Diffusion policies excel at robotic manipulation by naturally modeling multimodal action distributions in high-dimensional spaces. Nevertheless, diffusion policies suffer from diffusion representation collapse: semantically similar observations are mapped to indistinguishable features, ultimately impairing their ability to handle subtle but critical variations required for complex robotic manipulation. To address this problem, we propose D²PPO (Diffusion Policy Policy Optimization with Dispersive Loss). D²PPO introduces dispersive loss regularization that combats representation collapse by treating all hidden representations within each batch as negative pairs. D²PPO compels the network to learn discriminative representations of similar observations, thereby enabling the policy to identify subtle yet crucial differences necessary for precise manipulation. In evaluation, we find that early-layer regularization benefits simple tasks, while late-layer regularization sharply enhances performance on complex manipulation tasks. On RoboMimic benchmarks, D²PPO achieves an average improvement of 22.7% in pre-training and 26.1% after fine-tuning, setting new SOTA results. In comparison with SOTA, the results of real-world experiments on a Franka Emika Panda robot show the excitingly high success rate of our method. The superiority of our method is especially evident in complex tasks.

Radio telescopes produce visibility data about celestial objects, but these data are sparse and noisy. As a result, images created on raw visibility data are of low quality. Recent studies have used deep learning models to reconstruct visibility data to get cleaner images. However, these methods rely on a substantial amount of labeled training data, which requires significant labeling effort from radio astronomers. Addressing this challenge, we propose VisRec, a model-agnostic semi-supervised learning approach to visibility data reconstruction in radio astronomy. Specifically, VisRec consists of both a supervised learning module and an unsupervised learning module. In the supervised learning module, we introduce a set of data augmentation functions to produce diverse visibility examples. In comparison, the unsupervised learning module in VisRec augments unlabeled data and uses reconstructions from non-augmented visibility as pseudo-labels for training. This hybrid approach allows VisRec to effectively leverage both labeled and unlabeled data. This way, VisRec performs well even when labeled data is scarce. Our evaluation results show that VisRec is applicable to various models, and outperforms all baseline methods in terms of reconstruction quality, robustness, and generalizability.

Credit assignment is a critical problem in multi-agent reinforcement learning (MARL), aiming to identify agents' marginal contributions for optimizing cooperative policies. Current credit assignment methods typically assume synchronous decision-making among agents. However, many real-world scenarios require agents to act asynchronously without waiting for others. This asynchrony introduces conditional dependencies between actions, which pose great challenges to current methods. To address this issue, we propose an asynchronous credit assignment framework, incorporating a Virtual Synchrony Proxy (VSP) mechanism and a Multiplicative Value Decomposition (MVD) algorithm. VSP enables physically asynchronous actions to be virtually synchronized during credit assignment. We theoretically prove that VSP preserves both task equilibrium and algorithm convergence. Furthermore, MVD leverages multiplicative interactions to effectively model dependencies among asynchronous actions, offering theoretical advantages in handling asynchronous tasks. Extensive experiments show that our framework consistently outperforms state-of-the-art MARL methods on challenging tasks while providing improved interpretability for asynchronous cooperation.

We introduce DisPIM, a framework that leverages pretrained image models (PIMs) for visuo-motor control. Applying PIMs to visuo-motor control faces a big difficulty due to the distribution shift between the distribution of visual environmental states and that of the pretraining datasets. Due to such a distribution shift, fine-tuning PIMs specifically for visuo-motor control may hurt the generalizability of PIMs, while adding additional tunable parameters for specific actions apparently lead to high computational costs. DisPIM addresses these challenges using a novel feature distillation approach, which obtains a compact model that not only inherit the generalization capability of PIMs but also acquire task-specific skills for visuo-motor control. This good for both sides is mainly achieved by means of a target Q-ensemble mechanism, which is inspired by double Q-learning. This Q-ensemble mechanism can adaptively adjust the distillation rate, so as to balance the objective of generalization and task-specific ability during training. With this balancing mechanism, DisPIM achieves both task-specific and generalizable control requiring a low computation cost. Across a series of algorithms, task domains, and evaluation metrics in both simulation and real robot, our DisPIM demonstrates significant improvements in generalization and overall performance with low computational overhead.

