Knowledge graphs (KGs) can help enhance recommendations, especially for the data-sparsity scenarios with limited user-item interaction data. Due to the strong power of representation learning of graph neural networks (GNNs), recent works of KG-based recommendation deploy GNN models to learn from both knowledge graph and user-item bipartite interaction graph. However, these works have not well considered the hierarchical structure of knowledge graph, leading to sub-optimal results. Despite the benefit of hierarchical structure, leveraging it is challenging since the structure is always partly-observed. In this work, we first propose to reveal unknown hierarchical structures with a supervised signal detection method and then exploit the hierarchical structure with disentangling representation learning. We conduct experiments on two large-scale datasets, of which the results well verify the superiority and rationality of the proposed method. Further experiments of ablation study with respect to key model designs have demonstrated the effectiveness and rationality of our proposed model. The code is available at https://github.com/tsinghua-fib-lab/HIKE .

Location prediction acts as a fundamental service in today's location-based information platform, which helps users access locations satisfying their demands, improving both user experience and platform profit. Since users with unambiguous demands prefer specific locations while users with compound demands consider first regions and then specific locations, it is necessary to model multi-grained user preferences at different geographical scales. However, most of the existing works concentrate on user preferences at the location-scale only, which can not understand users traveling behaviors thoroughly. In this paper, we propose to model both the fine-grained user preferences at the location scale and the coarsegrained user preferences at the region scale. Specifically, the proposed model harnesses the efficient information extraction power of graph neural networks. Moreover, the proposed geographical calibration method also helps to capture multi-grained user preferences accurately. Experiments on datasets of two very large cities demonstrate the significant performance improvement using our approach over state-of-the-art models. We also conduct experiments to further demonstrate the effectiveness of each component in the proposed model. Source codes of this paper are available at https://github.com/tsinghua-fib-lab/SIGSPATIAL-MMGUP/.

Air pollution is a significant public concern worldwide, and accurate data‐driven air pollution prediction is crucial for developing alerting systems and making urban decisions. As more and more cities establish their monitoring networks, there is a pressing need for coldstart model training with limited data accumulation in new cities. However, traditional spatial‐temporal modeling and transfer learning schemes have been challenged under this scenario because of insufficient usage of available source data and suboptimal transferring strategy. To address these issues, we propose a meta‐learning‐based spatial‐temporal adaptation solution for coldstart air pollution prediction. Our approach is a model‐agnostic framework that enables a given backbone predictor with adaption ability across different space and time locations. Specifically, it learns a factorization of the available source data distribution and recognizes the target city as one of its components, greatly reducing the data accumulation requirement and providing coldstart capability. Furthermore, we design a novel bidirectional meta‐learner that can simultaneously leverage task embeddings learned from data and features constructed based on prior knowledge. We conduct comprehensive experiments on both synthetic and real‐world air pollution datasets of four distinct pollutants. The results demonstrate that our proposed method achieves a 5.2% lower 24‐hour prediction mean absolute error (MAE) than pretraining and fine‐tuning solutions when facing a new city with only 200 hours of data, which empirically verifies the effectiveness of our approach as a coldstart training solution.

Point-of-Interest (POI) recommendation has drawn a lot of attention in both academia and industry. It utilizes user check-in data, aiming at recommending unvisited POIs to users. To address the data-sparsity problem, geographical information of POIs is often incorporated into recommender systems. However, most of the existing approaches model geographical impact in an implicit way, in which geographical information is encoded as auxiliary vectors for learning unified representations of users and POIs. Following this paradigm, the embedding of POIs can not reflect geographical similarity directly; thus, an explicit modeling approach is needed as geography is of great importance in POI recommendation. To address challenges in disentangling geographical effect, we proposed a disentangled representation learning method named DIG (short for Disentangled embedding of user Interest and POIs' Geographical information). Aiming at decoupling the geographical factor and the user interest factor thoroughly, we first proposed a geo-constrained negative sampling strategy, which helps to find reliable negative samples for the two factors. Second, a geo-enhanced soft-weighted loss function was proposed to quantify the trade-off between the two factors in loss computation. Extensive experiments have been conducted on two real-world datasets, and results have demonstrated the significant improvement of DIG at 3.92% - 20.32% 3.92% - 20.32% on recall, and 2.53% - 11.48% 2.53% - 11.48% on hit ratio, compared with other state-of-the-art approaches.

Among various cross-modal retrieval methods, the supervised methods achieve the best performance by exploiting the semantic labels. However, in realistic applications, the data are not always complete with labels and full multi-modal data, which makes these methods hard to be used. In this paper, we propose a general framework for handling cross-modal retrieval tasks with both missing labels and missing modalities. To be more specific, in our framework we embed the data in each modality and labels all into a common feature space and maximize their correlation altogether. When labels or data in some modalities are missing, we can still maximize the correlation between the remaining data or labels. Combined with the label prediction and data reconstruction modules, our model can effectively extract useful information from the incomplete data for cross-modal retrieval tasks. In the extensive experiments, our model outperforms many other methods on different datasets, which proves the effectiveness and flexibility for handling incomplete data of our model.

With the development of sensing technology, multiple sensors are widely used in Internet of Things (IoT) devices. A key challenge is to learn feature representations from multimodal sensor data to combine the information of different sensors. Although progress has been made by previous works, the correlation between different sensors is still not well exploited, which may limit the performance of representation learning. To address this problem, we propose a deep learning approach to learn representations from multimodal sensor data with maximally correlated autoencoders (MCA). It can efficiently capture high dependence between different modalities at different feature levels. The learned representations are further used for the recognition task. Experimental results on the real-world RGB- D dataset demonstrate the high effectiveness of MCA.

Air pollution problem has caught much attention globally. In addition to the national air quality monitoring stations deployed by the government, the number of low-cost air quality sensors increases rapidly as a supplement to support fine-grained monitoring. In-field calibration methods are necessary for these low-cost sensor nodes to assure the data quality. However, it is costly to collect enough reference data after deployment to train the in-field calibration model and many sensors even have no synchronized reference in the real application scenarios. To address the above challenge, we propose a multi-task learning based blind calibraiton method for air quality sensors after deployments. Our method introduces not only the reference data of the target location to formulate calibration task, but also reference measurements collected from highly accurate stations already deployed by the government in other geographical locations to formulate prediction task. To utilize the reference measurements which are not in the same location with our target sensors, e.g., in other cities, we combine the proposed calibration task and prediction task under a multi-task learning scheme. The introduced references in other locations alleviate our few-reference challenge. Furthermore, we elaborate on the choices of different tasks to have better effect of the target calibraiton task. Evaluations on the real-world collected datasets show that our proposed algorithm has better calibraiton effect.

