Large language models are increasingly influencing human moral decisions, yet current approaches focus primarily on evaluating rather than actively steering their moral decisions. We formulate this as an out-of-distribution moral alignment problem, where LLM agents must learn to apply consistent moral reasoning frameworks to scenarios beyond their training distribution. We introduce Moral-Reason-QA, a novel dataset extending 680 human-annotated, high-ambiguity moral scenarios with framework-specific reasoning traces across utilitarian, deontological, and virtue ethics, enabling systematic evaluation of moral generalization in realistic decision contexts. Our learning approach employs Group Relative Policy Optimization with composite rewards that simultaneously optimize decision alignment and framework-specific reasoning processes to facilitate learning of the underlying moral frameworks. Experimental results demonstrate successful generalization to unseen moral scenarios, with softmax-normalized alignment scores improving by +0.757 for utilitarian and +0.450 for deontological frameworks when tested on out-of-distribution evaluation sets. The experiments also reveal training challenges and promising directions that inform future research. These findings establish that LLM agents can be systematically trained to internalize and apply specific moral frameworks to novel situations, providing a critical foundation for AI safety as language models become more integrated into human decision-making processes.

Precision agriculture demands continuous and accurate monitoring of soil moisture M and key macronutrients, including nitrogen N, phosphorus P, and potassium K, to optimize yields and conserve resources. Wireless soil sensing has been explored to measure these four components; however, current solutions require recalibration (i.e., re-train the data processing model) to handle variations in soil texture (characterized by aluminosilicates Al and organic carbon C, limiting their practicality. To address this, we introduce SoilX, a calibration-free soil sensing system that jointly measures six key components: {M, N, P, K, C, Al}. By explicitly modeling C and Al, SoilX eliminates texture- and carbon-dependent recalibration. SoilX incorporates Contrastive Cross-Component Learning (3CL), with two customized terms: the Orthogonality Regularizer and Separation Loss, to effectively disentangle cross-component interference. Additionally, we design a novel Tetrahedral Antenna Array with an antenna-switching mechanism, which can robustly measure soil dielectric permittivity independent of device placement. Extensive experiments demonstrate that SoilX reduces estimation errors by 23.8% to 31.5% over baselines and generalizes well to unseen fields.

Managing a vast number of virtual machines (VMs) efficiently is a critical challenge in modern large-scale data centers. The continuous creation and termination of VMs lead to resource fragmentation across physical machines (PMs), necessitating periodic VM rescheduling to optimize resource utilization. Despite its significance, VM rescheduling has received limited attention in the literature. A key challenge is that, unlike conventional combinatorial optimization problems, the efficiency of rescheduling algorithms is heavily impacted by inference time, as VM states evolve dynamically during execution. This scalability bottleneck hampers existing methods. To address this, we propose VMR$^{2}$L, a reinforcement learning framework tailored for VM rescheduling. VMR$^{2}$L integrates a two-stage decision-making process to accommodate complex operational constraints, a feature extraction mechanism that captures critical relational information for rescheduling, and a risk-aware evaluation strategy that enables users to balance execution speed and rescheduling accuracy. Extensive experiments using real-world data from a production-scale data center demonstrate that VMR$^{2}$L achieves near-optimal performance while reducing inference time to a matter of seconds. To facilitate reproducibility, we provide access to our implementation and datasets.

Personalized Federated Learning (PFL) aims to provide client-specific models that adapt to local data distributions while leveraging shared knowledge across clients. A common design in PFL is the head-representation architecture, which combines a shared global representation with a local head on each client. Although effective, deploying this architecture in real-world systems remains challenging due to the presence of stragglers and the high communication cost. To address these issues, we propose FedSTEP, a unified framework that integrates asynchronous training with dynamic communication sparsification. Specifically, it adaptively adjusts each client's local training duration and communication sparsity based on staleness, enabling more efficient coordination between local adaptation and global representation. This design mitigates the impact of stragglers and ensures robust performance in heterogeneous environments. We provide a theoretical analysis of the convergence behavior and communication efficiency of FedSTEP under standard assumptions. Extensive experiments on five public datasets demonstrate that FedSTEP consistently outperforms existing methods. It achieves up to 4.65% higher accuracy, a 3.68× speedup in training, and a 1.91× reduction in communication cost.

Modern industry-scale data centers need to manage a large number of virtual machines (VMs). Due to the continual creation and release of VMs, many small resource fragments are scattered across physical machines (PMs). To handle these fragments, data centers periodically reschedule some VMs to alternative PMs, a practice commonly referred to as VM rescheduling. Despite the increasing importance of VM rescheduling as data centers grow in size, the problem remains understudied. We first show that, unlike most combinatorial optimization tasks, the inference time of VM rescheduling algorithms significantly influences their performance, due to dynamic VM state changes during this period. This causes existing methods to scale poorly. Therefore, we develop a reinforcement learning system for VM rescheduling, VMR2L, which incorporates a set of customized techniques, such as a two-stage framework that accommodates diverse constraints and workload conditions, a feature extraction module that captures relational information specific to rescheduling, as well as a risk-seeking evaluation enabling users to optimize the trade-off between latency and accuracy. We conduct extensive experiments with data from an industry-scale data center. Our results show that VMR2L can achieve a performance comparable to the optimal solution but with a running time of seconds. Code12 and datasets3 are open-sourced.

Large pre-trained models have significantly advanced computer vision (CV) and natural language processing (NLP). However, their deployment is challenging in privacy-sensitive scenarios where data must remain decentralized. Federated Learning (FL) addresses this issue by enabling local model training without sharing raw data. Despite this advantage, integrating large models into FL introduces challenges such as training inefficiencies, label scarcity, and data heterogeneity. In this paper, we propose FedDiAL, a framework designed to effectively incorporate large pre-trained models into FL while addressing these challenges. At its core, FedDiAL, features the novel HDis-Net, which enhances the efficiency of large models in resource-constrained environments. We introduce a two-phase training strategy with probabilistic feature augmentation to improve feature discrimination. Additionally, we propose an adaptive pseudo-labeling method to generate high-confidence labels, mitigating label scarcity. To handle data heterogeneity, we develop a focused fine-tuning strategy that adapts HDis-Net to diverse client data distributions. Our theoretical analysis establishes the convergence of HDis-Net. Extensive experiments on four datasets, including Tiny ImageNet and AG News, demonstrate that FedDiAL outperforms state-of-the-art methods, achieving up to a 35.66% accuracy improvement in both CV and NLP tasks.

Integrating large pre-trained models into federated learning (FL) can significantly improve generalization and convergence efficiency. A widely adopted strategy freezes the pre-trained backbone and fine-tunes a lightweight task head, thereby reducing computational and communication costs. However, this partial fine-tuning paradigm introduces new security risks, making the system vulnerable to poisoned updates and backdoor attacks. To address these challenges, we propose FedRACE, a unified framework for robust FL with partially frozen models. FedRACE comprises two core components: HStat-Net, a hierarchical network that refines frozen features into compact, linearly separable representations; and DevGuard, a server-side mechanism that detects malicious clients by evaluating statistical deviance in class-level predictions modeling generalized linear models (GLMs). DevGuard further incorporates adaptive thresholding based on theoretical misclassification bounds and employs randomized majority voting to enhance detection reliability. We implement FEDRACE on the FedScale platform and evaluate it on CIFAR-100, Food-101, and Tiny ImageNet under diverse attack scenarios. FedRACE achieves a true positive rate of up to 99.3% with a false positive rate below 1.2%, while preserving model accuracy and improving generalization.

Synthesizing radio-frequency (RF) data given the transmitter and receiver positions, e.g., received signal strength indicator (RSSI), is critical for wireless networking and sensing applications, such as indoor localization. However, it remains challenging due to complex propagation interactions, including reflection, diffraction, and scattering. State-of-the-art neural radiance field (NeRF)-based methods achieve high-fidelity RF data synthesis but are limited by long training times and high inference latency. We introduce GSRF, a framework that extends 3D Gaussian Splatting (3DGS) from the optical domain to the RF domain, enabling efficient RF data synthesis. GSRF realizes this adaptation through three key innovations: First, it introduces complex-valued 3D Gaussians with a hybrid Fourier–Legendre basis to model directional and phase-dependent radiance. Second, it employs orthographic splatting for efficient ray–Gaussian intersection identification. Third, it incorporates a complex-valued ray tracing algorithm, executed on RF-customized CUDA kernels and grounded in wavefront propagation principles, to synthesize RF data in real time. Evaluated across various RF technologies, GSRF preserves high-fidelity RF data synthesis while achieving significant improvements in training efficiency, shorter training time, and reduced inference latency.

