Tabular prediction, a well-established problem in machine learning, has consistently garnered significant research attention within academia and industry. Recently, with the rapid development of large language models (LLMs), there has been increasing exploration of how to apply LLMs to tabular prediction tasks. Many existing methods, however, typically rely on extensive pre-training or fine-tuning of LLMs, which demands considerable computational resources. To avoid this, we propose a retrieval-based approach that utilizes the powerful capabilities of LLMs in representation, comprehension, and inference. Our approach eliminates the need for training any modules or performing data augmentation, depending solely on information from target dataset. Experimental results reveal that, even without specialized training for tabular data, our method exhibits strong predictive performance on tabular prediction task, affirming its practicality and effectiveness.

Contrastive learning has emerged as a highly effective and versatile technique in information retrieval. However, its application within table retrieval remains limited, and often neglecting a typical phenomenon in table retrieval: one table can be associated with multiple, distinct queries. Directly applying traditional contrastive learning strategies may lead to semantic contrast conflicts during training, potentially impairing the quality of learned representations. Additionally, many current table retrieval methods still operate on query-table joint encoding, which introduces notable inefficiencies during both the training and retrieval processes. For this issue, this paper proposes ConTR, a tabular semantic contrastive learning method that simultaneously considers both inter-table and intra-table differences. By segmenting table into multiple vector representations and enabling the matching of diverse queries through differentiated vectors, thereby facilitating a more focused contrastive learning process. Retrieval experiments based on two typical table-related tasks validate the feasibility and effectiveness of proposed method.

Database knob tuning is essential for optimizing the performance of modern database management systems, which often expose hundreds of knobs with continuous or categorical values. However, the large number of knobs and the vast configuration space make it difficult to identify optimal settings efficiently. Although learning-based tuning has shown promise, existing approaches either ignore domain knowledge by relying solely on benchmark feedback or struggle to explore the high-dimensional knob space, resulting in high tuning costs and suboptimal performance. To address these challenges, we propose MCTuner , an adaptive knob tuning framework that minimizes exploration in ineffective regions of the configuration space. MCTuner employs a Mixture-of-Experts mechanism with specialized LLMs to identify performance-critical knobs. In further, MCTuner introduces the first spatial decomposition algorithm that recursively partitions the space into hierarchical subspaces, on which Bayesian Optimization is performed to efficiently search for near-optimal configurations. Evaluated on different benchmarks (OLAP, OLTP, and HTAP), MCTuner achieves up to 19.2% performance gains and 1.4x faster configuration discovery per iteration compared to state-of-the-art methods.

Learning-based models have shown promise in addressing query optimization challenges in the database field, where the learned cost model plays a central role. While these models outperform traditional optimizers on static datasets, their resilience and reliability in real-world applications remain a concern, limiting their widespread adoption. In this paper, we take a step towards a practical cost estimation model, named Tosure, which can quantify the uncerT ainty for cost estimation and generalizes to unseen databases accurately and efficiently. It consists primarily of two modules: a Cross-Database Representation (CDR) module and a Cost Estimation with Uncertainty (CEU) module. The CDR module captures the transferable features by focusing the minimal set based on deep-learning network, thereby enhancing the model's generalization capabilities. The CEU module introduces a novel Neural Network Gaussian Process (NNGP) to quantify the uncertainty in cost estimation, ensuring more robust estimations with an upper bound. To improve the model's performance, we perform pre-training on diverse large-scale datasets. Furthermore, we implement the model and integrate it with traditional query optimizer to validate its usability and effectiveness in real-world scenarios. Extensive experimentation demonstrates that Tosure outperforms state-of-the-art methods, achieving a 20% improvement in cost estimation accuracy and twice of the robustness.