Parallel decoding of backscatter improves communication throughput by enabling concurrent transmission of backscatter tags. In practical applications of parallel decoding, it is extremely difficult to distinguish collided signals in superclusters where multiple signal clusters overlap. Existing methods are usually effective for superclusters with uniformly distributed signals. Nevertheless, there are many more scenarios in which signals in superclusters tend to gather unevenly, and existing methods cannot work. Such uneven clustering of signals occurs due to the following two possible causes: (1) signal-strengthdifferences (SSDs) among tags; or (2) cluster drifting (CD) driven by interferences from other objects within communication environments. This paper proposes a novel scheme called SalixLeaf, which aims to identify the main veins of signal clusters to address this problem of superclusters with unevenly distributed signals. Salix-Leaf identifies the main vein of each signal cluster for fine-grained clustering so that the direction of the main veins can be used to verify the accuracy of clustering. In addition, SalixLeaf employs a supercluster decomposer that divides signals into different segments for clustering analysis, enhancing robustness and practicability. Experimental results show that Salix-Leaf achieves a 1.2-fold increase in throughput and a 25% reduction in bit error rate (BER) compared to the state-of-the-art.

Visual reinforcement learning is a technique that learns effective policies from image pixels. Data augmentation is widely adopted in visual reinforcement learning to improve the generalization of the learned policies as data augmentation increases data diversity. However, applying data augmentation to all pixels simultaneously results in a divergence in action distribution as well and degrades the training stability in turn. Additionally, existing methods compute task weights for each pixel and apply augmentation methods separately based on tasks. As a result, they require a significant amount of computational resources. To enhance both the training stability and computational efficiency in the computation of task weights, we propose a Task-Aware Lipschitz Confidence (TALC) data augmentation method for visual reinforcement tasks. TALC calculates the task-aware confidence of all pixels on the image at once, only enhancing low confidence pixels to increase data diversity. We have conducted experiments on DeepMind Control suite tasks and the results demonstrate that TALC not only improves the training efficiency, but also enhances the generalization ability during testing. Overall, TALC out-performs existing methods in most different visual control benchmarks.

Online Scheduling for Partial charging with Multi-Mobile Chargers (OSPM) is critical for Wireless Rechargeable Sensor Networks (WRSNs) performing high-power monitoring tasks with a large number of simultaneous charging requests. However, existing studies for online scheduling assume full charging of sensors, leading to delays and inefficient resource utilization. Partially charging the sensors can improve scheduling efficiency and flexibility, but these studies focus on off-line scheduling, hindering dynamic decision-making. Multi-Agent Reinforcement Learning (MARL) is advantageous in online collaboration. Nevertheless, existing MARL methods assume synchronized actions, while Mobile Chargers (MCs) performing charging tasks asynchronously due to the difference in movement and charging times. On the other hand, hybrid actions are required to capture the simultaneous decision-making of MCs, involving sensor selection (discrete action) and energy allocation (continuous parameter). This introduces a circular dependency between a discrete action and its corresponding continuous parameter due to their interdependence. To deal with the above problems and address OSPM, we propose Asynchronous and Scalable Multi-agent Hybrid Proximal Policy Optimization (ASM-HPPO). The evaluation results not only indicate that our ASM-HPPO has advantages in terms of various performance metrics over existing schemes, but also demonstrate that our methods achieve higher stability and scalability.

Contrastive learning has been used to learn useful low-dimensional state representations in visual reinforcement learning (RL). Such state representations substantially improve the sample efficiency of visual RL. Nevertheless, existing contrastive learning-based RL methods have the problem of unstable training. Such instability comes from the fact that contrastive learning requires an extremely large batch size (e.g., 4096 or larger), while current contrastive learning-based RL methods typically set a small batch size (e.g., 512). In this paper, we propose an approach of discrete information bottleneck (DIB) to address this problem. DIB applies the technique of discretization and information bottleneck to contrastive learning in representing the state with concise discrete representation. Using this discrete representation for policy learning results in more stable algorithm training and higher sample efficiency with a small batch size. We demonstrate the advantage of discrete state representation of DIB on several continuous control tasks in the DeepMind Control suite. In the experiments, DIB outperforms prior visual RL methods, both model-based and model-free, in terms of performance and sample efficiency.