Soil composition sensing is essential for precision agriculture, sustainable land management, and optimizing crop yields. However, existing sensing systems face major limitations, including extensive calibration needs to account for soil variability, a narrow focus on measurements for specific properties, and sensitivity to the placement of the device. These challenges hinder practical deployment. This demo shows SoilX, a comprehensive wireless soil sensing system that quantifies all major soil components---including aluminosilicates, water, organic carbon, and micronutrients---using RF and VNIR sensing technologies. To enable the generalizability, SoilX employs contrastive pretraining to mitigate cross-component interference. Additionally, a tetrahedron-based antenna geometry ensures robustness to device placements. Extensive evaluations in both lab and field settings demonstrate that SoilX achieves state-of-the-art accuracy in soil composition analysis with low costs.

Effective communication and sensing in next-generation wireless technologies require resource-intensive site surveys for data collection. These surveys capture key RF characteristics at various positions, including the Received Signal Strength Indicator (RSSI) and spatial spectrum (RSSI measured from all directions around the receiver). An alternative approach is Radio-Frequency (RF) signal spatial propagation modeling, which predicts received signals based on transceiver positions. Existing Neural Radiance Field (NeRF)-based methods exhibit a fundamental trade-off between scalability and fidelity. To address this challenge, we explore leveraging 3D Gaussian Splatting, an advanced technique for real-time image synthesis of 3D scenes from arbitrary camera poses. This work develops RFSPM, an end-to-end 3D Gaussian distribution-based framework for scalable RF signal Spatial Propagation Modeling. We evaluate RFSPM in spatial spectrum synthesis, demonstrating its learning efficiency compared to NeRF-based methods.

Model-based reinforcement learning (MBRL) is widely studied for heating, ventilation, and air conditioning (HVAC) control in buildings. One of the critical challenges is the large amount of data required to effectively train neural networks for modeling building dynamics. This article presents CLUE, an MBRL system for HVAC control in buildings. CLUE optimizes HVAC operations by integrating a Gaussian process (GP) model to model building dynamics with uncertainty awareness. CLUE utilizes GP to predict state transitions as Gaussian distributions, effectively capturing prediction uncertainty and enhancing decision-making under sparse data conditions. Our approach employs a meta-kernel learning technique to efficiently set GP kernel hyperparameters using domain knowledge from diverse buildings. This drastically reduces the data requirements typically associated with GP models in HVAC applications. Additionally, CLUE incorporates these uncertainty estimates into a model predictive path integral (MPPI) algorithm, enabling the selection of safe, energy-efficient control actions. This uncertainty-aware control strategy evaluates and selects action trajectories based on their predicted impact on energy consumption and human comfort, optimizing operations even under uncertain conditions. Extensive simulations in a five-zone office building demonstrate that CLUE reduces the required training data from hundreds of days to just seven while maintaining robust control performance. It reduces comfort violations by an average of 12.07% compared to existing MBRL methods, without compromising on energy efficiency. Our code and dataset are available athttps://github.com/ryeii/CLUE.

The application of reinforcement learning in controlling Heating, Ventilation, and Air Conditioning (HVAC) systems has been extensively researched. Existing studies primarily focus on Model-Free Reinforcement Learning (MFRL), which involves trial-and-error interactions with real buildings to train the agent. However, MFRL encounters a significant challenge: it requires a large amount of training data to achieve satisfactory performance. While simulation models have been used to generate training data and expedite the training process, they necessitate high-fidelity building models that are difficult to calibrate. As a result, Model-Based Reinforcement Learning (MBRL) has been employed for HVAC control. Although MBRL demonstrates remarkable sample efficiency, it often falls short in terms of asymptotic control performance, particularly in achieving substantial energy savings while ensuring occupants’ thermal comfort. In this study, we conduct experiments to analyze the limitations of current MBRL-based HVAC control methods, focusing on model uncertainty and controller effectiveness. Leveraging the insights gained from these experiments, we develop MB2C, an innovative MBRL-based HVAC control system that combines high control performance with exceptional sample efficiency. MB2C learns the dynamics of the building by employing an ensemble of environment-conditioned neural networks and utilizes a novel control method called Model Predictive Path Integral (MPPI) for HVAC control. MPPI generates candidate action sequences using an importance sampling weighted algorithm, which is well-suited for multi-zone buildings with high state and action dimensions. We evaluate MB2C using EnergyPlus simulations in a five-zone office building, and the results demonstrate that MB2C achieves 8.23% higher energy savings compared to the state-of-the-art MBRL solution while maintaining comparable thermal comfort. Moreover, MB2C significantly reduces the required training data set by an order of magnitude ($10.52\times $) while delivering performance on par with MFRL approaches. Note to Practitioners—Our research addresses a critical challenge in HVAC control, offering an innovative solution to enhance the data efficiency of HVAC systems while optimizing energy usage. Traditional approaches, such as Model-Free Reinforcement Learning, often require a large volume of real-world data. Our primary focus is improving the effectiveness of HVAC control, a vital aspect of building management that directly affects energy consumption and occupant well-being. We introduce MB2C, a Model-Based Reinforcement Learning system designed to significantly improve energy savings while maintaining thermal comfort. MB2C achieves remarkable results, offering exceptional sample efficiency and substantially reducing the required training data. Our research leverages an ensemble of environment-conditioned neural networks and employs Model Predictive Path Integral in HVAC control. While MB2C presents notable benefits, it also has limitations. Further research and development are required to optimize its performance across different building environments and specific use cases. Future directions should focus on addressing the safety challenges associated with real-world deployment. Beyond HVAC control, the principles and methods explored in this research have potential applications in various automation domains, such as robotics, industrial automation, and manufacturing processes.

Precise robot localization at the tree level is essential for smart agriculture applications such as precision disease management and targeted nutrient distribution. Existing methods fail to achieve the required accuracy. We propose OrchLoc, a fingerprinting-based localization solution that achieves treelevel precision using a single Long Range (LoRa) gateway. Our approach utilizes channel state information (CSI) across eight channels as a localization fingerprint. To minimize labor-intensive site surveys for fingerprint database construction and maintenance, we develop a CSI generative model (CGM) that learns the relationship between CSI vectors and their corresponding locations. The CGM is fine-tuned using CSI data from static agricultural LoRa sensor nodes, enabling continuous fingerprint database updates. Extensive experiments in two orchards demonstrate that OrchLoc effectively achieves accurate tree-level localization with minimal overhead, improving robot navigation

LoRa networks have been deployed in many orchards for environmental monitoring and crop management. An accurate propagation model is essential for efficiently deploying a LoRa network in orchards, e.g., determining gateway coverage and sensor placement. Although some propagation models have been studied for LoRa networks, they are not suitable for orchard environments, because they do not consider the shadowing effect on wireless propagation caused by the ground and tree canopies. This article presents FLog , a propagation model for LoRa signals in orchard environments. FLog leverages a unique feature of orchards, i.e., all trees have similar shapes and are planted regularly in space. We develop a three-dimensional model of orchards. Once we have the location of a sensor and a gateway, we know the media that the wireless signal traverses. Based on this knowledge, we generate the First Fresnel Zone (FFZ) between the sender and the receiver. The intrinsic path loss exponents of all media can be combined into a classic Log-Normal Shadowing model in the FFZ. Extensive experiments in almond orchards show that FLog reduces the link quality estimation error by 42.7% and improves gateway coverage estimation accuracy by 70.3%, compared with a widely used propagation model. The source codes and dataset are released at https://github.com/ycucm/Flog .

Recent research has shown the potential of Model-based Reinforcement Learning (MBRL) to enhance energy efficiency of Heating, Ventilation, and Air Conditioning (HVAC) systems. However, existing methods rely on black-box thermal dynamics models and stochastic optimizers, lacking reliability guarantees and posing risks to occupant health. In this work, we overcome the reliability bottleneck by redesigning HVAC controllers using decision trees extracted from existing thermal dynamics models and historical data. Our decision tree-based policies are deterministic, verifiable, interpretable, and more energy-efficient than current MBRL methods. First, we introduce a novel verification criterion for RL agents in HVAC control based on domain knowledge. Second, we develop a policy extraction procedure that produces a verifiable decision tree policy. We found that the high dimensionality of the thermal dynamics model input hinders the efficiency of policy extraction. To tackle the dimensionality challenge, we leverage importance sampling conditioned on historical data distributions, significantly improving policy extraction efficiency. Lastly, we present an offline verification algorithm that guarantees the reliability of a control policy. Extensive experiments show that our method saves 68.4% more energy and increases human comfort gain by 14.8% compared to the state-of-the-art method, in addition to an 1127× reduction in computation overhead. Our code and data are available at https://github.com/ryeii/Veri_HVAC.