Automatic knob tuning has emerged as a critical field of study within database optimization, focusing on simplifying the configuration of database parameters to boost performance, particularly in the realm of advanced modern database management systems with myriad adjustable knobs. The primary challenge revolves around identifying the ideal knob configurations that can markedly enhance system efficiency. Various machine learning techniques have been devised to automate this tuning process. Nevertheless, these methods frequently entail running extensive workloads, resulting in significant time and resource consumption. This inefficiency arises from their reliance on runtime feedback or the limited exploitation of domain knowledge.To overcome these limitations, we propose MLETune, a novel deep reinforcement learning-based approach guided by multi-Large Language Models (LLMs) experts. Our method leverages a remix retrieval-augmented generation algorithm to harness knowledge and distill expert guidance effectively. Additionally, we utilize a genetic algorithm for coarse-grained exploration based on system and query-level knob knowledge to expedite the cold start process in deep reinforcement learning. By classifying and compressing metrics and optimizing tuning knobs based on workload and knob-level insights, we aim to reduce the search space efficiently. In addition, adopting a delayed update strategy helps mitigate the training time required for the deep reinforcement learning model. Our extensive experiments demonstrate that MLETune outperforms existing methods by identifying superior configurations in significantly less time, showing an average improvement of ${6x}$, along with achieving up to a $26 \%$ performance improvement.

The query optimizer is a critical component within the database management system(DBMS), tasked with translating user-input SQL queries into efficient execution plans. Traditional query optimizers rely on statistical data that may become outdated, resulting in inaccuracies leading to suboptimal execution plans and consequent declines in query performance. In response, learning-based optimizers have emerged, utilizing historical data to improve plan selection quality. However, these approaches often struggle to handle dynamic workloads and fail to consistently achieve robust optimization outcomes. This paper introduces MIMO-Lero, an uncertainty-aware learning-based query optimizer designed for seamless integration into existing DBMS platforms without requiring extensive modifications. Inspired by neural network uncertainty principles, we design a Multi-in Multi-out (MIMO) architecture-based plan ranker. This ranker predicts both the relative ranking order of plans and their associated uncertainty levels, signifying the confidence in the order prediction. Furthermore, we propose two novel selection strategies that incorporate uncertainty to enhance the robustness of query optimization. By implementing MIMO-Lero and evaluating its performance using PostgreSQL, experimental results on diverse datasets showcase significant improvements in robust query optimization while maintaining high prediction accuracy.

Table-based fact verification (TFV) aims to classify whether a statement is entailed or refuted by a given table, which necessitates adept comprehension and logical inference skills among both tabular and textual data. The complexity of TFV is attributed to the involvement of both soft linguistic reasoning and hard symbolic reasoning. Existing studies tend to rely exclusively on table pre-trained models, lacking sufficient reasoning ability and treating various types of reasoning without distinction. In this paper, we propose a novel approach that transforms TFV task into a latent variable learning problem, employing a set of task-specific functions. Specifically, we leverage the hard Expectation-Maximization (EM) algorithm to ascertain the latent logic type underlying statements, then channel each statement through a specialized network designed for unique logical reasoning. Furthermore, we conduct a comprehensive exploration of the practical implementations of our proposed method in TFV task. Our approach diverges from the prevalent reliance on table-based pre-trained models, yet manages to surpass performance of various baseline models, exemplifying its efficacy and innovation.

Dynamic graphs are widely used in real-world applications and exhibit structural skew, which leads to skewed updates. Existing systems that support transactional updates often fail to fully consider this phenomenon, struggling to balance update and query performance. Inspired by the concepts of hierarchical thinking and uneven rebalancing on PMA, we propose DAUSK, a high-performance in-memory structure for dynamic graph storage that supports efficient graph analytics and rapid transactional updates. DAUSK addresses the skewed characteristics of graphs by employing two types of data structures: an unrolled skip list for frequently updated high-degree vertices, allowing asymptotically faster searches and updates, and a compact array-like structure called UPMA for medium and low-degree vertices, enabling efficient sequential scans. At the same time, DAUSK uses a vertex-centric strategy to partition UPMA and applies uneven gap allocation based on vertex degrees. Futhermore, considering the characteristics of transactions on graphs, DAUSK uses the well-established 2PL concurrency protocol to support millions of transactional updates per second. Experimental results demonstrate that DAUSK is up to 10.17×, 3.29× and 1.52× faster in ingesting graph updates compared to three state-of-the-art transactional graph systems, i.e., LiveGraph, Teseo and Sortledton. As for graph analytics, DAUSK achieves comparable, if not superior, performance compared to the other three graph systems.

