With the rapid development of 6G and Internet of Vehicles (IoV) technologies, the volume of computation-intensive tasks generated by intelligent vehicles is growing exponentially. Given limited onboard processing capabilities, vehicles increasingly rely on edge servers deployed by service providers (SPs) at roadside units to offload tasks. Vehicle clients can offload the tasks to SPs to mitigate their onboard computation load, while SPs derive economic benefits through the provision of computation resources. However, this interaction introduces a conflict of interest, as vehicles aim to minimize their offloading costs, while SPs seek to maximize revenue. To address this problem, we propose SPOR, a Stackelberg game-based service priority-aware computation offloading and resource pricing scheme in IoV. SPOR is a hierarchical game-theoretic framework in which SPs act as leaders setting prices, while vehicles act as followers determining their offloading strategies. A novel service prioritization function is introduced, incorporating booking price, system load, and reputation to ensure fair and balanced resource allocation. We provide a theoretical proof of the existence and uniqueness of a Nash equilibrium. Extensive experiments on a real-world vehicle edge computing dataset show that SPOR outperforms baseline methods in delay, energy consumption, average load, and task completion rate. Notably, SPOR maintains task completion rates above 97% even under heavy workloads, demonstrating its effectiveness in enhancing system reliability and overall performance.

Inan era of widespread dissemination on social networks, the dissemination of various kinds of fake news has posed a great challenge to social network management. Previous studies on fake news detection rely on the attention mechanism to fuse multi-modal features while ignoring the differences with common sense knowledge, resulting in an increase in the under-detection rate. To address these issues, we propose Knowledge-augmented Dual-Ievel Contrastive learning and subgraph-Guided multi-modal fusion (KDCoG), which aims to improve the accuracy and effectiveness of fake news detection services. Specifically, we extract entity and conceptual information from the text and retrieve common sense knowledge from real-world knowledge graphs to augment multi-modal large language models' visual understanding and generate thorough insights. Moreover, we devise the knowledge-augmented dual-level contrastive learning to better learn and align multi-modal representations. Finally, we design subgraph-guided multi-modal fusion to introduce subgraphs associated with each modality, which can further capture contextual information related to opinions within the relevant modality in fake news. Extensive experiments demon-strate the superiority of our method, representing a significant advancement in the field.

In unmanned aerial systems, especially in complex environments, accurately detecting tiny objects is crucial. Resizing images is a common strategy to improve detection accuracy, particularly for small objects. However, simply enlarging images significantly increases computational costs and the number of negative samples, severely degrading detection performance and limiting its applicability. This paper proposes a Dynamic Pooling Network (DPNet) for tiny object detection to mitigate these issues. DPNet employs a flexible down-sampling strategy by introducing a factor (df) to relax the fixed down-sampling process of the feature map to an adjustable one. Furthermore, we design a lightweight predictor to predict df for each input image, which will be used to decrease the resolution of feature map in backbone. Thus, we achieve input-aware down-sampling. We design an Adaptive Normalization Module (ANM) to make a unified detector well compatible with different dfs. At the same time, we also design a guidance loss to supervise the predictor’s training. DPNet realizes the dynamic allocation of computing resources to trade off detection accuracy and efficiency through this. Experiments on the TinyCOCO and TinyPerson datasets show that our DPNet can save over 35% and 25% GFLOPs, respectively, while maintaining comparable detection performance.The code will be made publicly available.

Remote sensing data from hyperspectral imaging (HSI) and LiDAR provide complementary perspectives for terrain and object analysis. However, existing methods for multimodal data fusion primarily focus on spatial-domain feature alignment, often overlooking the potential of frequency-domain information to enhance classification accuracy. To bridge this gap, we introduce the Frequency-Domain Hierarchical Perception Fusion Network (FHPF-Net), a novel framework for precise classification of remote sensing images. This network leverages both spatial and frequency-domain information, and provides a new perspective for heterogeneous data integration. To extract and utilize frequency-domain features, we propose the HighLow Spectral Separation and Mining (HLSSM) module, which isolates high-frequency details such as edges and textures from low-frequency structural patterns in HSI and LiDAR data. This separation facilitates targeted feature extraction while preserving crucial contextual information. Additionally, we introduce the Hierarchical Superimposed Multi-domain Information Fusion (HSMIF) module, which employs a multi-level fusion strategy to integrate spatial and frequency-domain features, ensuring consistency and complementarity between the two data sources. Finally, we introduce a Learnable Voting Pre-label Fusion (LVPF) strategy to effectively integrate multi-branch outputs, enhancing classification performance and model robustness. The proposed FHPF-Net effectively captures diverse responses across heterogeneous data types, enabling robust classification in complex environments. Extensive experiments demonstrate that our approach significantly outperforms state-of-the-art methods.