Air pollution has become a global threat to human health. Fine-grained air quality monitoring has attracted much attention in recent years. Low-cost calibrated sensors make it possible for the large-scale deployment of IoT air quality monitoring systems. In practice, the calibration performance degrades after deployment due to the dynamic and diversity of system conditions. However, it is infeasible to collect sufficient in-field reference data to train calibration models for these new conditions. To address themulticonditionandfew-datachallenge, we proposed metalearning-based adaptive in-field calibration (MAIC), a metalearning-based adaptive in-field calibration algorithm. Specifically, MAIC adopts metalearning to learn how to adapt to new conditions quickly. To effectively leverage historical data, we first develop task generation strategies for sensor calibration under this scheme. Then, task-oriented optimization is introduced to train a model with superior adaptability in the offline training phase. Furthermore, an adaptation method is presented to learn the task-specific data distribution without forgetting the metaknowledge, enabling continual learning to utilize the temporal dependencies between multiple conditions. Our evaluations on synthetic and real-world data sets show that MAIC has high robustness and adaptability under multiple complicated conditions. Our proposed method outperforms the state-of-the-art calibration algorithms by 4.23%–29.46% in the real-world deployment data set, but with fewer requirements for the available in-field reference data.

Fine-grained city-scale outdoor air pollution maps provide important environmental information for both city managers and residents. Installing portable sensors on vehicles (e.g., taxis, Ubers) provides a low-cost, easy-maintenance, and high-coverage approach to collecting data for air pollution estimation. However, as non-dedicated platforms, vehicles like taxis usually prefer gathering at busy areas of a city where it is more likely to pick up riders. This leaves many parts of the city unsensed or less-sensed. In addition, due to the natural changes in a city and the movements of the vehicles, the sensed and unsensed areas change over time. Consequently, challenges of air pollution estimation with data collected by non-dedicated mobile platforms are twofold:i.data coverage is sparse;ii.data coverage changes over time. Therefore, the major research question is: how can we derive accurate and robust fine-grained field (e.g., air pollution) estimation given dynamic and sparse data collected from uncontrollable mobile sensing platforms? This paper presents adaptiveHMSS, an adaptivehybridmodel-enabledsensingsystem for fine-grained air pollution estimation with dynamic and sparse data collected from uncontrollable mobile sensing platforms, which is achieved by combining the advantages of aphysics guided modeland adata driven model. To address the challenge of sparse coverage, the physical understanding of the spatiotemporal correlation for air pollution distribution in thephysics guided modelis utilized to infer values at unsensed sparse areas. Meanwhile, thedata driven modelis adopted to estimate the air pollution influential factors (e.g., buildings) not included in thephysics guided model. To address the challenge of time-varying coverage, an adaptive model combination algorithm is designed to enable the system bias to either of the two models according to the amount of data collection and uncertainty of the model. To evaluate the system performance, we deployed 47 air pollution sensing devices on taxis and fixed locations in 2 cities for both controlled and uncontrolled experiments for over two weeks. The results show that with a resolution of$500 \;\mathrm m$by$500\;\mathrm m$by$1\;\mathrm {hour}$, our system achieves up to$3.2\times$error reduction when compared to the baseline approaches.

Air pollution problem has been a worldwide environmental concern in recent years. Accurate air pollution prediction can effectively protect public health and help government decisions. However, strong instability and frequent pattern shift in air pollution data challenges the conventional time series prediction paradigm and attracts interests in adaptive prediction algorithm. Recent progress in deep learning community, such as attention mechanism and meta learning algorithm, both use handcrafted adaptive strategy and lack sufficient usage of supporting observation data. In this paper, we adopt a variational Bayesian approach to enable fast adaption ability for a given air pollution predictor, which can make better use of recent observation data and adaptively inference task-specific parameters to achieve better adaption performance. Specifically, without explicitly designing a heuristic adaptive procedure, we formulate the adaptive prediction as a maximizing conditional likelihood problem on a generative graphic model, where a variational approximation to the intractable likelihood is further derived for end-to-end training. Experiments on real-world air pollution datasets show significant improvements of the proposed method compared to previous works.

Cross-modal retrieval is a classic task in the multimedia community, which aims to search for semantically similar results from different modalities. The core of cross-modal retrieval is to learn the most correlated features in a common feature space for the multi-modal data so that the similarity can be directly measured. In this paper, we propose a novel model using optimal transport for bridging the heterogeneity gap in cross-modal retrieval tasks. Specifically, we calculate the optimal transport plans between feature distributions of different modalities and then minimize the transport cost by optimizing the feature embedding functions. In this way, the feature distributions of multi-modal data can be well aligned in the common feature space. In addition, our model combines the complementary losses in different levels: 1) semantic level, 2) distributional level, and 3) pairwise level for improving cross-modal retrieval performance. In extensive experiments, our method outperforms many other cross-modal retrieval methods, which proves the efficacy of using optimal transport in cross-modal retrieval tasks.

Missing data is a common problem in multimodal and multi-view learning. It raises a critical challenge for most multimodal algorithms, which are unable to deal with incomplete datasets. Rather than discarding entries with missing modalities, this paper aims to reconstruct the complete image-based multimodal data by imputing missing modalities. We solve the imputation problem as an image translation task, which transforms images in one domain to other domains. Existing image translation techniques either can not fully utilize the information contained in partially complete entries or are limited to the bimodal situation. We propose a semi-supervised algorithm for multimodal learning with missing data, namely Cyclic Autoencoder (CycAE). Specifically, a novel cyclical structure, as well as the correlation among modalities, is integrated to leverage infoπnation from complete entries to incomplete ones. Experiments on two multimodal datasets show that our model outperforms state-of-the-art models. Downstream tasks can also benefit from the completed datasets.

Audio-visual emotion recognition is important for human-machine interaction systems by combining the information of audio and visual modalities. Although great progress has been made by previous works using multimodal learning compared with unimodal learning, they still cannot effectively deal with two key challenges. Firstly, it is difficult or expensive to acquire labeled emotional data, which results in a large amount of data with missing labels. Secondly, emotional data often has missing modalities. To address these problems, we propose a unified deep learning framework to efficiently handle missing labels and missing modalities for audio-visual emotion recognition through correlation analysis. Specifically, we consider four types of emotional data during the training stage: complete, label missing, visual missing, and audio missing. We propose a correlation loss based on Hirschfeld-Gebelein-Ŕenyi (HGR) maximal correlation to effectively capture the common information in different types of training data for emotion prediction. Experiments on the eNTERFACE’05 and RAVDESS datasets show that our deep learning approach has high effectiveness for audio-visual emotion recognition.

Human activity in the room causes signal changes on the power-lines. Therefore, the state of a person can be inferred by measuring the signal changes on the powerlines. Previous powerline-based indoor human sensing systems suffer from expensive hardware costs and thus cannot be deployed on a large scale. In this work, we propose a more cost-effective version of the sensing system and achieve sufficiently good results in a real deployment.

With the rapid growth of multimedia data, the cross-modal retrieval problem has attracted a lot of interest in both research and industry in recent years. However, the inconsistency of data distribution from different modalities makes such task challenging. In this paper, we propose Semantically Supervised Maximal Correlation (S2MC) method for cross-modal retrieval by incorporating semantic label information into the traditional maximal correlation framework. Combining with maximal correlation based method for extracting unsupervised pairing information, our method effectively exploits supervised semantic information on both common feature space and label space. Extensive experiments show that our method outperforms other current state-of-the-art methods on cross-modal retrieval tasks on three widely used datasets.

