Self-touch gestures (e.g., nuanced facial touches and subtle finger scratches) provide rich insights into human behaviors, from hygiene practices to health monitoring. However, existing approaches fall short in detecting such micro gestures due to their diverse movement patterns.This paper presents μTouch, a novel magnetic sensing platform for self-touch gesture recognition. μTouch features (1) a compact hardware design with low-power magnetometers and magnetic silicon, (2) a lightweight semi-supervised framework requiring minimal user data, and (3) an ambient field detection module to mitigate environmental interference. We evaluated μTouch in two representative applications in user studies with 11 and 12 participants. μTouch only requires three-second fine-tuning data for each gesture — new users need less than one minute before starting to use the system. μTouch can distinguish eight different face-touching behaviors with an average accuracy of 93.41%, and reliably detect body-scratch behaviors with an average accuracy of 94.63%. μTouch demonstrates accurate and robust sensing performance even after a month, showcasing its potential as a practical tool for hygiene monitoring and dermatological health applications.

Our hands serve as a fundamental means of interaction with the world around us. Therefore, understanding hand poses and interaction contexts is critical for human-computer interaction (HCI). We present EchoWrist, a low-power wristband that continuously estimates 3D hand poses and recognizes hand-object interactions using active acoustic sensing. EchoWrist is equipped with two speakers emitting inaudible sound waves toward the hand. These sound waves interact with the hand and its surroundings through reflections and diffractions, carrying rich information about the hand’s shape and the objects it interacts with. The information captured by the two microphones goes through a deep learning inference system that recovers hand poses and identifies various everyday hand activities. Results from the two 12-participant user studies show that EchoWrist is effective and efficient at tracking 3D hand poses and recognizing hand-object interactions. Operating at 57.9 mW, EchoWrist can continuously reconstruct 20 3D hand joints with MJEDE of 4.81 mm and recognize 12 naturalistic hand-object interactions with 97.6% accuracy.

In this paper, we introduce EyeEcho, a minimally-obtrusive acoustic sensing system designed to enable glasses to continuously monitor facial expressions. It utilizes two pairs of speakers and microphones mounted on glasses, to emit encoded inaudible acoustic signals directed towards the face, capturing subtle skin deformations associated with facial expressions. The reflected signals are processed through a customized machine-learning pipeline to estimate full facial movements. EyeEcho samples at 83.3 Hz with a relatively low power consumption of 167mW. Our user study involving 12 participants demonstrates that, with just four minutes of training data, EyeEcho achieves highly accurate tracking performance across different real-world scenarios, including sitting, walking, and after remounting the devices. Additionally, a semi-in-the-wild study involving 10 participants further validates EyeEcho’s performance in naturalistic scenarios while participants engage in various daily activities. Finally, we showcase EyeEcho’s potential to be deployed on a commercial-off-the-shelf (COTS) smartphone, offering real-time facial expression tracking.

In this paper, we present GazeTrak, the first acoustic-based eye tracking system on glasses. Our system only needs one speaker and four microphones attached to each side of the glasses. These acoustic sensors capture the formations of the eyeballs and the surrounding areas by emitting encoded inaudible sound towards eyeballs and receiving the reflected signals. These reflected signals are further processed to calculate the echo profiles, which are fed to a customized deep learning pipeline to continuously infer the gaze position. In a user study with 20 participants, GazeTrak achieves an accuracy of 3.6° within the same remounting session and 4.9° across different sessions with a refreshing rate of 83.3 Hz and a power signature of 287.9 mW. Furthermore, we report the performance of our gaze tracking system fully implemented on an MCU with a low-power CNN accelerator (MAX78002). In this configuration, the system runs at up to 83.3 Hz and has a total power signature of 95.4 mW with a 30 Hz FPS.

We present EchoSpeech, a minimally-obtrusive silent speech interface (SSI) powered by low-power active acoustic sensing. EchoSpeech uses speakers and microphones mounted on a glass-frame and emits inaudible sound waves towards the skin. By analyzing echos from multiple paths, EchoSpeech captures subtle skin deformations caused by silent utterances and uses them to infer silent speech. With a user study of 12 participants, we demonstrate that EchoSpeech can recognize 31 isolated commands and 3-6 figure connected digits with 4.5% (std 3.5%) and 6.1% (std 4.2%) Word Error Rate (WER), respectively. We further evaluated EchoSpeech under scenarios including walking and noise injection to test its robustness. We then demonstrated using EchoSpeech in demo applications in real-time operating at 73.3mW, where the real-time pipeline was implemented on a smartphone with only 1-6 minutes of training data. We believe that EchoSpeech takes a solid step towards minimally-obtrusive wearable SSI for real-life deployment.