In the multi-turn dialogue reasoning task, existing models conduct word-level interaction on the entire context to gather reasoning evidence, which aims to select the logically correct one from the candidate response options. Observing the fact that the salient reasoning evidence usually comes from certain snippets of the whole dialogue session, one promising study direction is to explicitly identify the candidate reasoning contexts correlated with the dialogue reasoning options, called option-related contexts, and then make logical inference among them. However, such option-related contexts are stained with noisy information. As a result, existing models may reason unfairly with biased context and select wrong options. To tackle the context bias problem, in this article, we propose a novel CounterFactual learning framework for Dialogue Reasoning, named CF-DialReas, which mitigates the bias information by subtracting the counterfactual representation from the total causal representation. Specifically, we consider two scenarios, i.e., factual dialogue reasoning where the whole context is available to estimate the total causal representation, and the counterfactual dialogue reasoning, which firstly utilizes three different types of utterance selectors to select option-unrelatedcontext, and then only the option-unrelatedcontext is available to guess the counterfactual representation. Experimental results on two public dialogue reasoning datasets show that the model with our mechanism can obtain higher ranking measures, validating the effectiveness of counterfactual learning of CF-DialReas. Further analysis on the generality of CF-DialReas shows that our counterfactual learning mechanism is generally effective to the widely-used models.

Fine-tuning is widely used as the default algorithm for transfer learning from pre-trained models. Parameter inefficiency can however arise when, during transfer learning, all the parameters of a large pre-trained model need to be updated for individual downstream tasks. As the number of parameters grows, fine-tuning is prone to overfitting and catastrophic forgetting. In addition, full fine-tuning can become prohibitively expensive when the model is used for many tasks. To mitigate this issue, parameter-efficient transfer learning algorithms, such as adapters and prefix tuning, have been proposed as a way to introduce a few trainable parameters that can be plugged into large pre-trained language models such as BERT, HuBERT. In this paper, we introduce the Speech UndeRstanding Evaluation (SURE) benchmark for parameter-efficient learning for various speech processing tasks. Additionally, we introduce a new adapter, ConvAdapter, based on 1D convolution. We show that ConvAdapter outperforms the standard adapters while showing comparable performance against prefix tuning and Low-Rank Adaptation with only 0.94% of trainable parameters.

The local parts of the target are vitally important for robust object tracking. Nevertheless, existing excellent context regression methods involving siamese networks and discrimination correlation filters mostly represent the target appearance from the holistic model, showing high sensitivity in scenarios with partial occlusion and drastic appearance changes. In this paper, we address this issue by proposing a novel part-aware framework based on context regression, which simultaneously considers the global and local parts of the target and fully exploits their relationship to be collaboratively aware of the target state online. To this end, the spatial-temporal measure among context regressors corresponding to multiple parts is designed to evaluate the tracking quality of each part regressor by solving the imbalance among global and local parts. The coarse target locations provided by part regressors are further aggregated by treating their measures as weights to refine the final target location. Furthermore, the divergence of multiple part regressors in each frame reveals the interference degree of background noise, which is quantified to control the proposed combination window functions in part regressors to adaptively filter redundant noise. Besides, the spatial-temporal information among part regressors is also leveraged to assist in accurately estimating the target scale. Extensive evaluations demonstrate that the proposed framework help many context regression trackers achieve performance improvements and perform favorably against state-of-the-art methods on the popular benchmarks: OTB, TC128, UAV, UAVDT, VOT, TrackingNet, GOT-10k, LaSOT.

The fine-grained prediction of traffic anomalies is crucial for Traffic Management Bureau to alleviate congestion and avoid public safety incidents. While in practice, the fine-grained prediction is very challenging due to two issues. 1)Data sparsity. At the fine-grained setting, missing data is inevitable and widespread on spatial and temporal dimension. Existing methods have weak performance as they do not handle missing data properly. 2)Data distribution mutation. At the fine-grained setting, the traffic conditions of adjacent road segments are sometimes completely different, invalidating existing spatiotemporal smoothing-based methods. This paper proposes GMAT-DU, a novel model that aims to predict traffic anomaly from sparse data in fine-grained manner. To solve the first issue, we propose a Decay Unrolling (DU) mechanism to make the model applicable to sparse datasets. The performance will be progressively enhanced by the spatiotemporal unrolling of high-impact neighbors. For the second issue, we combine the meta-features of roads with correlations between roads, which are learnt from road semantic information and historical spatiotemporal data, and make the model focusing on the high-impact neighbors by a Graph Meta-features based ATtention (GMAT) mechanism. Extensive experiments on two real-world datasets validate the effectiveness of our method. The experiment results show the significant advantages against the state-of-the-art models.