The rapid decline in groundwater around the world poses a significant challenge to sustainable agriculture. To address this issue, agricultural managed aquifer recharge (Ag-MAR) is proposed to recharge the aquifer by artificially flooding agricultural lands using surface water. Ag-MAR requires a carefully selected flooding schedule to avoid affecting the oxygen absorption of crop roots. However, current Ag-MAR scheduling does not take into account complex environmental factors such as weather and soil oxygen, resulting in crop damage and insufficient recharging amounts. This paper proposes MARLP, the first end-to-end data-driven control system for Ag-MAR. We first formulate Ag-MAR as an optimization problem. To that end, we analyze four-year in-field datasets, which reveal the multi-periodicity feature of the soil oxygen level trends and the opportunity to use external weather forecasts and flooding proposals as exogenous clues for soil oxygen prediction. Then, we design a two-stage forecasting framework. In the first stage, it extracts both the cross-variate dependency and the periodic patterns from historical data to conduct preliminary forecasting. In the second stage, it uses weather-soil and flooding-soil causality to facilitate an accurate prediction of soil oxygen levels. Finally, we conduct model predictive control (MPC) for Ag-MAR flooding. To address the challenge of large action spaces, we devise a heuristic planning module to reduce the number of flooding proposals to enable the search for optimal solutions. Real-world experiments show that MARLP reduces the oxygen deficit ratio by 86.8% while improving the recharging amount in unit time by 35.8%, compared with the previous four years.

In orchards, tree-level localization of robots is critical for smart agriculture applications like precision disease management and targeted nutrient dispensing. However, prior solutions cannot provide adequate accuracy. We develop our system, a fingerprinting-based localization system that can provide tree-level accuracy with only one LoRa gateway. We extract channel state information (CSI) measured over eight channels as the fingerprint. To avoid labor-intensive site surveys for building and updating the fingerprint database, we design a CSI Generative Model (CGM) that learns the relationship between CSIs and their corresponding locations. The CGM is fine-tuned using CSIs from static LoRa sensor nodes to build and update the fingerprint database. Extensive experiments in two orchards validate our system's effectiveness in achieving tree-level localization with minimal overhead and enhancing robot navigation accuracy.

Soil moisture level sensing is essential for enabling smart irrigation, which is crucial for our food security and sustainable agriculture. Existing soil moisture sensing systems face limitations such as single-layer sensing, limited depth, power supply reliance, and complex calibration. In addition, costly and cumbersome sensor unit design hinders mass and dense deployment of passive intelligence. This paper introduces MetaSoil, a soil moisture sensing system that is calibration-free, continuous, and multi-layered, leveraging a passive 3D printable mmWave metamaterial. When soil moisture level changes, our hydrogel patched polylactic acid (PLA) metamaterial alters resonant frequency in the impinging mmWave signals due to impedance match offset. Our system eliminates in-soil power supply dependencies by utilizing the RF resonance of 3D-printed metamaterial, allowing for deeper placement, and simultaneous multi-layer sensing. We then integrate a commercial-off-the-shelf (COTS) mmWave radar to query the metamaterial sensor. With MetaSoil's fully passive metamaterial pole, RF signal from far is redirected towards the sensor unit, bypassing soil's heavy attenuation effect. Through our extensive evaluation, MetaSoil achieves 98.9 % accuracy with ±10% moisture level precision in single-layered sensing, at depth of 1m meter. It achieves 98.8 % accuracy with ±10% in double layered sensing at same depth with 10cm sensor spacing. We further examine the robustness of our system with real-world requirements. Overall, MetaSoil represents a low-cost, durable, and easily deployable solution that supports remote and continuous soil moisture monitoring, advancing the scalability and effectiveness of smart agricultural practices.

This paper presents a novel map matching framework that adopts deep learning techniques to map a sequence of cell tower locations to a trajectory on a road network. Map matching is an essential pre-processing step for many applications, such as traffic optimization and human mobility analysis. However, most recent approaches are based on hidden Markov models (HMMs) or neural networks that are hard to consider high-order location information or heuristics observed from real driving scenarios. In this paper, we develop a deep reinforcement learning based map matching framework for cellular data, named as DMM, which adopts a recurrent neural network (RNN) coupled with a reinforcement learning scheme to identify the most-likely trajectory of roads given a sequence of cell towers. To transform DMM into a practical system, several challenges are addressed by developing a set of techniques, including spatial-aware representation of input cell tower sequences, an encoder-decoder based RNN network for map matching model with variable-length input and output, and a global heuristics-driven reinforcement learning based scheme for optimizing the parameters of the encoder-decoder map matching model. Extensive experiments on a large-scale anonymized cellular dataset reveal that DMM provides high map matching accuracy and fast inference time.

Both our experiments and previous studies show that LoRa links vary dynamically, which makes data transmission unreliable and consumes much energy of sensor nodes by retransmissions. This paper presents, a Rateless-enabled link Adaptation system for LoRa networks. Rateless coding approaches the optimal data rate of a link by continuously transmitting encoded data with an initial data rate. However, LoRa’s modulation, Chirp Spread Spectrum (CSS), introduces unique challenges to rateless-enabled transmissions. With CSS, Spreading Factor (SF) simultaneously determines the initial data rate and the concurrent transmissions of multiple links. This dual role of SF requires the co-design of coding and networking. We thus formulate an optimization problem for allocating network resources (SF, frequency channels, and transmission power) and coding parameters (block size and packet size) to all sensor nodes. A key component of this formulation is a rateless-aware network model that estimates the data transmission results of sensor nodes based on their link quality and transmission setting. Given that the optimization problem for obtaining the best transmission setting of all sensor nodes is NP-complete, a two-stage heuristic algorithm is designed. A Kalman filter-based link quality predictor is developed to capture the link quality variation. We implement on commodity LoRa hardware. Extensive experiments on a real testbed show that extends the lifetime of LoRaWAN by 66.1 %.

In recent years, the focus has been on enhancing user comfort in commercial buildings while cutting energy costs. Efforts have mainly centered on improving HVAC systems, the central control system. However, it’s evident that HVAC alone can’t ensure occupant comfort. Lighting, blinds, and windows, often overlooked, also impact energy use and comfort. This paper introduces a holistic approach to managing the delicate balance between energy efficiency and occupant comfort in commercial buildings. We present OCTOPUS , a system employing a deep reinforcement learning (DRL) framework using data-driven techniques to optimize control sequences for all building subsystems, including HVAC, lighting, blinds, and windows. OCTOPUS ’s DRL architecture features a unique reward function facilitating the exploration of tradeoffs between energy usage and user comfort, effectively addressing the high-dimensional control problem resulting from interactions among these four building subsystems. To meet data training requirements, we emphasize the importance of calibrated simulations that closely replicate target-building operational conditions. We train OCTOPUS using 10-year weather data and a calibrated building model in the EnergyPlus simulator. Extensive simulations demonstrate that OCTOPUS achieves substantial energy savings, outperforming state-of-the-art rule-based and DRL-based methods by 14.26% and 8.1%, respectively, in a LEED Gold Certified building while maintaining desired human comfort levels.

Agricultural irrigation is a significant contributor to freshwater consumption. However, the current irrigation systems used in the field are not efficient. They rely mainly on soil moisture sensors and the experience of growers but do not account for future soil moisture loss. Predicting soil moisture loss is challenging because it is influenced by numerous factors, including soil texture, weather conditions, and plant characteristics. This article proposes a solution to improve irrigation efficiency, which is called DRLIC (deep reinforcement learning for irrigation control). DRLIC is a sophisticated irrigation system that uses deep reinforcement learning (DRL) to optimize its performance. The system employs a neural network, known as the DRL control agent, which learns an optimal control policy that considers both the current soil moisture measurement and the future soil moisture loss. We introduce an irrigation reward function that enables our control agent to learn from previous experiences. However, there may be instances in which the output of our DRL control agent is unsafe, such as irrigating too much or too little. To avoid damaging the health of the plants, we implement a safety mechanism that employs a soil moisture predictor to estimate the performance of each action. If the predicted outcome is deemed unsafe, we perform a relatively conservative action instead. To demonstrate the real-world application of our approach, we develop an irrigation system that comprises sprinklers, sensing and control nodes, and a wireless network. We evaluate the performance of DRLIC by deploying it in a testbed consisting of six almond trees. During a 15-day in-field experiment, we compare the water consumption of DRLIC with a widely used irrigation scheme. Our results indicate that DRLIC outperforms the traditional irrigation method by achieving water savings of up to 9.52%.

