Navigating complex urban environments using natural language instructions poses significant challenges for embodied agents, including noisy language instructions, ambiguous spatial references, diverse landmarks, and dynamic street scenes. Current visual navigation methods are typically limited to simulated or off-street environments, and often rely on precise goal formats, such as specific coordinates or images. This limits their effectiveness for autonomous agents like last-mile delivery robots navigating unfamiliar cities. To address these limitations, we introduce UrbanNav, a scalable framework that trains embodied agents to follow free-form language instructions in diverse urban settings. Leveraging web-scale city walking videos, we develop an scalable annotation pipeline that aligns human navigation trajectories with language instructions grounded in real-world landmarks. UrbanNav encompasses over 1,500 hours of navigation data and 3 million instruction-trajectory-landmark triplets, capturing a wide range of urban scenarios. Our model learns robust navigation policies to tackle complex urban scenarios, demonstrating superior spatial reasoning, robustness to noisy instructions, and generalization to unseen urban settings. Experimental results show that UrbanNav significantly outperforms existing methods, highlighting the potential of large-scale web video data to enable language-guided, real-world urban navigation for embodied agents.

In today's cloud networks, host servers widely deploy Data Processing Units (DPUs) as network accelerators under the "Sep-Path" paradigm. However, as server capabilities scale with increasing CPU cores and network bandwidth, the software slow path (executed on a DPU's CPU) has become a critical bottleneck for workloads with high new-flow rates. Meanwhile, new-flow setup logic on host servers must continuously evolve to meet diverse and changing customer demands, making flexibility a key requirement alongside performance. To address this gap, we present XFir, the first hardware-accelerated new-flow setup system for cloud host servers that delivers high CPS throughput while preserving sufficient flexibility. XFir leverages a next-generation DPU equipped with a Cloud Network co-Processor (CNP) to execute the host server's new-flow setup logic. XFir redesigns the host-server flow-setup datapath and table layout, optimizes LPM lookups, and introduces CPU-CNP collaboration mechanisms to further improve performance and reliability. Our evaluation shows that XFir achieves over 776K new-flow CPS on a single host server with 11.7μs slow-path latency. Compared to prior work (Fornax), XFir achieves 4.8x CPS and reduces latency by 69.2%. Moreover, XFir is cost-effective to deploy, requiring only a single DPU per host. Overall, XFir improves new-flow throughput while maintaining development flexibility at low financial cost.

Detecting 3D objects from surround-view images focuses on capturing the spatio-temporal positions of the surrounding environment, serving as a pivotal capability for vision-centric autonomous driving and robotics. While existing approaches primarily employ either dense BEV queries or sparse 3D queries, both paradigms have inherent limitations: dense queries suffer from redundant feature interactions and optimization conflicts, while sparse queries rely on high-quality initialization and struggle with error propagation in complex scenarios. To address these challenges, we proposeTAS-DAQ, a novel two-stage framework that synergizes dense and sparse query strategies. In Stage I, we generate geometry-aware coarse queries through the BEV feature providing robust initialization, thereby ensuring robust query initialization with explicit 3D priors. Stage II introduces a learnable Query Bank with temporal fusion to iteratively refine sparse queries by capturing discriminative instance features across views and frames. Moreover, considering the optimization conflicts caused by redundant query interactions in dense paradigms, we introduce adaptive query aggregation in the query bank that dynamically prioritizes high-confidence queries from BEV features, effectively addressing query error propagation while enhancing instance-level representation consistency. Extensive experiments on the nuScenes R50 benchmark demonstrate state-of-the-art performance, achieving56.9 % NDSand46.1% mAP.

With the rise of AI in education, knowledge tracing (KT) has become important for modeling students’ knowledge from interaction data. However, existing methods still face three major challenges, including limited modeling of personalized exercise–concept relations, low robustness to noisy interactions, and inefficient training due to suboptimal data selection. To address these issues, we propose R 2 GCurL, a novel KT framework with two key designs. First, we recast KT as a graph classification problem and construct dynamic graphs from student responses, enabling the model to capture structural relations between exercises and concepts for more personalized KT. Second, we introduce a data-centric curriculum learning strategy based on dynamic graph entropy. Under our definition, pairwise dynamic graph entropy measures graph-transition continuity, where larger values indicate stronger structural similarity. Its sequence-level aggregation is used to derive a structure-aware difficulty signal for sample scheduling. On top of this, an RL-based scheduler further adapts batch selection based on model feedback and is especially beneficial under noisier and more unstable training regimes. Theoretical analysis shows that R 2 GCurL has lower computational complexity than existing graph-based KT models. Extensive experiments on five real-world datasets confirm its effectiveness, robustness, and generalizability, including as a plug-and-play enhancement for sequence-based KT models.

The Multi-Agent Path Finding (MAPF) problem aims to determine the shortest and collision-free paths for multiple agents in a known, potentially obstacle-ridden environment. It is the core challenge for robotic deployments in large-scale logistics and transportation. Decentralized learningbased approaches have shown great potential for addressing the MAPF problems, offering more reactive and scalable solutions. However, existing learning-based MAPF methods usually rely on agents making decisions based on a limited field of view (FOV), resulting in short-sighted policies and inefficient cooperation in complex scenarios. There, a critical challenge is to achieve consensus on potential movements between agents based on limited observations and communications. To tackle this challenge, we introduce a new framework that applies sheaf theory to decentralized deep reinforcement learning, enabling agents to learn geometric cross-dependencies between each other through local consensus and utilize them for tightly cooperative decision-making. In particular, sheaf theory provides a mathematical proof of conditions for achieving global consensus through local observation. Inspired by this, we incorporate a neural network to approximately model the consensus in latent space based on sheaf theory and train it through self-supervised learning. During the task, in addition to normal features for MAPF as in previous works, each agent distributedly reasons about a learned consensus feature, leading to efficient cooperation on pathfinding and collision avoidance. As a result, our proposed method demonstrates significant improvements over state-of-the-art learning-based MAPF planners, especially in relatively large and complex scenarios, demonstrating its superiority over baselines in various simulations and real-world robot experiments.

The development and application of large language models (LLM) have demonstrated that foundational models can be utilized to solve a wide array of tasks. However, their performance in multi-agent path finding (MAPF) tasks has been less than satisfactory, with only a few studies exploring this area. MAPF is a complex problem requiring both planning and multi-agent coordination. To improve the performance of LLM in MAPF tasks, we propose a novel framework, LLM-NAR, which leverages neural algorithmic reasoners (NAR) to inform LLM for MAPF. LLM-NAR consists of three key components: an LLM for MAPF, a pre-trained graph neural network-based NAR, and a cross-attention mechanism. This is the first work to propose using a neural algorithmic reasoner to integrate GNNs with the map information for MAPF, thereby guiding LLM to achieve superior performance. LLM-NAR can be easily adapted to various LLM models. Both simulation and real-world experiments demonstrate that our method significantly outperforms existing LLM-based approaches in solving MAPF problems.