As pollution problems become increasingly prominent nowadays, urban air quality monitoring has attracted more and more attention. In recent years, sensing systems based on low-cost sensors are proposed to achieve fine-grained monitoring with larger amount of deployment as supplyment to conventional monitoring stations. Calibration is critical to guarantee the accuracy and consistency of these sensing systems to fight against sensor drift. While conventional field calibration approaches often rely on real-time data from a nearby standard station, they are not applicable to low-cost sensors which cannot receive the latest reference data from nearby stations after deployment. In reality, it is very difficult for sensors to get access to nearby standard stations deployed sparsely. To reduce the dependency on real-time and nearby reference data, we present a Robust Calibration approach based on Historical data (RCH) for the low-cost air pollution sensor calibration. Our method corrects the sensor drift by adapting sensitivity and offset based on estimating the probability distribution of pollutant's concentration. Experiments with real-world NO2data in Foshan, China show that our proposed method acheives close performance to conventional field calibration methods but addresses above challenges. Moreover, our method can use historical data collected from the sensors in more distant geographic locations than the compared method.

The reproducibility of scientific experiment is vital for the advancement of disciplines based on previous work. To achieve this goal, many researchers focus on complex methodology and self-invented tools which have difficulty in practical usage. In this article, we introduce the Cloud DevOps infrastructure from software engineering community and shows how it can be used effectively for heterogeneous agents to reproduce experiments for computer science related disciplines. DevOps can be enabled using freely available cloud computing machines for medium-sized experiment and self-hosted computing engines for large-scale computing, thus powering researchers to share their experiment result with others in a more reliable way.

Vehicular mobile crowdsensing (MCS) enables many smart city applications. Ridesharing vehicle fleets provide promising solutions to MCS due to the advantages of low cost, easy maintenance, high mobility, and long operational time. However, as nondedicated mobile sensing platforms, the first priorities of these vehicles are delivering passengers, which may lead to poor sensing coverage quality. Therefore, to help MCS derive good (large and balanced) sensing coverage quality, an actuation system is required to dispatch vehicles with a limited amount of monetary budget. This article presents PAS, a prediction-based actuation system for city-wide ridesharing vehicular MCS to achieve optimal sensing coverage quality with a limited budget. In PAS, two prediction models forecast probabilities of potential near-future vehicle routes and ride requests across the city. Based on prediction results, a prediction-based actuation planning algorithm is proposed to decide which vehicles to actuate and the corresponding routes. Experiments on city-scale deployments and physical feature-based simulations show that our PAS achieves up to 40% more improvement in sensing coverage quality and up to 20% higher ride request matching rate than baselines. In addition, to achieve a similar level of sensing coverage quality as the baseline, our PAS only needs 10% budget.

Predicting blood glucose concentration facilitates timely preventive measures against health risks induced by abnormal glucose events. Advances in IoT devices, such as continuous blood glucose monitors (CGMs) have made it convenient for measurements of blood glucose in real time. However, accurate and personalized blood glucose concentration prediction is still challenging. Previous inference models yield low-inference accuracy due to the ineffective feature extraction and the limited, imbalanced personal training data. The underlying causal correlations among the blood glucose series are scarcely captured by these models. In this article, we propose CausalBG, a causal recurrent neural network (CausalRNN) deployed on an IoT platform with smartphones and CGM for the accurate and efficient individual blood glucose concentration prediction. CausalBG automatically captures the underlying causal relationships embedded in the blood glucose features through CausalRNN, and efficiently shares the limited personal data among users for the sufficient training via the multitask framework. Evaluations and case studies on 112 users demonstrate that CausalBG significantly outperforms the conventional predictive models on the blood glucose dynamics inference.

One primary focus in multimodal feature extraction is to find the representations of individual modalities that are maximally correlated. As a well-known measure of dependence, the Hirschfeld-Gebelein-Rényi (HGR) maximal correlation be-´ comes an appealing objective because of its operational meaning and desirable properties. However, the strict whitening constraints formalized in the HGR maximal correlation limit its application. To address this problem, this paper proposes Soft-HGR, a novel framework to extract informative features from multiple data modalities. Specifically, our framework prevents the “hard” whitening constraints, while simultaneously preserving the same feature geometry as in the HGR maximal correlation. The objective of Soft-HGR is straightforward, only involving two inner products, which guarantees the efficiency and stability in optimization. We further generalize the framework to handle more than two modalities and missing modalities. When labels are partially available, we enhance the discriminative power of the feature representations by making a semi-supervised adaptation. Empirical evaluation implies that our approach learns more informative feature mappings and is more efficient to optimize.

Air pollution has become an important factor constraining city development and threatening public health in recent years. Air pollution prediction has been considered as the key part for the early warning of pollution event. Considering the multi-scale nature of geo-sensory data such as air pollution signal, in this paper we adopt a multi-level graph data structure for better utilization of multi-scale spatio-temporal information. We further present a novel deep convolutional neural network model, named Multi-Scale Spatial Temporal Network (MSSTN), for the learning task on this data structure. The MSSTN is specially designed to better discover multi-scale spatial temporal patterns and their high-level interactions, by explicitly using multi-scale neural network structure in both spatial and temporal component. We conduct extensive experiments and ablation studies on Urban Air Pollution Datasets in North China, where the MSSTN can make hourly PM2.5 concentration predictions jointly for a number of cities. And our results shows an outstanding prediction accuracy as well as high computational efficiency compared to existing works.

Task transfer learning is a popular technique in image processing applications that uses pre-trained models to reduce the supervision cost of related tasks. An important question is to determine task transferability, i.e. given a common input domain, estimating to what extent representations learned from a source task can help in learning a target task. Typically, transferability is either measured experimentally or inferred through task relatedness, which is often defined without a clear operational meaning. In this paper, we present a novel metric, H-score, an easily-computable evaluation function that estimates the performance of transferred representations from one task to another in classification problems using statistical and information theoretic principles. Experiments on real image data show that our metric is not only consistent with the empirical transferability measurement, but also useful to practitioners in applications such as source model selection and task transfer curriculum learning.

Multilabel learning, the problem of mapping each data instance to a subset of labels, appears frequently in many real-world applications. However, obtaining complete label annotation for every instance requires tremendous efforts, especially when the label set is large. As a result, multilabel learning with missing labels remains as a common challenge. Existing works either cannot handle missing labels or lack nonlinear expressiveness and scalability to large label set. In this paper, we present a novel end-to-end solution for multilabel learning with missing labels. Our algorithm, Maximal Correlation Embedding Network learns a low dimensional label embedding using an encoder-decoder architecture. It exploits label similarity through a maximal correlation regularization in the embedded label space to reduce the classification bias due to missing labels. A series of experiments on popular multilabel datasets demonstrate that our approach outperforms state of the art, both in complete data and partially observed data.