Retrieving similar trajectories aims to search for the trajectories that are close to a query trajectory in spatio-temporal domain from a large trajectory dataset. This is critical for a variety of applications, like transportation planning and mobility analysis. Unlike previous studies that perform similar trajectory retrieval on fine-grained GPS data or single cellular carrier, we investigate the feasibility of finding similar trajectories from cellular data of multiple carriers, which provide more comprehensive coverage of population and space. To handle the issues of spatial bias of cellular data from multiple carriers, coarse spatial granularity, and irregular sparse temporal sampling, we develop a holistic system cellSim . Specifically, to avoid the issue of spatial bias, we first propose a novel map matching approach, which transforms the cell tower sequences from multiple carriers to routes on a unified road map. Then, to address the issue of temporal sparse sampling, we generate multiple routes with different confidences to increase the probability of finding truly similar trajectories. Finally, a new trajectory similarity measure is developed for similar trajectory search by calculating the similarities between the irregularly-sampled trajectories. Extensive experiments on a large-scale cellular dataset from two carriers and real-world 1,701 km query trajectories reveal that cellSim provides state-of-the-art performance for similar trajectory retrieval.

This article presents a novel system, LLDPC , 1 which brings Low-Density Parity-Check (LDPC) codes into Long Range (LoRa) networks to improve Forward Error Correction, a task currently managed by less efficient Hamming codes. Three challenges in achieving this are addressed: First, Chirp Spread Spectrum (CSS) modulation used by LoRa produces only hard demodulation outcomes, whereas LDPC decoding requires Log-Likelihood Ratios (LLR) for each bit. We solve this by developing a CSS-specific LLR extractor. Second, we improve LDPC decoding efficiency by using symbol-level information to fine-tune LLRs of error-prone bits. Finally, to minimize the decoding latency caused by the computationally heavy Soft Belief Propagation (SBP) algorithm typically used in LDPC decoding, we apply graph neural networks to accelerate the process. Our results show that LLDPC extends default LoRa’s lifetime by 86.7% and reduces SBP algorithm decoding latency by 58.09×.

LoRa networks have been deployed in many orchards for environmental monitoring and crop management. An accurate propagation model is essential for efficiently deploying a LoRa network in orchards, e.g., determining gateway coverage and sensor placement. Although some propagation models have been studied for LoRa networks, they are not suitable for orchard environments, because they do not consider the shadowing effect on wireless propagation caused by the ground and tree canopies. This paper presents FLog, a propagation model for LoRa signals in orchard environments. FLog leverages a unique feature of orchards, i.e., all trees have similar shapes and are planted regularly in space. We develop a 3D model of the orchards. Once we have the location of a sensor and a gateway, we know the mediums that the wireless signal traverse. Based on this knowledge, we generate the First Fresnel Zone (FFZ) between the sender and the receiver. The intrinsic path loss exponents (PLE) of all mediums can be combined into a classic Log-Normal Shadowing model in the FFZ. Extensive experiments in almond orchards show that FLog reduces the link quality estimation error by 42.7% and improves gateway coverage estimation accuracy by 70.3%, compared with a widely-used propagation model.

Model-based Reinforcement Learning (MBRL) has been widely studied for energy-efficient control of the Heating, Ventilation, and Air Conditioning (HVAC) systems. One of the fundamental issues of the current approaches is the large amount of data required to train an accurate building system dynamics model. In this work, we developed a data-efficient system capable of excellent HVAC control performance with only days of training data. We use a Gaussian Process (GP) as the dynamics model which provides uncertainty for each prediction. To improve the data efficiency, we designed a meta kernel learning technique for GP kernel selection. To incorporate uncertainty in the control decisions, we designed a model predictive control method that considers the uncertainty of every prediction. Simulation experiments show that our method achieves excellent data efficiency, yielding similar energy savings and 12.07% less human comfort violation compared with the state-of-the-art MBRL method, while only trained on a seven-day training dataset.

This paper examines fault resilience among citizen-science air quality monitoring networks in California's economically challenged San Joaquin Valley (SJV). We examine disparities in monitoring capabilities and data equity between the SJV and the San Francisco Bay Area. We found significant inequities through experimental analysis simulating sensor failures. Our results emphasize the need for reliable monitoring systems and advanced modeling algorithms in resource-limited areas.

This paper aims to predict a set of apps a user will open on her mobile device in the next time slot. Such an information is essential for many smartphone operations, e.g., app pre-loading and content pre-caching, to improve user experience. However, it is hard to build an explicit model that accurately captures the complex environment context and predicts a set of apps at one time. This paper presents a deep reinforcement learning framework, named as DeepAPP, which learns a model-free predictive neural network from historical app usage data. Meanwhile, an online updating strategy is designed to adapt the predictive network to the time-varying app usage behavior. To transform DeepAPP into a practical deep reinforcement learning system, several challenges are addressed by developing a context representation method for complex contextual environment, a general agent for overcoming data sparsity and a lightweight personalized agent for minimizing the prediction time. Extensive experiments on a large-scale anonymized app usage dataset reveal that DeepAPP provides high accuracy (precision 70.6 percent and recall of 62.4 percent) and reduces the prediction time of the state-of-the-art by 6.58×. A field experiment of 29 participants demonstrates DeepAPP can effectively reduce launch time of apps.

LoRa has become one of the most promising networking technologies for Internet-of-Things applications. Distant end devices have to use a low data rate to reach a LoRa gateway, causing long in-the-air transmission time and high energy consumption. Compared with the end devices using high data rates, they will drain the batteries much earlier and the network may be broken early. Such an energy unfairness can be mitigated by deploying more gateways. However, with more gateways, more end devices may choose small spreading factors to reach closer gateways, increasing the collision probability. In this paper, we propose a networking solution for LoRa networks, EF-LoRa, that can achieve energy fairness among end devices by carefully allocating network resources, including frequency channels, spreading factors and transmission power. We develop a LoRa network model to study the energy consumption of the end devices, considering the unique features of LoRa networks such as LoRaWAN MAC protocol and the capacity limitation of a gateway. We formulate the energy fairness allocation as an optimization problem, and propose a greedy allocation algorithm to achieve max-min fairness of energy efficiency. Simulation results show that EF-LoRa can improve the energy fairness of the state-of-the-art works by 177.8%.

This paper presents GeoDMA , which processes the GPS data from multiple vehicles to detect anomalous driving maneuvers, such as rapid acceleration, sudden braking, and rapid swerving. First, an unsupervised deep auto-encoder is designed to learn a set of unique features from the normal historical GPS data of all drivers. We consider the temporal dependency of the driving data for individual drivers and the spatial correlation among different drivers. Second, to incorporate the peer dependency of drivers in local regions, we develop a geographical partitioning algorithm to partition a city into several sub-regions to do the driving anomaly detection. Specifically, we extend the vehicle-vehicle dependency to road-road dependency and formulate the geographical partitioning problem into an optimization problem. The objective of the optimization problem is to maximize the dependency of roads within each sub-region and minimize the dependency of roads between any two different sub-regions. Finally, we train a specific driving anomaly detection model for each sub-region and perform in-situ updating of these models by incremental training. We implement GeoDMA in Pytorch and evaluate its performance using a large real-world GPS trajectories. The experiment results demonstrate that GeoDMA achieves up to 8.5% higher detection accuracy than the baseline methods.

Predicting the next application (app) a user will open is essential for improving the user experience, e.g., app pre-loading and app recommendation. Unlike previous solutions that only predict which app the user will open, this article predicts both the next app and the time to open it. Time prediction is essential to avoid loading the next app too early and consuming unnecessary resources on smartphones. To predict the next app and open time jointly, we model the app usage sequence as a marked temporal point process (MTPP), whose conditional intensity function can capture the probability of a new app usage event. We develop a novel data-driven MTPP-based app prediction system, named ATPP (App Temporal Point Process), which adopts a recurrent neural network architecture to learn the MTPP conditional intensity function for app prediction. ATPP adopts a set of techniques to incorporate the unique features of app prediction in our RNN architecture, including learning the correlated usage behavior of different apps by representation learning, the temporal dependency of app usage by an attention mechanism, and the location-related app usage behavior by feature extraction and fusion layer. We conduct extensive experiments on a large-scale anonymized app usage dataset to verify ATPP’s effectiveness.

Agricultural irrigation is a major consumer of freshwater. Current irrigation systems used in the field are not efficient, since they are mainly based on soil moisture sensors' measurement and growers' experience, but not future soil moisture loss. It is hard to predict soil moisture loss, as it depends on a variety of factors, such as soil texture, weather and plants' characteristics. To improve irrigation efficiency, this paper presents DRLIC, a deep reinforcement learning (DRL)-based irrigation system. DRLIC uses a neural network (DRL control agent) to learn an optimal control policy that takes both current soil moisture measurement and future soil moisture loss into account. We define an irrigation reward function that facilitates the control agent to learn from past experience. Sometimes, our DRL control agent may output an unsafe action (e.g., irrigating too much water or too little). To prevent any possible damage to plants' health, we adopt a safe mechanism that leverages a soil moisture predictor to estimate each action's performance. If it is unsafe, we will perform a relatively-conservative action instead. Finally, we develop a real-world irrigation system that is composed of sprinklers, sensing and control nodes, and a wireless network. We deploy DRLIC in our testbed composed of six almond trees. Through a IS-day in-field experiment, we find that DRLIC can save up to 9.52% of water over a widely-used irrigation scheme.

