Abstract

Artificial Intelligence (AI) is taking centre stage in economic growth and business operations alike. Public discourse about the practical and ethical implications of AI has mainly focussed on the societal level. There is an emerging knowledge base on AI risks to human rights around data security and privacy concerns. A separate strand of work has highlighted the stresses of working in the gig economy. This prevailing focus on human rights and gig impacts has been at the expense of a closer look at how AI may be reshaping traditional workplace relations and, more specifically, workplace health and safety. To address this gap, we outline a conceptual model for developing an AI Work Health and Safety (WHS) Scorecard as a tool to assess and manage the potential risks and hazards to workers resulting from AI use in a workplace. A qualitative, practice-led research study of AI adopters was used to generate and test a novel list of potential AI risks to worker health and safety. Risks were identified after cross-referencing Australian AI Ethics Principles and Principles of Good Work Design with AI ideation, design and implementation stages captured by the AI Canvas, a framework otherwise used for assessing the commercial potential of AI to a business. The unique contribution of this research is the development of a novel matrix itemising currently known or anticipated risks to the WHS and ethical aspects at each AI adoption stage.

Introduction

Artificial intelligence (AI) has given rise to a new type of machine, a prediction machine, which can automate cognitive tasks traditionally associated with white-collar workers. These smart machines are lowering the cost and effort of making accurate predictions in operational processes. The AI technology may thus have potential benefits, such as increasing productivity, streamlining processes, and integrating value chains. Advocates of AI maintain that companies that do not take advantage of these benefits risk being driven out of the marketplace by others that do. As human expertise is being outperformed by AI, companies may prefer delivering their products and services, internally as well as externally, with the help of AI. The impact that such operational and logistical change in the workplaces may have on workers, however, remains uncertain.

Sociologists of work have long argued that workplace technologies are a key instrument of social change, reshaping labour relations and introducing new systems of worker discipline and control (Barley 1988; Braverman 1974; Kellogg et al. 2020; Zuboff 1988). From this critical sociological perspective, AI technologies in the workplace represent a new, contested domain for workers, raising questions around job security, worker autonomy, and worker status for which there is yet no clear social consensus. There is emerging research evidence on the qualitative impacts of AI on workers in specific industries, particularly insecure workers in the gig economy (Myhill et al. 2020; Convery et al. 2020). While the COVID-19 pandemic of 2020 has, at least temporarily, normalized flexible and remote work, many firms had already integrated complex, networked technologies integrating AI even before the pandemic to deliver products and services across borders and time zones, and to deploy skilled workers in more effective ways. The rise of networked technologies and “digital first” business strategy played out in the global economic context of increasingly precarious forms of employment, unequal wage growth, the transformation of manufacturing, and a growing income and skills divide in the workforce leading to reduced economic and social mobility. These outcomes are not inevitable, but are the result of personal, economic and political decisions (Srnicek and Williams 2016; Benanav 2020). Whether the new technologies adversely affect the security and wellbeing of employees in a workplace is above all a question of whether they are permitted to do so, or whether instead these risks are contained by regulation and oversight.

Conclusion

A growing use of AI will change economies, the manufacturing of goods and delivery of services. It will also affect human relations at a societal level, including how we collect, use fairly and keep safe the data that drive AI. Whilst much of the debate of the ethical use of AI has focussed on the societal level, AI also has profound implications in and for the workplaces where it is being used. These workplaces are currently and in most industrial and late-industrial nations regulated by WHS guidelines, rules and prescriptions, which rarely address the specific impact of AI on processes, job roles, and communication among employees, and between employees and managers.

In this paper, we have outlined a model for detecting risks and hazards that AI may bring to workplaces, using a set of AI Ethics Principles, as endorsed by the Australian Government, and the AI Canvas, a technical stages model of AI implementation. The explorative process commenced with a review of the literature on AI risks and hazards as they may apply to workplaces. These potential risks and hazards were further explored in consultation with AI experts, professionals and users—a process that also helped to populate the risk assessment matrix with examples of workplace specific AI risks and hazards. These risk examples were further developed and validated during consultations with AI adopters and WHS professionals. Each of these risks and hazards was linked to statutory WHS principles as advocated by SWA, the Australian WHS regulators and oversight agency.