In robotic systems, the performance of reinforcement learning depends on the rationality of predefined reward functions. However, manually designed reward functions often lead to policy failures due to inaccuracies. Inverse Reinforcement Learning (IRL) addresses this problem by inferring implicit reward functions from expert demonstrations. Nevertheless, existing methods rely heavily on large amounts of expert demonstrations to accurately recover the reward function. The high cost of collecting expert demonstrations in robotic applications, particularly in multi-robot systems, severely hinders the practical deployment of IRL. Consequently, improving sample efficiency has emerged as a critical challenge in multi-agent inverse reinforcement learning (MIRL). Inspired by the symmetry inherent in multi-agent systems, this work theoretically demonstrates that leveraging symmetry enables the recovery of more accurate reward functions. Building upon this insight, we propose a universal framework that integrates symmetry into existing multi-agent adversarial IRL algorithms, thereby significantly enhancing sample efficiency. Experimental results from multiple challenging tasks have demonstrated the effectiveness of this framework. Further validation in physical multi-robot systems has shown the practicality of our method.

Goal assignment is a critical challenge in multi-robot systems. The emergence of large language models (LLMs) has enabled the use of natural language commands for tackling goal assignment problems. However, applying LLMs directly to these tasks presents two limitations: 1) limited accuracy and 2) excessive decision delays due to their autoregressive nature, hindering adaptability to unexpected changes. To address these issues, inspired by dual-process theory, we propose a framework called Collaborative LLMs for dynamic Goal Assignment (CLGA). Specifically, we leverage LLMs for pre-planning tasks and invoke an external solver to generate an initial goal assignment solution, ensuring solution accuracy. During execution, small-scale models enable real-time adjustments to respond to dynamic environmental changes. This approach integrates the strengths of slow, precise pre-planning and fast, adaptive online adjustments, allowing agents to efficiently handle real-world challenges. Additionally, we introduce a benchmark dataset for NLP-based goal assignment to advance research in this domain. Simulation and real-world experiments demonstrate that CLGA significantly enhances task execution efficiency and flexibility in multi-robot systems. The prompt, experimental videos, and datasets associated with this work are available at https://sites.google.com/view/project-clga/.

Embodied agents are expected to perform object navigation in dynamic, open-world environments. However, existing approaches typically rely on static trajectories and a fixed set of object categories during training, overlooking the real-world requirement for continual adaptation to evolving scenarios. To facilitate related studies, we introduce the continual object navigation benchmark, which requires agents to acquire navigation skills for new object categories while avoiding catastrophic forgetting of previously learned knowledge. To tackle this challenge, we propose C-Nav, a continual visual navigation framework that integrates two key innovations: (1) A dual-path anti-forgetting mechanism, which comprises feature distillation that aligns multi-modal inputs into a consistent representation space to ensure representation consistency, and feature replay that retains temporal features within the action decoder to ensure policy consistency. (2) An adaptive sampling strategy that selects diverse and informative experiences, thereby reducing redundancy and minimizing memory overhead. Extensive experiments across multiple model architectures demonstrate that C-Nav consistently outperforms existing approaches, achieving superior performance even compared to baselines with full trajectory retention, while significantly lowering memory requirements. The code will be publicly available at \url{https://bigtree765.github.io/C-Nav-project}.

EEG-based emotion recognition plays an important role in developing adaptive brain-computer communication systems, yet faces two fundamental challenges in practical implementations: (1) effective integration of non-stationary spatial-temporal neural patterns, (2) robust adaptation to dynamic emotional intensity variations in real-world scenarios. This paper proposes STT-CL, a novel framework integrating spatial-temporal transformers with curriculum learning. Our method introduces two core components: a spatial encoder that models inter-channel relationships and a temporal encoder that captures multi-scale dependencies through windowed attention mechanisms, enabling simultaneous extraction of spatial correlations and temporal dynamics from EEG signals. Complementing this architecture, an intensity-aware curriculum learning strategy progressively guides training from high-intensity to low-intensity emotional states through dynamic sample scheduling based on a dual difficulty assessment. Comprehensive experiments on three benchmark datasets demonstrate state-of-the-art performance across various emotional intensity levels, with ablation studies confirming the necessity of both architectural components and the curriculum learning mechanism.

ABSTRACT In the realm of software development, selecting the appropriate Java application programming interfaces (APIs) from a vast pool remains a significant challenge for developers. This research addresses this complexity by tackling the limitations of current API recommendation methods, which often struggle to align API suggestions with the specific queries and development contexts. In this paper, we introduce a novel prompt method named DSKIPP (Development Scenario, key Knowledge and Intention's Progressive Prompt), designed to enhance the efficiency of large language models (LLMs) in Java API recommendations. Firstly, we devise an overview of DSKIPP which conducts LLMs through a sequential process: first, inferring the package level, followed by the class level, and ultimately the method level as an API comprises three distinct components at varying levels—package, class and method. Secondly, at each level, DSKIPP assists LLMs in deducing the development scenario associated with a query and the essential key knowledge relevant to that scenario. This approach enables LLMs to gain a more profound contextual understanding of the query's intention. Moreover, during the inference process at the class and method level, we implement a self‐check mechanism enabling LLMs to validate the results and ensure a more reasoned and reliable outcome. To validate the efficiency of DSKIPP, comparison and ablation experiments are both conducted within Java programming environment. The comparison results affirm that our method outperforms the current state‐of‐the‐art technologies in API recommendation tasks, while the ablation results shed light on why DSKIPP can enhance the reliability of API recommendations in LLMs. This research contributes to the field by offering a more reliable and context‐sensitive solution for API recommendation in software development.

Multi-Agent Reinforcement Learning (MARL) has shown great potential in solving complex tasks. Despite great success, low training efficiency remains a pervasive and long-standing challenge in MARL. To tackle this issue, it is promising to leverage prior knowledge or environmental properties to inform and improve the MARL. We notice that many multi-agent tasks specify certain goal states where special rewards are granted, guiding agents to achieve the goal. Inspired by the theory of Lyapunov stability, an intuitive optimal policy to the tasks should be able to asymptotically converge to the goal states from any initial, making the goal states stable equilibria. Focusing on this type of tasks, we introduce the concept of Lyapunov Markov game (LMG), a new subclass of the cooperative Markov game, featuring a set of goal states and goal-oriented reward function. We then provide a theoretical bound on scaled value distance as a necessary condition to obtain a stable suboptimal policy in LMG. Motivated by this insight, we further propose the Lyapunov-informed MARL, which leverages a newly-designed Lyapunov-informed reward. Theoretical work is conducted to show that the Lyapunov-informed MARL enjoys a broadened bound, facilitating the training process to find a stable suboptimal policy more easily and then converge to an optimal policy more efficiently. Extensive experiments and real-world multi-robot implementations are conducted to show the superior performance of the proposed approach over advanced baseline models.