Fine-grained urban crime prediction is of great significance to urban management and public safety. Previous crime prediction work has been done at a relatively coarse time granularity, which may suffer from two issues for fine-grained crime prediction. 1)The zero-inflation problemassociated with fine-grained granularity. Crime occurrence is sparse, and when the time granularity becomes finer, it leads to a more sparse prediction label for this problem resulting in the zero inflation problem. 2)Insufficient amount of informationinvolved in crime datasets. When the spatio-temporal granularity becomes smaller, more information from related fields needs to be introduced to extract spatio-temporal features to assist the analysis. To address the first issue, we introduce a classification-labeled continuousization strategy and a weighted loss function for sparse classification problem, making the model more likely to focus on non-zero elements in zero-inflated datasets. For the second issue, we propose a novel deep learning based model, termed attention-based spatio-temporal multi-domain fusion network, which fuses features from multiple datasets in related domains. We evaluate our method on six real-world datasets collected in New York City and experiments on our model show the advantages beyond many competitive baselines.

It is important to minimize the energy consumption of large-scale, geographically distributed edge data centers (EDCs). While modern processing units (PUs) have energy-saving features like Dynamic Voltage and Frequency Scaling (DVFS) and Per-Core Power Gating (PCPG), optimization is still complex and requires a holistic approach. This article presents a new decentralized, three-timescale, online optimization approach that enables multicore micro data centers (MDCs) to optimize their per-PU power states, per-enabled-PU voltage-frequency levels and offloading schedules at three different timescales. The key idea is that we employ multi-timescale Lyapunov optimization to decouple the energy minimization between workload scheduling and result delivery at a small timescale and PU configuration at large timescales. Another important aspect is that we apply the primal decomposition to decouple the PU configuration between a per-enabled-PU voltage-frequency level at an intermediate timescale and a per-PU power state at a large timescale. Experiments demonstrate that the proposed approach improves energy efficiency significantly by up to 4.5 times in our considered lightly loaded situations where DVFS alone does not work effectively, compared to existing benchmarks.

Few-shot relation learning refers to infer facts for relations with a few observed triples. Existing metric-learning methods mostly neglect entity interactions within and between triples. In this paper, we explore this kind of fine-grained semantic meaning and propose our model TransAM. Specifically, we serialize reference entities and query entities into sequence and apply transformer structure with local-global attention to capture intra- and inter-triple entity interactions. Experiments on two public datasets with 1-shot setting prove the effectiveness of TransAM.

Long-term traffic prediction is essential for pre-control of traffic departments, which allows traffic dispatchers to make earlier decisions than short-term traffic prediction. This task is extremely challenging mainly due to the difficulty of obtaining accurate spatial dependency at different time periods and weak correlation between predicted values and historical data for largest time step. Existing methods either use the same adjacency matrix at every moment or recompute a different adjacency matrix at every moment, which may introduce incorrect neighbors to the target node. Moreover, many previous methods either obtain the predicted values step by step, which causes error propagation problem, or obtain the predicted values for each step independently, which loses the correlation information between the multi-step predicted values. In this paper, a Time-varying Adjacency Mask is proposed to correct the spatial dependence which makes spatial dependence different but highly similar at each moment. Besides, a Self-Smoothing Regularization is proposed to establish the relationship between the predicted values of adjacent time slices and to restrict their differential values. Extensive experiments including traditional long-term traffic speed prediction, time-phased speed prediction and rush hour speed prediction are conducted on two real-world datasets, experimental results show the superior performance of our proposed model.

Devamanyu Hazarika, Yingting Li, Bo Cheng, Shuai Zhao, Roger Zimmermann, Soujanya Poria. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2022.

Most of siamese network and correlation filter (CF) based trackers usually employ the context regression scheme to achieve appealing performance in both accuracy and efficiency. However, they are prone to drifting in challenging situations exhibiting occlusion, out-of-view and large-scale variations due to the lack of failure correction ability in these regressors. Particle filter based trackers can help to recover from tracking failures since several particles of high confidence about the target can be remained for the probability estimation of next frames, but need the large numbers of particles for each frame. In this paper, we propose a generic dynamic particle filter framework, which can reasonably control the number of particles in different scenarios, to improve the robustness of siamese and CF trackers by jointing the target classifier to relieve drifting. Our fundamental insight is that general scenarios are processed efficiently by the context regressor with few particles, while special scenarios are handled effectively by the target classifier with many particles. We propose a novel measure to determine whether to adopt the regressor and few particles to estimate target states with high measure scores, or increase the number of particles to prevent drifting with the proposed multi-template matching strategy in the classifier. In extensive experiments on eight large-scale benchmarks including OTB, UAV, TC128, VOT2017, VOT2019, LaSOT, TrackingNet and Got-10k, the proposed framework enables many basic siamese and CF trackers to operate at least over 24 frames per second and achieve superior tracking performance than themself, as well as the comparable accuracy with the state-of-the-art trackers. Furthermore, our framework is flexible and still has great potential for improvement and generalization.