Abstract

Keywords

1. Introduction

2. The concept of a metaverse and its possible applications in medicine

3. The medical Internet of Things (MIoT) facilitates important application scenarios for the metaverse

4. The metaverse provides technical support to maximize the value of the MIoT

5. Prospects

Author contributions

Declaration of Competing Interest

Acknowledgements

Availability of data and material

Funding

Consent for publication

Ethics approval and consent to participate

References

Abstract

Background

     Recently, Professor Chunxue Bai and colleagues have proposed a definition of the Metaverse in Medicine as the medical Internet of Things (MIoT) facilitated using AR and/or VR glasses.

Methods

     A multi-disciplinary panel of doctors and IT experts from Asia, the United States, and Europe analyzed published articles regarding expert consensus on the Medical Internet of Things, with reference to study results in the field of metaverse technology.

Findings

     It is feasible to implement the three basic functions of the MIoT, namely, comprehensive perception, reliable transmission, and intelligent processing, by applying a metaverse platform, which is composed of AR and VR glasses and the MIoT system, and integrated with the technologies of holographic construction, holographic emulation, virtuality-reality integration, and virtuality-reality interconnection. In other words, through interactions between virtual and real cloud experts and terminal doctors, we will be able to carry out medical education, science popularization, consultation, graded diagnosis and treatment, clinical research, and even comprehensive healthcare in the metaverse. The interaction between virtual and real cloud experts and terminal users (including terminal doctors, patients, and even their family members) could also facilitate different medical services, such as disease prevention, healthcare, physical examination, diagnosis and treatment of diseases, rehabilitation, management of chronic diseases, in-home care, first aid, outpatient attendance, consultation, etc. In addition, it is noteworthy that security is a prerequisite for the Metaverse in Medicine, and a reliable security system is the foundation to ensure the normal operation of such a platform.

     The rise of the metaverse has brought infinite possibilities to all types of sectors and occupations, such as video game production, leisure, and entertainment. Museum exhibitions have evolved with diverse digital technologies,4 and new metaverse sales models have emerged from traditional retail.5 Some researchers have studied the art community of the 3D virtual world. Concerning social media, on October 28th, 2021, Mark Zuckerberg announced that Facebook had changed its name to “Meta” to align the company with its focus on new computing technologies and the metaverse.6 Others seek to understand how journalism is practiced in the metaverse.7, 8

Conclusion

     The application of a Cloud Plus Terminal platform could enable interaction between virtual and real cloud experts and terminal doctors, in order to realize medical education, science popularization, consultation, graded diagnosis and treatment, clinical research, and even comprehensive healthcare in the metaverse.

Introduction

     Since 2021, the concept of the metaverse has been widely discussed. It refers to the internet accessed via virtual reality (VR) and augmented reality (AR) glasses, and is considered to be the next-generation mobile computing platform that will be widely used in the future.1 Others believe that the metaverse is a ternary digital world established on the basis of digital technology integrating the virtual and the real worlds, which people enter with digital identities. The idea originated from the novel True Names by Professor Vernor Vinge, an American mathematician. In this story, published in 1981, the author creatively conceived a virtual world that enters and obtains sensory experience through a brain-computer interface. Later, in 1992, the term “metaverse” was coined by American science-fiction writer Neal Stephenson in his novel Snow Crash, in which the characters explore an internet world parallel to the real world, using digital avatars of themselves for perception and interaction.2, 3

     The rise of the metaverse has brought infinite possibilities to all types of sectors and occupations, such as video game production, leisure, and entertainment. Museum exhibitions have evolved with diverse digital technologies,4 and new metaverse sales models have emerged from traditional retail.5 Some researchers have studied the art community of the 3D virtual world. Concerning social media, on October 28th, 2021, Mark Zuckerberg announced that Facebook had changed its name to “Meta” to align the company with its focus on new computing technologies and the metaverse.6 Others seek to understand how journalism is practiced in the metaverse.7, 8

Funding

     Science and Technology Commission of Shanghai Municipality (20DZ2254400, 21DZ2200600, 20DZ2261200), National Scientific Foundation of China (82170110), Shanghai Pujiang Program (20PJ1402400).