Sequential recommendation systems aim to predict the future behaviors of users based on their historical interactions. Despite the success of neural architectures like Transformer and Graph Neural Networks, these models often struggle with the inherent challenge of sparse data in accurately predicting future user behaviors. To alleviate the data sparsity problem, some methods leverage the contrastive learning to generate contrastive views, assuming the items appear discretely at the same time intervals and focusing on the sequence order. However, these approaches neglect the crucial temporal-aware collaborative patterns hidden within the user-item interactions, leading to a limited variety of contrastive pairs and less informative embeddings. The proposed framework,Temporal-awaregraph contrastive learning with theoretical guarantees for sequentialRecommendation (TagRec), integrates temporal-aware collaborative patterns with adaptive data augmentation to generate more informative user and item representations. TagRec employs a temporal-aware graph neural network to embed the original graph, then generates augmented graphs through the addition of interactions via latent user interest mining, the dropping of redundant interaction edges, and the perturbation of temporal information. Theoretical guarantees are provided that these augmentations enhance the graph’s utility. Extensive experiments on real-world datasets demonstrate the superiority of the proposed approach over the state-of-the-art recommendation methods.

Uncrewed aerial vehicle-mounted base stations (UAV-MBSs) provide flexible wireless connectivity, extending communication coverage in underserved areas. Recently, multi-agent reinforcement learning (MARL) has shown great potential for cooperative UAV swarm control to support efficient communication coverage in dynamic and complex environments. However, existing MARL-based methods often suffer from low sample efficiency due to its trial-and-error training characteristics, limiting its ability to control large UAV swarms with continuous state-action space and partial observation. We notice that UAV swarm systems in communication coverage tasks exhibit a spatial symmetry property, e.g., a rotation in the spatial observation of a UAV results in a same rotation in its optimal action. Exploiting this property, we formulate the task as a symmetric decentralized partially observable Markov decision process and introduce symmetry-informed MARL, featuring a novel network called the symmetry-informed graph neural network (SiGNN) to serve as the policy/value networks. SiGNN leverages the inherent symmetry in multi-UAV systems by embedding the symmetry into the network structure, thereby enhancing the training efficiency to handle large swarms with continuous control. Theoretical analysis shows that the SiGNN strictly preserves symmetry properties, which guarantees the effectiveness of the approach. Experiments in simulation were conducted to handle communication coverage using up to 20 UAVs with continuous control. Experimental results demonstrate that SiGNN-based MARL outperforms advanced baselines, verifying its superior sample efficiency, scalability and robustness.

Incorporating symmetry as an inductive bias into multi-agent reinforcement learning (MARL) has led to improvements in generalization, data efficiency, and physical consistency. While prior research has succeeded in using perfect symmetry prior, the realm of partial symmetry in the multi-agent domain remains unexplored. To fill in this gap, we introduce the partially symmetric Markov game, a new subclass of the Markov game. We then theoretically show that the performance error introduced by utilizing symmetry in MARL is bounded, implying that the symmetry prior can still be useful in MARL even in partial symmetry situations. Motivated by this insight, we propose the Partial Symmetry Exploitation (PSE) framework that is able to adaptively incorporate symmetry prior in MARL under different symmetry-breaking conditions. Specifically, by adaptively adjusting the exploitation of symmetry, our framework is able to achieve superior sample efficiency and overall performance of MARL algorithms. Extensive experiments are conducted to demonstrate the superior performance of the proposed framework over baselines. Finally, we implement the proposed framework in real-world multi-robot testbed to show its superiority.

LLM has achieved impressive performance on multi-modal tasks, which have received everincreasing research attention.Recent research focuses on improving prediction performance and reliability (e.g., addressing the hallucination problem).They often prepend relevant external knowledge to the input text as an extra prompt.However, these methods would be affected by the noise in the knowledge and the context length limitation of LLM.In our work, we focus on making better use of external knowledge and propose a method to actively extract valuable information in the knowledge to produce the latent vector as a soft prompt, which is then fused with the image embedding to form a knowledge-enhanced context to instruct LLM.The experimental results on knowledge-based VQA benchmarks show that the proposed method enjoys better utilization of external knowledge and helps the model achieve better performance.

Achieving high sample efficiency is a critical research area in reinforcement learning. This becomes extremely difficult in multi-agent reinforcement learning (MARL), as the capacity of the joint state and action space grows exponentially with the number of agents. The reliance of MARL solely on exploration and trial-and-error, without incorporating prior knowledge, exacerbates the issue of low sample efficiency. Currently, introducing symmetry into MARL is an effective approach to address this issue. Yet the concept of hierarchical symmetry, which maintains symmetry across different levels of a multi-agent system (MAS), has not been explored in existing methods. This paper focuses on multi-agent cooperative tasks and proposes a method incorporating hierarchical symmetry, termed the Hierarchical Equivariant Policy Network (HEPN) which is O(n)-equivariant. Specifically, HEPN utilizes clustering to perform hierarchical information extraction in MAS, and employs graph neural networks to model agent interactions. We conducted extensive experiments across various multi-agent tasks. The results indicate that our method achieves faster convergence speeds and higher convergence rewards compared to baseline algorithms. Additionally, we have deployed our algorithm in a physical multi-robot system, confirming its effectiveness in real-world environments. Supplementary materials are available at https://yongkai-tian.github.io/HEPN/.

Graph neural networks (GNNs) have shown ad-vantages in graph-based analysis tasks. However, most existing methods have the homogeneity assumption and show poor performance on heterophilic graphs, where the linked nodes have dissimilar features and different class labels, and the semantically related nodes might be multi-hop away. To address this limitation, this paper presents GraphRARE, a general framework built upon node relative entropy and deep reinforcement learning, to strengthen the expressive capability of GNNs. An innovative node relative entropy, which considers node features and structural similarity, is used to measure mutual information between node pairs. In addition, to avoid the sub-optimal solutions caused by mixing useful information and noises of remote nodes, a deep reinforcement learning-based algorithm is developed to optimize the graph topology. This algorithm selects informative nodes and discards noisy nodes based on the defined node relative en-tropy. Extensive experiments are conducted on seven real-world datasets. The experimental results demonstrate the superiority of GraphRARE in node classification and its capability to optimize the original graph topology.

Multi-agent reinforcement learning has emerged as a promising approach for the control of multi-robot systems. Nevertheless, the low sample efficiency of MARL poses a significant obstacle to its broader application in robotics. While data augmentation appears to be a straightforward solution for improving sample efficiency, it usually incurs training instability, making the sample efficiency worse. Moreover, manually choosing suitable augmentations for a variety of tasks is a tedious and time-consuming process. To mitigate these challenges, our research theoretically analyzes the implications of data augmentation on MARL algorithms. Guided by these insights, we present AdaptAUG, an adaptive framework designed to selectively identify beneficial data augmentations, thereby achieving superior sample efficiency and overall performance in multi-robot tasks. Extensive experiments in both simulated and real-world multi-robot scenarios validate the effectiveness of our proposed framework.