This paper builds a Near-field Communication (NFC) based localization system that allows ordinary surfaces to locate surrounding objects with high accuracy in the near-field. While there is rich prior work on device-free localization using far-field wireless technologies, the near-field is less explored. Prior work in this space operates at extremely small ranges (a few centimeters), leading to designs that sense close proximity rather than location.

With the emergence of Internet of Things (IoT), many battery-operated sensors are deployed in different applications to collect, process, and analyze useful information. In these applications, sensors are often grouped into different clusters to support higher scalability and better data aggregation. Clustering based on energy distribution among nodes can reduce energy consumption and prolong the network lifespan. In our paper, we propose a machine-learning-based energy-efficient clustering algorithm named QLEC to select cluster heads in high-dimensional space and help non-cluster-head nodes route packets. QLEC first selects cluster heads based on their residual energy through successive rounds. Besides, we prove the optimal cluster number in a high-dimensional wireless network and adopt it in our QLEC algorithm. Furthermore, Q-learning method is utilized to maximize residual energy of the network while routing packets from sensors to the base station (BS). The energy-efficient clustering problem in high dimensional space can be formed as an NP-Complete problem and QLEC is proved to solve it in the running time O(kX), where k is the cluster number and X is the number of updates Q-learning needs to converge. Extensive simulations and experiments based on a large-scale dataset show that the proposed scheme outperforms a newly proposed FCM-based algorithm and k-means clustering in terms of network lifespan, packet delivery rate, and transmission latency. To the best of our knowledge, this is the first work adopting Q-learning method in clustering problems in high-dimensional space.

In the past few years, wireless sensor networks (WSNs) have been widely used in many areas. In these applications, sensors are remotely deployed to gather related environmental information for further analysis. To support higher scalability and better data aggregation, sensor nodes are often grouped into disjoint and mostly non-overlapping clusters. All nodes in a cluster can send their data to the cluster head within d-hop distance, and the head should communicate with other cluster heads and pass all data to base station. For better communication between these cluster heads, lower maintenance cost, and easier management, it is necessary to make the number of the clusters as small as possible. Moreover, in many environments such as mountainous area or underwater monitoring, node deployment is often not flat, resulting in a high dimensional network. In this paper, we focus on proposing a scheme to select cluster heads for a homogeneous network in three-dimensional situation. The scheme meets two requirements: the number of cluster heads is minimum and the head nodes can communicate with each other. These requirements can be formed as an NP-complete problem named d-hop connected dominating set. Correspondingly, we proposed a distributed approximation algorithm and proved its approximation ratio as (d+1)β, where β is a calculated parameter with respect to d. We also analyzed the performance of our algorithm with corresponding numerical experiments.

Summary Anomaly detection plays a crucial part in identifying unforeseen attacks for network and information security. However, the accuracy of existing network anomaly detection approaches is limited because of the lack of sufficient and high‐quality features. Most research works only take information from one network layer into account, which leads to a situation that some key features of other network layers are omitted. To address this issue, we propose a novel approach, named Multi‐Layers Anomaly Detection, which extracts and combines features from different network layers. In order to reduce redundancy and noise derived from the combination of multiple layers, an algorithm called RanPF is designed by applying principal components analysis (PCA) into random forest (RF) algorithm. RanPF uses features selected by PCA to decide the height of every tree in RF and provides a method to select which features for tree nodes to use according to the weights of principal components. To obtain high‐quality features, we adopt an attribute learning mechanism. Naive Bayes is used to characterize the attribute information, which is fast and simple compared with other learning algorithms such as SVM. In addition, a series of experiments conducted on two real‐life datasets demonstrate that our approach outperforms the state‐of‐the‐art methods in terms of detection rate and false alarm rate. MLAD achieves about 99%detection rate and about 0.6%false alarm rate on average when the ratio of the training set is 60%. Copyright © 2016 John Wiley & Sons, Ltd.