Agriculture is a major user of ground and surface water in the United States. Improving the efficiency of agricultural irrigation systems is critical for sustainable agriculture. We propose an IoT-based irrigation system, which includes two major components, i.e., an IoT wireless network of sensing and actuation nodes, and a DRL-based control algorithm. Given the collected soil moisture data and weather data, the DRL-based algorithm finds an optimal irrigation schedule, which uses the minimum amount of water to guarantee the soil-water content above the required level before the next irrigation cycle. We deploy the system in our testbed composed of six almond trees. Through a 12-day in-field experiment, we find that our proposed system can save up to 7.8% of water over a widely-used irrigation scheme.

Arm posture tracking is essential for many applications, such as gesture recognition, fitness training, and motion-based controls. Smartwatches with Inertial Measurement Unit (IMU) sensors (i.e., accelerometer, gyroscope, and magnetometer) provide a convenient way to track the orientation and location of the wrist. Existing orientation estimations are based on predefined data fusion methods that do not consider the variations in the data quality of different IMU sensors. Existing location estimations rely on the estimated orientation results. A small orientation estimation error may cause high inaccuracy in location estimation. Moreover, these location estimation algorithms, e.g., Hidden Markov Model and Particle Filters, cannot provide real-time tracking on commercial mobile devices due to high computation overhead. This paper presents RTAT, a Real-Time Arm Tracking system that tackles the above limitations in a data-driven way. RTAT estimates both orientation and location simultaneously using a multitask learning neural network. It also incorporates a unique attention layer and a dedicated loss function to learn the dynamic relationship among IMU sensors. RTAT supports real-time tracking by performing model inference on smartphones. Finally, to train RTAT's neural network, we develop an easy-to-use labeled data collection system that uses a low-cost virtual reality system to provide orientation and location labels for the smartwatch. Extensive experiments show RTAT significantly outperforms existing state-of-the-art solutions in both accuracy and latency.

In this demo, we present RTAT, a real-time arm tracking system that tracks both orientation and location of a smartwatch simultaneously by a multitask learning neural network. We incorporate an attention layer and design a dedicated loss for the multitask neural network to learn the dynamic relationships among Inertial Measurement Unit (IMU) sensors. RTAT supports real-time tracking by performing deep learning inference on a smartphone. Finally, to train RTAT, we develop an easy-to-use labeled data collection system that uses a low-cost virtual reality system to measure the ground truth orientation and location of the smartwatch. Extensive experiments show RTAT outperforms significantly the state-of-the-art solutions in inference accuracy and latency.

Low-density parity-check (LDPC) codes have been widely used for Forward Error Correction (FEC) in wireless networks because they can approach the capacity of wireless links with lightweight encoding complexity. Although LoRa networks have been developed for many applications, they still adopt simple FEC codes, i.e., Hamming codes, which provide limited FEC capacity, causing unreliable data transmissions and high energy consumption of LoRa nodes. To close this gap, this paper develops LLDPC, which realizes LDPC coding in LoRa networks. Three challenges are addressed. 1) LoRa employs Chirp Spread Spectrum (CSS) modulation, which only provides hard demodulation results without soft information. However, LDPC requires the Log-Likelihood Ratio (LLR) of each received bit for decoding. We develop an LLR extractor for LoRa CSS. 2) Some erroneous bits may have high LLRs (i.e., wrongly confident in their correctness), significantly affecting the LDPC decoding efficiency. We use symbol-level information to fine-tune the LLRs of some bits to improve the LDPC decoding efficiency. 3) Soft Belief Propagation (SBP) is typically used as the LDPC decoding algorithm. It involves heavy iterative computation, resulting in a long decoding latency, which prevents the gateway from sending timely an acknowledgment. We take advantage of recent advances in graph neural networks for fast belief propagation in LDPC decoding. Extensive simulations on a large-scale synthetic dataset and in-filed experiments reveal that LLDPC can extend the lifetime of the default LoRa by 86.7% and reduce the decoding latency of the SBP algorithm by 58.09×.

Erasure coding is widely used in distributed storage systems (DSSs) to efficiently achieve fault tolerance. However, when the original data need to be updated, erasure coding must update every encoded block, resulting in long update time and high bandwidth consumption. Exiting solutions are mainly focused on coding schemes to minimize the size of transmitted update information, while ignoring more efficient utilization of bandwidth among update racks. In this article, we propose a parallel Cross-rack Pipelining Update scheme (CPU), which divides the update information into small-size units and transmits these units in parallel along with an update pipeline path among multiple racks. The performance ofCPUis mainly determined by slice size and update path. More slices bring finer-grained parallel transmissions over cross-rack links, but also introduces more overheads. An update path that traverses all racks with large-bandwidth links provide short update time. We formulate the proposed pipelining update scheme as an optimization problem, based on a new theoretical pipelining update model. We prove the optimization problem is NP-hard and develop a heuristic algorithm to solve it based on the features of practical DSSs and our implementations, includingBig chunkandSmall overhead. Specifically, we determine the best update path first by solving a max-min problem and then decide the slice size. We further simplify the slice size selection by offline learning a range of interesting (RoI), in which all slice sizes provide similar performance. We implementCPUand conduct experiments on Amazon EC2 under a variety of scenarios. The results show thatCPUcan reduce the average update time by 48.2 percent, compared with the state-of-the-art update schemes.

Predicting the app that a user will open next is essential for improving user experience, e.g., app pre-loading. Unlike previous solutions that only predict next app’s ID, this work also predicts the time to open next app. Time prediction is important to avoid loading the next app too early, consuming too much memory and energy on smartphones. To predict next app’s ID and open time jointly, we model app usage as a marked temporal point process (MTPP), whose conditional intensity function can capture the probability of a new app usage event. We develop a novel data-driven MTPP-based app prediction system, named as ATPP (App Temporal Point Process), which adopts a recurrent neural network architecture to learn the MTPP conditional intensity function for app prediction. ATPP adopts a set of techniques to incorporate the unique features of app prediction in our RNN architecture, including learning the correlated usage behavior of different apps by representation learning, the temporal dependency of app usage events by an attention mechanism, and the location-related app usage behavior by a feature extraction and fusion layer. We conduct extensive experiments on a large-scale anonymized app usage dataset from 443 users over 21 days. The experiment results demonstrate that ATPP outperforms the state-of-the-art app prediction method by 6.0% in the prediction accuracy of next app ID and 2.09× reduction in the prediction error of next app open time. A field experiment of 22 users reveals that ATPP can reduce the app loading time by 78%.

In this paper, we propose a single-agent Monte Carlo based reinforced feature selection (MCRFS) method, as well as two efficiency improvement strategies, i.e., early stopping (ES) strategy and reward-level interactive (RI) strategy. Feature selection is one of the most important technologies in data prepossessing, aiming to find the optimal feature subset for a given downstream machine learning task. Enormous research has been done to improve its effectiveness and efficiency. Recently, the multi-agent reinforced feature selection (MARFS) has achieved great success in improving the performance of feature selection. However, MARFS suffers from the heavy burden of computational cost, which greatly limits its application in real-world scenarios. In this paper, we propose an efficient reinforcement feature selection method, which uses one agent to traverse the whole feature set, and decides to select or not select each feature one by one. Specifically, we first develop one behavior policy and use it to traverse the feature set and generate training data. And then, we evaluate the target policy based on the training data and improve the target policy by Bellman equation. Besides, we conduct the importance sampling in an incremental way, and propose an early stopping strategy to improve the training efficiency by the removal of skew data. In the early stopping strategy, the behavior policy stops traversing with a probability inversely proportional to the importance sampling weight. In addition, we propose a reward-level interactive strategy to improve the training efficiency via reward-level external advice. Finally, we design extensive experiments on real-world data to demonstrate the superiority of the proposed method.

