Article Preview
Top1. Introduction
The use of various Intelligent Internet of Things (IoT) system’s techniques (Gupta and Shanker, 2020) for big data analytics is becoming popular now-a-days in most of the industrial and domestic applications, which is attributed to high performance and very low cost for different devices. Today, rapid developments in wearable sensors, actuators, the IoT, and intelligent algorithms form the foundation for new healthcare applications including pattern recognition or prognostic modeling (Gupta and Shanker, 2020). In the immediate future, aged persons and people with disabilities can utilize smart assistive technologies to enable them to carry out day to day regular activities, enjoy the fun events, experience entertainment, and make them socialize while retaining good health and well-being. The function of health-related activities (DariaBattini et al., 2013), that require information and communication technologies (Elharakanyrt al., 2018) complements those smart environments. The approaches for good health and well-being make use of sophisticated networks and IoT technologies. Intellectual disabilities, also known as mental retardation or general learning disability, are a group of disorders defined by diminished cognitive and adaptive functioning. Cognitive disabilities are typically categorezed in four phases, i.e., mild (about 80%), moderate (about 14%), severe (about 4%) and extreme (about 2%). Most cases are linked to mild to moderate type disorder. Thereofre, IntelliAssistant is a form of orientation (Liu et al., 2009; Carmien et al., 2005) for people of mild to moderate handicaps in earlier phases of cognitive disabilities (Dawe, 2006, pp. 1143–1152; American Psychiatric Association, 2013). The individual cannot use a mobile device in an advanced, serious, and extreme phase’s condition, and thus the orientation is not feasible. The key features of this type of location –based services (LBS) (Gupta and Shanker, 2018) were defined as being an on-going work (Ramos et al., 2013; Sadilek&Kautz, 2010). Augmented reality (AR) user interfaces in LBS has been used here to guide cognitively disabled persons. It reduced the cognition effort needed to understand the route to follow. While the device determines the best travel path, a screen should appear to remind the user to wait. The traveling route (Spichkova, 2016) needs to be fed to the speculative computing module for anticipating the users’ errors and ensuring the proper travel direction. The implementation and evaluation of the trajectory data mining method have been done for the aim of achieving the travel route to the user preferences. A person with cognitive impairments has the Trajectory (Lou et al., 2009) denoted as T from their log L. It is a sequenced series of GPS points with a successive interval that does not reach a fixed threshold Th. It is represented by T:p1→p2→···→pm, where, Th>pi+t·t>0 with (m >i≥1) and pi∈ P⊂L. The |T| is the number of samplings (|T| = m), and t is defined as the interval ofthe sampling point. P = p1, p2· · ·, pm are the arrangement of points known as GPS log, where each point pi ∈ P contains pi.lat, pi.lng, pi.t as latitude, longitude, and timestamp, respectively. Path W is a related street fragment arrangement that starts at vertex Vi and ends at Vj, i.e., W: e1→e2→···→en, where, Vi = e1.start, Vj= en.end, ek+1.start = ek.end, 1≤ k ≤ n. A summary of the GPS client movement log & Trajectory is given in Figure 1.
Figure 1. Log and trajectory for moving person
Figure 2. Illustrations of road segments