In multi-agent reinforcement learning (MARL), the Centralized Training with Decentralized Execution (CTDE) framework is pivotal but struggles due to a gap: global state guidance in training versus reliance on local observations in execution, lacking global signals. Inspired by human societal consensus mechanisms, we introduce the Hierarchical Consensus-based Multi-Agent Reinforcement Learning (HC-MARL) framework to address this limitation. HC-MARL employs contrastive learning to foster a global consensus among agents, enabling cooperative behavior without direct communication. This approach enables agents to form a global consensus from local observations, using it as an additional piece of information to guide collaborative actions during execution. To cater to the dynamic requirements of various tasks, consensus is divided into multiple layers, encompassing both short-term and long-term considerations. Short-term observations prompt the creation of an immediate, low-layer consensus, while long-term observations contribute to the formation of a strategic, high-layer consensus. This process is further refined through an adaptive attention mechanism that dynamically adjusts the influence of each consensus layer. This mechanism optimizes the balance between immediate reactions and strategic planning, tailoring it to the specific demands of the task at hand. Extensive experiments and real-world applications in multi-robot systems showcase our framework’s superior performance, marking significant advancements over baselines.

As microservices architectures become increasingly prevalent, they introduce significant operational challenges due to the complexities in service interactions and fault propagation. These architectures often conceal the origins of faults due to intricate inter-service communications, making fault localization both critical and challenging. Addressing these difficulties, this paper introduces a novel fault localization method that leverages synergies between domain prior knowledge, ensemble learning, and graph-based modeling. Our approach models microservices as a graph, with services as nodes and their interactions as edges, illuminating complex dependencies and enhancing the depth of data analysis. The method integrates expert knowledge with a unique blend of multi-class decision trees and strategy models derived from a knowledge base, enabling effective de-tection of diverse patterns and anomalies. Additionally, a meta-learner refines the outputs from base models using a weighted decision-making process, significantly improving the accuracy and robustness of fault detection. Compared to traditional models, including graph neural networks, our approach sub-stantially reduces model complexity and enhances adaptability to evolving service patterns. It demonstrates superior scalability and real-time processing capabilities, offering a robust solution to the challenges of fault localization in dynamic microservice environments.

Knowledge tracing models based on deep learning can achieve impressive predictive performance by leveraging attention mechanisms. However, there still exist two challenges in attentive knowledge tracing (AKT): First, the mechanism of classical models of AKT demonstrates relatively low attention when processing exercise sequences with shifting knowledge concepts (KC), making it difficult to capture the comprehensive state of knowledge across sequences. Second, classical models do not consider stochastic behaviors, which negatively affects models of AKT in terms of capturing anomalous knowledge states. This article proposes a model of AKT, called Enhancing Locality for Attentive Knowledge Tracing (ELAKT), that is a variant of the deep KT model. The proposed model leverages the encoder module of the transformer to aggregate knowledge embedding generated by both exercises and responses over all timesteps. In addition, it uses causal convolutions to aggregate and smooth the states of local knowledge. The ELAKT model uses the states of comprehensive KCs to introduce a prediction correction module to forecast the future responses of students to deal with noise caused by stochastic behaviors. The results of experiments demonstrated that the ELAKT model consistently outperforms state-of-the-art baseline KT models.

Modeling and predicting the performance of students in collaborative learning paradigms is an important task. Most of the research presented in literature regarding collaborative learning focuses on the discussion forums and social learning networks. There are only a few works that investigate how students interact with each other in team projects and how such interactions affect their academic performance. In order to bridge this gap, we choose a software engineering course as the study subject. The students who participate in a software engineering course are required to team up and complete a software project together. In this work, we construct an interaction graph based on the activities of students grouped in various teams. Based on this student interaction graph, we present an extended graph transformer framework for collaborative learning (CLGT) for evaluating and predicting the performance of students. Moreover, the proposed CLGT contains an interpretation module that explains the prediction results and visualizes the student interaction patterns. The experimental results confirm that the proposed CLGT outperforms the baseline models in terms of performing predictions based on the real-world datasets. Moreover, the proposed CLGT differentiates the students with poor performance in the collaborative learning paradigm and gives teachers early warnings, so that appropriate assistance can be provided.

Multi-agent reinforcement learning (MARL) has achieved promising results in recent years. However, most existing reinforcement learning methods require a large amount of data for model training. In addition, data-efficient reinforcement learning requires the construction of strong inductive biases, which are ignored in the current MARL approaches. Inspired by the symmetry phenomenon in multi-agent systems, this paper proposes a framework for exploiting prior knowledge by integrating data augmentation and a well-designed consistency loss into the existing MARL methods. In addition, the proposed framework is model-agnostic and can be applied to most of the current MARL algorithms. Experimental tests on multiple challenging tasks demonstrate the effectiveness of the proposed framework. Moreover, the proposed framework is applied to a physical multi-robot testbed to show its superiority.

Active learning can select informative data for model training to reduce the amount of labelling efforts required. Because traditional active learning methods cannot be directly used for deep learning, researchers have proposed multiple deep active learning methods. However, none of the previous research efforts on deep active learning algorithms presents a specific framework for learning-to-rank tasks. In this work, we introduce a novel deep active learning framework based on Deep Expected Loss Optimization (DELO) for the answer selection task.

API, namely application programming interface, can help developers implement their functions conveniently. To implement a function like dialing in Android, developers sometimes need to call many APIs organised in a special pattern, called API call sequence. However, existing methods rarely focus on code generation for API call sequence. In this paper, we introduce neural network into the application field of generating API call sequence code for Android. The purpose is realising Android code automatically generation by inputting function description. To reach this goal, we first design an API call sequence code graph which is named ACSCG to well represent the Android function code structure and then we convert the ACSCG to API call sequence. Besides, we devise an AI model based on Encoder-Decoder neural network to study the corresponding relation feature of function description and API call sequence. When finishing training the model, one can give a function description to it and generate corresponding API call sequence. After all above has been done, an algorithm is implemented to successfully convert the API call sequence into target code. To verify the efficiency of our method, we collect high quality code from Github and Gitee to build a dataset including 1000 items associated with essential functions in Android such as taking photo, file management, android browser and so on. The experiment shows that our model has a better performance in generating API call sequence code than state-of-the-art technologies.

Reinforcement learning for swarms of flying robots is a challenging task that requires a large number of data samples. Moreover, the problem of sim-to-real transfer has long been a challenge in robotics algorithm deployment. To address these issues, we propose Air-M, a platform that facilitates large-scale drone swarm learning in a distributed docker container environment and deployment in a virtual reality setting. Air-M trains the policy network using physics engines and creates replicas of agents in docker containers, which helps amortize the computational cost. In addition, Air-M establishes an intermediate link between the simulation and the real world, allowing real drones to interact with virtual objects via virtual sensors. This enables the policy network to be trained using virtual agents and seamlessly transferred to real drones. Air-Mis highly scalable, accommodating hundreds of agents with dynamic models and virtual sensors. We evaluate the effectiveness of our approach by conducting experiments in three representative virtual scenarios with an increasing number of agents. Our results demonstrate that our method outperforms the state-of- the-art in terms of training efficiency and transferability, making it a promising platform for swarm robotics applications.

