Search

Device-free human activity recognition (HAR) has gained attention in recent years. While much has been done in coarse-grained HAR, the recognition of fine-grained human activities is still a research challenge. In this article, we present a novel method to combine channel state information (CSI) and received signal strength indicator (RSSI) signals at the feature level to improve the performance of device-free fine-grained HAR using WiFi data. We extract seven CSI and three RSSI non-segmented frequency-domain features, 12 segmented time-domain features, and five segmented frequency-domain features to select the feature set. We evaluate our method using a dataset containing 12 human-to-human fine-grained interactions. We utilized various classification methods like support vector machine (SVM), Gaussian–Naïve–Bayes (GNB), decision tree (DT), logistic regression (LR), linear discriminant analysis (LDA), K-nearest neighbors (KNN), and random forest (RF) using the feature set as input. Our evaluation result yields 94.16% of accuracy, 94.3% of precision, 94.24% of recall, 94.13% $F1$ -score, 93.18% of ${k}$ -score, and 95.91% area under the curve (AUC) in recognition of seven human-to-human interactions using RF.

Conflict is one of the important factors affecting user satisfaction and trust in smart environments, yet conflict modeling in mixed initiative smart environments has not been sufficiently explored. Most of the existing literature on conflict in smart homes are centered on conflicts between users. Although research has shown that about 75% of conflicts are between users and system [1], only a few studies have considered user-system conflicts in smart homes. The aim of this article is to empirically propose both a definition and a run-time detection method for conflicts between users and smart home systems. Our empirical study is based on conflict sample scenarios collected from 163 users. Using clustering on these scenarios, we form an empirical definition of user-system conflict in smart homes. We also propose two functions that characterize each class of the collected scenarios, and we detect conflicts from this characterization. Our conflict detection model could help users achieve a more satisfactory experience in smart homes. Moreover, the model can offer benefits for system developers to design and deploy more reliable smart homes.

An important challenge in smart environments is how to manipulate the smart objects. Although mobile applications are typically used for controlling a smart environment, no previous study has evaluated the users performance in manipulating smart objects under different environmental complexities. This article presents an experimental comparison between three different selection techniques 3-D, 2-D, and physical user interfaces (UIs). We evaluate these techniques across two levels of environment complexity measuring 51 participants timing data and errors. Our results indicate that the 3-D UI is superior for task completion time and error, and the 2-D UI is not a better solution than the physical UI when the environment is not complex. The results also show the importance of considering the environment complexity in choosing the proper UI.

Initiative or control authority is an important challenge in smart environments, including smart homes. One of the solutions to this challenge is End-user Development (EUD). The EUD refers to defining customized rules by users to determine their desired behaviour and preferences in the format of trigger-action or event-condition-action for their smart home. But EUD rules need an understanding of mathematical logic; hence they are not understandable for general users including children. This paper proposes a user interface specifically designed for children to define EUD tasks in smart homes. The proposed UI was designed and evaluated in three iterations and had two main characteristics: gamification and 3D abstraction level for showing devices. The proposed UI is evaluated through an experiment by 32 participants aged 8–12 to measure efficiency, operability, perceived usability, enjoyment, and engagement. The experiment results show that game-based design improved usability by increasing efficiency and operability metrics. Also, based on the survey result, it improved enjoyment, engagement, and perceived usability.