Abstract Logical table‐to‐text generation is a task within the realm of natural language generation (NLG) that aims to generate coherent and logically faithful sentences based on tables. Unlike conventional NLG tasks, this task demands not only surface‐level fluency but also a high degree of logic‐level fidelity in the generated outputs. Current table‐to‐text systems grapple with various quality issues, such as repetitive generation, insufficient reasoning and limited complexity. Therefore, we introduce LogicMoE, a dedicated Mixture‐of‐Experts (MoE) model tailored for logical table‐to‐text generation. The primary objective of LogicMoE is to enrich the diversity of generated sentences from both semantic and logical perspectives. In particular, each expert within the model serves as a specialized generator responsible for generating sentences of a specific logical type. Additionally, we propose and employ novel evaluation metrics to comprehensively assess the diversity of generated outputs. Our experimental results showcase LogicMoE's superiority with absolute improvements of 0.8 and 2.2 in BLEU‐3 over the strong baselines on LogicNLG and Logic2Text datasets, respectively, driving the state‐of‐the‐art performance to a new level. Furthermore, we highlight its inherent advantages in terms of diversity and controllability, signifying its potential to spearhead advancements in logical table‐to‐text generation applications.

Popular topic detection is a topic identification by the information of documents posted by users in social networking platforms. In a large body of research literature, most popular topic detection methods identify the distribution of unknown topics by integrating information from documents based on social networking platforms. However, among these popular topic detection methods, most of them have a low accuracy in topic detection due to the short text content and the abundance of useless punctuation marks and emoticons. Image information in short texts has also been overlooked, while this information may contain the real topic matter of the user's posted content. In order to solve the above problems and improve the quality of topic detection, this paper proposes a popular topic detection method based on microblog images and short text information. The method uses an image description model to obtain more information about short texts, identifies hot words by a new word discovery algorithm in the preprocessing stage, and uses a PTM model to improve the quality and effectiveness of topic detection during topic detection and aggregation. The experimental results show that the topic detection method in this paper improves the values of evaluation indicators compared with the other three topic detection methods. In conclusion, the popular topic detection method proposed in this paper can improve the performance of topic detection by integrating microblog images and short text information, and outperforms other topic detection methods selected in this paper.

The automated diagnosis of breast cancer through Whole Slide Images (WSI) is a critical endeavour to combat the threat it poses to women’s health. However, traditional deep learning algorithms strongly rely on Independent and Identically Distributed (I.I.D) and then encounter challenges related to multi-instance bias when analyzing multiple tissue sections from the same patient, limiting their generalization capability. To address this, this study introduces Multi-Instance Bias Suppression (MIBS), a novel approach leveraging adversarial training to mitigate patient-specific overfitting. MIBS employs an instance-level discriminator to guide feature generation, disentangling instance-specific cues from broader diagnostic patterns. Through competitive adversarial training, MIBS enhances feature generalization, effectively addressing overfitting and boosting cross-patient accuracy. Validated on the BreakHis dataset, MIBS effectively tackles multi-instance bias-induced overfitting. By bridging the gap between cutting-edge deep learning techniques and the challenges posed by large-scale medical image data, MIBS advances the accuracy and applicability of breast cancer diagnosis. Our approach addresses the multi-instance bias challenge and integrates seamlessly with big data, propelling medical image analysis to new heights of efficiency and precision.