Abstract

Open Access and Permissions

Share and Cite

Article Metrics

Order Article Reprints

Abstract:

COVID-19 has disrupted normal life and has enforced a substantial change in the policies, priorities and activities of individuals, organisations and governments. These changes are proving to be a catalyst for technology and innovation. In this paper, we discuss the pandemic’s potential impact on the adoption of the Internet of Things (IoT) in various broad sectors, namely healthcare, smart homes, smart buildings, smart cities, transportation and industrial IoT. Our perspective and forecast of this impact on IoT adoption is based on a thorough research literature review, a careful examination of reports from leading consulting firms and interactions with several industry experts. For each of these sectors, we also provide the details of notable IoT initiatives taken in the wake of COVID-19. We also highlight the challenges that need to be addressed and important research directions that will facilitate accelerated IoT adoption.

1. Introduction

The Internet of Things (IoT) is envisioned as a network of billions of devices that can sense, communicate and share data which can then be analyzed to unlock a wealth of intelligence useful for planning, management and decision making [1]. IoT promises huge benefits for a variety of domains such as healthcare, manufacturing, agriculture, telecommunication and transportation. Despite the popularity of the IoT concept and its promised benefits, its adoption has been significantly slower than expected [2,3]. Some of the major reasons behind this include: (1) security, privacy, policy and trust issues [3–5]; (2) organisational inertia, long capital cycles and shortage of specialist workforce needed to successfully implement IoT [2,5]; and (3) lack of convincing use cases with clear return on investment (ROI) in some sectors.

COVID-19 has impacted all walks of life so much that we may never return to the old normal. This pandemic is proving to be a catalyst for digital transformation because COVID19 has created or expanded applications and use cases of digital technologies [6–8]. It has also forced governments, organisations and individuals to change/adapt their priorities, their views on societal/ethical issues, and the way they operate. In many cases, this has addressed or mitigated many of the above mentioned reasons behind the slower-thanexpected adoption of IoT across many verticals. For example, governments have invested huge amounts of resources in IoT and other technologies to combat COVID-19. Lifestyle changes brought about by COVID-19 such as work/study from home have also provided new use cases of IoT with clear ROI such as remote asset control, workforce tracking and remote employee collaboration [9]. Consequently, many organisations have increased investment in IoT and the pace of their IoT projects [10,11]. The fight against COVID-19 has resulted in a less strict stance on privacy issues, higher trust in technology and fasttracked approval procedures. This is also paving the way for accelerated adoption of IoT in various verticals. Furthermore, regulatory changes such as stricter cleaning and tracking requirements for businesses are also accelerating the IoT adoption in smart buildings.

1- Introduction

2- Literature review

3- Problem formulation

4- Solving method

5- Model implementation and numerical results

6- Conclusion

References

Abstract

Medical Supply chain network design is one of the crucial planning problems that if solved efficiently and effectively, can alleviate the dangers arising from the accumulation of wastes. Furthermore, the harmful effects of medical waste, with their infectious nature in the environment, have increased justifies the significance of this research. In this article, forward and reverse supply chain network design for consumer medical products is considered taking into account the biological risks. The proposed model has two objectives: first, maximizing the profit obtained from subtracting the costs from the revenues of the supply chain. Revenues are gained from selling medical supplies to hospitals and medical wastes to recycling centers, as well as getting the permission to use sterilize services from clinics lacking a sterilization center. The costs include activation cost of inventory, sterilization and collection centers, transportation cost, purchasing cost of medical supplies, municipality cost for destruction of medical waste, etc. The second objective is to reduce biological risks. The primary source of infectious medical supplies is from disposable supplies and equipment. Thus, the second objective function is to minimize the distance and travel time between the clinic and the sterilization center. The proposed model is implemented in hospitals in Tehran’s 4th municipal district using the Bounded De Novo Programming approach which initially attempts to redesign rare sources of the problem. The issue has two types of resource and policy constraints. The policy constraints of the problem cannot be changed, which is why the bounded De Novo Programming approach is used to solve the problem. Redesigning the capacity of the sterilization center leads to the decrease of biological risks, and in addition to can causes to increasing profitability. Also, by raising the productivity of medical waste in the recycling process, the distribution center can receive more profits.