Deep neural networks (DNNs) have achieved remarkable performance across a wide range of applications, while they are vulnerable to adversarial examples , which motivates the evaluation and benchmark of model robustness. However, current evaluations usually use simple metrics to study the performance of defenses, which are far from understanding the limitation and weaknesses of these defense methods. Thus, most proposed defenses are quickly shown to be attacked successfully, which results in the “arm race” phenomenon between attack and defense. To mitigate this problem, we establish a model robustness evaluation framework containing 23 comprehensive and rigorous metrics, which consider two key perspectives of adversarial learning (i.e., data and model). Through neuron coverage and data imperceptibility , we use data-oriented metrics to measure the integrity of test examples; by delving into model structure and behavior, we exploit model-oriented metrics to further evaluate robustness in the adversarial setting . To fully demonstrate the effectiveness of our framework, we conduct large-scale experiments on multiple datasets including CIFAR-10, SVHN, and ImageNet using different models and defenses with our open-source platform. Overall, our paper provides a comprehensive evaluation framework, where researchers could conduct comprehensive and fast evaluations using the open-source toolkit, and the analytical results could inspire deeper understanding and further improvement to the model robustness.

The rapid rise of microservice architecture poses severe challenges to workflow scheduling, resource allocation, and goal optimization. However, faults and failures usually happen during workflow running. To ensure the workflow's successful execution during scheduling microservices, this article proposes a dynamic workflow scheduling algorithm by integrating cognition cost and reliability QoS for using reinforcement learning (WS-CCR). First, we explore the ‘restart policy’ of containers in the Kubernetes architecture, which lays the foundation for our work that adopts the redundancy strategy to ensure workflow operation. Then we consider the cognitive cost based on the fact that users have a cognitive process for different microservices in selecting microservices. Additionally, another optimization goal is the reliability of workflows. On this basis, we design a reasonable reward function in reinforcement learning to generate dynamic strategies. Furthermore, following some generated strategies, our engine will schedule candidate microservices for tasks to execute step by step. A series of experiments on Alibaba and business areas workflows have proven the superior performance of our algorithm. Our WS-CCR can generate better Pareto solution sets than other baselines in terms of improving the reliability of running workflows. Finally, we give a case study to prove the practicability of our method.

Workflow scheduling for microservice has become an important and challenging research topic. To design a high-performance and reliable scheduling model, we propose a dependable workflow scheduling algorithm for microservice quality of service (QoS) based on deep-Q-Network, namely the DWSM. Firstly, we utilize the redundancy strategy based on the restart strategy of the Kubernetes container to optimize the dependability of workflow. Then this paper quantifies the dependability indicator and designs the reward function based on three QoS attributes including execution time, resources consumption and dependability to generate the scheduling strategy through DQN. Finally, we utilize a real-world data set to evaluate our algorithm and compare it with several state-of-art baselines including heterogeneous earliest-finish-time (HEFT), greedy algorithm and nondominated sorting genetic algorithm (NSGA-III). Experimental results show that our DWSM algorithm achieves higher performance in dependability and saves more CPU resources. In addition to simulation, we have implemented it on a workflow engine and deployed real workflow cases to test its effectiveness in practice.

Software developers need to take advantage of a variety of APIs (application programming interface) in their programs to implement specific functions. The problem of API misuses often arises when developers have incorrect understandings about the new APIs without carefully reading API documents. In order to avoid software defects caused by API misuse, researchers have explored multiple methods, including using AI(artificial intelligence) technology.As a kind of neural network in AI, Transformer has a good sequence processing ability, and the self attention mechanism used by Transformer can better catch the relation in a sequence or between different sequences. Besides it has a good model interpretability. From the perspective of combining API misuse detection with AI, this paper implements a standard Transformer model and a target-combination Transformer model to the learning of API usage information in a named API call sequence extracted from API usage program code. Then we present in the paper the way that our models use API usage information to detect if an API is misused in code. We use F1, precision and recall to evaluate the detection ability and show the advantages of our models in these three indexes. Besides, our models based on Transformer both have a better convergence. Finally, this paper explains why the models based on Transformer has a better performance by showing attention weight among different elements in code.

Given a question and a set of candidate answers, answer selection is the task of identifying the best answer, which can be viewed as a kind of learning-to-rank tasks. Learning to rank arises in many information retrieval applications, where deep learning models can achieve inspiring results. Training a deep learning model often requires large scale annotated data that are expensive and time-consuming to obtain. Active learning presents a promising approach to this problem by selecting more informative training data to reduce the amount of labelling efforts required. Because traditional active learning methods cannot be directly used for deep learning, researchers have proposed multiple deep active learning methods. However, none of the previous research efforts on deep active learning algorithms presents a specific framework for learning-to-rank tasks. In this work, we introduce a novel deep active learning framework based onDeepExpectedLossOptimization (DELO) for the answer selection task. It adopts a data acquisition function based on model uncertainty with Bayesian deep learning and the expected loss optimization. Moreover, a two-step batch-mode procedure, combining DELO and other data acquisition strategies is proposed to further improve the performance of active learning. Experimental results verify the effectiveness of the proposed framework.

Complex global behavior can emerge from local interactions in biological systems. Many models have been introduced to describe the interaction rules of biological individuals. Nonetheless, most research efforts cannot capture the inner cognitive and sequential decision process of individual animals in their swarms. In this paper, we formulate this problem as homogeneous Markov game and focus on identifying the potential reward function of individual animals so as to understand their collective behaviors. We propose an inverse reinforcement learning method PS-AIRL specifically for biological systems, where the parameter sharing paradigm is combined with a deep inverse reinforcement learning. Theoretical analysis and experimental evaluation show that PS-AIRL can learn the policy and the reward function from collective behavior demonstrations. Moreover, our methods can be applied to a wide range of biological behavioral studies.

Tagging is well regarded as one of the best ways of managing web services, in which keywords are assigned by users to describe the published services. As users are required to select multiple tags from a large set of candidate tags based on their own understanding, such user-attached tags are not always reliable and may affect the efficiency of service discovery. To alleviate the issue, tag prediction can suggest users appropriate tags for web services based on the textual descriptions of their functionality. Therefore, it is necessary to design tag prediction methods to support service search and recommendation. In this work, we propose a tag prediction model that adopts BERT-based label-wise attention mechanism, and use adversarial training to further improve the model performance. Experimental results on the service datasets collected from ProgrammableWeb show that the proposed method can achieve better prediction performance than other state-of-art methods.