Finding the optimal query plan within a large planning space plays a crucial role in determining the performance of an SQL statement. Since traditional cost model-based approaches rely on manual parameter adjustments and DBA experience, the learned query optimizer has been proposed as an alternative to automatically determine the optimal query plan. However, recent methods face challenges in capturing all candidate query plan relationships and adapting to dynamic environments. In this paper, we design an improved learned query optimizer, Li-Lero, that could plug into the existing DBMS with non-intrusive modification. Inspirations from learning to rank, we employ a listwise approach to train a ranker to obtain the optimal with minimal execution time. Rather than computing the real execution time, such a ranker only measures the relative relationship of candidate plans. Furthermore, a robustness enhancement method is proposed to improve the dynamic adaptability of the model by utilizing the masking technique. We implement Li-Lero and demonstrate its outstanding performance using PostgreSQL. Comparative evaluations are conducted using two data sets with different data distributions, and results show that our proposed method achieves high prediction accuracy and is robust to dynamic environments.

In database systems, materialized views (MV) pre-emptively materialize the common portion of query workloads to reduce redundant computations through query rewriting. However, the utilization of these rewritten queries depends on the accuracy of cost estimation models. Despite the promising performance of learning-based cost estimation models, they still exhibit limitations. Firstly, they are unable to capture the relationships between cross-node dependencies and node hierarchy across physical execution plan trees, hindering accuracy improvements. Secondly, they cannot simultaneously support original queries and rewritten queries, thereby limiting compatibility enhancements. In this paper, we introduce TGAE, a cost estimation model employing Graph Attention Network (GAT) to learn cross-node dependencies among physical execution plans. TGAE first utilizes learning embeddings instead of one-hot encoding and then introduces an efficient node feature encoding to facilitate the dynamic creation of base tables tailored to meet the requirements of MV environments. To demonstrate the effectiveness of TGAE, we design and implement AGatMv, a system with view design and exploitation capabilities. Experimental results on two query workloads from the real-world IMDb dataset show significant improvements in cost estimation accuracy and rewrite evaluation correctness compared to PostgreSQL.

Concurrent transmission (CT) has been widely adopted to optimize the throughput of various data transmissions in wireless networks, such as bulk data dissemination and high-rate data collection. In CT, besides the possible data frame collision at receivers, we observe that acknowledgment frame (ACK) collision at senders can also significantly diminish concurrency opportunities. In this article, to avoid the potential ACK collision in CT, we propose ALIGNER which develops a new transmission pattern to coordinate concurrent senders in a distributed manner. The key idea is to align the silent periods of concurrent transmitters. To achieve this goal, we align the end of data frames concurrently transmitted by several senders. Therefore, the potentially arriving ACKs can avoid a collision with ongoing data transmissions because the concurrent senders are in a listening state to wait for receivers’ ACKs for a short and fixed period. ALIGNER can be applied for both deterministic and opportunistic forwarding protocols. It optionally uses a random back-off and slotted ACK mechanism to avoid a potential collision among simultaneously arrived ACKs in opportunistic forwarding. In addition, ALIGNER adopts a tailor-made metrics to analyze the throughput benefit of concurrent transmission for both deterministic and opportunistic data collection protocols. We have implemented ALIGNER in TinyOS and conducted extensive experiments on a real testbed. Experimental results show that ALIGNER can significantly increase the concurrency opportunities in both deterministic (up to 105%) and opportunistic (up to 89.7%) forwarding compared with the state-of-the-art CT methods.

The emerging of Generative Adversarial Networks (GANs) gives rise to a significant improvement in image generation. However, a controllable way of synthesizing images with specific characteristics still is a challenging issue. Many existing methods are not efficient enough that require additional information and pre-designed attributes, and are with much more human intervention. In this paper, we propose GAGAN, an extension method to the Generative Adversarial Network, that is the first work to generate specific images from a trained GAN model. To control the characteristics of images, a DNA pool of the trained GAN model is introduced and evolved by a genetic algorithm (GA). Then, with the DNA pool, GAGAN can generate the corresponding latent vector (DNA) of target images. Furthermore, GAGAN can synthesize images containing a single specific characteristic or multiple specific attributes (including AND and OR relation). Moreover, several fitness evaluation strategies are also proposed to make GAGAN flexible to control the target characteristics. Experiments on CelebA and MNIST are conducted, and results show that the proposed method is feasible and effective in specific image generation problem.