Introduction

In the past, producers and consumers were not responsible for the products used. In other words, they were careless of the post consumption process. Many of the consumed and expired products were out of place, regardless of the extent of their return. They saw a fate of including burial, burning, or destruction ahead of them. Each of the above operations would undoubtedly impose destructive effects and damage to the surrounding environment. Now, the point of view of the advancement and development of countries, people, and the government are expecting to pay attention to their funds (Guo et al. 2019). Therefore, the producers plan to reduce the production of their defective goods. Thus, organizations are working to prevent more of the waste by devising an effective and efficient system in distribution network management. In turn, it includes determining the role of existing or potential supply chain resources as well as the interactions between these entities to manage the physical flows related to the recycling of products (Rajendran and Ravindran, 2019).

1- Introduction

2- Overview of targeted ISO standards

3- Agile metrics to support monitoring and control processes

4- Conformance with targeted ISO standards

5- Conclusion

References

Abstract

Agile approaches are well perceived in software development companies. These approaches are not faced with traditional process models. This research analyses how by defining and monitoring a set of Agile metrics, Agile mature companies can be also conformant with the best practices proposed by the targeted ISO process reference models. Conformance has been identified with five Technical Management processes of the ISO/IEC/IEEE 12207 standard and with two activities of the Project Management process of the ISO/IEC TR 29110-5-1-2 standard. The findings may be of the interest of those Agile settings that need to work according to the process model established in the company.

Introduction

Since the emergence of Agile in the early 1990s, Information Technology (IT) companies have had an increasing interest in applying Agile software development methods. Many settings claim to be Agile or wish to adopt these methods [1]. Implementation of Agile approaches helps software development companies to tailor their services and products, thus providing the ability to adapt to current dynamics in the market [2], [3]. The use of Agile has caused a significant change on how projects are organized and executed [4], [5]. Due to its optimization effect and reduction of overhead, Agile practices can help mature organizations to become more flexible [6], [7]. As a consequence, Agile approaches are well perceived by both management and developers [8], and software development organizations recognize the need for agility in nearly every project they execute [9]. Agile approaches are also appropriate for organizations that develop critical software, as well as for other settings in other critical sectors such as automobile, medical or aerospace, among others. Although this kind of companies need to show conformance to recognized and widely accepted standards such as CMMI or SPICE, they need to be more agile. In any case, it is not incompatible to have a certification according to a maturity model and work following an Agile approach.

1- Introduction

2- Literature review

3- Problem definition and the proposed model

4- Solution methodology

5- Experimental results

6- Managerial insight

7- Conclusion

References

Abstract

The blood supply of hospitals in disasters is a crucial issue in supply chain management. In this paper, a dynamic robust location–allocation model is presented for designing a blood supply chain network under facility disruption risks and uncertainty in a disaster situation. A scenario-based robust approach is adapted to the model to tackle the inherent uncertainty of the problem, such as a great deal of a periodic variation in demands and facilities disruptions. It is considered that the effect of disruption in facilities depends on the initial investment level for opening them, which are affected by the allocated budget. The usage of the model is implemented by a real-world case example that addresses the demand and disruption probability as uncertain parameters. For large-scale problems, two meta-heuristic algorithms, namely the self-adaptive imperialist competitive algorithm and invasive weed optimization, are presented to solve the model. Furthermore, several numerical examples of managerial insights are evaluated.

