Federated learning (FL) is an emerging distributed machine (ML) paradigm with enhanced privacy, aiming to achieve a "good" ML model for as many participants while consuming little wall clock time. By executing across thousands or even millions of clients, FL demonstrates heterogeneous statistical characteristics and system divergence widely participants, making its training suffer when adopting the traditional paradigm. The root cause efficiency degradation random client selection criteria....

User identified gesture recognition is a fundamental step towards ubiquitous device-free sensing. We propose WiHF, which first simultaneously enables cross-domain and user identification using WiFi in real-time manner. The basic idea of WiHF to derive motion change pattern arm gestures from signals, rendering both unique characteristics the personalized performing styles. To extract realtime, we develop an efficient method based on seam carving algorithm. Moreover, taking as input pattern,...

Low-Power Wide-Area Networks (LPWANs) are an emerging Internet-of-Things (IoT) paradigm marked by low-power and long-distance communication. Among them, LoRa is widely deployed for its unique characteristics open-source technology. By adopting the Chirp Spread Spectrum (CSS) modulation, enables low signal-to-noise ratio (SNR) However, standard demodulation method does not fully exploit properties of chirp signals, thus yields a sub-optimal SNR threshold under which decoding fails....

Due to the impact of climate change on agriculture and emergence water security issues, proper irrigation management has become increasingly important overcome challenges. The Internet Things (IoT) technology is being utilized in for collecting field information sharing it through websites real time. This study discusses efforts taken develop an IoT-based sensor station, a user-friendly website, smartphone app management. In addition, demonstration station its effectiveness are discussed....

Soil monitoring plays an essential role in agricultural systems. Rather than deploying sensors' antennas above the ground, burying them soil is attractive way to retain a non-intrusive aboveground space. Low Power Wide-Area Network (LPWAN) has shown its long-distance and low-power features for Internet-of-Things (IoT) communication, presenting potential of extending underground cross-soil communication over wide area, which however not been investigated before. The variation conditions...

We study the ubiquitous data collection for mobile users in wireless sensor networks. People with handheld devices can easily interact network and collect data. propose a novel approach to network-wide The routing structure of is additively updated movement user. With this approach, we only perform local modification update while performance bounded controlled compared optimal performance. proposed protocol easy implement. Our analysis shows that scalable maintenance overheads, performs...

To save energy, wireless sensor networks often run in a low duty cycle mode, where the radios of nodes are scheduled between ON and OFF states. For to communicate with each other, Low Power Listening (LPL) Probing (LPP) two types rendezvous mechanisms. Nodes LPL or LPP rely on signal strength probe packets detect potential transmissions, then keep radio-on for communications. Unfortunately, many cases, susceptible interference, resulting undesirable radio time when interference is above...

User identified gesture recognition is a fundamental step towards ubiquitous WiFi based sensing. We propose WiHF, which first simultaneously enables cross-domain and user identification using commodity in real-time manner. The basic idea of WiHF to derive domain-independent motion change pattern arm gestures from signals, rendering the unique characteristics personalized performing styles. To extract real time, we develop an efficient method on seam carving algorithm. Moreover, taking as...

LoRa (Long Range) is an emerging wireless technology that enables long-distance communication and keeps low power consumption. Therefore, plays a more important role in Low-Power Wide-Area Networks (LPWANs), which easily extend many large-scale Internet of Things (IoT) applications diverse scenarios (e.g., industry, agriculture, city). In lots environments where various types land-covers usually exist, it challenging to precisely predict link's path loss. As result, how deploy gateways...

This paper introduces ChirpTransformer, a versatile LoRa encoding framework that harnesses broad chirp features to dynamically modulate data, enhancing network coverage, throughput, and energy efficiency. Unlike the standard encoder offers only single configurable feature, our four distinct features, expanding spectrum of methods available for data modulation. To implement these on commercial off-the-shelf (COTS) nodes, we utilize combination software design hardware interrupt....

Motion tracking via Inertial Measurement Units (IMUs) on mobile and wearable devices has attracted significant interest in recent years. High-accuracy IMU-tracking can be applied various applications, such as indoor navigation, gesture recognition, text input, etc. Many efforts have been devoted to improving IMU-based motion the last two decades, from early calibration techniques ships or airplanes, arm models used smart devices. In this paper, we present a comprehensive survey We also...

The integration of the Internet Things (IoT) and modern Artificial Intelligence (AI) has given rise to a new paradigm known as (AIoT). In this survey, we provide systematic comprehensive review AIoT research. We examine literature related sensing, computing, networking & communication, which form three key components AIoT. addition advancements in these areas, domain-specific systems that are designed for various important application domains. have also created an accompanying GitHub...

More than one billion people lack access to safe drinking water in the world. Providing a way measure automatically quality will help tackle this problem. This paper presents design of measuring system and proposes prototype implementation wireless sensor network (WQWSN) as solution challenging When applied developing countries, such must take into consideration difficult environment which it operate. An application measurement Malawi reveals relevance using our novel mitigate two issues:...

We present a comprehensive delay performance measurement and analysis in large-scale wireless sensor network. build lightweight system robust method to calculate the per-packet delay. show that can identify incorrect delays recover them with bounded error. Through of other metrics, we seek answer following fundamental questions: What are spatial temporal characteristics real network? most important impacting factors, is there any practical model capture those factors? implications protocol...

Device-to-device communication is widely used for mobile devices and Internet of Things. Authentication key agreement are critical to build a secure channel between two devices. However, existing approaches often rely on pre-built fingerprint database suffer from low generation rate. We present GeneWave, fast device authentication protocol commodity GeneWave first achieves bidirectional initial based the physical response interval To keep accuracy estimation, we eliminate time uncertainty...

To save energy, wireless sensor networks often run in a low-duty-cycle mode, where the radios of nodes are scheduled between ON and OFF states. For to communicate with each other, low power listening (LPL) probing (LPP) two types rendezvous mechanisms. Nodes LPL or LPP rely on signal strength probe packets detect potential transmissions, then keep radio-ON for communications. Unfortunately, co-existing environments, susceptible interference, resulting undesirable radio time when interference...

Internet-of-Things (IoT) aims to connect billions of low-date rate and energy-constrained end-devices in the near future. Although many IoT systems have been commercialized, most them focus on home body scale applications. To establish a low-cost at city scale, LoRa Wide Area Networks (LoRaWAN) become attractive recent years due their desirable kilometer or even longer communication distance with low energy consumption. However, expensive cost densely deploying end-nodes, understanding link...

Energy-constrained wireless sensor networks are duty-cycled, relaying on multi-hop forwarding to collect data packets. A scheme generally involves three design elements: media access, link estimation, and routing strategy. Most existing studies, however, focus only a subset of those three. Disregarding the low duty cycle nature access often leads overestimate quality. Neglecting characteristic bursty loss over links inevitably consumes much more energy than necessary underutilizes channels....