Multimodal emotion recognition is important for facilitating efficient interaction between humans and machines. To better detect emotional states from multimodal data, we need to effectively extract both the common information that captures dependencies among different modalities, and the private information that characterizes variations in each modality. However, existing works are mostly designed to pursue either one of these objectives but not both. In our work, we propose an end-to-end learning approach to simultaneously extract the common and private information for multimodal emotion recognition. Specifically, we use a correlation loss based on Hirschfeld-Gebelein-Renyi (HGR) maximal correlation and a reconstruction loss based on autoencoders to preserve the common and private information, respectively. Experimental results on eNTERFACE'05 database and RML database demonstrate the effectiveness of our proposed approach.

Real-time human context recognition is one of the most exciting emerging technologies in sensing nowadays. Compared with most recognition problems in machine learning, the challenge lies in the complexity and incompleteness of labels, in other words, each sample can have several label concepts simultaneously but some of them could be missing. This poster proposes an effective approach for multilabel human context recognition with signals from sensors embedded in the wearable devices. The proposed algorithm demonstrates to be very robust to incomplete labels.

Unsupervised anomaly detection is a fundamental problem in various research areas and application domains, namely the discrimination of abnormal samples from normal samples where training data are only composed of one class (normal) while testing data contains both among which the majority are normal samples. However, previous works can not effectively fit the distribution of high dimensional data and suffers from low AUC scores which measures the classification performance of imbalanced data. To solve these problems, we propose an unsupervised anomaly detection model based on GAN, i.e., UAD-GAN. Specifically, we adopt transfer learning to extract visual features with pre-trained Inception-v3 model and use the discriminator to detect anomalies. UAD-GAN can fit the data distribution and detect anomalies efficiently. Extensive experiments show that UAD-GAN achieves state-of-the-art performance compared to other approaches.

Air pollution is a serious urban problem that threatens human health. Therefore, fine-grained pollution events detection has become a concerned issue for environmental management. Algorithms in previous studies identify pollution events as uptrend intervals at hour level. However, a significant part of pollution events caused by traffic and industry can be brief but frequent, which may be neglected under traditional coarse-grained detection. In this paper, we propose a fine-grained analysis of air pollution pattern based on minute-level event detection. Over the real-world deployment in Foshan, these events are analyzed according to their geographical contexts and temporal features. Results show insightful findings and this case study provides a practical reference for government inspection and pollution control.

Anomaly detection is an important area for both research and real-world applications. In the surface mounting technology (SMT) process, the defectives of solder paste printing need to be detected immediately or it may cause great effort for recycling and slow down the whole process. In this paper, we propose a novel model, MM-DNN, for anomaly detection with multi-modal data. We collect a multi-modal dataset from different sensors in the factory. Our method efficiently extracts both predictive features for classification and correlative features between multi-modal data to achieve a higher detection rate. As shown in the experiment, our method can further reduce 77% false alarm rate of the detection result in the factory while keeping 95% of real defectives be correctly detected.

Mobile sensor networks are widely deployed for air quality monitoring. However, fine-grained pollution inference based on these systems is challenging. Specifically, diverse geospatial attributes in urban areas bring great spatial variations of the pollution field. Besides, the preprocessing on raw samples, such as discretization and averaging, leads to the lost of fine-grained information of mobile sensing. In this paper, we propose an inference algorithm with the attention mechanism to better capture high-frequency information in the pollution field. Furthermore, we introduce the sensing gradients in the attention network to utilize the high-granularity information from the mobile sensors. Evaluations on real-world dataset show that our model outperforms the state-of-the-art method by 13.15% ~ 27.04%.

The surveillance of air pollution is becoming a highly concerned issue for city residents and urban administrators. Fixed air quality stations as well as mobile gas sensors have been deployed for air quality monitoring but with sparse observations over the entire temporal-spatial space. Therefore, an inference algorithm is essential for comprehensive fine-grained air pollution sensing. Conventional physically-based models can hardly be applied to all the scenarios, while pure data-driven methods suffer from sampling bias and overfitting problems. This paper presents a hybrid algorithm for air pollution inference by guiding the data learning process with physical model. The quantitative combination of knowledge from observed dataset and a discretized convective-diffusion model is performed within a multi-task learning scheme. Evaluations show that, benefited from physical guidance, our hybrid method obtains higher extrapolation ability and more robustness, achieving the same performance with 1/8 sample amount and obtaining 31.9% less error in noisy synthesized environment. In a real-world deployment in Tianjin, our algorithm outperforms the pure data-driven model with 9.69% less inference error over a 9-day PM2.5data collection.

Direct localization using antenna-array systems outperforms two-step localization algorithms by jointly processing all the measurements observed at base stations. However, it incurs high communication cost especially when the arrays have a large number of antennas. Local computing can offload such communication traffic by signal preprocessing and data compression at local platforms. In this paper, we propose beamspace design methods that can provide the best localization accuracy under communication constraints. We first derive the performance limits of beamspace direct localization and provide an optimal beamspace design with lossless signal compression.We then prove that two beams are sufficient for direct localization, regardless of the antenna numbers. Moreover, we propose a robust formulation for beamspace design in the presence of agent position uncertainty and quantify the performance gap to the ideal scenario. Simulation results validate that the proposed direct localization with low-dimensional beamspace signals can achieve near-optimal performance.

In this paper, we formulate the generalized softmax learning (GSL) problem, as a symmetric extension of the softmax regression problem. We further study the geometric structure of GSL and demonstrate the equivalence of GSL and the original softmax regression problem. Besides, this geometric structure indicates the symmetry between a neural network and its reverse network, and the symmetric roles of the weights and feature in a neural network. Finally, we present a numerical simulation to verify these symmetry properties in neural networks.

Mobility pattern mining answers the fundamental question of where people are likely to go from a given location. It plays an important role in city planning, public transport management and location-based mobile applications. Among these applications, many concern the mobility pattern over contiguous spatial regions as a whole. Traditional ways of mobility pattern mining either result in trip clusters with overlapped origin and destination regions, or require an extra step to partition the city into discrete regions, which may not be optimal for mobility pattern extraction. In this paper, we present a region-aware mobility pattern mining framework to jointly extract trip clusters while maintaining non-overlapping partitions of trip origins and destinations. We developed kernelized ACE, a novel extension to a classic algorithm in statistics to compute the optimal mobility clusters under spatial constraints. Experimental results using Beijing taxi trip data show that our approach outperforms other methods with only ~ 0.3% spatial overlap and 86.43% origin-destination correlation. Our case studies on New York City's and Beijing's taxi datasets also yield insightful findings that reveal city-scale mobility patterns and propose potential improvement for public transportation.

Time series classification is a critical problem in the machine learning field, which spawns numerous research works on it. In this work, we propose AttLSTM-CNNs, an attention-based LSTM network and convolution network that jointly extracts the underlying pattern among the time-series for the classification. The attention-based LSTM automatically captures the long-term temporal dependency among the series, and the CNN describes the spatial sparsity and heterogeneity in the data. The extensive experiments show that the proposed model outperforms the other methods for time-series classification.

