A new imputation-based incomplete data-driven fuzzy modeling for accuracy improvement in ubiquitous computing applications

Purpose In real-world decision-making, high accuracy data analysis is essential in a ubiquitous environment. However, we encounter missing data while collecting user-related data information because of various privacy concerns on account of a user. This paper aims to deal with incomplete data for fuzzy model identification, a new method of parameter estimation of a Takagi–Sugeno model in the presence of missing features. Design/methodology/approach In this work, authors proposed a three-fold approach for fuzzy model identification in which imputation-based linear interpolation technique is used to estimate missing features of the data, and then fuzzy c-means clustering is used for determining optimal number of rules and for the determination of parameters of membership functions of the fuzzy model. Finally, the optimization of the all antecedent and consequent parameters along with the width of the antecedent (Gaussian) membership function is done by gradient descent algorithm based on the minimization of root mean square error. Findings The proposed method is tested on two well-known simulation examples as well as on a real data set, and the performance is compared with some traditional methods. The result analysis and statistical analysis show that the proposed model has achieved a considerable improvement in accuracy in the presence of varying degree of data incompleteness. Originality/value The proposed method works well for fuzzy model identification method, a new method of parameter estimation of a Takagi–Sugeno model in the presence of missing features with varying degree of missing data as compared to some well-known methods.

Smartlife: A Point of Intelligence for Wireless Sensor Networks in Ubiquitous Environment

As home becomes more technologically advanced nowadays people not only need to protect their homes and families from theft or fire, but from carbon monoxide, excessive heat or low temperatures, flooding as well as monitoring their loved ones while they are away. In this research Project, we present the design case for an intelligent embedded system (Hardware and Software) called "SmartLife". We build a working prototype for SmartLife which is made up of tiny sensors, mobile devices, appliances and personal computers from diverse sources. Considering diversity in smart home environment the architecture must be open and flexible to embrace a variety of entities without any special favor towards particular participants or target domains. SmartLife will be the point of intelligence in the smart home environment (complete pervasive environment) which not only communicates with wireless sensors network (monitor & control) but also provides a secure state of mind to elderly homeowners. The work introduces the basics of uClinux kernel as well as the differences between uClinux and the general purpose operating system Linux. It also introduces FPGA based softcore CPU NIOS-II as an embedded platform for our research project. Our uClinux based architecture provides an integrated and comprehensive framework for building pervasive applications. We describe the design and implementation of our architecture as well as building SmartLife application within it.

Smartlife: A Point of Intelligence for Wireless Sensor Networks in Ubiquitous Environment

As home becomes more technologically advanced nowadays people not only need to protect their homes and families from theft or fire, but from carbon monoxide, excessive heat or low temperatures, flooding as well as monitoring their loved ones while they are away. In this research Project, we present the design case for an intelligent embedded system (Hardware and Software) called "SmartLife". We build a working prototype for SmartLife which is made up of tiny sensors, mobile devices, appliances and personal computers from diverse sources. Considering diversity in smart home environment the architecture must be open and flexible to embrace a variety of entities without any special favor towards particular participants or target domains. SmartLife will be the point of intelligence in the smart home environment (complete pervasive environment) which not only communicates with wireless sensors network (monitor & control) but also provides a secure state of mind to elderly homeowners. The work introduces the basics of uClinux kernel as well as the differences between uClinux and the general purpose operating system Linux. It also introduces FPGA based softcore CPU NIOS-II as an embedded platform for our research project. Our uClinux based architecture provides an integrated and comprehensive framework for building pervasive applications. We describe the design and implementation of our architecture as well as building SmartLife application within it.

Modeling the process of personal digital archiving through ubiquitous and desktop devices: A systematic review

The purpose of this study is to explore Personal Digital Archiving, and its practices, reasons, and challenges in desktop and in ubiquitous environment such as desktop computers, laptops, mobile phones or smartphones, tablets, and cloud services. Moreover, it is also aimed to develop a model of Personal Digital Archiving process for desktop and ubiquitous devices. This study used Preferred Reporting Items for the Systematic Review and Meta-Analysis guidelines for searching and devising, and inclusion and exclusion criteria. The Search was conducted from selected repositories, databases, and core journals, potentially containing studies related with Personal Digital Archiving. Consequently, 21 studies were included through identification, screening, eligibility, and inclusion of studies process. It was found that people used multiple devices such as mobile phones or smartphones along with other devices. It was established that people had also used cloud services with different devices including computers and smartphones or tablets for Personal Digital Archiving. Five major categories of individuals’ Personal Digital Archiving practices, that is, backup, replication or duplication, reorganizing and updating, cleaning or removing, and migration of information were found. Moreover, emotional motives, technological causes, alternative access, easy retrieval, and task completion were the reasons to adopt Personal Digital Archiving. On the basis of findings of selected studies, researchers developed a four steps model of Personal Digital Archiving process, consisting of initiation, identification, action, and evaluation constructs. Personal Digital Archiving challenges were also identified such as the individuals had to face through the use of desktop and ubiquitous devices including technical, fragmented and overloaded information, lack of training and expertise, and psychological and miscellaneous challenges. Personal Digital Archiving process model is based on the extracted data from studies published worldwide, and it is useful for both desktop and ubiquitous devices with reference to Personal Information Management context. The findings of the study will be helpful for software designers and android application developers to design and develop users’ centered Personal Information Management software.