Unsupervised pre-training has demonstrated its potential for accurately constructing world models in visual model-based reinforcement learning (MBRL). However, such MBRL approaches exhibit limited generalizability, thereby limiting their practicality in diverse scenarios. These methods produce models that are restricted to the specific task they were trained on, and are not easily adaptable to other tasks. In this work, we introduce a powerful unsupervised pre-training reinforcement learning (RL) framework called VMBRL3, which improves the generalization ability of visual MBRL. VMBRL3 employs task-agnostic videos to pre-train both the autoencoder and world model without access to actions or rewards information. The fine-tuned world model can then be applied to a range of downstream reinforcement learning tasks, allowing for rapid adaptation to diverse environments and facilitating policy learning. We demonstrate that our framework significantly improves generalization ability in a variety of manipulation and locomotion tasks. Furthermore, VMBRL3 doubles the sample efficiency and overall performance compared to previous visual methods of MBRL.

Although reinforcement learning (RL) has achieved great success in diverse scenarios, complex gambling games still pose great challenges for RL. Common deep RL methods have difficulties maintaining stability and efficiency in such games. By theoretical analysis, we find that the return distribution of a gambling game is an intrinsic factor of this problem. Such return distribution of gambling games is partitioned into two parts, depending on the win/lose outcome. These two parts represent the gain and loss. They repel each other because the player keeps “raising,” i.e., making a wager. However, common deep RL methods directly approximate the expectation of the return, without considering the particularity of the distribution. This way causes a redundant loss term in the objective function and a subsequent high variance. In this work, we propose WagerWin, a new framework for gambling games. WagerWin introduces probability and value factorization to construct a more effective value function. Our framework removes the redundant loss term of the objective function in training. In addition, WagerWin supports customized policy adaptation, which can tune the pretrained policy for different inclinations. We conduct extensive experiments onDouDizhuand SmallDou, a reduced version ofDouDizhu. The results demonstrate that WagerWin outperforms the original state-of-the-art RL model in both training efficiency and stability.

Point clouds from 3D light detection and ranging (LiDAR) are widely used. Noise caused by falling snow reduces the availability of point clouds. Due to the sparseness of LiDAR point clouds and the fact that the snow point clouds are easily affected by multi factors such as wind or snowfall conditions, it is difficult to accurately remove the snow while preserving the details of the point clouds. To solve the problem, this paper presents a de-snowing approach combining the intensity and spatial-temporal features. An intensity-based filter firstly removes the snow. Then a repairing method restores the non-snow points based on the spatial-temporal features. Experimental results demonstrate that our approach outperforms existing work in the literature and performs the least damage to the point clouds in different snowfall scenarios.

The rapid spread of the novel coronavirus disease 2019 (COVID-19) causes a significant impact on public health. It is critical to diagnose COVID-19 patients so that they can receive reasonable treatments quickly. The doctors can obtain a precise estimate of the infection's progression and decide more effective treatment options by segmenting the CT images of COVID-19 patients. However, it is challenging to segment infected regions in CT slices because the infected regions are multi-scale, and the boundary is not clear due to the low contrast between the infected area and the normal area. In this paper, a coarse-refine segmentation network is proposed to address these challenges. The coarse-refine architecture and hybrid loss is used to guide the model to predict the delicate structures with clear boundaries to address the problem of unclear boundaries. The atrous spatial pyramid pooling module in the network is added to improve the performance in detecting infected regions with different scales. Experimental results show that the model in the segmentation of COVID-19 CT images outperforms other familiar medical segmentation models, enabling the doctor to get a more accurate estimate on the progression of the infection and thus can provide more reasonable treatment options.

The use of multi-modal data such as the combination of whole slide images (WSIs) and gene expression data for survival analysis can lead to more accurate survival predictions. Previous multi-modal survival models are not able to efficiently excavate the intrinsic information within each modality. Moreover, previous methods regard the information from different modalities as similarly important so they cannot flexibly utilize the potential connection between the modalities. To address the above problems, we propose a new asymmetrical multi-modal method, termed as AMMASurv. Different from previous works, AMMASurv can effectively utilize the intrinsic information within every modality and flexibly adapts to the modalities of different importance. Encouraging experimental results demonstrate the superiority of our method over other state-of-the-art methods.