As Augmented Reality television gains momentum, it is important to understand whether cultural differences among viewers favor different expectations and preferences for immersion in such new television environments. A previous study documented the preferences of 172 participants from various European countries for twenty application scenarios for ARTV, such as virtual objects coming out of the TV screen into the room. In this work, we conduct an empirical generalization of this previous study to understand potential cultural differences in users’ preferences for and expectations of ARTV. To this end, we report insights from data collected from a sample of 147 participants from China, which we compare against the preferences expressed by the participants from Europe from the original study. Our findings reveal similarities, but also differences in terms of expectations of ARTV across the two cultural groups. We draw implications for future research on culturally-aware augmentations of the television watching experience.

Reinforcement Learning, a common framework for AI planing or decision making, is regarded as an effective framework fro planning students' learning sequences. However, previous research efforts rely on simulation data or students and few of them have verified effectiveness of their algorithms with teaching students in real educational environments. Also, the previous research is hard to using in real task such as online course or real classroom because of the strong assumptions and restrictions. In this paper, We propose a new deep reinforcement learning framework for instructional sequencing that can recommend students with personalized learning exercises in both MOOCs and classrooms. Based on our ATC model, is used to trace students learning process and Deep Reinforcement Learning Agent is used to induce efficient l earning sequences for students adaptively. Both simulation and experiment in classrooms confirm the effectiveness of our method.

Answer Selection is an important subtask of Question Answering tasks. For this learning-to-rank problem, deep learning methods have outperformed traditional methods. To train a high-quality deep answer selection model, it often requires large amounts of labeled data, which is a costly and noise-prone process. Active learning and semi-supervised learning are usually applied in the modelling training procedure to achieve optimal accuracy with fewer labeled training samples. However, traditional active learning methods rely on good uncertainty estimates that are hard to obtain with standard neural networks. And the performance of semi-supervised learning methods are always affected adversely by the quality of the pseudo-labeled data. In this work, we propose a new framework integrating active learning and self-paced learning in training deep answer selection models. This framework proposes an uncertainty quantification method based on Bayesian neural network, which can guide active learning and self-paced learning in the same iterative process of model training. Experiments were conducted on two kinds of deep answer selection models with real-world datasets including YahooCQA and SemiEvalCQA. The results reveal that the proposed method can significantly reduce the labeled samples for model training.

Presents the introductory welcome message from the conference proceedings. May include the conference officers' congratulations to all involved with the conference event and publication of the proceedings record.

In the field of microservice, accurate indicator prediction is very important, which is helpful for service monitoring and anomaly detection. In many cases, it is difficult to accurately predict by the indicator itself, and other related indicators need to be imported to help predict. In traditional multi-indicator predicting, the related indicators are known or the amount is small, which is relatively easy to obtain. But there are many service indicators and the relationship between the indicators is constantly changing, so new methods need to be used to quickly and accurately find the related indicators in the mass of indicators. We combine Granger causality test and Attention LSTM time series prediction model to quickly find related indicators in microservice scenarios and participate in prediction. The experimental results show that our method can effectively improve the accuracy of indicator prediction.

In order to complete design and modeling of workflow more effectively, enterprises urgently need efficient workflow recommendation technology. At present, traditional recommendation algorithms based on process structure are widely used, yet tedious modeling operations and poor recommendation accuracy are noteworthy issues. To address the above problems, based on complex workflow relationships, we utilize graph embedding in workflow recommendation to provide convenience for business process operators. In this paper, we propose a Workflow Embedding Recommendation(namely WFER) method, which can deal with the adjacency matrix of complex process to obtain more detailed feature representation, so as to calculate the similarity accurately. Therefore, we implement efficient recommendation based on workflow semantics. Moreover, this recommendation tool is suitable for both transactional workflows and scientific workflows. Finally, based on real datasets and generated datasets, we carry out experiments to compare our method with other traditional algorithms and experimental results show its effectiveness and efficiency in practice.

We present SAPIENS, a software architecture designed to support engineering of interactive systems featuring peripheral interaction in the context of smart environments. SAPIENS introduces dedicated components for user and device tracking, attention detection, priority management for devices, tasks, and notifications, context-awareness inference, user interruptibility prediction, and device interchangeability that can be instantiated at will according to the needs of the application. To implement these components effectively, SAPIENS employs event-based processing by reusing the core engine of a recently introduced software architecture, Euphoria (Schipor et al., 2019), that was specifically designed for engineering interactions in smart environments with heterogeneous I/O devices, and relies entirely on web standards, protocols, and open data-interchange formats, such as JavaScript, WebSockets, HTTP, and JSON. This inheritance makes SAPIENS flexible and adaptable to support implementation of diverse application scenarios for peripheral interaction and for a wide variety of smart environments, devices, platforms, data formats, and contexts of use. We present our design criteria for SAPIENS regarding (1) event handling techniques, (2) quality, (3) contextual, and (4) attention-related properties, and describe its components and dataflows that make SAPIENS a specialized software architecture for peripheral interaction scenarios. We also demonstrate SAPIENS with a practical application, inspired and adapted from Bakker's (2013) classical example for peripheral interaction, for which we provide an online simulation tool that researchers and practitioners can readily use to consult actual JavaScript code implementing the inner logic of selected components of our architecture as well as to observe live JSON messages exchanged by the various components of SAPIENS.

With the advent of Massive Online Open Courses (MOOCs), the data scale of student learning behavior and knowledge mastery has significantly increased. In order to effectively and efficiently analyze these datasets and present on-the-fly intelligent tutoring to online learners, it is necessary to improve existing learning analytics tools in a parallel and automatic way. One of the most common tools is Bayesian Knowledge Tracing (BKT) that can model temporal progress of online learners and evaluate their mastery of course knowledge. Current implementation of BKT is mostly based on single machine, which leads to slow execution performance during its Expectation Maximization(EM) algorithm for parameter fitting. Although there are a few parallel implementations for EM algorithm, they don't support automatic initial BKT parameter tuning to ensure the correct convergence of the EM iteration. Therefore, this paper presents a new parallel BKT open source tool based on the Spark computational framework with the method of automatic tuning of initial parameters. This tool improves traditional knowledge tracing systems using a parallel EM algorithm with the capabilty of automatically choosing initial parameters. Experimental result demonstrates that our tool can achieve fast execution speed and greatly improve the accuracy of training parameters on both different sizes of simulated data and real educational data sets.

A large amount of data generated by students in online education can be used to improve the quality of education. The important task of online education is to estimate the student proficiency and the characteristics of educational components. We developed the T-BMIRT model: a temporal, multidimensional, IRT-based method for estimating the above parameters. The model added learning video parameters and modeled the student proficiencies over time as a random process, accounting for the student learning and forgetting process. And it was extended to multidimensional to estimate the educational components which contain multiple skills. So the model can describe the student learning trajectories in an online education system. In addition, we evaluated this model by predicting student next response to assessment, and found it is better than the IRT and temporal IRT models on each dataset we used, especially when the dataset contains learning videos interactions.

