Smart Home: Cognitive Interactive People-Centric Internet of Things
This article proposes to integrate two entities, the Internet of Things and a cognitive dynamic system (CDS), and studies a smart home scenario as the application of interest. As a people-centric IoT, the smart home aims to enhance the intelligence level of the living environment and improve the quality of human life. Cognition, the distinct principles of which are perception–action cycle, memory, attention, intelligence, and language, can play a key role to pave the way for building truly smart homes. With cognition as its foundation, the engineering paradigm of CDS provides step-by-step guidelines for systematic development of smart homes. Hence, CDS can significantly contribute to the interactive IoT ecosystem.
Environment in which computing and communications technologies are employed for the use and control of different home appliances remotely or automatically to improve the resident’s quality of life. It can be viewed as a subclass of larger categories involving smart buildings or even smart cities. In the smart home scenario, “things” in IoT refer to a set of sensors and actuators for daily use. In this context, data gathered by sensors is transferred to a decision making unit, which computes suitable control signals for achieving predefined goals. These computed control signals are then sent to the corresponding actuators. In this way, a real-time control system is built over a network. In this scenario, the IoT components are remotely controlled; therefore, in effect, the communication network plays a key role. IoT may include a diverse range of devices, such as cameras and thermometers as sensors, and electrical appliances and electronic locks as actuators. Such components can be remotely controlled by a smartphone or a computer via Bluetooth or the Internet. The smart home may also benefit from programmable devices such as light switches.
In this article, we mainly focus on the smart home scenario based on CIoT. The supervision of CDS over the networked components of interactive IoT in a house will make a remarkable difference in our daily lives. To be more specific, let us take a look at the following situation, which will be referred to as the “falling- asleep problem” throughout the rest of this article: Imagine that a person is gradually falling asleep on his/her sofa while watching a TV drama in the living room on a Friday night. To ensure a good environment for sleep, the air conditioner, TV, sofa, and other appliances should be enabled to sense people’s movement, gestures, body temperature, and/or voice in a coordinated manner. Then the gathered information can be used to realize whether the resident is awake, asleep, or half-asleep. Knowing the state of the person in the room, appropriate decisions can be made to further comfort her/him. For instance, the TV itself gradually lowers or turns off the voice, the sofa slowly changes its shape into a bed, and the air conditioner dynamically adjusts the temperature to be suitable for sleep based on the body and room temperature. Moreover, the washer or dryer in the basement should also stop working to avoid noise (and restart to finish the work the next morning automatically). If the lights at the front door are still on, it would be better for them to be dimmed or turned off for energy conservation. The security systems should also become alert once the resident has fallen asleep. All of these visions can be brought into reality with a CDS acting as the “brain” of the household. Obviously, there are plenty of other situations that would also make the smart home seem very appealing. These situations share a similarity, which is that the home appliances are capable of sensing the changes in the environment and adjusting themselves to adapt to the environment cooperatively.
This article proposes using the cognitive dynamic system paradigm for enabling the Internet of Things with cognition, where the smart home is the application of interest. A smart home can benefit from different building blocks of the CDS: 1. The smart home must be aware of the household and its surroundings; the perceptual part of the CDS will do the job. 2. Implementing the CDS requires almost the same set of sensors/actuators, which are already used to perform daily tasks in a smart home. 3. The smart home must establish an efficient but very comfortable living environment for the resident; the executive part of the CDS equipped with attention and intelligence takes actions to achieve this goal. This list can continue. Therefore, the combination of CDS and IoT to form a CIoT is anticipated to have great advantages compared to the existing smart home applications. With the cognitive actions being performed from one cycle to the next, the quality of service and even the quality of experience of the CIoT will be significantly improved.
 V. Ovidiu and F. Peter, Internet of Things: Converging Technologies for Smart Environments and Integrated Ecosystems, River Publishers, 2013.
 C. Perera et al., “A Survey on Internet of Things: From Industrial Market Perspective,” IEEE Access, vol. 2, Dec. 2014, pp. 1660–79.
 A. A.-Fuqaha et al., “Internet of Things: A Survey on Enabling Technologies, Protocols, and Applications,” IEEE Commun. Surveys & Tutorials, vol. 17, no. 4, 4th qtr. 2015, pp. 2347–76
 A. Zanella et al., “Internet of Things for Smart Cities,” IEEE Internet Things J., vol. 1, no. 1, Feb. 2014, pp. 22–32.
 Q. Wu et al., “Cognitive Internet of Things: A New Paradigm Beyond Connection,” IEEE Internet Things J., vol. 1, no. 2, Apr. 2014, pp. 129–43.
 V. Foteinos et al., “Cognitive Management for the Internet of Things: A Framework for Enabling Autonomous Applications,” IEEE Vehic. Tech. Mag., vol. 8, no. 4, Dec. 2013, pp. 90–99.
 S. Haykin, Cognitive Dynamic Systems: Perception-Action Cycle, Radar, and Radio, Cambridge Univ. Press, 2012.
 S. Haykin, “Cognitive Dynamic Systems: Radar, Control, and Radio,” Proc. IEEE, vol. 100, no. 7, July 2012, pp. 2095– 2103.
 A. Zipperer et al., “Electric Energy Management in the Smart Home: Perspectives on Enabling Technologies and Consumer Behavior,” Proc. IEEE, vol. 101, no. 7, Nov. 2013, pp. 239–408.
 D. J. Cook et al., “CASAS: A Smart Home in a Box,” Computer, vol. 46, no. 7, July 2013, pp. 62–69.
 K. Xu et al., “Toward Software Defined Smart Home,” IEEE Commun. Mag., vol. 54, no. 5, May 2016, pp. 116–22.
 S. Haykin, Neural Networks and Learning Machines, 3rd ed., Pearson Press, 2009.