1,720,990 research outputs found
Managing plug-in electric vehicles in eco-environmental operation optimization of local multi-energy systems
No full textLocal multi-energy systems (LMES) have been recently recognized as a promising alternative to centralized energy supply systems to meet local energy needs, since they promote efficient use of the available energy thanks to the coordination of heat and power technologies, storage, flexible demand and plug-in electric vehicles (PEVs). In this framework, PEVs represent loads to satisfy in the grid-to-vehicle (G2V) mode, while also serving as distributed storage when equipped with vehicle-to-grid (V2G) technology, and can provide both economic and environmental benefits if properly managed. The contribution of this paper is to present a comprehensive multi-objective optimization model for the energy management of an LMES in the presence of PEVs, with the aim to combine maximization of LMES operator's profit with the minimization of CO2 emissions. The LMES supplies electricity, heat and cooling to a building cluster with PEVs, which can operate in both G2V and V2G modes. The problem consists of dispatching technologies in the LMES and finding the optimized charging/discharging strategies of PEVs in order to maximize the operator's profit while also reducing CO2 emissions, and it is addressed by formulating a multi-objective linear programming problem with the detailed modeling of interdependencies among energy carriers. The weighted sum method is used to represent the eco-environmental optimization problem, and it is solved by using CPLEX solver and considering a cluster of office buildings located in Italy as end-user of the LMES with PEVs owned by the offices’ employees. Testing results demonstrate the effectiveness of the optimization framework to maximize the operator's profit while also reducing the CO2 emissions, thanks to the optimal coordination of the multiple energy carriers in the LMES and the effective management of the flexibility collected at both supply and demand sides. Moreover, it is found that through the optimized charging and discharging strategies, the PEVs, acting as distributed energy storage, allow the provision of demand response services by also complementing renewable power to improve energy efficiency. In detail, under the economic optimization, most of flexibility collected from PEVs is sold into the wholesale market in order to maximize the operator's profit, whereas, under the environmental optimization, the power discharged from PEVs is exploited for self-use in the LMES to minimize environmental impacts by using a carbon-free source
Hear to see-See to hear: A smart home system user interface for visually or hearing-impaired people
No full textIn this paper, we introduce a novel approach to design a user interface for commercial Smart Home Systems (SHS), following the needs of visually or hearing impaired users. The interface is able to transform visual information and alarms into audio signals and vice versa by using a mobile application. The aim of the interface is to make a commercial SHS usable for visually or hearing-impaired people, while maintaining a high level of acceptability, due to the use of an inclusive device, i.e., the smartphone. © 2018 IEEE
A machine-learning based emotion recognition system in patients with Parkinson's disease
No full textIn this paper, a Machine-Learning Based Emotion Recognition System in patients with Parkinson's disease is presented. The development of this system is composed of three steps. Firstly, each user is required to execute an experimental protocol while a simple device (i.e., smartwatch), worn on the wrist, collects data. During the experimental protocol, a nine-point clinical scale and a commercial emotion recognition software have been used to identify emotions. Secondly, from smartwatch data, features extraction is implemented. Lastly, a Machine Learning Algorithm (MLA) is trained with extracted features as input and emotion classes as output
Cross-domain classification of physical activity intensity: An eda-based approach validated by wrist-measured acceleration and physiological data
Full text linkPerforming regular physical activity positively affects individuals’ quality of life in both the short-and long-term and also contributes to the prevention of chronic diseases. However, exerted effort is subjectively perceived from different individuals. Therefore, this work explores an out-of-laboratory approach using a wrist-worn device to classify the perceived intensity of physical effort based on quantitative measured data. First, the exerted intensity is classified by two machine learning algorithms, namely the Support Vector Machine and the Bagged Tree, fed with features computed on heart-related parameters, skin temperature, and wrist acceleration. Then, the outcomes of the classification are exploited to validate the use of the Electrodermal Activity signal alone to rate the perceived effort. The results show that the Support Vector Machine algorithm applied on physiological and acceleration data effectively predicted the relative physical activity intensities, while the Bagged Tree performed best when the Electrodermal Activity data were the only data used
A sensor fusion approach for measuring emotional customer experience in an intelligent retail environment
No full textCustomer experience depends not only on the aspects which retailers can easily control, but also on emotional factors that are unpredictable. In this paper, a Multi-Task MultiKernel learning approach is proposed to recognise positive users' emotion in a retail scenario. The overall system is composed by the Ultra-Wide Band (UWB) tracking system and a consumer smartwatch device. Data gathered from sensors are combined in a multi-kernel scenario to estimate shoppers emotion (i.e., valence and arousal) which is strictly correlated to different shoppers feelings. Results in term of accuracy and macro-F1 score prove the effectiveness and the suitability of the proposed approach
AI-Powered Home Electrical Appliances as Enabler of Demand-Side Flexibility
No full textIn the digitalization era, the increasing number of connected appliances and the rise of artificial intelligence (AI) enabled a new realm of possibilities in the residential energy sector, including the chance for a consumer to play an active role in flexibility programs. We talk about demand-side flexibility (DSF) when a consumer adapts his/her energy consumption behavior in response to variable energy prices or market incentives. The procedure depends on a two-way communication between an energy supplier and a customer, and his/her willingness to act on the electricity consumption. The success of the different DSF approaches is strongly related to the estimation of appliance usage patterns and AI techniques represent a viable solution
A Gamification Approach For Residential Electricity Demand Decarbonization
No full textReduction and decarbonization of residential electricity consumption has become a major goal for EU. The use of ICT applications is one of the main drivers to reach this target. In this paper authors introduce a hardware and software solution able to monitor residential electricity consumption, suggest energy management/efficiency actions and products, guide and monitor user progresses towards a virtuous energy behavior. Gamification features (charts, badges, achievements) have been then added to the platform in order to enhance the engagement of users
An Open Source Electric Vehicle Simulator with Battery Aging Modeling
No full textThe ever growing incidence of electric vehicles in the transportation industry required the development of innovative strategies and tools to help engineers in the design of demand side management strategies and to solve grid issues. In this study, a battery aging model is integrated in an electric vehicle simulator in order to better reproduce the vehicle's life in a consumer perspective and for Vehicle-to-grid applications
A stress detection system based on multimedia input peripherals
No full textIn this paper a Stress Detection System based on Machine Learning Algorithms (MLAs), keyboard and mouse data is presented. The development of this system is composed by three steps. Firstly, each user performs some tasks while a web application framework collects data from keyboard and mouse. At the end of each task, he/she communicates the stress level in order to create the stress class. Secondly, from collected data, features extraction and features selection procedures through a Neighborhood Component Analysis (NCA) are implemented. Lastly, three MLAs, trained with features as input and stress classes as output, are implemented to detect stress
A comparative study of driver torque demand prediction methods
Full text linkThe performances of energy management systems or electric vehicles and hybrid electric vehicles are highly dependent on the forecast of future driver torque/power request sequence that affects vehicle efficiency and economy. Since the behaviour of the driver is challenging to model/predict by first-principles models, modern artificial intelligence algorithms would represent feasible methods for approaching this problem in real-world automotive systems. This work provides a comparative study and analysis of performances of different data-driven torque prediction strategies. The studied and compared torque demand prediction techniques are exponentially varying model, linear regression, shallow and deep neural networks, and least square support vector machine-based approaches. The prediction performance and computational cost of these techniques are evaluated and reported, and the possibility of exploiting these techniques in real-world scenarios is also discussed
- …
