Recently, gesture recognition has gained considerable attention in emerging applications (e.g., AR/VR systems) to provide a better user experience for human-computer interaction. Existing solutions usually recognize the gestures based on wearable sensors or specialized signals WiFi, acoustic and visible light), but they are either incurring high energy consumption susceptible ambient environment, which prevents them from efficiently sensing fine-grained finger movements. In this paper, we...

Enabling touch gesture sensing on all surfaces of the mobile device, not limited to touchscreen area, leads new user interaction experiences. In this paper, we propose VSkin, a system that supports fine-grained gesture-sensing back devices based acoustic signals. VSkin utilizes both structure-borne sounds, i.e., sounds propagating through structure and air-borne air, sense finger tapping movements. By measuring amplitude phase each path sound signals, detects events with an accuracy 99.65%...

Due to the widespread use of mobile devices, it is essential authenticate users on devices prevent sensitive information leakage. In this paper, we propose TouchID, which combinedly uses touch sensor and inertial for gesture analysis, provide a based user authentication scheme. Specifically, TouchID utilizes analyze on-screen while using device's motion caused by gesture, then combines unique features from authentication. To mitigate intra-class difference reduce inter-class similarity,...

In recent years, healthcare IoT have been helpful in mitigating pressures of hospital and medical resources caused by aging population to a large extent. As safety-critical system, the rapid response from health care system is extremely important. To fulfill low latency requirement, fog computing competitive solution deploying devices on edge clouds. However, these generate huge amount sensor data. Designing specific framework for ensure reliable data transmission processing becomes topic...

This novel double heterojunction carbon quantum dots (CQDs)/CeO2/BaFe12O19 magnetic separation photocatalysts (CCBFOMSPs) were successfully prepared via a polyacrylamide gel method and low temperature sintering technology combined with hydrothermal method. The CQDs components in CCBFOMSPs identified by neutron powder diffraction, Raman spectroscopy X-ray photoelectron spectroscopy. charge carriers could transfer between the valence state (CeO2 BaFe12O19) facilely, inhibiting recombination of...

Coupling photocatalytic H2 evolution with benzyl alcohol (BA) oxidation to benzaldehyde (BAD) reaction allows the full utilization of energy light-induced electron and hole produce fuel valuable chemicals, which has received widespread attention recently. Herein, Co(OH)2 nanosheet array-GR composites cocatalyst can be successfully synthesized by simple precipitation method, then CdS nanoparticles are in situ grown hybrid finally obtain CdS-Co(OH)2-GR ternary photocatalysts. Composting...

In this paper we consider how to efficiently identify tags on the moving conveyor. Considering conditions like path loss and multi-path effect in realistic settings, first propose a probabilistic model for RFID tag identification. Based model, efficient solutions tags, according fixed-path mobility A dynamic program based solution an adaptive are proposed select optimized frame sizes during query cycles. Simulation results indicate that by leveraging our can achieve much better performance...

The advances of Radio-Frequency Identification (RFID) technology have significantly enhanced the capability capturing data from pervasive space. It becomes a great challenge in information era to effectively understand human behavior, mobility and activity through perceived RFID data. Focusing on management, this article provides an overview current challenges, emerging opportunities recent progresses RFID. In particular, has described analyzed research work three aspects: algorithm,...

As an important indicator of autonomic regulation for circulatory function, Heart Rate Variability (HRV) is widely used general health evaluation. Apart from using dedicated devices (e.g, ECG) in a wired manner, current methods search ubiquitous manner by either wearable devices, which suffer low accuracy and limited battery life, or applying wireless techniques (e.g., FMCW), usually utilize USRP) the measurement. To address these issues, we present RF-ECG based on Commercial-Off-The-Shelf...

In this paper, we propose to use the vibration of chest in response heartbeat as a biometric feature authenticate user on mobile devices. We built-in accelerometer capture signals commercial phones. The only needs press phone his/her chest, and system can identify within few heartbeats. To reliably extract features, design two-step alignment scheme that handle natural variability human heart rates. further an adaptive template selection under different body postures states. Based collected...

Dual regulation of the electrode interface and solvation structure is reported. We employ polyhydroxy Suc as additive for AZIBs, which effectively reduces number coordination water molecules realizes uniform deposition Zn 2+ .

The rising popularity of electronic devices with gesture recognition capabilities makes the gesture-based human-computer interaction more attractive. Along this direction, tracking body movement in 3D space is desirable to further facilitate behavior various scenarios. Existing solutions attempt track based on computer version or wearable sensors, but they are either dependent light incurring high energy consumption. This paper presents RF-Kinect, a training-free system which tracks by...

In a number of RFID-based applications such as logistics monitoring, the RFID systems are deployed to monitor large tags. They usually required track movement all tags in real-time approach, since tagged-goods moved and out rather frequent approach. However, typical cycle tag inventory COTS system takes tens seconds interrogate hundreds This hinders time. One critical issue type monitoring is efficiently distinguish motion status tags, i.e., stationary or moving. According different...

This paper introduces the NWPU Team's entry to ICASSP 2022 AEC Challenge. We take a hybrid approach that cascades linear with neural post-filter. The former is used deal echo components while latter suppresses residual non-linear components. use gated convolutional F-T-LSTM network (GFTNN) as backbone and shape post-filter by multi-task learning (MTL) framework, where voice activity detection (VAD) module adopted an auxiliary task along suppression, aim avoid over suppression may cause...

With the proliferation of voice assistants, microphone-based speech recognition technology usually cannot achieve good performance in situation multiple sound sources and ambient noises. In this paper, we propose a novel mmWave-based solution to perform tackle issues noises, by precisely extracting multi-modal features from lip motion vocal-cords vibration single channel mmWave. We difference-based method for feature extraction suppress dynamic interference body head motion. detection based...

Controllable speech generation methods typically rely on single or fixed prompts, hindering creativity and flexibility. These limitations make it difficult to meet specific user needs in certain scenarios, such as adjusting the style while preserving a selected speaker's timbre, choosing generating voice that matches character's visual appearance. To overcome these challenges, we propose \textit{FleSpeech}, novel multi-stage framework allows for more flexible manipulation of attributes by...

Health care informatics has emerged as a diverse and important new field of study. The can be very broadly defined the science that addresses how best to use information improve health care. includes four areas ...

Autonomous racing presents a complex environment requiring robust controllers capable of making rapid decisions under dynamic conditions. While traditional based on tire models are reliable, they often demand extensive tuning or system identification. RL methods offer significant potential due to their ability learn directly from interaction, yet typically suffer the Sim-to-Reall gap, where policies trained in simulation fail perform effectively real world. In this paper, we propose RLPP,...

Integrating human feedback to align text-to-speech (TTS) system outputs with preferences has proven be an effective approach for enhancing the robustness of language model-based TTS systems. Current approaches primarily focus on using preference data annotated at utterance level. However, frequent issues that affect listening experience often only arise in specific segments audio samples, while other are well-generated. In this study, we propose a fine-grained optimization (FPO) enhance FPO...

Designing drugs that can restore a diseased cell to its healthy state is an emerging approach in systems pharmacology address medical needs conventional target-based drug discovery paradigms have failed meet. Single-cell transcriptomics comprehensively map the differences between and cellular states, making it valuable technique for pharmacology. However, single-cell omics data noisy, heterogeneous, scarce, high-dimensional. As result, no machine learning methods currently exist use design...