This paper studies cooperative charging, in which multiple mobile chargers cooperatively provide wireless charging services in a Wireless Rechargeable Sensor Network (WRSN). The ultimate goal of this cooperative charging is the long-term optimization that maximizes both the lifetime of all sensor nodes and the charging utility of each Mobile Charger (MC). We have attempted to apply Multi-Agent Reinforcement Learning (MARL) algorithms to this problem. Unfortunately, similar to existing methods, MARL algorithms also fail early in cooperative charging. We found that an MARL algorithm trained in each time-step of fixed length is neither accurate nor efficient in cooperative charging. We propose a new MARL framework, called VarLenMARL. For the accuracy of reward estimation, VarLenMARL allows each MC completes an action within a time-step of variable length before estimating rewards. Furthermore, we design a special mechanism in VarLenMARL for the long-term optimality of cooperative charging within a WRSN. Our results show that algorithms implemented on VarLenMARL achieved both higher charging utility of MCs and longer lifetime of sensor nodes.

Indoor, underground, or underwater three-dimensional (3D) localization provides fundamental support to the applications of mobile wireless sensor networks (WSNs). In these applications, a single robot cannot work, as there are no GPS signals and few references for the robot to loalizae itself in the large in-door spaces. Existing in-door localization approaches usually rely on the projection of the 3D topology graph onto a horizontal plane. Such projection is infeasible in a narrow vertical space, either, since it requires three location-known nodes, called anchors, as reference nodes on a large horizontal plane. In this paper, we propose a new distributed 3D localization protocol, FlagLoc, for the mobile WSNs. FlagLoc uses a flag that is composed of three anchor nodes on a plane of any angle to start the localization and to lead the network motion of a mobile WSN. Furthermore, FlagLoc compensates for distance and motion measurement errors. The evaluation shows that FlagLoc significantly outperforms the existing state-of-the-art schemes in terms of accuracy.

We study the realistic problem of range-based localization for mobile Internet of Things (IoT) without using GPS. This problem arises from the real-world applications and is characterized by the following three challenges: 1) inaccurate devices, such as the low cost motion sensors and moving parts in the mobile IoT nodes, make it infeasible to localize the nodes using their speed and direction; 2) when a team of IoT nodes keep moving, some nodes may get lost and be disconnected from the network due to the large accumulated errors in the distances; and 3) although the theory of global rigidity ensures the position uniqueness of nodes, there are still nonlocalizable nodes in a globally rigid graph. To address these challenges, we propose a distributed localization protocol, called GROLO. GROLO is able to perform efficient distributed localization through an adaptive global rigidity formation maintenance mechanism especially designed for the resource limited IoT nodes. GROLO is able to localize all of the nodes periodically in a mobile IoT by short distance adjustment. Furthermore, GROLO requires only necessary additional neighbor distance measurements. We evaluated GROLO and other localization protocols using both simulated nodes and ten real mobile nodes in an IoT. The results show that GROLO is promising for the localization and formation control with inaccurate mobile IoT in realistic environments.

Recognizing objects from simultaneously sensed photometric (RGB) and depth channels is a fundamental yet practical problem in many machine vision applications, such as robot grasping and autonomous driving. In this paper, we address this problem by developing a cross-modal attentional context (CMAC) learning framework, which enables the full exploitation of the context information from both RGB and depth data. Compared to existing RGB-D object detection frameworks, our approach has several appealing properties. First, it consists of an attention-based global context model for exploiting adaptive contextual information and incorporating this information into a region-based CNN (e.g., fast RCNN) framework to achieve improved object detection performance. Second, our CMAC framework further contains a fine-grained object part attention module to harness multiple discriminative object parts inside each possible object region for superior local feature representation. While greatly improving the accuracy of RGB-D object detection, the effective cross-modal information fusion as well as attentional context modeling in our proposed model provide an interpretable visualization scheme. Experimental results demonstrate that the proposed method significantly improves upon the state of the art on all public benchmarks.

We propose an integrated approach to human action recognition from a depth video. The two major contributions of this approach are a novel feature descriptor for depth videos and the corresponding deep learning neural network structures. In this paper, we first present pyramid energy Maps (PeMaps) as the feature descriptor for a sequence of frames in a depth video. The pyramid structure is able to present the history of an action. Furthermore, PeMaps uses the levels of energy to carry the spatial dynamics of actions in a depth video. We then design PeMapNet that applies convolution neural networks and bidirectional long-short term memory (BLSTM) recurrent neural networks to PeMaps for action recognition. We evaluate our approach on three challenging datasets including MSR-Action3D, UTKinect-Action3D and MSR-Gesture3D. The experimental results demonstrate that our approach obtained higher accuracy than most of the existing methods and advance in efficiency.