By processing a large dataset composed of daily trajectories of thousands of students in Singapore, we find that, instead of simply picking up students from their homes, an optimal school shuttle planning system needs to learn the real transportation usage and plan across all potential pickup locations for every student to generate need-satisfying routes. It is challenging, however, to perform route planning over a large number of students each having multiple potential pickup locations. We develop a graph-based data structure that embeds potential pickup locations of all students with the awareness of real-world constraints and existing public transits. Based on the graph structure, we prove that the optimal last-mile school shuttle planning problem is NP-hard and thereafter design a Tabu-based expansion algorithm to solve the problem, which strikes at a proper balance between the savings of students' commute time and the total cost of operating the shuttle buses. Extensive experiments with large-scale real-world crowdsensed trajectory data demonstrate that our last-mile school shuttles can save the traveling time for most students by over 20% and the savings can be up to 65% for 10% of the students.

Current localization schemes on mobile devices are experiencing great diversity that is mainly shown in two aspects: the large number of available localization schemes and their diverse performance. This paper presents UniLoc, a unified framework that gains improved performance from multiple localization schemes by exploiting their diversity. UniLoc predicts the localization error of each scheme online based on an error model and real-time context. It further combines the results of all available schemes based on the error prediction results and an ensemble learning algorithm. The combined result is more accurate than any individual schemes. With the flexible design of error modeling and ensemble learning, UniLoc can easily integrate a new localization scheme. The energy consumption of UniLoc is low, since its computation, including both error prediction and ensemble learning, only involves simple linear calculation. Our experience with extensive experiments tells that such easy aggregation incurs little overhead in integrating and training a localization scheme, but gains substantially from the scheme diversity. UniLoc outperforms individual localization schemes by 1.6× in a variety of environments, including > 89% new places where we did not train the error models.

This paper presents AdaVP, a continuous and real-time video processing system for mobile devices without offloading. AdaVP uses Deep Neural Network (DNN) based tools like YOLOv3 for object detection. Since DNN computation is time-consuming, multiple frames may be captured by the camera during the processing of one frame. To support real-time video processing, we develop a mobile parallel detection and tracking (MPDT) pipeline that executes object detection and tracking in parallel. When the object detector is processing a new frame, a light-weight object tracker is used to track the objects in the accumulated frames. As the tracking accuracy decreases gradually, due to the accumulation of tracking error and the appearance of new objects, new object detection results are used to calibrate the tracking accuracy periodically. In addition, a large DNN model produces high accuracy, but requires long processing latency, resulting in a great degradation for tracking accuracy. Based on our experiments, we find that the tracking accuracy degradation is also related to the variation of video content, e.g., for a dynamically changing video, the tracking accuracy degrades fast. A model adaptation algorithm is thus developed to adapt the DNN models according to the change rate of video content. We implement AdaVP on Jetson TX2 and conduct a variety of experiments on a large video dataset. The experiment results reveal that AdaVP improves the accuracy of the state-of-the-art solution by up to 43.9%.

Map matching for cellular data is to transform a sequence of cell tower locations to a trajectory on a road map. It is an essential processing step for many applications, such as traffic optimization and human mobility analysis. However, most current map matching approaches are based on Hidden Markov Models (HMMs) that have heavy computation overhead to consider high-order cell tower information. This paper presents a fast map matching framework for cellular data, named as DMM, which adopts a recurrent neural network (RNN) to identify the most-likely trajectory of roads given a sequence of cell towers. Once the RNN model is trained, it can process cell tower sequences as making RNN inference, resulting in fast map matching speed. To transform DMM into a practical system, several challenges are addressed by developing a set of techniques, including spatial-aware representation of input cell tower sequences, an encoder-decoder framework for map matching model with variable-length input and output, and a reinforcement learning based model for optimizing the matched outputs. Extensive experiments on a large-scale anonymized cellular dataset reveal that DMM provides high map matching accuracy (precision 80.43% and recall 85.42%) and reduces the average inference time of HMM-based approaches by 46.58×.

Real-time detection of inshore ships plays an essential role in the efficient monitoring and management of maritime traffic and transportation for port management. Current ship detection methods which are mainly based on remote sensing images or radar images hardly meet real-time requirement due to the timeliness of image acquisition. In this paper, we propose to use visual images captured by an on-land surveillance camera network to achieve real-time detection. However, due to the complex background of visual images and the diversity of ship categories, the existing convolution neural network (CNN) based methods are either inaccurate or slow. To achieve high detection accuracy and real-time performance simultaneously, we propose a saliency-aware CNN framework for ship detection, comprising comprehensive ship discriminative features, such as deep feature, saliency map, and coastline prior. This model uses CNN to predict the category and the position of ships and uses the global contrast based salient region detection to correct the location. We also extract coastline information and respectively incorporate it into CNN and saliency detection to obtain more accurate ship locations. We implement our model on Darknet under CUDA 8.0 and CUDNN V5 and use a real-world visual image dataset for training and evaluation. The experimental results show that our model outperforms representative counterparts (Faster R-CNN, SSD, and YOLOv2) in terms of accuracy and speed.

LoRa has recently become one of the most promising networking technologies for the Internet of Things applications. Distant end devices have to use a low data rate to reach a LoRa gateway, which can cause long in-the-air transmission time and high energy consumption. Compared with the end devices using high data rate, they will drain the batteries much earlier and the network may be broken. Such an energy unfairness can be mitigated by deploying more gateways, since it allows end devices to reach closer gateways with higher data rates. However, multiple gateways may not solve the energy unfairness problem efficiently due to the collision problem caused by the chirp spread spectrum modulation of LoRa networks. Spreading factors of LoRa links can determine both data rate and multiplexing of different transmissions. With more gateways, more end devices may choose low spreading factors and reach closer gateways, which increase the collision probability. In this paper, we propose a networking solution for LoRa networks named EF-LoRa that can achieve fair energy consumption among end devices by carefully allocating different network resources, including frequency channels, spreading factors and transmission power, to achieve fair energy consumption among end devices in LoRa networks. We develop a LoRa network model to study the energy consumption of all the end devices in a network by considering the unique features of LoRa networks, such as LoRaWAN MAC protocol, spreading factors, interference, and the capacity limitation of a LoRa gateway. We formulate the energy fairness problem as an optimization problem and finally propose a greedy resource allocation algorithm to achieve the max-min fairness of energy efficiency in the LoRa networks. Simulation results show that the proposed solution EF-LoRa can improve the energy fairness of legacy LoRa networks by 177.8%.

Training deep learning models on mobile devices recently becomes possible, because of increasing computation power on mobile hardware and the advantages of enhancing user experiences. Most of the existing work on machine learning at mobile devices is focused on the inference of deep learning models, but not training. The performance characterization of training deep learning models on mobile devices is largely unexplored, although understanding the performance characterization is critical for designing and implementing deep learning models on mobile devices. In this paper, we perform a variety of experiments on a representative mobile device (the NVIDIA TX2) to study the performance of training deep learning models. We introduce a benchmark suite and a tool to study performance of training deep learning models on mobile devices, from the perspectives of memory consumption, hardware utilization, and power consumption. The tool can correlate performance results with fine-grained operations in deep learning models, providing capabilities to capture performance variance and problems at a fine granularity. We reveal interesting performance problems and opportunities, including under-utilization of heterogeneous hardware, large energy consumption of the memory, and high predictability of workload characterization. Based on the performance analysis, we suggest interesting research directions.

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, and the issue of charging security/threat is ignored, causing it vulnerable to attacks. In this paper, we develop a novel attack for WRSN through Denial of Charge (DoC) aiming at maximizing destructiveness. At first, we form a generalized on-demand charging model, which provides fundamental basis for designing charging attacks. Then a request prediction method (RPM) is introduced for predicting the emergences of charging requests. Afterwards, a Collaborative DoC attacking algorithm (CoDoC) is developed, which tempers/modifies and generates fake charging requests, yielding normal nodes exhausted. Finally, to demonstrate the outperformed features of CoDoC, extensive simulations and test-bed experiments are conducted. The results show that, CoDoC outperforms in making sensor exhausted as well as causing missing events.

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. Rechargeable sensors together with Unmanned Aerial Vehicles (UAVs) are collaboratively employed for fulfilling periodic coverage tasks. However, traditional coverage solutions are normally based on static deployment of sensors and not suitable for such coverage requirements. In this paper, we propose a new concept of coverage problem named Period-Area Coverage (PAC) which requires data of the overall area must be collected periodically. We focus on maximizing the energy efficiency of UAVs and propose two heuristic scheduling schemes to balance energy cost. Moreover, we adopt adjustable sensing range to further promote efficiency and develop a charging re-allocation mechanism for UAVs. Test-bed experiments and extensive simulations demonstrate that the proposed schemes can enhance energy efficiency by 18.2% compared to prior arts.

