Smart and Healthy Walking

This chapter begins by defining smart technologies. Some common applications of smart technologies in the healthcare field are then listed. From these applications, the most widely used smart technologies in mobile healthcare are concluded as apps (smartphone applications), the Internet of things (IoT), social distance monitors, robots, wireless medical sensor networks and smart watches. These smart technologies are driven by forces include high healthcare spending, the need for disruptive solutions, the rapid and continued growth of wireless connectivity, and the need for more precise and personalized healthcare. Subsequently, the concept of smart cities is defined. The most commonly used smart technology applications in smart cities are also summarized. Some representative cases of smart technology applications in smart city healthcare are reviewed. It is concluded that disease detection, health monitoring and medical resource management are the most popular smart healthcare applications in smart cities.

Walking is an inevitable activity in daily life. Walking is also a moderate-intensity physical activity with much epidemiological evidence for promoting health. However, when people walk, they may fall or bump into things. In addition, walking in unfamiliar and complex environments is also dangerous for people. In these cases, smart technologies can come into play. This chapter first emphasizes the importance of healthy walking and mentions some of the difficulties that people face in walking safely and healthily. Then the application of smart technologies for healthy walking is introduced. The most commonly used smart technologies for smart and healthy walking include smart pedometers, smart canes, location awareness services (LAS) (smartphone applications), smart backpacks, etc. As cities transform into smart cities, sensors play an important role. Therefore, in smart cities, sensors can be widely used to collect movement, health, safety and other information to ensure that people walk healthily and safely. To this end, this chapter reviews some smart technology applications, including those based on location-aware services (LASs), sensors (e.g., wearable medical sensors), smart materials, smart canes, and smartphones. However, ordinary people may be reluctant to use these smart technology applications. These smart technology applications seem to be more suitable for people with disabilities and limited mobility. From this perspective, existing smart technology applications are reviewed to support disabled people and people with reduced mobility to walk healthily and safely in smart cities. According to the review results, the smart technologies most widely used to support people with disabilities and reduced mobility include the Internet of things (IoT), smart systems and machine learning (ML).

This chapter first introduces the basic principles and parameters of gait and then explains the laboratory equipment for gait analysis, including motion capture systems, force plates, and pressure pads. Real-life gait detection equipment is introduced, including video and sensor-based detection. Regarding visual perception, video surveillance systems, such as multiple CCTV cameras, can capture gait cycles by processing consecutive video frames using threshold filtering, edge detection, pixel counting, and background segmentation. Regarding wearable sensors, pressure pads and IMUs (inertial measurement units) can be used for gait detection. Pressure pads can be placed inside shoes to measure foot pressure distribution by detecting applied pressure and corresponding electronic changes. IMUs can measure and record motion data, including displacement, velocity, and acceleration. These wearable sensors can effectively detect gait and have good wearability and freedom, suitable for natural gait indoors and outdoors. The application of these technologies provides various options for gait detection and has comprehensive practical value in smart walking. It also covers the application of machine learning and deep learning in gait analysis, as well as research results on health-related walking applications. The chapter provides a comprehensive introduction and overview of the related technologies and applications of health-related walking detection and analysis.

This chapter introduces the fundamental principles of gait analysis, covering normal and abnormal gait features and the significance of clinical gait analysis. Wearable sensor technology, particularly Inertial Measurement Units (IMUs), is highlighted for utilization in gait analysis, referencing studies that explore IMU data methods for gait recognition and prediction and using deep learning models for gait classification. Thoroughly explores gait biometrics, highlighting physical and behavioral traits crucial for gait recognition while underscoring the importance of sensor and posture datasets in training and assessing machine and deep learning models. Furthermore, diverse sensing modalities like video, pressure, and IMU are applied in gait recognition, detailing their respective features and techniques. Environmental-based gait biometrics systems’ potential applications and value showcase practical scenarios such as indoor positioning, activity monitoring, and personal identification in smart buildings and home environments. Intelligent gait health applications encompass clinical intelligent gait, remote gait monitoring, and smart home integration. An innovative method for gait assessment involving advanced wearable technology and AI-powered computational platforms, live monitoring via wearable IMU devices and machine learning, and a gait biometric recognition system hosted in the cloud for secure smart home entry. These innovations offer broader prospects for gait assessment and monitoring, along with associated challenges and requirements for clinical and daily life applications.

Fall detection and prevention is a critical task in smart homes and smart cities. To fulfill this task, smart technology applications have great potential. This chapter begins by highlighting the consequences of falls, particularly in older adults, thus emphasizing the importance of fall detection and prevention. Subsequently, existing smart technology applications for fall detection and prevention are reviewed. Judging from the review results, existing smart technology applications can be divided into two major categories: smart wearable technology applications and cloud and edge computing applications. However, it is not easy to choose a suitable smart technology application for fall detection. To address this issue, a fuzzy multi-criteria decision making (MCDM) approach is introduced. In the fuzzy MCDM approach, alpha-cut operations are applied to derive the fuzzy weights of criteria for each decision maker. Then, fuzzy intersection is applied to aggregate the fuzzy weights derived by all decision makers. Subsequently, the fuzzy technique for order preference by similarity to the ideal solution (TOPSIS) is applied to assess the suitability of a smart technology application for fall detection. The fuzzy MCDM approach is a posterior-aggregation method that guarantees a consensus exists among decision makers.