Wireless networks have been widely deployed for many Internet-of-Things (IoT) applications, like smart cities and precision agriculture. Low Power Wide Area Networking (LPWAN) is an emerging IoT networking paradigm to meet three key requirements of i.e., low cost, large scale deployment high energy efficiency. Among all available LPWAN technologies, LoRa has attracted much attention from both academia industry, since it specifies open standard allows us build autonomous without any...

In this paper, we introduce a new large-scale dataset of ships, called SeaShips, which is designed for training and evaluating ship object detection algorithms. The currently consists 31 455 images covers six common types (ore carrier, bulk cargo general ship, container fishing boat, passenger ship). All the are from about 10 080 real-world video segments, acquired by monitoring cameras in deployed coastline surveillance system. They carefully selected to mostly cover all possible imaging...

Real-time detection of inshore ships plays an essential role in the efficient monitoring and management maritime traffic transportation for port management. Current ship methods which are mainly based on remote sensing images or radar hardly meet real-time requirement due to timeliness image acquisition. In this paper, we propose use visual captured by on-land surveillance camera network achieve detection. However, complex background diversity categories, existing convolution neural (CNN)...

This paper presents Pando, a completely contention-free data dissemination protocol for wireless sensor networks. Pando encodes by Fountain codes and disseminates the rateless stream of encoded packets along fast parallel pipelines built on constructive interference channel diversity. Since every packet contains innovative information to original object, avoids duplicate retransmissions fully exploits broadcast effect in dissemination. To transform into practical system, we devise several...

LoRa has recently become one of the most promising networking technologies for Internet Things applications. Distant end devices have to use a low data rate reach gateway, which can cause long in-the-air transmission time and high energy consumption. Compared with using rate, they will drain batteries much earlier network may be broken. Such an unfairness mitigated by deploying more gateways, since it allows closer gateways higher rates. However, multiple not solve problem efficiently due...

Screen-camera links for Visible Light Communication (VLC) are diverse, as the link quality varies according to many factors, such ambient light and camera's performance. This paper presents SoftLight, a channel coding approach that considers unique characteristics of VLC automatically adapts transmission data rate qualities various scenarios. SoftLight incorporates two new ideas: (1) an expanded color modulation interface provides soft hint about its confidence in each demodulated bit...

This paper presents DopEnc, an acoustic-based encounter profiling system on smartphones. DopEnc can automatically identify the persons that users interact with in context of encountering. performs two major steps: (1) Doppler to detect approach and stop front each other via effective trajectory, (2) voice confirm they are thereafter engaged interactive conversation. is further extended support parallel acoustic exploration many by incorporating a unique multiple access scheme within limited...

Training deep learning models on mobile devices recently becomes possible, because of increasing computation power hardware and the advantages enhancing user experiences. Most existing work machine at is focused inference models, but not training. The performance characterization training largely unexplored, although understanding critical for designing implementing devices. In this paper, we perform a variety experiments representative device (the NVIDIA TX2) to study models. We introduce...

We collaborate with environmental scientists to study the hydrodynamics and water quality in an urban district, where surface wind distribution is essential input but undergoes high spatial temporal variations due complex landform created by surrounding buildings. In this work, we optimal sensor placement scheme measure over a large reservoir limited number of sensors. Unlike existing solutions that assume Gaussian process target phenomena, measures which inherently exhibits strong...

This paper presents a distanceless networking approach for wireless sensor networks sparsely deployed in large areas. By leveraging rateless codes, we provide transmission to expand the communication range of motes and fully exploit network diversity. We address variety practical challenges accommodate coding on resource-constrained devise protocol efficiently coordinate link transmissions. propose new metric (expected time) routing selection further adapt transmissions low duty-cycled...

This paper aims to predict the apps a user will open on her mobile device next. Such an information is essential for many smartphone operations, e.g., app pre-loading and content pre-caching, save energy. However, it hard build explicit model that accurately depicts affecting factors their mechanism of time-varying usage behavior. presents deep reinforcement learning framework, named as DeepAPP, which learns model-free predictive neural network from historical data. Meanwhile, online...