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, to save mobile energy. However, it is hard to build an explicit model that accurately depicts the affecting factors and their affecting mechanism of time-varying app usage behavior. This paper presents a deep reinforcement learning framework, named as DeepAPP, which learns a model-free predictive neural network from historical app usage data. Meanwhile, an online updating strategy is designed to adapt the predictive network to the time-varying app usage behavior. To transform DeepAPP into a practical deep reinforcement learning system, several challenges are addressed by developing a context representation method for complex contextual environment, a general agent for overcoming data sparsity and a lightweight personalized agent for minimizing the prediction time. Extensive experiments on a large-scale anonymized app usage dataset reveal that DeepAPP provides high accuracy (precision 70.6% and recall of 62.4%) and reduces the prediction time of the state-of-the-art by 6.58×. A field experiment of 29 participants also demonstrates DeepAPP can effectively reduce time of loading apps.

This paper presents StrLight, the first practical VLC system that leverages widely-deployed string lights to transmit data. The data transmission is imperceptible to human eyes. Users can decode the data by mobile devices (e.g., smartphones) equipped with cameras. StrLight primarily differs from existing VLC systems in using string lights which are composed of a large number of small LEDs and thus the unique design to address practical issues including a special data modulation/encoding scheme, a data representation with unstructured/unknown topologies of LEDs in the string light, and a fault tolerance against broken and blocked LEDs. To the best of our knowledge, StrLight is the first practical VLC system of its kind. We build several prototypes of string light transmitters and test with different smartphone models and a customized mobile device as receivers. The experiment results show that StrLight provides an efficient and robust data broadcasting. A string light of 100 LEDs working in 450 Hz and a camera with a capture rate of 30 Hz and an image resolution of as low as 320 × 240 pixels, delivers data rate of ~1 kbps, without observable light flickers.

Current localization schemes on mobile devices are experiencing great diversity that is mainly shown in two aspects: the large number of available localization schemes and their diverse performance. This paper presents UniLoc, a unified framework that gains improved performance from multiple localization schemes by exploiting their diversity. UniLoc predicts the localization error of each scheme online based on an error model and real-time context. It further combines the results of all available schemes based on the error prediction results and an ensemble learning algorithm. The combined result is more accurate than any individual schemes. With the flexible design of error modeling and ensemble learning, UniLoc can easily integrate a new localization scheme. The energy consumption of UniLoc is low, since its computation, including both error prediction and ensemble learning, only involves simple linear calculation. Our experience with extensive experiments tells that such easy aggregation incurs little overhead in integrating and training a localization scheme, but gains substantially from the scheme diversity. UniLoc outperforms individual localization schemes by 1.6X in a variety of environments, including >89% new places where we did not train the error models.

This paper presents DopEnc, an acoustic-based encounter profiling system on commercial off-the-shelf smartphones. DopEnc automatically identifies the persons that users interact with in the context of encountering. DopEnc performs encounter profiling in two major steps: (1) Doppler profiling to detect that two persons approach and stop in front of each other via an effective trajectory, and (2) voice profiling to confirm that they are thereafter engaged in an interactive conversation. DopEnc is further extended to support parallel acoustic exploration of many users by incorporating a unique multiple access scheme within the limited inaudible acoustic frequency band. All implementation of DopEnc is based on commodity sensors like speakers, microphones, and accelerometers integrated on mainstream smartphones. We evaluate DopEnc with detailed experiments and a real use-case study of 11 participants. Overall DopEnc achieves an accuracy of 6.9 percent false positive and 9.7 percent false negative in real usage.

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 dataset currently consists of 31 455 images and covers six common ship types (ore carrier, bulk cargo carrier, general cargo ship, container ship, fishing boat, and passenger ship). All of the images are from about 10 080 real-world video segments, which are acquired by the monitoring cameras in a deployed coastline video surveillance system. They are carefully selected to mostly cover all possible imaging variations, for example, different scales, hull parts, illumination, viewpoints, backgrounds, and occlusions. All images are annotated with ship-type labels and high-precision bounding boxes. Based on the SeaShips dataset, we present the performance of three detectors as a baseline to do the following: 1) elementarily summarize the difficulties of the dataset for ship detection; 2) show detection results for researchers using the dataset; and 3) make a comparison to identify the strengths and weaknesses of the baseline algorithms. In practice, the SeaShips dataset would hopefully advance research and applications on ship detection.

Screen-camera links for Visible Light Communication (VLC) are diverse, as the link quality varies according to many factors, such as ambient light and camera's performance. This paper presents SoftLight, a channel coding approach that considers the unique channel characteristics of VLC links and automatically adapts the transmission data rate to the link qualities of various scenarios. SoftLight incorporates two new ideas: (1) an expanded color modulation interface that provides soft hint about its confidence in each demodulated bit and establishes a bit-level VLC erasure channel, and (2) a rateless coding scheme that achieves bit-level rateless transmissions with low computation complexity and tolerates the false positive of bits provided by the soft hint enabled erasure channel. SoftLight is orthogonal to the visual coding schemes and can be applied atop any barcode layouts. We implement SoftLight on Android smartphones and evaluate its performance under a variety of environments. The experiment results show that SoftLight can correctly transmit a 22-KByte photo between two smartphones within 0.6 second and improves the average goodput of the state-of-the-art screen-camera VLC solution by 2.2×.

This paper presents Pando, a completely contention-free data dissemination protocol for wireless sensor networks. Pando encodes data by Fountain codes and disseminates the rateless stream of encoded packets along the fast and parallel pipelines built on constructive interference and channel diversity. Since every encoded packet contains innovative information to the original data object, Pando avoids duplicate retransmissions and fully exploits the wireless broadcast effect in data dissemination. To transform Pando into a practical system, we devise several techniques, including the integration of Fountain coding with the timing-critical operations of constructive interference and pipelining, a silence-based feedback scheme for the one-way pipelined dissemination, and packet-level adaptation of network density and channel diversity. Based on these techniques, Pando can accomplish data dissemination entirely over the fast and parallel pipelines. We implement Pando in Contiki and for TelosB motes. We evaluate Pando with various settings on two large-scale open test beds, Indriya and Flocklab. Our experimental results show that Pando can provide 100% reliability and reduce the dissemination time of state of the art by 3.5×.

This paper presents a hopless networking paradigm. Incorporating recent techniques of rateless codes, senders break packets into rateless information streams and each single stream automatically adapts to diverse channel qualities at all potential receivers, regardless of their hop distances. The receivers are capable of accumulating rateless information pieces from different senders and jointly decoding the packet, largely improving throughput. We develop a practical protocol, called HOPE, which instantiates the hopless networking paradigm. Compared with the existing opportunistic routing protocol family, HOPE best exploits the wireless channel diversity and takes full advantage of the wireless broadcast effect. HOPE incurs minimum protocol overhead and serves general networking applications. We extensively evaluate the performance of HOPE with indoor network traces collected from USRP N210s and Intel 5300 NICs. The results show that HOPE achieves 1.7× and 1.3× goodput gain over EXOR and MIXIT, respectively. We further implement HOPE on a sensor network testbed, achieving the goodput gains over CTP.

Screen-camera links for Visible Light Communication (VLC) are diverse, as the link quality varies according to many factors, such as ambient light and camera's performance. This paper presents SoftLight, a channel coding approach that considers the unique channel characteristics of VLC links and automatically adapts the transmission data rate to the link qualities of various scenarios. SoftLight incorporates two new ideas: (1) an expanded color modulation interface that provides soft hint about its confidence in each demodulated bit and establishes a bit-level VLC erasure channel, and (2) a rateless coding scheme that achieves bit-level rateless transmissions with low computation complexity and tolerates the false positive of bits provided by the soft hint enabled erasure channel. SoftLight is orthogonal to the visual coding schemes and can be applied atop any barcode layouts. We implement SoftLight on Android smartphones and evaluate its performance under a variety of environments. The experiment results show that SoftLight can correctly transmit a 22-KByte photo between two smartphones within 0.6 second and improves the average goodput of the state-of-the-art screen-camera VLC solution by 2.2.

This paper presents DopEnc, an acoustic-based encounter profiling system on smartphones. DopEnc can automatically identify the persons that users interact with in the context of encountering. DopEnc performs encounter profiling in two major steps: (1) Doppler profiling to detect that two persons approach and stop in front of each other via an effective trajectory, and (2) voice profiling to confirm that they are thereafter engaged in an interactive conversation. DopEnc is further extended to support parallel acoustic exploration of many users by incorporating a unique multiple access scheme within the limited inaudible acoustic frequency band. All implementation of DopEnc is based on commodity sensors like speakers, microphones and accelerometers integrated on commercial-off-the-shelf smartphones. We evaluate DopEnc with detailed experiments and a real use-case study of 11 participants. Overall DopEnc achieves an accuracy of 6.9% false positive and 9.7% false negative in real usage.