Knowledge Tracing (KT) is a standard model for inferring student knowledge mastery from their performance data. Generally, there are five parameters in KT model we need to estimate, they are transition parameters: learning and forgetting probability, emission parameters: guessing and slipping probability, and prior probability. KT model is widely used in students learning outcome modeling. However, it does not support multiple subskills modeling, for the model works by checking the historical observations at a specific skill. To overcome this drawback, this paper proposes three models using logistic regression over each step: KTLR-GS, extending guessing and slipping parameters; KTLR-LFID, introducing item difficult into the KT model while extending learning and forgetting parameters; KTLR-FP, extending both transition and emission parameters. Unlike previous methods our models discuss the efficiency of extending transition and emission parameters while relaxing the assumptions that subskills are independent. In the end we evaluate how well our models perform with comparison to LR-DBN, KT-IDEM and KT on two datasets: the open dataset ASSISTments, and one private dataset, student algebra dataset collected through our tutoring system. Our models outperform LR-DBN, KT-IDEM and KT on both datasets.

The Internet based cyber-physical world has profoundly changed the information environment for the development of artificial intelligence (AI), bringing a new wave of AI research and promoting it into the new era of AI 2.0. As one of the most prominent characteristics of research in AI 2.0 era, crowd intelligence has attracted much attention from both industry and research communities. Specifically, crowd intelligence provides a novel problem-solving paradigm through gathering the intelligence of crowds to address challenges. In particular, due to the rapid development of the sharing economy, crowd intelligence not only becomes a new approach to solving scientific challenges, but has also been integrated into all kinds of application scenarios in daily life, e.g., online-to-offline (O2O) application, real-time traffic monitoring, and logistics management. In this paper, we survey existing studies of crowd intelligence. First, we describe the concept of crowd intelligence, and explain its relationship to the existing related concepts, e.g., crowdsourcing and human computation. Then, we introduce four categories of representative crowd intelligence platforms. We summarize three core research problems and the state-of-the-art techniques of crowd intelligence. Finally, we discuss promising future research directions of crowd intelligence.

Recently, crowdsourcing platforms have attracted a number of citizens to perform a variety of location-specific tasks. However, most existing approaches consider the arrangement of a set of tasks for a set of crowd workers, while few consider crowd workers arriving in a dynamic manner. Therefore, how to arrange suitable location-specific tasks to a set of crowd workers such that the crowd workers obtain maximum satisfaction when arriving sequentially represents a challenge. To address the limitation of existing approaches, we first identify a more general and useful model that considers not only the arrangement of a set of tasks to a set of crowd workers, but also all the dynamic arrivals of all crowd workers. Then, we present an effective crowd-task model which is applied to offline and online settings, respectively. To solve the problem in an offline setting, we first observe the characteristics of task planning (CTP) and devise a CTP algorithm to solve the problem. We also propose an effective greedy method and integrated simulated annealing (ISA) techniques to improve the algorithm performance. To solve the problem in an online setting, we develop a greedy algorithm for task planning. Finally, we verify the effectiveness and efficiency of the proposed solutions through extensive experiments using real and synthetic datasets.

Adaptive video streaming is very important for delivering high-quality video content of MOOCs (Massive Online Open Courses) to online learners because they often have Internet connections with different levels of bandwidth. Although DASH (Dynamic adaptive streaming over HTTP) is widely accepted as a viable streaming technology to implement scalable Internet streaming using HTTP transport, few research efforts have been made to investigate how to apply this relatively new technology on improving the quality of experience (QoE) of MOOC video streaming. This paper proposes a DASH scheme for MOOC video streaming (MOOC-DASH) to improve QoE of DASH-based MOOC. This scheme consists of content-aware ROI-based video encoding for MOOCs video and bitrate selection algorithm to provide a high-quality and smooth video streaming service to online learners. Experimental results demonstrate that it can effectively reduce the bandwidth of the video content and improve QoE of MOOC Streaming.

Massive amount scientific data often need to be visualized in ultra-large images for scientific discovery. Although ultra-high resolution tiled-display environments have been widely used, there still lacks of proper image viewers that can display ultra-large images with billions of pixels in tiled-display environments. To address the problem, we propose Magic View, an optimized ultra-large scientific image viewer for SAGE tiled-display environment. It can achieve real-time interactive performance in viewing images with billions of pixels. Our experiments show that the performance of Magic View are at lease 8x better than Juxta View, another ultra-large image viewer for SAGE.

This paper proposes key SaaS (Software-as-a-Service) design strategies for those SaaS systems that run on top of a commercial PaaS (Platform-as-a-Service) system such as GAE (Google App Engine)[1]. Specifically, this paper proposes a model-based approach for customization, multi-tenancy architecture, scalability, and redundancy & recovery techniques for GAE. The ACDATER (Actors, Conditions, Data, Actions, Timing, Events, and Relationship) model is used for various features, and then automated code generation is used to generate code based on the model specified. Simulation can be performed to ensure correctness before deployment.

Satellite data products derived from the remote sensing observations describe features of the land, ocean and atmosphere. And by data processing, they can be used to study processes and trends on local/global scale for real-time environmental research and applications. However, the advances of cutting-edge remote sensing technology bring the challenge of data deluge for satellite data analysis and interpretation. With combinations of human intelligence and machine intelligence, we develop a satellite data portal for crowdsourcing data analysis and interpretation through teaching and learning to cope with the overwhelming data deluge. Compared with all the existing data portals and crowdsourcing systems, it is the first attempt to embed crowdsourcing into a data portal to provide integrated services of satellite data access and analysis.

In an e-Science data infrastructure, access control is a vital component to facilitate the management of the collective data and computing resources shared by researchers from geographically distributed locations. But conventional virtual organization based access control frameworks are not suitable for self-organizing, ad-hoc and opportunistic scientific collaborations, in which scientists can easily set up group-oriented authorization rules across the administrative domains. Using the emerging OAuth2.0 protocol, this paper introduces a novel Open Social based access control framework to support ad-hoc team formation and user-controlled resource sharing. Our experiences with development of the framework in e-Science data infrastructure projects demonstrate that the proposed framework is a very promising approach to resource sharing in cross-domain e-science environments.

In video conference system, the multimedia gateway plays an important role in forwarding audio and video data, whose performance is a bottleneck of the system. A flexible framework of cloud-based video conference multi-gateway system is proposed to meet the needs of a high-definition video conference system, which can control a variety of virtual gateway resources based on physical devices, thus multimedia gateways can be deployed dynamically. In addition, a real-time user migration strategy is designed and implemented based on the framework, which combines active pattern with passive pattern. The experiments show that the user migration strategy could control the time delay of user migration under 65 milliseconds, ensure the continuity of audio and video data during user migration, and successfully solve the reliability problems caused by system shutdown or overload of the multimedia gateway.

In data-driven science projects, researchers distributed in different institutions often wish to easily team up for data and computing resource sharing to address challenging scientific problems. Typical VO based authorization schemes is not suitable for such a user organized scientific collaboration. Using the emerging OAuthprotocol, we introduce a novel group authorization scheme to support ad-hoc team formation and user controlled resource sharing. Integrating this group authorization scheme, we define an Open Social based scientific collaboration framework and develop a science gateway prototype named as Open Life Science Gateway (OLSGW) to verify and refine the framework. Our experience with development of the OLSGW shows that OAuth 2.0 based group authorization scheme is avery promising approach to resource sharing in Cloud environments, and the Open Social based framework can facilitate science gateway developers to create domain-specific collaborative applications in a very flexible way.