Personal information management through ubiquitous devices: Students’ mobile self-efficacy and PIM practices

This study aims to explore personal information management (PIM) practices of undergraduate university students on ubiquitous devices such as mobile phones. The purpose was to investigate the relationship between mobile self-efficacy and mobile-based PIM practices of the respondentsin terms of finding/re-finding, keeping and organizing information. This study was the offspring of a PhD project. The quantitative research design was used to conduct this study. Structured questionnaire was used to collect data from undergraduate students Regression analysis was applied to investigate the relationship between mobile self-efficacy and their mobile based PIM practices. The findings revealed that undergraduate students search, browse, and scan information through mobile phones. They used keywords, searched from recently opened file, and from send item to find/re-find information. They save their personal information in folders, use mobile applications, and take screen shot of information to keep it for future use. Current study reported “ Sharing as keeping ‘as a new phenomenon in mobile based personal information keeping (ubiquitous environment). This study also reported ‘ Ubiquity’ as an emerging trend in PIM among young generation. Study found positive correlations between mobile self-efficacy and mobile based PIM. Current study developed a model of mobile self-efficacy and PIM. Based on new phenomena “ sharing as keeping’ (which occurred in current study), a model “mobile based personal information keeping” may be developed. This study helps software developers of smartphones to develop mobile phone applications according to users’ needs. This study provides better understanding of PIM model (finding/re-finding, keeping and organizing information) through ubiquitous devices (smart phones). Although studies have been conducted to know the impact or relationship between mobile self-efficacy and PIM, but no comprehensive study has been conducted to explore the relationship between mobile self-efficacy and the holistic picture of mobile based PIM (finding/re-finding, keeping, and organizing information) especially in developing countries like Pakistan.

Cyberbullying From a Research Viewpoint

In less than two decades, social media has become a part of life for many people, increasing the positive and negative effects of social relationships. In a sense, the traditional offline behaviors moved into a ubiquitous environment, enhancing the social phenomenon of cyberbullying. Thus, it attracted much attention from different fields within academia. To understand how research has been conducted in the last 20 years and the topics addressed, this study applied a bibliometric analysis to academic literature from 2000 to 2020 related to cyberbullying in social media, using techniques such as citation analysis, co-citation analysis, and content analysis. The growing interest of the field is confirmed, and some research gaps are unveiled. Since this is one of the first studies to explore cyberbullying that occurs in social media networks, it is hoped that this chapter will stimulate further research on this topic reinforcing the gaps found.

Dynamic Scheduling Framework of the Flexible Mixed-Model Assembly Line Based on the Internet of Manufacturing Things

To satisfy the needs of market customization, the traditional manufacturing is gradually transforming and upgrading into the intelligent manufacturing. In mass customization (MC), the assembly operations of modular products tend to be organized as the form of flexible mixed-model assembly line (FMMAL). The dynamic scheduling problem of FMMAL is quite complex with three issues of the product sequencing, station allocation and material delivery. At the same time, the disruption events of station failure, product inserting and product reworking are also considered. To solve this problem, a comprehensive framework combining the architecture of Internet of Manufacturing Things (IoMT) with the dynamic scheduling algorithms is proposed. Firstly, the IoMT-based FMMAL are constructed via the multi-agent system (MAS) and ubiquitous environment. Secondly, a mathematical model of FMMAL are formulated with the decision variables, optimization objectives and constraint conditions. Thirdly, the IoMT-oriented algorithms for dynamic scheduling are proposed including the fuzzy analytic hierarchy process (FAHP) for normalization, weighted sum of properties-improved genetic algorithm (WSP-IGA) for prescheduling, priority weights search-simulated annealing (PWS-SA) for rescheduling. Lastly, a discrete event simulation of a numerical case is conducted to demonstrate the practicality and validity of proposed theories and algorithms. The results show that the proposed hyper-heuristics (WSP-IGA and PWS-SA) can respectively realize the prescheduling and rescheduling of FMMAL in four modes including the synthesized mode, time-efficient mode, just-in-time mode and energy-saving mode, which are superior to the four referenced meta-heuristics.

Dynamic Scheduling Framework of the Flexible Mixed-Model Assembly Line Based on the Internet of Manufacturing Things

To satisfy the needs of market customization, the traditional manufacturing is gradually transforming and upgrading into the intelligent manufacturing. In mass customization (MC), the assembly operations of modular products tend to be organized as the form of flexible mixed-model assembly line (FMMAL). The dynamic scheduling problem of FMMAL is quite complex with three issues of the product sequencing, station allocation and material delivery. At the same time, the disruption events of station failure, product inserting and product reworking are also considered. To solve this problem, a comprehensive framework combining the architecture of Internet of Manufacturing Things (IoMT) with the dynamic scheduling algorithms is proposed. Firstly, the IoMT-based FMMAL are constructed via the multi-agent system (MAS) and ubiquitous environment. Secondly, a mathematical model of FMMAL are formulated with the decision variables, optimization objectives and constraint conditions. Thirdly, the IoMT-oriented algorithms for dynamic scheduling are proposed including the fuzzy analytic hierarchy process (FAHP) for normalization, weighted sum of properties-improved genetic algorithm (WSP-IGA) for prescheduling, priority weights search-simulated annealing (PWS-SA) for rescheduling. Lastly, a discrete event simulation of a numerical case is conducted to demonstrate the practicality and validity of proposed theories and algorithms. The results show that the proposed hyper-heuristics (WSP-IGA and PWS-SA) can respectively realize the prescheduling and rescheduling of FMMAL in four modes including the synthesized mode, time-efficient mode, just-in-time mode and energy-saving mode, which are superior to the four referenced meta-heuristics.