A5030974418- Indoor and Outdoor Localization Technologies
- Underwater Vehicles and Communication Systems
- Energy Harvesting in Wireless Networks
- Context-Aware Activity Recognition Systems
- Speech and Audio Processing
- Mobile Ad Hoc Networks
- Water Quality Monitoring Technologies
- Wireless Body Area Networks
- Opportunistic and Delay-Tolerant Networks
- Wireless Networks and Protocols
- Advanced Surface Polishing Techniques
- IoT and Edge/Fog Computing
- Visual Attention and Saliency Detection
- Robotic Path Planning Algorithms
- Evaluation Methods in Various Fields
- Advanced Image and Video Retrieval Techniques
- Advanced Wireless Network Optimization
- Caching and Content Delivery
- Obstructive Sleep Apnea Research
- Advanced MIMO Systems Optimization
- Hydrological Forecasting Using AI
- Wireless Communication Security Techniques
- Non-Invasive Vital Sign Monitoring
- Advancements in Photolithography Techniques
- Housing Market and Economics
University of Georgia
2023-2024
University of Connecticut
2015-2023
Liaoning Technical University
2013
Tianjin University
2012
Wuhan University of Technology
2010
Anhui University
2010
Artificial General Intelligence (AGI), possessing the capacity to comprehend, learn, and execute tasks with human cognitive abilities, engenders significant anticipation intrigue across scientific, commercial, societal arenas. This fascination extends particularly Internet of Things (IoT), a landscape characterized by interconnection countless devices, sensors, systems, collectively gathering sharing data enable intelligent decision-making automation. research embarks on an exploration...
The demand for indoor localization services in the Internet of Things (IoT) has been increasing dramatically during last decade. Many systems adopt Wi-Fi fingerprinting with received signal strength indicators (RSSIs) as a source sensors to localize an object because it is cost effective and can give high accuracy. However, fluctuation wireless signals resulting from environmental uncertainties leads considerable variations RSSIs, which poses challenge accurate on single floor, not mention...
No abstract available.
The location-based services for Internet of Things (IoTs) have attracted extensive research effort during the last decades. Wi-Fi fingerprinting with received signal strength indicator (RSSI) has been widely adopted in vast indoor localization systems due to its relatively low cost and potency high accuracy. However, fluctuation wireless resulting from environment uncertainties leads considerable variations on RSSIs, which poses grand challenges fingerprint-based regarding positioning In...
The widespread deployment of machine learning techniques in ubiquitous computing environments has sparked interests exploiting the vast amount data stored on mobile devices. To preserve privacy, federated (FL) been proposed to learn a shared model by performing distributed training locally participating devices and aggregating local models into global one. Reinforcement (RL) can improve indoor localization accounting for environmental dynamics, but trained centralized data. An FL version RL...
Recently, Underwater Wireless Sensor Networks (UWSNs) have attracted increasing attentions from the public as it enables a wide range of underwater applications. However, long propagation delay and high error probability in UWSNs pose grand challenges for efficient reliable protocol designs time critical applications such pollution detection. In this paper, we propose new medium access control (MAC) protocol, named On-demand Pipelined MAC (OPMAC), UWSNs. The basic idea is to establish an...
The high propagation delay in Underwater Sensor Networks (UWSNs) causes space-time uncertainty, making spatial fairness a challenging problem UWSNs. In this paper, we propose weight-based spatially fair MAC protocol (WSF-MAC) for It postpones sending the underwater-reply (UW-REP) packet silence duration time, and then determines node to send UW-REQ first according time competition count of underwater-request (UW-REQ) packets UW-REP get ready transmission. simulation results show that WSF-MAC...
Real-time video streaming over wireless links imposes strong demands on codecs and quality of networks. Many measures are made to design proper routing protocols channel assignments (CAs) for multi-channel multi-interface (MCMI) networks, since it can provide higher performance than single channel. However, there still has not been a well-studied proposal guarantee real-time in this situation. Hence, motivates us explore the potential synergies exchanging information between different layers...
In automated sleep monitoring systems, bed occupancy detection is the foundation or first step before other downstream tasks, such as inferring activities and vital signs. The existing methods do not generalize well to real-world environments due single environment settings rely on threshold-based approaches. Manually selecting thresholds requires observing a large amount of data may yield optimal results. contrast, acquiring extensive labeled sensory poses significant challenges regarding...
Fine-tuning large language models (LLMs) poses significant memory challenges, as the back-propagation process demands extensive resources, especially with growing model sizes. Recent work, MeZO, addresses this issue using a zeroth-order (ZO) optimization method, which reduces consumption by matching usage to inference phase. However, MeZO experiences slow convergence due varying curvatures across parameters. To overcome limitation, we introduce HELENE, novel scalable and memory-efficient...
Body Mass Index (BMI) is a critical metric for assessing public health and identifying populations at risk obesity-related conditions. Traditional BMI monitoring methods often raise privacy concerns require active cooperation from individuals, limiting their applicability in real-world scenarios. This paper introduces novel approach to that leverages proximal federated learning (PFL) using commodity WiFi devices. Our method addresses the challenges of data heterogeneity intermittent...
Relevant to visual attention mechanism, saliency are concerns of detecting the salient regions in image and video. Saliency detection is a critical pre-process many computer vision applications, which requires high-level recognition scene understanding as well low-level photo video processing. In this paper, We propose new bi-subspace bottom-up model. Inspired by visually intuitions priors, we formulate problem subspace analysis depicting background aside from object image. meanwhile,...
在海洋环境的影响下，水下无线传感器网络(UWSN)节点始终处于运动状态；UWSN采用声信号通信，缓慢的节点移动也会造成UWSN现有的多址接入技术(MAC)协议冲突避免机制失效。该文建立了水下节点的运动模型，基于AR运动预测模型减小水下节点的时空不确定性对于MAC协议的影响，提高发送信息在预约时隙到达的概率。仿真结果表明，采用AR(5)预测可以减小74.8%的时延探测误差。提出了基于预测的预约MAC协议：P-MAC。NS-2仿真结果表明该协议在海浪运动场景下能提高收包成功率(PRR)10%-15%。
Property restriction order that is caused by the rapid rise in housing prices some cities of China and developed government, a series measures to restrict commercial house transaction, control protect rigid demand. There no clear economic standard determine city when implement property since two years more. This paper use Fisher discriminant analysis method research whether should order, came conclusions. According model, we can build purchase limit standards. For any one city, just put all...
Accurate prediction of crop yield under the conditions climate change is crucial to ensure food security. Transformers have shown remarkable success in modeling sequential data and hold potential for improving prediction. To understand how weather meteorological sequence variables affect yield, positional encoding used typically shared across different sample sequences. We argue that it necessary beneficial differentiate distinct samples based on time-invariant properties Particularly,...