Search Results (8)

Guide dogs play a crucial role in enhancing independence and mobility for people with visual impairment, offering invaluable assistance in navigating daily tasks and environments. However, the extensive training required for these dogs is costly, resulting in a limited availability that does not meet the high demand for such skilled working animals. Towards optimizing the training process and to better understand the challenges these guide dogs may be experiencing in the field, we have created a multi-sensor smart collar system. In this study, we developed and compared two supervised machine learning methods to analyze the data acquired from these sensors. We found that the Convolutional Long Short-Term Memory (Conv-LSTM) network worked much more efficiently on subsampled data and Kernel Principal Component Analysis (KPCA) on interpolated data. Each attained approximately 40% accuracy on a 10-state system. Not needing training, KPCA is a much faster method, but not as efficient with larger datasets. Among various sensors on the collar system, we observed that the inertial measurement units account for the vast majority of predictability, and that the addition of environmental acoustic sensing data slightly improved performance in most datasets. We also created a lexicon of data patterns using an unsupervised autoencoder. We present several regions of relatively higher density in the latent variable space that correspond to more common patterns and our attempt to visualize these patterns. In this preliminary effort, we found that several test states could be combined into larger superstates to simplify the testing procedures. Additionally, environmental sensor data did not carry much weight, as air conditioning units maintained the testing room at standard conditions. Full article

Technological innovation has revolutionized healthcare, particularly in neurological rehabilitation, where it has been used to address chronic conditions. Smart home and building automation (SH&BA) technologies offer promising solutions for managing chronic disabilities associated with such conditions. This single group, pre-post longitudinal pilot study, part of the H2020 HosmartAI project, aims to explore the integration of smart home technologies into neurorehabilitation. Eighty subjects will be enrolled from IRCCS San Camillo Hospital (Venice, Italy) and will receive rehabilitation treatment through virtual reality (VR) and robotics devices for 15 h per day, 5 days a week for 3 weeks in the HosmartAI Room (HR), equipped with SH&BA devices measuring the environment. The study seeks to optimize patient outcomes and refine rehabilitation practices. Findings will be disseminated through peer-reviewed publications and scientific meetings, contributing to advancements in neurological rehabilitation and guiding future research. Full article

Given the advancements in modern living standards and technological development, conventional smart devices have proven inadequate in meeting the demands for a high-quality lifestyle. Therefore, a revolution is necessary to overcome this impasse and facilitate the emergence of flexible electronics. Specifically, there is a growing focus on health detection, necessitating advanced flexible preparation technology for biosensor-based smart wearable devices. Nowadays, numerous flexible products are available on the market, such as electronic devices with flexible connections, bendable LED light arrays, and flexible radio frequency electronic tags for storing information. The manufacturing process of these devices is relatively straightforward, and their integration is uncomplicated. However, their functionality remains limited. Further research is necessary for the development of more intricate applications, such as intelligent wearables and energy storage systems. Taking smart wear as an example, it is worth noting that the current mainstream products on the market primarily consist of bracelet-type health testing equipment. They exhibit limited flexibility and can only be worn on the wrist for measurement purposes, which greatly limits their application diversity. Flexible energy storage and flexible display also face the same problem, so there is still a lot of room for development in the field of flexible electronics manufacturing. In this review, we provide a brief overview of the developmental history of flexible devices, systematically summarizing representative preparation methods and typical applications, identifying challenges, proposing solutions, and offering prospects for future development. Full article

This work is devoted to a cost-effective method for the automatic placement of visual sensors within a smart room to ensure the requirements for its design. Various unique conditions make the process of manually placing sensors time consuming and can also lead to a decrease in system efficiency. To automate the design process, we solve a multi-objective optimization problem known as the art gallery problem in 3D, modified as follows. For the specified regions of interest within a smart room, the required pixels per meter level (PPM) should be ensured. The optimization criteria are visibility of the room and the cost of equipment. To meet these criteria, we describe a room model with doors, windows, and obstacles represented in such a way as to consider their impact on the field of view of the sensors. To model sensor placement, a genetic algorithm is used. The optimal solution is selected from the Pareto front by means of the technique for order of preference by similarity to ideal solution (TOPSIS). The developed method’s effectiveness has been tested on modeling real premises of various types. The method is flexible because of the assignment of weights to certain aspects when placing sensors. Further, it can be scalable to other types of sensors. Full article

