Wisdom Web of Things

An emerging hyper-world encompasses all human activities in a social-cyber-physical space. Its power derives from the Wisdom Web of Things (W2T) cycle, namely, “from things to data, information, knowledge, wisdom, services, humans, and then back to things.” The W2T cycle leads to a harmonious symbiosis among humans, computers and things, which can be constructed by large-scale converging of intelligent information technology applications with an open and interoperable architecture. The recent advances in cloud computing, the Internet/Web of Things, big data and other research fields have provided just such an open system architecture with resource sharing/services. The next step is therefore to develop an open and interoperable content architecture with intelligence sharing/services for the organization and transformation in the “data, information, knowledge and wisdom (DIKW)” hierarchy. This chapter introduces Wisdom as a Service (WaaS) as a content architecture based on the “paying only for what you use” IT business trend. The WaaS infrastructure, WaaS economics, and the main challenges in WaaS research and applications are discussed. A case study is described to demonstrate the usefulness and significance of WaaS. Relying on the clouds (cloud computing), things (Internet of Things) and big data, WaaS provides a practical approach to realize the W2T cycle in the hyper-world for the coming age of ubiquitous intelligent IT applications.

Development of methods for Wisdom Web of Things (W2T) should be based on foundations of computations performed in the complex environments of W2T. We discuss some characteristic features of decision making processes over W2T. First of all the decisions in W2T are very often made by different agents on the basis of complex vague concepts and relations among them (creating domain ontology) which are semantically far away from dynamically changing and huge raw data. Methods for approximation of such vague concepts based on information granulation are needed. It is also important to note that the abstract objects represented by different agents are dynamically linked by them with some physical objects and the aim is very often to control performance of computations in the physical world for achieving the target goals. Moreover, the decision making by different agents working in the W2T environment requires mechanisms for understanding (to a satisfactory degree) reasoning performed in natural language on concepts and relations from the domain ontology. We discuss a new computation model, where computations are progressing due to interactions of complex granules (c-granules) linked with the physical objects. C-granules are defined relative to a given agent. We extend the existing Granular Computing (GrC) approach by introducing complex granules (c-granules, for short) making it possible to model interactive computations of agents in complex systems over W2T. One of the challenges in the approach is to develop methods and strategies for adaptive reasoning, called adaptive judgement, e.g., for adaptive control of computations. In particular, adaptive judgement is required in the risk/efficiency management by agents supported by W2T. The discussed approach is a step toward realization of the Wisdom Technology (WisTech) program. The approach was developed over years of work on different real-life projects.

Computers are getting smaller, cheaper, faster, with lower power requirements, more memory capacity, better connectivity, and are increasingly distributed. Accordingly, smartphones became more of a commodity worldwide, and the use of smartphones as a platform for ubiquitous computing is promising. Nevertheless, we still lack much of the architecture and service infrastructure we will need to transition computers to become situation aware to a similar extent that humans are. Our Everything is Alive (EiA) project illustrates an integrated approach to fill in the void with a broad scope of works encompassing Ubiquitous Intelligence (RFID, spatial searchbot, etc.), Cyber-Individual (virtual world, 3D modeling, etc.), Brain Informatics (psychological experiments, computational neuroscience, etc.), and Web Intelligence (ontology, workflow, etc.). In this chapter, we describe the vision and architecture for a future where smart real-world objects dynamically discover and interact with other real or virtual objects, humans or virtual humans. We also discuss how the vision in EiA fits into a seamless data cycle like the one proposed in the Wisdom Web of Things (W2T), where data circulate through things, data, information, knowledge, wisdom, services, and humans. Various open research issues related to internal computer representations needed to model real or virtual worlds are identified, and challenges of using those representations to generate visualizations in a virtual world and of “parsing” the real world to recognize and record these data structures are also discussed.

In recent years, after the proposal of the Internet of Things and, later, of the Web of Things, context awareness is a central issue at various levels including devices, communications and applications. In this chapter we present an overview of the current state of research in autonomic communications by focusing on aspects of context awareness on which the emerging new paradigm of Context-Aware Autonomic Communication systems is based. As an example of application we also provide a synthetic analysis of the problem of contextual search and of the issues related to defining contextual search systems.

Systematic brain informatics studies on mental health care produce various health big data of mental disorders and bring new requirements on the data acquisition and computing, from the data level to the information, knowledge and wisdom levels. Aiming at these challenges, this chapter proposes a brain and health big data center. A global content integrating mechanism and a content-oriented cloud service architecture are developed. The illustrative example demonstrates significance and usefulness of the proposed approach.

Given its complexity, understanding the behavior of users on the Web has been one of the most challenging tasks for data mining-related fields. Historically, most of the approaches have considered web logs as the main source of data. This has led to several successful cases, both in industry and academia, but has also presented several issues and limitations. Given the new challenges and the need for personalization, improvement is required in the overall understanding of the processes that lie behind web browsing decision making. The use of neurodata to support this analysis represents a huge opportunity in terms of understanding the actions taken by the user on the web in a more comprehensive way. Techniques such as eye tracking, pupil dilation and EEG analysis could provide valuable information to craft more robust models. This chapter overviews the current state of the art of the use of neurodata for web-based analysis, providing a description and analysis in terms of the feasibility and effectiveness of each strategy given a specific problem.