Real-time emotion detection has being attracted to human attention recently. Recognizing the inner emotion not only assists people to communicate and understand with each other, but also prevents the occurrence of the serious diseases (e.g., autism) and the emergency (i.e., child abuse, sexual invasion). Existing works usually adopt the professional and cumbersome devices to learn the emotions, and therefore limited in the daily usage. In this work, we design a pervasive and wearable device E-See that enables to recognize the emotion in real time. The prototype of the device is deployed in a microcomputer currently, and it can be resized as a small button worn on the collar or extend as a platform to detect the real-time emotion.

Mobile sensing systems are deployed for urban air pollution monitoring to increase coverage over a city. However, the sampling irregularity brings great challenges for fine-grained pollution field recovery. To address this problem, we proposed a generative model based inference algorithm. By modeling the air pollution evolution and data sampling process separately, the temporal-spatial correlation of pollution field can be considered with irregular sampled data. We use a convolutional long-short term memory structure in the generative model and train it with the scattered observations from mobile sensing. Evaluations on synthesized data and a deployment in the city of Tianjin show that our algorithm accurately captures fine-grained PM2.5 pollution patterns and changes. The average inference error is 6.7μg/m3, which achieves 23.8% improvement over existing techniques.

Speech unlocks the huge potentials in emotion recognition. High accurate and real-time understanding of human emotion via speech assists Human-Computer Interaction. Previous works are often limited in either coarse-grained emotion learning tasks or the low precisions on the emotion recognition. To solve these problems, we construct a real-world large-scale corpus composed of 4 common emotions (i.e., anger, happiness, neutral and sadness). We also propose a multi-task attention-based DNN model (i.e., MT-A-DNN) on the emotion learning. MT-A-DNN efficiently learns the high-order dependency and non-linear correlations underlying in the audio data. Extensive experiments show that MT-A-DNN outperforms conventional methods on the emotion recognition. It could take one step further on the real-time acoustic emotion recognition in many smart audio-devices.

Air pollution in a city is the major environmental risk to health. Mobile sensing has become a popular solution in recent years. However, it still suffers from problems such as lack of data and high system uncertainty. This is because that the data amount and distribution vary over time. To address the problems, this paper combines two classic data driven models -- Kriging and Inverse Distance Weighting (IDW). We adopt the Random Forest Algorithm (RF) to adaptively choose the more accurate models (Kriging or IDW) according to the features we extracted. The experiment based on real world testbed shows our adaptive method achieves up to 30.6% error reduction.

Emotion recognition technologies have been widely used in numerous areas including advertising, healthcare and online education. Previous works usually recognize the emotion from either the acoustic or the visual signal, yielding unsatisfied performances and limited applications. To improve the inference capability, we present a multimodal emotion recognition model, EMOdal. Apart from learning the audio and visual data respectively, EMOdal efficiently learns the common and modality-specific information underlying the two kinds of signals, and therefore improves the inference ability. The model has been evaluated on our large-scale emotional data set. The comprehensive evaluations demonstrate that our model outperforms traditional approaches.

No abstract available.

Understanding human drivers' behavior is critical for the self-driving cars, and has been intensively studied in the past decade. We exploit the widely available camera and motion sensor data from car recorders, and propose a hybrid method of recognizing driving events based on the random forest approach. The classification results are analyzed by comparing different features, classifiers and filters. A high accuracy of 98.1% on driving behavior classification is obtained and the robustness is verified on a dataset including 2400 driving events.

The accelerating urbanization procedure is putting increasing pressure on the management of cities. The administrative zones by which a city is managed are setup based on historical or political reasons, while the dynamics of people is hardly considered in the context. We exploit the widely available mobility data to divide the urban areas into zones by the joint K-mean clustering in origin and destination spaces. The method is evaluated with the New York City and Shenzhen taxi data, and the created zones are compared with the current static zoning plans of the city to evaluate the effectiveness.

E-Loc is an indoor localization system, which, through using existing indoor electric wiring, detects occupants' location. While many indoor localization technologies require intensive infrastructural supports, E-Loc obtain locations by injecting a signal into the protected earth line of existing residential power network. Caused by human body inside a room, the electromagnetic character changes can be detected to deduce a resident's location. We evaluate our system through experiments inside multiple rooms and our system is able to reach meter-level accuracy.

In this paper, we model the unsupervised learning of a sequence of observed data vector as a problem of extracting joint patterns among random variables. In particular, we formulate an information-theoretic problem to extract common features of random variables by measuring the loss of total correlation given the feature. This problem can be solved by a local geometric approach, where the solutions can be represented as singular vectors of some matrices related to the pairwise distributions of the data. In addition, we illustrate how these solutions can be transferred to feature functions in machine learning, which can be computed by efficient algorithms from data vectors. Moreover, we present a generalization of the HGR maximal correlation based on these feature functions, which can be viewed as a nonlinear generalization to linear PCA. Finally, the simulation result shows that our extracted feature functions have great performance in real-world problems.

Detecting dangerous riding behaviors is of great importance to improve bicycling safety. Existing bike safety precautionary measures rely on dedicated infrastructures that incur high installation costs. In this work, we propose BikeMate, a ubiquitous bicycling behavior monitoring system with smartphones. BikeMate invokes smartphone sensors to infer dangerous riding behaviors including lane weaving, standing pedalling and wrong-way riding. For easy adoption, BikeMate leverages transfer learning to reduce the overhead of training models for different users, and applies crowdsourcing to infer legal riding directions without prior knowledge. Experiments with 12 participants show that BikeMate achieves an overall accuracy of 86.8% for lane weaving and standing pedalling detection, and yields a detection accuracy of 90% for wrong-way riding using crowdsourced GPS traces.

Predicting blood glucose dynamics is vital for people to take preventive measures in time against health risks. Previous efforts adopt handcrafted features and design prediction models for each person, which result in low accuracy due to ineffective feature representation and the limited training data. This work proposes MT-LSTM, a multi-time-series deep LSTM model for accurate and efficient blood glucose concentration prediction. MT-LSTM automatically learns feature representations and temporal dependencies of blood glucose dynamics by jointly sharing data among multiple users and utilizes an individual learning layer for personalized prediction. Evaluations on 112 users demonstrate that MT-LSTM significant outperform conventional predictive regression models.

In this paper, given the scenario of a mobile sensing system for air pollution monitoring, we aim at the cause and influence of delay effect on measurement and present a filter-based solution to calibrate the sensing data. We also validate the idea and solution by a real-data experiment. It indicates that the solution decreases deviation on spatial measurement and can be applied in mobile sensing systems to improve the sensing data quality.

Low-cost sensors are widely used to realize large-scale deployment for sensing systems. In this paper, we discuss challenges in using industrial-grade gas sensors for air quality monitoring. To overcome variation due to system errors, we present a framework for individualized calibration. Within the framework, multiple regression and interpolation methods are prepared for alternative optimization on fitting sensors' response to gas concentration.

