Abstract
Ambient Intelligence (AmI) is built using sensors and actuators connected through real-time networks for smart systems. The data and signals captured from sensors are ambiguous for both human and machine. Artificial Intelligence (AI) is merged into an ambient environment to translate data and signals into a language understandable by human users and to transform an operational setting from machine-centered to human-centered. However, the implementation of AI technology into an ambient environment requires quantitative modeling approaches to emphasize system requirements. This article aims to give a clear snapshot of the design and structure of advanced AmI technology for an AmI-based decision support system (Am-IDSS). The proposed approach explores the basic principles of an Am-IDSS structure concerning the role of the Internet, data, Industrial robotics, and other AI technologies for smart manufacturing. To supplement this research, the study is concluded by proposing managerial suggestions for systems development and observations about future trends in implementing Am-IDSS.
TopIntroduction
Competitiveness among companies and nations is forcing decision makers in companies to strategically re-creating manufacturing processes and supply chains toward smart production. The goals of smart manufacturing include: 1) optimizing production and increasing profitability and innovation, 2) responding to market changes faster and with agility, 3) better-informed decisions, and 4) more flexibility in physical processes, cf., Clemons, 2018. Smart manufacturing can create dynamic, competitive operations, and global supply chains by using intelligent computerized control, advanced information technologies, the Internet of Things (IoT) technologies, and flexible manufacturing systems.
Research in the broad area of smart manufacturing and its challenges for encompassing IDSS into the production process appeared in a wide range of topics and methodologies. For instance, Simeone et al. (2019) investigated the requirements for cloud manufacturing platform for making a sharing platform in the smart manufacturing network. Weber (2018) introduced effective stakeholders in measuring key performance indicators (KPIs) for the smart production process in the high-tech industry. Meng et al. (2018) considered the smart recovery decision-making process for sustainable manufacturing purposes. Latorre-Biel et al. (2018) designed a Petri net model of a smart factory regarding the Industry 4.0 paradigm as virtualization for decision making support. Avventuroso et al. (2017) introduced a networked production system to implement virtual enterprise and product lifecycle information loops. Preuveneers et al. (2017) reviewed the emerging trends on the smartness of manufacturing, including the relevant research challenges and opportunities to shape an IDSS. Brodsky et al. (2014) investigated the decision support system for reusable components, including knowledge, data, control variables, and decisions, for leading the environment to the smartness. However, there is a lack of a good snapshot of quantitative modeling approaches and trends based on system engineering design, emphasizing system requirements analysis and specification, the use of alternative analytical methods and systems’ evaluation.
The purpose of this article is to introduce an IDSS based on AmI technology for smart manufacturing landscape, emphasizing on design and structure of AmI technology and covers the technological foundations of smart manufacturing. To build essential knowledge around AI technology and its role in influencing Am-IDSS platform, we are focusing almost exclusively on issues relevant to understanding, constructing, and analyzing the different challenges of smart manufacturing from the system engineering point of views based on human-centric computer (HCC) interaction design.
Our approach is to explain the basic principles of Am-IDSS structure in the area of smart manufacturing. First, we address the new and rapidly growing role of the internet and high-tech computing in manufacturing. Other topics include the definition of smart manufacturing, smart DSS, AI potentials for smart manufacturing, and the necessity for advance Am-IDSS in smart manufacturing. Thereafter, problems of coordinating the advanced robotics, Cyber-Physical systems (CPS), IoT and admitting the big-data, machine learning, and cloud and cognitive computing in industrial development will discuss. Following these topics, the structure of Am-IDSS including component of collaborations, services and logical issues in Am-IDSS, infrastructural layers of Am-IDSS such as physical, functional, integrated, and human-computer layers, architecture of human-centered DSS, components of database module, information collection components, components of knowledge management (KM) module, decision making process components, and user-interface components will be reviewed. The system engineering design of each model implements the role of AI in different segments of Am-IDSS. Models and applications of Am-IDSS for smart manufacturing will be explored, including (not limited) the advanced manufacturing processes, rapid prototyping, collaborative virtual factory (VF) platforms, advanced human-machine interaction (HMI), machine-to-machine (M2M) communication, and open manufacturing. The development and future trend of IDSS for smart manufacturing such as HCC and Information architect (IA) will discuss.
Key Terms in this Chapter
Executive Information Systems (EIS): A branch of management information system which facilitates the decision-making system’s needs. EIS merges with user-experience knowledge. In recent years, by entering advance technologies such as augmented reality, and turning to a smarter environment, EIS lost its popularity.
Case-Based Reasoning: The process of learning to solve new problems based on the solutions of similar past problems.
Service-Oriented Architecture (SOA): The software-based design of services for application components over a network and communication protocol. One individual SOA system can contain other sub-SOA, it is self-contained and acts and updates independently from its vendor.
Context Awareness: The property of mobile devices which define the location awareness. The location is used to identify how a particular process is operating around a contributed device, such as a smartphone.
Human-Centric Computer (HCC): The design, development, and analysis of a mixed-initiative human-computer system. It emerges two concepts of human-computer interaction and information science together to increase the usability of information and system by human and machine.
Rule-Based Reasoning: The process of learning to solve new problems based on the research and the application of AI.
Haptic/Kinesthetic Computing: A mechanical simulation for creating the sense of touch by applying vibrations, forces, or motions to users for controlling the virtual devices or remote-control machines or robots.
Ambient Intelligence (AmI): Refers to a data-intensive environment that senses changes in state and responds appropriately to correct, act and alert. The goal of this sensor-rich AmI environment is stability and homeostasis.
Pervasive/Ubiquitous Computing: Accessibility of computing in any place at any device and with any format, through the aid of mobile computing, sensors, internet, AI, context awareness and human-computer interaction.
Semantic Web: An integrator which provides a framework for sharing and reusing data for every application, enterprise, and community. It is an extension or the World Wide Web.