The energy efficiency and delivery robustness are two critical issues for low duty-cycled wireless sensor networks. The asynchronous receiver-initiated duty-cycling media access control (MAC) protocols have shown their effectiveness through various studies. In receiver-initiated MACs, packet transmission is triggered by the probe of receiver. However, it suffers from the performance degradation incurred by packet collision, especially under bursty traffic. Several protocols have been proposed to address this problem, but their performance is restricted by the unnecessary backoff time and long negotiation process. In this article, we present CD-MAC, an energy-efficient and robust contention-detectable mechanism for addressing the collision-catching problem in receiver-initiated MACs. By exploring the temporal diversity of the acknowledgments, a receiver recognizes the potential senders and subsequently polls individual senders one by one. On that basis, CD-MAC can successfully avoid packet collision even though multiple senders have data packets to transmit to the same receiver. We implement CD-MAC in TinyOS and evaluate its performance on an indoor testbed with single-hop and multi-hop network scenarios. The results show that CD-MAC can significantly improve throughput by 1.72 times compared with the state-of-the-art receiver-initiated MAC protocol under bursty traffic loads. The results also demonstrate that CD-MAC can effectively mitigate the influence of hidden terminal problem and adapt to network dynamics well.

Due to limited energy supply of Internet of Things (Zhao et al. 2018) (IoT) devices, asynchronous duty cycle radio management is widely adopted to save energy. Since the sleep schedules of nodes are unsynchronized, a sender has to repeatedly send frames to coordinate with its receiver or keep sleeping until the receiver’s wake-up time will come according to receiver’s sleep-wake schedule. In such contexts, opportunistic forwarding, which takes the earliest forwarding opportunity instead of a deterministic forwarder, shows great advantage in utilizing channel resource for duty-cycled IoT networks. The multiple forwarding choices with temporal and spatial diversity increase the chance of collision tolerance in opportunistic forwarding, potentially enhancing the overall performance of duty-cycled multi-hop networks. However, since the current channel contention mechanisms mainly focus on collision avoidance, it is too conservative to exploit concurrency. To address this problem, in this article, we propose COF to fully exploit the potential Concurrency for Opportunistic Forwarding in duty-cycled IoT networks. COF achieves concurrent transmission by: (i) measuring conditional link quality under the interference of on-going transmissions, and then (ii) further modeling the benefit of potential concurrency opportunities. According to the expected benefit of concurrency, COF decides whether or not to transmit in concurrent way. COF also adopts concurrency flag and signal features to avoid data collision caused by disordered concurrent transmissions and enhance the accuracy of conditional link quality estimation. COF can be easily integrated into the conventional unsynchronized and duty-cycled protocols. We have implemented COF and evaluated its performance on a 40-node testbed. The results show that COF can effectively exploit potential concurrency in opportunistic forwarding and COF outperforms the state-of-art protocols under diverse traffic load and network density.

In recent years, Generative Adversarial Networks (GANs) have achieved significant improvements in image processing, especially image-to-image translation problem and image generation. But, few works are presented to creatively produce a novel domain from many training datasets with different domains. Inspired by creating a new calligraphic style, we propose a novel GAN model that supports creatively generate data domain, such as context, style and so on. In this paper, we call it as WHGAN. What is one key innovation is that WHGAN brings in a discriminative set (contains k discriminative models) that each one is responsible for a training dataset, in addition, the single generative model obtains feedbacks from discriminative models and produces a novel data distribution. Relatively, each discriminative model distinguishes the generated data distribution from its corresponding input dataset. Meanwhile, in order to make the generated data adjustable, we redesign the objective function with a set of variable weights that each one is responsible for a discriminator. For ease of presentation, we set k to be 2 in our implementation. Then, we conduct two evaluation on image dataset and synthesized 2D dataset respectively. Results show that WHGAN successfully generates oil-painting style images from photo-realistic and cartoon style inputs, furthermore, we also visually and objectively verify the impact of weights.

