Search for: All records

Abstract Segmentation of structural components in infrastructure inspection images is crucial for automated and accurate condition assessment. While deep neural networks hold great potential for this task, existing methods typically require fully annotated ground truth masks, which are time‐consuming and labor‐intensive to create. This paper introducesScribble‐supervised StructuralComponent SegmentationNetwork (ScribCompNet), the first weakly‐supervised method requiring only scribble annotations for multiclass structural component segmentation. ScribCompNet features a dual‐branch architecture with higher‐resolution refinement to enhance fine detail detection. It extends supervision from labeled to unlabeled pixels through a combined objective function, incorporating scribble annotation, dynamic pseudo label, semantic context enhancement, and scale‐adaptive harmony losses. Experimental results show that ScribCompNet outperforms other scribble‐supervised methods and most fully‐supervised counterparts, achieving 90.19% mean intersection over union (mIoU) with an 80% reduction in labeling time. Further evaluations confirm the effectiveness of the novel designs and robust performance, even with lower‐quality scribble annotations. 

Smart glasses have become more prevalent as they provide an increasing number of applications for users. They store various types of private information or can access it via connections established with other devices. Therefore, there is a growing need for user identification on smart glasses. In this paper, we introduce a low-power and minimally-obtrusive system called SonicID, designed to authenticate users on glasses. SonicID extracts unique biometric information from users by scanning their faces with ultrasonic waves and utilizes this information to distinguish between different users, powered by a customized binary classifier with the ResNet-18 architecture. SonicID can authenticate users by scanning their face for 0.06 seconds. A user study involving 40 participants confirms that SonicID achieves a true positive rate of 97.4%, a false positive rate of 4.3%, and a balanced accuracy of 96.6% using just 1 minute of training data collected for each new user. This performance is relatively consistent across different remounting sessions and days. Given this promising performance, we further discuss the potential applications of SonicID and methods to improve its performance in the future. 

We present ActSonic, an intelligent, low-power active acoustic sensing system integrated into eyeglasses that can recognize 27 different everyday activities (e.g., eating, drinking, toothbrushing) from inaudible acoustic waves around the body. It requires only a pair of miniature speakers and microphones mounted on each hinge of the eyeglasses to emit ultrasonic waves, creating an acoustic aura around the body. The acoustic signals are reflected based on the position and motion of various body parts, captured by the microphones, and analyzed by a customized self-supervised deep learning framework to infer the performed activities on a remote device such as a mobile phone or cloud server. ActSonic was evaluated in user studies with 19 participants across 19 households to track its efficacy in everyday activity recognition. Without requiring any training data from new users (leave-one-participant-out evaluation), ActSonic detected 27 activities, achieving an average F1-score of 86.6% in fully unconstrained scenarios and 93.4% in prompted settings at participants' homes. 

With the advances in deep learning, speaker verification has achieved very high accuracy and is gaining popularity as a type of biometric authentication option in many scenes of our daily life, especially the growing market of web services. Compared to traditional passwords, “vocal passwords” are much more convenient as they relieve people from memorizing different passwords. However, new machine learning attacks are putting these voice authentication systems at risk. Without a strong security guarantee, attackers could access legitimate users’ web accounts by fooling the deep neural network (DNN) based voice recognition models. In this article, we demonstrate an easy-to-implement data poisoning attack to the voice authentication system, which cannot be captured effectively by existing defense mechanisms. Thus, we also propose a more robust defense method called Guardian, a convolutional neural network-based discriminator. The Guardian discriminator integrates a series of novel techniques including bias reduction, input augmentation, and ensemble learning. Our approach is able to distinguish about 95% of attacked accounts from normal accounts, which is much more effective than existing approaches with only 60% accuracy. 

We present Ring-a-Pose, a single untethered ring that tracks continuous 3D hand poses. Located in the center of the hand, the ring emits an inaudible acoustic signal that each hand pose reflects differently. Ring-a-Pose imposes minimal obtrusions on the hand, unlike multi-ring or glove systems. It is not affected by the choice of clothing that may cover wrist-worn systems. In a series of three user studies with a total of 36 participants, we evaluate Ring-a-Pose's performance on pose tracking and micro-finger gesture recognition. Without collecting any training data from a user, Ring-a-Pose tracks continuous hand poses with a joint error of 14.1mm. The joint error decreases to 10.3mm for fine-tuned user-dependent models. Ring-a-Pose recognizes 7-class micro-gestures with a 90.60% and 99.27% accuracy for user-independent and user-dependent models, respectively. Furthermore, the ring exhibits promising performance when worn on any finger. Ring-a-Pose enables the future of smart rings to track and recognize hand poses using relatively low-power acoustic sensing. 

Leaves are the primary harvest portion in forage crops such as alfalfa (Medicago sativa). Delaying leaf senescence is an effective strategy to improve forage biomass production and quality. In this study, we employed transcriptome sequencing to analyze the transcriptional changes and identify key senescence-associated genes under age-dependent leaf senescence in Medicago truncatula, a legume forage model plant. Through comparing the obtained expression data at different time points, we obtained 1057 differentially expressed genes, with 108 consistently up-regulated genes across leaf growth and senescence. Gene Ontology and Kyoto Encyclopedia of Genes and Genomes pathway enrichment analyses showed that the 108 SAGs mainly related to protein processing, nitrogen metabolism, amino acid metabolism, RNA degradation and plant hormone signal transduction. Among the 108 SAGs, seven transcription factors were identified in which a novel bZIP transcription factor MtbZIP60 was proved to inhibit leaf senescence. MtbZIP60 encodes a nuclear-localized protein and possesses transactivation activity. Further study demonstrated MtbZIP60 could associate with MtWRKY40, both of which exhibited an up-regulated expression pattern during leaf senescence, indicating their crucial roles in the regulation of leaf senescence. Our findings help elucidate the molecular mechanisms of leaf senescence in M. truncatula and provide candidates for the genetic improvement of forage crops, with a focus on regulating leaf senescence.