Recent developments of smart devices and mobile applications have significantly increased the level at which human users interact with mobile systems. As a result, human activities, usage behavior, and perceived experience of users weigh increasingly on the performance of mobile networks, which has created new challenges for system operation in various aspects, such as increasing uncertainty, selfishness in operations, and complicated performance evaluation. On the other hand, the strong engagement of a large population of human users makes it possible to take advantage of the unique features of human behavior and to leverage the computing powers owned by users. Due to these emerging features of mobile networks, their design and evaluation require a hybrid view of human factor and information technology, and a paradigm shift is required for designing a new human-in-the-loop architecture by actively learning, adapting, and steering user behavior, so as to exploit the human factor in future ubiquitous mobile systems, and to greatly enhance system efficiency and provide superior quality-of-experience to users. The goal of this survey is to summarize recent results that focus on understanding and exploiting the human factor in mobile networks. In the tutorial, we summarize and discuss novelties of these formulations, adopted methodologies, and interesting results. We also point out some future research directions.

Metro has become the first choice of traveling for tourists and citizens in metropolis due to its efficiency and convenience. Yet passengers have to rely on metro broadcasts to know their locations because popular localization services (e.g. GPS and wireless localization technologies) are often inaccessible underground. To this end, we propose MetroEye, an intelligent smartphone-based tracking system for metro passengers underground. MetroEye leverages low-power sensors embedded in modern smartphones to record ambient contextual features, and infers the state of passengers (Stop, Running, and Interchange) during an entire metro trip using a Conditional Random Field (CRF) model. MetroEye further provides arrival alarm services based on individual passenger state, and aggregates crowdsourced interchange durations to guide passengers for intelligent metro trip planning. Experimental results within 6 months across over 14 subway trains in 3 major cities demonstrate that MetroEye yields an overall accuracy of 80.5% outperforming the state-of-the-art.

This paper presents a hybrid adaptive particle filter (HAP) with online feedback to dynamically reconstruct high spatial-temporal resolution air pollution information from sparse vehicular based sensors. To deal with data sparsity, we apply both spatial and temporal correlation of air dispersion to reduce data dimension requirement. HAP adaptively predicts when the accumulated prediction error is low and then uses data compensation for correction whenever the prediction error becomes high. The preliminary results based on the city scale deployments with 10 taxis show that our system achieves up to 50% reduction on system errors.

Resilient localization and navigation for autonomous Unmanned Aerial Vehicles (UAVs) still remains a challenge in certain scenarios, like GPS-deprived environments such as indoors or urban canyons. In this work, we explore a heterogeneous UAV swarm design, in which a small number of sensor and computationally powerful UAVs collaborate with the remaining resource-constrained UAVs to guarantee optimal localization accuracy.

According to the World Health Organization (WHO), outdoor air pollution led to an estimated 3.7 million premature deaths worldwide in 2012. To address this problem, it is necessary for both residents and city administrations to understand air quality in their immediate environment with fine-grained temporal-spatial resolution. Currently both fixed and mobile systems are used to attempt to sense the pollution field. However, they generally are expensive, cover small areas and thus result in lower accuracy.

No abstract available.

The deployment of charging infrastructures is a key factor for the operation of electric taxis in urban area. This paper focuses on the operational efficiency and the charging convenience of electric taxis, and introduces a two-step optimization process of the charging station location for electric taxis. We propose a modified k-means clustering method to divide the urban area into multiple service regions according to the market demand distribution. Then we utilize the optimal location model in the service region to calculate the optimal sites of the charging stations to maximize the operational efficiency and charging convenience. We collect GPS data of electric taxis in Shenzhen and examine the behavior of our proposed approach. Numerical results suggest that the proposed approach outperforms the traditional particle swarm optimization (PSO) method and has improved the operational efficiency by 14.03% and reduced the average distance for the charging service by 12.30% compared with the actual physical sites.

PM2.5 is one of the major ambient air pollutants to threaten our health in urban area. However, there are only a few air monitoring stations in a city, which make it difficult to precisely measure PM2.5 concentration at the place without installation of air monitor. In this paper, we consider the PM2.5 inference problem and propose a model taking the PM2.5 nonlinear characteristic into account based on support vector machine (SVM). We collect the features of meteorology, geographical locations and PM2.5 indexes observed by air monitoring stations. Unlike the previous work, we add points of interest (POIs) feature and reduce its dimension by latent Dirichlet allocation (LDA) model due to its sparsity and adopt wavelet decomposition to improve the inference accuracy. Numerical results show that the proposed approach outperforms other related methods in terms of RMSE, correlation coefficient and mean absolute error (MAE) with the real value.

The Chinese Spring Festival travel season (Chunyun) has been called the largest annual human migration in the world with approximately 3.6 billion trips in 2014. Understandably, all forms of transportation are stressed at or near saturation during this period and many people, especially lower-income individuals fail to get to their destinations. We present CountryRoads, a ridesharing system to address the transportation shortage during Chunyun. The CountryRoads system collects users' route information, and matches drivers and passengers as an online bipartite matching problem based on the proximity of the passenger's origin and destination and the route of the driver. The system is evaluated during four Chunyun periods from 2012 to 2015 with up to 17272 users and forms 4777 ridesharing tuples in 2015.

Urban environment has significant impacts on the health of city dwellers. To understand these impacts, city planners have to obtain fine-grained environmental information, however such information is not available with traditional environmental systems. To address this problem, we present Gotcha, a taxi-based mobile sensing system for fine-grained environmental data acquisition. Gotcha utilizes taxi cabs to serve as a sensor that collects a variety of environmental information (such as concentrations of carbon-dioxide, carbon-monoxide, ozone, particulate matter, etc.). We aim to deploy our system in the city of Shenzhen on a fleet of 100 taxi cabs, and we present here our results from our initial deployment.

Topology-transparent scheduling algorithms can work well in mobile ad hoc networks, since they are oblivious to the network topology changes and can provide throughput and delay guarantees. Recently, it has been shown that topology-transparent algorithms can provide comparable or even better performance, compared to topology-dependent algorithms. However, most existing topology-transparent scheduling algorithms are designed for single channel networks and few work have been done in multi-channel (MC) networks. In this paper, we focus on broadcasting and propose a distributed multi-channel topology-transparent broadcast scheduling algorithm. In our algorithm, each node randomly selects one or several subchannels to transmit and utilizes both assigned and unassigned slots efficiently. We study the performance of our algorithm analytically and obtain the optimal number of selected subchannels that maximizes the throughput. The simulation results show that our proposed algorithm outperforms existing multi-channel topology-transparent broadcast scheduling algorithms dramatically. More importantly, our work answers the question “Will dividing the spectrum into subchannels lead to a better network performance?” under different network configurations.

Disseminating shared information to many vehicles could incur significant access fees if it relies only on unicast cellular communications. We consider the problem of efficient content dissemination over a vehicular network, in which vehicles are equipped with two kinds of radios: a high-cost low-bandwidth, long-range cellular radio, and a free high-bandwidth short-range radio. We formulate and solve an optimization problem to maximize content dissemination from the infrastructure to vehicles within a predetermined deadline while minimizing the cost associated with communicating over the cellular connection. We examine numerically the tradeoffs between cost, delay and system utility in the optimum regime. We find that, in the optimum regime, (a) system utility is more sensitive to the cost budget when the allowed delay for the dissemination is not large, (b) the system requires relatively smaller cost budget as more vehicles participate and more delay is allowed, (c) when the cost is very important, it is better not to spread the content if it needs small delay. We also develop a polynomial-time algorithm to obtain the optimal discrete solution needed in practice. Finally, we verify our analysis using real GPS traces of 632 taxis in Beijing, China.

