Intelligent Houses are very simmilar to Programmable houses, that are programmed to perform some activities. The difference is in a way the house is being programmed. In case of Programmable House technologies it was a human that needed to program or reprogram the house. In case of Intelligent Houses it would be done automatically by the house itself. This is achieved by the capability of the house to observe the inhabitants in the search for patterns. After the pattern is found the house would start performing the activities automatically every time the pattern would be noticed again.
By performing some activities for the people, the house can ensure, that some important activities like closing the door or activating an alarm when an inhabitant is going out of the house. There is a differentiation in Intelligent Houses between the systems reaction on simple sensor inputs and system recognizing and assessing situations. The second kind is much difficult to implement achieving a satisfactore reliability. Nevertheless the Intelligent Houses are capable of dealing with such problems. Intially there is a problem with the trade off between the house doing some unwanted activities or the house not performing activities that were expected. Finding the right parameters that would solve that problem would be a very long task that would require hundreds of adjustments. It is not a problem for a Intelligent House, as the ambient intelligence that is assessing the situations and scenarios is present all the time focusing on its improvements. So eventually the right reliability would be achieved.
Other advantages of the Intelligent House are capabilities of intrusion or accident detection. As the house is observing the inhabitant all the time and all their usual activities are stored, then it is possible to easily detect an unusual activity. In some circumstances it could be a sign that an intruder entered the house in others especially in case of elderly people is that a person for example fainted. In such cases the neighbours, police or health care can be informed.
The real difficulties are in the implementation of the learning algorithm. First of all the powerful infrastructure for the system is required. The house intelligence needs to be able to collect all the data from all the sensors, needs to store it and needs to be able to analyze them all the time. This requires a bigger storage and higher computational capabilities. Secondly to write an efficient learning algorithm is not an easy task. There are many research projects about Artificial Intelligence or Neural Networks. None of them have any extraordinary achievements. The only achievement is the possibility to create an efficient learning algorithm for a particular implementation, but such a task is extremely difficult and requires a lot of development.
The functionalities of Intelligent Houses mentioned above can be seen on the following scenarios. Additionally a legend to all symbols that are used in animations is presented at the following link:
Watching TV scenario
The scenario illustrates a functionality of Intelligent Houses to redirect the sound of a device to the speakers in another room. The inhabitant of the house (Tom) is watching TV and decides to go to the kitchen to fetch some food. On his way there, the house detects his movement and notices that the TV is on. The house compares the stored situations and finds out, that Tom always switches on the speakers in the kitchen while he is present there. Also Tom always switches off the speakers in a living room to preserve some energy. Thus the house when Tom enters the kitchen decides to switch on the speakers there. At the same time, it switches off the speakers in the living room, since nobody is present.
Automatic lights scenario
The scenario illustrates a ability of Intelligent Houses to automatically switch on and off lights in the house. After dusk, when an inhabitant is going from one room to another within a house, he or she switches on the light in a room that he or she enters and in the same time switches off the light in the room that he or she leaves. The house observes the habits of switching on and off the lights so later the lights can be switched on and off automatically. In this scenario Tom is watching TV. Afterwards he goes to the bathroom to brush his teeth and then he goes to bed. When he is walking in the house, the sensors detects his position and the appropriate lights are being switched on and off automatically.
Intrusion detection scenario
The scenario illustrates a functionality of Intelligent Houses to detect intruders. The house constantly monitors all inhabitants. Different sequences of sensor inputs are stored and used in a search for some patterns that can be used afterwards to facilitate the life of inhabitants. However, the stored data can also be used to detect scenarios that greatly differ from the ones stores in the database. In this scenario, Tom is sleeping and an intruder is breaking into his garage. The intruder manages to get quite far before being detected. The house detects the movement in the middle of the garage next to the car. All scenarios that are stored in the database are completely different. Always the sensor before the garage entrance or the sensor in the corridor detect some movement first. Then the video camera in the garage detects a person next to one of the entrances. As the current situation is different and the garage during the night is treated as a security area, hence the house classifies the situation as an intrusion. Then the video camera starts recording and the video stream is send to the Police station.
Accident detection scenario
The scenario illustrates a functionality of Intelligent Houses to detect accidents. Similarly to the previous scenario, the house database can be used to recognise unusual situations. If an inhabitant stays without movement in a place he or she have never stayed before for such a long time, there is a probability, that he or she for example fainted. In such a case the neighbours or a family members would be informed, so they can check that everything is ok. In this scenario, Tom is taking a bath after working in front of computer . The house detects such a scenario and classifies it as usual. After a long time the house notices that for a long while, there is no movement in the area, where an inhabitant has been before. This is different to all the scenarios that are stored in the database. Hence the house classifies the situation as a possible accident and informs the right people.