Introduction

Supply chain management (SCM) is often described as a procedure of planning, implementation, and control of supply chain operations based on efficient practices (Melo et al., 2009). The supply chain network design (SCND) has played a dominant role in the performance of the supply chain (SC). It copes with so many prospects of the SC such as information, location of facilities and allocation of material. The SCND is considered as a significant issue in strategic and operational decisions in the SCM scope (Devika et al., 2014; Amin et al., 2017; Fu and Fu, 2015). Blood supply management and its products are vital issues for humankind. Blood is not a regular commodity since its demand is relatively random, and efficient coordination between supply and demand has not been resolved in various researches yet (Beliën and Forcé, 2012). Human blood is a rare and vital source that is produced only by human beings, and since there is currently no other product that can produce blood and also its uncertainty supply and demand side, keeping an adequate supply level is very important to fulfill demands (Duan and Liao, 2014).

1- Introduction

2- Road transportation

3- Maritime transportation

4- ‘Greening’ other modes of transport

5- Conclusions

References

Abstract

Recent years have witnessed an increased awareness of the negative external impacts of freight transportation. The field of Operational Research (OR) has, particularly in the recent years, continued to contribute to alleviating the negative impacts through the use of various optimization models and solution techniques. This paper presents the basic principles behind and an overview of the existing body of recent research on ‘greening’ freight transportation using OR-based planning techniques. The particular focus is on studies that have been described for two heavily used modes for transporting freight across the globe, namely road (including urban and electric vehicles) and maritime transportation, although other modes are also briefly discussed.

Conclusions

This work set out to answer a question that concerns the role of OR in green freight transportation. Whilst we do not claim to have provided a complete answer, nor believe that such an endeavor is a simple task, we suggest here, on the basis of the work surveyed in this paper, that there are at least three fundamental roles that OR can continue to play in this area of research: 1. To devise methods, tools and algorithms that help design effective transportation plans that capture the trade-off between environmental and economic performance, with the ultimate goal of arriving at win-win solutions. To achieve this goal, however, one must carefully consider, for a particular freight transportation problem (a) who the players are, and the criteria by which they ‘win’. The review of the current body of work in this area, at least on two major modes of transport, has revealed that problems are often solved for a single player (e.g., an individual freight operator), where the win criterion is the ability to jointly reduce internal and external costs, but with an emphasis on the former.

1- Introduction

2- Automobile Internet of Things

3- IoT Requirements for Robotic First Aid System

4- Robotic First Aid System IoT Architecture

5- Conclusion

References

Abstract

Health emergencies occur in passenger cars where victims do not have immediate access to either layperson or professional, proper medical services, resulting in deterioration of their health or death. Installation of a robotic first aid system for passenger car occupants has been proposed. This research is part of a larger work of designing the system and identifies the existing hardware and software automotive infrastructure that the robotic first aid system can functionally use. These resources are reviewed in categories of sensing, connectivity, data analysis and information exchange, which form the internet of things. Consequently, the system’s design for internet of things mechanical requirements are identified in sensing. Finally, a preliminary framework for the system’s internet of things infrastructure is established to facilitate the development of a smart robot.