Suction cups (SCs) are used extensively by the industrial sector, particularly for a wide variety of automated material-handling applications. To enhance productivity and reduce maintenance costs, an online supervision system is essential to check the status of SCs. This paper thus proposes an innovative method for condition monitoring of SCs coated with printed electronics whose electrical resistance is supposed to be correlated with the mechanical strain. A simulation model is first examined to observe the deformation of SCs under vacuum compression, which is needed for the development of sensor coating thanks to the 3D printing process. The proposed design involves three circle-shaped sensors, two for the top and bottom bellows (whose mechanical strains are revealed to be the most significant), and one for the lip (small strain, but important stress that might provoke wear and tear in the long term). For the sake of simplicity, practical measurement is performed on 2D samples coated with two different conductive inks subjected to unidirectional tensile loading. Graphical representations together with analytical models of both linear and nonlinear piezoresistive responses allows for the characterization of the inks’ behavior under several conditions of displacement and speed inputs. After a comparison of the two inks, the most appropriate is selected as a consequence of its excellent adhesion and stretchability, which are essential criteria to meet the target field. Room temperature extrusion-based 3D printing is then investigated using a motorized 3D Hyrel printer with a syringe-extrusion modular system. Design optimization is finally carried out to enhance the surface detection of sensitive elements while minimizing the effect of electrodes. Although several issues still need to be further considered to match specifications imposed by our industrial partner, the achievement of this work is meaningful and could pave the way for a new generation of SCs integrated with smart sensing devices. The 3D printing of conductive ink directly on the cup’s curving surface is a true challenge, which has been demonstrated, for the first time, to be technically feasible throughout the additive manufacturing (AM) process. Full article

Solving the challenge of occupancy prediction is crucial in order to design efficient and sustainable office spaces and automate lighting, heating, and air circulation in these facilities. In office spaces where large areas need to be observed, multiple sensors must be used for full coverage. In these cases, it is normally important to keep the costs low, but also to make sure that the privacy of the people who use such environments are preserved. Low-cost and low-resolution heat (thermal) sensors can be very useful to build solutions that address these concerns. However, they are extremely sensitive to noise artifacts which might be caused by heat prints of the people who left the space or by other objects, which are either using electricity or exposed to sunlight. There are some earlier solutions for occupancy prediction that employ low-resolution heat sensors; however, they have not addressed nor compensated for such heat artifacts. Therefore, in this paper, we presented a low-cost and low-energy consuming smart space implementation to predict the number of people in the environment based on whether their activity is static or dynamic in time. We used a low-resolution $(8\times 8)$ and non-intrusive heat sensor to collect data from an actual meeting room. We proposed two novel workflows to predict the occupancy; one that is based on computer vision and one based on machine learning. Besides comparing the advantages and disadvantages of these different workflows, we used several state-of-the-art explainability methods in order to provide a detailed analysis of the algorithm parameters and how the image properties influence the resulting performance. Furthermore, we analyzed noise resources that affect the heat sensor data. The experiments show that the feature classification based method gives high accuracy when the data are clean from noise artifacts. However, when there are noise artifacts, the computer vision based method can compensate for those artifacts providing robust results. Because the computer vision based method requires an empty room recording, the feature classification based method should be chosen either when there is no expectancy of seeing noise artifacts in the data or when there is no empty recording available. We hope that our analysis brings light into understanding how to handle very low-resolution heat images in these environments. The presented workflows could be used in various domains and applications other than smart offices, where occupancy prediction is essential, e.g., for elderly care. Full article

The monitoring of small houses and rooms has become possible due to the advances in IoT sensors, actuators and low power communication protocols in the last few years. As buildings are one of the biggest energy consuming entities, monitoring them has great interest for trying to avoid non-necessary energy waste. Moreover, human behaviour has been reported as being the main discrepancy source between energy usage simulations and real usage, so the ability to monitor and predict actions as opening windows, using rooms, etc. is gaining attention to develop stronger models which may lead to reduce the overall energy consumption of buildings, considering buildings thermal inertia and additional capabilities. In this paper, a case study is described in which four meeting rooms have been monitored to obtain information about the usage of the rooms and later use it to predict their future usage. The results show the possibility to deploy a simple and non-intrusive sensing system whose output could be used to develop advanced control strategies. Full article

In this paper, we see the Data Centers (DCs) as producers of waste heat integrated with smart energy infrastructures, heat which can be re-used for nearby neighborhoods. We provide a model of the thermo-electric processes within DCs equipped with heat reuse technology, allowing them to adapt their thermal response profile to meet various levels of hot water demand. On top of the model, we have implemented computational fluid dynamics-based simulations to determine the cooling system operational parameters settings, which allow the heat to build up without endangering the servers’ safety operation as well as the distribution of the workload on the servers to avoid hot spots. This will allow for setting higher temperature set points for short periods of time and using pre-cooling and post-cooling as flexibility mechanisms for DC thermal profile adaptation. To reduce the computational time complexity, we have used neural networks, which are trained using the simulation results. Experiments have been conducted considering a small operational DC featuring a server room of 24 square meters and 60 servers organized in four racks. The results show the DCs’ potential to meet different levels of thermal energy demand by re-using their waste heat in nearby neighborhoods. Full article