This paper presents a distanceless networking approach for wireless sensor networks sparsely deployed in large areas. By leveraging rateless codes, we provide distanceless transmission to expand the communication range of sensor motes and fully exploit network diversity. We address a variety of practical challenges to accommodate rateless coding on resource-constrained sensor motes and devise a communication protocol to efficiently coordinate the distanceless link transmissions. We propose a new metric (expected distanceless transmission time) for routing selection and further adapt the distanceless transmissions to low duty-cycled sensor networks. We implement the proposed scheme in TinyOS on the TinyNode platform and deploy the sensor network in a real-world project, in which 12 wind measurement sensors are installed around a large urban reservoir of 2.5 × 3.0 km2to monitor the field wind distribution. Extensive experiments show that our proposed scheme significantly outperforms the state-of-the-art approaches for data collection in sparse sensor networks.

This paper presents a hopless networking paradigm. Incorporating recent techniques of rateless codes, senders break packets into rateless information streams and each single stream automatically adapts to diverse channel qualities at all potential receivers, regardless of their hop distances. The receivers are capable of accumulating rateless information pieces from different senders and jointly decoding the packet, largely improving throughput. We develop a practical protocol, called HOPE, which instantiates the hopless networking paradigm. Compared with the existing opportunistic routing protocol family, HOPE best exploits the wireless channel diversity and takes full advantage of the wireless broadcast effect. HOPE incurs minimum protocol overhead and serves general networking applications. We extensively evaluate the performance of HOPE with indoor network traces collected from USRP N210s and Intel 5300 NICs. The results show that HOPE achieves 1.7x and 1.3x goodput gain over ExOR and MIXIT, respectively.

This paper presents Pando, a completely contention-free data dissemination protocol for wireless sensor networks. Pando encodes data by Fountain codes and disseminates the rateless stream of encoded packets along the fast and parallel pipelines built on constructive interference and channel diversity. Since every encoded packet contains innovative information to the original data object, Pando avoids duplicate retransmissions and fully exploits the wireless broadcast effect in data dissemination. To transform Pando into a practical system, we devise several techniques, including the integration of Fountain coding with the timing-critical operations of constructive interference and pipelining, a silence based feedback scheme for the one-way pipelined dissemination, and packet-level adaptation of network density and channel diversity. Based on these techniques, Pando can accomplish the data dissemination process entirely over the fast and parallel pipelines. We implement Pando in Contiki and for TelosB sensor motes. We evaluate Pando's performance with various settings on two large-scale open testbeds, Indriya and Flocklab. Our experimental results show that Pando can provide 100% reliability and reduce the dissemination time of the state-of-the-art by 3.5.

We study the water quality in an urban district, where the surface wind distribution is an essential input but undergoes high spatial and temporal variations due to the impact of surrounding buildings. In this work, we develop an optimal sensor placement scheme to measure the wind distribution over a large urban reservoir using a limited number of wind sensors. Unlike existing solutions that assume Gaussian process of target phenomena, this study measures the wind that inherently exhibits strong non-Gaussian yearly distribution. By leveraging the local monsoon characteristics of wind, we segment a year into different monsoon seasons that follow a unique distribution respectively. We also use computational fluid dynamics to learn the spatial correlation of wind. The output of sensor placement is a set of the most informative locations to deploy the wind sensors, based on the readings of which we can accurately predict the wind over the entire reservoir in real time. Ten wind sensors are deployed. The in-field measurement results of more than 3 months suggest that the proposed sensor placement and spatial prediction scheme provides accurate wind measurement that outperforms the state-of-the-art Gaussian model based on interpolation-based approaches.

Water quality monitoring and prediction are critical for ensuring the sustainability of water resources which are essential for social security, especially for countries with limited land like Singapore. For example, the Singapore government identified water as a new growth sector and committed in 2006 to invest S$ 330 million over the following five years for water research and development [1]. To investigate the water quality evolution numerically, some key water quality parameters at several discrete locations in the reservoir (e.g., dissolved oxygen, chlorophyll, and temperature) and some environmental parameters (e.g., the wind distribution above water surface, air temperature and precipitation) are used as inputs to a three-dimensional hydrodynamics-ecological model, Estuary Lake and Coastal Ocean Model — Computational Aquatic Ecosystem Dynamics Model (ELCOM-CAEDYM) [2]. Based on the calculation in the model, we can obtain the distribution of water quality in the whole reservoir. We can also study the effect of different environmental parameters on the water quality evolution, and finally predict the water quality of the reservoir with a time step of 30 seconds. In this demo, we introduce our data collection system which enables water quality studies with real-time sensor data.

This paper presents a distanceless networking approach for wireless sensor networks sparsely deployed in large areas. By leveraging rateless codes, we provide distanceless transmission to expand the communication range of sensor motes and fully exploit network diversity. We address a variety of practical challenges to accommodate rateless coding on resource-constrained sensor motes and devise a communication protocol to efficiently coordinate the distanceless link transmissions. We propose a new metric (expected distanceless transmission time) for routing selection and further adapt the distanceless transmissions to low duty-cycled sensor networks. We implement the proposed scheme in TinyOS on the TinyNode platform and deploy the sensor network in a real-world project, in which 12 wind measurement sensors are installed around a large urban reservoir of 2.5km * 3.0km to monitor the field wind distribution. Extensive experiments show that our proposed scheme significantly outperforms the state-of-the-art approaches for data collection in sparse sensor networks.

This demo presents a distanceless networking approach for wireless sensor networks sparsely deployed in large areas. We implement the proposed scheme and deploy the sensor network in a large urban reservoir of 2.5km * 3.0km to monitor the field wind distribution. We show the in-field deployment procedure of the wind field measurement system and demonstrate the performance of the data collection protocol by a small testbed on site.

Based on plenty of sensors on smartphones and tablets, their location information becomes more accurate and easy to access. Many position-based applications have thus been developed. As these mobile devices have become the main access approach of 802.11-based wireless local area networks (WLAN), location information also provides opportunities to improve the performance of underlying wireless communication. This paper presents CO-MAP (Co-Occurrence MAP), which leverages location information to handle exposed and hidden terminal problems, which are still a major cause of throughput degradation in mobile WLANs. With the positions of nodes, CO-MAP rapidly builds a co-occurrence map showing which two links can occur concurrently. Meanwhile, to avoid potential collisions, it selects the best settings of frame transmissions based on a novel analytic network model when hidden terminals are distinguished. CO-MAP improves the goodputs of both downlinks and uplinks in an instant and distributed manner. Our implementation on a hardware testbed demonstrates that CO-MAP can accurately detect potential interferers, and provide significant gain of goodput for both exposed and hidden terminal scenarios. The simulation results also suggest that imperfect position hints can still bring substantial improvement on the multiple access efficiency.

Benefiting from the abundant sensor hints of current mobile devices, their location information has become pervasively available and easy to access. As smartphones and tablets have become recently the main access devices of 802.11-based WLAN, location information provides large opportunity to improve the performance of underlying wireless communication. This paper presents CO-MAP (Co-Occurrence MAP) which leverages the position of devices to handle exposed and hidden terminal problems in mobile WLANs so as to improve the multiple access efficiency. With the location information, CO-MAP rapidly builds a co-occurrence map showing which two links can occur concurrently. Meanwhile, it selects the best settings of frame transmissions based on a novel analytical network model when hidden terminals are distinguished. CO-MAP improves the goodputs of both downlinks and uplinks in instant and distributed manner. Our implementation on a testbed of 6 laptops demonstrates that CO-MAP can accurately detect potential hidden and exposed interferers, and provide a large gain of goodput for both exposed terminal and hidden terminal scenarios. The simulation results of large scale networks on NS-2 also suggest that imperfect position hints can still bring substantial improvement on the multiple access efficiency.

This paper presents IDEA1, a validated SystemC-based simulator for WSNs. It allows the system-level performance evaluation (e.g., packet transmission and energy consumption) with elaborate models of sensor nodes. IDEA1 uses a clock-based synchronization mechanism to support simulations with cycle accurate communication and approximate time computation. Its accuracy has been validated by a testbed of 9 nodes. The average deviation between the IDEA1 simulations and experimental measurements is 5.9%. The performances of IDEA1 have also been compared with NS-2, one of the most widely used simulators in WSN research. To provide a similar result (deviation less than 5%) at the same abstraction level, the simulation of IDEA1 is 2 times faster than NS-2. Moreover, with the hardware and software co-simulation feature, IDEA1 provides more detailed modeling of sensor nodes than NS-2.

This paper presents a complete SystemC-based Wireless Sensor Network model. It implements the entire IEEE 802.15.4 standard, and permits to simulate scenarios at high level, taking hardware and software low level parameters into account, also enabling design space exploration for system level designers.