Introduction

We live in an invisible jungle of communication where millions of devices interact with each other at any one time, their signals travelling at colossal speed through land, air and even water – all because of the internet. As envisioned by its pioneers, the internet today connects computers in automobiles, homes, industrial and business spaces, and wearable devices, forming the Internet of Things (IoT). The past decade has seen rapid development of IoT systems because gadgets operate more efficiently, effectively and at lower costs towards a common goal when connected to share information and facilities, both hardware and software [1], [2]. One of the most significant research areas in the field of IoT is human healthcare. Vehicle safety is a top priority for automakers, consumers, governments and other parties concerned with road transport safety [3]–[5]. Despite their efforts, several studies report that morbidity and mortality rates resulting from road-traffic accidents (RTAs) are on the rise in some regions of the world, particularly low- and middle-income countries (LICs and MICs), and road traffic injuries are a leading cause of preventable death [6]–[9]. Additionally, vehicle occupants are susceptible to non-traumatic medical emergencies including cardiovascular and respiratory complications [10]–[12]. It is well documented that quick and correct medical assistance is the key to survival of any major medical emergency, such as an injury, a stroke or a heart attack [13], [14]. First aid given to victims of RTAs is known to preserve life, prevent further harm y and at lower costs towards a common goal when connected to share information and facilities, both hardware and software [1], [2]. One of the most significant research areas in the field of IoT is human healthcare. and promote recovery in most cases [15]–[18]. Unfortunately, a number of studies have found that there are high chances of victims not getting proper help for reasons including unavailability of bystanders, responders fearful of worsening the condition and entrapment of victims in the wreckage, thus inaccessible [16], [19]– [25]. Evidence suggests that professional emergency medical service (EMS) post-crash response also influences the recovery of patients [26], [27], and the underlying assumption is that EMS response times should be reduced continuously. A more recent report confirms that if trauma care systems for severely injured RTA victims in LICs and MICs countries were improved to match those in high-income countries (HICs), half a million lives could be saved each year [28]. However, it has been shown that even for areas with effective EMSs, the greatest delays in responding to emergencies come not from EMS response time but from the reaction of patients and bystanders [29]. For such scenarios, it has been suggested that policy concentrates on public first aid education – the same public with a low response rate as mentioned earlier!

Introduction

Methods

Discussion

References

Abstract

Background
Machine learning is increasingly used to predict healthcare outcomes, including cost, utilization, and quality.
Objective
We provide a high-level overview of machine learning for healthcare outcomes researchers and decision makers.
Methods
We introduce key concepts for understanding the application of machine learning methods to healthcare outcomes research. We first describe current standards to rigorously learn an estimator, which is an algorithm developed through machine learning to predict a particular outcome. We include steps for data preparation, estimator family selection, parameter learning, regularization, and evaluation. We then compare 3 of the most common machine learning methods: (1) decision tree methods
that can be useful for identifying how different subpopulations experience different risks for an outcome; (2) deep learning methods that can identify complex nonlinear patterns or interactions between variables predictive of an outcome; and (3) ensemble methods that can improve predictive performance by combining multiple machine learning methods.
Results
We demonstrate the application of common machine methods to a simulated insurance claims dataset. We specifically include statistical code in R and Python for the development and evaluation of estimators for predicting which patients are at heightened risk for hospitalization from ambulatory care-sensitive conditions.
Conclusions
Outcomes researchers should be aware of key standards for rigorously evaluating an estimator developed through machine learning approaches. Although multiple methods use machine learning concepts, different approaches are best suited for different research problems.

Introduction

Machine learning is a rapidly growing field that attempts to extract general concepts from large datasets, commonly in the form of an algorithm that predicts an outcome (commonly referred to as a predictive model or estimator)—a task that has become increasingly difficult to accomplish by humans because data volume and complexity has increased beyond what was capable with traditional statistics and desktop computers. Recently, machine learning has been used to predict healthcare outcomes including cost, utilization, and quality; for example, machine learning methods have been used to predict “cost bloomers,” or patients who move from a lower to the highest decile of per capita healthcare expenditures.1 Machine learning has also been used to predict which patients are most likely to experience a hospital re-admission for congestive heart failure and related conditions.2 Although causal research identifies what factors cause healthcare outcomes, machine learning will inter alia use these factors to identify which patients will have these outcomes. Because machine learning remains an emerging field and its application to healthcare outcomes research is also nascent, we provide a high-level overview of key concepts and best practices in machine learning for practitioners and readers of healthcare outcomes research. We describe the steps of data preparation, estimator family selection, parameter learning, regularization, and evaluation. We then compare 3 of the most common machine learning methods: (1) decision tree methods that can be useful for identifying how different subpopulations experience different risks for an outcome; (2) deep learning methods that can identify complex non-linear patterns or interactions between variables predictive of an outcome; and (3) ensemble methods that can improve predictive performance by combining multiple machine learning methods.