This paper investigates how to fuse grayscale and thermal video data for detecting foreground objects in challenging scenarios. To this end, we propose an intuitive yet effective method called weighted low-rank decomposition (WELD), which adaptively pursues the cross-modality low-rank representation. Specifically, we form two data matrices by accumulating sequential frames from the grayscale and the thermal videos, respectively. Within these two observing matrices, WELD detects moving foreground pixels as sparse outliers against the low-rank structure background and incorporates the weight variables to make the models of two modalities complementary to each other. The smoothness constraints of object motion are also introduced in WELD to further improve the robustness to noises. For optimization, we propose an iterative algorithm to efficiently solve the low-rank models with three subproblems. Moreover, we utilize an edge-preserving filtering-based method to substantially speed up WELD while preserving its accuracy. To provide a comprehensive evaluation benchmark of grayscale-thermal foreground detection, we create a new data set including 25 aligned grayscale-thermal video pairs with high diversity. Our extensive experiments on both the newly created data set and the public data set OSU3 suggest that WELD achieves superior performance and comparable efficiency against other state-of-the-art approaches.

Determining whether nodes can be localized, called localizability detection, is essential for wireless sensor networks (WSNs). This step is required for localizing nodes, achieving low-cost deployments, and identifying prerequisites in location-based applications. Centralized graph algorithms are inapplicable to a resource-limited WSN because of their high computation and communication costs, whereas distributed approaches may miss a large number of theoretically localizable nodes in a resource-limited WSN. In this paper, we propose an efficient and effective distributed approach in order to address this problem. Furthermore, we prove the correctness of our algorithm and analyze the reasons our algorithm can find more localizable nodes while requiring fewer known location nodes than existing algorithms, under the same network configurations. The time complexity of our algorithm is linear with respect to the number of nodes in a network. We conduct both simulations and real-world WSN experiments to evaluate our algorithm under various network settings. The results show that our algorithm significantly outperforms the existing algorithms in terms of both the latency and the accuracy of localizability detection.

Shortest path is a fundamental graph problem with numerous applications. However, the concept of classic shortest path is insufficient. In this paper, we study various concepts of “shortest” path in temporal graphs, called minimum temporal paths. Computing these minimum temporal paths is challenging as subpaths of a “shortest” path may not be “shortest” in a temporal graph. We propose efficient algorithms to compute minimum temporal paths and verified their efficiency using large real-world temporal graphs.

Core decomposition has been applied widely in the visualization and analysis of massive networks. However, existing studies of core decomposition were only limited to non-temporal graphs, while many real-world graphs can be naturally modeled as temporal graphs (e.g., the interaction between users at different time in online social networks, the phone call or messaging records between friends over time, etc.). In this paper, we define the problem of core decomposition in a temporal graph, propose efficient distributed algorithms to compute the cores in massive temporal graphs, and discuss how the technique can be used in temporal graph analysis.

In embedded systems, it brings great benefits to use NAND flash for dynamic data exchange like using RAM, since RAM is usually expensive and consumes much energy. However, the major hardware limitations of NAND flash make it difficult to directly and dynamically read\write\erase on NAND flash. Traditional virtual memory systems are all based on flash translation layer and file system, which lead to frequently flash read\write\erase and more RAM requirement. To address this problem, we propose a Comet Circle Model (CCM) to emulate RAM for low cost embedded systems in this paper. CCM dynamically makes the distribution of valid pages in NAND flash follow a fixed function through integrating its physical page-level mapping and circularly write-back techniques. As a result, CCM can select a block without valid pages to write data almost every time in data writing, which avoids data moving among blocks. Both theoretical analysis and experimental results show that the data moving times and erase counts of CCM closely reach the theoretical lower bounds.

Cooperative caching is a desirable approach to achieve efficient data access in multi-hop wireless networks. Existing cooperative caching algorithms mostly focus on cache placement. Another key issue, cache consistency, has not been adequately addressed. In this paper, we propose CACC, a cooperative approach to maintain cache consistency for wireless mesh networks. CACC combines push and pull by making use of the hierarchical architecture of mesh networks. The key contribution of CACC lies in two techniques that introduce cooperation among network nodes in delivering invalidation reports (IRs) so as to reduce communication cost and tolerate message losses. The first technique, IR integration, buffers and merges IRs at gateway nodes and periodically broadcasts them. The second technique, cooperative IR re-sending, lets intermediate nodes resend missed IR messages upon request. The interval of IR broadcast is optimized to achieve the optimal tradeoff between push and pull. We conduct numerical analysis to find optimal values for different scenarios. We also perform simulation to confirm our analysis results and compare with existing approaches. The results show that CACC can save message cost significantly (50-70 percent).

