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

Abstract

Automatic data annotation eliminates most of the challenges we faced due to the manual methods of annotating sensor data. It significantly improves users’ experience during sensing activities since their active involvement in the labeling process is reduced. An unsupervised learning technique such as clustering can be used to automatically annotate sensor data. However, the lingering issue with clustering is the validation of generated clusters. In this paper, we adopted the k-means clustering algorithm for annotating unlabeled sensor data for the purpose of detecting sensitive location information of mobile crowd sensing users. Furthermore, we proposed a cluster validation index for the k-means algorithm, which is based on Multiple Pair-Frequency. Thereafter, we trained three classifiers (Support Vector Machine, K-Nearest Neighbor, and Naïve Bayes) using cluster labels generated from the k-means clustering algorithm. The accuracy, precision, and recall of these classifiers were evaluated during the classification of “non-sensitive” and “sensitive” data from motion and location sensors. Very high accuracy scores were recorded from Support Vector Machine and K-Nearest Neighbor classifiers while a fairly high accuracy score was recorded from the Naïve Bayes classifier. With the hybridized machine learning (unsupervised and supervised) technique presented in this paper, unlabeled sensor data was automatically annotated and then classified.

Cyber-criminology defense in pervasive environment: A study of cybercrimes in Malaysia

“…This information is then could be inputted as in designing access control in terms of adding user permission and its level. Another promising path is in the protection of metadata using technologies which are secure and tamper proof such as blockchain technologies [41]. The mechanisms of authentication are divided based on authenticator IDS, channel/communications, protocol and technologies and authentication requirements.…”

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

“…To apply unsupervised approaches, one needs to define to which labels these underlying structures refer and the applicability of them within the particular application domain. Unsupervised approaches successfully used in the wearables domain include clustering methods [20], cross-correlation-based ones [17] and information gain-based methods [21]. Part of our data was completely unlabeled and so we used a basic peak detector and compared it to the local cyclicity estimator, the cross-correlation-based unsupervised method from [17].…”

Security analysis of mobile crowd sensing applications

“…Despite its benefits, MCS applications still face challenges such as quality and reliability of sensed data (data and user trustworthiness) [10], incentivizing participants [11,12], energy consumption of mobile sensing devices [9,13], sensor data annotation [14], security and privacy [15,16]. The quality and reliability of sensed data is a lingering issue in MCS applications, as participants could deliberately report low-quality or fake data.…”