Recent advances in the physical layer have enabled wireless devices to have multiple packet reception (MPR) capability, which is the capability of decoding more than one packet, simultaneously, when concurrent transmissions occur. In this paper, we focus on the interaction between the MPR physical layer and the medium access control (MAC) layer. Some random access MAC protocols have been proposed to improve the network performance by exploiting the powerful MPR capability. However, there are very few investigations on the schedule-based MAC protocols. We propose a novel m-MPR-l-code topology-transparent scheduling ((m, l)-TTS) algorithm for mobile ad hoc networks with MPR, where m indicates the maximum number of concurrent transmissions being decoded, and l is the number of codes assigned to each user. Our algorithm can take full advantage of the MPR capability to improve the network performance. The minimum guaranteed throughput and average throughput of our algorithm are studied analytically. The improvement of our (m, l)-TTS algorithm over the conventional topology-transparent scheduling algorithms with the collision-based reception model is linear with m. The simulation results show that our proposed algorithm performs better than slotted ALOHA as well.

The wide deployment of GPS devices has generated gigantic datasets of pedestrian and vehicular trajectories. These datasets offer great opportunities for enhancing our understanding of human mobility patterns, thus benefiting many applications ranging from location-based services (LBS) to transportation system planning. In this work, we introduce the notion of pathlet for the purpose of compressing and planning trajectories. Given a collection of trajectories on a roadmap as input, we seek to compute a compact dictionary of pathlets so that the number of pathlets that are used to represent each trajectory is minimized. We propose an effective approach whose complexity is linear in the number of trajectories. Experimental results show that our approach is able to extract a compact pathlet dictionary such that all trajectories can be represented by the concatenations of a few pathlets from the dictionary. We demonstrate the usefulness of the learned pathlet dictionary in route planning.

We present a robust method for solving the map matching problem exploiting massive GPS trace data. Map matching is the problem of determining the path of a user on a map from a sequence of GPS positions of that user --- what we call a trajectory. Commonly obtained from GPS devices, such trajectory data is often sparse and noisy. As a result, the accuracy of map matching is limited due to ambiguities in the possible routes consistent with trajectory samples. Our approach is based on the observation that many regularity patterns exist among common trajectories of human beings or vehicles as they normally move around. Among all possible connected k-segments on the road network (i.e., consecutive edges along the network whose total length is approximately k units), a typical trajectory collection only utilizes a small fraction. This motivates our data-driven map matching method, which optimizes the projected paths of the input trajectories so that the number of the k-segments being used is minimized. We present a formulation that admits efficient computation via alternating optimization. Furthermore, we have created a benchmark for evaluating the performance of our algorithm and others alike. Experimental results demonstrate that the proposed approach is superior to state-of-art single trajectory map matching techniques. Moreover, we also show that the extracted popular k-segments can be used to process trajectories that are not present in the original trajectory set. This leads to a map matching algorithm that is as efficient as existing single trajectory map matching algorithms, but with much improved map matching accuracy.

Although the techniques of cooperative transmission have been developed for terrestrial sensor networks in recent years to improve the bit‐error‐rate (BER) performance, the unique characteristics of the underwater acoustic communication channel, such as large and variable propagation delay and the three‐dimensional network topology, make it necessary to reconsider the implementation and analysis of cooperative transmission in underwater acoustic networks. In this study, two asynchronous forwarding schemes, namely underwater amplify‐and‐forward (UAF) and underwater decode‐and‐forward (UDF), are proposed. Although the fading model for underwater channel is complex and there is still no consensus in the research community on a model which is applicable for all underwater channels, the authors simulation results show that both UDF and UAF have better performance than direct transmission under different underwater channel configurations, and there is a breathing effect for BER performance improvement caused by underwater multi‐path fading. Finally, some insights on choosing the proper parameters to improve performance of underwater cooperative transmission are provided.

Energy harvesting sensor nodes based on real nonvolatile processors are demonstrated to show the desirable characteristics of those systems, such as no battery, zero stand-by power, microsecond-scale sleep and wake-up time, high resilience to random power failures and fine-grained power management. Furthermore, we show its applications to a distributed moving object detection system, one of novel nonvolatile computing systems.

Cities have long been considered as complex entities with nonlinear and dynamic properties. Pervasive urban sensing and crowd sourcing have become prevailing technologies that enhance the interplay between the cyber space and the physical world. In this paper, a spectral graph based manifold learning method is proposed to alleviate the impact of noisy, sparse and high-dimensional dataset. Correlation analysis of two physical processes is enhanced by semi-supervised machine learning. Preliminary evaluations on the correlation of traffic density and air quality reveal great potential of our method in future intelligent evironment study.

Distributed faulty node detection and isolation in metropolitan-area delay-tolerant vehicular sensor networks are investigated in this paper. For the intermittently connected large-scale dynamic networks, we design a practical faulty node detection algorithm that vehicles can perform on board to detect faulty sensors by utilizing the local data's spatial correlation. Based on the distributed detection algorithm, a faulty node isolation scheme is proposed to control the diffusion of the faulty data. The parameters of the detection and isolation algorithms to achieve the best performance are investigated based on simulations over real-world data sets. The results show that our detection algorithm performs almost as well as other relative algorithms but demands much less on sensors' communication ability. More than 70 percent of faulty nodes can be identified, and more than half of the faulty data can be reduced in the network by the means of isolation while the total overhead decreases by 35%.

Energy saving is the main goal in most building energy monitoring applications. These systems, however, are operated by people. For this reason, an intuitive user interface is an essential element that will affect users' data understandability, thereby determining the system's usability. Traditional energy monitoring generally focuses on getting energy information by utilizing graphs or static text interfaces. However, these approaches are not related to the physical space. With the increase of information in energy monitoring systems, intuitive and efficient ways of displaying information are needed. In this demo, we present iCEnergy, a vision-based mobile information interface that provides power monitoring using augmented reality. Using existing system data, the system overlays an interactive "energy cloud" over corresponding devices in order to illustrate information about the physical environment. This approach aims to provide users with a comfortable interaction experience through its intuitive information display.

Transmission scheduling is a key problem in mobile ad hoc networks. Many transmission scheduling algorithms have been proposed to maximize the spatial reuse and minimize the time-division multiple-access (TDMA) frame length in mobile ad hoc networks. Most algorithms are dependent on the exact network topology and cannot adapt to the dynamic topology in a mobile wireless network. To overcome this limitation, several topology-transparent scheduling algorithms have been proposed. The slots are assigned to guarantee that there is at least one collision-free time slot in each frame. In this paper, we consider multicast and broadcast, and propose a novel topology-transparent distributed scheduling algorithm. Instead of guaranteeing at least one collision-free transmission, the proposed algorithm guarantees one successful transmission exceeding a given probability, and achieves a much better average throughput. The simulation results show that the performance of our proposed algorithm is much better than the conventional TDMA and other existing algorithms in most cases.