Both siamese network and correlation filter (CF)-based trackers have exhibited superior performance by formulating tracking as a similarity measure problem, where a similarity map is learned by the correlation between a target template and a region of interest (ROI) with a cosine window. Nevertheless, this window function is usually fixed for various targets and not changed, undergoing significant noise variations during tracking, which easily makes model drift. In this article, we focus on the study of a noise-aware (NA) framework for robust visual tracking. To this end, the impact of various window functions is first investigated in visual tracking. We identify that the low signal-to-noise ratio (SNR) of windowed ROIs makes the above trackers degenerate. At the prediction phase, a novel NA window customized for visual tracking is introduced to improve the SNR of windowed ROIs by adaptively suppressing the variable noise according to the observation of similarity maps. In addition, to further optimize the SNR of windowed pyramid ROIs for scale estimation, we propose to use the particle filter to dynamically sample several windowed ROIs with more favorable signals in temporal domains instead of this pyramid ROIs extracted in spatial domains. Extensive experiments on the popular OTB-2013, OTB-50, OTB-2015, VOT2017, TC128, UAV123, UAV123@10fps, UAV20L, and LaSOT datasets show that our NA framework can be extended to many siamese and CF trackers and our variants obtain superior performance than baseline trackers with a modest impact on efficiency.

Question Answering (QA) models over Knowledge Bases (KBs) are capable of providing more precise answers by utilizing relation information among entities. Although effective, most of these models solely rely on fixed relation representations to obtain answers for different question-related KB subgraphs. Hence, the rich structured information of these subgraphs may be overlooked by the relation representation vectors. Meanwhile, the direction information of reasoning, which has been proven effective for the answer prediction on graphs, has not been fully explored in existing work. To address these challenges, we propose a novel neural model, Relation-updated Direction-guided Answer Selector (RDAS), which converts relations in each subgraph to additional nodes to learn structure information. Additionally, we utilize direction information to enhance the reasoning ability. Experimental results show that our model yields substantial improvements on two widely used datasets.

Multi-hop question answering models based on knowledge graph have been extensively studied. Most existing models predict a single answer with the highest probability by ranking candidate answers. However, they are stuck in predicting all the right answers caused by the ranking method. In this paper, we propose a novel model that converts the ranking of candidate answers into individual predictions for each candidate, named heterogeneous knowledge graph based multi-hop and multi-answer model (HGMAN). HGMAN is capable of capturing more informative representations for relations assisted by our heterogeneous graph, which consists of multiple entity nodes and relation nodes. We rely on graph convolutional network for multi-hop reasoning and then binary classification for each node to get multiple answers. Experimental results on MetaQA dataset show the performance of our proposed model over all baselines.

Multiple domain fusion has been widely used for urban anomalies forecasting problem, as urban anomalies such as traffic accidents or illegal assembly are usually caused by many complex factors and they would affect many fields. Although many efforts have been devoted to fusing multiple datasets for anomalies detection, most of the work is to extract the spatio-temporal features one by one from multiple datasets and then fuse to get the result or anomaly score. However, the correlation between data from multiple domains at each moment is ignored, which is especially important when detecting anomalies by analyzing the impacts from multiple datasets. In this paper, we propose a novel end-to-end deep learning based framework, namely deep spatio-temporal multiple domain fusion network to collect the impacts of urban anomalies on multiple datasets and detect anomalies in each region of the city at next time interval in turn. We formulate the problem on a weighted graph and obtain spatiotemporal features with adaptive graph convolution and temporal convolution. In addition, a cross-domain convolution network is applied to fully obtain connection between multiple domains. We evaluate our method with real-world dataset collected in New York City and experiments on our model show the advantages nearly 10% beyond the state-of-the-art urban anomalies detection methods.

The structural information of Knowledge Bases (KBs) has proven effective to Question Answering (QA).Previous studies rely on deep graph neural networks (GNNs) to capture rich structural information, which may not model node relations in particularly long distance due to oversmoothing issue.To address this challenge, we propose a novel framework GlobalGraph, which models long-distance node relations from two views: 1) Node type similarity: GlobalGraph assigns each node a global type label and models long-distance node relations through the global type label similarity; 2) Correlation between nodes and questions: we learn similarity scores between nodes and the question, and model long-distance node relations through the sum score of two nodes.We conduct extensive experiments on two widely used multi-hop KBQA datasets to prove the effectiveness of our method.

Urban anomaly prediction is of great importance for urban management and public safety. Accurate anomaly prediction can avoid much unnecessary loss. Urban anomalies are usually caused by many complex factors, such as festivals, demonstrations and market promotions. It is not possible to predict anomalies from the perspective of reason, thus, most of the previous work analyzes the impacts of anomalies from multiple crowd flow datasets and observes the shift to ordinary distribution when they occur. Most existing models use observation-based methods to extract relevant spatiotemporal features, which are difficult to fully extract hidden relationships and eventually lead to low accuracy and low recall. In this paper, we propose an end-to-end deep learning based approach, called spatiotemporal multi-modal fusion model to collect the impacts of urban anomalies on multiple crowd flow datasets and predict anomalies in each region of the city for next time interval in turn. More specifically, we model the city into a graph and regard each region as a node. We use graph convolution network to obtain its spatial features and use gate recurrent units to obtain its temporal features. The features of those multiple modalities are further aggregated with points of interest in a two-stage-fusion method for assigning different weights to different functional regions. We evaluate our method using five datasets associated with New York City: 311 complaints, taxicab data, bike rental data, points of interest and road network dataset. Results show the advantages nearly 10% beyond the-state-of-the-art urban anomalies prediction methods.