Sedentary behavior and lack of exercise pose a threat to both individual health and the viability of health-care systems and societies. Portable fitness trackers as prominent persuasive technologies are seen as a way to increase the level of physical activity. Yet, despite their technical capabilities, their affordability, and their advantages in regard to increased physical activity, they are neither used across the population, nor for long periods of time. To understand if and how product design influences acceptance and projected use, we evaluated users’ preferences of using wearables, using a conjoint analysis approach with 412 participants of a wide age spectrum. Besides different relative importances of product properties (privacy design, perceived utility, accuracy, motivational design are rated from most to least important), three user segments with distinct technical requirements were identified (data protectors, benefit maximizers, facts enthusiasts). The three segments differ not only in product preference but also regarding other user factors. We presume that a broader and more sustainable use of wearables can be achieved when tailoring information and communication strategies alongside with the requirements of these user segments.

Introduction

Digitalization and automation have changed the working life of today’s societies tremendously. The majority of Western work nowadays includes the use of electronic devices, and, more often than not, that of computers. Therefore, eight or more hours a day are spend sitting in front of a monitor or hunched over a touchscreen. Not only does this have a negative impact on posture, but studies have shown that prolonged sedentary behavior plays a major factor in health issues such as decreased mobility, weight-gain or even obesity, and other cardiovascular impairments, see, e.g., (Biswas et al., 2015; de Rezende, Lopes, Rey-López, Matsudo, & Do Carmo Luiz, 2014; Owen, Sparling, Healy, Dunstan, & Matthews, 2010). According to Knight, physical activity is declining in North America and Europe, relates to several diseases, such as cancer, diabetes, hypertension, and coronary or cerebrovascular diseases, and therefore has a negative impact on life expectancy and – in the long run – the viability of health-care systems (Knight, 2012). Yet, Mendes et al. show that regular medium-intense exercises have a positive effect on health (Mendes, Sousa, & Barata, 2011); especially for children, older adults, and people dealing with overweight or obesity. And although intensity, frequency, and duration of the exercises might be optimized to achieve the highest health benefits, some physical activity is always considered as better than none. Other benefits of regular physical activities include the mitigation of migraines (Varkey et al., 2011), the reduction of symptoms of depression (Cooney et al., 2013), as well as increased executive functioning and working memory performance for young children, young adults, as well as older adults.

1. Introduction

2. Kernelized Principal Component Analysis(KPCA)

3. Bat Algorithm(BA)

4. Least Square Support Vector Machine(LSSVM)

5. Summary and Prospect

References

Data mining technology has important clinical significance for disease classification and prevention. In order to improve the performance of the model and the accuracy of disease classification, this paper proposes KPCA-IBA-LSSVM model. In view of the high dimensionality and nonlinearity of medical data, KPCA is used to reduce dimension. BA algorithm is used to optimize the parameters of LSSVM. At the same time, BA algorithm is easy to fall into local extreme and premature convergence. So this paper improves BA algorithm from three aspects. Finally, in order to verify the validity of the algorithm, this paper uses Breast Cancer, Statlog (Heart) and Heart Disease datasets from UCI machine learning database to validate the model. The simulation results show that the model has achieved better classification accuracy, and the model can also be used for classification and prediction of other diseases. The method proves to have certain feasibility and promotion.

Introduction

In particular, it is of important practical significance for disease prediction, for it will greatly improve the prevention of disease and reduce the incidence of new diseases. Data mining technology is widely used in the medical field, but the model is relatively single and some parameters are set manually. Besides, medical data has the characteristics of wide dimensions, noise, strong coupling and non-linearity, which can not optimize the performance of the model. Therefore, the KPCA-IBA-LSSVM model is proposed to classify diseases. Kernelized principal component analysis is a nonlinear dimensionality reduction method based on kernel technique. Least square support vector machine is an improved algorithm of SVM. It transforms the quadratic programming problem of SVM into the problem of linear equations, which makes the problems easier to solve. In addition, the performance of the classifier is closely related to the selection of parameters.