Wireless rechargeable sensor networks (WRSNs), benefiting from recent breakthrough in wireless power transfer (WPT) technology, emerge as very promising for network lifetime extension. Traditional methods focus on scheduling algorithms and system optimization, the issue of charging security/threat is ignored, causing it vulnerable to attacks. In this paper, we develop a novel attack WRSN through Denial Charge (DoC) aiming at maximizing destructiveness. At first, form generalized on-demand...

Maximizing the lifetime of wireless sensor networks ( WSNs ) is an important and challenging research problem. Properly scheduling movements mobile sinks to balance energy consumption network one most effective approaches prolong networks. However, existing sink methods either require a great amount computational time or lack effectiveness in finding high-quality solutions. To address above issues, this paper proposes novel hyperheuristic framework, which can automatically construct...

Inputting a pattern or PIN code on the touch screen is popular method to prevent unauthorized access mobile devices. However, these sensitive tokens are highly susceptible being inferred by various types of side-channel attacks, which can compromise security private data stored in device. This paper presents second-factor authentication method, TouchPrint, relies user's hand posture shape traits (dependent individual different type and unique geometry biometrics) when user inputs pattern. It...

Summary Wireless sensor networks have been widely applied in industrial applications especially since the release of IEEE 802.15.4 standard. By participating an automobile project which based and actuator network is deployed to measure control vibrations automotive system, we need study many metrics (e.g., packet delivery rate, latency, energy consumption) under various sampling rates. In order provide detailed modeling hardware software as well behaviors on each node, conduct plenty...

We study the water quality in an urban district, where surface wind distribution is essential input but undergoes high spatial and temporal variations due to impact of surrounding buildings. In this work, we develop optimal sensor placement scheme measure over a large reservoir using limited number sensors. Unlike existing solutions that assume Gaussian process target phenomena, measures inherently exhibits strong non-Gaussian yearly distribution. By leveraging local monsoon characteristics...

We collaborate with environmental scientists to study the hydrodynamics and water quality in an urban district, where surface wind distribution is essential input but undergoes high spatial temporal variations due complex landform created by surrounding buildings. In this work, we optimal sensor placement scheme measure over a large reservoir limited number of sensors. Unlike existing solutions that assume Gaussian process target phenomena, measures which inherently exhibits strong...

This paper presents Pando, a completely contention-free data dissemination protocol for wireless sensor networks. Pando encodes by Fountain codes and disseminates the rateless stream of encoded packets along fast parallel pipelines built on constructive interference channel diversity. Since every packet contains innovative information to original object, avoids duplicate retransmissions fully exploits broadcast effect in dissemination. To transform into practical system, we devise several...

Both our experiments and previous studies show that LoRa links vary dynamically, which makes data transmission unreliable consumes much energy of sensor nodes by retransmissions. This paper presents, a Rateless-enabled link Adaptation system for networks. Rateless coding approaches the optimal rate continuously transmitting encoded with an initial rate. However, LoRa's modulation, Chirp Spread Spectrum (CSS), introduces unique challenges to rateless-enabled transmissions. With CSS, Spreading...

Energy consumption is one of the most important metrics in wireless sensor networks because limited power supply nodes. Many efforts have been taken to reduce energy hardware, software, communication protocols and applications. Simulation widely used evaluate performance these new designs. Thus, it necessary accurately model during simulation WSN. In this paper, an for WSN proposed. It has implemented IDEA1, a simulator developed by SystemC C++. enables estimation both hardware components...

This paper presents a distanceless networking approach for wireless sensor networks sparsely deployed in large areas. By leveraging rateless codes, we provide transmission to expand the communication range of motes and fully exploit network diversity. We address variety practical challenges accommodate coding on resource-constrained devise protocol efficiently coordinate link transmissions. propose new metric (expected time) routing selection further adapt transmissions low duty-cycled...

Many limitations (e.g. complexity, cost, scalability and capability) make the analytical methods physical testbeds improper to evaluate performances of wireless sensor networks (WSNs). Simulations can provide a good approximation at lower cost in less time. Hence, number simulation

Wireless Rechargeable Sensor Networks (WRSNs) with perpetual network lifetime have been used in many Internet of Things (IoT) applications, like smart city and precision agriculture. sensors together Unmanned Aerial Vehicles (UAVs) are collaboratively employed for fulfilling periodic coverage tasks. However, traditional solutions normally based on static deployment not suitable such requirements. In this paper, we propose a new concept problem named Period-Area Coverage (PAC) which requires...