In many signal detection and classification problems, we have knowledge of the distribution under each hypothesis, but not the prior probabilities. This paper is aimed at providing theory to quantify the performance of detection via estimating prior probabilities from either labeled or unlabeled training data. The error or risk is considered as a function of the prior probabilities. We show that the risk function is locally Lipschitz in the vicinity of the true prior probabilities, and the error of detectors based on estimated prior probabilities depends on the behavior of the risk function in this locality. In general, we show that the error of detectors based on the maximum likelihood estimate (MLE) of the prior probabilities converges to the Bayes error at a rate of$n^{-1/2}$, where$n$is the number of training data. If the behavior of the risk function is more favorable, then detectors based on the MLE have errors converging to the corresponding Bayes errors at optimal rates of the form$n^{-(1+\alpha)/2}$, where$\alpha > 0$is a parameter governing the behavior of the risk function with a typical value$\alpha = 1$. The limit$\alpha \rightarrow{} \infty$corresponds to a situation where the risk function is flat near the true probabilities, and thus insensitive to small errors in the MLE; in this case, the error of the detector based on the MLE converges to the Bayes error exponentially fast with$n$. We show that the bounds are achievable no matter given labeled or unlabeled training data and are minimax-optimal in the labeled case.

A Vehicular Sensor Network (VSN) may be used for urban environment surveillance utilizing vehicle- based sensors to provide an affordable yet good coverage for the urban area. The sensors in VSN enjoy the vehicle's steady power supply and strong computational capacity not available in traditional Wireless Sensor Network (WSN). However, the mobility of the vehicles results in highly dynamic and unpredictable network topology, leading to packet losses and distorted surveillance results. To resolve these problems, we propose a cooperative data sensing and compression approach with zero inter-sensor collaboration overhead based on sparse random projections. The algorithm provides excellent reconstruction accuracy for the sensed field, and by taking advantage of the spatial correlation of the data, enjoys much smaller communication traffic load compared to traditional sampling algorithms in wireless sensor networks. Real urban environment data sets are used in the experiments to test the reconstruction accuracy and energy efficiency under different vehicular mobility models. The results show that our approach is superior to the conventional sampling and interpolation strategy which propagates data in an uncompressed form, with 4-5dB gain in reconstruction quality and 21-55% savings in communication cost for the same sampling times.

With the advancement of the sensor network technology and cyber physical systems [2], the merging between the virtual cyber space and the real physical world is bound to happen, which will impact the lifestyle of the human being. The metropolitan area sensor networks, composed of millions of heterogeneous sensors and penetrating every aspect of the city life, provide gigantic amount of real-time information of the city, which makes it possible to reconstruct the real world in an on-line cyber space.

Environmental surveillance applications usually require a long living cycle of sensor nodes, especially when they are powered by non-charged batteries. Inspired by cellular automata, we propose a non-cluster based topology control method to prolong the lifetime of wireless sensor networks. Differing from the traditional cluster-based methods, our approaches lead a special way to maintain longer system lifetime by sacrificing a small proportion of network coverage and connectivity degrees. The demonstration contains both theoretical simulation and system-level experiment, which will be instructive for future study.

We consider the range-based localization with highly insufficient inter-node distance measurements in Wireless Sensor Networks (WSNs). With an error model established, a novel distributed probabilistic localization approach which exploits the network constraints through statistical inference on missing distances is proposed. The advantage of the new approach over traditional methods is proved analytically and further confirmed by extensive simulations.

This paper studies Ranking-Based localization method, which, as a special case of common Range-Based localization methods, statistically estimates node positions using the ranking-order constraints rather than the actual values of network measurements. Through extensive empirical evaluation, the advantages of Ranking-Based approach over traditional Range-Based approaches under extreme network conditions are verified. Ranking-Based approach turns out to be more robust to measurement insufficiency and more immune to measurement noise.

A novel adaptive resource-based probabilistic search algorithm (ARPS) for P2P networks is proposed in this paper. ARPS introduces weighted probabilistic forwarding for query messages according to the node degree distribution and the popularity of the resource being searched. A mechanism is introduced to estimate the popularity and adjust the forwarding probability accordingly such that a tradeoff between search performance and cost can be made. Using computer simulations, we compare the performance of ARPS with several other search algorithms. It is shown that ARPS performs well under various P2P scenarios. ARPS guarantees a success rate above a certain level under all circumstances, and enjoys high and popularity-invariant search success rate.

An energy model for wireless sensor networks based on the cooperative MIMO (multiple-in-multiple-out) technique is proposed, taking into consideration of both the transmission and data aggregation energy. Based on the model, two cooperative wireless sensor network schemes, namely, MIMO approach and SISO (single-in-single-out) approach are compared. It is shown that the overall energy consumption in the systems is related to not only the transmission range but also the correlation among the raw sensor data, and can be solved as a nonlinear programming problem. Furthermore, a critical value above which MIMO approach outperforms SISO approach is analyzed. Simulation results show that jointly considering both data aggregation and cooperative MIMO techniques further reduce the total energy consumption and thus prolong the network lifetime.

This paper addresses the issue of transmission scheduling in multi-channel wireless ad hoc networks. The authors propose a multi-channel time division multiple access (TDMA) scheduling based on edge coloring and algebraic coding theory, called CC-TDMA. The authors categorized the conflicts suffered by wireless links into two types: explicit conflicts and implicit conflicts, and CC-TDMA utilize two different strategies to deal with them. Explicit conflicts are avoided completely by a simple distributed edge-coloring algorithm mu-M, and implicit conflicts are minimized by using coding theory to assign channels to links. The authors evaluate CC-TDMA analytically and numerically, and find that it exhibits a better performance than previous work in terms of throughput and delay.

A novel receiver-initiated soft-state probabilistic multicasting protocol (RISP) for mobile ad hoc network is proposed in this paper. RISP introduces probabilistic forwarding and soft-state for making relay decisions. Multicast members periodically initiate control packets, through which intermediate nodes adjust the forwarding probability. With a probability decay function (soft-state), routes traversed by more control packets are reinforced, while the less utilized paths are gradually relinquished. In this way, RISP can adapt to node mobility; at low mobility, RISP performs similar to a tree-based protocol; at high mobility, it produces a multicast mesh in the network. Simulation results show RISP has lower delivery redundancy than mesh-based protocols, while achieving higher delivery ratio. Further, the control overhead is lower than other compared protocols.

Multicasting protocols deliver data packets from a source node to multiple receivers, and serve a very important function in mobile ad-hoc networks (MANETs). In this paper, a novel receiver-initiated soft-state probabilistic multicasting protocol (RISP) for MANETs is proposed. RISP is inspired by the ant colony's route-seeking mechanism, in which an individual ant chooses the optimal path to its destination through cooperation with others in a totally distributed manner. Imitating the behaviour of ants in nature, RISP introduces probabilistic forwarding and soft-state for making relay decisions that are automatically adaptive to node mobility in MANETs. Compared with other protocols, we show by computer simulations that RISP has lower delivery redundancy, while achieving higher delivery ratio at all mobility scenarios. Furthermore, RISP has lower control overhead.