Knowledge-guided conversation models, whose inputs are current input sentence with its background knowledge, make the generation of responses more informative and meaningful. Existing methods assume that words in responses come from the vocabulary of the whole corpus. However, for specific input and knowledge, only a small vocabulary is useful in prediction and other words lead to uncorrelated noise. In this paper, we propose a Dynamic Vocabulary based Knowledge-guided Conversation Model (DVKCM). Inspired by dynamic vocabulary mechanism, DVKCM adopts the vocabulary construction module to allocate the sentence-level vocabulary which relates to the input sentence and background knowledge, and then only uses the small vocabulary to execute the decoding part. Through the sentence-level vocabulary mechanism, we reduce the generation of noise effectively. Experiments on both automatic and human evaluation verify the performance of our model compared with previous models. Moreover, we find that dynamic vocabulary can be applied to other conversation models to improve their performance.

Both siamese network and correlation filter (CF) based trackers have recently achieved superior performance in tracking scenarios with various challenging factors. For the challenging scale variations, most of these state-of-the-art trackers usually employ multiple patches with different bounding boxes to estimate the target size. However, these patches are fixedly generated by the hand-crafted bounding boxes in spatial domains, which may be suboptimal to cope with scale changes due to the lack of temporal scale information. In this letter, we tackle the problem of efficient scale estimation by presenting a generic scheme that allows the adaptive generation of bounding boxes in temporal domains and improves the tracking accuracy. Specifically, we introduce the novel particle scale space by refining the conventional particle filter and extend this space to many siamese and CF trackers for robust tracking. Extensive experiments are performed on the OTB2013, OTB50, OTB100 and UAVDT datasets. The proposed variants maintain at least almost identical frame-rates with baseline trackers and perform favorably against them, as well as other state-of-the-art trackers.

Particle filter algorithms are a very important branch for visual object tracking in the past decades, showing strong robustness to challenging scenarios with partial occlusion and large-scale variations. However, since a large number of particles need to be extracted for the accurate target state estimation, their tracking efficiency typically suffers especially when meeting deep convolutional features, which have been developed for handling significant variations of the target appearance in the visual tracking community. In this paper, we propose to elegantly exploit deep convolutional features with few particles in a novel hierarchical particle filter, which formulates correlation filters as observation models and breaks the standard particle filter framework down into two constituent particle layers, namely, particle translation layer and particle scale layer. The particle translation layer focuses on the object location with the deep convolutional features capturing semantics but failing to precisely estimate the object scale, while the particle scale layer pays attention to large-scale variations with the lightweight hand-crafted features handling spatial details of the object size. Moreover, an efficient ensemble method is proposed to help explore deeper convolutional features with more semantics in the particle translation layer. Extensive experiments on four challenging tracking datasets, including OTB-2013, OTB-2015, VOT2014, and VOT2015 demonstrate that the proposed method performs favorably against a number of state-of-the-art trackers.

Nowadays Telecom service providers are seeking new paradigms of service creation and execution platform to reduce new services' time to market and increase profitability. However, the existing static services orchestration approaches cannot meet the dynamic complicated business demands. This paper proposes a hybrid service orchestration platform for Internet-Telephony networks. Firstly, designs a hybrid service orchestration language for developers to achieve dynamic and rapid orchestration of new hybrid services over the Internet-Telephony networks. Secondly, proposes an event-driven and component-based hybrid service orchestration container to meet the asynchronous dynamic interactions between hybrid services. Thirdly, proposes a cost-aware auto-scaling approach, including the pre-scaling and real-time scaling stages, to dynamically scale the required resources at different levels. Finally, illustrates the hybrid voice chatting services orchestration scenario, and also the effectiveness and practicability of the proposed platform are validated through extensive experiments.

Network Function Virtualization (NFV) is an emerging technology decouples network functions from hardware. Network service in NFV is deployed as a service chain, also known as Service Function Chain (SFC). SFC consists of an ordered set of Virtual Network Functions (VNFs). However, VNFs bring new challenges in providing network services with availability guarantee. In addition, in a customizable and dynamic NFV-enabled network, the composition and mapping of service chain are different from that of a traditional network. In this paper, we define an availability model that takes both hardware and VNF failures into consideration. Then we propose Joint Path-VNF backup model to combine path and VNF backup in a joint way. And a priority-based algorithm is designed for service chain composition and mapping. Simulation results show that our proposed solutions can reduce resource consumption while guaranteeing availability.