Healthcare is a challenging issue for persons with physical disabilities (e.g., the elderly). One significant issue refers to non-adherence of medication regimens in geriatric healthcare, particularly among elderly patients who live alone. To address this problem, thousands of ubiquitous hardware (e.g., smart objects) and software (e.g., u-pillbox, etc.) have been developed. Although partial solutions were given, it is important to have a comprehensive understanding to medication adherence. This requires a framework expected to host healthcare devices, execute related applications, and provide an open platform for accessing and interacting with other healthcare systems (e.g., hospital and pharmacy). This chapter proposes a W2T data cycle based holistic elderly healthcare framework and demonstrates its functionality with a u-pillbox system for the elderly. The u-pillbox system consists of three main processes: data acquisition of the elderly situation and medicine taking state; data analysis and elderly model enhancement; and provision of empathetic services to the elderly, in which cyber-I, human model, data cycle for the spiral quality of model enhancement, knowledge fusion towards wisdom for providing smart services are our critical concepts and techniques. Although this system is designated for geriatric healthcare, it has a potential extension to general health monitoring and care at home.

A social event is often unlimitedly amplified and promptly spread in blogspace, and it is valuable to correctly detect blog hot topics for managing the cyberspace. Although hot topic detection techniques have a great improvement, it is more significant o find what determines the life span of a blog topic, because the online consensus brought by the topic unavoidably experiences the real life. The W2T (Wisdom Web of Things) methodology considers the information organization and management from the perspective of Web services, which contributes to a deep understanding of online phenomena such as users’ behaviors and comments in e-commerce platforms and online social networks. This chapter first applies the W2T methodology to analyze the formation and evolution of a blog hot topic, and some influential factors which determine the development of the topic are identified to recognize hot topics. And then, the construction of a blog topic model considers information granularity in order to detect and track the evolution of the topic. Experimental results show that the proposed method for detecting the blog hot topic is feasible and effective.

Internet of things (IoT) is an attractive paradigm for intelligent interconnections among ubiquitous things through physical-cyber-social space (CPSS). During the things’ cross-space interactions, heterogeneous sensors establish pervasive sensing during with the mapping from physical objects into the corresponding cyber entities in the cyber space. Such mapping depends on the available system resources, and thus resource allocation becomes challenging for resource-constrained IoT applications. In this chapter, human attention (including sustained attention, selective attention, and divided attention) is considered as limited cognitive resource to establish an attention-aware resource framework in IoT. The consideration of a heterogeneous sensors based IoT system model is built with ubiquitous attributes, and a human attention inspired resource allocation scheme is presented to facilitate the dynamic resource interaction.

Wisdom Web of Things (W2T) can be modeled and studied from the perspective of complex networks. The complex network perspective aims to model and characterize complex systems that consist of multiple and interdependent components. Among the studies on complex networks, topological structure analysis is of the most fundamental importance, as it represents a natural route to understand the dynamics, as well as to synthesize or optimize the functions, of networks. A broad spectrum of network structural patterns have been respectively reported in the past decade, such as communities, multipartites, hubs, authorities, outliers, bow ties, and others. In this chapter, we show that many real-world networks demonstrate multiplex structure patterns. A multitude of known or even unknown (hidden) patterns can simultaneously exist in the same network, and moreover they may be overlapped and nested with each other to collaboratively form a heterogeneous, nested or hierarchical organization, in which different connective phenomena can be observed at different granular levels. In addition, we show that such patterns hidden in exploratory networks can be well defined as well as effectively recognized within an unified framework consisting of a set of proposed concepts, models, and algorithms. Our findings provide a strong evidence that many real-world complex systems are driven by a combination of heterogeneous mechanisms that may collaboratively shape their ubiquitous multiplex structures as we currently observe. This work also contributes a mathematical tool for analyzing different sources of networks from a new perspective of unveiling multiplex structure patterns, which will be beneficial to Wisdom Web of Things.

With the increasing popularity of mobile phones, large amounts of real and reliable mobile phone data are being generated every day. These mobile phone data represent the practical travel routes of users and imply the intelligence of them in selecting a suitable route. Usually, an experienced user knows which route is congested in a specified period of time but unblocked in another period of time. Moreover, a route used frequently and recently by a user is usually the suitable one to satisfy the user’s needs. ACT-R (Adaptive Control of Thought-Rational) is a computational cognitive architecture, which provides a good framework to understand the principles and mechanisms of information organization, retrieval and selection in human memory. In this chapter, we employ ACT-R to model the process of selecting a suitable route of users. We propose a cognition-inspired route recommendation method to mine the intelligence of users in selecting a suitable route, evaluate the suitability of the routes, and recommend an ordered list of routes for subscribers. Experiments show that it is effective and feasible to recommend the suitable routes inspired by cognition.

With the development of the Internet of things, monitoring systems for the safety of building structure (SBS) provide people with the important data about the main supporting points in the buildings. More and more data give the engineers an overload work problem, which can be solved by a systematic method making these monitoring systems more reliable, efficient and intelligent. Under the framework of the Wisdom Web of Things (W2T), we design a monitoring system for the SBS, by using the semantic technology. This system establishes a data cycle among the physical world (buildings), the social world (humans) and the cyber world (computers), and provides various services in the monitoring process to alleviate the engineers’ workload. In this system, the sensors which are connected via cable or wireless way, are used to monitor the different parameters of building structure. The semantic data can be obtained and represented by RDF to describe the meanings of sensor data, and can provide the application background for users. LarKC, a platform for scalable semantic data processing, is used for semantic querying about the data. Based on this uniform representation of data and semantic processing, intelligent services can be provided by the effective data analysis. This provides the possibility to integrate all of the monitoring systems for the safety of building structure in urban computing.

The chapter summarizes main aspects of brain informatics based big data interacting with a social-cyber-physical space of Wisdom Web of Things (W2T). It describes how to realize human-level collective intelligence as a big data sharing mind—a harmonized collectivity of consciousness on the W2T by developing brain inspired intelligent technologies to provide wisdom services, and it proposes five guiding principles to deeper understand the nature of the vigorous interaction and interdependence of brain-body-environment.