Users submit queries to an online database via its query interface. Query interface parsing, which is important for many applications, understands the query capabilities of a query interface. Since most query interfaces are organized hierarchically, we present a novel query interface parsing method, StatParser (Statistical Parser), to automatically extract the hierarchical query capabilities of query interfaces. StatParser automatically learns from a set of parsed query interfaces and parses new query interfaces. StatParser starts from a small grammar and enhances the grammar with a set of probabilities learned from parsed query interfaces under the maximum-entropy principle. Given a new query interface, the probability-enhanced grammar identifies the parse tree with the largest global probability to be the query capabilities of the query interface. Experimental results show that StatParser very accurately extracts the query capabilities and can effectively overcome the problems of existing query interface parsers.

Fault tolerance in wireless sensor networks (WSNs) has been studied extensively by computer science researchers and they proposed many fault-tolerant schemes for various applications including target and event detection. However, these schemes would fail in a particular application of WSNs: structural health monitoring (SHM). Different from other applications of WSNs, detecting structural damage requires significant amount of civil domain knowledge and utilizes different detection model. Meanwhile, researchers in civil engineering also proposed some fault-tolerant SHM algorithms. However, these algorithms are all centralized and not applicable to resource-limited wireless sensor networks. To our best knowledge, we are the first to address fault tolerance problem in WSN-based SHM. We target faulty sensor reading, one of the most difficult types of sensor fault to be detected, and propose a fault-tolerant SHM approach. The proposed approach is lightweight and it is able to disambiguate structural damage from sensor faults. The effectiveness of the proposed approach is demonstrated through both simulation and real implementation.

Cooperative caching is especially desirable for multi-hop wireless networks to achieve efficient data access. Existing cooperative caching algorithms for wireless networks mostly focus on cache placement. Another key issue, cache consistency maintenance has not been adequately addressed. In this paper, we propose the first cooperative approach to maintain cache consistency for wireless mesh networks. It basically combines push and pull by making use of the hierarchical architecture of mesh networks. More precisely, we propose two techniques introducing cooperation among network nodes in delivering Invalidation Reports (IR) so as to reduce communication cost and tolerate message losses: IR integration buffers and integrates IRs at the gateway nodes and periodically broadcasts them, Cooperative IR re-sending lets the intermediate nodes resend missed IR messages upon request. The most challenging issue in our design is the determination of the optimal IR broadcast period in order to achieve the optimal tradeoff between push and pull. We conduct numerical analysis to get optimal values for different scenarios. Simulation results confirm our analysis well and comparisons with existing approaches show that our approach can save message cost significantly (50%-70%).

In recent years, research on using wireless sensor networks (WSNs) for structural health monitoring (SHM) has attracted increasing attention. Unlike other monitoring applications, detection of possible structure damage requires significant amount of domain knowledge that computer science researchers are usually unfamiliar with. As a result, most previous work in WSN-based SHM was done by researchers in civil engineering. However, civil researchers often tend to solve practical engineering problems but rarely consider designing a system in an optimal way, particularly when the limited wireless bandwidth and restricted resources of WSNs need to be addressed. Through the collaboration with civil researchers, we demonstrate that optimization design can significantly help improve the performance of a WSN-based SHM system. We consider a fundamental problem in SHM: modal analysis, which is used to obtain the dynamic structural vibration characteristics. Cluster-based modal analysis approach is adopted. In each cluster, the vibration characteristics are identified and then are assembled together. Different from other applications, clustering in this approach should meet some extra requirements of modal analysis. Moreover, cluster size should be optimized to minimize the total energy consumption. This clustering problem is formally formulated and proven to be NP complete. Two centralized and one distributed algorithms are proposed to solve the problem. The effectiveness and efficiency of the proposed cluster-based modal analysis along with the clustering algorithms are evaluated using both simulation and experiments.

We investigate the problem of adaptive traffic light control of multiple intersections using real-time traffic data collected by a wireless sensor network (WSN). Previous studies mainly focused on optimizing the intervals of green lights in fixed sequences of traffic lights and ignored the traffic flow's characteristics and special traffic circumstances. In this paper, we propose an adaptive traffic light control scheme that adjusts the sequences of green lights in multiple intersections based on the real- time traffic data, including traffic volume, waiting time, number of stops, and vehicle density. Subsequently, the optimal green light length can be calculated from the local traffic data and traffic condition of neighbor intersections. Simulation results demonstrate that our scheme produces much higher throughput, lower average waiting time and fewer number of stops, compared with three control approaches: the optimal fixed-time control, an actuated control and an adaptive control.

