Automatic Annotation of Unlabeled Data from Smartphone-Based Motion and Location Sensors

Comparative Analysis of the Clustering Quality in Self-Organizing Maps for Human Posture Classification

The objective of this article is to develop a methodology for selecting the appropriate number of clusters to group and identify human postures using neural networks with unsupervised self-organizing maps. Although unsupervised clustering algorithms have proven effective in recognizing human postures, many works are limited to testing which data are correctly or incorrectly recognized. They often neglect the task of selecting the appropriate number of groups (where the number of clusters corresponds to the number of output neurons, i.e., the number of postures) using clustering quality assessments. The use of quality scores to determine the number of clusters frees the expert to make subjective decisions about the number of postures, enabling the use of unsupervised learning. Due to high dimensionality and data variability, expert decisions (referred to as data labeling) can be difficult and time-consuming. In our case, there is no manual labeling step. We introduce a new clustering quality score: the discriminant score (DS). We describe the process of selecting the most suitable number of postures using human activity records captured by RGB-D cameras. Comparative studies on the usefulness of popular clustering quality scores-such as the silhouette coefficient, Dunn index, Calinski-Harabasz index, Davies-Bouldin index, and DS-for posture classification tasks are presented, along with graphical illustrations of the results produced by DS. The findings show that DS offers good quality in posture recognition, effectively following postural transitions and similarities.

Security analysis of mobile crowd sensing applications

The proliferation of mobile phones with integrated sensors makes large scale sensing possible at low cost. During mobile sensing, data mostly contain sensitive information of users such as their real-time location. When such information are not effectively secured, users’ privacy can be violated due to eavesdropping and information disclosure. In this paper, we demonstrated the possibility of unauthorized access to location information of a user during sensing due to the ineffective security mechanisms in most sensing applications. We analyzed 40 apps downloaded from Google Play Store and results showed a 100% success rate in traffic interception and disclosure of sensitive information of users. As a countermeasure, a security scheme which ensures encryption and authentication of sensed data using Advanced Encryption Standard 256-Galois Counter Mode was proposed. End-to-end security of location and motion data from smartphone sensors are ensured using the proposed security scheme. Security analysis of the proposed scheme showed it to be effective in protecting Android based sensor data against eavesdropping, information disclosure and data modification.

SenseCrypt: A Security Framework for Mobile Crowd Sensing Applications

The proliferation of mobile devices such as smartphones and tablets with embedded sensors and communication features has led to the introduction of a novel sensing paradigm called mobile crowd sensing. Despite its opportunities and advantages over traditional wireless sensor networks, mobile crowd sensing still faces security and privacy issues, among other challenges. Specifically, the security and privacy of sensitive location information of users remain lingering issues, considering the "on" and "off" state of global positioning system sensor in smartphones. To address this problem, this paper proposes "SenseCrypt", a framework that automatically annotates and signcrypts sensitive location information of mobile crowd sensing users. The framework relies on K-means algorithm and a certificateless aggregate signcryption scheme (CLASC). It incorporates spatial coding as the data compression technique and message query telemetry transport as the messaging protocol. Results presented in this paper show that the proposed framework incurs low computational cost and communication overhead. Also, the framework is robust against privileged insider attack, replay and forgery attacks. Confidentiality, integrity and non-repudiation are security services offered by the proposed framework.

Artificial Intelligence Techniques for Cognitive Sensing in Future IoT: State-of-the-Art, Potentials, and Challenges

Smart, secure and energy-efficient data collection (DC) processes are key to the realization of the full potentials of future Internet of Things (FIoT)-based systems. Currently, challenges in this domain have motivated research efforts towards providing cognitive solutions for IoT usage. One such solution, termed cognitive sensing (CS) describes the use of smart sensors to intelligently perceive inputs from the environment. Further, CS has been proposed for use in FIoT in order to facilitate smart, secure and energy-efficient data collection processes. In this article, we provide a survey of different Artificial Intelligence (AI)-based techniques used over the last decade to provide cognitive sensing solutions for different FIoT applications. We present some state-of-the-art approaches, potentials, and challenges of AI techniques for the identified solutions. This survey contributes to a better understanding of AI techniques deployed for cognitive sensing in FIoT as well as future research directions in this regard.

Hidden Markov Model-Based Smart Annotation for Benchmark Cyclic Activity Recognition Database Using Wearables

Activity monitoring using wearables is becoming ubiquitous, although accurate cycle level analysis, such as step-counting and gait analysis, are limited by a lack of realistic and labeled datasets. The effort required to obtain and annotate such datasets is massive, therefore we propose a smart annotation pipeline which reduces the number of events needing manual adjustment to 14%. For scenarios dominated by walking, this annotation effort is as low as 8%. The pipeline consists of three smart annotation approaches, namely edge detection of the pressure data, local cyclicity estimation, and iteratively trained hierarchical hidden Markov models. Using this pipeline, we have collected and labeled a dataset with over 150,000 labeled cycles, each with 2 phases, from 80 subjects, which we have made publicly available. The dataset consists of 12 different task-driven activities, 10 of which are cyclic. These activities include not only straight and steady-state motions, but also transitions, different ranges of bouts, and changing directions. Each participant wore 5 synchronized inertial measurement units (IMUs) on the wrists, shoes, and in a pocket, as well as pressure insoles and video. We believe that this dataset and smart annotation pipeline are a good basis for creating a benchmark dataset for validation of other semi- and unsupervised algorithms.