Cloud computing is increasingly becoming a popular solution to massive data analysis in life science community. To completely harness the power of Cloud computing, scientists need science gateways to efficiently manage their virtual machines, share Cloud resources, and run high-throughput sequence analysis with bioinformatics software tools. This paper introduces the development and use of Open Life Science Gateway, which manages computational jobs on top of Hadoop streaming, and supports user-customized runtime environment with virtual machine images. Moreover, it facilitates researchers to team up on solving challenging computing problems by sharing Cloud based data sources and software tools. This gateway has been used for investigating better B-cell epitope prediction.

Real-time video communication such as Internet video conferencing is often afflicted by packet loss over the network. To improve the quality of video, error protection schemes have been introduced based on FMO in H.264 whose encoding efficiency is unacceptable. This paper presents a novel region of interest (ROI) protection scheme that can accurately extract ROI area using facial recognition and greatly speedup video encoding based on feedback using x264 codec implementation. In this scheme, the video receiver uses a packet loss prediction model to predict whether to send feedback to the video sender that dynamically adjust the ROI protecting scheme. Experiments prove that the quality of the ROI area can be effectively improved by the scheme whose encoding performance increases by 50 times compared with FMO based algorithms.

BACKGROUND: Target specific antibodies are pivotal for the design of vaccines, immunodiagnostic tests, studies on proteomics for cancer biomarker discovery, identification of protein-DNA and other interactions, and small and large biochemical assays. Therefore, it is important to understand the properties of protein sequences that are important for antigenicity and to identify small peptide epitopes and large regions in the linear sequence of the proteins whose utilization result in specific antibodies. RESULTS: Our analysis using protein properties suggested that sequence composition combined with evolutionary information and predicted secondary structure, as well as solvent accessibility is sufficient to predict successful peptide epitopes. The antigenicity and the specificity in immune response were also found to depend on the epitope length. We trained the B-Cell Epitope Oracle (BEOracle), a support vector machine (SVM) classifier, for the identification of continuous B-Cell epitopes with these protein properties as learning features. The BEOracle achieved an F1-measure of 81.37% on a large validation set. The BEOracle classifier outperformed the classical methods based on propensity and sophisticated methods like BCPred and Bepipred for B-Cell epitope prediction. The BEOracle classifier also identified peptides for the ChIP-grade antibodies from the modENCODE/ENCODE projects with 96.88% accuracy. High BEOracle score for peptides showed some correlation with the antibody intensity on Immunofluorescence studies done on fly embryos. Finally, a second SVM classifier, the B-Cell Region Oracle (BROracle) was trained with the BEOracle scores as features to predict the performance of antibodies generated with large protein regions with high accuracy. The BROracle classifier achieved accuracies of 75.26-63.88% on a validation set with immunofluorescence, immunohistochemistry, protein arrays and western blot results from Protein Atlas database. CONCLUSIONS: Together our results suggest that antigenicity is a local property of the protein sequences and that protein sequence properties of composition, secondary structure, solvent accessibility and evolutionary conservation are the determinants of antigenicity and specificity in immune response. Moreover, specificity in immune response could also be accurately predicted for large protein regions without the knowledge of the protein tertiary structure or the presence of discontinuous epitopes. The dataset prepared in this work and the classifier models are available for download at https://sites.google.com/site/oracleclassifiers/.

A significant obstacle to building usable, web-based interfaces for computational science in a Grid environment is how to deploy scientific applications on computational resources and expose these applications as web services. To streamline the development of these interfaces, we propose a new application framework that can deliver user-defined scientific workflows as both web services and OpenSocial gadgets. Through this application framework, scientists can focus on defining computational workflows using domain-specific applications and can use the software tools in the framework to quickly generate gadgets for running the applications and visualizing the output from workflow executions. By assembling these domain-specific gadgets and some common gadgets predefined in the framework for workflow management, scientists can easily set up a customized computational workspace to meet their requirements.

Problem solving environments (PSEs) are increasingly important for scientific discovery. Today's most challenging problems often require multi-disciplinary teams, the ability to analyze very large amounts of data, and the need to rely on infrastructure built by others rather than reinventing solutions for each science team. The TeraGrid Science Gateways program recognizes these challenges and works with science teams to harness high-end resources that significantly extend a PSE's functionality.

Abstract We discuss our message‐based approach to managing real‐time data streams and building higher level services to produce and consume them. Our messaging system acts as a substrate that can be used to provide qualities of service to various streaming applications ranging from audio–video collaboration systems to sensor Grids. The messaging substrates are composed of distributed, hierarchically arranged message broker networks. Services such as filters are deployed along the edges of the network. We discuss the role of management systems for both broker networks and filter services: broker network topologies must be created and maintained, and distributed filters must be arranged in appropriate sequences. These managed broker networks may be applied to a wide range of problems. We discuss applications to audio–video collaboration in some detail and also describe applications to streaming Global Positioning System data streams. These provide specific application filters that can transform and republish message streams to the broker system. Copyright © 2006 John Wiley & Sons, Ltd.

We study the current architecture of the grid and Web services and that of the global information grid (GiG) with the Network Centric Operations and Warfare (NCOW) from the Department of Defense. We compare the GiG core enterprise services with those being developed for Grids (the open grid services architecture) and Web Services (so called WS-* specifications), identifying both similarities and differences. We discuss both modeling and simulation with HLA (high level architecture) and broad defense NCOW applications. We illustrate this analysis with an open geospatial community (OGC) compatible set of geographical information system grid services. We illustrate the use of grids to efficiently support realtime simulation by an application of grids to audio-video conferencing.

We designed eSports - a collaborative and synchronous video annotation platform, which is to be used in Internet scale cross-platform grid computing environment to facilitate computer supported cooperative work (CSCW) in education settings such as distance sport coaching, distance classroom etc. Different from traditional multimedia annotation systems, eSports provides the capabilities to collaboratively and synchronously play and archive real time live video, to take snapshots, to annotate video snapshots using whiteboard and to play back the video annotations synchronized with original video streams. eSports is designed based on the grid based collaboration paradigm $the shared event model using NaradaBrokering, which is a publish/subscribe based distributed message passing and event notification system. In addition to elaborate the design and implementation of eSports, we analyze the potential use cases of eSports under different education settings. We believed that eSports is very useful to improve the online collaborative coaching and education.

Abstract In order to build an integrated collaboration system over heterogeneous collaboration technologies, we propose a global multimedia collaboration system (Global‐MMCS) based on XGSP A/V Web‐Services framework. This system can integrate multiple A/V services, and support various collaboration clients and communities. Now the prototype is being developed and deployed across many universities in U.S.A. and China. Copyright © 2004 John Wiley & Sons, Ltd.