so that the householder has a positive return on investment? An answer to that question can
encourage the aforementioned transition.
In order to make the smart home transition profitable, each customer is supposed to use its own HEMS to maximize its comfort level or/and minimizes its cost. If the same tariffs are used for every user, they will try to consume more electricity in cheaper periods rather than expensive ones. With the increase in the number of smarthomes, a new problem for the generator company (GENCO) appears: a high-peak load consumption in cheaper periods. Hence, the coordination of the users’ consumption can attenuate this problem. One coordination approach is Demand Response (DR) programs, which expects that customers change their electricity consumption in response to incentive: payments or different tariffs. Comparing with industries, individual residences have little contribution to the DR strategies output due to the scale of consumption. Aggregators, entities that aggregates the consump- tion of many users, are used to compromise interests of a group of users and a GENCO, which are keeping comfort level and minimizing electricity bills for users, and minimizing costs for the GENCO.
We apply artificial intelligence techniques to perform data analysis and activity recognition in smarthomes. Sensors embedded in smart home provide primary data to reason about observations and provide appropriate assistance for residents to complete their Activities Daily Livings (ADLs). These residents may suffer from different levels of Alzheimer disease. In this paper, we introduce a qualitative approach that considers spatiotemporal specifications of activities in the Activity Recognition Agent (ARA) to do knowledge representation and reasoning about the observations. In this paper, we consider different existing uncertainties within sensors observations and Observed Agent‟s activities. In the introduced approach if the more details about environment context be provided, the less activity recognition process complexity and more precise functionality is expected.
Our approach for on-line activity recognition from audio and home automation sensors is detailed in this section. In SmartHomes, AR can be performed from a set of very heterogeneous raw data streams of various sensors, such as binary presence detectors (Presence Infra-Red sensors or PIR), continuous microphone sig- nals or temperature measurement. To handle this het- erogeneity, the overall strategy we adopted is to sum- marise data from these sensors within temporal sliding windows to generate vectors of attributes that will feed into an activity classifier. This approach relies on the hypothesis that each instance of any activity is com- posed of a set of events whose observations are cap- tured by the set of sensors. These observations are sig- natures of the activities and they can be described by statistics of predefined variables computed over tem- poral windows shorter than the minimal activity dura- tion. Although activities captured in this manner might be large scale activities, we showed that they can pro- vide sufficient contextual information to an home au- tomation decision module .
Keywords: smarthomes; user-centered decision making; Markov decision process
Research on smarthomes and on ambient-assisted living has grown these last years. This is due mainly to the low price of sensors and actuators and their facility of installation. This brought some new applications, using data mining techniques, to improve the way of responding of automation systems. An application appeared these last year with the evolution of the population in developed countries. The augmentation of quality of life and of the capacity of the medicine made people live longer. However, problems appear when the person starts losing autonomy. Lots of research nowadays concentrate on the use of ambient assisted living architectures to monitor elderly people at home. This is done using, for instance, activity recognition to evaluate the performances of Activities of Daily Living (ADL).
One of the field that uses these possibilities of acquiring data is telemedicine. Indeed with the evolution of the world population, we face a lack of institution and one of the solution could be to remotely monitor elderly people to detect, as early as possible, a dangerous evolution of the state of the person. This can be achieved in multiple ways, including Health SmartHomes  that uses sensors integrated in the environment of the person to analyze his activity during long-term measurements. This leads to different applications, but the one that we would like to favor with this work is an assistance to the geriatricians to complete the autonomy evaluation of the person using scales like Activities of Daily
Demographic change and ageing in developed countries imply challenges for the society to continue to improve the well being of its elderly and frail inhabitants. Since the dramatic evolution of Information and Communication Technologies (ICT), one way to achieve this aim is to promote the development of smarthomes. In the health domain, a health smart home is a habitation equipped with a set of sensors, actuators, automated devices and centralised software controllers specifically designed for daily living task support, early detection of distress situations, remote monitoring and promotion of safety and well-being . Among all the interaction and sensing technologies used in smarthomes (e.g., infra-red sensors, contact doors, video cameras, RFID tags, etc.), audio processing technology has a great potential to become one of the major interaction modalities. Voice interfaces can be much more adapted to disabled people and the ageing population who have difficulties in moving or seeing than tactile interfaces (e.g., remote control) which require physical and visual interaction. Moreover, audio processing is particularly suited to distress situations .