Central heating is a sophisticated process, and many factors influence the heating loading for boilers, without comprehensively monitoring and analysis, it is difficult to find out potential hazards of heating supplying electrical equipment. This paper presents the architectural model for OLE process control Web service based real time remote monitoring for central heating electrical equipment, and focus on the development of OPC XML Web service interface, data types, structures and XML message interaction, and the Publish-Subscribe based real time messages dispatching, and the service component architecture based visual configuration software. We also illustrated remote monitoring and control scenarios for central heating electrical equipment.

With the fast development of Internet of Things (IoT), a large amount of services are being generated continuously by different business process applications hosted on edge devices. In order to facilitate seamless access and service life cycle management of large, distributed and heterogeneous IoT services, service computing and fog computing have been widely used as the promising technologies. However, an execution environment integrating IoT services into these two technologies is still an open research challenge. In this paper, we proposed a novel service-based fog execution environment to make the business process applications fit in the dynamic IoT service environment. The proposed IoT execution environment promises a full-life cycle management of the IoT services, a low latency response of the edge devices and a distributed execution of the business process applications. An actual running intelligent medical case is given to validate our proposed IoT execution environment.

In order to ensure the safety of ships during the voyage, we need to use the AIS data to find outlying ship trajectories and remind other ships to take the necessary avoidance actions. In the process of ship trajectory outlier detection, on the one hand, the ship trajectory outlier detection model trained on historical data is needed, on the other hand, the requirement for real-time detection should be met. Therefore, this paper designs ship trajectory outlier detection service system based on collaborative computing. The service system can combine the advantages of batch computing framework and stream computing framework. Trajectory data services, real-time annotation service are implemented in stream computing framework, F-DBSCAN outlier detection service, model training service, and model-based outlier detection service are implemented in batch computing framework. Memory database is used to complete data interaction between the two frameworks. The experiment shows that the service system can detect the outlying ship trajectories according to the real-time AIS data while using the outlier detection model.

Correlation-filter-based trackers, showing strong discrimination ability in challenging situations, have recently achieved superior performance in visual tracking. However, because the model treats the tracker's predictions in new frames as training data, the filter can be contaminated by small incorrect predictions, which cause model drift. Particle-filter-based trackers usually produce more accurate results due to the richer image representations used in prediction, but suffer when the environments are complex throughout an image sequence. In this letter, we propose an innovative real-time algorithm, which combines the particle filter with correlation filters in the prediction stage, enabling accurate predictions by the particle filter and alleviating model drift. Moreover, an effective decision fusion strategy is proposed to get more precise object predictions, thus further enhancing the overall tracking performance. Extensive evaluations on the OTB-2013 benchmark demonstrate that the proposed tracker is very promising compared with the state-of-the-art trackers, while operating over 85 frames/s.

Internet of Things (IoT) can provide new value-added service by connecting the physical devices to virtual environments association with their context, and there is also a huge demand in ad hoc services by the end users for IoT applications. By extending mashup concept into IoT applications, we can achieve a novel and more lightweight services creation approach. This paper proposes a lightweight IoT service mashup middleware based on REST-style architecture for IoT applications, and design an uniform sensor devices access and dynamically protocol stack management framework, propose a distributed publish/subscribe based messages distribution service, and situational IoT services mashup approach, which can be integrated easily to create new composite and situational applications, and also apply the REST principles to define an extensible interface to build comprehensive and situational mashup applications. Based on proposed service mashup middleware, the end user can integrate applications and services in a more lightweight manner. We also illustrated the scenarios for RESTful Web service mashups representing for coal mine safety monitoring and control automation. In the experiments, the end-user evaluation has been conducted to evaluate the middleware, and also the performance has been measured and analyzed.

The rapid development of Internet of Things (IoT) attracts growing attention from both industry and academia. IoT seamlessly connects the physical world and cyberspace via various sensors. It is more worth for us to pay attention to the mechanism of the events to work collaboratively rather than those standalone sensors. In this paper, we present a Distributed Event-centric Collaborative Workflows development system for IoT application, called DECW. It supports loosely coupled event-based interaction between processes, which enables real-time response to events from the physical world. Unlike traditional centralized control flow mode, the interaction between processes in DECW is constrained by the event interface. Users could dynamically adjust the interface between processes without modifying the internal logic of the process. In addition, DECW system provides a full lifecycle for the development and operation of the IoT application, including graphical creation of processes, dynamic definition of the process interaction interfaces, logical validation, distributed packaging and deployment, parallel execution, and real-time monitoring and managing the running status of the IoT application.

In some special circumstances, e.g. tsunamis, floods, battlefields, earthquakes, etc., communication infrastructures are damaged or non-existent, as well as unmanned aerial vehicle (UAV) cluster. For the communication between people or UAVs, UAVs or mobile smart devices (MSDs) can be used to construct Mobile Ad Hoc Networks (MANETs), and Multipath TCP (MPTCP) can be used to simultaneously transmit in one TCP connection via multiple interfaces of MSDs. However the original MPTCP subpaths creating algorithm can establish multiple subpaths between two adjacent nodes, thus cannot achieve true concurrent data transmission. To solve this issue, we research and improve both the algorithm of adding routing table entries and the algorithm of establishing subpaths to offer more efficient use of multiple subpaths and better network traffic load balancing. The main works are as follows: (1) improve multi-hop routing protocol; (2) run MPTCP on UAVs or MSDs; (3) improve MPTCP subpaths establishment algorithm. The results show that our algorithms have better performance than the original MPTCP in achieving higher data throughput.

