A Cognitive-IoE Approach to Ambient-intelligent Smart Home

Abstract

In today's world, we are living in busy metropolitan cities and want our homes to be ambient intelligent enough towards our cognitive requirements for assisted living in smart space environment and an excellent smart home control system should not rely on the users' instructions. Cognitive IoE is a new state-of-art computing paradigm for interconnecting and controlling network objects in context-aware perception-action cycle for our cognitive needs. The interconnected objects (sensors, RFID, network objects etc.) behave as agents to learn, think and adapt situations according to dynamic contextual environment with no or minimum human intervention. One most important recent research problem is "how to recognize inhabitant activity patterns from the observed sensors data". In this paper, we proposed a two level classification model named as ACM (Ambient Cognition Model) for inhabitant's activities pattern recognition, using Hidden Markov Model based probabilistic model and subtractive clustering classification method. While subtractive clustering separates similar activity states from non-similar activity state, a HMM works as the top layer to train systems for temporal-sequential activities to learn and predict inhabitant activity pattern proactively. The proposed ACM framework play, a significant role to identify user activity intention in more proactive manner such as routine, location, social activity intentions in smart home scenario. The experimental results have been performed on Matlab simulation to evaluate the efficiency and accuracy of proposed ACM model.

A Survey on Data Perception in Cognitive Internet of Things

“…Context aware computing. Jamnal et al [38] have proposed a new form of ambient intelligent architecture for smart homes by anticipating occupant's intentions for understanding purpose. This is achieved with a combined knowledge from traditional context aware pervasive systems and present epoch of CIoT technologies.…”

A Multi-Agent System for Service Provisioning in an Internet-of-Things Smart Space Based on User Preferences

“…AmI and CIoT are intertwined, with overlapping application scenarios [ 8 , 9 , 10 , 11 ]. Although the distinction between the terms may be subtle, Jamnal and Liu [ 12 ] argue that CIoT extends the capabilities of AmI in smart environments, going beyond monitoring and supporting people’s tasks to proactively influencing users’ plans and intentions.…”

“…Groupu_agent 5 proposition:[12, 76] backed ranges: [1/1][2/4] → forward proposition u_agent 6 proposition:[43, 100] backed ranges: [1/1][4/4] → forward proposition Round 1-Group 2 u_agent 3 proposition: [82, 100] backed ranges: [0/1][2/4] → broaden range [74, 100] u_agent 4 proposition: [43, 67] backed ranges: [0/1][3/4] → forward proposition u_agent 3 proposition: [74, 100] backed ranges: [0/1][3/4] → forward proposition u_agent 4 proposition: [43, 67] backed ranges: [0/1][3/4] → forward proposition Round 1/2-Group 1 u_agent 1 proposition: [88, 96] backed ranges: [0/1][2/4] → broaden range [76, 96] u_agent 2 proposition: [59, 71] backed ranges: [0/1][3/4] → forward proposition u_agent 1 proposition: [76, 96] backed ranges: [0/1][3/4] → forward proposition u_agent 2 proposition: [59, 71] backed ranges: [0/1][3/4] → forward proposition Round 2-Group 2 u_agent 3 proposition: [74, 100] backed ranges: [0/1][3/4] → forward proposition u_agent 4 proposition: [43, 67] backed ranges: [0/1][3/4] → broaden range [43, 73] u_agent 3 proposition: [74, 100] backed ranges: [0/1][3/4] → broaden range [72, 100] u_agent 4 proposition: [43, 73] backed ranges: [0/1][3/4] → forward proposition u_agent 3 proposition: [72, 100] backed ranges: [1/1][3/4] → forward proposition u_agent 4 proposition: [43, 73] backed ranges: [1/1][3/4] → forward proposition Round 2/3-Group 1 u_agent 1 proposition: [76, 96] backed ranges: [0/1][3/4] → broaden range → final proposal 73 u_agent 2 proposition: [59, 71] backed ranges: [0/1][4/4] → forward proposition…”

Home automation:HMM based fuzzy rule engine for Ambient intelligent smart space

“…The aim of an ambient intelligent system is to provide comfortable assisted living to inhabitants. Scientific work has been done in ambient intelligent space such as Care-lab, CASAS, Grator-Tech HIS, aware home, iDorm and MavHome projects, the process of activity recognition is subdivided into four part as (i)sensing, (ii)data-preprocessing, (iii)data modelling for feature extraction (iv)feature selection [1]. Many blue-chip companies including IBM Watson, researching into identifying inhabitants preference, activity patterns to provide a customized digital assistant for granting access and controlling various appliance to automated tasks [2].…”

“…HMM is a generative probabilistic model used for identifying hidden states <s1,s2,..,sn>from given observation sequences<o1,o2,..on> [3]. Furthermore, [1] suggested that observable state sequence(st1) at time t , depends only on the current state(st), irrespective of previous state (st -1).During HMM training we tend to find optimal state sequence with higher probability of Pr(S|O), 1 1 DOI reference number: 10.18293/SEKE2017-035 known as most likelihood pattern. As an iterative trend, HMM require re-estimation of input parameters to train the system (transition and emission matrix), Baum-welch algorithm work well here as solution.…”