Index Terms—Natural Language Understanding, Smart Envi- ronments, Deep Neural Network, Voice-User Interface
I. I NTRODUCTION
Smart-homes with integrated voice-user interfaces (VUI) can provide in-home assistance to aging individuals , allow- ing them to retain autonomy . It is also a domain of great interest for the industry . Such systems usually include sev- eral modules, such as Automatic Speech Recognition (ASR), Natural Language Understanding (NLU) and Decision Making modules. The NLU module takes as input a transcript of the voice command provided by the ASR module and extracts its meaning in a form that can be processed by the Decision Making module.
Last but not least, one of the most pressing concerns for the smart home technologies is regarding the security and the privacy of the collected, stored and transmitted data. In our case, the data may contain sensitive, protected or confidential information, such as the health data, that may endanger residents’ privacy and safety, if breached. Therefore, ensuring strong data encryption, database security, secured communication channels, and so on and so forth is required for the next generation smarthomes. In Ref. [ 43 ], the authors investigate these issues, by providing a holistic approach of security together with recommendations and good practices for all the stakeholders involved in the smart home environment. The study focuses mainly on the IoT devices inside the smart home (which can be either constrained or with high capability), the interaction and data exchange with remote services and finally the interaction and data exchange with mobile applications. Even though this work implements a security layer in order to guarantee the fundamental security requirement, which are: the confidentiality and integrity, the authentication, and the access control. However, still, he security and the privacy are not the core of this proposition, since, the main goal of this work is the proposition of a new smart home architecture encompassing both the energy and the health services. Therefore, a deeper security and privacy analysis is subject of future work.
The results presented previously can be seen as intuitive. However, they show some interesting tradeoffs that need to be considered when proposing a DR solu- tion. As suggested by the results, a fine grained control may not be always needed depending on the system’s available capacity: its value is the highest for very low capacities. As a matter of fact, a solution based on static information can have high performance thanks to the deployment of a fine grained solution in smart- homes that can manage to efficiently schedule appliances based on user’s needs when capacity is high enough.
Aging-in-place usually means the need for punctual health services (physiotherapy, nursing, etc.) at the home of the person. In the context of a shortage of clinical professionals, this often proves challenging and threatens the security of the person if their services are not adequate. It is why, in this context, smarthomes are embraced as a potentially cheap alternative to enable secure, semi-autonomous life for the elders . Most of the smart home initiatives adopt the model based on cheap ubiquitous sensors distributed in strategic places in the environment of the person such as passive infrared sensors, electromagnetic contacts, smart plugs, and temperature sensors . These types of sensors produce little data, are often noisy, and provide a very partial view of what is happening in the smart home. Therefore, a large body of the literature focuses on developing and improving pattern recognition algorithms in order to make the most out of this scarce data . Nevertheless, there are fundamental limits to the improvement of the patterns that can be extracted from such data. Consequently, some teams, including ours, try to develop or exploit more informative technology. For instance, passive RFID can be exploited to track a multitude of objects in the smart home giving approximate movement information . This rich data is, however, difficult to exploit. Moreover, spatial data tends to reduce the model generalization . Some teams prefer to rely on wearable technology  which usually embed an Inertial Central Unit (IMU) and sometimes other sensors providing information on the health status (photoplethysmogram, tremor sensor, heart rate sensor). The IMU in itself can provide a variety of information on the ADLs of the person. The main disadvantages of wearables are that they must be charged daily and that it depends on the will of the person to always wear it. Another alternative replacing ubiquitous sensors is vision-based technology . Vision-based sensing has the advantage of being more expressive in terms of information. Nevertheless, it is generally considered as more challenging to extract the interesting information (i.e., correct segmentation of the image). Moreover, the smarthomes based on these technologies are more difficult to generalize since changing conditions may significantly affect the performance of those methods (i.e., light intensity in the smart home environment). Finally, the main reason preventing the adoption of vision-based technologies for aging-in-place is probably their perceived intrusiveness .
We have two take-away messages. First, longitudinal experiments of a EUDE like SPOK in real-world settings require a middleware that reliably supports dynamic software adaptation and automatic deployment. Secondly, an initial deployment using “our own dog food” in homes of project team members provides highly valuable information for tuning the protocols before the start of field studies, thus improving the quality of the evaluation itself while saving time and discovery for future research.
Electricity Demand at the Feeder Scale
Summary The feeder electricity demand sums up all of the individual demand of the clients connected to an electric feeder. The number of clients connected ranges from 1000 to 10,000 depending on the population density. Compared to the features of the individual electricity demand measured by smart meters, the measures of this feeder demand have several advantages: they are exhaustive all clients are included, non-invasive individual demand is hidden among the others, and have been col- lected over a long period decades or so. Substantial research has been devoted to the demand at this scale, and what drives it. These driving eects have been clearly identied at this aggregated scale, such as the temperature inuence. In fact, the aggre- gation smooths out the individual behavior and reveals the eects, even marginal, that are indistinguishable at the individual scale. This means that forecasting the feeder demand for short to medium horizons, up to several weeks in advance, is quite e- cient: state-of-the-art relative errors are around 10%. On the other hand, forecasting for longer horizon necessitates a better understanding of the underlying mechanisms of the demand. Such task is yet necessary for planning the network infrastructure.