In some special circumstances, e.g. tsunamis, floods, battlefields, earthquakes, etc., communication infrastructures are damaged or non-existent, as well as unmanned aerial vehicle (UAV) cluster. For the communication between people or UAVs, UAVs or mobile smart devices (MSDs) can be used to construct Mobile Ad Hoc Networks (MANETs), and Multipath TCP (MPTCP) can be used to simultaneously transmit in one TCP connection via multiple interfaces of MSDs. However the original MPTCP subpaths creating algorithm can establish multiple subpaths between two adjacent nodes, thus cannot achieve true concurrent data transmission. To solve this issue, we research and improve both the algorithm of adding routing table entries and the algorithm of establishing subpaths to offer more efficient use of multiple subpaths and better network traffic load balancing. The main works are as follows: (1) improve multi-hop routing protocol; (2) run MPTCP on UAVs or MSDs; (3) improve MPTCP subpaths establishment algorithm. The results show that our algorithms have better performance than the original MPTCP in achieving higher data throughput.

Customizable mobile services are usually expressed with complex services composed of different atomic services. Fine-grained atomic mobile services are not so convenient for end users to reuse. Considering that in identical or similar service domains, a great deal of the business logics and functions are reusable within the scope. So we present a template-based framework to allow reuse of services and to achieve rapid mobile application development. The reusable fine-grained service logics and functions are encapsulated into comparatively coarse-grained templates, from which the designers can create the personalized composite services and edit the templates efficiently.

Recently, the frequent coal mine safety accidents have caused serious casualties and huge economic losses. It is urgent for the global mining industry to increase operational efficiency and improve overall mining safety. This paper proposes a lightweight mashup middleware to achieve remote monitoring and control automation of underground physical sensor devices. First, the cluster tree based on ZigBee Wireless Sensor Network (WSN) is deployed in an underground coal mine, and propose an Open Service Gateway initiative (OSGi)-based uniform devices access framework. Then, propose a uniform message space and data distribution model, and also, a lightweight services mashup approach is implemented. With the help of visualization technology, the graphical user interface of different underground physical sensor devices could be created, which allows the sensors to combine with other resources easily. Besides, four types of coal mine safety monitoring and control automation scenarios are illustrated, and the performance has also been measured and analyzed. It has been proved that our lightweight mashup middleware can reduce the costs efficiently to create coal mine safety monitoring and control automation applications.

In recent years, Web service discovery has been a hot research topic. In this paper, we propose a novel Web services discovery approach, which can mine the underlying semantic structures of interaction interface parameters to help users find and employ Web services, and can match interfaces with high precision when the parameters of those interfaces contain meaningful synonyms, abbreviations, and combinations of disordered fragments. Our approach is based on mining the underlying semantics. First, we propose a conceptual Web services description model in which we include the type path for the interaction interface parameters in addition to the traditional text description. Then, based on this description model, we mine the underlying semantics of the interaction interface to create index libraries by clustering interaction interface names and fragments under the supervision of co-occurrence probability. This index library can help provide a high-efficiency interface that can match not only synonyms but also abbreviations and fragment combinations. Finally, we propose a Web service Operations Discovery algorithm (OpD). The OpD discovery results include two types of Web services: services with “Single” operations and services with “Composite” operations. The experimental evaluation shows that our approach performs better than other Web service discovery methods in terms of both discovery time and precision/ recall rate.

Modern Internet of Things (IoT)-aware business processes include various geographically dispersed sensor devices. Large amounts of raw data acquired from sensors need to be regularly transmitted to the targeted processes in enterprise data centers, resulting in a significant increase in network load and latency. It is necessary to execute such processes in a distributed way. The existing work has proposed different algorithms to partition a given process for distributed execution; however, they cannot satisfy the decentralized nature of IoT-aware business processes. Moreover, up to now, there is few work that studies uncertain optimal deployment problems in which traffic data for guiding subsequent deployment derives from experts' empirical knowledge. This paper proposes a novel location-based fragmentation algorithm and α-optimal deployment solution to deal with the mentioned problems, where α is the given confidence level. A hardware-in-the-loop simulation platform based on NS-3 was built. Based on this platform, an integrated monitoring process was deployed that ran on different virtual computers, and process fragments communicated with each other via a simulated network. The experimental results show that the proposed approach can reduce network traffic and round-trip time.