Convolutional Neural Networks (CNNs) is capable of automatically learning feature representations, CNN-based recognition algorithm has been an alternative method for human activity recognition. Even though general convolution operation followed by pooling could expand the receptive fields for extracting features, it will bring about information loss in feature representation. Due to that dilated convolutions not only could expand receptive field exponentially without changing the size of field map or pooling, but it also will not cause information loss, hence, we propose D2CL, a novel deep learning framework for human activity recognition using multi-model wearable sensors. This framework consists of dilated convolutional neural networks and recurrent neural networks. At first, learning from previous works, we add a general convolutional layer to map inputs into a hidden space for improving the capability of nonlinear representations. Subsequently, a stacked dilated convolutional networks automatically learn feature representations for inter-sensors and intra-sensors from hidden space. Then, given these learned features, two RNNs are applied to model their latent temporal dependencies. Finally, a softmax classifier at the topmost layer is utilized to recognize activities. To evaluate the performance of D2CL on activity recognition, we select two open datasets OPPORTUNITY and PAMAP2 for training and testing. Results show that our proposed model achieves a higher classification performance than the state-of-the-art DeepConvLSTM.

Link estimation is a fundamental component of forwarding protocols in wireless sensor networks. In low power forwarding, however, the asynchronous nature of widely adopted duty-cycled radio control brings new challenges to achieve accurate and real-time estimation. First, the repeatedly transmitted frames (called wake-up frame) increase the complexity of accurate statistic, especially with bursty channel contention and coexistent interference. Second, frequent update of every link status will soon exhaust the limited energy supply. In this paper, we propose meter, which is a distributed wake-up frame counter. Meter takes the opportunities of link overhearing to update link status in real time. Furthermore, meter does not only depend on counting the successfully decoded wake-up frames, but also counts the corrupted ones by exploiting the feasibility of ZigBee identification based on short-term sequence of the received signal strength. We implement meter in TinyOS and further evaluate the performance through extensive experiments on indoor and outdoor test beds. The results demonstrate that meter can significantly improve the performance of the state-of-the-art link estimation scheme.

Despite very significant efforts on smartphonebased indoor localization, highly accurate and practical method remains an open problem. To guarantee accuracy, robustness, and practicality, in this paper, we propose SITE, a novel scheme uses acoustic Signal and phone Images to achieve accurate and robust indoor posiTion systEm. Our key observation is that if the simultaneously computed locations according to different sets of acoustic sources vary small, the positioning result is close to the true physical location. Based on the pre-deployed acoustic sources, SITE first tracks the direction of smartphone relative to an individual acoustic source according to proactively generated doppler effect in rough horizontal plane. Given m (m >= 3) acoustic sources, SITE can compute the relative coordinate of the phone in floor plan. By respectively selecting different sets of acoustic sources to compute the related coordinates, SITE can make sure whether these positioning results satisfy the requirement of positioning accuracy. If not, using images captured by phone camera, SITE exploits the synergy between its acoustic-based localization (coarse-grained) and the relative positions in reconstructed 3D point cloud by VisualSFM technique to refine the positioning result using acoustic signals. We have built a prototype of the SITE system and conducted evaluations in real testbed. Experimental results show that SITE is excellent in accuracy, robust and valuable in practical application.

Link estimation is a fundamental component of forwarding protocols in wireless sensor networks. In low power forwarding, however, the asynchronous nature of widely adopted duty-cycled radio control brings new challenges to achieve accurate and real- time estimation. First, the repeatedly transmitted frames (called wake-up frame) increase the complexity of accurate statistic, especially with bursty channel contention and coexistent interference. Second, frequent update of every link status exhausts the limited energy supply due to long duration of beacon broadcast. In this paper, we propose meter (Distributed Frame Counter), which takes the opportunities of link overhearing to update link status in real time. Furthermore, meter does not only depend on counting the successfully decoded wake-up frames, but also counts the corrupted ones by exploiting the feasibility of ZigBee identification based on short-term sequence of the received signal strength. We implement meter in TinyOS and further evaluate the performance through extensive experiments on indoor and outdoor testbeds. The results demonstrate that meter can significantly improve the performance of the state-of-the-art link estimation schemes.

