios that demonstrated the viability of the system. Results show that, depending on the metering period and the average current value in the mains line, the device could work forever acquiring and sending electricity consumption data. Perpetual working was achieved with an average current of 3.1 A to meter every 15 min, and an average current of 5 A for a 5-min metering period. Full article

Electroencephalography (EEG) signals to detect motor imagery have been used to help patients with low mobility. However, the regular brain computer interfaces (BCI) capturing the EEG signals usually require intrusive devices and cables linked to machines. Recently, some commercial low-intrusive BCI headbands have appeared, but with less electrodes than the regular BCIs. Some works have proved the ability of the headbands to detect basic motor imagery. However, all of these works have focused on the accuracy of the detection, using session sizes larger than 10 s, in order to improve the accuracy. These session sizes prevent actuators using the headbands to interact with the user within an adequate response time. In this work, we explore the reduction of time-response in a low-intrusive device with only 4 electrodes using deep learning to detect right/left hand motion imagery. The obtained model is able to lower the detection time while maintaining an acceptable accuracy in the detection. Our findings report an accuracy above 83.8% for response time of 2 s overcoming the related works with both low- and high-intrusive devices. Hence, our low-intrusive and low-cost solution could be used in an interactive system with a reduced response time of 2 s. Full article

In modern society, the average person spends more than 90% of their time indoors. However, despite the growing scientific understanding of the impact of light on biological mechanisms, the existing light in the built environment is designed predominantly to meet visual performance requirements only. Lighting can also be exploited as a means to improve occupant health and well-being through the circadian functions that regulate sleep, mood, and alertness. The benefits of well-lit spaces map across other regularly occupied building types, such as residences and schools, as well as patient rooms in healthcare and assisted-living facilities. Presently, Human Centric Lighting is being offered based on generic insights on population average experiences. In this paper, we suggest a personalized bio-adaptive office lighting system, controlled to emit a lighting recipe tailored to the individual employee. We introduce a new mathematical optimization for lighting schedules that align the 24-h circadian cycle. Our algorithm estimates and optimizes parameters in experimentally validated models of the human circadian pacemaker. Moreover, it constrains deviations from the light levels desired and needed to perform daily activities. We further translate these into general principles for circadian lighting. We use experimentally validated models of the human circadian pacemaker to introduce a new algorithm to mathematically optimize lighting schedules to achieve circadian alignment to the 24-h cycle, with constrained deviations from the light levels desired for daily activities. Our suggested optimization algorithm was able to translate our findings into general principles for circadian lighting. In particular, our simulation results reveal: (1) how energy constrains drive the shape of optimal lighting profiles by dimming the light levels in the time window that light is less biologically effective; (2) how inter-individual variations in the characteristic internal duration of the day shift the timing of optimal lighting exposure; (3) how user habits and, in particular, late-evening light exposure result in differentiation in late afternoon office lighting. Full article