The Internet of Things (IoT) infrastructure with numerous diverse physical devices are growing up rapidly, which need a dynamic services coordination approach that can integrate those heterogeneous physical devices into the context-aware IoT infrastructure. This paper proposes a situation-aware dynamic IoT services coordination approach. First, focusing on the definition of formal situation event pattern with event selection and consumption strategy, an automaton-based situational event detection algorithm is proposed. Second, the enhanced event-condition-action is used to coordinate the IoT services effectively, and also the collaboration process decomposing algorithm and the rule mismatch detection algorithms are proposed. Third, the typical scenarios of IoT services coordination for smart surgery process are also illustrated and the measurement and analysis of the platform's performance are reported. Finally, the conclusions and future works are given.

This paper proposes a novel Web service discovery approach that depend on the mining the underlying semantic structures of interaction interface parameters, which can match interfaces with high precision when the parameters of those interfaces contain meaningful synonyms, abbreviations, and combinations of disordered fragments. Especially, we propose a conceptual Web services description model in which we include the type path for the interaction interface parameters in addition to the traditional text description. Then, based on this description model, we mine the underlying semantics of the interaction interface to create index libraries by clustering interaction interface names and fragments under the supervision of co-occurrence probability. Finally, we propose a Web service Operations Discovery algorithm (OpD) that support the “Single” operations and services with “Composite” operations discovery. The experimental shows that our approach performs better than other approaches in terms of both discovery time and precision.

Applications in Android often have the ability of accessing sensitive resources on mobile devices. These resources have different levels of security and usage constraint in scenarios which have different requirements for privacy. Therefore, it is in demand for users to have fine-grained privacy protection and resources usage constraint that taking the context information into account, which is not supported by inherent access control mechanism of Android. To address these issues, we designed and implemented an enhanced context-aware adaptive access control system (EasyGuard) in Android to provide adaptive access control automatically when the specific context is detected according to the pre-configured policies. In addition, we developed an application to facilitate users that have little domain knowledge in android to configure policies reasonably. Experimental results show that users can easily protect their privacy, security and save energy of mobile devices through this system.

In some special circumstances, such as earthquakes, tsunamis and floods, etc. Infrastructure communication facilities are damaged, all communications are interrupted. For the communication between peoples, Android smartphones can be used to construct Mobile Ad Hoc Networks (MANETs). To improve the work efficiency, it is necessary to run the Information Systems (Android Applications) in MANETs, therefore the distribution of information becomes convenient. However, it is very hard to get a real MANET environment to test Android Applications, and so far, we have not found any MANETs simulation environments which can be used to test actual Android Applications. Therefore, we propose a Simulation Experimental Environment for Android Applications in MANETs (SEEM). The test results show that the SEEM is practicable to test Android Applications in MANETs. We believe that the SEEM will be beneficial to the researchers and developers who need to develop and test actual Android Applications in MANETs.

Internet of Things (IoT) technology demands a complex, lightweight distributed architecture with numerous diverse components, including end devices and applications adapted for specific contexts. This paper proposes a situation-aware IoT services coordination platform based on the event-driven service-oriented architecture (SOA) paradigm. Focus is placed on the design of an event-driven, service-oriented IoT services coordination platform, for which we present a situational event definition language (SEDL), an automaton-based situational event detection algorithm, and a situational event-driven service coordination behavior model, which is based on an extended event-condition-action trigger mechanism. Moreover, we propose a reliable real-time data distribution model to support the effective dispatching sensory data between information providers and consumers, which is based on the grid quorum mechanism to organize those brokers into a grid overlay network to facilitate the asynchronous communication in a large-scale, distributed, and loosely coupled IoT applications environment. We also illustrate the various illustrations for IoT services coordination and alarming disposal process of coal mine safety monitoring and control automation scenarios, and also report the measurement and analysis of the platform's performance.

Summary With the development of Internet of Things (IoT), many middleware solutions have been proposed for the integration of physical world with the Web. However, most leading middleware solutions provide only limited resource matching and selection functionality. When significant amounts of resources are available, selecting the appropriate resources becomes challenging and time‐consuming. This paper addresses the growing issues of resource matching and selection in IoT solutions. In this paper, we propose a novel resource model to describe the IoT resources in a multidimensional manner. Based on the resource model, a resource matching algorithm that selects the well‐matched resources by matching the similarity between resources is proposed. Moreover, we constructed a combined resource set and used it and OWLS‐TC to evaluate our work comprehensively. Experimental results show that the proposed resource matching approach is more effective and efficient than existing approaches. Copyright © 2013 John Wiley & Sons, Ltd.

Community detection is one of the most important problems in social network analysis in the context of the structure of the underlying graphs. Many researchers have proposed their own methods for discovering dense regions in social networks. Such methods are only designed with links of the underlying social network. However, with the development of recent applications, rich edge content can be available to give another view to the community detection process. In this study, we focus on improving community detection with the edge content in social networks. In order to regulate the effect of both linkage structure and edge content, we propose two feature integration strategies. Experiment results illustrate that the presence of edge content provides unprecedented opportunities and flexibility for the community detection process.