Most researchers encountered the following two problems when working with real Wireless Sensor Networks (WSNs): (1) Sensor nodes cannot satisfy application requirements even though the nominal sensing/transmission rates of these nodes are much higher than required. (2) In a WSN deployed in a large area, it is difficult or infeasible to get runtime performance evaluation of sensor nodes. We found out that the root reason of these two problems is resource competition, in which an operation has to wait for the resources being used by other operations. Therefore, we propose a dual-mote testbed, which is able to avoid both hardware competition on a node and wireless channel competition in a network. We have implemented the hardware, supporting protocols and tools of the testbed. The experimental results show that, compared to a general WSN, the improvement on performances such as throughput and response speed by our testbed are more than doubled.

We investigate the problem of adaptive traffic light control using real-time traffic information collected by a wireless sensor network (WSN). Existing studies mainly focused on determining the green light length in a fixed sequence of traffic lights. In this paper, we propose an adaptive traffic light control algorithm that adjusts both the sequence and length of traffic lights in accordance with the real time traffic detected. Our algorithm considers a number of traffic factors such as traffic volume, waiting time, vehicle density, etc., to determine green light sequence and the optimal green light length. Simulation results demonstrate that our algorithm produces much higher throughput and lower vehicle's average waiting time, compared with a fixed-time control algorithm and an actuated control algorithm. We also implement proposed algorithm on our transportation testbed, iSensNet, and the result shows that our algorithm is effective and practical.

In-network sensor query processing systems (ISQPs), or sensor databases, have been developed to acquire, process and aggregate data from wireless sensor networks (WSNs). Because WSNs are resource-limited and involve multiple layers of embedded software, the system design issues have a significant impact on the performance of sensor databases. Therefore, we propose this tutorial to study the state of the art on these issues with a focus on their interaction with query processing techniques. Our goal is to present the challenges and efforts in developing holistic, efficient ISQPs. Specifically, we will cover architectural design, scheduling, data-centric routing, and wireless medium access control. This tutorial is intended for database researchers who are interested in sensor networks.

Adaptive sampling is proposed to improve the power efficiency of wireless sensor networks in that the sampling rate of a sensor node can change in response to the changes in the environment. To transmit the sampled data promptly, the nodes with different and dynamically changing sampling rates have to transmit at different and changing rates correspondingly, which in turn causes severe packet loss and power consumption. To address this problem, we propose a routing-layer scheduling scheme, SPAS, to support adaptive sampling. In SPAS, each node keeps a record of packets to be forwarded and wakes up at scheduled times to transmit and to receive. Furthermore, each node can dynamically optimize its route to the sink based on the transmission rates of its neighboring nodes. Our simulation results show that SPAS achieves both high power efficiency and a low packet loss rate in adaptive sampling.

Many research activities on wireless sensor networks (WSNs) need detailed performance statistics about protocols, systems, and applications; however, current simulation tools and testbeds lack mechanisms to report these statistics realistically and conveniently. To address this need, we have developed a WSN emulator, VMNet. VMNet emulates networked sensor nodes at the level of CPU clock cycles and executes the binary code of real applications directly. It emulates the radio channel with loss and noise as well as emulates the peripherals in sufficient detail. Moreover, VMNet takes parameter values from the real world and logs detailed runtime information of emulated nodes. Consequently, the application performance, both in response time and in power consumption, is reported realistically in VMNet, as demonstrated by our comparison studies with real sensor networks

In-network sensor query processing is a cross-layer design paradigm in which networked sensor nodes process data acquisitional queries in collaboration with one another. As power efficiency is still one of the most severe constraints in this paradigm, we propose a distributed, cross-layer scheduling scheme for it. In this scheme, each node employs its MAC, routing, and query layers to negotiate with its parent its timing for transmission and constructs a schedule for its query processing. It then follows the schedule to compute, communicate, and sleep in each query processing cycle. This scheduling reduces wasted listening and receiving as well as the switching between active and sleeping modes. Consequently, it results in 50-60% of power saving on real sensor nodes in our experiments. Additionally, it outperforms two existing scheduling schemes both on schedule construction efficiency and on schedule quality.