Skip to main content
main-content

Über dieses Buch

Over the last decade, there has been a growing interest in human behavior analysis, motivated by societal needs such as security, natural interfaces, affective computing, and assisted living. However, the accurate and non-invasive detection and recognition of human behavior remain major challenges and the focus of many research efforts.

Traditionally, in order to identify human behavior, it is first necessary to continuously collect the readings of physical sensing devices (e.g., camera, GPS, and RFID), which can be worn on human bodies, attached to objects, or deployed in the environment. Afterwards, using recognition algorithms or classification models, the behavior types can be identified so as to facilitate advanced applications. Although such traditional approaches deliver satisfactory performance and are still widely used, most of them are intrusive and require specific sensing devices, raising issues such as privacy and deployment costs.

In this book, we will present our latest findings on non-invasive sensing and understanding of human behavior. Specifically, this book differs from existing literature in the following senses. Firstly, we focus on approaches that are based on non-invasive sensing technologies, including both sensor-based and device-free variants. Secondly, while most existing studies examine individual behaviors, we will systematically elaborate on how to understand human behaviors of various granularities, including not only individual-level but also group-level and community-level behaviors. Lastly, we will discuss the most important scientific problems and open issues involved in human behavior analysis.

Inhaltsverzeichnis

Frontmatter

Chapter 1. Introduction

Abstract
Human behavior sensing and understanding has been a popular research area during the past decades, which plays an important role in human-computer interaction and public security. It aims to understand what people are doing by sensing and recognizing their activities and their environments. However, accurate detection and recognition of human behavior is still a big challenge that attracts a lot of research efforts. In this chapter, we aim to present an overview of human behavior sensing and understanding techniques, including from vision-based to sensor-based and device-free behavior sensing, from individual to group and community behavior understanding, and from pattern-based to model-based behavior understanding.
Zhiwen Yu, Zhu Wang

Chapter 2. Main Steps of Human Behavior Sensing and Understanding

Abstract
Human behavior sensing and understanding is a complex process that can be roughly characterized by four main steps, including the following: (1) to choose appropriate sensors to monitor and capture a user’s behavior along with the state change of the environment; (2) to collect, store, and process collected information through data analysis techniques and/or knowledge representation formalisms at appropriate levels of abstraction; (3) to extract features in a way that different behaviors can be distinguished accordingly; and (4) to select or develop reasoning/classification algorithms to infer behaviors from sensor data. For each individual task, a number of methods, technologies, and tools are available for use. It is often the case that the selection of a method used for one task is dependent on the method of another task. We present the comprehensive methods used for each of these steps in the following sections.
Zhiwen Yu, Zhu Wang

Chapter 3. Sensor-Based Behavior Recognition

Abstract
In this monograph, sensor-based behavior recognition mainly refers to the use of emerging sensor network technologies for behavior monitoring and understanding. The generated sensor data from sensor-based monitoring are mainly time series of state changes and/or various parameter values that are usually processed through data fusion, probabilistic, or statistical analysis methods and formal knowledge technologies for behavior recognition. Specifically, sensors can be attached to an actor under observation, namely wearable sensors or smartphones, or objects that constitute the environment, namely dense sensing. Wearable sensors often use inertial measurement units and radio frequency identification (RFID) tags to gather a user’s behavioral information. This approach is effective to recognize physical movements such as physical exercises. In contrast, dense sensing infers behaviors by monitoring human–object interactions through the usage of multiple multimodal miniaturized sensors. In this chapter, we first give a brief introduction to the historical evolution of sensor-based behavior recognition. Afterwards, we present the mobile device-enabled behavior recognition approach, which is a typical type of sensor-based behavior recognition, followed by a discussion on the key issues of developing behavior recognition systems using mobile devices.
Zhiwen Yu, Zhu Wang

Chapter 4. Device-Free Behavior Recognition

Abstract
Traditional methods to sense and recognize human behavior include using wearable devices, cameras, and devices embedded in the environment. Recently, a new kind of behavior sensing approach, device-free behavior sensing, attracts a great amount of interests as it holds the promise to provide a ubiquitous sensing solution by using the pervasive signal (including RF signal, acoustic signal, optical signal, etc). In this chapter, we first introduce the basic concept of device-free behavior sensing and understanding, and then present two typical device-free behavior sensing approaches, i.e., Wi-Fi based and acoustic based.
Zhiwen Yu, Zhu Wang

Chapter 5. Individual Behavior Recognition

Abstract
In this chapter, we present some of our recent research advances on individual behavior sensing and recognition. Specifically, in Sections 5.1 and 5.2, we present two human mobility-related works (i.e., mobility prediction and disorientation detection) by leveraging GPS trajectories. Afterwards, we discuss how to recognize human behaviors by using smartphones in Sections 5.3 and 5.4 (i.e., human-computer operation recognition and human localization), followed by two device-free sensing-based behavior analysis practices in Sections 5.5 and 5.6 (i.e., human identity recognition and respiration detection).
Zhiwen Yu, Zhu Wang

Chapter 6. Group Behavior Recognition

Abstract
Compared with individual behavior sensing and understanding, the recognition of group behavior is more challenging. In this chapter, we present some of our recent progress on group behavior sensing and recognition. Specifically, in Sect. 6.1, we discuss how to recognize the mobility level and structure of groups in the physical world by leveraging mobile devices. Afterwards, we present the recognition of human semantic interactions and group interaction patterns in smart spaces in Sects. 6.2 and 6.3. Finally, we discuss how we can organize, suggest, or predict group activities by leveraging the power of mobile crowdsensing and mobile social networking in Sects. 6.4 and 6.5.
Zhiwen Yu, Zhu Wang

Chapter 7. Community Behavior Understanding

Abstract
The recent rapid development of smart mobile devices and mobile social networking services makes it possible to explore human behaviors in an unprecedented large scale. In this chapter, we present some of our recent research advances on community behavior understanding. Specifically, in Sect. 7.1, we present the discovering and profiling communities in mobile social networks, followed by a study on how to understand the evolution of social relationships in Sect. 7.2. Finally, in Sect. 7.3, we discuss how to enhance human social interactions by interlinking off-line and online communities.
Zhiwen Yu, Zhu Wang

Chapter 8. Open Issues and Emerging Trends

Abstract
While there have been significant progress in the sensing and understanding of human behaviors, we still face a number of theoretical and technical challenges which need to be further explored. In this chapter, we discuss possible challenges and open issues from the aspects of human behavior itself, the data, as well as the models and evaluations, respectively. Afterwards, we present some emerging trends and directions, with hoped-for potential breakthroughs promising advanced human behavior sensing and understanding models and techniques.
Zhiwen Yu, Zhu Wang
Weitere Informationen

Premium Partner

    Bildnachweise