Opportunistic routing, offering relatively efficient and adaptive forwarding in low-duty-cycled sensor networks, generally allows multiple nodes to forward the same packet simultaneously, especially in networks with intensive traffic. Uncoordinated transmissions often incur a number of duplicate packets, which are further forwarded in the network, occupy the limited network resource, and hinder the packet delivery performance. Existing solutions to this issue, e.g., overhearing or coordination based approaches, either cannot scale up with the system size, or suffer high control overhead. We present Duplicate-Detectable Opportunistic Forwarding (DOF), a duplicate-free opportunistic forwarding protocol for low-duty-cycled wireless sensor networks. DOF enables senders to obtain the information of all potential forwarders via a slotted acknowledgment scheme, so the data packets can be sent to the deterministic next-hop forwarder. Based on light-weight coordination, DOF explores the opportunities as many as possible and removes duplicate packets from the forwarding process. We implement DOF and evaluate its performance on an indoor testbed with 20 TelosB nodes. The experimental results show that DOF reduces the average duplicate ratio by 90%, compared to state-of-the-art opportunistic protocols, and achieves 61.5% enhancement in network yield and 51.4% saving in energy consumption.

On-air access of individual sensor node (called remote control) is an indispensable function in operational wireless sensor networks, for purposes like network management and real-time information delivery. To realize reliable and efficient remote control in a wireless sensor network (WSN), however, is extremely challenging, due to the stringent resource constraints and intrinsically unrealizable wireless communication. In this paper, we propose TeleAdjusting, a ready-to-use protocol to remotely control any individual node in a WSN. We develop a coding scheme for addressing on the cost-optimal reverse routing tree. In the address of each node, all its upstream relaying nodes are implicitly encoded. Then through a distributed prefix matching process between the local address and the destination address, a packet used for remote control is forwarded along a cost-optimal path. Moreover, TeleAdjusting incorporates opportunistic forwarding into the addressing process, so as to improve the network performance in terms of reliability and energy efficiency. We implement TeleAdjusting with TinyOS and evaluate its performance through extensive simulations and experiments. The results demonstrate that compared to the existing protocols, TeleAdjusting can provide high performance of remote control, which is as reliable as network-wide flooding and much more efficient than remote control through a pre-determined path.

Due to the constraint of energy resource, the radio of sensor nodes usually works in a duty-cycled mode. Since the sleep schedules of nodes are unsynchronized, a sender has to send preambles to coordinate with its receiver(s). In such contexts, opportunistic forwarding, which takes the earliest forwarding opportunity instead of a deterministic forwarder, shows great advantage in utilizing channel resource. The multiple forwarding choices with temporal and spatial diversity increase the chance of collision tolerance in concurrent transmissions, potentially enhancing end-to-end network performance. However, the current channel contention mechanism based on collision avoidance is too conservative to exploit concurrency. To address this problem, we propose COF, a practical protocol to exploit the potential Concurrency for low power Opportunistic Forwarding. COF determines whether a node should concurrently transmit or not, by incorporating: (1) a distributed and light-weight link quality measurement scheme for concurrent transmission and (2) a synthetic method to estimate the benefit of potential concurrency opportunity. COF can be easily integrated into the conventional unsynchronized sender-initiated protocols. We evaluate COF on a 40-node testbed. The results show that COF can reduce the end-to-end delay by up to 41% and energy consumption by 18.9%, compared with the state-of-the-art opportunistic forwarding protocol.