1. Introduction

2. Smart Health

3. ML Approaches in Smart Health

4. Conclusions and Future Work

References

The increase of age average led to an increase in the demand of providing and improving the service of healthcare. The advancing of the information and communication technology (ICT) led to the development of smart cities which have a lot of components. One of those components is Smart Health (s-Health), which is used in improving healthcare by providing many services such as patient monitoring, early diagnosis of diseases and so on. Nowadays there are many machine learning techniques that can facilitates s-Health services. This paper reviews recent published papers in the area of smart health starting from the years 2011 to 2017, and a structured analysis for different machine learning (ML) approaches that are applied in s-Health. The results show that the ML approach is used in many s-Health applications such as Glaucoma diagnosis, Alzheimer’s disease, bacterial sepsis diagnoses, the Intensive Care Unit (ICU) readmissions, and cataract detection. The Artificial Neural Network (ANN), Support Vector Machine (SVM) algorithm and deep learning models especially the Convolutional Neural Network (CNN) are the most commonly used machine learning approaches where they proved to get high evaluation performance in most cases.

Introduction

e-Health can be defined as “an emerging field in the intersection of medical informatics, public health and business, referring to health services and information delivered or enhanced through the Internet and related technologies. In a broader sense, the term characterizes not only a technical development, but also a state-of-mind, a way of thinking, an attitude, and a commitment for networked, global thinking, to improve health care locally, regionally, and worldwide by using information and communication technology.”3. There is an intersection between s-Health and Mobile Health (m-Health); m-Health can be defined as “emerging mobile communications and network technologies for healthcare systems”4. Machine Learning (ML) is a field that grew out of Artificial Intelligence (AI). It is concerned with designing and developing algorithms that enable the computers to evolve their behaviors according to empirical data. The ML approach is evolving rapidly as a result of the improvement of the ML algorithms, enhanced methods of capturing data, improved computer networks, new sensors/IO units, and the interest in self-customization to users’ behavior 5.

1. Introduction

2. System structure

3. Result

4. Conclusion

Acknowledgement

References

In recent years, many studies have focus on health care. We designed a non-invasive wearable device that not only equipped with BLE to detect vital signals but also combining an intelligent terminal to develop healthcare IoT. In most studies, an electrode potential is used in ECG, while for PPG, heart rates are measured by the amount of reflected LED light. However, in this paper, we detect heart vibration signals based on radial artery vibration signals by the wrist PVDF piezo film sensor that the user wears to detect his/her heart rate. The device can also reduce power consumption. In order to promote Signal to Noise Ratio (SNR), we adopt filter circuit design and peak detection algorithm to eliminate noise by using the intelligent terminal, then we are able to achieve high accuracy heart rate calculation. Furthermore, the intelligent terminal will upload the data to the cloud, so not only the user can monitor self-vital information anytime but also medical institutions can access the data in case of an emergency.

Introduction

Normally, we measure heart rates on ECG and PPG. When applying ECG, we need to stick many electrodes on the user’s skin which is not comfortable and convenient for the user [1]. As for PPG, it utilities LED to detect blood flow to measure heartbeat. So the battery energy will be exhausted soon [1] [2]. In this paper, we will not only compare ECG, PPG and PVDF (please refer to Table1) but also adopt PVDF sensor to measure heart rates and can get slightly vibration which come from arterial wall’s jumping of wrist[5]. In order to get heart rate easily, we add op-amp (operational amplifier) circuit and Butterworth filter circuit to enhance SNR. Moreover, we adopt PAN TOMPKINs algorithm [6] to peak searching when using an intelligent terminal device in order to eliminate noise and increase heart rate detection accuracy. Apart from having Wi-Fi and BLE functions, the intelligent terminal also equips with a powerful CPU to process raw data immediately and share the workload of the cloud server.