Eggs and chickens serve as crucial animal-source proteins in our diets, making large-scale breeding egg incubation an essential undertaking. However, current solutions, i.e., vision-based sensor-based methods, are primarily designed for fertility detection tasks under single-egg settings, which have not yet satisfied the goal of multi-target multi-task sensing. In this paper, we propose RF-Egg, first RF-based fine-grained sensing system with respect to fertility, status, early mortality...

In this paper, we proposed F2Key, the first earable physical security system based on commercial off-the-shelf headphones. F2Key enables impactful applications, such as enhancing voiceprint-based authentication systems, reliable voice assistants, audio deepfake defense, and legal validity of artifacts. The key idea is to establish a stable acoustic sensing field across user's face embed facial structures articulatory habits into user-specific generative model that serves private key. can...

This paper presents EMGSense, a low-effort self-supervised domain adaptation framework for sensing applications based on Electromyography (EMG). EMGSense addresses one of the fundamental challenges in EMG cross-user sensing—the significant performance degradation caused by time-varying biological heterogeneity—in (data-efficient and label-free) manner. To alleviate burden data collection avoid labor-intensive annotation, we propose two EMG-specific augmentation methods to simulate signals...

Water has a significant impact on the dielectric constant of materials. As multiphase composite material, effect water content must be taken into account when modeling cement concrete. Cement concrete traditionally been thought as three-phase mixed material consisting mortar, aggregate (limestone), and pores (air). was used constituent in this paper, its described terms saturation. By abstracting components independent medium units arranging them according to certain rules, four-phase mixing...

Handwritten signature verification has become one of the most important document authentication methods that are widely used in financial, legal, and administrative sectors. Compared with offline based on static images, online handwritten more reliable because temporary dynamic information (e.g., signing velocity, writing force, stroke order) alleviates risk being forged. However, existing solutions reliant specific devices customized pens or pads) require extensive data collection during...

Low exothermic polyurethane grouting material, as a new type of is used for road reinforcement and repair engineering in frozen earth areas. This study investigates the mechanical properties this material under different ambient temperatures. The effects temperature density on expansion pressure, compressive strength, tensile strength materials were determined study. characteristics material's stress–strain curves analyzed microscopically. results demonstrate that significantly influenced...

Speech enhancement is regarded as the key to quality of digital communication and gaining increasing attention in research field audio processing. In this paper, we present EarSE, first robust, hands-free, multi-modal speech solution using commercial off-the-shelf headphones. The idea EarSE a novel hardware setting---leveraging form factor headphones equipped with boom microphone establish stable acoustic sensing across user's face. Furthermore, designed methodology based on...

Vowels are a fundamental component of Mandarin Chinese syllables. Accurate pronunciation relies on the distinct articulation different vowels, especially visually similar "ü" and "u". Korean-speaking learners as second language commonly exhibit non-standard or errors in articulating "ü", leading to confusion, particularly non-low vowels centered around this sound. Using Praat analyze Formant values vowel sounds from six participants, comparison between Korean L2 speakers native revealed...

In the realm of smart sensing with Internet Things, earable devices are empowered capability multi-modality and intelligence context-aware computing, leading to its wide usage in Human Activity Recognition (HAR).Nonetheless, unlike movements captured by Inertial Measurement Unit (IMU) sensors placed on upper or lower body, those motion signals obtained from show significant changes amplitudes patterns, especially presence dynamic unpredictable head movements, posing a challenge for activity...

The remarkable growth of Virtual Reality (VR) in recent years has extended its applications beyond entertainment to sectors including education, e-commerce, and remote communication. Since VR devices contain user's private information, user authentication becomes increasingly important. Current systems VR, such as password-based or static biometric-based methods, are either cumbersome use vulnerable attacks shoulder surfing. To address these limitations, we propose Medusa3D, a...

Resistance training is widely incorporated in exercise programs, including in-home fitness and rehabilitation. However, improper motion patterns muscle stimulation can undermine the safety of subjects, making precise monitoring essential. Existing solutions primarily focus on correcting with difficulties assessing contraction levels. In this work, we introduce MyoTrainer, which provides muscle-aware descriptions personalized feedback natural language. Taking a person's video as input,...

In this paper, we propose Argus, a wearable add-on system based on stripped-down (i.e., compact, lightweight, low-power, limited-capability) mmWave radars. It is the first to achieve egocentric human mesh reconstruction in multi-view manner. Compared with conventional frontal-view sensing solutions, it addresses several pain points, such as restricted range, occlusion, and multipath effect caused by surroundings. To overcome limited capabilities of radars (with only one transmit antenna...

Millimeter-wave (mmWave) radar-based gesture recognition is gaining attention as a key technology to enable intuitive human-machine interaction. Nevertheless, the significant challenge lies in obtaining large-scale, high-quality mmWave datasets. To tackle this problem, we present iRadar, novel cross-modal framework that employs Inertial Measurement Unit (IMU) data synthesize radar signals generated by corresponding gestures. The idea exploit IMU signals, which are commonly available...

In this study, the combination of macroporous adsorbent resins (MARs) and thin-film evaporation coupling distillation (TFECD) was studied systematically, with aim to obtain high value-added squalene from soybean oil deodorizer distillate (SODD). Five types (X-5, D-101, D4020, DM301, AB-8) were first used evaluate adsorption/desorption properties squalene. D101 resin exhibited higher capacities desorption ratios for based on static adsorption results among tested resins. We further...

Abstract Various toxic metal ions were successfully removed from solid matrix into supercritical CO 2 (scCO ) by open-chain crown ether bridged diphosphates at 313.15 K and 20 MPa, these with different ester side chains length of ethylene oxide bridge group are highly soluble in . The extraction efficiency ( E %) heavy metals is between 55 89%. Mulliken charge distribution ligand’s P=O coordination was calculated to indicate the stability complex. ligand structure effects rationale for...

Vowels are the main components of Chinese syllables, and in order to produce standard pronunciation, it is essential accurately distinguish pronunciation vowel variants under different conditions. Korean-speaking learners often struggle with differentiating non-low back vowels, leading errors. Through Praat speech analysis formant values for vowels by six participants, Korean L2 speakers L1 speakers’ spaces were compared. It was found that distinction between /ʅ / /ɿ not very clear, both...