HMSs promote human safety in healthcare for the var- ious stakeholders including the elderly, caregivers, emer- gency personnel, etc. This factor is of paramount impor- tance in healthcare and remains a concern. It has been studied in a number of surveys such as , , and . The authors in  provide five major recommen- dations when considering safety factors: build capacity among caregivers to understand the HFE, integrate HFE into medical technologies, increase the number of human factors and ergonomic practitioners in healthcare institu- tions, expand investments in improvement efforts informed by HFE, and support interdisciplinary research. For sub- jects, these factors are perceived as the most useful of HMS systems and are usually the main causes of subjects leaving their homes and moving to care facilities. HMSs are ex- pected to continually provide care services, like emergency help and accident detection, especially when caregivers are away. HMSs should ensure the safety of subjects and care- givers in various settings and prevent violence and abuse from any source including from subjects with mental dis- orders. HMS could may rely on existing tools, ranging from simple presence sensors to video surveillance systems with advanced functionalities such as movement pattern tracking and recognition, real-time alerts, etc. Biometric sensors can also be used for detecting the signs of stress and aggression especially in healthcare institutions.
Figure 2: Components of the framework for the e-health monitoring system.
3.3. Framework description
Daily activities represent the context in our context-aware approach. It is used as the base layer for the different functionalities such as sensing, processing, and recommending services (Fig. 2). The person evolves in a smart space with adequate sensors. Data is collected and transmitted by sensors in a continuous or periodic way. The coordinator analyses and processes the received data. Streams coming from different sources are handled by the data management system, which is able to apply database primitives such as queries and updates. The analysis agents consider the person’s profile which includes dependency-context (D.C.) and history-context (H.C.) for a specific period of time. The first inference is applied to set up the monitoring mode. This is achieved thanks to the connection between the analysis agents and the model-base management. The latter selects the geriatric model which is in turn considered in the data management and combined with input data to adjust the monitoring. Finally, sensing and processing data will result in recommending e-health services adapted to the person’s situation.
Our contribution. We define a script language for voters to express ranked, possibly complex, delegations in collective decisions with multiple issues (Section 2). The intended ap- plication is voting in a purely preferential setting (deciding on food is a perfect example [see, e.g., Hardt and Lopes, 2015]), and delegations are seen as a way to elicit trust or influence relations among voters. To transform profiles of smart ballots into direct votes for alternatives we propose four unravelling procedures (Section 2), and we show that they terminate in polynomial time (Section 3). The final objective of smart vot- ing is that of obtaining a collective decision from the agents’
This chapter deals with smart bolometers according to the IEEE 1451.2 definition of smart sensors which states that smart sensors are sensors that provide functions beyond those necessary for generating a correct representation of a sensed or controlled quantity. Test, identification and configurability are some examples of functions beyond conventional use, also called smart functions. Such smart functions contribute to an easier use of sensors and allow the sensors to take into account parameters discrepancies or evolutions. For instance, identification can be used to compensate for discrepancies between bolometers due to the process variations during the technological fabrication. Identification can, as well, allow the sensors to adjust to aging effects during their operating life. Combined with the configurability, the identification function makes possible to satisfy a large number of applications. The configurability takes advantage of the operation in a closed-loop mode to overcome the traditional trade-off between time constant and responsivity (Rice, 2000) and allows some flexibility in the choice of these characteristics.
Despite the increasing usage of the Cloud by mobile application, exploiting its full potential is not done in systematic and well structured manner. Furthermore both mobile’s and Cloud’s contexts are managed separately, therefore the benefits of the Cloud upon mobile technology remains limited. Addressing this challenges to question that must be asked is; how to take advantage of the Cloud in a smart manner? Our suggested Answer is an environment composed of three levels: Architectural level, the intermediate level composed of two middleware Smart Cloud Gate and Smart Mobile Cloud Middleware. Finally the last level consists of mobile level (i.e. application level). An overview
Canadian research has implications for smoke detectors in homes Su, J. Z.
L’accès à ce site Web et l’utilisation de son contenu sont assujettis aux conditions présentées dans le site LISEZ CES CONDITIONS ATTENTIVEMENT AVANT D’UTILISER CE SITE WEB.