The energy efficiency and delivery robustness are two critical issues for low duty cycled wireless sensor networks. The asynchronous receiver-initiated duty cycling media access control (MAC) protocols have shown the effectiveness through various studies. In receiver-initiated MACs, packet transmission is triggered by the probe of receiver. However, it suffers from the performance degradation incurred by packet collision, especially under bursty traffic. Several protocols have been proposed to address this problem, but their performance is restricted by the unnecessary backoff time and long negotiation process. In this paper, we present Contention Detectable MAC (CD-MAC), an energy efficient and robust duty-cycled MAC for general wireless sensor network applications. By exploring the temporal diversity of the acknowledgements, a receiver recognizes the potential senders and subsequently polls individual senders one by one. We further design efficient algorithm to avoid the possible acknowledgement collision. We implement CD-MAC in TinyOS and evaluate the performance on an indoor testbed with single-hop and multi-hop networks. The results show that CD-MAC can significantly improve throughput by 1.72 times compared with the state-of-the-art receiver-initiated MAC protocol under bursty traffic loads. The results also demonstrate that CD-MAC can effectively mitigate the influence of hidden terminal problem and adapt to network dynamics well.

In large scale wireless sensor networks, retransmission strategies are widely adopted to guarantee the reliability of multi-hop forwarding. However, keeping retransmission over a bursty link may fail consecutively. Moreover, the retransmission will also be useless over those back-up links which are spatial correlated with the failed link. Thus, it is necessary to design an unified retransmission strategy, which considers both temporal and spacial link properties, to further improve network reliability and efficiency. In this paper, we propose RxLayer, a practical and general supporting layer of data retransmission. Without inducing noticeable overhead, RxLayer captures the temporal and spatial link properties by conditional probability models. A sender will retransmit data over the candidate link with the highest delivery probability while failures occur. RxLayer can be transparently integrated with most of the existing forwarding protocols. We implement RxLayer and evaluate it on both indoor and outdoor testbeds. The results show that RxLayer improves networks reliability and energy efficiency in various scenarios. The network reliability is improved by up to 7.82%, and the total number of transmissions is reduced by up to 36.3%.

Opportunistic routing, offering relatively efficient and adaptive forwarding in low-duty-cycled sensor networks, generally allows multiple nodes to forward the same packet simultaneously, especially in networks with intensive traffic. Uncoordinated transmissions often incur a number of duplicate packets, which are further forwarded in the network, occupy the limited network resource, and hinder the packet delivery performance. Existing solutions to this issue, e.g. overhearing or coordination based approaches, either cannot scale up with the system size, or suffers high control overhead. We present Duplicate-Detectable Opportunistic Forwarding (DOF), a duplicate free opportunistic forwarding protocol for low-duty-cycled wireless sensor networks. DOF enables senders to obtain the information of all potential forwarders via a slotted acknowledgement scheme, so the data packets can be sent to the deterministic next-hop forwarder. Based on light-weight coordination, DOF explores the opportunities as many as possible and removes duplicate packets from the forwarding process. We implement DOF and evaluate its performance on an indoor test-bed with 20 TelosB nodes. The experimental results show that DOF reduces the average duplicate ratio by 90%, compared to state-of-the-art opportunistic protocols, and achieves 61.5% enhancement in network yield and 51.4% saving in energy consumption.

In this paper, we study deliverability of greedy routing in wireless sensor networks, where nodes are distributed over a disk area according to a homogeneous Poisson point process. In our work, we model the level of deliverability of a sensor network as the probability that all sensor nodes can successfully send their data to a base station, which is named probability of guaranteed delivery. We study the relationship between the critical transmission power of sensor nodes and the probability of guaranteed delivery, such that when all sensor nodes transmit with a higher power than the critical transmission power, the sensor network can reach the desired probability of guaranteed delivery. We identify two very tight analytical upper bounds on the critical transmission power for the idealistic u-disk model and the realistic log-normal shadowing model respectively. The correctness and tightness of these two upper bounds are verified by extensive simulations.